1073 files changed, 75638 insertions, 36024 deletions

diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index 4725a8cfd695..ecdea58e6a21 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -859,7 +859,7 @@ static int corkscrew_open(struct net_device *dev)
 static void corkscrew_timer(struct timer_list *t)
 {
 #ifdef AUTOMEDIA
-	struct corkscrew_private *vp = from_timer(vp, t, timer);
+	struct corkscrew_private *vp = timer_container_of(vp, t, timer);
 	struct net_device *dev = vp->our_dev;
 	int ioaddr = dev->base_addr;
 	unsigned long flags;
@@ -1414,7 +1414,7 @@ static int corkscrew_close(struct net_device *dev)
 			dev->name, rx_nocopy, rx_copy, queued_packet);
 	}
 
-	del_timer_sync(&vp->timer);
+	timer_delete_sync(&vp->timer);
 
 	/* Turn off statistics ASAP.  We update lp->stats below. */
 	outw(StatsDisable, ioaddr + EL3_CMD);
diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c
index dc3b7c960611..1f2070497a75 100644
--- a/drivers/net/ethernet/3com/3c574_cs.c
+++ b/drivers/net/ethernet/3com/3c574_cs.c
@@ -858,7 +858,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id)
 */
 static void media_check(struct timer_list *t)
 {
-	struct el3_private *lp = from_timer(lp, t, media);
+	struct el3_private *lp = timer_container_of(lp, t, media);
 	struct net_device *dev = lp->p_dev->priv;
 	unsigned int ioaddr = dev->base_addr;
 	unsigned long flags;
@@ -1140,7 +1140,7 @@ static int el3_close(struct net_device *dev)
 
 	link->open--;
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->media);
+	timer_delete_sync(&lp->media);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c
index be58dac0502a..ea49be43b8c3 100644
--- a/drivers/net/ethernet/3com/3c589_cs.c
+++ b/drivers/net/ethernet/3com/3c589_cs.c
@@ -685,7 +685,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id)
 
 static void media_check(struct timer_list *t)
 {
-	struct el3_private *lp = from_timer(lp, t, media);
+	struct el3_private *lp = timer_container_of(lp, t, media);
 	struct net_device *dev = lp->p_dev->priv;
 	unsigned int ioaddr = dev->base_addr;
 	u16 media, errs;
@@ -946,7 +946,7 @@ static int el3_close(struct net_device *dev)
 
 	link->open--;
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->media);
+	timer_delete_sync(&lp->media);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 790270912913..8c9cc97efd4e 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1783,7 +1783,7 @@ out:
 static void
 vortex_timer(struct timer_list *t)
 {
-	struct vortex_private *vp = from_timer(vp, t, timer);
+	struct vortex_private *vp = timer_container_of(vp, t, timer);
 	struct net_device *dev = vp->mii.dev;
 	void __iomem *ioaddr = vp->ioaddr;
 	int next_tick = 60*HZ;
@@ -2691,7 +2691,7 @@ vortex_down(struct net_device *dev, int final_down)
 	netdev_reset_queue(dev);
 	netif_stop_queue(dev);
 
-	del_timer_sync(&vp->timer);
+	timer_delete_sync(&vp->timer);
 
 	/* Turn off statistics ASAP.  We update dev->stats below. */
 	iowrite16(StatsDisable, ioaddr + EL3_CMD);
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index fea489af72fb..7c8213011b5c 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -504,7 +504,7 @@ static int axnet_close(struct net_device *dev)
     
     link->open--;
     netif_stop_queue(dev);
-    del_timer_sync(&info->watchdog);
+    timer_delete_sync(&info->watchdog);
 
     return 0;
 } /* axnet_close */
@@ -550,7 +550,7 @@ static irqreturn_t ei_irq_wrapper(int irq, void *dev_id)
 
 static void ei_watchdog(struct timer_list *t)
 {
-    struct axnet_dev *info = from_timer(info, t, watchdog);
+    struct axnet_dev *info = timer_container_of(info, t, watchdog);
     struct net_device *dev = info->p_dev->priv;
     unsigned int nic_base = dev->base_addr;
     unsigned int mii_addr = nic_base + AXNET_MII_EEP;
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 780fb4afb6af..19f9c5db3f3b 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -947,7 +947,7 @@ static int pcnet_close(struct net_device *dev)
 
     link->open--;
     netif_stop_queue(dev);
-    del_timer_sync(&info->watchdog);
+    timer_delete_sync(&info->watchdog);
 
     return 0;
 } /* pcnet_close */
@@ -1018,7 +1018,7 @@ static irqreturn_t ei_irq_wrapper(int irq, void *dev_id)
 
 static void ei_watchdog(struct timer_list *t)
 {
-    struct pcnet_dev *info = from_timer(info, t, watchdog);
+    struct pcnet_dev *info = timer_container_of(info, t, watchdog);
     struct net_device *dev = info->p_dev->priv;
     unsigned int nic_base = dev->base_addr;
     unsigned int mii_addr = nic_base + DLINK_GPIO;
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 9a542e3c9b05..f86d4557d8d7 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -20,6 +20,7 @@ source "drivers/net/ethernet/actions/Kconfig"
 source "drivers/net/ethernet/adaptec/Kconfig"
 source "drivers/net/ethernet/aeroflex/Kconfig"
 source "drivers/net/ethernet/agere/Kconfig"
+source "drivers/net/ethernet/airoha/Kconfig"
 source "drivers/net/ethernet/alacritech/Kconfig"
 source "drivers/net/ethernet/allwinner/Kconfig"
 source "drivers/net/ethernet/alteon/Kconfig"
@@ -159,7 +160,7 @@ config ETHOC
 	  Say Y here if you want to use the OpenCores 10/100 Mbps Ethernet MAC.
 
 config OA_TC6
-	tristate "OPEN Alliance TC6 10BASE-T1x MAC-PHY support"
+	tristate "OPEN Alliance TC6 10BASE-T1x MAC-PHY support" if COMPILE_TEST
 	depends on SPI
 	select PHYLIB
 	help
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 99fa180dedb8..67182339469a 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_NET_VENDOR_ADAPTEC) += adaptec/
 obj-$(CONFIG_GRETH) += aeroflex/
 obj-$(CONFIG_NET_VENDOR_ADI) += adi/
 obj-$(CONFIG_NET_VENDOR_AGERE) += agere/
+obj-$(CONFIG_NET_VENDOR_AIROHA) += airoha/
 obj-$(CONFIG_NET_VENDOR_ALACRITECH) += alacritech/
 obj-$(CONFIG_NET_VENDOR_ALLWINNER) += allwinner/
 obj-$(CONFIG_NET_VENDOR_ALTEON) += alteon/
diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c
index 115f48b3342c..0a08da799255 100644
--- a/drivers/net/ethernet/actions/owl-emac.c
+++ b/drivers/net/ethernet/actions/owl-emac.c
@@ -1325,15 +1325,10 @@ static int owl_emac_mdio_init(struct net_device *netdev)
 	struct device_node *mdio_node;
 	int ret;
 
-	mdio_node = of_get_child_by_name(dev->of_node, "mdio");
+	mdio_node = of_get_available_child_by_name(dev->of_node, "mdio");
 	if (!mdio_node)
 		return -ENODEV;
 
-	if (!of_device_is_available(mdio_node)) {
-		ret = -ENODEV;
-		goto err_put_node;
-	}
-
 	priv->mii = devm_mdiobus_alloc(dev);
 	if (!priv->mii) {
 		ret = -ENOMEM;
diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index 68fad5575fd4..30f9d271e595 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -1599,7 +1599,7 @@ static int adin1110_probe_netdevs(struct adin1110_priv *priv)
 		netdev->netdev_ops = &adin1110_netdev_ops;
 		netdev->ethtool_ops = &adin1110_ethtool_ops;
 		netdev->priv_flags |= IFF_UNICAST_FLT;
-		netdev->netns_local = true;
+		netdev->netns_immutable = true;
 
 		port_priv->phydev = get_phy_device(priv->mii_bus, i + 1, false);
 		if (IS_ERR(port_priv->phydev)) {
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index b325e0cef120..678eddb36172 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3076,7 +3076,8 @@ err_out:
  */
 static void et131x_error_timer_handler(struct timer_list *t)
 {
-	struct et131x_adapter *adapter = from_timer(adapter, t, error_timer);
+	struct et131x_adapter *adapter = timer_container_of(adapter, t,
+							    error_timer);
 	struct phy_device *phydev = adapter->netdev->phydev;
 
 	if (et1310_in_phy_coma(adapter)) {
@@ -3639,7 +3640,7 @@ static int et131x_close(struct net_device *netdev)
 	free_irq(adapter->pdev->irq, netdev);
 
 	/* Stop the error timer */
-	return del_timer_sync(&adapter->error_timer);
+	return timer_delete_sync(&adapter->error_timer);
 }
 
 /* et131x_set_packet_filter - Configures the Rx Packet filtering */
diff --git a/drivers/net/ethernet/airoha/Kconfig b/drivers/net/ethernet/airoha/Kconfig
new file mode 100644
index 000000000000..ad3ce501e7a5
--- /dev/null
+++ b/drivers/net/ethernet/airoha/Kconfig
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config NET_VENDOR_AIROHA
+	bool "Airoha devices"
+	depends on ARCH_AIROHA || COMPILE_TEST
+	help
+	  If you have a Airoha SoC with ethernet, say Y.
+
+if NET_VENDOR_AIROHA
+
+config NET_AIROHA_NPU
+	tristate "Airoha NPU support"
+	select WANT_DEV_COREDUMP
+	select REGMAP_MMIO
+	help
+	  This driver supports Airoha Network Processor (NPU) available
+	  on the Airoha Soc family.
+
+config NET_AIROHA
+	tristate "Airoha SoC Gigabit Ethernet support"
+	depends on NET_DSA || !NET_DSA
+	select NET_AIROHA_NPU
+	select PAGE_POOL
+	help
+	  This driver supports the gigabit ethernet MACs in the
+	  Airoha SoC family.
+
+config NET_AIROHA_FLOW_STATS
+	default y
+	bool "Airoha flow stats"
+	depends on NET_AIROHA && NET_AIROHA_NPU
+	help
+	  Enable Aiorha flowtable statistic counters.
+
+endif #NET_VENDOR_AIROHA
diff --git a/drivers/net/ethernet/airoha/Makefile b/drivers/net/ethernet/airoha/Makefile
new file mode 100644
index 000000000000..94468053e34b
--- /dev/null
+++ b/drivers/net/ethernet/airoha/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Airoha for the Mediatek SoCs built-in ethernet macs
+#
+
+obj-$(CONFIG_NET_AIROHA) += airoha-eth.o
+airoha-eth-y := airoha_eth.o airoha_ppe.o
+airoha-eth-$(CONFIG_DEBUG_FS) += airoha_ppe_debugfs.o
+obj-$(CONFIG_NET_AIROHA_NPU) += airoha_npu.o
diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 6c683a12d5aa..06dea3a13e77 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -3,841 +3,31 @@
  * Copyright (c) 2024 AIROHA Inc
  * Author: Lorenzo Bianconi <lorenzo@kernel.org>
  */
-#include <linux/etherdevice.h>
-#include <linux/iopoll.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <linux/of_reserved_mem.h>
 #include <linux/platform_device.h>
-#include <linux/reset.h>
 #include <linux/tcp.h>
 #include <linux/u64_stats_sync.h>
-#include <net/dsa.h>
+#include <net/dst_metadata.h>
 #include <net/page_pool/helpers.h>
+#include <net/pkt_cls.h>
 #include <uapi/linux/ppp_defs.h>
 
-#define AIROHA_MAX_NUM_GDM_PORTS	1
-#define AIROHA_MAX_NUM_QDMA		2
-#define AIROHA_MAX_NUM_RSTS		3
-#define AIROHA_MAX_NUM_XSI_RSTS		5
-#define AIROHA_MAX_MTU			2000
-#define AIROHA_MAX_PACKET_SIZE		2048
-#define AIROHA_NUM_TX_RING		32
-#define AIROHA_NUM_RX_RING		32
-#define AIROHA_FE_MC_MAX_VLAN_TABLE	64
-#define AIROHA_FE_MC_MAX_VLAN_PORT	16
-#define AIROHA_NUM_TX_IRQ		2
-#define HW_DSCP_NUM			2048
-#define IRQ_QUEUE_LEN(_n)		((_n) ? 1024 : 2048)
-#define TX_DSCP_NUM			1024
-#define RX_DSCP_NUM(_n)			\
-	((_n) ==  2 ? 128 :		\
-	 (_n) == 11 ? 128 :		\
-	 (_n) == 15 ? 128 :		\
-	 (_n) ==  0 ? 1024 : 16)
-
-#define PSE_RSV_PAGES			128
-#define PSE_QUEUE_RSV_PAGES		64
-
-/* FE */
-#define PSE_BASE			0x0100
-#define CSR_IFC_BASE			0x0200
-#define CDM1_BASE			0x0400
-#define GDM1_BASE			0x0500
-#define PPE1_BASE			0x0c00
-
-#define CDM2_BASE			0x1400
-#define GDM2_BASE			0x1500
-
-#define GDM3_BASE			0x1100
-#define GDM4_BASE			0x2500
-
-#define GDM_BASE(_n)			\
-	((_n) == 4 ? GDM4_BASE :	\
-	 (_n) == 3 ? GDM3_BASE :	\
-	 (_n) == 2 ? GDM2_BASE : GDM1_BASE)
-
-#define REG_FE_DMA_GLO_CFG		0x0000
-#define FE_DMA_GLO_L2_SPACE_MASK	GENMASK(7, 4)
-#define FE_DMA_GLO_PG_SZ_MASK		BIT(3)
-
-#define REG_FE_RST_GLO_CFG		0x0004
-#define FE_RST_GDM4_MBI_ARB_MASK	BIT(3)
-#define FE_RST_GDM3_MBI_ARB_MASK	BIT(2)
-#define FE_RST_CORE_MASK		BIT(0)
-
-#define REG_FE_WAN_MAC_H		0x0030
-#define REG_FE_LAN_MAC_H		0x0040
-
-#define REG_FE_MAC_LMIN(_n)		((_n) + 0x04)
-#define REG_FE_MAC_LMAX(_n)		((_n) + 0x08)
-
-#define REG_FE_CDM1_OQ_MAP0		0x0050
-#define REG_FE_CDM1_OQ_MAP1		0x0054
-#define REG_FE_CDM1_OQ_MAP2		0x0058
-#define REG_FE_CDM1_OQ_MAP3		0x005c
-
-#define REG_FE_PCE_CFG			0x0070
-#define PCE_DPI_EN_MASK			BIT(2)
-#define PCE_KA_EN_MASK			BIT(1)
-#define PCE_MC_EN_MASK			BIT(0)
-
-#define REG_FE_PSE_QUEUE_CFG_WR		0x0080
-#define PSE_CFG_PORT_ID_MASK		GENMASK(27, 24)
-#define PSE_CFG_QUEUE_ID_MASK		GENMASK(20, 16)
-#define PSE_CFG_WR_EN_MASK		BIT(8)
-#define PSE_CFG_OQRSV_SEL_MASK		BIT(0)
-
-#define REG_FE_PSE_QUEUE_CFG_VAL	0x0084
-#define PSE_CFG_OQ_RSV_MASK		GENMASK(13, 0)
-
-#define PSE_FQ_CFG			0x008c
-#define PSE_FQ_LIMIT_MASK		GENMASK(14, 0)
-
-#define REG_FE_PSE_BUF_SET		0x0090
-#define PSE_SHARE_USED_LTHD_MASK	GENMASK(31, 16)
-#define PSE_ALLRSV_MASK			GENMASK(14, 0)
-
-#define REG_PSE_SHARE_USED_THD		0x0094
-#define PSE_SHARE_USED_MTHD_MASK	GENMASK(31, 16)
-#define PSE_SHARE_USED_HTHD_MASK	GENMASK(15, 0)
-
-#define REG_GDM_MISC_CFG		0x0148
-#define GDM2_RDM_ACK_WAIT_PREF_MASK	BIT(9)
-#define GDM2_CHN_VLD_MODE_MASK		BIT(5)
-
-#define REG_FE_CSR_IFC_CFG		CSR_IFC_BASE
-#define FE_IFC_EN_MASK			BIT(0)
-
-#define REG_FE_VIP_PORT_EN		0x01f0
-#define REG_FE_IFC_PORT_EN		0x01f4
-
-#define REG_PSE_IQ_REV1			(PSE_BASE + 0x08)
-#define PSE_IQ_RES1_P2_MASK		GENMASK(23, 16)
-
-#define REG_PSE_IQ_REV2			(PSE_BASE + 0x0c)
-#define PSE_IQ_RES2_P5_MASK		GENMASK(15, 8)
-#define PSE_IQ_RES2_P4_MASK		GENMASK(7, 0)
-
-#define REG_FE_VIP_EN(_n)		(0x0300 + ((_n) << 3))
-#define PATN_FCPU_EN_MASK		BIT(7)
-#define PATN_SWP_EN_MASK		BIT(6)
-#define PATN_DP_EN_MASK			BIT(5)
-#define PATN_SP_EN_MASK			BIT(4)
-#define PATN_TYPE_MASK			GENMASK(3, 1)
-#define PATN_EN_MASK			BIT(0)
-
-#define REG_FE_VIP_PATN(_n)		(0x0304 + ((_n) << 3))
-#define PATN_DP_MASK			GENMASK(31, 16)
-#define PATN_SP_MASK			GENMASK(15, 0)
-
-#define REG_CDM1_VLAN_CTRL		CDM1_BASE
-#define CDM1_VLAN_MASK			GENMASK(31, 16)
-
-#define REG_CDM1_FWD_CFG		(CDM1_BASE + 0x08)
-#define CDM1_VIP_QSEL_MASK		GENMASK(24, 20)
-
-#define REG_CDM1_CRSN_QSEL(_n)		(CDM1_BASE + 0x10 + ((_n) << 2))
-#define CDM1_CRSN_QSEL_REASON_MASK(_n)	\
-	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
-
-#define REG_CDM2_FWD_CFG		(CDM2_BASE + 0x08)
-#define CDM2_OAM_QSEL_MASK		GENMASK(31, 27)
-#define CDM2_VIP_QSEL_MASK		GENMASK(24, 20)
-
-#define REG_CDM2_CRSN_QSEL(_n)		(CDM2_BASE + 0x10 + ((_n) << 2))
-#define CDM2_CRSN_QSEL_REASON_MASK(_n)	\
-	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
-
-#define REG_GDM_FWD_CFG(_n)		GDM_BASE(_n)
-#define GDM_DROP_CRC_ERR		BIT(23)
-#define GDM_IP4_CKSUM			BIT(22)
-#define GDM_TCP_CKSUM			BIT(21)
-#define GDM_UDP_CKSUM			BIT(20)
-#define GDM_UCFQ_MASK			GENMASK(15, 12)
-#define GDM_BCFQ_MASK			GENMASK(11, 8)
-#define GDM_MCFQ_MASK			GENMASK(7, 4)
-#define GDM_OCFQ_MASK			GENMASK(3, 0)
-
-#define REG_GDM_INGRESS_CFG(_n)		(GDM_BASE(_n) + 0x10)
-#define GDM_INGRESS_FC_EN_MASK		BIT(1)
-#define GDM_STAG_EN_MASK		BIT(0)
-
-#define REG_GDM_LEN_CFG(_n)		(GDM_BASE(_n) + 0x14)
-#define GDM_SHORT_LEN_MASK		GENMASK(13, 0)
-#define GDM_LONG_LEN_MASK		GENMASK(29, 16)
-
-#define REG_FE_CPORT_CFG		(GDM1_BASE + 0x40)
-#define FE_CPORT_PAD			BIT(26)
-#define FE_CPORT_PORT_XFC_MASK		BIT(25)
-#define FE_CPORT_QUEUE_XFC_MASK		BIT(24)
-
-#define REG_FE_GDM_MIB_CLEAR(_n)	(GDM_BASE(_n) + 0xf0)
-#define FE_GDM_MIB_RX_CLEAR_MASK	BIT(1)
-#define FE_GDM_MIB_TX_CLEAR_MASK	BIT(0)
-
-#define REG_FE_GDM1_MIB_CFG		(GDM1_BASE + 0xf4)
-#define FE_STRICT_RFC2819_MODE_MASK	BIT(31)
-#define FE_GDM1_TX_MIB_SPLIT_EN_MASK	BIT(17)
-#define FE_GDM1_RX_MIB_SPLIT_EN_MASK	BIT(16)
-#define FE_TX_MIB_ID_MASK		GENMASK(15, 8)
-#define FE_RX_MIB_ID_MASK		GENMASK(7, 0)
-
-#define REG_FE_GDM_TX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x104)
-#define REG_FE_GDM_TX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x10c)
-#define REG_FE_GDM_TX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x110)
-#define REG_FE_GDM_TX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x114)
-#define REG_FE_GDM_TX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x118)
-#define REG_FE_GDM_TX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x11c)
-#define REG_FE_GDM_TX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x120)
-#define REG_FE_GDM_TX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x124)
-#define REG_FE_GDM_TX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x128)
-#define REG_FE_GDM_TX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x12c)
-#define REG_FE_GDM_TX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x130)
-#define REG_FE_GDM_TX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x134)
-#define REG_FE_GDM_TX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x138)
-#define REG_FE_GDM_TX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x13c)
-#define REG_FE_GDM_TX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x140)
-
-#define REG_FE_GDM_RX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x148)
-#define REG_FE_GDM_RX_FC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x14c)
-#define REG_FE_GDM_RX_RC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x150)
-#define REG_FE_GDM_RX_OVERFLOW_DROP_CNT(_n)	(GDM_BASE(_n) + 0x154)
-#define REG_FE_GDM_RX_ERROR_DROP_CNT(_n)	(GDM_BASE(_n) + 0x158)
-#define REG_FE_GDM_RX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x15c)
-#define REG_FE_GDM_RX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x160)
-#define REG_FE_GDM_RX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x164)
-#define REG_FE_GDM_RX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x168)
-#define REG_FE_GDM_RX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x16c)
-#define REG_FE_GDM_RX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x170)
-#define REG_FE_GDM_RX_ETH_CRC_ERR_CNT(_n)	(GDM_BASE(_n) + 0x174)
-#define REG_FE_GDM_RX_ETH_FRAG_CNT(_n)		(GDM_BASE(_n) + 0x178)
-#define REG_FE_GDM_RX_ETH_JABBER_CNT(_n)	(GDM_BASE(_n) + 0x17c)
-#define REG_FE_GDM_RX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x180)
-#define REG_FE_GDM_RX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x184)
-#define REG_FE_GDM_RX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x188)
-#define REG_FE_GDM_RX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x18c)
-#define REG_FE_GDM_RX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x190)
-#define REG_FE_GDM_RX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x194)
-#define REG_FE_GDM_RX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x198)
-#define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x19c)
-
-#define REG_PPE1_TB_HASH_CFG		(PPE1_BASE + 0x250)
-#define PPE1_SRAM_TABLE_EN_MASK		BIT(0)
-#define PPE1_SRAM_HASH1_EN_MASK		BIT(8)
-#define PPE1_DRAM_TABLE_EN_MASK		BIT(16)
-#define PPE1_DRAM_HASH1_EN_MASK		BIT(24)
-
-#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x280)
-#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x284)
-#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x288)
-#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x28c)
-
-#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x290)
-#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x294)
-#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x298)
-#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x29c)
-#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2b8)
-#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2bc)
-#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2c0)
-#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2c4)
-#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2c8)
-#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2cc)
-#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2e8)
-#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2ec)
-#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2f0)
-#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2f4)
-#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2f8)
-#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2fc)
-
-#define REG_GDM2_CHN_RLS		(GDM2_BASE + 0x20)
-#define MBI_RX_AGE_SEL_MASK		GENMASK(26, 25)
-#define MBI_TX_AGE_SEL_MASK		GENMASK(18, 17)
-
-#define REG_GDM3_FWD_CFG		GDM3_BASE
-#define GDM3_PAD_EN_MASK		BIT(28)
-
-#define REG_GDM4_FWD_CFG		(GDM4_BASE + 0x100)
-#define GDM4_PAD_EN_MASK		BIT(28)
-#define GDM4_SPORT_OFFSET0_MASK		GENMASK(11, 8)
-
-#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x33c)
-#define GDM4_SPORT_OFF2_MASK		GENMASK(19, 16)
-#define GDM4_SPORT_OFF1_MASK		GENMASK(15, 12)
-#define GDM4_SPORT_OFF0_MASK		GENMASK(11, 8)
-
-#define REG_IP_FRAG_FP			0x2010
-#define IP_ASSEMBLE_PORT_MASK		GENMASK(24, 21)
-#define IP_ASSEMBLE_NBQ_MASK		GENMASK(20, 16)
-#define IP_FRAGMENT_PORT_MASK		GENMASK(8, 5)
-#define IP_FRAGMENT_NBQ_MASK		GENMASK(4, 0)
-
-#define REG_MC_VLAN_EN			0x2100
-#define MC_VLAN_EN_MASK			BIT(0)
-
-#define REG_MC_VLAN_CFG			0x2104
-#define MC_VLAN_CFG_CMD_DONE_MASK	BIT(31)
-#define MC_VLAN_CFG_TABLE_ID_MASK	GENMASK(21, 16)
-#define MC_VLAN_CFG_PORT_ID_MASK	GENMASK(11, 8)
-#define MC_VLAN_CFG_TABLE_SEL_MASK	BIT(4)
-#define MC_VLAN_CFG_RW_MASK		BIT(0)
-
-#define REG_MC_VLAN_DATA		0x2108
-
-#define REG_CDM5_RX_OQ1_DROP_CNT	0x29d4
-
-/* QDMA */
-#define REG_QDMA_GLOBAL_CFG			0x0004
-#define GLOBAL_CFG_RX_2B_OFFSET_MASK		BIT(31)
-#define GLOBAL_CFG_DMA_PREFERENCE_MASK		GENMASK(30, 29)
-#define GLOBAL_CFG_CPU_TXR_RR_MASK		BIT(28)
-#define GLOBAL_CFG_DSCP_BYTE_SWAP_MASK		BIT(27)
-#define GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK	BIT(26)
-#define GLOBAL_CFG_MULTICAST_MODIFY_FP_MASK	BIT(25)
-#define GLOBAL_CFG_OAM_MODIFY_MASK		BIT(24)
-#define GLOBAL_CFG_RESET_MASK			BIT(23)
-#define GLOBAL_CFG_RESET_DONE_MASK		BIT(22)
-#define GLOBAL_CFG_MULTICAST_EN_MASK		BIT(21)
-#define GLOBAL_CFG_IRQ1_EN_MASK			BIT(20)
-#define GLOBAL_CFG_IRQ0_EN_MASK			BIT(19)
-#define GLOBAL_CFG_LOOPCNT_EN_MASK		BIT(18)
-#define GLOBAL_CFG_RD_BYPASS_WR_MASK		BIT(17)
-#define GLOBAL_CFG_QDMA_LOOPBACK_MASK		BIT(16)
-#define GLOBAL_CFG_LPBK_RXQ_SEL_MASK		GENMASK(13, 8)
-#define GLOBAL_CFG_CHECK_DONE_MASK		BIT(7)
-#define GLOBAL_CFG_TX_WB_DONE_MASK		BIT(6)
-#define GLOBAL_CFG_MAX_ISSUE_NUM_MASK		GENMASK(5, 4)
-#define GLOBAL_CFG_RX_DMA_BUSY_MASK		BIT(3)
-#define GLOBAL_CFG_RX_DMA_EN_MASK		BIT(2)
-#define GLOBAL_CFG_TX_DMA_BUSY_MASK		BIT(1)
-#define GLOBAL_CFG_TX_DMA_EN_MASK		BIT(0)
-
-#define REG_FWD_DSCP_BASE			0x0010
-#define REG_FWD_BUF_BASE			0x0014
-
-#define REG_HW_FWD_DSCP_CFG			0x0018
-#define HW_FWD_DSCP_PAYLOAD_SIZE_MASK		GENMASK(29, 28)
-#define HW_FWD_DSCP_SCATTER_LEN_MASK		GENMASK(17, 16)
-#define HW_FWD_DSCP_MIN_SCATTER_LEN_MASK	GENMASK(15, 0)
-
-#define REG_INT_STATUS(_n)		\
-	(((_n) == 4) ? 0x0730 :		\
-	 ((_n) == 3) ? 0x0724 :		\
-	 ((_n) == 2) ? 0x0720 :		\
-	 ((_n) == 1) ? 0x0024 : 0x0020)
-
-#define REG_INT_ENABLE(_n)		\
-	(((_n) == 4) ? 0x0750 :		\
-	 ((_n) == 3) ? 0x0744 :		\
-	 ((_n) == 2) ? 0x0740 :		\
-	 ((_n) == 1) ? 0x002c : 0x0028)
-
-/* QDMA_CSR_INT_ENABLE1 */
-#define RX15_COHERENT_INT_MASK		BIT(31)
-#define RX14_COHERENT_INT_MASK		BIT(30)
-#define RX13_COHERENT_INT_MASK		BIT(29)
-#define RX12_COHERENT_INT_MASK		BIT(28)
-#define RX11_COHERENT_INT_MASK		BIT(27)
-#define RX10_COHERENT_INT_MASK		BIT(26)
-#define RX9_COHERENT_INT_MASK		BIT(25)
-#define RX8_COHERENT_INT_MASK		BIT(24)
-#define RX7_COHERENT_INT_MASK		BIT(23)
-#define RX6_COHERENT_INT_MASK		BIT(22)
-#define RX5_COHERENT_INT_MASK		BIT(21)
-#define RX4_COHERENT_INT_MASK		BIT(20)
-#define RX3_COHERENT_INT_MASK		BIT(19)
-#define RX2_COHERENT_INT_MASK		BIT(18)
-#define RX1_COHERENT_INT_MASK		BIT(17)
-#define RX0_COHERENT_INT_MASK		BIT(16)
-#define TX7_COHERENT_INT_MASK		BIT(15)
-#define TX6_COHERENT_INT_MASK		BIT(14)
-#define TX5_COHERENT_INT_MASK		BIT(13)
-#define TX4_COHERENT_INT_MASK		BIT(12)
-#define TX3_COHERENT_INT_MASK		BIT(11)
-#define TX2_COHERENT_INT_MASK		BIT(10)
-#define TX1_COHERENT_INT_MASK		BIT(9)
-#define TX0_COHERENT_INT_MASK		BIT(8)
-#define CNT_OVER_FLOW_INT_MASK		BIT(7)
-#define IRQ1_FULL_INT_MASK		BIT(5)
-#define IRQ1_INT_MASK			BIT(4)
-#define HWFWD_DSCP_LOW_INT_MASK		BIT(3)
-#define HWFWD_DSCP_EMPTY_INT_MASK	BIT(2)
-#define IRQ0_FULL_INT_MASK		BIT(1)
-#define IRQ0_INT_MASK			BIT(0)
-
-#define TX_DONE_INT_MASK(_n)					\
-	((_n) ? IRQ1_INT_MASK | IRQ1_FULL_INT_MASK		\
-	      : IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
-
-#define INT_TX_MASK						\
-	(IRQ1_INT_MASK | IRQ1_FULL_INT_MASK |			\
-	 IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
-
-#define INT_IDX0_MASK						\
-	(TX0_COHERENT_INT_MASK | TX1_COHERENT_INT_MASK |	\
-	 TX2_COHERENT_INT_MASK | TX3_COHERENT_INT_MASK |	\
-	 TX4_COHERENT_INT_MASK | TX5_COHERENT_INT_MASK |	\
-	 TX6_COHERENT_INT_MASK | TX7_COHERENT_INT_MASK |	\
-	 RX0_COHERENT_INT_MASK | RX1_COHERENT_INT_MASK |	\
-	 RX2_COHERENT_INT_MASK | RX3_COHERENT_INT_MASK |	\
-	 RX4_COHERENT_INT_MASK | RX7_COHERENT_INT_MASK |	\
-	 RX8_COHERENT_INT_MASK | RX9_COHERENT_INT_MASK |	\
-	 RX15_COHERENT_INT_MASK | INT_TX_MASK)
-
-/* QDMA_CSR_INT_ENABLE2 */
-#define RX15_NO_CPU_DSCP_INT_MASK	BIT(31)
-#define RX14_NO_CPU_DSCP_INT_MASK	BIT(30)
-#define RX13_NO_CPU_DSCP_INT_MASK	BIT(29)
-#define RX12_NO_CPU_DSCP_INT_MASK	BIT(28)
-#define RX11_NO_CPU_DSCP_INT_MASK	BIT(27)
-#define RX10_NO_CPU_DSCP_INT_MASK	BIT(26)
-#define RX9_NO_CPU_DSCP_INT_MASK	BIT(25)
-#define RX8_NO_CPU_DSCP_INT_MASK	BIT(24)
-#define RX7_NO_CPU_DSCP_INT_MASK	BIT(23)
-#define RX6_NO_CPU_DSCP_INT_MASK	BIT(22)
-#define RX5_NO_CPU_DSCP_INT_MASK	BIT(21)
-#define RX4_NO_CPU_DSCP_INT_MASK	BIT(20)
-#define RX3_NO_CPU_DSCP_INT_MASK	BIT(19)
-#define RX2_NO_CPU_DSCP_INT_MASK	BIT(18)
-#define RX1_NO_CPU_DSCP_INT_MASK	BIT(17)
-#define RX0_NO_CPU_DSCP_INT_MASK	BIT(16)
-#define RX15_DONE_INT_MASK		BIT(15)
-#define RX14_DONE_INT_MASK		BIT(14)
-#define RX13_DONE_INT_MASK		BIT(13)
-#define RX12_DONE_INT_MASK		BIT(12)
-#define RX11_DONE_INT_MASK		BIT(11)
-#define RX10_DONE_INT_MASK		BIT(10)
-#define RX9_DONE_INT_MASK		BIT(9)
-#define RX8_DONE_INT_MASK		BIT(8)
-#define RX7_DONE_INT_MASK		BIT(7)
-#define RX6_DONE_INT_MASK		BIT(6)
-#define RX5_DONE_INT_MASK		BIT(5)
-#define RX4_DONE_INT_MASK		BIT(4)
-#define RX3_DONE_INT_MASK		BIT(3)
-#define RX2_DONE_INT_MASK		BIT(2)
-#define RX1_DONE_INT_MASK		BIT(1)
-#define RX0_DONE_INT_MASK		BIT(0)
-
-#define RX_DONE_INT_MASK					\
-	(RX0_DONE_INT_MASK | RX1_DONE_INT_MASK |		\
-	 RX2_DONE_INT_MASK | RX3_DONE_INT_MASK |		\
-	 RX4_DONE_INT_MASK | RX7_DONE_INT_MASK |		\
-	 RX8_DONE_INT_MASK | RX9_DONE_INT_MASK |		\
-	 RX15_DONE_INT_MASK)
-#define INT_IDX1_MASK						\
-	(RX_DONE_INT_MASK |					\
-	 RX0_NO_CPU_DSCP_INT_MASK | RX1_NO_CPU_DSCP_INT_MASK |	\
-	 RX2_NO_CPU_DSCP_INT_MASK | RX3_NO_CPU_DSCP_INT_MASK |	\
-	 RX4_NO_CPU_DSCP_INT_MASK | RX7_NO_CPU_DSCP_INT_MASK |	\
-	 RX8_NO_CPU_DSCP_INT_MASK | RX9_NO_CPU_DSCP_INT_MASK |	\
-	 RX15_NO_CPU_DSCP_INT_MASK)
-
-/* QDMA_CSR_INT_ENABLE5 */
-#define TX31_COHERENT_INT_MASK		BIT(31)
-#define TX30_COHERENT_INT_MASK		BIT(30)
-#define TX29_COHERENT_INT_MASK		BIT(29)
-#define TX28_COHERENT_INT_MASK		BIT(28)
-#define TX27_COHERENT_INT_MASK		BIT(27)
-#define TX26_COHERENT_INT_MASK		BIT(26)
-#define TX25_COHERENT_INT_MASK		BIT(25)
-#define TX24_COHERENT_INT_MASK		BIT(24)
-#define TX23_COHERENT_INT_MASK		BIT(23)
-#define TX22_COHERENT_INT_MASK		BIT(22)
-#define TX21_COHERENT_INT_MASK		BIT(21)
-#define TX20_COHERENT_INT_MASK		BIT(20)
-#define TX19_COHERENT_INT_MASK		BIT(19)
-#define TX18_COHERENT_INT_MASK		BIT(18)
-#define TX17_COHERENT_INT_MASK		BIT(17)
-#define TX16_COHERENT_INT_MASK		BIT(16)
-#define TX15_COHERENT_INT_MASK		BIT(15)
-#define TX14_COHERENT_INT_MASK		BIT(14)
-#define TX13_COHERENT_INT_MASK		BIT(13)
-#define TX12_COHERENT_INT_MASK		BIT(12)
-#define TX11_COHERENT_INT_MASK		BIT(11)
-#define TX10_COHERENT_INT_MASK		BIT(10)
-#define TX9_COHERENT_INT_MASK		BIT(9)
-#define TX8_COHERENT_INT_MASK		BIT(8)
-
-#define INT_IDX4_MASK						\
-	(TX8_COHERENT_INT_MASK | TX9_COHERENT_INT_MASK |	\
-	 TX10_COHERENT_INT_MASK | TX11_COHERENT_INT_MASK |	\
-	 TX12_COHERENT_INT_MASK | TX13_COHERENT_INT_MASK |	\
-	 TX14_COHERENT_INT_MASK | TX15_COHERENT_INT_MASK |	\
-	 TX16_COHERENT_INT_MASK | TX17_COHERENT_INT_MASK |	\
-	 TX18_COHERENT_INT_MASK | TX19_COHERENT_INT_MASK |	\
-	 TX20_COHERENT_INT_MASK | TX21_COHERENT_INT_MASK |	\
-	 TX22_COHERENT_INT_MASK | TX23_COHERENT_INT_MASK |	\
-	 TX24_COHERENT_INT_MASK | TX25_COHERENT_INT_MASK |	\
-	 TX26_COHERENT_INT_MASK | TX27_COHERENT_INT_MASK |	\
-	 TX28_COHERENT_INT_MASK | TX29_COHERENT_INT_MASK |	\
-	 TX30_COHERENT_INT_MASK | TX31_COHERENT_INT_MASK)
-
-#define REG_TX_IRQ_BASE(_n)		((_n) ? 0x0048 : 0x0050)
-
-#define REG_TX_IRQ_CFG(_n)		((_n) ? 0x004c : 0x0054)
-#define TX_IRQ_THR_MASK			GENMASK(27, 16)
-#define TX_IRQ_DEPTH_MASK		GENMASK(11, 0)
-
-#define REG_IRQ_CLEAR_LEN(_n)		((_n) ? 0x0064 : 0x0058)
-#define IRQ_CLEAR_LEN_MASK		GENMASK(7, 0)
-
-#define REG_IRQ_STATUS(_n)		((_n) ? 0x0068 : 0x005c)
-#define IRQ_ENTRY_LEN_MASK		GENMASK(27, 16)
-#define IRQ_HEAD_IDX_MASK		GENMASK(11, 0)
-
-#define REG_TX_RING_BASE(_n)	\
-	(((_n) < 8) ? 0x0100 + ((_n) << 5) : 0x0b00 + (((_n) - 8) << 5))
-
-#define REG_TX_RING_BLOCKING(_n)	\
-	(((_n) < 8) ? 0x0104 + ((_n) << 5) : 0x0b04 + (((_n) - 8) << 5))
-
-#define TX_RING_IRQ_BLOCKING_MAP_MASK			BIT(6)
-#define TX_RING_IRQ_BLOCKING_CFG_MASK			BIT(4)
-#define TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK		BIT(2)
-#define TX_RING_IRQ_BLOCKING_MAX_TH_TXRING_EN_MASK	BIT(1)
-#define TX_RING_IRQ_BLOCKING_MIN_TH_TXRING_EN_MASK	BIT(0)
-
-#define REG_TX_CPU_IDX(_n)	\
-	(((_n) < 8) ? 0x0108 + ((_n) << 5) : 0x0b08 + (((_n) - 8) << 5))
-
-#define TX_RING_CPU_IDX_MASK		GENMASK(15, 0)
-
-#define REG_TX_DMA_IDX(_n)	\
-	(((_n) < 8) ? 0x010c + ((_n) << 5) : 0x0b0c + (((_n) - 8) << 5))
-
-#define TX_RING_DMA_IDX_MASK		GENMASK(15, 0)
-
-#define IRQ_RING_IDX_MASK		GENMASK(20, 16)
-#define IRQ_DESC_IDX_MASK		GENMASK(15, 0)
-
-#define REG_RX_RING_BASE(_n)	\
-	(((_n) < 16) ? 0x0200 + ((_n) << 5) : 0x0e00 + (((_n) - 16) << 5))
-
-#define REG_RX_RING_SIZE(_n)	\
-	(((_n) < 16) ? 0x0204 + ((_n) << 5) : 0x0e04 + (((_n) - 16) << 5))
-
-#define RX_RING_THR_MASK		GENMASK(31, 16)
-#define RX_RING_SIZE_MASK		GENMASK(15, 0)
-
-#define REG_RX_CPU_IDX(_n)	\
-	(((_n) < 16) ? 0x0208 + ((_n) << 5) : 0x0e08 + (((_n) - 16) << 5))
-
-#define RX_RING_CPU_IDX_MASK		GENMASK(15, 0)
-
-#define REG_RX_DMA_IDX(_n)	\
-	(((_n) < 16) ? 0x020c + ((_n) << 5) : 0x0e0c + (((_n) - 16) << 5))
-
-#define REG_RX_DELAY_INT_IDX(_n)	\
-	(((_n) < 16) ? 0x0210 + ((_n) << 5) : 0x0e10 + (((_n) - 16) << 5))
-
-#define RX_DELAY_INT_MASK		GENMASK(15, 0)
-
-#define RX_RING_DMA_IDX_MASK		GENMASK(15, 0)
-
-#define REG_INGRESS_TRTCM_CFG		0x0070
-#define INGRESS_TRTCM_EN_MASK		BIT(31)
-#define INGRESS_TRTCM_MODE_MASK		BIT(30)
-#define INGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define INGRESS_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define REG_TXQ_DIS_CFG_BASE(_n)	((_n) ? 0x20a0 : 0x00a0)
-#define REG_TXQ_DIS_CFG(_n, _m)		(REG_TXQ_DIS_CFG_BASE((_n)) + (_m) << 2)
-
-#define REG_LMGR_INIT_CFG		0x1000
-#define LMGR_INIT_START			BIT(31)
-#define LMGR_SRAM_MODE_MASK		BIT(30)
-#define HW_FWD_PKTSIZE_OVERHEAD_MASK	GENMASK(27, 20)
-#define HW_FWD_DESC_NUM_MASK		GENMASK(16, 0)
-
-#define REG_FWD_DSCP_LOW_THR		0x1004
-#define FWD_DSCP_LOW_THR_MASK		GENMASK(17, 0)
-
-#define REG_EGRESS_RATE_METER_CFG		0x100c
-#define EGRESS_RATE_METER_EN_MASK		BIT(31)
-#define EGRESS_RATE_METER_EQ_RATE_EN_MASK	BIT(17)
-#define EGRESS_RATE_METER_WINDOW_SZ_MASK	GENMASK(16, 12)
-#define EGRESS_RATE_METER_TIMESLICE_MASK	GENMASK(10, 0)
-
-#define REG_EGRESS_TRTCM_CFG		0x1010
-#define EGRESS_TRTCM_EN_MASK		BIT(31)
-#define EGRESS_TRTCM_MODE_MASK		BIT(30)
-#define EGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define EGRESS_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define REG_TXWRR_MODE_CFG		0x1020
-#define TWRR_WEIGHT_SCALE_MASK		BIT(31)
-#define TWRR_WEIGHT_BASE_MASK		BIT(3)
-
-#define REG_PSE_BUF_USAGE_CFG		0x1028
-#define PSE_BUF_ESTIMATE_EN_MASK	BIT(29)
-
-#define REG_GLB_TRTCM_CFG		0x1080
-#define GLB_TRTCM_EN_MASK		BIT(31)
-#define GLB_TRTCM_MODE_MASK		BIT(30)
-#define GLB_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define GLB_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define REG_TXQ_CNGST_CFG		0x10a0
-#define TXQ_CNGST_DROP_EN		BIT(31)
-#define TXQ_CNGST_DEI_DROP_EN		BIT(30)
-
-#define REG_SLA_TRTCM_CFG		0x1150
-#define SLA_TRTCM_EN_MASK		BIT(31)
-#define SLA_TRTCM_MODE_MASK		BIT(30)
-#define SLA_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define SLA_FAST_TICK_MASK		GENMASK(15, 0)
-
-/* CTRL */
-#define QDMA_DESC_DONE_MASK		BIT(31)
-#define QDMA_DESC_DROP_MASK		BIT(30) /* tx: drop - rx: overflow */
-#define QDMA_DESC_MORE_MASK		BIT(29) /* more SG elements */
-#define QDMA_DESC_DEI_MASK		BIT(25)
-#define QDMA_DESC_NO_DROP_MASK		BIT(24)
-#define QDMA_DESC_LEN_MASK		GENMASK(15, 0)
-/* DATA */
-#define QDMA_DESC_NEXT_ID_MASK		GENMASK(15, 0)
-/* TX MSG0 */
-#define QDMA_ETH_TXMSG_MIC_IDX_MASK	BIT(30)
-#define QDMA_ETH_TXMSG_SP_TAG_MASK	GENMASK(29, 14)
-#define QDMA_ETH_TXMSG_ICO_MASK		BIT(13)
-#define QDMA_ETH_TXMSG_UCO_MASK		BIT(12)
-#define QDMA_ETH_TXMSG_TCO_MASK		BIT(11)
-#define QDMA_ETH_TXMSG_TSO_MASK		BIT(10)
-#define QDMA_ETH_TXMSG_FAST_MASK	BIT(9)
-#define QDMA_ETH_TXMSG_OAM_MASK		BIT(8)
-#define QDMA_ETH_TXMSG_CHAN_MASK	GENMASK(7, 3)
-#define QDMA_ETH_TXMSG_QUEUE_MASK	GENMASK(2, 0)
-/* TX MSG1 */
-#define QDMA_ETH_TXMSG_NO_DROP		BIT(31)
-#define QDMA_ETH_TXMSG_METER_MASK	GENMASK(30, 24)	/* 0x7f no meters */
-#define QDMA_ETH_TXMSG_FPORT_MASK	GENMASK(23, 20)
-#define QDMA_ETH_TXMSG_NBOQ_MASK	GENMASK(19, 15)
-#define QDMA_ETH_TXMSG_HWF_MASK		BIT(14)
-#define QDMA_ETH_TXMSG_HOP_MASK		BIT(13)
-#define QDMA_ETH_TXMSG_PTP_MASK		BIT(12)
-#define QDMA_ETH_TXMSG_ACNT_G1_MASK	GENMASK(10, 6)	/* 0x1f do not count */
-#define QDMA_ETH_TXMSG_ACNT_G0_MASK	GENMASK(5, 0)	/* 0x3f do not count */
-
-/* RX MSG1 */
-#define QDMA_ETH_RXMSG_DEI_MASK		BIT(31)
-#define QDMA_ETH_RXMSG_IP6_MASK		BIT(30)
-#define QDMA_ETH_RXMSG_IP4_MASK		BIT(29)
-#define QDMA_ETH_RXMSG_IP4F_MASK	BIT(28)
-#define QDMA_ETH_RXMSG_L4_VALID_MASK	BIT(27)
-#define QDMA_ETH_RXMSG_L4F_MASK		BIT(26)
-#define QDMA_ETH_RXMSG_SPORT_MASK	GENMASK(25, 21)
-#define QDMA_ETH_RXMSG_CRSN_MASK	GENMASK(20, 16)
-#define QDMA_ETH_RXMSG_PPE_ENTRY_MASK	GENMASK(15, 0)
-
-struct airoha_qdma_desc {
-	__le32 rsv;
-	__le32 ctrl;
-	__le32 addr;
-	__le32 data;
-	__le32 msg0;
-	__le32 msg1;
-	__le32 msg2;
-	__le32 msg3;
-};
-
-/* CTRL0 */
-#define QDMA_FWD_DESC_CTX_MASK		BIT(31)
-#define QDMA_FWD_DESC_RING_MASK		GENMASK(30, 28)
-#define QDMA_FWD_DESC_IDX_MASK		GENMASK(27, 16)
-#define QDMA_FWD_DESC_LEN_MASK		GENMASK(15, 0)
-/* CTRL1 */
-#define QDMA_FWD_DESC_FIRST_IDX_MASK	GENMASK(15, 0)
-/* CTRL2 */
-#define QDMA_FWD_DESC_MORE_PKT_NUM_MASK	GENMASK(2, 0)
-
-struct airoha_qdma_fwd_desc {
-	__le32 addr;
-	__le32 ctrl0;
-	__le32 ctrl1;
-	__le32 ctrl2;
-	__le32 msg0;
-	__le32 msg1;
-	__le32 rsv0;
-	__le32 rsv1;
-};
-
-enum {
-	QDMA_INT_REG_IDX0,
-	QDMA_INT_REG_IDX1,
-	QDMA_INT_REG_IDX2,
-	QDMA_INT_REG_IDX3,
-	QDMA_INT_REG_IDX4,
-	QDMA_INT_REG_MAX
-};
-
-enum {
-	XSI_PCIE0_PORT,
-	XSI_PCIE1_PORT,
-	XSI_USB_PORT,
-	XSI_AE_PORT,
-	XSI_ETH_PORT,
-};
-
-enum {
-	XSI_PCIE0_VIP_PORT_MASK	= BIT(22),
-	XSI_PCIE1_VIP_PORT_MASK	= BIT(23),
-	XSI_USB_VIP_PORT_MASK	= BIT(25),
-	XSI_ETH_VIP_PORT_MASK	= BIT(24),
-};
-
-enum {
-	DEV_STATE_INITIALIZED,
-};
-
-enum {
-	CDM_CRSN_QSEL_Q1 = 1,
-	CDM_CRSN_QSEL_Q5 = 5,
-	CDM_CRSN_QSEL_Q6 = 6,
-	CDM_CRSN_QSEL_Q15 = 15,
-};
-
-enum {
-	CRSN_08 = 0x8,
-	CRSN_21 = 0x15, /* KA */
-	CRSN_22 = 0x16, /* hit bind and force route to CPU */
-	CRSN_24 = 0x18,
-	CRSN_25 = 0x19,
-};
-
-enum {
-	FE_PSE_PORT_CDM1,
-	FE_PSE_PORT_GDM1,
-	FE_PSE_PORT_GDM2,
-	FE_PSE_PORT_GDM3,
-	FE_PSE_PORT_PPE1,
-	FE_PSE_PORT_CDM2,
-	FE_PSE_PORT_CDM3,
-	FE_PSE_PORT_CDM4,
-	FE_PSE_PORT_PPE2,
-	FE_PSE_PORT_GDM4,
-	FE_PSE_PORT_CDM5,
-	FE_PSE_PORT_DROP = 0xf,
-};
+#include "airoha_regs.h"
+#include "airoha_eth.h"
 
-struct airoha_queue_entry {
-	union {
-		void *buf;
-		struct sk_buff *skb;
-	};
-	dma_addr_t dma_addr;
-	u16 dma_len;
-};
-
-struct airoha_queue {
-	struct airoha_qdma *qdma;
-
-	/* protect concurrent queue accesses */
-	spinlock_t lock;
-	struct airoha_queue_entry *entry;
-	struct airoha_qdma_desc *desc;
-	u16 head;
-	u16 tail;
-
-	int queued;
-	int ndesc;
-	int free_thr;
-	int buf_size;
-
-	struct napi_struct napi;
-	struct page_pool *page_pool;
-};
-
-struct airoha_tx_irq_queue {
-	struct airoha_qdma *qdma;
-
-	struct napi_struct napi;
-
-	int size;
-	u32 *q;
-};
-
-struct airoha_hw_stats {
-	/* protect concurrent hw_stats accesses */
-	spinlock_t lock;
-	struct u64_stats_sync syncp;
-
-	/* get_stats64 */
-	u64 rx_ok_pkts;
-	u64 tx_ok_pkts;
-	u64 rx_ok_bytes;
-	u64 tx_ok_bytes;
-	u64 rx_multicast;
-	u64 rx_errors;
-	u64 rx_drops;
-	u64 tx_drops;
-	u64 rx_crc_error;
-	u64 rx_over_errors;
-	/* ethtool stats */
-	u64 tx_broadcast;
-	u64 tx_multicast;
-	u64 tx_len[7];
-	u64 rx_broadcast;
-	u64 rx_fragment;
-	u64 rx_jabber;
-	u64 rx_len[7];
-};
-
-struct airoha_qdma {
-	struct airoha_eth *eth;
-	void __iomem *regs;
-
-	/* protect concurrent irqmask accesses */
-	spinlock_t irq_lock;
-	u32 irqmask[QDMA_INT_REG_MAX];
-	int irq;
-
-	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
-
-	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
-	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
-
-	/* descriptor and packet buffers for qdma hw forward */
-	struct {
-		void *desc;
-		void *q;
-	} hfwd;
-};
-
-struct airoha_gdm_port {
-	struct airoha_qdma *qdma;
-	struct net_device *dev;
-	int id;
-
-	struct airoha_hw_stats stats;
-};
-
-struct airoha_eth {
-	struct device *dev;
-
-	unsigned long state;
-	void __iomem *fe_regs;
-
-	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
-	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
-
-	struct net_device *napi_dev;
-
-	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
-	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
-};
-
-static u32 airoha_rr(void __iomem *base, u32 offset)
+u32 airoha_rr(void __iomem *base, u32 offset)
 {
 	return readl(base + offset);
 }
 
-static void airoha_wr(void __iomem *base, u32 offset, u32 val)
+void airoha_wr(void __iomem *base, u32 offset, u32 val)
 {
 	writel(val, base + offset);
 }
 
-static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
+u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 {
 	val |= (airoha_rr(base, offset) & ~mask);
 	airoha_wr(base, offset, val);
@@ -845,68 +35,40 @@ static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 	return val;
 }
 
-#define airoha_fe_rr(eth, offset)				\
-	airoha_rr((eth)->fe_regs, (offset))
-#define airoha_fe_wr(eth, offset, val)				\
-	airoha_wr((eth)->fe_regs, (offset), (val))
-#define airoha_fe_rmw(eth, offset, mask, val)			\
-	airoha_rmw((eth)->fe_regs, (offset), (mask), (val))
-#define airoha_fe_set(eth, offset, val)				\
-	airoha_rmw((eth)->fe_regs, (offset), 0, (val))
-#define airoha_fe_clear(eth, offset, val)			\
-	airoha_rmw((eth)->fe_regs, (offset), (val), 0)
-
-#define airoha_qdma_rr(qdma, offset)				\
-	airoha_rr((qdma)->regs, (offset))
-#define airoha_qdma_wr(qdma, offset, val)			\
-	airoha_wr((qdma)->regs, (offset), (val))
-#define airoha_qdma_rmw(qdma, offset, mask, val)		\
-	airoha_rmw((qdma)->regs, (offset), (mask), (val))
-#define airoha_qdma_set(qdma, offset, val)			\
-	airoha_rmw((qdma)->regs, (offset), 0, (val))
-#define airoha_qdma_clear(qdma, offset, val)			\
-	airoha_rmw((qdma)->regs, (offset), (val), 0)
-
-static void airoha_qdma_set_irqmask(struct airoha_qdma *qdma, int index,
-				    u32 clear, u32 set)
+static void airoha_qdma_set_irqmask(struct airoha_irq_bank *irq_bank,
+				    int index, u32 clear, u32 set)
 {
+	struct airoha_qdma *qdma = irq_bank->qdma;
+	int bank = irq_bank - &qdma->irq_banks[0];
 	unsigned long flags;
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(qdma->irqmask)))
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(irq_bank->irqmask)))
 		return;
 
-	spin_lock_irqsave(&qdma->irq_lock, flags);
+	spin_lock_irqsave(&irq_bank->irq_lock, flags);
 
-	qdma->irqmask[index] &= ~clear;
-	qdma->irqmask[index] |= set;
-	airoha_qdma_wr(qdma, REG_INT_ENABLE(index), qdma->irqmask[index]);
+	irq_bank->irqmask[index] &= ~clear;
+	irq_bank->irqmask[index] |= set;
+	airoha_qdma_wr(qdma, REG_INT_ENABLE(bank, index),
+		       irq_bank->irqmask[index]);
 	/* Read irq_enable register in order to guarantee the update above
 	 * completes in the spinlock critical section.
 	 */
-	airoha_qdma_rr(qdma, REG_INT_ENABLE(index));
-
-	spin_unlock_irqrestore(&qdma->irq_lock, flags);
-}
+	airoha_qdma_rr(qdma, REG_INT_ENABLE(bank, index));
 
-static void airoha_qdma_irq_enable(struct airoha_qdma *qdma, int index,
-				   u32 mask)
-{
-	airoha_qdma_set_irqmask(qdma, index, 0, mask);
+	spin_unlock_irqrestore(&irq_bank->irq_lock, flags);
 }
 
-static void airoha_qdma_irq_disable(struct airoha_qdma *qdma, int index,
-				    u32 mask)
+static void airoha_qdma_irq_enable(struct airoha_irq_bank *irq_bank,
+				   int index, u32 mask)
 {
-	airoha_qdma_set_irqmask(qdma, index, mask, 0);
+	airoha_qdma_set_irqmask(irq_bank, index, 0, mask);
 }
 
-static bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port)
+static void airoha_qdma_irq_disable(struct airoha_irq_bank *irq_bank,
+				    int index, u32 mask)
 {
-	/* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
-	 * GDM{2,3,4} can be used as wan port connected to an external
-	 * phy module.
-	 */
-	return port->id == 1;
+	airoha_qdma_set_irqmask(irq_bank, index, mask, 0);
 }
 
 static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
@@ -922,6 +84,8 @@ static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
 	val = (addr[3] << 16) | (addr[4] << 8) | addr[5];
 	airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), val);
 	airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), val);
+
+	airoha_ppe_init_upd_mem(port);
 }
 
 static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
@@ -937,30 +101,23 @@ static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
 		      FIELD_PREP(GDM_UCFQ_MASK, val));
 }
 
-static int airoha_set_gdm_port(struct airoha_eth *eth, int port, bool enable)
+static int airoha_set_vip_for_gdm_port(struct airoha_gdm_port *port,
+				       bool enable)
 {
-	u32 val = enable ? FE_PSE_PORT_PPE1 : FE_PSE_PORT_DROP;
-	u32 vip_port, cfg_addr;
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 vip_port;
 
-	switch (port) {
-	case XSI_PCIE0_PORT:
+	switch (port->id) {
+	case 3:
+		/* FIXME: handle XSI_PCIE1_PORT */
 		vip_port = XSI_PCIE0_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(3);
 		break;
-	case XSI_PCIE1_PORT:
-		vip_port = XSI_PCIE1_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(3);
-		break;
-	case XSI_USB_PORT:
-		vip_port = XSI_USB_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(4);
-		break;
-	case XSI_ETH_PORT:
+	case 4:
+		/* FIXME: handle XSI_USB_PORT */
 		vip_port = XSI_ETH_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(4);
 		break;
 	default:
-		return -EINVAL;
+		return 0;
 	}
 
 	if (enable) {
@@ -971,51 +128,17 @@ static int airoha_set_gdm_port(struct airoha_eth *eth, int port, bool enable)
 		airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, vip_port);
 	}
 
-	airoha_set_gdm_port_fwd_cfg(eth, cfg_addr, val);
-
-	return 0;
-}
-
-static int airoha_set_gdm_ports(struct airoha_eth *eth, bool enable)
-{
-	const int port_list[] = {
-		XSI_PCIE0_PORT,
-		XSI_PCIE1_PORT,
-		XSI_USB_PORT,
-		XSI_ETH_PORT
-	};
-	int i, err;
-
-	for (i = 0; i < ARRAY_SIZE(port_list); i++) {
-		err = airoha_set_gdm_port(eth, port_list[i], enable);
-		if (err)
-			goto error;
-	}
-
 	return 0;
-
-error:
-	for (i--; i >= 0; i--)
-		airoha_set_gdm_port(eth, port_list[i], false);
-
-	return err;
 }
 
 static void airoha_fe_maccr_init(struct airoha_eth *eth)
 {
 	int p;
 
-	for (p = 1; p <= ARRAY_SIZE(eth->ports); p++) {
+	for (p = 1; p <= ARRAY_SIZE(eth->ports); p++)
 		airoha_fe_set(eth, REG_GDM_FWD_CFG(p),
 			      GDM_TCP_CKSUM | GDM_UDP_CKSUM | GDM_IP4_CKSUM |
 			      GDM_DROP_CRC_ERR);
-		airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(p),
-					    FE_PSE_PORT_CDM1);
-		airoha_fe_rmw(eth, REG_GDM_LEN_CFG(p),
-			      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
-			      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
-			      FIELD_PREP(GDM_LONG_LEN_MASK, 4004));
-	}
 
 	airoha_fe_rmw(eth, REG_CDM1_VLAN_CTRL, CDM1_VLAN_MASK,
 		      FIELD_PREP(CDM1_VLAN_MASK, 0x8100));
@@ -1401,6 +524,25 @@ static int airoha_fe_init(struct airoha_eth *eth)
 	/* disable IFC by default */
 	airoha_fe_clear(eth, REG_FE_CSR_IFC_CFG, FE_IFC_EN_MASK);
 
+	airoha_fe_wr(eth, REG_PPE_DFT_CPORT0(0),
+		     FIELD_PREP(DFT_CPORT_MASK(7), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(6), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(5), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(4), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(3), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(2), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(1), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(0), FE_PSE_PORT_CDM1));
+	airoha_fe_wr(eth, REG_PPE_DFT_CPORT0(1),
+		     FIELD_PREP(DFT_CPORT_MASK(7), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(6), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(5), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(4), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(3), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(2), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(1), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(0), FE_PSE_PORT_CDM2));
+
 	/* enable 1:N vlan action, init vlan table */
 	airoha_fe_set(eth, REG_MC_VLAN_EN, MC_VLAN_EN_MASK);
 
@@ -1463,7 +605,7 @@ static int airoha_qdma_get_gdm_port(struct airoha_eth *eth,
 
 	sport = FIELD_GET(QDMA_ETH_RXMSG_SPORT_MASK, msg1);
 	switch (sport) {
-	case 0x10 ... 0x13:
+	case 0x10 ... 0x14:
 		port = 0;
 		break;
 	case 0x2 ... 0x4:
@@ -1487,53 +629,93 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 	while (done < budget) {
 		struct airoha_queue_entry *e = &q->entry[q->tail];
 		struct airoha_qdma_desc *desc = &q->desc[q->tail];
-		dma_addr_t dma_addr = le32_to_cpu(desc->addr);
+		u32 hash, reason, msg1 = le32_to_cpu(desc->msg1);
+		struct page *page = virt_to_head_page(e->buf);
 		u32 desc_ctrl = le32_to_cpu(desc->ctrl);
-		struct sk_buff *skb;
-		int len, p;
+		struct airoha_gdm_port *port;
+		int data_len, len, p;
 
 		if (!(desc_ctrl & QDMA_DESC_DONE_MASK))
 			break;
 
-		if (!dma_addr)
-			break;
-
-		len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
-		if (!len)
-			break;
-
 		q->tail = (q->tail + 1) % q->ndesc;
 		q->queued--;
 
-		dma_sync_single_for_cpu(eth->dev, dma_addr,
+		dma_sync_single_for_cpu(eth->dev, e->dma_addr,
 					SKB_WITH_OVERHEAD(q->buf_size), dir);
 
+		len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
+		data_len = q->skb ? q->buf_size
+				  : SKB_WITH_OVERHEAD(q->buf_size);
+		if (!len || data_len < len)
+			goto free_frag;
+
 		p = airoha_qdma_get_gdm_port(eth, desc);
-		if (p < 0 || !eth->ports[p]) {
-			page_pool_put_full_page(q->page_pool,
-						virt_to_head_page(e->buf),
-						true);
-			continue;
+		if (p < 0 || !eth->ports[p])
+			goto free_frag;
+
+		port = eth->ports[p];
+		if (!q->skb) { /* first buffer */
+			q->skb = napi_build_skb(e->buf, q->buf_size);
+			if (!q->skb)
+				goto free_frag;
+
+			__skb_put(q->skb, len);
+			skb_mark_for_recycle(q->skb);
+			q->skb->dev = port->dev;
+			q->skb->protocol = eth_type_trans(q->skb, port->dev);
+			q->skb->ip_summed = CHECKSUM_UNNECESSARY;
+			skb_record_rx_queue(q->skb, qid);
+		} else { /* scattered frame */
+			struct skb_shared_info *shinfo = skb_shinfo(q->skb);
+			int nr_frags = shinfo->nr_frags;
+
+			if (nr_frags >= ARRAY_SIZE(shinfo->frags))
+				goto free_frag;
+
+			skb_add_rx_frag(q->skb, nr_frags, page,
+					e->buf - page_address(page), len,
+					q->buf_size);
 		}
 
-		skb = napi_build_skb(e->buf, q->buf_size);
-		if (!skb) {
-			page_pool_put_full_page(q->page_pool,
-						virt_to_head_page(e->buf),
-						true);
-			break;
+		if (FIELD_GET(QDMA_DESC_MORE_MASK, desc_ctrl))
+			continue;
+
+		if (netdev_uses_dsa(port->dev)) {
+			/* PPE module requires untagged packets to work
+			 * properly and it provides DSA port index via the
+			 * DMA descriptor. Report DSA tag to the DSA stack
+			 * via skb dst info.
+			 */
+			u32 sptag = FIELD_GET(QDMA_ETH_RXMSG_SPTAG,
+					      le32_to_cpu(desc->msg0));
+
+			if (sptag < ARRAY_SIZE(port->dsa_meta) &&
+			    port->dsa_meta[sptag])
+				skb_dst_set_noref(q->skb,
+						  &port->dsa_meta[sptag]->dst);
 		}
 
-		skb_reserve(skb, 2);
-		__skb_put(skb, len);
-		skb_mark_for_recycle(skb);
-		skb->dev = eth->ports[p]->dev;
-		skb->protocol = eth_type_trans(skb, skb->dev);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		skb_record_rx_queue(skb, qid);
-		napi_gro_receive(&q->napi, skb);
+		hash = FIELD_GET(AIROHA_RXD4_FOE_ENTRY, msg1);
+		if (hash != AIROHA_RXD4_FOE_ENTRY)
+			skb_set_hash(q->skb, jhash_1word(hash, 0),
+				     PKT_HASH_TYPE_L4);
+
+		reason = FIELD_GET(AIROHA_RXD4_PPE_CPU_REASON, msg1);
+		if (reason == PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
+			airoha_ppe_check_skb(eth->ppe, q->skb, hash);
 
 		done++;
+		napi_gro_receive(&q->napi, q->skb);
+		q->skb = NULL;
+		continue;
+free_frag:
+		if (q->skb) {
+			dev_kfree_skb(q->skb);
+			q->skb = NULL;
+		} else {
+			page_pool_put_full_page(q->page_pool, page, true);
+		}
 	}
 	airoha_qdma_fill_rx_queue(q);
 
@@ -1550,9 +732,20 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
 		done += cur;
 	} while (cur && done < budget);
 
-	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(q->qdma, QDMA_INT_REG_IDX1,
-				       RX_DONE_INT_MASK);
+	if (done < budget && napi_complete(napi)) {
+		struct airoha_qdma *qdma = q->qdma;
+		int i, qid = q - &qdma->q_rx[0];
+		int intr_reg = qid < RX_DONE_HIGH_OFFSET ? QDMA_INT_REG_IDX1
+							 : QDMA_INT_REG_IDX2;
+
+		for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+			if (!(BIT(qid) & RX_IRQ_BANK_PIN_MASK(i)))
+				continue;
+
+			airoha_qdma_irq_enable(&qdma->irq_banks[i], intr_reg,
+					       BIT(qid % RX_DONE_HIGH_OFFSET));
+		}
+	}
 
 	return done;
 }
@@ -1608,6 +801,7 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q,
 			FIELD_PREP(RX_RING_THR_MASK, thr));
 	airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK,
 			FIELD_PREP(RX_RING_DMA_IDX_MASK, q->head));
+	airoha_qdma_set(qdma, REG_RX_SCATTER_CFG(qid), RX_RING_SG_EN_MASK);
 
 	airoha_qdma_fill_rx_queue(q);
 
@@ -1754,7 +948,7 @@ unlock:
 	}
 
 	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0,
+		airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX0,
 				       TX_DONE_INT_MASK(id));
 
 	return done;
@@ -1789,6 +983,10 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q,
 		WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val));
 	}
 
+	/* xmit ring drop default setting */
+	airoha_qdma_set(qdma, REG_TX_RING_BLOCKING(qid),
+			TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK);
+
 	airoha_qdma_wr(qdma, REG_TX_RING_BASE(qid), dma_addr);
 	airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK,
 			FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head));
@@ -1867,37 +1065,64 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
 
 static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 {
+	int size, index, num_desc = HW_DSCP_NUM;
 	struct airoha_eth *eth = qdma->eth;
+	int id = qdma - &eth->qdma[0];
+	u32 status, buf_size;
 	dma_addr_t dma_addr;
-	u32 status;
-	int size;
+	const char *name;
 
-	size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc);
-	qdma->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr,
-					      GFP_KERNEL);
-	if (!qdma->hfwd.desc)
+	name = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d-buf", id);
+	if (!name)
 		return -ENOMEM;
 
-	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
+	buf_size = id ? AIROHA_MAX_PACKET_SIZE / 2 : AIROHA_MAX_PACKET_SIZE;
+	index = of_property_match_string(eth->dev->of_node,
+					 "memory-region-names", name);
+	if (index >= 0) {
+		struct reserved_mem *rmem;
+		struct device_node *np;
 
-	size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
-	qdma->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr,
-					   GFP_KERNEL);
-	if (!qdma->hfwd.q)
-		return -ENOMEM;
+		/* Consume reserved memory for hw forwarding buffers queue if
+		 * available in the DTS
+		 */
+		np = of_parse_phandle(eth->dev->of_node, "memory-region",
+				      index);
+		if (!np)
+			return -ENODEV;
+
+		rmem = of_reserved_mem_lookup(np);
+		of_node_put(np);
+		dma_addr = rmem->base;
+		/* Compute the number of hw descriptors according to the
+		 * reserved memory size and the payload buffer size
+		 */
+		num_desc = div_u64(rmem->size, buf_size);
+	} else {
+		size = buf_size * num_desc;
+		if (!dmam_alloc_coherent(eth->dev, size, &dma_addr,
+					 GFP_KERNEL))
+			return -ENOMEM;
+	}
 
 	airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr);
 
+	size = num_desc * sizeof(struct airoha_qdma_fwd_desc);
+	if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
+		return -ENOMEM;
+
+	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
+	/* QDMA0: 2KB. QDMA1: 1KB */
 	airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG,
 			HW_FWD_DSCP_PAYLOAD_SIZE_MASK,
-			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0));
+			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, !!id));
 	airoha_qdma_rmw(qdma, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK,
 			FIELD_PREP(FWD_DSCP_LOW_THR_MASK, 128));
 	airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG,
 			LMGR_INIT_START | LMGR_SRAM_MODE_MASK |
 			HW_FWD_DESC_NUM_MASK,
-			FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) |
-			LMGR_INIT_START);
+			FIELD_PREP(HW_FWD_DESC_NUM_MASK, num_desc) |
+			LMGR_INIT_START | LMGR_SRAM_MODE_MASK);
 
 	return read_poll_timeout(airoha_qdma_rr, status,
 				 !(status & LMGR_INIT_START), USEC_PER_MSEC,
@@ -1955,18 +1180,49 @@ static void airoha_qdma_init_qos(struct airoha_qdma *qdma)
 			FIELD_PREP(SLA_SLOW_TICK_RATIO_MASK, 40));
 }
 
+static void airoha_qdma_init_qos_stats(struct airoha_qdma *qdma)
+{
+	int i;
+
+	for (i = 0; i < AIROHA_NUM_QOS_CHANNELS; i++) {
+		/* Tx-cpu transferred count */
+		airoha_qdma_wr(qdma, REG_CNTR_VAL(i << 1), 0);
+		airoha_qdma_wr(qdma, REG_CNTR_CFG(i << 1),
+			       CNTR_EN_MASK | CNTR_ALL_QUEUE_EN_MASK |
+			       CNTR_ALL_DSCP_RING_EN_MASK |
+			       FIELD_PREP(CNTR_CHAN_MASK, i));
+		/* Tx-fwd transferred count */
+		airoha_qdma_wr(qdma, REG_CNTR_VAL((i << 1) + 1), 0);
+		airoha_qdma_wr(qdma, REG_CNTR_CFG(i << 1),
+			       CNTR_EN_MASK | CNTR_ALL_QUEUE_EN_MASK |
+			       CNTR_ALL_DSCP_RING_EN_MASK |
+			       FIELD_PREP(CNTR_SRC_MASK, 1) |
+			       FIELD_PREP(CNTR_CHAN_MASK, i));
+	}
+}
+
 static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 {
 	int i;
 
-	/* clear pending irqs */
-	for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++)
+	for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+		/* clear pending irqs */
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), 0xffffffff);
-
-	/* setup irqs */
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0, INT_IDX0_MASK);
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX1, INT_IDX1_MASK);
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX4, INT_IDX4_MASK);
+		/* setup rx irqs */
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX0,
+				       INT_RX0_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX1,
+				       INT_RX1_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX2,
+				       INT_RX2_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX3,
+				       INT_RX3_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+	}
+	/* setup tx irqs */
+	airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX0,
+			       TX_COHERENT_LOW_INT_MASK | INT_TX_MASK);
+	airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX4,
+			       TX_COHERENT_HIGH_INT_MASK);
 
 	/* setup irq binding */
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
@@ -1982,7 +1238,6 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 	}
 
 	airoha_qdma_wr(qdma, REG_QDMA_GLOBAL_CFG,
-		       GLOBAL_CFG_RX_2B_OFFSET_MASK |
 		       FIELD_PREP(GLOBAL_CFG_DMA_PREFERENCE_MASK, 3) |
 		       GLOBAL_CFG_CPU_TXR_RR_MASK |
 		       GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK |
@@ -2005,36 +1260,46 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 
 	airoha_qdma_set(qdma, REG_TXQ_CNGST_CFG,
 			TXQ_CNGST_DROP_EN | TXQ_CNGST_DEI_DROP_EN);
+	airoha_qdma_init_qos_stats(qdma);
 
 	return 0;
 }
 
 static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 {
-	struct airoha_qdma *qdma = dev_instance;
-	u32 intr[ARRAY_SIZE(qdma->irqmask)];
+	struct airoha_irq_bank *irq_bank = dev_instance;
+	struct airoha_qdma *qdma = irq_bank->qdma;
+	u32 rx_intr_mask = 0, rx_intr1, rx_intr2;
+	u32 intr[ARRAY_SIZE(irq_bank->irqmask)];
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++) {
+	for (i = 0; i < ARRAY_SIZE(intr); i++) {
 		intr[i] = airoha_qdma_rr(qdma, REG_INT_STATUS(i));
-		intr[i] &= qdma->irqmask[i];
+		intr[i] &= irq_bank->irqmask[i];
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), intr[i]);
 	}
 
 	if (!test_bit(DEV_STATE_INITIALIZED, &qdma->eth->state))
 		return IRQ_NONE;
 
-	if (intr[1] & RX_DONE_INT_MASK) {
-		airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX1,
-					RX_DONE_INT_MASK);
+	rx_intr1 = intr[1] & RX_DONE_LOW_INT_MASK;
+	if (rx_intr1) {
+		airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX1, rx_intr1);
+		rx_intr_mask |= rx_intr1;
+	}
 
-		for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
-			if (!qdma->q_rx[i].ndesc)
-				continue;
+	rx_intr2 = intr[2] & RX_DONE_HIGH_INT_MASK;
+	if (rx_intr2) {
+		airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX2, rx_intr2);
+		rx_intr_mask |= (rx_intr2 << 16);
+	}
 
-			if (intr[1] & BIT(i))
-				napi_schedule(&qdma->q_rx[i].napi);
-		}
+	for (i = 0; rx_intr_mask && i < ARRAY_SIZE(qdma->q_rx); i++) {
+		if (!qdma->q_rx[i].ndesc)
+			continue;
+
+		if (rx_intr_mask & BIT(i))
+			napi_schedule(&qdma->q_rx[i].napi);
 	}
 
 	if (intr[0] & INT_TX_MASK) {
@@ -2042,7 +1307,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 			if (!(intr[0] & TX_DONE_INT_MASK(i)))
 				continue;
 
-			airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX0,
+			airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX0,
 						TX_DONE_INT_MASK(i));
 			napi_schedule(&qdma->q_tx_irq[i].napi);
 		}
@@ -2051,6 +1316,39 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 	return IRQ_HANDLED;
 }
 
+static int airoha_qdma_init_irq_banks(struct platform_device *pdev,
+				      struct airoha_qdma *qdma)
+{
+	struct airoha_eth *eth = qdma->eth;
+	int i, id = qdma - &eth->qdma[0];
+
+	for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+		struct airoha_irq_bank *irq_bank = &qdma->irq_banks[i];
+		int err, irq_index = 4 * id + i;
+		const char *name;
+
+		spin_lock_init(&irq_bank->irq_lock);
+		irq_bank->qdma = qdma;
+
+		irq_bank->irq = platform_get_irq(pdev, irq_index);
+		if (irq_bank->irq < 0)
+			return irq_bank->irq;
+
+		name = devm_kasprintf(eth->dev, GFP_KERNEL,
+				      KBUILD_MODNAME ".%d", irq_index);
+		if (!name)
+			return -ENOMEM;
+
+		err = devm_request_irq(eth->dev, irq_bank->irq,
+				       airoha_irq_handler, IRQF_SHARED, name,
+				       irq_bank);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int airoha_qdma_init(struct platform_device *pdev,
 			    struct airoha_eth *eth,
 			    struct airoha_qdma *qdma)
@@ -2058,9 +1356,7 @@ static int airoha_qdma_init(struct platform_device *pdev,
 	int err, id = qdma - &eth->qdma[0];
 	const char *res;
 
-	spin_lock_init(&qdma->irq_lock);
 	qdma->eth = eth;
-
 	res = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d", id);
 	if (!res)
 		return -ENOMEM;
@@ -2070,12 +1366,7 @@ static int airoha_qdma_init(struct platform_device *pdev,
 		return dev_err_probe(eth->dev, PTR_ERR(qdma->regs),
 				     "failed to iomap qdma%d regs\n", id);
 
-	qdma->irq = platform_get_irq(pdev, 4 * id);
-	if (qdma->irq < 0)
-		return qdma->irq;
-
-	err = devm_request_irq(eth->dev, qdma->irq, airoha_irq_handler,
-			       IRQF_SHARED, KBUILD_MODNAME, qdma);
+	err = airoha_qdma_init_irq_banks(pdev, qdma);
 	if (err)
 		return err;
 
@@ -2125,6 +1416,10 @@ static int airoha_hw_init(struct platform_device *pdev,
 			return err;
 	}
 
+	err = airoha_ppe_init(eth);
+	if (err)
+		return err;
+
 	set_bit(DEV_STATE_INITIALIZED, &eth->state);
 
 	return 0;
@@ -2138,17 +1433,14 @@ static void airoha_hw_cleanup(struct airoha_qdma *qdma)
 		if (!qdma->q_rx[i].ndesc)
 			continue;
 
-		napi_disable(&qdma->q_rx[i].napi);
 		netif_napi_del(&qdma->q_rx[i].napi);
 		airoha_qdma_cleanup_rx_queue(&qdma->q_rx[i]);
 		if (qdma->q_rx[i].page_pool)
 			page_pool_destroy(qdma->q_rx[i].page_pool);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) {
-		napi_disable(&qdma->q_tx_irq[i].napi);
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++)
 		netif_napi_del(&qdma->q_tx_irq[i].napi);
-	}
 
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
 		if (!qdma->q_tx[i].ndesc)
@@ -2173,6 +1465,21 @@ static void airoha_qdma_start_napi(struct airoha_qdma *qdma)
 	}
 }
 
+static void airoha_qdma_stop_napi(struct airoha_qdma *qdma)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++)
+		napi_disable(&qdma->q_tx_irq[i].napi);
+
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+		if (!qdma->q_rx[i].ndesc)
+			continue;
+
+		napi_disable(&qdma->q_rx[i].napi);
+	}
+}
+
 static void airoha_update_hw_stats(struct airoha_gdm_port *port)
 {
 	struct airoha_eth *eth = port->qdma->eth;
@@ -2319,12 +1626,12 @@ static void airoha_update_hw_stats(struct airoha_gdm_port *port)
 
 static int airoha_dev_open(struct net_device *dev)
 {
+	int err, len = ETH_HLEN + dev->mtu + ETH_FCS_LEN;
 	struct airoha_gdm_port *port = netdev_priv(dev);
 	struct airoha_qdma *qdma = port->qdma;
-	int err;
 
 	netif_tx_start_all_queues(dev);
-	err = airoha_set_gdm_ports(qdma->eth, true);
+	err = airoha_set_vip_for_gdm_port(port, true);
 	if (err)
 		return err;
 
@@ -2335,9 +1642,15 @@ static int airoha_dev_open(struct net_device *dev)
 		airoha_fe_clear(qdma->eth, REG_GDM_INGRESS_CFG(port->id),
 				GDM_STAG_EN_MASK);
 
+	airoha_fe_rmw(qdma->eth, REG_GDM_LEN_CFG(port->id),
+		      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
+		      FIELD_PREP(GDM_LONG_LEN_MASK, len));
+
 	airoha_qdma_set(qdma, REG_QDMA_GLOBAL_CFG,
 			GLOBAL_CFG_TX_DMA_EN_MASK |
 			GLOBAL_CFG_RX_DMA_EN_MASK);
+	atomic_inc(&qdma->users);
 
 	return 0;
 }
@@ -2349,20 +1662,24 @@ static int airoha_dev_stop(struct net_device *dev)
 	int i, err;
 
 	netif_tx_disable(dev);
-	err = airoha_set_gdm_ports(qdma->eth, false);
+	err = airoha_set_vip_for_gdm_port(port, false);
 	if (err)
 		return err;
 
-	airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG,
-			  GLOBAL_CFG_TX_DMA_EN_MASK |
-			  GLOBAL_CFG_RX_DMA_EN_MASK);
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++)
+		netdev_tx_reset_subqueue(dev, i);
 
-	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
-		if (!qdma->q_tx[i].ndesc)
-			continue;
+	if (atomic_dec_and_test(&qdma->users)) {
+		airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG,
+				  GLOBAL_CFG_TX_DMA_EN_MASK |
+				  GLOBAL_CFG_RX_DMA_EN_MASK);
 
-		airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]);
-		netdev_tx_reset_subqueue(dev, i);
+		for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
+			if (!qdma->q_tx[i].ndesc)
+				continue;
+
+			airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]);
+		}
 	}
 
 	return 0;
@@ -2382,12 +1699,81 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p)
 	return 0;
 }
 
+static void airhoha_set_gdm2_loopback(struct airoha_gdm_port *port)
+{
+	u32 pse_port = port->id == 3 ? FE_PSE_PORT_GDM3 : FE_PSE_PORT_GDM4;
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 chan = port->id == 3 ? 4 : 0;
+
+	/* Forward the traffic to the proper GDM port */
+	airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(2), pse_port);
+	airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC);
+
+	/* Enable GDM2 loopback */
+	airoha_fe_wr(eth, REG_GDM_TXCHN_EN(2), 0xffffffff);
+	airoha_fe_wr(eth, REG_GDM_RXCHN_EN(2), 0xffff);
+	airoha_fe_rmw(eth, REG_GDM_LPBK_CFG(2),
+		      LPBK_CHAN_MASK | LPBK_MODE_MASK | LPBK_EN_MASK,
+		      FIELD_PREP(LPBK_CHAN_MASK, chan) | LPBK_EN_MASK);
+	airoha_fe_rmw(eth, REG_GDM_LEN_CFG(2),
+		      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
+		      FIELD_PREP(GDM_LONG_LEN_MASK, AIROHA_MAX_MTU));
+
+	/* Disable VIP and IFC for GDM2 */
+	airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(2));
+	airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(2));
+
+	if (port->id == 3) {
+		/* FIXME: handle XSI_PCE1_PORT */
+		airoha_fe_rmw(eth, REG_FE_WAN_PORT,
+			      WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
+			      FIELD_PREP(WAN0_MASK, HSGMII_LAN_PCIE0_SRCPORT));
+		airoha_fe_rmw(eth,
+			      REG_SP_DFT_CPORT(HSGMII_LAN_PCIE0_SRCPORT >> 3),
+			      SP_CPORT_PCIE0_MASK,
+			      FIELD_PREP(SP_CPORT_PCIE0_MASK,
+					 FE_PSE_PORT_CDM2));
+	} else {
+		/* FIXME: handle XSI_USB_PORT */
+		airoha_fe_rmw(eth, REG_SRC_PORT_FC_MAP6,
+			      FC_ID_OF_SRC_PORT24_MASK,
+			      FIELD_PREP(FC_ID_OF_SRC_PORT24_MASK, 2));
+		airoha_fe_rmw(eth, REG_FE_WAN_PORT,
+			      WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
+			      FIELD_PREP(WAN0_MASK, HSGMII_LAN_ETH_SRCPORT));
+		airoha_fe_rmw(eth,
+			      REG_SP_DFT_CPORT(HSGMII_LAN_ETH_SRCPORT >> 3),
+			      SP_CPORT_ETH_MASK,
+			      FIELD_PREP(SP_CPORT_ETH_MASK, FE_PSE_PORT_CDM2));
+	}
+}
+
 static int airoha_dev_init(struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 pse_port;
 
 	airoha_set_macaddr(port, dev->dev_addr);
 
+	switch (port->id) {
+	case 3:
+	case 4:
+		/* If GDM2 is active we can't enable loopback */
+		if (!eth->ports[1])
+			airhoha_set_gdm2_loopback(port);
+		fallthrough;
+	case 2:
+		pse_port = FE_PSE_PORT_PPE2;
+		break;
+	default:
+		pse_port = FE_PSE_PORT_PPE1;
+		break;
+	}
+
+	airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(port->id), pse_port);
+
 	return 0;
 }
 
@@ -2413,21 +1799,103 @@ static void airoha_dev_get_stats64(struct net_device *dev,
 	} while (u64_stats_fetch_retry(&port->stats.syncp, start));
 }
 
+static int airoha_dev_change_mtu(struct net_device *dev, int mtu)
+{
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 len = ETH_HLEN + mtu + ETH_FCS_LEN;
+
+	airoha_fe_rmw(eth, REG_GDM_LEN_CFG(port->id),
+		      GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_LONG_LEN_MASK, len));
+	WRITE_ONCE(dev->mtu, mtu);
+
+	return 0;
+}
+
+static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb,
+				   struct net_device *sb_dev)
+{
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	int queue, channel;
+
+	/* For dsa device select QoS channel according to the dsa user port
+	 * index, rely on port id otherwise. Select QoS queue based on the
+	 * skb priority.
+	 */
+	channel = netdev_uses_dsa(dev) ? skb_get_queue_mapping(skb) : port->id;
+	channel = channel % AIROHA_NUM_QOS_CHANNELS;
+	queue = (skb->priority - 1) % AIROHA_NUM_QOS_QUEUES; /* QoS queue */
+	queue = channel * AIROHA_NUM_QOS_QUEUES + queue;
+
+	return queue < dev->num_tx_queues ? queue : 0;
+}
+
+static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	struct ethhdr *ehdr;
+	u8 xmit_tpid;
+	u16 tag;
+
+	if (!netdev_uses_dsa(dev))
+		return 0;
+
+	if (dev->dsa_ptr->tag_ops->proto != DSA_TAG_PROTO_MTK)
+		return 0;
+
+	if (skb_cow_head(skb, 0))
+		return 0;
+
+	ehdr = (struct ethhdr *)skb->data;
+	tag = be16_to_cpu(ehdr->h_proto);
+	xmit_tpid = tag >> 8;
+
+	switch (xmit_tpid) {
+	case MTK_HDR_XMIT_TAGGED_TPID_8100:
+		ehdr->h_proto = cpu_to_be16(ETH_P_8021Q);
+		tag &= ~(MTK_HDR_XMIT_TAGGED_TPID_8100 << 8);
+		break;
+	case MTK_HDR_XMIT_TAGGED_TPID_88A8:
+		ehdr->h_proto = cpu_to_be16(ETH_P_8021AD);
+		tag &= ~(MTK_HDR_XMIT_TAGGED_TPID_88A8 << 8);
+		break;
+	default:
+		/* PPE module requires untagged DSA packets to work properly,
+		 * so move DSA tag to DMA descriptor.
+		 */
+		memmove(skb->data + MTK_HDR_LEN, skb->data, 2 * ETH_ALEN);
+		__skb_pull(skb, MTK_HDR_LEN);
+		break;
+	}
+
+	return tag;
+#else
+	return 0;
+#endif
+}
+
 static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
-	struct skb_shared_info *sinfo = skb_shinfo(skb);
 	struct airoha_gdm_port *port = netdev_priv(dev);
-	u32 msg0 = 0, msg1, len = skb_headlen(skb);
-	int i, qid = skb_get_queue_mapping(skb);
 	struct airoha_qdma *qdma = port->qdma;
-	u32 nr_frags = 1 + sinfo->nr_frags;
+	u32 nr_frags, tag, msg0, msg1, len;
 	struct netdev_queue *txq;
 	struct airoha_queue *q;
-	void *data = skb->data;
+	void *data;
+	int i, qid;
 	u16 index;
 	u8 fport;
 
+	qid = skb_get_queue_mapping(skb) % ARRAY_SIZE(qdma->q_tx);
+	tag = airoha_get_dsa_tag(skb, dev);
+
+	msg0 = FIELD_PREP(QDMA_ETH_TXMSG_CHAN_MASK,
+			  qid / AIROHA_NUM_QOS_QUEUES) |
+	       FIELD_PREP(QDMA_ETH_TXMSG_QUEUE_MASK,
+			  qid % AIROHA_NUM_QOS_QUEUES) |
+	       FIELD_PREP(QDMA_ETH_TXMSG_SP_TAG_MASK, tag);
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		msg0 |= FIELD_PREP(QDMA_ETH_TXMSG_TCO_MASK, 1) |
 			FIELD_PREP(QDMA_ETH_TXMSG_UCO_MASK, 1) |
@@ -2438,8 +1906,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 		if (skb_cow_head(skb, 0))
 			goto error;
 
-		if (sinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
-			__be16 csum = cpu_to_be16(sinfo->gso_size);
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 |
+						 SKB_GSO_TCPV6)) {
+			__be16 csum = cpu_to_be16(skb_shinfo(skb)->gso_size);
 
 			tcp_hdr(skb)->check = (__force __sum16)csum;
 			msg0 |= FIELD_PREP(QDMA_ETH_TXMSG_TSO_MASK, 1);
@@ -2457,6 +1926,8 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	spin_lock_bh(&q->lock);
 
 	txq = netdev_get_tx_queue(dev, qid);
+	nr_frags = 1 + skb_shinfo(skb)->nr_frags;
+
 	if (q->queued + nr_frags > q->ndesc) {
 		/* not enough space in the queue */
 		netif_tx_stop_queue(txq);
@@ -2464,11 +1935,14 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
+	len = skb_headlen(skb);
+	data = skb->data;
 	index = q->head;
+
 	for (i = 0; i < nr_frags; i++) {
 		struct airoha_qdma_desc *desc = &q->desc[index];
 		struct airoha_queue_entry *e = &q->entry[index];
-		skb_frag_t *frag = &sinfo->frags[i];
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		dma_addr_t addr;
 		u32 val;
 
@@ -2597,13 +2071,695 @@ airoha_ethtool_get_rmon_stats(struct net_device *dev,
 	} while (u64_stats_fetch_retry(&port->stats.syncp, start));
 }
 
+static int airoha_qdma_set_chan_tx_sched(struct airoha_gdm_port *port,
+					 int channel, enum tx_sched_mode mode,
+					 const u16 *weights, u8 n_weights)
+{
+	int i;
+
+	for (i = 0; i < AIROHA_NUM_TX_RING; i++)
+		airoha_qdma_clear(port->qdma, REG_QUEUE_CLOSE_CFG(channel),
+				  TXQ_DISABLE_CHAN_QUEUE_MASK(channel, i));
+
+	for (i = 0; i < n_weights; i++) {
+		u32 status;
+		int err;
+
+		airoha_qdma_wr(port->qdma, REG_TXWRR_WEIGHT_CFG,
+			       TWRR_RW_CMD_MASK |
+			       FIELD_PREP(TWRR_CHAN_IDX_MASK, channel) |
+			       FIELD_PREP(TWRR_QUEUE_IDX_MASK, i) |
+			       FIELD_PREP(TWRR_VALUE_MASK, weights[i]));
+		err = read_poll_timeout(airoha_qdma_rr, status,
+					status & TWRR_RW_CMD_DONE,
+					USEC_PER_MSEC, 10 * USEC_PER_MSEC,
+					true, port->qdma,
+					REG_TXWRR_WEIGHT_CFG);
+		if (err)
+			return err;
+	}
+
+	airoha_qdma_rmw(port->qdma, REG_CHAN_QOS_MODE(channel >> 3),
+			CHAN_QOS_MODE_MASK(channel),
+			mode << __ffs(CHAN_QOS_MODE_MASK(channel)));
+
+	return 0;
+}
+
+static int airoha_qdma_set_tx_prio_sched(struct airoha_gdm_port *port,
+					 int channel)
+{
+	static const u16 w[AIROHA_NUM_QOS_QUEUES] = {};
+
+	return airoha_qdma_set_chan_tx_sched(port, channel, TC_SCH_SP, w,
+					     ARRAY_SIZE(w));
+}
+
+static int airoha_qdma_set_tx_ets_sched(struct airoha_gdm_port *port,
+					int channel,
+					struct tc_ets_qopt_offload *opt)
+{
+	struct tc_ets_qopt_offload_replace_params *p = &opt->replace_params;
+	enum tx_sched_mode mode = TC_SCH_SP;
+	u16 w[AIROHA_NUM_QOS_QUEUES] = {};
+	int i, nstrict = 0;
+
+	if (p->bands > AIROHA_NUM_QOS_QUEUES)
+		return -EINVAL;
+
+	for (i = 0; i < p->bands; i++) {
+		if (!p->quanta[i])
+			nstrict++;
+	}
+
+	/* this configuration is not supported by the hw */
+	if (nstrict == AIROHA_NUM_QOS_QUEUES - 1)
+		return -EINVAL;
+
+	/* EN7581 SoC supports fixed QoS band priority where WRR queues have
+	 * lowest priorities with respect to SP ones.
+	 * e.g: WRR0, WRR1, .., WRRm, SP0, SP1, .., SPn
+	 */
+	for (i = 0; i < nstrict; i++) {
+		if (p->priomap[p->bands - i - 1] != i)
+			return -EINVAL;
+	}
+
+	for (i = 0; i < p->bands - nstrict; i++) {
+		if (p->priomap[i] != nstrict + i)
+			return -EINVAL;
+
+		w[i] = p->weights[nstrict + i];
+	}
+
+	if (!nstrict)
+		mode = TC_SCH_WRR8;
+	else if (nstrict < AIROHA_NUM_QOS_QUEUES - 1)
+		mode = nstrict + 1;
+
+	return airoha_qdma_set_chan_tx_sched(port, channel, mode, w,
+					     ARRAY_SIZE(w));
+}
+
+static int airoha_qdma_get_tx_ets_stats(struct airoha_gdm_port *port,
+					int channel,
+					struct tc_ets_qopt_offload *opt)
+{
+	u64 cpu_tx_packets = airoha_qdma_rr(port->qdma,
+					    REG_CNTR_VAL(channel << 1));
+	u64 fwd_tx_packets = airoha_qdma_rr(port->qdma,
+					    REG_CNTR_VAL((channel << 1) + 1));
+	u64 tx_packets = (cpu_tx_packets - port->cpu_tx_packets) +
+			 (fwd_tx_packets - port->fwd_tx_packets);
+	_bstats_update(opt->stats.bstats, 0, tx_packets);
+
+	port->cpu_tx_packets = cpu_tx_packets;
+	port->fwd_tx_packets = fwd_tx_packets;
+
+	return 0;
+}
+
+static int airoha_tc_setup_qdisc_ets(struct airoha_gdm_port *port,
+				     struct tc_ets_qopt_offload *opt)
+{
+	int channel;
+
+	if (opt->parent == TC_H_ROOT)
+		return -EINVAL;
+
+	channel = TC_H_MAJ(opt->handle) >> 16;
+	channel = channel % AIROHA_NUM_QOS_CHANNELS;
+
+	switch (opt->command) {
+	case TC_ETS_REPLACE:
+		return airoha_qdma_set_tx_ets_sched(port, channel, opt);
+	case TC_ETS_DESTROY:
+		/* PRIO is default qdisc scheduler */
+		return airoha_qdma_set_tx_prio_sched(port, channel);
+	case TC_ETS_STATS:
+		return airoha_qdma_get_tx_ets_stats(port, channel, opt);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int airoha_qdma_get_rl_param(struct airoha_qdma *qdma, int queue_id,
+				    u32 addr, enum trtcm_param_type param,
+				    u32 *val_low, u32 *val_high)
+{
+	u32 idx = QDMA_METER_IDX(queue_id), group = QDMA_METER_GROUP(queue_id);
+	u32 val, config = FIELD_PREP(RATE_LIMIT_PARAM_TYPE_MASK, param) |
+			  FIELD_PREP(RATE_LIMIT_METER_GROUP_MASK, group) |
+			  FIELD_PREP(RATE_LIMIT_PARAM_INDEX_MASK, idx);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+	if (read_poll_timeout(airoha_qdma_rr, val,
+			      val & RATE_LIMIT_PARAM_RW_DONE_MASK,
+			      USEC_PER_MSEC, 10 * USEC_PER_MSEC, true, qdma,
+			      REG_TRTCM_CFG_PARAM(addr)))
+		return -ETIMEDOUT;
+
+	*val_low = airoha_qdma_rr(qdma, REG_TRTCM_DATA_LOW(addr));
+	if (val_high)
+		*val_high = airoha_qdma_rr(qdma, REG_TRTCM_DATA_HIGH(addr));
+
+	return 0;
+}
+
+static int airoha_qdma_set_rl_param(struct airoha_qdma *qdma, int queue_id,
+				    u32 addr, enum trtcm_param_type param,
+				    u32 val)
+{
+	u32 idx = QDMA_METER_IDX(queue_id), group = QDMA_METER_GROUP(queue_id);
+	u32 config = RATE_LIMIT_PARAM_RW_MASK |
+		     FIELD_PREP(RATE_LIMIT_PARAM_TYPE_MASK, param) |
+		     FIELD_PREP(RATE_LIMIT_METER_GROUP_MASK, group) |
+		     FIELD_PREP(RATE_LIMIT_PARAM_INDEX_MASK, idx);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_DATA_LOW(addr), val);
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+
+	return read_poll_timeout(airoha_qdma_rr, val,
+				 val & RATE_LIMIT_PARAM_RW_DONE_MASK,
+				 USEC_PER_MSEC, 10 * USEC_PER_MSEC, true,
+				 qdma, REG_TRTCM_CFG_PARAM(addr));
+}
+
+static int airoha_qdma_set_rl_config(struct airoha_qdma *qdma, int queue_id,
+				     u32 addr, bool enable, u32 enable_mask)
+{
+	u32 val;
+	int err;
+
+	err = airoha_qdma_get_rl_param(qdma, queue_id, addr, TRTCM_MISC_MODE,
+				       &val, NULL);
+	if (err)
+		return err;
+
+	val = enable ? val | enable_mask : val & ~enable_mask;
+
+	return airoha_qdma_set_rl_param(qdma, queue_id, addr, TRTCM_MISC_MODE,
+					val);
+}
+
+static int airoha_qdma_set_rl_token_bucket(struct airoha_qdma *qdma,
+					   int queue_id, u32 rate_val,
+					   u32 bucket_size)
+{
+	u32 val, config, tick, unit, rate, rate_frac;
+	int err;
+
+	err = airoha_qdma_get_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+				       TRTCM_MISC_MODE, &config, NULL);
+	if (err)
+		return err;
+
+	val = airoha_qdma_rr(qdma, REG_INGRESS_TRTCM_CFG);
+	tick = FIELD_GET(INGRESS_FAST_TICK_MASK, val);
+	if (config & TRTCM_TICK_SEL)
+		tick *= FIELD_GET(INGRESS_SLOW_TICK_RATIO_MASK, val);
+	if (!tick)
+		return -EINVAL;
+
+	unit = (config & TRTCM_PKT_MODE) ? 1000000 / tick : 8000 / tick;
+	if (!unit)
+		return -EINVAL;
+
+	rate = rate_val / unit;
+	rate_frac = rate_val % unit;
+	rate_frac = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate_frac) / unit;
+	rate = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate) |
+	       FIELD_PREP(TRTCM_TOKEN_RATE_FRACTION_MASK, rate_frac);
+
+	err = airoha_qdma_set_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+				       TRTCM_TOKEN_RATE_MODE, rate);
+	if (err)
+		return err;
+
+	val = bucket_size;
+	if (!(config & TRTCM_PKT_MODE))
+		val = max_t(u32, val, MIN_TOKEN_SIZE);
+	val = min_t(u32, __fls(val), MAX_TOKEN_SIZE_OFFSET);
+
+	return airoha_qdma_set_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					TRTCM_BUCKETSIZE_SHIFT_MODE, val);
+}
+
+static int airoha_qdma_init_rl_config(struct airoha_qdma *qdma, int queue_id,
+				      bool enable, enum trtcm_unit_type unit)
+{
+	bool tick_sel = queue_id == 0 || queue_id == 2 || queue_id == 8;
+	enum trtcm_param mode = TRTCM_METER_MODE;
+	int err;
+
+	mode |= unit == TRTCM_PACKET_UNIT ? TRTCM_PKT_MODE : 0;
+	err = airoha_qdma_set_rl_config(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					enable, mode);
+	if (err)
+		return err;
+
+	return airoha_qdma_set_rl_config(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					 tick_sel, TRTCM_TICK_SEL);
+}
+
+static int airoha_qdma_get_trtcm_param(struct airoha_qdma *qdma, int channel,
+				       u32 addr, enum trtcm_param_type param,
+				       enum trtcm_mode_type mode,
+				       u32 *val_low, u32 *val_high)
+{
+	u32 idx = QDMA_METER_IDX(channel), group = QDMA_METER_GROUP(channel);
+	u32 val, config = FIELD_PREP(TRTCM_PARAM_TYPE_MASK, param) |
+			  FIELD_PREP(TRTCM_METER_GROUP_MASK, group) |
+			  FIELD_PREP(TRTCM_PARAM_INDEX_MASK, idx) |
+			  FIELD_PREP(TRTCM_PARAM_RATE_TYPE_MASK, mode);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+	if (read_poll_timeout(airoha_qdma_rr, val,
+			      val & TRTCM_PARAM_RW_DONE_MASK,
+			      USEC_PER_MSEC, 10 * USEC_PER_MSEC, true,
+			      qdma, REG_TRTCM_CFG_PARAM(addr)))
+		return -ETIMEDOUT;
+
+	*val_low = airoha_qdma_rr(qdma, REG_TRTCM_DATA_LOW(addr));
+	if (val_high)
+		*val_high = airoha_qdma_rr(qdma, REG_TRTCM_DATA_HIGH(addr));
+
+	return 0;
+}
+
+static int airoha_qdma_set_trtcm_param(struct airoha_qdma *qdma, int channel,
+				       u32 addr, enum trtcm_param_type param,
+				       enum trtcm_mode_type mode, u32 val)
+{
+	u32 idx = QDMA_METER_IDX(channel), group = QDMA_METER_GROUP(channel);
+	u32 config = TRTCM_PARAM_RW_MASK |
+		     FIELD_PREP(TRTCM_PARAM_TYPE_MASK, param) |
+		     FIELD_PREP(TRTCM_METER_GROUP_MASK, group) |
+		     FIELD_PREP(TRTCM_PARAM_INDEX_MASK, idx) |
+		     FIELD_PREP(TRTCM_PARAM_RATE_TYPE_MASK, mode);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_DATA_LOW(addr), val);
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+
+	return read_poll_timeout(airoha_qdma_rr, val,
+				 val & TRTCM_PARAM_RW_DONE_MASK,
+				 USEC_PER_MSEC, 10 * USEC_PER_MSEC, true,
+				 qdma, REG_TRTCM_CFG_PARAM(addr));
+}
+
+static int airoha_qdma_set_trtcm_config(struct airoha_qdma *qdma, int channel,
+					u32 addr, enum trtcm_mode_type mode,
+					bool enable, u32 enable_mask)
+{
+	u32 val;
+
+	if (airoha_qdma_get_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE,
+					mode, &val, NULL))
+		return -EINVAL;
+
+	val = enable ? val | enable_mask : val & ~enable_mask;
+
+	return airoha_qdma_set_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE,
+					   mode, val);
+}
+
+static int airoha_qdma_set_trtcm_token_bucket(struct airoha_qdma *qdma,
+					      int channel, u32 addr,
+					      enum trtcm_mode_type mode,
+					      u32 rate_val, u32 bucket_size)
+{
+	u32 val, config, tick, unit, rate, rate_frac;
+	int err;
+
+	if (airoha_qdma_get_trtcm_param(qdma, channel, addr, TRTCM_MISC_MODE,
+					mode, &config, NULL))
+		return -EINVAL;
+
+	val = airoha_qdma_rr(qdma, addr);
+	tick = FIELD_GET(INGRESS_FAST_TICK_MASK, val);
+	if (config & TRTCM_TICK_SEL)
+		tick *= FIELD_GET(INGRESS_SLOW_TICK_RATIO_MASK, val);
+	if (!tick)
+		return -EINVAL;
+
+	unit = (config & TRTCM_PKT_MODE) ? 1000000 / tick : 8000 / tick;
+	if (!unit)
+		return -EINVAL;
+
+	rate = rate_val / unit;
+	rate_frac = rate_val % unit;
+	rate_frac = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate_frac) / unit;
+	rate = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate) |
+	       FIELD_PREP(TRTCM_TOKEN_RATE_FRACTION_MASK, rate_frac);
+
+	err = airoha_qdma_set_trtcm_param(qdma, channel, addr,
+					  TRTCM_TOKEN_RATE_MODE, mode, rate);
+	if (err)
+		return err;
+
+	val = max_t(u32, bucket_size, MIN_TOKEN_SIZE);
+	val = min_t(u32, __fls(val), MAX_TOKEN_SIZE_OFFSET);
+
+	return airoha_qdma_set_trtcm_param(qdma, channel, addr,
+					   TRTCM_BUCKETSIZE_SHIFT_MODE,
+					   mode, val);
+}
+
+static int airoha_qdma_set_tx_rate_limit(struct airoha_gdm_port *port,
+					 int channel, u32 rate,
+					 u32 bucket_size)
+{
+	int i, err;
+
+	for (i = 0; i <= TRTCM_PEAK_MODE; i++) {
+		err = airoha_qdma_set_trtcm_config(port->qdma, channel,
+						   REG_EGRESS_TRTCM_CFG, i,
+						   !!rate, TRTCM_METER_MODE);
+		if (err)
+			return err;
+
+		err = airoha_qdma_set_trtcm_token_bucket(port->qdma, channel,
+							 REG_EGRESS_TRTCM_CFG,
+							 i, rate, bucket_size);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_tc_htb_alloc_leaf_queue(struct airoha_gdm_port *port,
+					  struct tc_htb_qopt_offload *opt)
+{
+	u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
+	u32 rate = div_u64(opt->rate, 1000) << 3; /* kbps */
+	struct net_device *dev = port->dev;
+	int num_tx_queues = dev->real_num_tx_queues;
+	int err;
+
+	if (opt->parent_classid != TC_HTB_CLASSID_ROOT) {
+		NL_SET_ERR_MSG_MOD(opt->extack, "invalid parent classid");
+		return -EINVAL;
+	}
+
+	err = airoha_qdma_set_tx_rate_limit(port, channel, rate, opt->quantum);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(opt->extack,
+				   "failed configuring htb offload");
+		return err;
+	}
+
+	if (opt->command == TC_HTB_NODE_MODIFY)
+		return 0;
+
+	err = netif_set_real_num_tx_queues(dev, num_tx_queues + 1);
+	if (err) {
+		airoha_qdma_set_tx_rate_limit(port, channel, 0, opt->quantum);
+		NL_SET_ERR_MSG_MOD(opt->extack,
+				   "failed setting real_num_tx_queues");
+		return err;
+	}
+
+	set_bit(channel, port->qos_sq_bmap);
+	opt->qid = AIROHA_NUM_TX_RING + channel;
+
+	return 0;
+}
+
+static int airoha_qdma_set_rx_meter(struct airoha_gdm_port *port,
+				    u32 rate, u32 bucket_size,
+				    enum trtcm_unit_type unit_type)
+{
+	struct airoha_qdma *qdma = port->qdma;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+		int err;
+
+		if (!qdma->q_rx[i].ndesc)
+			continue;
+
+		err = airoha_qdma_init_rl_config(qdma, i, !!rate, unit_type);
+		if (err)
+			return err;
+
+		err = airoha_qdma_set_rl_token_bucket(qdma, i, rate,
+						      bucket_size);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_tc_matchall_act_validate(struct tc_cls_matchall_offload *f)
+{
+	const struct flow_action *actions = &f->rule->action;
+	const struct flow_action_entry *act;
+
+	if (!flow_action_has_entries(actions)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "filter run with no actions");
+		return -EINVAL;
+	}
+
+	if (!flow_offload_has_one_action(actions)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "only once action per filter is supported");
+		return -EOPNOTSUPP;
+	}
+
+	act = &actions->entries[0];
+	if (act->id != FLOW_ACTION_POLICE) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "unsupported action");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.exceed.act_id != FLOW_ACTION_DROP) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "invalid exceed action id");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.notexceed.act_id != FLOW_ACTION_ACCEPT) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "invalid notexceed action id");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.notexceed.act_id == FLOW_ACTION_ACCEPT &&
+	    !flow_action_is_last_entry(actions, act)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "action accept must be last");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.peakrate_bytes_ps || act->police.avrate ||
+	    act->police.overhead || act->police.mtu) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "peakrate/avrate/overhead/mtu unsupported");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int airoha_dev_tc_matchall(struct net_device *dev,
+				  struct tc_cls_matchall_offload *f)
+{
+	enum trtcm_unit_type unit_type = TRTCM_BYTE_UNIT;
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	u32 rate = 0, bucket_size = 0;
+
+	switch (f->command) {
+	case TC_CLSMATCHALL_REPLACE: {
+		const struct flow_action_entry *act;
+		int err;
+
+		err = airoha_tc_matchall_act_validate(f);
+		if (err)
+			return err;
+
+		act = &f->rule->action.entries[0];
+		if (act->police.rate_pkt_ps) {
+			rate = act->police.rate_pkt_ps;
+			bucket_size = act->police.burst_pkt;
+			unit_type = TRTCM_PACKET_UNIT;
+		} else {
+			rate = div_u64(act->police.rate_bytes_ps, 1000);
+			rate = rate << 3; /* Kbps */
+			bucket_size = act->police.burst;
+		}
+		fallthrough;
+	}
+	case TC_CLSMATCHALL_DESTROY:
+		return airoha_qdma_set_rx_meter(port, rate, bucket_size,
+						unit_type);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int airoha_dev_setup_tc_block_cb(enum tc_setup_type type,
+					void *type_data, void *cb_priv)
+{
+	struct net_device *dev = cb_priv;
+
+	if (!tc_can_offload(dev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return airoha_ppe_setup_tc_block_cb(dev, type_data);
+	case TC_SETUP_CLSMATCHALL:
+		return airoha_dev_tc_matchall(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int airoha_dev_setup_tc_block(struct airoha_gdm_port *port,
+				     struct flow_block_offload *f)
+{
+	flow_setup_cb_t *cb = airoha_dev_setup_tc_block_cb;
+	static LIST_HEAD(block_cb_list);
+	struct flow_block_cb *block_cb;
+
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	f->driver_block_list = &block_cb_list;
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		block_cb = flow_block_cb_lookup(f->block, cb, port->dev);
+		if (block_cb) {
+			flow_block_cb_incref(block_cb);
+			return 0;
+		}
+		block_cb = flow_block_cb_alloc(cb, port->dev, port->dev, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		flow_block_cb_incref(block_cb);
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &block_cb_list);
+		return 0;
+	case FLOW_BLOCK_UNBIND:
+		block_cb = flow_block_cb_lookup(f->block, cb, port->dev);
+		if (!block_cb)
+			return -ENOENT;
+
+		if (!flow_block_cb_decref(block_cb)) {
+			flow_block_cb_remove(block_cb, f);
+			list_del(&block_cb->driver_list);
+		}
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void airoha_tc_remove_htb_queue(struct airoha_gdm_port *port, int queue)
+{
+	struct net_device *dev = port->dev;
+
+	netif_set_real_num_tx_queues(dev, dev->real_num_tx_queues - 1);
+	airoha_qdma_set_tx_rate_limit(port, queue + 1, 0, 0);
+	clear_bit(queue, port->qos_sq_bmap);
+}
+
+static int airoha_tc_htb_delete_leaf_queue(struct airoha_gdm_port *port,
+					   struct tc_htb_qopt_offload *opt)
+{
+	u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
+
+	if (!test_bit(channel, port->qos_sq_bmap)) {
+		NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id");
+		return -EINVAL;
+	}
+
+	airoha_tc_remove_htb_queue(port, channel);
+
+	return 0;
+}
+
+static int airoha_tc_htb_destroy(struct airoha_gdm_port *port)
+{
+	int q;
+
+	for_each_set_bit(q, port->qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS)
+		airoha_tc_remove_htb_queue(port, q);
+
+	return 0;
+}
+
+static int airoha_tc_get_htb_get_leaf_queue(struct airoha_gdm_port *port,
+					    struct tc_htb_qopt_offload *opt)
+{
+	u32 channel = TC_H_MIN(opt->classid) % AIROHA_NUM_QOS_CHANNELS;
+
+	if (!test_bit(channel, port->qos_sq_bmap)) {
+		NL_SET_ERR_MSG_MOD(opt->extack, "invalid queue id");
+		return -EINVAL;
+	}
+
+	opt->qid = AIROHA_NUM_TX_RING + channel;
+
+	return 0;
+}
+
+static int airoha_tc_setup_qdisc_htb(struct airoha_gdm_port *port,
+				     struct tc_htb_qopt_offload *opt)
+{
+	switch (opt->command) {
+	case TC_HTB_CREATE:
+		break;
+	case TC_HTB_DESTROY:
+		return airoha_tc_htb_destroy(port);
+	case TC_HTB_NODE_MODIFY:
+	case TC_HTB_LEAF_ALLOC_QUEUE:
+		return airoha_tc_htb_alloc_leaf_queue(port, opt);
+	case TC_HTB_LEAF_DEL:
+	case TC_HTB_LEAF_DEL_LAST:
+	case TC_HTB_LEAF_DEL_LAST_FORCE:
+		return airoha_tc_htb_delete_leaf_queue(port, opt);
+	case TC_HTB_LEAF_QUERY_QUEUE:
+		return airoha_tc_get_htb_get_leaf_queue(port, opt);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int airoha_dev_tc_setup(struct net_device *dev, enum tc_setup_type type,
+			       void *type_data)
+{
+	struct airoha_gdm_port *port = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_ETS:
+		return airoha_tc_setup_qdisc_ets(port, type_data);
+	case TC_SETUP_QDISC_HTB:
+		return airoha_tc_setup_qdisc_htb(port, type_data);
+	case TC_SETUP_BLOCK:
+	case TC_SETUP_FT:
+		return airoha_dev_setup_tc_block(port, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops airoha_netdev_ops = {
 	.ndo_init		= airoha_dev_init,
 	.ndo_open		= airoha_dev_open,
 	.ndo_stop		= airoha_dev_stop,
+	.ndo_change_mtu		= airoha_dev_change_mtu,
+	.ndo_select_queue	= airoha_dev_select_queue,
 	.ndo_start_xmit		= airoha_dev_xmit,
 	.ndo_get_stats64        = airoha_dev_get_stats64,
 	.ndo_set_mac_address	= airoha_dev_set_macaddr,
+	.ndo_setup_tc		= airoha_dev_tc_setup,
 };
 
 static const struct ethtool_ops airoha_ethtool_ops = {
@@ -2612,13 +2768,58 @@ static const struct ethtool_ops airoha_ethtool_ops = {
 	.get_rmon_stats		= airoha_ethtool_get_rmon_stats,
 };
 
-static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
+static int airoha_metadata_dst_alloc(struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(port->dsa_meta); i++) {
+		struct metadata_dst *md_dst;
+
+		md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+					    GFP_KERNEL);
+		if (!md_dst)
+			return -ENOMEM;
+
+		md_dst->u.port_info.port_id = i;
+		port->dsa_meta[i] = md_dst;
+	}
+
+	return 0;
+}
+
+static void airoha_metadata_dst_free(struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(port->dsa_meta); i++) {
+		if (!port->dsa_meta[i])
+			continue;
+
+		metadata_dst_free(port->dsa_meta[i]);
+	}
+}
+
+bool airoha_is_valid_gdm_port(struct airoha_eth *eth,
+			      struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
+		if (eth->ports[i] == port)
+			return true;
+	}
+
+	return false;
+}
+
+static int airoha_alloc_gdm_port(struct airoha_eth *eth,
+				 struct device_node *np, int index)
 {
 	const __be32 *id_ptr = of_get_property(np, "reg", NULL);
 	struct airoha_gdm_port *port;
 	struct airoha_qdma *qdma;
 	struct net_device *dev;
-	int err, index;
+	int err, p;
 	u32 id;
 
 	if (!id_ptr) {
@@ -2627,20 +2828,21 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	}
 
 	id = be32_to_cpup(id_ptr);
-	index = id - 1;
+	p = id - 1;
 
 	if (!id || id > ARRAY_SIZE(eth->ports)) {
 		dev_err(eth->dev, "invalid gdm port id: %d\n", id);
 		return -EINVAL;
 	}
 
-	if (eth->ports[index]) {
+	if (eth->ports[p]) {
 		dev_err(eth->dev, "duplicate gdm port id: %d\n", id);
 		return -EINVAL;
 	}
 
 	dev = devm_alloc_etherdev_mqs(eth->dev, sizeof(*port),
-				      AIROHA_NUM_TX_RING, AIROHA_NUM_RX_RING);
+				      AIROHA_NUM_NETDEV_TX_RINGS,
+				      AIROHA_NUM_RX_RING);
 	if (!dev) {
 		dev_err(eth->dev, "alloc_etherdev failed\n");
 		return -ENOMEM;
@@ -2653,12 +2855,19 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	dev->watchdog_timeo = 5 * HZ;
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 			   NETIF_F_TSO6 | NETIF_F_IPV6_CSUM |
-			   NETIF_F_SG | NETIF_F_TSO;
+			   NETIF_F_SG | NETIF_F_TSO |
+			   NETIF_F_HW_TC;
 	dev->features |= dev->hw_features;
+	dev->vlan_features = dev->hw_features;
 	dev->dev.of_node = np;
-	dev->irq = qdma->irq;
+	dev->irq = qdma->irq_banks[0].irq;
 	SET_NETDEV_DEV(dev, eth->dev);
 
+	/* reserve hw queues for HTB offloading */
+	err = netif_set_real_num_tx_queues(dev, AIROHA_NUM_TX_RING);
+	if (err)
+		return err;
+
 	err = of_get_ethdev_address(np, dev);
 	if (err) {
 		if (err == -EPROBE_DEFER)
@@ -2675,9 +2884,21 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	port->qdma = qdma;
 	port->dev = dev;
 	port->id = id;
-	eth->ports[index] = port;
+	eth->ports[p] = port;
 
-	return register_netdev(dev);
+	err = airoha_metadata_dst_alloc(port);
+	if (err)
+		return err;
+
+	err = register_netdev(dev);
+	if (err)
+		goto free_metadata_dst;
+
+	return 0;
+
+free_metadata_dst:
+	airoha_metadata_dst_free(port);
+	return err;
 }
 
 static int airoha_probe(struct platform_device *pdev)
@@ -2738,11 +2959,12 @@ static int airoha_probe(struct platform_device *pdev)
 
 	err = airoha_hw_init(pdev, eth);
 	if (err)
-		goto error;
+		goto error_hw_cleanup;
 
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_qdma_start_napi(&eth->qdma[i]);
 
+	i = 0;
 	for_each_child_of_node(pdev->dev.of_node, np) {
 		if (!of_device_is_compatible(np, "airoha,eth-mac"))
 			continue;
@@ -2750,24 +2972,29 @@ static int airoha_probe(struct platform_device *pdev)
 		if (!of_device_is_available(np))
 			continue;
 
-		err = airoha_alloc_gdm_port(eth, np);
+		err = airoha_alloc_gdm_port(eth, np, i++);
 		if (err) {
 			of_node_put(np);
-			goto error;
+			goto error_napi_stop;
 		}
 	}
 
 	return 0;
 
-error:
+error_napi_stop:
+	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
+		airoha_qdma_stop_napi(&eth->qdma[i]);
+error_hw_cleanup:
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_hw_cleanup(&eth->qdma[i]);
 
 	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
 		struct airoha_gdm_port *port = eth->ports[i];
 
-		if (port && port->dev->reg_state == NETREG_REGISTERED)
+		if (port && port->dev->reg_state == NETREG_REGISTERED) {
 			unregister_netdev(port->dev);
+			airoha_metadata_dst_free(port);
+		}
 	}
 	free_netdev(eth->napi_dev);
 	platform_set_drvdata(pdev, NULL);
@@ -2780,8 +3007,10 @@ static void airoha_remove(struct platform_device *pdev)
 	struct airoha_eth *eth = platform_get_drvdata(pdev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
+	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) {
+		airoha_qdma_stop_napi(&eth->qdma[i]);
 		airoha_hw_cleanup(&eth->qdma[i]);
+	}
 
 	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
 		struct airoha_gdm_port *port = eth->ports[i];
@@ -2791,9 +3020,11 @@ static void airoha_remove(struct platform_device *pdev)
 
 		airoha_dev_stop(port->dev);
 		unregister_netdev(port->dev);
+		airoha_metadata_dst_free(port);
 	}
 	free_netdev(eth->napi_dev);
 
+	airoha_ppe_deinit(eth);
 	platform_set_drvdata(pdev, NULL);
 }
 
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
new file mode 100644
index 000000000000..a970b789cf23
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -0,0 +1,632 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#ifndef AIROHA_ETH_H
+#define AIROHA_ETH_H
+
+#include <linux/debugfs.h>
+#include <linux/etherdevice.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/reset.h>
+#include <net/dsa.h>
+
+#define AIROHA_MAX_NUM_GDM_PORTS	4
+#define AIROHA_MAX_NUM_QDMA		2
+#define AIROHA_MAX_NUM_IRQ_BANKS	4
+#define AIROHA_MAX_DSA_PORTS		7
+#define AIROHA_MAX_NUM_RSTS		3
+#define AIROHA_MAX_NUM_XSI_RSTS		5
+#define AIROHA_MAX_MTU			9216
+#define AIROHA_MAX_PACKET_SIZE		2048
+#define AIROHA_NUM_QOS_CHANNELS		4
+#define AIROHA_NUM_QOS_QUEUES		8
+#define AIROHA_NUM_TX_RING		32
+#define AIROHA_NUM_RX_RING		32
+#define AIROHA_NUM_NETDEV_TX_RINGS	(AIROHA_NUM_TX_RING + \
+					 AIROHA_NUM_QOS_CHANNELS)
+#define AIROHA_FE_MC_MAX_VLAN_TABLE	64
+#define AIROHA_FE_MC_MAX_VLAN_PORT	16
+#define AIROHA_NUM_TX_IRQ		2
+#define HW_DSCP_NUM			2048
+#define IRQ_QUEUE_LEN(_n)		((_n) ? 1024 : 2048)
+#define TX_DSCP_NUM			1024
+#define RX_DSCP_NUM(_n)			\
+	((_n) ==  2 ? 128 :		\
+	 (_n) == 11 ? 128 :		\
+	 (_n) == 15 ? 128 :		\
+	 (_n) ==  0 ? 1024 : 16)
+
+#define PSE_RSV_PAGES			128
+#define PSE_QUEUE_RSV_PAGES		64
+
+#define QDMA_METER_IDX(_n)		((_n) & 0xff)
+#define QDMA_METER_GROUP(_n)		(((_n) >> 8) & 0x3)
+
+#define PPE_NUM				2
+#define PPE1_SRAM_NUM_ENTRIES		(8 * 1024)
+#define PPE_SRAM_NUM_ENTRIES		(2 * PPE1_SRAM_NUM_ENTRIES)
+#ifdef CONFIG_NET_AIROHA_FLOW_STATS
+#define PPE1_STATS_NUM_ENTRIES		(4 * 1024)
+#else
+#define PPE1_STATS_NUM_ENTRIES		0
+#endif /* CONFIG_NET_AIROHA_FLOW_STATS */
+#define PPE_STATS_NUM_ENTRIES		(2 * PPE1_STATS_NUM_ENTRIES)
+#define PPE1_SRAM_NUM_DATA_ENTRIES	(PPE1_SRAM_NUM_ENTRIES - PPE1_STATS_NUM_ENTRIES)
+#define PPE_SRAM_NUM_DATA_ENTRIES	(2 * PPE1_SRAM_NUM_DATA_ENTRIES)
+#define PPE_DRAM_NUM_ENTRIES		(16 * 1024)
+#define PPE_NUM_ENTRIES			(PPE_SRAM_NUM_ENTRIES + PPE_DRAM_NUM_ENTRIES)
+#define PPE_HASH_MASK			(PPE_NUM_ENTRIES - 1)
+#define PPE_ENTRY_SIZE			80
+#define PPE_RAM_NUM_ENTRIES_SHIFT(_n)	(__ffs((_n) >> 10))
+
+#define MTK_HDR_LEN			4
+#define MTK_HDR_XMIT_TAGGED_TPID_8100	1
+#define MTK_HDR_XMIT_TAGGED_TPID_88A8	2
+
+enum {
+	QDMA_INT_REG_IDX0,
+	QDMA_INT_REG_IDX1,
+	QDMA_INT_REG_IDX2,
+	QDMA_INT_REG_IDX3,
+	QDMA_INT_REG_IDX4,
+	QDMA_INT_REG_MAX
+};
+
+enum {
+	HSGMII_LAN_PCIE0_SRCPORT = 0x16,
+	HSGMII_LAN_PCIE1_SRCPORT,
+	HSGMII_LAN_ETH_SRCPORT,
+	HSGMII_LAN_USB_SRCPORT,
+};
+
+enum {
+	XSI_PCIE0_VIP_PORT_MASK	= BIT(22),
+	XSI_PCIE1_VIP_PORT_MASK	= BIT(23),
+	XSI_USB_VIP_PORT_MASK	= BIT(25),
+	XSI_ETH_VIP_PORT_MASK	= BIT(24),
+};
+
+enum {
+	DEV_STATE_INITIALIZED,
+};
+
+enum {
+	CDM_CRSN_QSEL_Q1 = 1,
+	CDM_CRSN_QSEL_Q5 = 5,
+	CDM_CRSN_QSEL_Q6 = 6,
+	CDM_CRSN_QSEL_Q15 = 15,
+};
+
+enum {
+	CRSN_08 = 0x8,
+	CRSN_21 = 0x15, /* KA */
+	CRSN_22 = 0x16, /* hit bind and force route to CPU */
+	CRSN_24 = 0x18,
+	CRSN_25 = 0x19,
+};
+
+enum {
+	FE_PSE_PORT_CDM1,
+	FE_PSE_PORT_GDM1,
+	FE_PSE_PORT_GDM2,
+	FE_PSE_PORT_GDM3,
+	FE_PSE_PORT_PPE1,
+	FE_PSE_PORT_CDM2,
+	FE_PSE_PORT_CDM3,
+	FE_PSE_PORT_CDM4,
+	FE_PSE_PORT_PPE2,
+	FE_PSE_PORT_GDM4,
+	FE_PSE_PORT_CDM5,
+	FE_PSE_PORT_DROP = 0xf,
+};
+
+enum tx_sched_mode {
+	TC_SCH_WRR8,
+	TC_SCH_SP,
+	TC_SCH_WRR7,
+	TC_SCH_WRR6,
+	TC_SCH_WRR5,
+	TC_SCH_WRR4,
+	TC_SCH_WRR3,
+	TC_SCH_WRR2,
+};
+
+enum trtcm_unit_type {
+	TRTCM_BYTE_UNIT,
+	TRTCM_PACKET_UNIT,
+};
+
+enum trtcm_param_type {
+	TRTCM_MISC_MODE, /* meter_en, pps_mode, tick_sel */
+	TRTCM_TOKEN_RATE_MODE,
+	TRTCM_BUCKETSIZE_SHIFT_MODE,
+	TRTCM_BUCKET_COUNTER_MODE,
+};
+
+enum trtcm_mode_type {
+	TRTCM_COMMIT_MODE,
+	TRTCM_PEAK_MODE,
+};
+
+enum trtcm_param {
+	TRTCM_TICK_SEL = BIT(0),
+	TRTCM_PKT_MODE = BIT(1),
+	TRTCM_METER_MODE = BIT(2),
+};
+
+#define MIN_TOKEN_SIZE				4096
+#define MAX_TOKEN_SIZE_OFFSET			17
+#define TRTCM_TOKEN_RATE_MASK			GENMASK(23, 6)
+#define TRTCM_TOKEN_RATE_FRACTION_MASK		GENMASK(5, 0)
+
+struct airoha_queue_entry {
+	union {
+		void *buf;
+		struct sk_buff *skb;
+	};
+	dma_addr_t dma_addr;
+	u16 dma_len;
+};
+
+struct airoha_queue {
+	struct airoha_qdma *qdma;
+
+	/* protect concurrent queue accesses */
+	spinlock_t lock;
+	struct airoha_queue_entry *entry;
+	struct airoha_qdma_desc *desc;
+	u16 head;
+	u16 tail;
+
+	int queued;
+	int ndesc;
+	int free_thr;
+	int buf_size;
+
+	struct napi_struct napi;
+	struct page_pool *page_pool;
+	struct sk_buff *skb;
+};
+
+struct airoha_tx_irq_queue {
+	struct airoha_qdma *qdma;
+
+	struct napi_struct napi;
+
+	int size;
+	u32 *q;
+};
+
+struct airoha_hw_stats {
+	/* protect concurrent hw_stats accesses */
+	spinlock_t lock;
+	struct u64_stats_sync syncp;
+
+	/* get_stats64 */
+	u64 rx_ok_pkts;
+	u64 tx_ok_pkts;
+	u64 rx_ok_bytes;
+	u64 tx_ok_bytes;
+	u64 rx_multicast;
+	u64 rx_errors;
+	u64 rx_drops;
+	u64 tx_drops;
+	u64 rx_crc_error;
+	u64 rx_over_errors;
+	/* ethtool stats */
+	u64 tx_broadcast;
+	u64 tx_multicast;
+	u64 tx_len[7];
+	u64 rx_broadcast;
+	u64 rx_fragment;
+	u64 rx_jabber;
+	u64 rx_len[7];
+};
+
+enum {
+	PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED = 0x0f,
+};
+
+enum {
+	AIROHA_FOE_STATE_INVALID,
+	AIROHA_FOE_STATE_UNBIND,
+	AIROHA_FOE_STATE_BIND,
+	AIROHA_FOE_STATE_FIN
+};
+
+enum {
+	PPE_PKT_TYPE_IPV4_HNAPT = 0,
+	PPE_PKT_TYPE_IPV4_ROUTE = 1,
+	PPE_PKT_TYPE_BRIDGE = 2,
+	PPE_PKT_TYPE_IPV4_DSLITE = 3,
+	PPE_PKT_TYPE_IPV6_ROUTE_3T = 4,
+	PPE_PKT_TYPE_IPV6_ROUTE_5T = 5,
+	PPE_PKT_TYPE_IPV6_6RD = 7,
+};
+
+#define AIROHA_FOE_MAC_SMAC_ID		GENMASK(20, 16)
+#define AIROHA_FOE_MAC_PPPOE_ID		GENMASK(15, 0)
+
+struct airoha_foe_mac_info_common {
+	u16 vlan1;
+	u16 etype;
+
+	u32 dest_mac_hi;
+
+	u16 vlan2;
+	u16 dest_mac_lo;
+
+	u32 src_mac_hi;
+};
+
+struct airoha_foe_mac_info {
+	struct airoha_foe_mac_info_common common;
+
+	u16 pppoe_id;
+	u16 src_mac_lo;
+
+	u32 meter;
+};
+
+#define AIROHA_FOE_IB1_UNBIND_PREBIND		BIT(24)
+#define AIROHA_FOE_IB1_UNBIND_PACKETS		GENMASK(23, 8)
+#define AIROHA_FOE_IB1_UNBIND_TIMESTAMP		GENMASK(7, 0)
+
+#define AIROHA_FOE_IB1_BIND_STATIC		BIT(31)
+#define AIROHA_FOE_IB1_BIND_UDP			BIT(30)
+#define AIROHA_FOE_IB1_BIND_STATE		GENMASK(29, 28)
+#define AIROHA_FOE_IB1_BIND_PACKET_TYPE		GENMASK(27, 25)
+#define AIROHA_FOE_IB1_BIND_TTL			BIT(24)
+#define AIROHA_FOE_IB1_BIND_TUNNEL_DECAP	BIT(23)
+#define AIROHA_FOE_IB1_BIND_PPPOE		BIT(22)
+#define AIROHA_FOE_IB1_BIND_VPM			GENMASK(21, 20)
+#define AIROHA_FOE_IB1_BIND_VLAN_LAYER		GENMASK(19, 16)
+#define AIROHA_FOE_IB1_BIND_KEEPALIVE		BIT(15)
+#define AIROHA_FOE_IB1_BIND_TIMESTAMP		GENMASK(14, 0)
+
+#define AIROHA_FOE_IB2_DSCP			GENMASK(31, 24)
+#define AIROHA_FOE_IB2_PORT_AG			GENMASK(23, 13)
+#define AIROHA_FOE_IB2_PCP			BIT(12)
+#define AIROHA_FOE_IB2_MULTICAST		BIT(11)
+#define AIROHA_FOE_IB2_FAST_PATH		BIT(10)
+#define AIROHA_FOE_IB2_PSE_QOS			BIT(9)
+#define AIROHA_FOE_IB2_PSE_PORT			GENMASK(8, 5)
+#define AIROHA_FOE_IB2_NBQ			GENMASK(4, 0)
+
+#define AIROHA_FOE_ACTDP			GENMASK(31, 24)
+#define AIROHA_FOE_SHAPER_ID			GENMASK(23, 16)
+#define AIROHA_FOE_CHANNEL			GENMASK(15, 11)
+#define AIROHA_FOE_QID				GENMASK(10, 8)
+#define AIROHA_FOE_DPI				BIT(7)
+#define AIROHA_FOE_TUNNEL			BIT(6)
+#define AIROHA_FOE_TUNNEL_ID			GENMASK(5, 0)
+
+#define AIROHA_FOE_TUNNEL_MTU			GENMASK(31, 16)
+#define AIROHA_FOE_ACNT_GRP3			GENMASK(15, 9)
+#define AIROHA_FOE_METER_GRP3			GENMASK(8, 5)
+#define AIROHA_FOE_METER_GRP2			GENMASK(4, 0)
+
+struct airoha_foe_bridge {
+	u32 dest_mac_hi;
+
+	u16 src_mac_hi;
+	u16 dest_mac_lo;
+
+	u32 src_mac_lo;
+
+	u32 ib2;
+
+	u32 rsv[5];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv4_tuple {
+	u32 src_ip;
+	u32 dest_ip;
+	union {
+		struct {
+			u16 dest_port;
+			u16 src_port;
+		};
+		struct {
+			u8 protocol;
+			u8 _pad[3]; /* fill with 0xa5a5a5 */
+		};
+		u32 ports;
+	};
+};
+
+struct airoha_foe_ipv4 {
+	struct airoha_foe_ipv4_tuple orig_tuple;
+
+	u32 ib2;
+
+	struct airoha_foe_ipv4_tuple new_tuple;
+
+	u32 rsv[2];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv4_dslite {
+	struct airoha_foe_ipv4_tuple ip4;
+
+	u32 ib2;
+
+	u8 flow_label[3];
+	u8 priority;
+
+	u32 rsv[4];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv6 {
+	u32 src_ip[4];
+	u32 dest_ip[4];
+
+	union {
+		struct {
+			u16 dest_port;
+			u16 src_port;
+		};
+		struct {
+			u8 protocol;
+			u8 pad[3];
+		};
+		u32 ports;
+	};
+
+	u32 data;
+
+	u32 ib2;
+
+	struct airoha_foe_mac_info_common l2;
+
+	u32 meter;
+};
+
+struct airoha_foe_entry {
+	union {
+		struct {
+			u32 ib1;
+			union {
+				struct airoha_foe_bridge bridge;
+				struct airoha_foe_ipv4 ipv4;
+				struct airoha_foe_ipv4_dslite dslite;
+				struct airoha_foe_ipv6 ipv6;
+				DECLARE_FLEX_ARRAY(u32, d);
+			};
+		};
+		u8 data[PPE_ENTRY_SIZE];
+	};
+};
+
+struct airoha_foe_stats {
+	u32 bytes;
+	u32 packets;
+};
+
+struct airoha_foe_stats64 {
+	u64 bytes;
+	u64 packets;
+};
+
+struct airoha_flow_data {
+	struct ethhdr eth;
+
+	union {
+		struct {
+			__be32 src_addr;
+			__be32 dst_addr;
+		} v4;
+
+		struct {
+			struct in6_addr src_addr;
+			struct in6_addr dst_addr;
+		} v6;
+	};
+
+	__be16 src_port;
+	__be16 dst_port;
+
+	struct {
+		struct {
+			u16 id;
+			__be16 proto;
+		} hdr[2];
+		u8 num;
+	} vlan;
+	struct {
+		u16 sid;
+		u8 num;
+	} pppoe;
+};
+
+enum airoha_flow_entry_type {
+	FLOW_TYPE_L4,
+	FLOW_TYPE_L2,
+	FLOW_TYPE_L2_SUBFLOW,
+};
+
+struct airoha_flow_table_entry {
+	union {
+		struct hlist_node list; /* PPE L3 flow entry */
+		struct {
+			struct rhash_head l2_node;  /* L2 flow entry */
+			struct hlist_head l2_flows; /* PPE L2 subflows list */
+		};
+	};
+
+	struct airoha_foe_entry data;
+	struct hlist_node l2_subflow_node; /* PPE L2 subflow entry */
+	u32 hash;
+
+	struct airoha_foe_stats64 stats;
+	enum airoha_flow_entry_type type;
+
+	struct rhash_head node;
+	unsigned long cookie;
+};
+
+/* RX queue to IRQ mapping: BIT(q) in IRQ(n) */
+#define RX_IRQ0_BANK_PIN_MASK			0x839f
+#define RX_IRQ1_BANK_PIN_MASK			0x7fe00000
+#define RX_IRQ2_BANK_PIN_MASK			0x20
+#define RX_IRQ3_BANK_PIN_MASK			0x40
+#define RX_IRQ_BANK_PIN_MASK(_n)		\
+	(((_n) == 3) ? RX_IRQ3_BANK_PIN_MASK :	\
+	 ((_n) == 2) ? RX_IRQ2_BANK_PIN_MASK :	\
+	 ((_n) == 1) ? RX_IRQ1_BANK_PIN_MASK :	\
+	 RX_IRQ0_BANK_PIN_MASK)
+
+struct airoha_irq_bank {
+	struct airoha_qdma *qdma;
+
+	/* protect concurrent irqmask accesses */
+	spinlock_t irq_lock;
+	u32 irqmask[QDMA_INT_REG_MAX];
+	int irq;
+};
+
+struct airoha_qdma {
+	struct airoha_eth *eth;
+	void __iomem *regs;
+
+	atomic_t users;
+
+	struct airoha_irq_bank irq_banks[AIROHA_MAX_NUM_IRQ_BANKS];
+
+	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
+
+	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
+	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
+};
+
+struct airoha_gdm_port {
+	struct airoha_qdma *qdma;
+	struct net_device *dev;
+	int id;
+
+	struct airoha_hw_stats stats;
+
+	DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
+
+	/* qos stats counters */
+	u64 cpu_tx_packets;
+	u64 fwd_tx_packets;
+
+	struct metadata_dst *dsa_meta[AIROHA_MAX_DSA_PORTS];
+};
+
+#define AIROHA_RXD4_PPE_CPU_REASON	GENMASK(20, 16)
+#define AIROHA_RXD4_FOE_ENTRY		GENMASK(15, 0)
+
+struct airoha_ppe {
+	struct airoha_eth *eth;
+
+	void *foe;
+	dma_addr_t foe_dma;
+
+	struct rhashtable l2_flows;
+
+	struct hlist_head *foe_flow;
+	u16 foe_check_time[PPE_NUM_ENTRIES];
+
+	struct airoha_foe_stats *foe_stats;
+	dma_addr_t foe_stats_dma;
+
+	struct dentry *debugfs_dir;
+};
+
+struct airoha_eth {
+	struct device *dev;
+
+	unsigned long state;
+	void __iomem *fe_regs;
+
+	struct airoha_npu __rcu *npu;
+
+	struct airoha_ppe *ppe;
+	struct rhashtable flow_table;
+
+	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
+	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
+
+	struct net_device *napi_dev;
+
+	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
+	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
+};
+
+u32 airoha_rr(void __iomem *base, u32 offset);
+void airoha_wr(void __iomem *base, u32 offset, u32 val);
+u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val);
+
+#define airoha_fe_rr(eth, offset)				\
+	airoha_rr((eth)->fe_regs, (offset))
+#define airoha_fe_wr(eth, offset, val)				\
+	airoha_wr((eth)->fe_regs, (offset), (val))
+#define airoha_fe_rmw(eth, offset, mask, val)			\
+	airoha_rmw((eth)->fe_regs, (offset), (mask), (val))
+#define airoha_fe_set(eth, offset, val)				\
+	airoha_rmw((eth)->fe_regs, (offset), 0, (val))
+#define airoha_fe_clear(eth, offset, val)			\
+	airoha_rmw((eth)->fe_regs, (offset), (val), 0)
+
+#define airoha_qdma_rr(qdma, offset)				\
+	airoha_rr((qdma)->regs, (offset))
+#define airoha_qdma_wr(qdma, offset, val)			\
+	airoha_wr((qdma)->regs, (offset), (val))
+#define airoha_qdma_rmw(qdma, offset, mask, val)		\
+	airoha_rmw((qdma)->regs, (offset), (mask), (val))
+#define airoha_qdma_set(qdma, offset, val)			\
+	airoha_rmw((qdma)->regs, (offset), 0, (val))
+#define airoha_qdma_clear(qdma, offset, val)			\
+	airoha_rmw((qdma)->regs, (offset), (val), 0)
+
+static inline bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port)
+{
+	/* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
+	 * GDM{2,3,4} can be used as wan port connected to an external
+	 * phy module.
+	 */
+	return port->id == 1;
+}
+
+bool airoha_is_valid_gdm_port(struct airoha_eth *eth,
+			      struct airoha_gdm_port *port);
+
+void airoha_ppe_check_skb(struct airoha_ppe *ppe, struct sk_buff *skb,
+			  u16 hash);
+int airoha_ppe_setup_tc_block_cb(struct net_device *dev, void *type_data);
+int airoha_ppe_init(struct airoha_eth *eth);
+void airoha_ppe_deinit(struct airoha_eth *eth);
+void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port);
+struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
+						  u32 hash);
+void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash,
+				    struct airoha_foe_stats64 *stats);
+
+#ifdef CONFIG_DEBUG_FS
+int airoha_ppe_debugfs_init(struct airoha_ppe *ppe);
+#else
+static inline int airoha_ppe_debugfs_init(struct airoha_ppe *ppe)
+{
+	return 0;
+}
+#endif
+
+#endif /* AIROHA_ETH_H */
diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
new file mode 100644
index 000000000000..0e5b8c21b9aa
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_npu.c
@@ -0,0 +1,590 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/devcoredump.h>
+#include <linux/firmware.h>
+#include <linux/platform_device.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/regmap.h>
+
+#include "airoha_eth.h"
+#include "airoha_npu.h"
+
+#define NPU_EN7581_FIRMWARE_DATA		"airoha/en7581_npu_data.bin"
+#define NPU_EN7581_FIRMWARE_RV32		"airoha/en7581_npu_rv32.bin"
+#define NPU_EN7581_FIRMWARE_RV32_MAX_SIZE	0x200000
+#define NPU_EN7581_FIRMWARE_DATA_MAX_SIZE	0x10000
+#define NPU_DUMP_SIZE				512
+
+#define REG_NPU_LOCAL_SRAM		0x0
+
+#define NPU_PC_BASE_ADDR		0x305000
+#define REG_PC_DBG(_n)			(0x305000 + ((_n) * 0x100))
+
+#define NPU_CLUSTER_BASE_ADDR		0x306000
+
+#define REG_CR_BOOT_TRIGGER		(NPU_CLUSTER_BASE_ADDR + 0x000)
+#define REG_CR_BOOT_CONFIG		(NPU_CLUSTER_BASE_ADDR + 0x004)
+#define REG_CR_BOOT_BASE(_n)		(NPU_CLUSTER_BASE_ADDR + 0x020 + ((_n) << 2))
+
+#define NPU_MBOX_BASE_ADDR		0x30c000
+
+#define REG_CR_MBOX_INT_STATUS		(NPU_MBOX_BASE_ADDR + 0x000)
+#define MBOX_INT_STATUS_MASK		BIT(8)
+
+#define REG_CR_MBOX_INT_MASK(_n)	(NPU_MBOX_BASE_ADDR + 0x004 + ((_n) << 2))
+#define REG_CR_MBQ0_CTRL(_n)		(NPU_MBOX_BASE_ADDR + 0x030 + ((_n) << 2))
+#define REG_CR_MBQ8_CTRL(_n)		(NPU_MBOX_BASE_ADDR + 0x0b0 + ((_n) << 2))
+#define REG_CR_NPU_MIB(_n)		(NPU_MBOX_BASE_ADDR + 0x140 + ((_n) << 2))
+
+#define NPU_TIMER_BASE_ADDR		0x310100
+#define REG_WDT_TIMER_CTRL(_n)		(NPU_TIMER_BASE_ADDR + ((_n) * 0x100))
+#define WDT_EN_MASK			BIT(25)
+#define WDT_INTR_MASK			BIT(21)
+
+enum {
+	NPU_OP_SET = 1,
+	NPU_OP_SET_NO_WAIT,
+	NPU_OP_GET,
+	NPU_OP_GET_NO_WAIT,
+};
+
+enum {
+	NPU_FUNC_WIFI,
+	NPU_FUNC_TUNNEL,
+	NPU_FUNC_NOTIFY,
+	NPU_FUNC_DBA,
+	NPU_FUNC_TR471,
+	NPU_FUNC_PPE,
+};
+
+enum {
+	NPU_MBOX_ERROR,
+	NPU_MBOX_SUCCESS,
+};
+
+enum {
+	PPE_FUNC_SET_WAIT,
+	PPE_FUNC_SET_WAIT_HWNAT_INIT,
+	PPE_FUNC_SET_WAIT_HWNAT_DEINIT,
+	PPE_FUNC_SET_WAIT_API,
+	PPE_FUNC_SET_WAIT_FLOW_STATS_SETUP,
+};
+
+enum {
+	PPE2_SRAM_SET_ENTRY,
+	PPE_SRAM_SET_ENTRY,
+	PPE_SRAM_SET_VAL,
+	PPE_SRAM_RESET_VAL,
+};
+
+enum {
+	QDMA_WAN_ETHER = 1,
+	QDMA_WAN_PON_XDSL,
+};
+
+#define MBOX_MSG_FUNC_ID	GENMASK(14, 11)
+#define MBOX_MSG_STATIC_BUF	BIT(5)
+#define MBOX_MSG_STATUS		GENMASK(4, 2)
+#define MBOX_MSG_DONE		BIT(1)
+#define MBOX_MSG_WAIT_RSP	BIT(0)
+
+#define PPE_TYPE_L2B_IPV4	2
+#define PPE_TYPE_L2B_IPV4_IPV6	3
+
+struct ppe_mbox_data {
+	u32 func_type;
+	u32 func_id;
+	union {
+		struct {
+			u8 cds;
+			u8 xpon_hal_api;
+			u8 wan_xsi;
+			u8 ct_joyme4;
+			u8 max_packet;
+			u8 rsv[3];
+			u32 ppe_type;
+			u32 wan_mode;
+			u32 wan_sel;
+		} init_info;
+		struct {
+			u32 func_id;
+			u32 size;
+			u32 data;
+		} set_info;
+		struct {
+			u32 npu_stats_addr;
+			u32 foe_stats_addr;
+		} stats_info;
+	};
+};
+
+static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
+			       void *p, int size)
+{
+	u16 core = 0; /* FIXME */
+	u32 val, offset = core << 4;
+	dma_addr_t dma_addr;
+	int ret;
+
+	dma_addr = dma_map_single(npu->dev, p, size, DMA_TO_DEVICE);
+	ret = dma_mapping_error(npu->dev, dma_addr);
+	if (ret)
+		return ret;
+
+	spin_lock_bh(&npu->cores[core].lock);
+
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(0) + offset, dma_addr);
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(1) + offset, size);
+	regmap_read(npu->regmap, REG_CR_MBQ0_CTRL(2) + offset, &val);
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(2) + offset, val + 1);
+	val = FIELD_PREP(MBOX_MSG_FUNC_ID, func_id) | MBOX_MSG_WAIT_RSP;
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(3) + offset, val);
+
+	ret = regmap_read_poll_timeout_atomic(npu->regmap,
+					      REG_CR_MBQ0_CTRL(3) + offset,
+					      val, (val & MBOX_MSG_DONE),
+					      100, 100 * MSEC_PER_SEC);
+	if (!ret && FIELD_GET(MBOX_MSG_STATUS, val) != NPU_MBOX_SUCCESS)
+		ret = -EINVAL;
+
+	spin_unlock_bh(&npu->cores[core].lock);
+
+	dma_unmap_single(npu->dev, dma_addr, size, DMA_TO_DEVICE);
+
+	return ret;
+}
+
+static int airoha_npu_run_firmware(struct device *dev, void __iomem *base,
+				   struct reserved_mem *rmem)
+{
+	const struct firmware *fw;
+	void __iomem *addr;
+	int ret;
+
+	ret = request_firmware(&fw, NPU_EN7581_FIRMWARE_RV32, dev);
+	if (ret)
+		return ret == -ENOENT ? -EPROBE_DEFER : ret;
+
+	if (fw->size > NPU_EN7581_FIRMWARE_RV32_MAX_SIZE) {
+		dev_err(dev, "%s: fw size too overlimit (%zu)\n",
+			NPU_EN7581_FIRMWARE_RV32, fw->size);
+		ret = -E2BIG;
+		goto out;
+	}
+
+	addr = devm_ioremap(dev, rmem->base, rmem->size);
+	if (!addr) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	memcpy_toio(addr, fw->data, fw->size);
+	release_firmware(fw);
+
+	ret = request_firmware(&fw, NPU_EN7581_FIRMWARE_DATA, dev);
+	if (ret)
+		return ret == -ENOENT ? -EPROBE_DEFER : ret;
+
+	if (fw->size > NPU_EN7581_FIRMWARE_DATA_MAX_SIZE) {
+		dev_err(dev, "%s: fw size too overlimit (%zu)\n",
+			NPU_EN7581_FIRMWARE_DATA, fw->size);
+		ret = -E2BIG;
+		goto out;
+	}
+
+	memcpy_toio(base + REG_NPU_LOCAL_SRAM, fw->data, fw->size);
+out:
+	release_firmware(fw);
+
+	return ret;
+}
+
+static irqreturn_t airoha_npu_mbox_handler(int irq, void *npu_instance)
+{
+	struct airoha_npu *npu = npu_instance;
+
+	/* clear mbox interrupt status */
+	regmap_write(npu->regmap, REG_CR_MBOX_INT_STATUS,
+		     MBOX_INT_STATUS_MASK);
+
+	/* acknowledge npu */
+	regmap_update_bits(npu->regmap, REG_CR_MBQ8_CTRL(3),
+			   MBOX_MSG_STATUS | MBOX_MSG_DONE, MBOX_MSG_DONE);
+
+	return IRQ_HANDLED;
+}
+
+static void airoha_npu_wdt_work(struct work_struct *work)
+{
+	struct airoha_npu_core *core;
+	struct airoha_npu *npu;
+	void *dump;
+	u32 val[3];
+	int c;
+
+	core = container_of(work, struct airoha_npu_core, wdt_work);
+	npu = core->npu;
+
+	dump = vzalloc(NPU_DUMP_SIZE);
+	if (!dump)
+		return;
+
+	c = core - &npu->cores[0];
+	regmap_bulk_read(npu->regmap, REG_PC_DBG(c), val, ARRAY_SIZE(val));
+	snprintf(dump, NPU_DUMP_SIZE, "PC: %08x SP: %08x LR: %08x\n",
+		 val[0], val[1], val[2]);
+
+	dev_coredumpv(npu->dev, dump, NPU_DUMP_SIZE, GFP_KERNEL);
+}
+
+static irqreturn_t airoha_npu_wdt_handler(int irq, void *core_instance)
+{
+	struct airoha_npu_core *core = core_instance;
+	struct airoha_npu *npu = core->npu;
+	int c = core - &npu->cores[0];
+	u32 val;
+
+	regmap_set_bits(npu->regmap, REG_WDT_TIMER_CTRL(c), WDT_INTR_MASK);
+	if (!regmap_read(npu->regmap, REG_WDT_TIMER_CTRL(c), &val) &&
+	    FIELD_GET(WDT_EN_MASK, val))
+		schedule_work(&core->wdt_work);
+
+	return IRQ_HANDLED;
+}
+
+static int airoha_npu_ppe_init(struct airoha_npu *npu)
+{
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_HWNAT_INIT;
+	ppe_data->init_info.ppe_type = PPE_TYPE_L2B_IPV4_IPV6;
+	ppe_data->init_info.wan_mode = QDMA_WAN_ETHER;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_ppe_deinit(struct airoha_npu *npu)
+{
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_HWNAT_DEINIT;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_ppe_flush_sram_entries(struct airoha_npu *npu,
+					     dma_addr_t foe_addr,
+					     int sram_num_entries)
+{
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_API;
+	ppe_data->set_info.func_id = PPE_SRAM_RESET_VAL;
+	ppe_data->set_info.data = foe_addr;
+	ppe_data->set_info.size = sram_num_entries;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_foe_commit_entry(struct airoha_npu *npu,
+				       dma_addr_t foe_addr,
+				       u32 entry_size, u32 hash, bool ppe2)
+{
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_ATOMIC);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_API;
+	ppe_data->set_info.data = foe_addr;
+	ppe_data->set_info.size = entry_size;
+	ppe_data->set_info.func_id = ppe2 ? PPE2_SRAM_SET_ENTRY
+					  : PPE_SRAM_SET_ENTRY;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	if (err)
+		goto out;
+
+	ppe_data->set_info.func_id = PPE_SRAM_SET_VAL;
+	ppe_data->set_info.data = hash;
+	ppe_data->set_info.size = sizeof(u32);
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+out:
+	kfree(ppe_data);
+
+	return err;
+}
+
+static int airoha_npu_stats_setup(struct airoha_npu *npu,
+				  dma_addr_t foe_stats_addr)
+{
+	int err, size = PPE_STATS_NUM_ENTRIES * sizeof(*npu->stats);
+	struct ppe_mbox_data *ppe_data;
+
+	if (!size) /* flow stats are disabled */
+		return 0;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_ATOMIC);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_FLOW_STATS_SETUP;
+	ppe_data->stats_info.foe_stats_addr = foe_stats_addr;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	if (err)
+		goto out;
+
+	npu->stats = devm_ioremap(npu->dev,
+				  ppe_data->stats_info.npu_stats_addr,
+				  size);
+	if (!npu->stats)
+		err = -ENOMEM;
+out:
+	kfree(ppe_data);
+
+	return err;
+}
+
+struct airoha_npu *airoha_npu_get(struct device *dev, dma_addr_t *stats_addr)
+{
+	struct platform_device *pdev;
+	struct device_node *np;
+	struct airoha_npu *npu;
+
+	np = of_parse_phandle(dev->of_node, "airoha,npu", 0);
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	pdev = of_find_device_by_node(np);
+	of_node_put(np);
+
+	if (!pdev) {
+		dev_err(dev, "cannot find device node %s\n", np->name);
+		return ERR_PTR(-ENODEV);
+	}
+
+	if (!try_module_get(THIS_MODULE)) {
+		dev_err(dev, "failed to get the device driver module\n");
+		npu = ERR_PTR(-ENODEV);
+		goto error_pdev_put;
+	}
+
+	npu = platform_get_drvdata(pdev);
+	if (!npu) {
+		npu = ERR_PTR(-ENODEV);
+		goto error_module_put;
+	}
+
+	if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_SUPPLIER)) {
+		dev_err(&pdev->dev,
+			"failed to create device link to consumer %s\n",
+			dev_name(dev));
+		npu = ERR_PTR(-EINVAL);
+		goto error_module_put;
+	}
+
+	if (stats_addr) {
+		int err;
+
+		err = airoha_npu_stats_setup(npu, *stats_addr);
+		if (err) {
+			dev_err(dev, "failed to allocate npu stats buffer\n");
+			npu = ERR_PTR(err);
+			goto error_module_put;
+		}
+	}
+
+	return npu;
+
+error_module_put:
+	module_put(THIS_MODULE);
+error_pdev_put:
+	platform_device_put(pdev);
+
+	return npu;
+}
+EXPORT_SYMBOL_GPL(airoha_npu_get);
+
+void airoha_npu_put(struct airoha_npu *npu)
+{
+	module_put(THIS_MODULE);
+	put_device(npu->dev);
+}
+EXPORT_SYMBOL_GPL(airoha_npu_put);
+
+static const struct of_device_id of_airoha_npu_match[] = {
+	{ .compatible = "airoha,en7581-npu" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, of_airoha_npu_match);
+
+static const struct regmap_config regmap_config = {
+	.name			= "npu",
+	.reg_bits		= 32,
+	.val_bits		= 32,
+	.reg_stride		= 4,
+	.disable_locking	= true,
+};
+
+static int airoha_npu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct reserved_mem *rmem;
+	struct airoha_npu *npu;
+	struct device_node *np;
+	void __iomem *base;
+	int i, irq, err;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	npu = devm_kzalloc(dev, sizeof(*npu), GFP_KERNEL);
+	if (!npu)
+		return -ENOMEM;
+
+	npu->dev = dev;
+	npu->ops.ppe_init = airoha_npu_ppe_init;
+	npu->ops.ppe_deinit = airoha_npu_ppe_deinit;
+	npu->ops.ppe_flush_sram_entries = airoha_npu_ppe_flush_sram_entries;
+	npu->ops.ppe_foe_commit_entry = airoha_npu_foe_commit_entry;
+
+	npu->regmap = devm_regmap_init_mmio(dev, base, &regmap_config);
+	if (IS_ERR(npu->regmap))
+		return PTR_ERR(npu->regmap);
+
+	np = of_parse_phandle(dev->of_node, "memory-region", 0);
+	if (!np)
+		return -ENODEV;
+
+	rmem = of_reserved_mem_lookup(np);
+	of_node_put(np);
+
+	if (!rmem)
+		return -ENODEV;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	err = devm_request_irq(dev, irq, airoha_npu_mbox_handler,
+			       IRQF_SHARED, "airoha-npu-mbox", npu);
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(npu->cores); i++) {
+		struct airoha_npu_core *core = &npu->cores[i];
+
+		spin_lock_init(&core->lock);
+		core->npu = npu;
+
+		irq = platform_get_irq(pdev, i + 1);
+		if (irq < 0)
+			return irq;
+
+		err = devm_request_irq(dev, irq, airoha_npu_wdt_handler,
+				       IRQF_SHARED, "airoha-npu-wdt", core);
+		if (err)
+			return err;
+
+		INIT_WORK(&core->wdt_work, airoha_npu_wdt_work);
+	}
+
+	err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	err = airoha_npu_run_firmware(dev, base, rmem);
+	if (err)
+		return dev_err_probe(dev, err, "failed to run npu firmware\n");
+
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(10),
+		     rmem->base + NPU_EN7581_FIRMWARE_RV32_MAX_SIZE);
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(11), 0x40000); /* SRAM 256K */
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(12), 0);
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(21), 1);
+	msleep(100);
+
+	/* setting booting address */
+	for (i = 0; i < NPU_NUM_CORES; i++)
+		regmap_write(npu->regmap, REG_CR_BOOT_BASE(i), rmem->base);
+	usleep_range(1000, 2000);
+
+	/* enable NPU cores */
+	/* do not start core3 since it is used for WiFi offloading */
+	regmap_write(npu->regmap, REG_CR_BOOT_CONFIG, 0xf7);
+	regmap_write(npu->regmap, REG_CR_BOOT_TRIGGER, 0x1);
+	msleep(100);
+
+	platform_set_drvdata(pdev, npu);
+
+	return 0;
+}
+
+static void airoha_npu_remove(struct platform_device *pdev)
+{
+	struct airoha_npu *npu = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(npu->cores); i++)
+		cancel_work_sync(&npu->cores[i].wdt_work);
+}
+
+static struct platform_driver airoha_npu_driver = {
+	.probe = airoha_npu_probe,
+	.remove = airoha_npu_remove,
+	.driver = {
+		.name = "airoha-npu",
+		.of_match_table = of_airoha_npu_match,
+	},
+};
+module_platform_driver(airoha_npu_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("Airoha Network Processor Unit driver");
diff --git a/drivers/net/ethernet/airoha/airoha_npu.h b/drivers/net/ethernet/airoha/airoha_npu.h
new file mode 100644
index 000000000000..98ec3be74ce4
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_npu.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#define NPU_NUM_CORES		8
+
+struct airoha_npu {
+	struct device *dev;
+	struct regmap *regmap;
+
+	struct airoha_npu_core {
+		struct airoha_npu *npu;
+		/* protect concurrent npu memory accesses */
+		spinlock_t lock;
+		struct work_struct wdt_work;
+	} cores[NPU_NUM_CORES];
+
+	struct airoha_foe_stats __iomem *stats;
+
+	struct {
+		int (*ppe_init)(struct airoha_npu *npu);
+		int (*ppe_deinit)(struct airoha_npu *npu);
+		int (*ppe_flush_sram_entries)(struct airoha_npu *npu,
+					      dma_addr_t foe_addr,
+					      int sram_num_entries);
+		int (*ppe_foe_commit_entry)(struct airoha_npu *npu,
+					    dma_addr_t foe_addr,
+					    u32 entry_size, u32 hash,
+					    bool ppe2);
+	} ops;
+};
+
+struct airoha_npu *airoha_npu_get(struct device *dev, dma_addr_t *stats_addr);
+void airoha_npu_put(struct airoha_npu *npu);
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
new file mode 100644
index 000000000000..0e217acfc5ef
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -0,0 +1,1343 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/rhashtable.h>
+#include <net/ipv6.h>
+#include <net/pkt_cls.h>
+
+#include "airoha_npu.h"
+#include "airoha_regs.h"
+#include "airoha_eth.h"
+
+static DEFINE_MUTEX(flow_offload_mutex);
+static DEFINE_SPINLOCK(ppe_lock);
+
+static const struct rhashtable_params airoha_flow_table_params = {
+	.head_offset = offsetof(struct airoha_flow_table_entry, node),
+	.key_offset = offsetof(struct airoha_flow_table_entry, cookie),
+	.key_len = sizeof(unsigned long),
+	.automatic_shrinking = true,
+};
+
+static const struct rhashtable_params airoha_l2_flow_table_params = {
+	.head_offset = offsetof(struct airoha_flow_table_entry, l2_node),
+	.key_offset = offsetof(struct airoha_flow_table_entry, data.bridge),
+	.key_len = 2 * ETH_ALEN,
+	.automatic_shrinking = true,
+};
+
+static bool airoha_ppe2_is_enabled(struct airoha_eth *eth)
+{
+	return airoha_fe_rr(eth, REG_PPE_GLO_CFG(1)) & PPE_GLO_CFG_EN_MASK;
+}
+
+static u32 airoha_ppe_get_timestamp(struct airoha_ppe *ppe)
+{
+	u16 timestamp = airoha_fe_rr(ppe->eth, REG_FE_FOE_TS);
+
+	return FIELD_GET(AIROHA_FOE_IB1_BIND_TIMESTAMP, timestamp);
+}
+
+static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
+{
+	u32 sram_tb_size, sram_num_entries, dram_num_entries;
+	struct airoha_eth *eth = ppe->eth;
+	int i;
+
+	sram_tb_size = PPE_SRAM_NUM_ENTRIES * sizeof(struct airoha_foe_entry);
+	dram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(PPE_DRAM_NUM_ENTRIES);
+
+	for (i = 0; i < PPE_NUM; i++) {
+		int p;
+
+		airoha_fe_wr(eth, REG_PPE_TB_BASE(i),
+			     ppe->foe_dma + sram_tb_size);
+
+		airoha_fe_rmw(eth, REG_PPE_BND_AGE0(i),
+			      PPE_BIND_AGE0_DELTA_NON_L4 |
+			      PPE_BIND_AGE0_DELTA_UDP,
+			      FIELD_PREP(PPE_BIND_AGE0_DELTA_NON_L4, 1) |
+			      FIELD_PREP(PPE_BIND_AGE0_DELTA_UDP, 12));
+		airoha_fe_rmw(eth, REG_PPE_BND_AGE1(i),
+			      PPE_BIND_AGE1_DELTA_TCP_FIN |
+			      PPE_BIND_AGE1_DELTA_TCP,
+			      FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP_FIN, 1) |
+			      FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP, 7));
+
+		airoha_fe_rmw(eth, REG_PPE_TB_HASH_CFG(i),
+			      PPE_SRAM_TABLE_EN_MASK |
+			      PPE_SRAM_HASH1_EN_MASK |
+			      PPE_DRAM_TABLE_EN_MASK |
+			      PPE_SRAM_HASH0_MODE_MASK |
+			      PPE_SRAM_HASH1_MODE_MASK |
+			      PPE_DRAM_HASH0_MODE_MASK |
+			      PPE_DRAM_HASH1_MODE_MASK,
+			      FIELD_PREP(PPE_SRAM_TABLE_EN_MASK, 1) |
+			      FIELD_PREP(PPE_SRAM_HASH1_EN_MASK, 1) |
+			      FIELD_PREP(PPE_SRAM_HASH1_MODE_MASK, 1) |
+			      FIELD_PREP(PPE_DRAM_HASH1_MODE_MASK, 3));
+
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(i),
+			      PPE_TB_CFG_SEARCH_MISS_MASK |
+			      PPE_TB_CFG_KEEPALIVE_MASK |
+			      PPE_TB_ENTRY_SIZE_MASK,
+			      FIELD_PREP(PPE_TB_CFG_SEARCH_MISS_MASK, 3) |
+			      FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0));
+
+		airoha_fe_wr(eth, REG_PPE_HASH_SEED(i), PPE_HASH_SEED);
+
+		for (p = 0; p < ARRAY_SIZE(eth->ports); p++)
+			airoha_fe_rmw(eth, REG_PPE_MTU(i, p),
+				      FP0_EGRESS_MTU_MASK |
+				      FP1_EGRESS_MTU_MASK,
+				      FIELD_PREP(FP0_EGRESS_MTU_MASK,
+						 AIROHA_MAX_MTU) |
+				      FIELD_PREP(FP1_EGRESS_MTU_MASK,
+						 AIROHA_MAX_MTU));
+	}
+
+	if (airoha_ppe2_is_enabled(eth)) {
+		sram_num_entries =
+			PPE_RAM_NUM_ENTRIES_SHIFT(PPE1_SRAM_NUM_DATA_ENTRIES);
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(0),
+			      PPE_SRAM_TB_NUM_ENTRY_MASK |
+			      PPE_DRAM_TB_NUM_ENTRY_MASK,
+			      FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK,
+					 sram_num_entries) |
+			      FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK,
+					 dram_num_entries));
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(1),
+			      PPE_SRAM_TB_NUM_ENTRY_MASK |
+			      PPE_DRAM_TB_NUM_ENTRY_MASK,
+			      FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK,
+					 sram_num_entries) |
+			      FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK,
+					 dram_num_entries));
+	} else {
+		sram_num_entries =
+			PPE_RAM_NUM_ENTRIES_SHIFT(PPE_SRAM_NUM_DATA_ENTRIES);
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(0),
+			      PPE_SRAM_TB_NUM_ENTRY_MASK |
+			      PPE_DRAM_TB_NUM_ENTRY_MASK,
+			      FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK,
+					 sram_num_entries) |
+			      FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK,
+					 dram_num_entries));
+	}
+}
+
+static void airoha_ppe_flow_mangle_eth(const struct flow_action_entry *act, void *eth)
+{
+	void *dest = eth + act->mangle.offset;
+	const void *src = &act->mangle.val;
+
+	if (act->mangle.offset > 8)
+		return;
+
+	if (act->mangle.mask == 0xffff) {
+		src += 2;
+		dest += 2;
+	}
+
+	memcpy(dest, src, act->mangle.mask ? 2 : 4);
+}
+
+static int airoha_ppe_flow_mangle_ports(const struct flow_action_entry *act,
+					struct airoha_flow_data *data)
+{
+	u32 val = be32_to_cpu((__force __be32)act->mangle.val);
+
+	switch (act->mangle.offset) {
+	case 0:
+		if ((__force __be32)act->mangle.mask == ~cpu_to_be32(0xffff))
+			data->dst_port = cpu_to_be16(val);
+		else
+			data->src_port = cpu_to_be16(val >> 16);
+		break;
+	case 2:
+		data->dst_port = cpu_to_be16(val);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_flow_mangle_ipv4(const struct flow_action_entry *act,
+				       struct airoha_flow_data *data)
+{
+	__be32 *dest;
+
+	switch (act->mangle.offset) {
+	case offsetof(struct iphdr, saddr):
+		dest = &data->v4.src_addr;
+		break;
+	case offsetof(struct iphdr, daddr):
+		dest = &data->v4.dst_addr;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	memcpy(dest, &act->mangle.val, sizeof(u32));
+
+	return 0;
+}
+
+static int airoha_get_dsa_port(struct net_device **dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	struct dsa_port *dp = dsa_port_from_netdev(*dev);
+
+	if (IS_ERR(dp))
+		return -ENODEV;
+
+	*dev = dsa_port_to_conduit(dp);
+	return dp->index;
+#else
+	return -ENODEV;
+#endif
+}
+
+static void airoha_ppe_foe_set_bridge_addrs(struct airoha_foe_bridge *br,
+					    struct ethhdr *eh)
+{
+	br->dest_mac_hi = get_unaligned_be32(eh->h_dest);
+	br->dest_mac_lo = get_unaligned_be16(eh->h_dest + 4);
+	br->src_mac_hi = get_unaligned_be16(eh->h_source);
+	br->src_mac_lo = get_unaligned_be32(eh->h_source + 2);
+}
+
+static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
+					struct airoha_foe_entry *hwe,
+					struct net_device *dev, int type,
+					struct airoha_flow_data *data,
+					int l4proto)
+{
+	int dsa_port = airoha_get_dsa_port(&dev);
+	struct airoha_foe_mac_info_common *l2;
+	u32 qdata, ports_pad, val;
+	u8 smac_id = 0xf;
+
+	memset(hwe, 0, sizeof(*hwe));
+
+	val = FIELD_PREP(AIROHA_FOE_IB1_BIND_STATE, AIROHA_FOE_STATE_BIND) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_PACKET_TYPE, type) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_UDP, l4proto == IPPROTO_UDP) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_VLAN_LAYER, data->vlan.num) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_VPM, data->vlan.num) |
+	      AIROHA_FOE_IB1_BIND_TTL;
+	hwe->ib1 = val;
+
+	val = FIELD_PREP(AIROHA_FOE_IB2_PORT_AG, 0x1f) |
+	      AIROHA_FOE_IB2_PSE_QOS;
+	if (dsa_port >= 0)
+		val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ, dsa_port);
+
+	if (dev) {
+		struct airoha_gdm_port *port = netdev_priv(dev);
+		u8 pse_port;
+
+		if (!airoha_is_valid_gdm_port(eth, port))
+			return -EINVAL;
+
+		if (dsa_port >= 0)
+			pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id;
+		else
+			pse_port = 2; /* uplink relies on GDM2 loopback */
+		val |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, pse_port);
+
+		/* For downlink traffic consume SRAM memory for hw forwarding
+		 * descriptors queue.
+		 */
+		if (airhoa_is_lan_gdm_port(port))
+			val |= AIROHA_FOE_IB2_FAST_PATH;
+
+		smac_id = port->id;
+	}
+
+	if (is_multicast_ether_addr(data->eth.h_dest))
+		val |= AIROHA_FOE_IB2_MULTICAST;
+
+	ports_pad = 0xa5a5a500 | (l4proto & 0xff);
+	if (type == PPE_PKT_TYPE_IPV4_ROUTE)
+		hwe->ipv4.orig_tuple.ports = ports_pad;
+	if (type == PPE_PKT_TYPE_IPV6_ROUTE_3T)
+		hwe->ipv6.ports = ports_pad;
+
+	qdata = FIELD_PREP(AIROHA_FOE_SHAPER_ID, 0x7f);
+	if (type == PPE_PKT_TYPE_BRIDGE) {
+		airoha_ppe_foe_set_bridge_addrs(&hwe->bridge, &data->eth);
+		hwe->bridge.data = qdata;
+		hwe->bridge.ib2 = val;
+		l2 = &hwe->bridge.l2.common;
+	} else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		hwe->ipv6.data = qdata;
+		hwe->ipv6.ib2 = val;
+		l2 = &hwe->ipv6.l2;
+	} else {
+		hwe->ipv4.data = qdata;
+		hwe->ipv4.ib2 = val;
+		l2 = &hwe->ipv4.l2.common;
+	}
+
+	l2->dest_mac_hi = get_unaligned_be32(data->eth.h_dest);
+	l2->dest_mac_lo = get_unaligned_be16(data->eth.h_dest + 4);
+	if (type <= PPE_PKT_TYPE_IPV4_DSLITE) {
+		l2->src_mac_hi = get_unaligned_be32(data->eth.h_source);
+		hwe->ipv4.l2.src_mac_lo =
+			get_unaligned_be16(data->eth.h_source + 4);
+	} else {
+		l2->src_mac_hi = FIELD_PREP(AIROHA_FOE_MAC_SMAC_ID, smac_id);
+	}
+
+	if (data->vlan.num) {
+		l2->etype = dsa_port >= 0 ? BIT(dsa_port) : 0;
+		l2->vlan1 = data->vlan.hdr[0].id;
+		if (data->vlan.num == 2)
+			l2->vlan2 = data->vlan.hdr[1].id;
+	} else if (dsa_port >= 0) {
+		l2->etype = BIT(15) | BIT(dsa_port);
+	} else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		l2->etype = ETH_P_IPV6;
+	} else {
+		l2->etype = ETH_P_IP;
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_foe_entry_set_ipv4_tuple(struct airoha_foe_entry *hwe,
+					       struct airoha_flow_data *data,
+					       bool egress)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	struct airoha_foe_ipv4_tuple *t;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV4_HNAPT:
+		if (egress) {
+			t = &hwe->ipv4.new_tuple;
+			break;
+		}
+		fallthrough;
+	case PPE_PKT_TYPE_IPV4_DSLITE:
+	case PPE_PKT_TYPE_IPV4_ROUTE:
+		t = &hwe->ipv4.orig_tuple;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	t->src_ip = be32_to_cpu(data->v4.src_addr);
+	t->dest_ip = be32_to_cpu(data->v4.dst_addr);
+
+	if (type != PPE_PKT_TYPE_IPV4_ROUTE) {
+		t->src_port = be16_to_cpu(data->src_port);
+		t->dest_port = be16_to_cpu(data->dst_port);
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_foe_entry_set_ipv6_tuple(struct airoha_foe_entry *hwe,
+					       struct airoha_flow_data *data)
+
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 *src, *dest;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+	case PPE_PKT_TYPE_IPV6_6RD:
+		hwe->ipv6.src_port = be16_to_cpu(data->src_port);
+		hwe->ipv6.dest_port = be16_to_cpu(data->dst_port);
+		fallthrough;
+	case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		src = hwe->ipv6.src_ip;
+		dest = hwe->ipv6.dest_ip;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	ipv6_addr_be32_to_cpu(src, data->v6.src_addr.s6_addr32);
+	ipv6_addr_be32_to_cpu(dest, data->v6.dst_addr.s6_addr32);
+
+	return 0;
+}
+
+static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 hash, hv1, hv2, hv3;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV4_ROUTE:
+	case PPE_PKT_TYPE_IPV4_HNAPT:
+		hv1 = hwe->ipv4.orig_tuple.ports;
+		hv2 = hwe->ipv4.orig_tuple.dest_ip;
+		hv3 = hwe->ipv4.orig_tuple.src_ip;
+		break;
+	case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+	case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+		hv1 = hwe->ipv6.src_ip[3] ^ hwe->ipv6.dest_ip[3];
+		hv1 ^= hwe->ipv6.ports;
+
+		hv2 = hwe->ipv6.src_ip[2] ^ hwe->ipv6.dest_ip[2];
+		hv2 ^= hwe->ipv6.dest_ip[0];
+
+		hv3 = hwe->ipv6.src_ip[1] ^ hwe->ipv6.dest_ip[1];
+		hv3 ^= hwe->ipv6.src_ip[0];
+		break;
+	case PPE_PKT_TYPE_BRIDGE: {
+		struct airoha_foe_mac_info *l2 = &hwe->bridge.l2;
+
+		hv1 = l2->common.src_mac_hi & 0xffff;
+		hv1 = hv1 << 16 | l2->src_mac_lo;
+
+		hv2 = l2->common.dest_mac_lo;
+		hv2 = hv2 << 16;
+		hv2 = hv2 | ((l2->common.src_mac_hi & 0xffff0000) >> 16);
+
+		hv3 = l2->common.dest_mac_hi;
+		break;
+	}
+	case PPE_PKT_TYPE_IPV4_DSLITE:
+	case PPE_PKT_TYPE_IPV6_6RD:
+	default:
+		WARN_ON_ONCE(1);
+		return PPE_HASH_MASK;
+	}
+
+	hash = (hv1 & hv2) | ((~hv1) & hv3);
+	hash = (hash >> 24) | ((hash & 0xffffff) << 8);
+	hash ^= hv1 ^ hv2 ^ hv3;
+	hash ^= hash >> 16;
+	hash &= PPE_NUM_ENTRIES - 1;
+
+	return hash;
+}
+
+static u32 airoha_ppe_foe_get_flow_stats_index(struct airoha_ppe *ppe, u32 hash)
+{
+	if (!airoha_ppe2_is_enabled(ppe->eth))
+		return hash;
+
+	return hash >= PPE_STATS_NUM_ENTRIES ? hash - PPE1_STATS_NUM_ENTRIES
+					     : hash;
+}
+
+static void airoha_ppe_foe_flow_stat_entry_reset(struct airoha_ppe *ppe,
+						 struct airoha_npu *npu,
+						 int index)
+{
+	memset_io(&npu->stats[index], 0, sizeof(*npu->stats));
+	memset(&ppe->foe_stats[index], 0, sizeof(*ppe->foe_stats));
+}
+
+static void airoha_ppe_foe_flow_stats_reset(struct airoha_ppe *ppe,
+					    struct airoha_npu *npu)
+{
+	int i;
+
+	for (i = 0; i < PPE_STATS_NUM_ENTRIES; i++)
+		airoha_ppe_foe_flow_stat_entry_reset(ppe, npu, i);
+}
+
+static void airoha_ppe_foe_flow_stats_update(struct airoha_ppe *ppe,
+					     struct airoha_npu *npu,
+					     struct airoha_foe_entry *hwe,
+					     u32 hash)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 index, pse_port, val, *data, *ib2, *meter;
+	u8 nbq;
+
+	index = airoha_ppe_foe_get_flow_stats_index(ppe, hash);
+	if (index >= PPE_STATS_NUM_ENTRIES)
+		return;
+
+	if (type == PPE_PKT_TYPE_BRIDGE) {
+		data = &hwe->bridge.data;
+		ib2 = &hwe->bridge.ib2;
+		meter = &hwe->bridge.l2.meter;
+	} else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		data = &hwe->ipv6.data;
+		ib2 = &hwe->ipv6.ib2;
+		meter = &hwe->ipv6.meter;
+	} else {
+		data = &hwe->ipv4.data;
+		ib2 = &hwe->ipv4.ib2;
+		meter = &hwe->ipv4.l2.meter;
+	}
+
+	airoha_ppe_foe_flow_stat_entry_reset(ppe, npu, index);
+
+	val = FIELD_GET(AIROHA_FOE_CHANNEL | AIROHA_FOE_QID, *data);
+	*data = (*data & ~AIROHA_FOE_ACTDP) |
+		FIELD_PREP(AIROHA_FOE_ACTDP, val);
+
+	val = *ib2 & (AIROHA_FOE_IB2_NBQ | AIROHA_FOE_IB2_PSE_PORT |
+		      AIROHA_FOE_IB2_PSE_QOS | AIROHA_FOE_IB2_FAST_PATH);
+	*meter |= FIELD_PREP(AIROHA_FOE_TUNNEL_MTU, val);
+
+	pse_port = FIELD_GET(AIROHA_FOE_IB2_PSE_PORT, *ib2);
+	nbq = pse_port == 1 ? 6 : 5;
+	*ib2 &= ~(AIROHA_FOE_IB2_NBQ | AIROHA_FOE_IB2_PSE_PORT |
+		  AIROHA_FOE_IB2_PSE_QOS);
+	*ib2 |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, 6) |
+		FIELD_PREP(AIROHA_FOE_IB2_NBQ, nbq);
+}
+
+struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
+						  u32 hash)
+{
+	if (hash < PPE_SRAM_NUM_ENTRIES) {
+		u32 *hwe = ppe->foe + hash * sizeof(struct airoha_foe_entry);
+		struct airoha_eth *eth = ppe->eth;
+		bool ppe2;
+		u32 val;
+		int i;
+
+		ppe2 = airoha_ppe2_is_enabled(ppe->eth) &&
+		       hash >= PPE1_SRAM_NUM_ENTRIES;
+		airoha_fe_wr(ppe->eth, REG_PPE_RAM_CTRL(ppe2),
+			     FIELD_PREP(PPE_SRAM_CTRL_ENTRY_MASK, hash) |
+			     PPE_SRAM_CTRL_REQ_MASK);
+		if (read_poll_timeout_atomic(airoha_fe_rr, val,
+					     val & PPE_SRAM_CTRL_ACK_MASK,
+					     10, 100, false, eth,
+					     REG_PPE_RAM_CTRL(ppe2)))
+			return NULL;
+
+		for (i = 0; i < sizeof(struct airoha_foe_entry) / 4; i++)
+			hwe[i] = airoha_fe_rr(eth,
+					      REG_PPE_RAM_ENTRY(ppe2, i));
+	}
+
+	return ppe->foe + hash * sizeof(struct airoha_foe_entry);
+}
+
+static bool airoha_ppe_foe_compare_entry(struct airoha_flow_table_entry *e,
+					 struct airoha_foe_entry *hwe)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, e->data.ib1);
+	int len;
+
+	if ((hwe->ib1 ^ e->data.ib1) & AIROHA_FOE_IB1_BIND_UDP)
+		return false;
+
+	if (type > PPE_PKT_TYPE_IPV4_DSLITE)
+		len = offsetof(struct airoha_foe_entry, ipv6.data);
+	else
+		len = offsetof(struct airoha_foe_entry, ipv4.ib2);
+
+	return !memcmp(&e->data.d, &hwe->d, len - sizeof(hwe->ib1));
+}
+
+static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe,
+				       struct airoha_foe_entry *e,
+				       u32 hash)
+{
+	struct airoha_foe_entry *hwe = ppe->foe + hash * sizeof(*hwe);
+	u32 ts = airoha_ppe_get_timestamp(ppe);
+	struct airoha_eth *eth = ppe->eth;
+	struct airoha_npu *npu;
+	int err = 0;
+
+	memcpy(&hwe->d, &e->d, sizeof(*hwe) - sizeof(hwe->ib1));
+	wmb();
+
+	e->ib1 &= ~AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	e->ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_TIMESTAMP, ts);
+	hwe->ib1 = e->ib1;
+
+	rcu_read_lock();
+
+	npu = rcu_dereference(eth->npu);
+	if (!npu) {
+		err = -ENODEV;
+		goto unlock;
+	}
+
+	airoha_ppe_foe_flow_stats_update(ppe, npu, hwe, hash);
+
+	if (hash < PPE_SRAM_NUM_ENTRIES) {
+		dma_addr_t addr = ppe->foe_dma + hash * sizeof(*hwe);
+		bool ppe2 = airoha_ppe2_is_enabled(eth) &&
+			    hash >= PPE1_SRAM_NUM_ENTRIES;
+
+		err = npu->ops.ppe_foe_commit_entry(npu, addr, sizeof(*hwe),
+						    hash, ppe2);
+	}
+unlock:
+	rcu_read_unlock();
+
+	return err;
+}
+
+static void airoha_ppe_foe_remove_flow(struct airoha_ppe *ppe,
+				       struct airoha_flow_table_entry *e)
+{
+	lockdep_assert_held(&ppe_lock);
+
+	hlist_del_init(&e->list);
+	if (e->hash != 0xffff) {
+		e->data.ib1 &= ~AIROHA_FOE_IB1_BIND_STATE;
+		e->data.ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_STATE,
+					  AIROHA_FOE_STATE_INVALID);
+		airoha_ppe_foe_commit_entry(ppe, &e->data, e->hash);
+		e->hash = 0xffff;
+	}
+	if (e->type == FLOW_TYPE_L2_SUBFLOW) {
+		hlist_del_init(&e->l2_subflow_node);
+		kfree(e);
+	}
+}
+
+static void airoha_ppe_foe_remove_l2_flow(struct airoha_ppe *ppe,
+					  struct airoha_flow_table_entry *e)
+{
+	struct hlist_head *head = &e->l2_flows;
+	struct hlist_node *n;
+
+	lockdep_assert_held(&ppe_lock);
+
+	rhashtable_remove_fast(&ppe->l2_flows, &e->l2_node,
+			       airoha_l2_flow_table_params);
+	hlist_for_each_entry_safe(e, n, head, l2_subflow_node)
+		airoha_ppe_foe_remove_flow(ppe, e);
+}
+
+static void airoha_ppe_foe_flow_remove_entry(struct airoha_ppe *ppe,
+					     struct airoha_flow_table_entry *e)
+{
+	spin_lock_bh(&ppe_lock);
+
+	if (e->type == FLOW_TYPE_L2)
+		airoha_ppe_foe_remove_l2_flow(ppe, e);
+	else
+		airoha_ppe_foe_remove_flow(ppe, e);
+
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int
+airoha_ppe_foe_commit_subflow_entry(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e,
+				    u32 hash)
+{
+	u32 mask = AIROHA_FOE_IB1_BIND_PACKET_TYPE | AIROHA_FOE_IB1_BIND_UDP;
+	struct airoha_foe_entry *hwe_p, hwe;
+	struct airoha_flow_table_entry *f;
+	int type;
+
+	hwe_p = airoha_ppe_foe_get_entry(ppe, hash);
+	if (!hwe_p)
+		return -EINVAL;
+
+	f = kzalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return -ENOMEM;
+
+	hlist_add_head(&f->l2_subflow_node, &e->l2_flows);
+	f->type = FLOW_TYPE_L2_SUBFLOW;
+	f->hash = hash;
+
+	memcpy(&hwe, hwe_p, sizeof(*hwe_p));
+	hwe.ib1 = (hwe.ib1 & mask) | (e->data.ib1 & ~mask);
+
+	type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe.ib1);
+	if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		memcpy(&hwe.ipv6.l2, &e->data.bridge.l2, sizeof(hwe.ipv6.l2));
+		hwe.ipv6.ib2 = e->data.bridge.ib2;
+		/* setting smac_id to 0xf instruct the hw to keep original
+		 * source mac address
+		 */
+		hwe.ipv6.l2.src_mac_hi = FIELD_PREP(AIROHA_FOE_MAC_SMAC_ID,
+						    0xf);
+	} else {
+		memcpy(&hwe.bridge.l2, &e->data.bridge.l2,
+		       sizeof(hwe.bridge.l2));
+		hwe.bridge.ib2 = e->data.bridge.ib2;
+		if (type == PPE_PKT_TYPE_IPV4_HNAPT)
+			memcpy(&hwe.ipv4.new_tuple, &hwe.ipv4.orig_tuple,
+			       sizeof(hwe.ipv4.new_tuple));
+	}
+
+	hwe.bridge.data = e->data.bridge.data;
+	airoha_ppe_foe_commit_entry(ppe, &hwe, hash);
+
+	return 0;
+}
+
+static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe,
+					struct sk_buff *skb,
+					u32 hash)
+{
+	struct airoha_flow_table_entry *e;
+	struct airoha_foe_bridge br = {};
+	struct airoha_foe_entry *hwe;
+	bool commit_done = false;
+	struct hlist_node *n;
+	u32 index, state;
+
+	spin_lock_bh(&ppe_lock);
+
+	hwe = airoha_ppe_foe_get_entry(ppe, hash);
+	if (!hwe)
+		goto unlock;
+
+	state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+	if (state == AIROHA_FOE_STATE_BIND)
+		goto unlock;
+
+	index = airoha_ppe_foe_get_entry_hash(hwe);
+	hlist_for_each_entry_safe(e, n, &ppe->foe_flow[index], list) {
+		if (e->type == FLOW_TYPE_L2_SUBFLOW) {
+			state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+			if (state != AIROHA_FOE_STATE_BIND) {
+				e->hash = 0xffff;
+				airoha_ppe_foe_remove_flow(ppe, e);
+			}
+			continue;
+		}
+
+		if (commit_done || !airoha_ppe_foe_compare_entry(e, hwe)) {
+			e->hash = 0xffff;
+			continue;
+		}
+
+		airoha_ppe_foe_commit_entry(ppe, &e->data, hash);
+		commit_done = true;
+		e->hash = hash;
+	}
+
+	if (commit_done)
+		goto unlock;
+
+	airoha_ppe_foe_set_bridge_addrs(&br, eth_hdr(skb));
+	e = rhashtable_lookup_fast(&ppe->l2_flows, &br,
+				   airoha_l2_flow_table_params);
+	if (e)
+		airoha_ppe_foe_commit_subflow_entry(ppe, e, hash);
+unlock:
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int
+airoha_ppe_foe_l2_flow_commit_entry(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e)
+{
+	struct airoha_flow_table_entry *prev;
+
+	e->type = FLOW_TYPE_L2;
+	prev = rhashtable_lookup_get_insert_fast(&ppe->l2_flows, &e->l2_node,
+						 airoha_l2_flow_table_params);
+	if (!prev)
+		return 0;
+
+	if (IS_ERR(prev))
+		return PTR_ERR(prev);
+
+	return rhashtable_replace_fast(&ppe->l2_flows, &prev->l2_node,
+				       &e->l2_node,
+				       airoha_l2_flow_table_params);
+}
+
+static int airoha_ppe_foe_flow_commit_entry(struct airoha_ppe *ppe,
+					    struct airoha_flow_table_entry *e)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, e->data.ib1);
+	u32 hash;
+
+	if (type == PPE_PKT_TYPE_BRIDGE)
+		return airoha_ppe_foe_l2_flow_commit_entry(ppe, e);
+
+	hash = airoha_ppe_foe_get_entry_hash(&e->data);
+	e->type = FLOW_TYPE_L4;
+	e->hash = 0xffff;
+
+	spin_lock_bh(&ppe_lock);
+	hlist_add_head(&e->list, &ppe->foe_flow[hash]);
+	spin_unlock_bh(&ppe_lock);
+
+	return 0;
+}
+
+static int airoha_ppe_get_entry_idle_time(struct airoha_ppe *ppe, u32 ib1)
+{
+	u32 state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
+	u32 ts, ts_mask, now = airoha_ppe_get_timestamp(ppe);
+	int idle;
+
+	if (state == AIROHA_FOE_STATE_BIND) {
+		ts = FIELD_GET(AIROHA_FOE_IB1_BIND_TIMESTAMP, ib1);
+		ts_mask = AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	} else {
+		ts = FIELD_GET(AIROHA_FOE_IB1_UNBIND_TIMESTAMP, ib1);
+		now = FIELD_GET(AIROHA_FOE_IB1_UNBIND_TIMESTAMP, now);
+		ts_mask = AIROHA_FOE_IB1_UNBIND_TIMESTAMP;
+	}
+	idle = now - ts;
+
+	return idle < 0 ? idle + ts_mask + 1 : idle;
+}
+
+static void
+airoha_ppe_foe_flow_l2_entry_update(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e)
+{
+	int min_idle = airoha_ppe_get_entry_idle_time(ppe, e->data.ib1);
+	struct airoha_flow_table_entry *iter;
+	struct hlist_node *n;
+
+	lockdep_assert_held(&ppe_lock);
+
+	hlist_for_each_entry_safe(iter, n, &e->l2_flows, l2_subflow_node) {
+		struct airoha_foe_entry *hwe;
+		u32 ib1, state;
+		int idle;
+
+		hwe = airoha_ppe_foe_get_entry(ppe, iter->hash);
+		if (!hwe)
+			continue;
+
+		ib1 = READ_ONCE(hwe->ib1);
+		state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
+		if (state != AIROHA_FOE_STATE_BIND) {
+			iter->hash = 0xffff;
+			airoha_ppe_foe_remove_flow(ppe, iter);
+			continue;
+		}
+
+		idle = airoha_ppe_get_entry_idle_time(ppe, ib1);
+		if (idle >= min_idle)
+			continue;
+
+		min_idle = idle;
+		e->data.ib1 &= ~AIROHA_FOE_IB1_BIND_TIMESTAMP;
+		e->data.ib1 |= ib1 & AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	}
+}
+
+static void airoha_ppe_foe_flow_entry_update(struct airoha_ppe *ppe,
+					     struct airoha_flow_table_entry *e)
+{
+	struct airoha_foe_entry *hwe_p, hwe = {};
+
+	spin_lock_bh(&ppe_lock);
+
+	if (e->type == FLOW_TYPE_L2) {
+		airoha_ppe_foe_flow_l2_entry_update(ppe, e);
+		goto unlock;
+	}
+
+	if (e->hash == 0xffff)
+		goto unlock;
+
+	hwe_p = airoha_ppe_foe_get_entry(ppe, e->hash);
+	if (!hwe_p)
+		goto unlock;
+
+	memcpy(&hwe, hwe_p, sizeof(*hwe_p));
+	if (!airoha_ppe_foe_compare_entry(e, &hwe)) {
+		e->hash = 0xffff;
+		goto unlock;
+	}
+
+	e->data.ib1 = hwe.ib1;
+unlock:
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int airoha_ppe_entry_idle_time(struct airoha_ppe *ppe,
+				      struct airoha_flow_table_entry *e)
+{
+	airoha_ppe_foe_flow_entry_update(ppe, e);
+
+	return airoha_ppe_get_entry_idle_time(ppe, e->data.ib1);
+}
+
+static int airoha_ppe_flow_offload_replace(struct airoha_gdm_port *port,
+					   struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct airoha_eth *eth = port->qdma->eth;
+	struct airoha_flow_table_entry *e;
+	struct airoha_flow_data data = {};
+	struct net_device *odev = NULL;
+	struct flow_action_entry *act;
+	struct airoha_foe_entry hwe;
+	int err, i, offload_type;
+	u16 addr_type = 0;
+	u8 l4proto = 0;
+
+	if (rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params))
+		return -EEXIST;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META))
+		return -EOPNOTSUPP;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
+		if (flow_rule_has_control_flags(match.mask->flags,
+						f->common.extack))
+			return -EOPNOTSUPP;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		l4proto = match.key->ip_proto;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	switch (addr_type) {
+	case 0:
+		offload_type = PPE_PKT_TYPE_BRIDGE;
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+			struct flow_match_eth_addrs match;
+
+			flow_rule_match_eth_addrs(rule, &match);
+			memcpy(data.eth.h_dest, match.key->dst, ETH_ALEN);
+			memcpy(data.eth.h_source, match.key->src, ETH_ALEN);
+		} else {
+			return -EOPNOTSUPP;
+		}
+		break;
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		offload_type = PPE_PKT_TYPE_IPV4_HNAPT;
+		break;
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		offload_type = PPE_PKT_TYPE_IPV6_ROUTE_5T;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_MANGLE:
+			if (offload_type == PPE_PKT_TYPE_BRIDGE)
+				return -EOPNOTSUPP;
+
+			if (act->mangle.htype == FLOW_ACT_MANGLE_HDR_TYPE_ETH)
+				airoha_ppe_flow_mangle_eth(act, &data.eth);
+			break;
+		case FLOW_ACTION_REDIRECT:
+			odev = act->dev;
+			break;
+		case FLOW_ACTION_CSUM:
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+			if (data.vlan.num == 2 ||
+			    act->vlan.proto != htons(ETH_P_8021Q))
+				return -EOPNOTSUPP;
+
+			data.vlan.hdr[data.vlan.num].id = act->vlan.vid;
+			data.vlan.hdr[data.vlan.num].proto = act->vlan.proto;
+			data.vlan.num++;
+			break;
+		case FLOW_ACTION_VLAN_POP:
+			break;
+		case FLOW_ACTION_PPPOE_PUSH:
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (!is_valid_ether_addr(data.eth.h_source) ||
+	    !is_valid_ether_addr(data.eth.h_dest))
+		return -EINVAL;
+
+	err = airoha_ppe_foe_entry_prepare(eth, &hwe, odev, offload_type,
+					   &data, l4proto);
+	if (err)
+		return err;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports ports;
+
+		if (offload_type == PPE_PKT_TYPE_BRIDGE)
+			return -EOPNOTSUPP;
+
+		flow_rule_match_ports(rule, &ports);
+		data.src_port = ports.key->src;
+		data.dst_port = ports.key->dst;
+	} else if (offload_type != PPE_PKT_TYPE_BRIDGE) {
+		return -EOPNOTSUPP;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		struct flow_match_ipv4_addrs addrs;
+
+		flow_rule_match_ipv4_addrs(rule, &addrs);
+		data.v4.src_addr = addrs.key->src;
+		data.v4.dst_addr = addrs.key->dst;
+		airoha_ppe_foe_entry_set_ipv4_tuple(&hwe, &data, false);
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		struct flow_match_ipv6_addrs addrs;
+
+		flow_rule_match_ipv6_addrs(rule, &addrs);
+
+		data.v6.src_addr = addrs.key->src;
+		data.v6.dst_addr = addrs.key->dst;
+		airoha_ppe_foe_entry_set_ipv6_tuple(&hwe, &data);
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		if (act->id != FLOW_ACTION_MANGLE)
+			continue;
+
+		if (offload_type == PPE_PKT_TYPE_BRIDGE)
+			return -EOPNOTSUPP;
+
+		switch (act->mangle.htype) {
+		case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+		case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+			err = airoha_ppe_flow_mangle_ports(act, &data);
+			break;
+		case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+			err = airoha_ppe_flow_mangle_ipv4(act, &data);
+			break;
+		case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
+			/* handled earlier */
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+		if (err)
+			return err;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		err = airoha_ppe_foe_entry_set_ipv4_tuple(&hwe, &data, true);
+		if (err)
+			return err;
+	}
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (!e)
+		return -ENOMEM;
+
+	e->cookie = f->cookie;
+	memcpy(&e->data, &hwe, sizeof(e->data));
+
+	err = airoha_ppe_foe_flow_commit_entry(eth->ppe, e);
+	if (err)
+		goto free_entry;
+
+	err = rhashtable_insert_fast(&eth->flow_table, &e->node,
+				     airoha_flow_table_params);
+	if (err < 0)
+		goto remove_foe_entry;
+
+	return 0;
+
+remove_foe_entry:
+	airoha_ppe_foe_flow_remove_entry(eth->ppe, e);
+free_entry:
+	kfree(e);
+
+	return err;
+}
+
+static int airoha_ppe_flow_offload_destroy(struct airoha_gdm_port *port,
+					   struct flow_cls_offload *f)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	struct airoha_flow_table_entry *e;
+
+	e = rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params);
+	if (!e)
+		return -ENOENT;
+
+	airoha_ppe_foe_flow_remove_entry(eth->ppe, e);
+	rhashtable_remove_fast(&eth->flow_table, &e->node,
+			       airoha_flow_table_params);
+	kfree(e);
+
+	return 0;
+}
+
+void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash,
+				    struct airoha_foe_stats64 *stats)
+{
+	u32 index = airoha_ppe_foe_get_flow_stats_index(ppe, hash);
+	struct airoha_eth *eth = ppe->eth;
+	struct airoha_npu *npu;
+
+	if (index >= PPE_STATS_NUM_ENTRIES)
+		return;
+
+	rcu_read_lock();
+
+	npu = rcu_dereference(eth->npu);
+	if (npu) {
+		u64 packets = ppe->foe_stats[index].packets;
+		u64 bytes = ppe->foe_stats[index].bytes;
+		struct airoha_foe_stats npu_stats;
+
+		memcpy_fromio(&npu_stats, &npu->stats[index],
+			      sizeof(*npu->stats));
+		stats->packets = packets << 32 | npu_stats.packets;
+		stats->bytes = bytes << 32 | npu_stats.bytes;
+	}
+
+	rcu_read_unlock();
+}
+
+static int airoha_ppe_flow_offload_stats(struct airoha_gdm_port *port,
+					 struct flow_cls_offload *f)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	struct airoha_flow_table_entry *e;
+	u32 idle;
+
+	e = rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params);
+	if (!e)
+		return -ENOENT;
+
+	idle = airoha_ppe_entry_idle_time(eth->ppe, e);
+	f->stats.lastused = jiffies - idle * HZ;
+
+	if (e->hash != 0xffff) {
+		struct airoha_foe_stats64 stats = {};
+
+		airoha_ppe_foe_entry_get_stats(eth->ppe, e->hash, &stats);
+		f->stats.pkts += (stats.packets - e->stats.packets);
+		f->stats.bytes += (stats.bytes - e->stats.bytes);
+		e->stats = stats;
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_flow_offload_cmd(struct airoha_gdm_port *port,
+				       struct flow_cls_offload *f)
+{
+	switch (f->command) {
+	case FLOW_CLS_REPLACE:
+		return airoha_ppe_flow_offload_replace(port, f);
+	case FLOW_CLS_DESTROY:
+		return airoha_ppe_flow_offload_destroy(port, f);
+	case FLOW_CLS_STATS:
+		return airoha_ppe_flow_offload_stats(port, f);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int airoha_ppe_flush_sram_entries(struct airoha_ppe *ppe,
+					 struct airoha_npu *npu)
+{
+	int i, sram_num_entries = PPE_SRAM_NUM_ENTRIES;
+	struct airoha_foe_entry *hwe = ppe->foe;
+
+	if (airoha_ppe2_is_enabled(ppe->eth))
+		sram_num_entries = sram_num_entries / 2;
+
+	for (i = 0; i < sram_num_entries; i++)
+		memset(&hwe[i], 0, sizeof(*hwe));
+
+	return npu->ops.ppe_flush_sram_entries(npu, ppe->foe_dma,
+					       PPE_SRAM_NUM_ENTRIES);
+}
+
+static struct airoha_npu *airoha_ppe_npu_get(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu = airoha_npu_get(eth->dev,
+						&eth->ppe->foe_stats_dma);
+
+	if (IS_ERR(npu)) {
+		request_module("airoha-npu");
+		npu = airoha_npu_get(eth->dev, &eth->ppe->foe_stats_dma);
+	}
+
+	return npu;
+}
+
+static int airoha_ppe_offload_setup(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu = airoha_ppe_npu_get(eth);
+	int err;
+
+	if (IS_ERR(npu))
+		return PTR_ERR(npu);
+
+	err = npu->ops.ppe_init(npu);
+	if (err)
+		goto error_npu_put;
+
+	airoha_ppe_hw_init(eth->ppe);
+	err = airoha_ppe_flush_sram_entries(eth->ppe, npu);
+	if (err)
+		goto error_npu_put;
+
+	airoha_ppe_foe_flow_stats_reset(eth->ppe, npu);
+
+	rcu_assign_pointer(eth->npu, npu);
+	synchronize_rcu();
+
+	return 0;
+
+error_npu_put:
+	airoha_npu_put(npu);
+
+	return err;
+}
+
+int airoha_ppe_setup_tc_block_cb(struct net_device *dev, void *type_data)
+{
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct flow_cls_offload *cls = type_data;
+	struct airoha_eth *eth = port->qdma->eth;
+	int err = 0;
+
+	mutex_lock(&flow_offload_mutex);
+
+	if (!eth->npu)
+		err = airoha_ppe_offload_setup(eth);
+	if (!err)
+		err = airoha_ppe_flow_offload_cmd(port, cls);
+
+	mutex_unlock(&flow_offload_mutex);
+
+	return err;
+}
+
+void airoha_ppe_check_skb(struct airoha_ppe *ppe, struct sk_buff *skb,
+			  u16 hash)
+{
+	u16 now, diff;
+
+	if (hash > PPE_HASH_MASK)
+		return;
+
+	now = (u16)jiffies;
+	diff = now - ppe->foe_check_time[hash];
+	if (diff < HZ / 10)
+		return;
+
+	ppe->foe_check_time[hash] = now;
+	airoha_ppe_foe_insert_entry(ppe, skb, hash);
+}
+
+void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	struct net_device *dev = port->dev;
+	const u8 *addr = dev->dev_addr;
+	u32 val;
+
+	val = (addr[2] << 24) | (addr[3] << 16) | (addr[4] << 8) | addr[5];
+	airoha_fe_wr(eth, REG_UPDMEM_DATA(0), val);
+	airoha_fe_wr(eth, REG_UPDMEM_CTRL(0),
+		     FIELD_PREP(PPE_UPDMEM_ADDR_MASK, port->id) |
+		     PPE_UPDMEM_WR_MASK | PPE_UPDMEM_REQ_MASK);
+
+	val = (addr[0] << 8) | addr[1];
+	airoha_fe_wr(eth, REG_UPDMEM_DATA(0), val);
+	airoha_fe_wr(eth, REG_UPDMEM_CTRL(0),
+		     FIELD_PREP(PPE_UPDMEM_ADDR_MASK, port->id) |
+		     FIELD_PREP(PPE_UPDMEM_OFFSET_MASK, 1) |
+		     PPE_UPDMEM_WR_MASK | PPE_UPDMEM_REQ_MASK);
+}
+
+int airoha_ppe_init(struct airoha_eth *eth)
+{
+	struct airoha_ppe *ppe;
+	int foe_size, err;
+
+	ppe = devm_kzalloc(eth->dev, sizeof(*ppe), GFP_KERNEL);
+	if (!ppe)
+		return -ENOMEM;
+
+	foe_size = PPE_NUM_ENTRIES * sizeof(struct airoha_foe_entry);
+	ppe->foe = dmam_alloc_coherent(eth->dev, foe_size, &ppe->foe_dma,
+				       GFP_KERNEL);
+	if (!ppe->foe)
+		return -ENOMEM;
+
+	ppe->eth = eth;
+	eth->ppe = ppe;
+
+	ppe->foe_flow = devm_kzalloc(eth->dev,
+				     PPE_NUM_ENTRIES * sizeof(*ppe->foe_flow),
+				     GFP_KERNEL);
+	if (!ppe->foe_flow)
+		return -ENOMEM;
+
+	foe_size = PPE_STATS_NUM_ENTRIES * sizeof(*ppe->foe_stats);
+	if (foe_size) {
+		ppe->foe_stats = dmam_alloc_coherent(eth->dev, foe_size,
+						     &ppe->foe_stats_dma,
+						     GFP_KERNEL);
+		if (!ppe->foe_stats)
+			return -ENOMEM;
+	}
+
+	err = rhashtable_init(&eth->flow_table, &airoha_flow_table_params);
+	if (err)
+		return err;
+
+	err = rhashtable_init(&ppe->l2_flows, &airoha_l2_flow_table_params);
+	if (err)
+		goto error_flow_table_destroy;
+
+	err = airoha_ppe_debugfs_init(ppe);
+	if (err)
+		goto error_l2_flow_table_destroy;
+
+	return 0;
+
+error_l2_flow_table_destroy:
+	rhashtable_destroy(&ppe->l2_flows);
+error_flow_table_destroy:
+	rhashtable_destroy(&eth->flow_table);
+
+	return err;
+}
+
+void airoha_ppe_deinit(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu;
+
+	rcu_read_lock();
+	npu = rcu_dereference(eth->npu);
+	if (npu) {
+		npu->ops.ppe_deinit(npu);
+		airoha_npu_put(npu);
+	}
+	rcu_read_unlock();
+
+	rhashtable_destroy(&eth->ppe->l2_flows);
+	rhashtable_destroy(&eth->flow_table);
+	debugfs_remove(eth->ppe->debugfs_dir);
+}
diff --git a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
new file mode 100644
index 000000000000..05a756233f6a
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include "airoha_eth.h"
+
+static void airoha_debugfs_ppe_print_tuple(struct seq_file *m,
+					   void *src_addr, void *dest_addr,
+					   u16 *src_port, u16 *dest_port,
+					   bool ipv6)
+{
+	__be32 n_addr[IPV6_ADDR_WORDS];
+
+	if (ipv6) {
+		ipv6_addr_cpu_to_be32(n_addr, src_addr);
+		seq_printf(m, "%pI6", n_addr);
+	} else {
+		seq_printf(m, "%pI4h", src_addr);
+	}
+	if (src_port)
+		seq_printf(m, ":%d", *src_port);
+
+	seq_puts(m, "->");
+
+	if (ipv6) {
+		ipv6_addr_cpu_to_be32(n_addr, dest_addr);
+		seq_printf(m, "%pI6", n_addr);
+	} else {
+		seq_printf(m, "%pI4h", dest_addr);
+	}
+	if (dest_port)
+		seq_printf(m, ":%d", *dest_port);
+}
+
+static int airoha_ppe_debugfs_foe_show(struct seq_file *m, void *private,
+				       bool bind)
+{
+	static const char *const ppe_type_str[] = {
+		[PPE_PKT_TYPE_IPV4_HNAPT] = "IPv4 5T",
+		[PPE_PKT_TYPE_IPV4_ROUTE] = "IPv4 3T",
+		[PPE_PKT_TYPE_BRIDGE] = "L2B",
+		[PPE_PKT_TYPE_IPV4_DSLITE] = "DS-LITE",
+		[PPE_PKT_TYPE_IPV6_ROUTE_3T] = "IPv6 3T",
+		[PPE_PKT_TYPE_IPV6_ROUTE_5T] = "IPv6 5T",
+		[PPE_PKT_TYPE_IPV6_6RD] = "6RD",
+	};
+	static const char *const ppe_state_str[] = {
+		[AIROHA_FOE_STATE_INVALID] = "INV",
+		[AIROHA_FOE_STATE_UNBIND] = "UNB",
+		[AIROHA_FOE_STATE_BIND] = "BND",
+		[AIROHA_FOE_STATE_FIN] = "FIN",
+	};
+	struct airoha_ppe *ppe = m->private;
+	int i;
+
+	for (i = 0; i < PPE_NUM_ENTRIES; i++) {
+		const char *state_str, *type_str = "UNKNOWN";
+		void *src_addr = NULL, *dest_addr = NULL;
+		u16 *src_port = NULL, *dest_port = NULL;
+		struct airoha_foe_mac_info_common *l2;
+		unsigned char h_source[ETH_ALEN] = {};
+		struct airoha_foe_stats64 stats = {};
+		unsigned char h_dest[ETH_ALEN];
+		struct airoha_foe_entry *hwe;
+		u32 type, state, ib2, data;
+		bool ipv6 = false;
+
+		hwe = airoha_ppe_foe_get_entry(ppe, i);
+		if (!hwe)
+			continue;
+
+		state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+		if (!state)
+			continue;
+
+		if (bind && state != AIROHA_FOE_STATE_BIND)
+			continue;
+
+		state_str = ppe_state_str[state % ARRAY_SIZE(ppe_state_str)];
+		type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+		if (type < ARRAY_SIZE(ppe_type_str) && ppe_type_str[type])
+			type_str = ppe_type_str[type];
+
+		seq_printf(m, "%05x %s %7s", i, state_str, type_str);
+
+		switch (type) {
+		case PPE_PKT_TYPE_IPV4_HNAPT:
+		case PPE_PKT_TYPE_IPV4_DSLITE:
+			src_port = &hwe->ipv4.orig_tuple.src_port;
+			dest_port = &hwe->ipv4.orig_tuple.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV4_ROUTE:
+			src_addr = &hwe->ipv4.orig_tuple.src_ip;
+			dest_addr = &hwe->ipv4.orig_tuple.dest_ip;
+			break;
+		case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+			src_port = &hwe->ipv6.src_port;
+			dest_port = &hwe->ipv6.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		case PPE_PKT_TYPE_IPV6_6RD:
+			src_addr = &hwe->ipv6.src_ip;
+			dest_addr = &hwe->ipv6.dest_ip;
+			ipv6 = true;
+			break;
+		default:
+			break;
+		}
+
+		if (src_addr && dest_addr) {
+			seq_puts(m, " orig=");
+			airoha_debugfs_ppe_print_tuple(m, src_addr, dest_addr,
+						       src_port, dest_port, ipv6);
+		}
+
+		switch (type) {
+		case PPE_PKT_TYPE_IPV4_HNAPT:
+		case PPE_PKT_TYPE_IPV4_DSLITE:
+			src_port = &hwe->ipv4.new_tuple.src_port;
+			dest_port = &hwe->ipv4.new_tuple.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV4_ROUTE:
+			src_addr = &hwe->ipv4.new_tuple.src_ip;
+			dest_addr = &hwe->ipv4.new_tuple.dest_ip;
+			seq_puts(m, " new=");
+			airoha_debugfs_ppe_print_tuple(m, src_addr, dest_addr,
+						       src_port, dest_port,
+						       ipv6);
+			break;
+		default:
+			break;
+		}
+
+		if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+			data = hwe->ipv6.data;
+			ib2 = hwe->ipv6.ib2;
+			l2 = &hwe->ipv6.l2;
+		} else {
+			data = hwe->ipv4.data;
+			ib2 = hwe->ipv4.ib2;
+			l2 = &hwe->ipv4.l2.common;
+			*((__be16 *)&h_source[4]) =
+				cpu_to_be16(hwe->ipv4.l2.src_mac_lo);
+		}
+
+		airoha_ppe_foe_entry_get_stats(ppe, i, &stats);
+
+		*((__be32 *)h_dest) = cpu_to_be32(l2->dest_mac_hi);
+		*((__be16 *)&h_dest[4]) = cpu_to_be16(l2->dest_mac_lo);
+		*((__be32 *)h_source) = cpu_to_be32(l2->src_mac_hi);
+
+		seq_printf(m, " eth=%pM->%pM etype=%04x data=%08x"
+			      " vlan=%d,%d ib1=%08x ib2=%08x"
+			      " packets=%llu bytes=%llu\n",
+			   h_source, h_dest, l2->etype, data,
+			   l2->vlan1, l2->vlan2, hwe->ib1, ib2,
+			   stats.packets, stats.bytes);
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_debugfs_foe_all_show(struct seq_file *m, void *private)
+{
+	return airoha_ppe_debugfs_foe_show(m, private, false);
+}
+DEFINE_SHOW_ATTRIBUTE(airoha_ppe_debugfs_foe_all);
+
+static int airoha_ppe_debugfs_foe_bind_show(struct seq_file *m, void *private)
+{
+	return airoha_ppe_debugfs_foe_show(m, private, true);
+}
+DEFINE_SHOW_ATTRIBUTE(airoha_ppe_debugfs_foe_bind);
+
+int airoha_ppe_debugfs_init(struct airoha_ppe *ppe)
+{
+	ppe->debugfs_dir = debugfs_create_dir("ppe", NULL);
+	debugfs_create_file("entries", 0444, ppe->debugfs_dir, ppe,
+			    &airoha_ppe_debugfs_foe_all_fops);
+	debugfs_create_file("bind", 0444, ppe->debugfs_dir, ppe,
+			    &airoha_ppe_debugfs_foe_bind_fops);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
new file mode 100644
index 000000000000..150c85995cc1
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -0,0 +1,933 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#ifndef AIROHA_REGS_H
+#define AIROHA_REGS_H
+
+#include <linux/types.h>
+
+/* FE */
+#define PSE_BASE			0x0100
+#define CSR_IFC_BASE			0x0200
+#define CDM1_BASE			0x0400
+#define GDM1_BASE			0x0500
+#define PPE1_BASE			0x0c00
+#define PPE2_BASE			0x1c00
+
+#define CDM2_BASE			0x1400
+#define GDM2_BASE			0x1500
+
+#define GDM3_BASE			0x1100
+#define GDM4_BASE			0x2500
+
+#define GDM_BASE(_n)			\
+	((_n) == 4 ? GDM4_BASE :	\
+	 (_n) == 3 ? GDM3_BASE :	\
+	 (_n) == 2 ? GDM2_BASE : GDM1_BASE)
+
+#define REG_FE_DMA_GLO_CFG		0x0000
+#define FE_DMA_GLO_L2_SPACE_MASK	GENMASK(7, 4)
+#define FE_DMA_GLO_PG_SZ_MASK		BIT(3)
+
+#define REG_FE_RST_GLO_CFG		0x0004
+#define FE_RST_GDM4_MBI_ARB_MASK	BIT(3)
+#define FE_RST_GDM3_MBI_ARB_MASK	BIT(2)
+#define FE_RST_CORE_MASK		BIT(0)
+
+#define REG_FE_FOE_TS			0x0010
+
+#define REG_FE_WAN_PORT			0x0024
+#define WAN1_EN_MASK			BIT(16)
+#define WAN1_MASK			GENMASK(12, 8)
+#define WAN0_MASK			GENMASK(4, 0)
+
+#define REG_FE_WAN_MAC_H		0x0030
+#define REG_FE_LAN_MAC_H		0x0040
+
+#define REG_FE_MAC_LMIN(_n)		((_n) + 0x04)
+#define REG_FE_MAC_LMAX(_n)		((_n) + 0x08)
+
+#define REG_FE_CDM1_OQ_MAP0		0x0050
+#define REG_FE_CDM1_OQ_MAP1		0x0054
+#define REG_FE_CDM1_OQ_MAP2		0x0058
+#define REG_FE_CDM1_OQ_MAP3		0x005c
+
+#define REG_FE_PCE_CFG			0x0070
+#define PCE_DPI_EN_MASK			BIT(2)
+#define PCE_KA_EN_MASK			BIT(1)
+#define PCE_MC_EN_MASK			BIT(0)
+
+#define REG_FE_PSE_QUEUE_CFG_WR		0x0080
+#define PSE_CFG_PORT_ID_MASK		GENMASK(27, 24)
+#define PSE_CFG_QUEUE_ID_MASK		GENMASK(20, 16)
+#define PSE_CFG_WR_EN_MASK		BIT(8)
+#define PSE_CFG_OQRSV_SEL_MASK		BIT(0)
+
+#define REG_FE_PSE_QUEUE_CFG_VAL	0x0084
+#define PSE_CFG_OQ_RSV_MASK		GENMASK(13, 0)
+
+#define PSE_FQ_CFG			0x008c
+#define PSE_FQ_LIMIT_MASK		GENMASK(14, 0)
+
+#define REG_FE_PSE_BUF_SET		0x0090
+#define PSE_SHARE_USED_LTHD_MASK	GENMASK(31, 16)
+#define PSE_ALLRSV_MASK			GENMASK(14, 0)
+
+#define REG_PSE_SHARE_USED_THD		0x0094
+#define PSE_SHARE_USED_MTHD_MASK	GENMASK(31, 16)
+#define PSE_SHARE_USED_HTHD_MASK	GENMASK(15, 0)
+
+#define REG_GDM_MISC_CFG		0x0148
+#define GDM2_RDM_ACK_WAIT_PREF_MASK	BIT(9)
+#define GDM2_CHN_VLD_MODE_MASK		BIT(5)
+
+#define REG_FE_CSR_IFC_CFG		CSR_IFC_BASE
+#define FE_IFC_EN_MASK			BIT(0)
+
+#define REG_FE_VIP_PORT_EN		0x01f0
+#define REG_FE_IFC_PORT_EN		0x01f4
+
+#define REG_PSE_IQ_REV1			(PSE_BASE + 0x08)
+#define PSE_IQ_RES1_P2_MASK		GENMASK(23, 16)
+
+#define REG_PSE_IQ_REV2			(PSE_BASE + 0x0c)
+#define PSE_IQ_RES2_P5_MASK		GENMASK(15, 8)
+#define PSE_IQ_RES2_P4_MASK		GENMASK(7, 0)
+
+#define REG_FE_VIP_EN(_n)		(0x0300 + ((_n) << 3))
+#define PATN_FCPU_EN_MASK		BIT(7)
+#define PATN_SWP_EN_MASK		BIT(6)
+#define PATN_DP_EN_MASK			BIT(5)
+#define PATN_SP_EN_MASK			BIT(4)
+#define PATN_TYPE_MASK			GENMASK(3, 1)
+#define PATN_EN_MASK			BIT(0)
+
+#define REG_FE_VIP_PATN(_n)		(0x0304 + ((_n) << 3))
+#define PATN_DP_MASK			GENMASK(31, 16)
+#define PATN_SP_MASK			GENMASK(15, 0)
+
+#define REG_CDM1_VLAN_CTRL		CDM1_BASE
+#define CDM1_VLAN_MASK			GENMASK(31, 16)
+
+#define REG_CDM1_FWD_CFG		(CDM1_BASE + 0x08)
+#define CDM1_VIP_QSEL_MASK		GENMASK(24, 20)
+
+#define REG_CDM1_CRSN_QSEL(_n)		(CDM1_BASE + 0x10 + ((_n) << 2))
+#define CDM1_CRSN_QSEL_REASON_MASK(_n)	\
+	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
+
+#define REG_CDM2_FWD_CFG		(CDM2_BASE + 0x08)
+#define CDM2_OAM_QSEL_MASK		GENMASK(31, 27)
+#define CDM2_VIP_QSEL_MASK		GENMASK(24, 20)
+
+#define REG_CDM2_CRSN_QSEL(_n)		(CDM2_BASE + 0x10 + ((_n) << 2))
+#define CDM2_CRSN_QSEL_REASON_MASK(_n)	\
+	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
+
+#define REG_GDM_FWD_CFG(_n)		GDM_BASE(_n)
+#define GDM_DROP_CRC_ERR		BIT(23)
+#define GDM_IP4_CKSUM			BIT(22)
+#define GDM_TCP_CKSUM			BIT(21)
+#define GDM_UDP_CKSUM			BIT(20)
+#define GDM_STRIP_CRC			BIT(16)
+#define GDM_UCFQ_MASK			GENMASK(15, 12)
+#define GDM_BCFQ_MASK			GENMASK(11, 8)
+#define GDM_MCFQ_MASK			GENMASK(7, 4)
+#define GDM_OCFQ_MASK			GENMASK(3, 0)
+
+#define REG_GDM_INGRESS_CFG(_n)		(GDM_BASE(_n) + 0x10)
+#define GDM_INGRESS_FC_EN_MASK		BIT(1)
+#define GDM_STAG_EN_MASK		BIT(0)
+
+#define REG_GDM_LEN_CFG(_n)		(GDM_BASE(_n) + 0x14)
+#define GDM_SHORT_LEN_MASK		GENMASK(13, 0)
+#define GDM_LONG_LEN_MASK		GENMASK(29, 16)
+
+#define REG_GDM_LPBK_CFG(_n)		(GDM_BASE(_n) + 0x1c)
+#define LPBK_GAP_MASK			GENMASK(31, 24)
+#define LPBK_LEN_MASK			GENMASK(23, 10)
+#define LPBK_CHAN_MASK			GENMASK(8, 4)
+#define LPBK_MODE_MASK			GENMASK(3, 1)
+#define LPBK_EN_MASK			BIT(0)
+
+#define REG_GDM_TXCHN_EN(_n)		(GDM_BASE(_n) + 0x24)
+#define REG_GDM_RXCHN_EN(_n)		(GDM_BASE(_n) + 0x28)
+
+#define REG_FE_CPORT_CFG		(GDM1_BASE + 0x40)
+#define FE_CPORT_PAD			BIT(26)
+#define FE_CPORT_PORT_XFC_MASK		BIT(25)
+#define FE_CPORT_QUEUE_XFC_MASK		BIT(24)
+
+#define REG_FE_GDM_MIB_CLEAR(_n)	(GDM_BASE(_n) + 0xf0)
+#define FE_GDM_MIB_RX_CLEAR_MASK	BIT(1)
+#define FE_GDM_MIB_TX_CLEAR_MASK	BIT(0)
+
+#define REG_FE_GDM1_MIB_CFG		(GDM1_BASE + 0xf4)
+#define FE_STRICT_RFC2819_MODE_MASK	BIT(31)
+#define FE_GDM1_TX_MIB_SPLIT_EN_MASK	BIT(17)
+#define FE_GDM1_RX_MIB_SPLIT_EN_MASK	BIT(16)
+#define FE_TX_MIB_ID_MASK		GENMASK(15, 8)
+#define FE_RX_MIB_ID_MASK		GENMASK(7, 0)
+
+#define REG_FE_GDM_TX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x104)
+#define REG_FE_GDM_TX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x10c)
+#define REG_FE_GDM_TX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x110)
+#define REG_FE_GDM_TX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x114)
+#define REG_FE_GDM_TX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x118)
+#define REG_FE_GDM_TX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x11c)
+#define REG_FE_GDM_TX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x120)
+#define REG_FE_GDM_TX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x124)
+#define REG_FE_GDM_TX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x128)
+#define REG_FE_GDM_TX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x12c)
+#define REG_FE_GDM_TX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x130)
+#define REG_FE_GDM_TX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x134)
+#define REG_FE_GDM_TX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x138)
+#define REG_FE_GDM_TX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x13c)
+#define REG_FE_GDM_TX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x140)
+
+#define REG_FE_GDM_RX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x148)
+#define REG_FE_GDM_RX_FC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x14c)
+#define REG_FE_GDM_RX_RC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x150)
+#define REG_FE_GDM_RX_OVERFLOW_DROP_CNT(_n)	(GDM_BASE(_n) + 0x154)
+#define REG_FE_GDM_RX_ERROR_DROP_CNT(_n)	(GDM_BASE(_n) + 0x158)
+#define REG_FE_GDM_RX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x15c)
+#define REG_FE_GDM_RX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x160)
+#define REG_FE_GDM_RX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x164)
+#define REG_FE_GDM_RX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x168)
+#define REG_FE_GDM_RX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x16c)
+#define REG_FE_GDM_RX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x170)
+#define REG_FE_GDM_RX_ETH_CRC_ERR_CNT(_n)	(GDM_BASE(_n) + 0x174)
+#define REG_FE_GDM_RX_ETH_FRAG_CNT(_n)		(GDM_BASE(_n) + 0x178)
+#define REG_FE_GDM_RX_ETH_JABBER_CNT(_n)	(GDM_BASE(_n) + 0x17c)
+#define REG_FE_GDM_RX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x180)
+#define REG_FE_GDM_RX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x184)
+#define REG_FE_GDM_RX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x188)
+#define REG_FE_GDM_RX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x18c)
+#define REG_FE_GDM_RX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x190)
+#define REG_FE_GDM_RX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x194)
+#define REG_FE_GDM_RX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x198)
+#define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x19c)
+
+#define REG_PPE_GLO_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x200)
+#define PPE_GLO_CFG_BUSY_MASK			BIT(31)
+#define PPE_GLO_CFG_FLOW_DROP_UPDATE_MASK	BIT(9)
+#define PPE_GLO_CFG_PSE_HASH_OFS_MASK		BIT(6)
+#define PPE_GLO_CFG_PPE_BSWAP_MASK		BIT(5)
+#define PPE_GLO_CFG_TTL_DROP_MASK		BIT(4)
+#define PPE_GLO_CFG_IP4_CS_DROP_MASK		BIT(3)
+#define PPE_GLO_CFG_IP4_L4_CS_DROP_MASK		BIT(2)
+#define PPE_GLO_CFG_EN_MASK			BIT(0)
+
+#define REG_PPE_PPE_FLOW_CFG(_n)		(((_n) ? PPE2_BASE : PPE1_BASE) + 0x204)
+#define PPE_FLOW_CFG_IP6_HASH_GRE_KEY_MASK	BIT(20)
+#define PPE_FLOW_CFG_IP4_HASH_GRE_KEY_MASK	BIT(19)
+#define PPE_FLOW_CFG_IP4_HASH_FLOW_LABEL_MASK	BIT(18)
+#define PPE_FLOW_CFG_IP4_NAT_FRAG_MASK		BIT(17)
+#define PPE_FLOW_CFG_IP_PROTO_BLACKLIST_MASK	BIT(16)
+#define PPE_FLOW_CFG_IP4_DSLITE_MASK		BIT(14)
+#define PPE_FLOW_CFG_IP4_NAPT_MASK		BIT(13)
+#define PPE_FLOW_CFG_IP4_NAT_MASK		BIT(12)
+#define PPE_FLOW_CFG_IP6_6RD_MASK		BIT(10)
+#define PPE_FLOW_CFG_IP6_5T_ROUTE_MASK		BIT(9)
+#define PPE_FLOW_CFG_IP6_3T_ROUTE_MASK		BIT(8)
+#define PPE_FLOW_CFG_IP4_UDP_FRAG_MASK		BIT(7)
+#define PPE_FLOW_CFG_IP4_TCP_FRAG_MASK		BIT(6)
+
+#define REG_PPE_IP_PROTO_CHK(_n)		(((_n) ? PPE2_BASE : PPE1_BASE) + 0x208)
+#define PPE_IP_PROTO_CHK_IPV4_MASK		GENMASK(15, 0)
+#define PPE_IP_PROTO_CHK_IPV6_MASK		GENMASK(31, 16)
+
+#define REG_PPE_TB_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x21c)
+#define PPE_SRAM_TB_NUM_ENTRY_MASK		GENMASK(26, 24)
+#define PPE_TB_CFG_KEEPALIVE_MASK		GENMASK(13, 12)
+#define PPE_TB_CFG_AGE_TCP_FIN_MASK		BIT(11)
+#define PPE_TB_CFG_AGE_UDP_MASK			BIT(10)
+#define PPE_TB_CFG_AGE_TCP_MASK			BIT(9)
+#define PPE_TB_CFG_AGE_UNBIND_MASK		BIT(8)
+#define PPE_TB_CFG_AGE_NON_L4_MASK		BIT(7)
+#define PPE_TB_CFG_AGE_PREBIND_MASK		BIT(6)
+#define PPE_TB_CFG_SEARCH_MISS_MASK		GENMASK(5, 4)
+#define PPE_TB_ENTRY_SIZE_MASK			BIT(3)
+#define PPE_DRAM_TB_NUM_ENTRY_MASK		GENMASK(2, 0)
+
+#define REG_PPE_TB_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x220)
+
+#define REG_PPE_BIND_RATE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x228)
+#define PPE_BIND_RATE_L2B_BIND_MASK		GENMASK(31, 16)
+#define PPE_BIND_RATE_BIND_MASK			GENMASK(15, 0)
+
+#define REG_PPE_BIND_LIMIT0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x22c)
+#define PPE_BIND_LIMIT0_HALF_MASK		GENMASK(29, 16)
+#define PPE_BIND_LIMIT0_QUARTER_MASK		GENMASK(13, 0)
+
+#define REG_PPE_BIND_LIMIT1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x230)
+#define PPE_BIND_LIMIT1_NON_L4_MASK		GENMASK(23, 16)
+#define PPE_BIND_LIMIT1_FULL_MASK		GENMASK(13, 0)
+
+#define REG_PPE_BND_AGE0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x23c)
+#define PPE_BIND_AGE0_DELTA_NON_L4		GENMASK(30, 16)
+#define PPE_BIND_AGE0_DELTA_UDP			GENMASK(14, 0)
+
+#define REG_PPE_UNBIND_AGE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x238)
+#define PPE_UNBIND_AGE_MIN_PACKETS_MASK		GENMASK(31, 16)
+#define PPE_UNBIND_AGE_DELTA_MASK		GENMASK(7, 0)
+
+#define REG_PPE_BND_AGE1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x240)
+#define PPE_BIND_AGE1_DELTA_TCP_FIN		GENMASK(30, 16)
+#define PPE_BIND_AGE1_DELTA_TCP			GENMASK(14, 0)
+
+#define REG_PPE_HASH_SEED(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x244)
+#define PPE_HASH_SEED				0x12345678
+
+#define REG_PPE_DFT_CPORT0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x248)
+#define DFT_CPORT_MASK(_n)			GENMASK(3 + ((_n) << 2), ((_n) << 2))
+
+#define REG_PPE_DFT_CPORT1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x24c)
+
+#define REG_PPE_TB_HASH_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x250)
+#define PPE_DRAM_HASH1_MODE_MASK		GENMASK(31, 28)
+#define PPE_DRAM_HASH1_EN_MASK			BIT(24)
+#define PPE_DRAM_HASH0_MODE_MASK		GENMASK(23, 20)
+#define PPE_DRAM_TABLE_EN_MASK			BIT(16)
+#define PPE_SRAM_HASH1_MODE_MASK		GENMASK(15, 12)
+#define PPE_SRAM_HASH1_EN_MASK			BIT(8)
+#define PPE_SRAM_HASH0_MODE_MASK		GENMASK(7, 4)
+#define PPE_SRAM_TABLE_EN_MASK			BIT(0)
+
+#define REG_PPE_MTU_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x304)
+#define REG_PPE_MTU(_m, _n)			(REG_PPE_MTU_BASE(_m) + ((_n) << 2))
+#define FP1_EGRESS_MTU_MASK			GENMASK(29, 16)
+#define FP0_EGRESS_MTU_MASK			GENMASK(13, 0)
+
+#define REG_PPE_RAM_CTRL(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x31c)
+#define PPE_SRAM_CTRL_ACK_MASK			BIT(31)
+#define PPE_SRAM_CTRL_DUAL_SUCESS_MASK		BIT(30)
+#define PPE_SRAM_CTRL_ENTRY_MASK		GENMASK(23, 8)
+#define PPE_SRAM_WR_DUAL_DIRECTION_MASK		BIT(2)
+#define PPE_SRAM_CTRL_WR_MASK			BIT(1)
+#define PPE_SRAM_CTRL_REQ_MASK			BIT(0)
+
+#define REG_PPE_RAM_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x320)
+#define REG_PPE_RAM_ENTRY(_m, _n)		(REG_PPE_RAM_BASE(_m) + ((_n) << 2))
+
+#define REG_UPDMEM_CTRL(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x370)
+#define PPE_UPDMEM_ACK_MASK			BIT(31)
+#define PPE_UPDMEM_ADDR_MASK			GENMASK(11, 8)
+#define PPE_UPDMEM_OFFSET_MASK			GENMASK(7, 4)
+#define PPE_UPDMEM_SEL_MASK			GENMASK(3, 2)
+#define PPE_UPDMEM_WR_MASK			BIT(1)
+#define PPE_UPDMEM_REQ_MASK			BIT(0)
+
+#define REG_UPDMEM_DATA(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x374)
+
+#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x280)
+#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x284)
+#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x288)
+#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x28c)
+
+#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x290)
+#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x294)
+#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x298)
+#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x29c)
+#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2b8)
+#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2bc)
+#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2c0)
+#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2c4)
+#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2c8)
+#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2cc)
+#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2e8)
+#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2ec)
+#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2f0)
+#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2f4)
+#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2f8)
+#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2fc)
+
+#define REG_GDM2_CHN_RLS		(GDM2_BASE + 0x20)
+#define MBI_RX_AGE_SEL_MASK		GENMASK(26, 25)
+#define MBI_TX_AGE_SEL_MASK		GENMASK(18, 17)
+
+#define REG_GDM3_FWD_CFG		GDM3_BASE
+#define GDM3_PAD_EN_MASK		BIT(28)
+
+#define REG_GDM4_FWD_CFG		GDM4_BASE
+#define GDM4_PAD_EN_MASK		BIT(28)
+#define GDM4_SPORT_OFFSET0_MASK		GENMASK(11, 8)
+
+#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x23c)
+#define GDM4_SPORT_OFF2_MASK		GENMASK(19, 16)
+#define GDM4_SPORT_OFF1_MASK		GENMASK(15, 12)
+#define GDM4_SPORT_OFF0_MASK		GENMASK(11, 8)
+
+#define REG_IP_FRAG_FP			0x2010
+#define IP_ASSEMBLE_PORT_MASK		GENMASK(24, 21)
+#define IP_ASSEMBLE_NBQ_MASK		GENMASK(20, 16)
+#define IP_FRAGMENT_PORT_MASK		GENMASK(8, 5)
+#define IP_FRAGMENT_NBQ_MASK		GENMASK(4, 0)
+
+#define REG_MC_VLAN_EN			0x2100
+#define MC_VLAN_EN_MASK			BIT(0)
+
+#define REG_MC_VLAN_CFG			0x2104
+#define MC_VLAN_CFG_CMD_DONE_MASK	BIT(31)
+#define MC_VLAN_CFG_TABLE_ID_MASK	GENMASK(21, 16)
+#define MC_VLAN_CFG_PORT_ID_MASK	GENMASK(11, 8)
+#define MC_VLAN_CFG_TABLE_SEL_MASK	BIT(4)
+#define MC_VLAN_CFG_RW_MASK		BIT(0)
+
+#define REG_MC_VLAN_DATA		0x2108
+
+#define REG_SP_DFT_CPORT(_n)		(0x20e0 + ((_n) << 2))
+#define SP_CPORT_PCIE1_MASK		GENMASK(31, 28)
+#define SP_CPORT_PCIE0_MASK		GENMASK(27, 24)
+#define SP_CPORT_USB_MASK		GENMASK(7, 4)
+#define SP_CPORT_ETH_MASK		GENMASK(7, 4)
+
+#define REG_SRC_PORT_FC_MAP6		0x2298
+#define FC_ID_OF_SRC_PORT27_MASK	GENMASK(28, 24)
+#define FC_ID_OF_SRC_PORT26_MASK	GENMASK(20, 16)
+#define FC_ID_OF_SRC_PORT25_MASK	GENMASK(12, 8)
+#define FC_ID_OF_SRC_PORT24_MASK	GENMASK(4, 0)
+
+#define REG_CDM5_RX_OQ1_DROP_CNT	0x29d4
+
+/* QDMA */
+#define REG_QDMA_GLOBAL_CFG			0x0004
+#define GLOBAL_CFG_RX_2B_OFFSET_MASK		BIT(31)
+#define GLOBAL_CFG_DMA_PREFERENCE_MASK		GENMASK(30, 29)
+#define GLOBAL_CFG_CPU_TXR_RR_MASK		BIT(28)
+#define GLOBAL_CFG_DSCP_BYTE_SWAP_MASK		BIT(27)
+#define GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK	BIT(26)
+#define GLOBAL_CFG_MULTICAST_MODIFY_FP_MASK	BIT(25)
+#define GLOBAL_CFG_OAM_MODIFY_MASK		BIT(24)
+#define GLOBAL_CFG_RESET_MASK			BIT(23)
+#define GLOBAL_CFG_RESET_DONE_MASK		BIT(22)
+#define GLOBAL_CFG_MULTICAST_EN_MASK		BIT(21)
+#define GLOBAL_CFG_IRQ1_EN_MASK			BIT(20)
+#define GLOBAL_CFG_IRQ0_EN_MASK			BIT(19)
+#define GLOBAL_CFG_LOOPCNT_EN_MASK		BIT(18)
+#define GLOBAL_CFG_RD_BYPASS_WR_MASK		BIT(17)
+#define GLOBAL_CFG_QDMA_LOOPBACK_MASK		BIT(16)
+#define GLOBAL_CFG_LPBK_RXQ_SEL_MASK		GENMASK(13, 8)
+#define GLOBAL_CFG_CHECK_DONE_MASK		BIT(7)
+#define GLOBAL_CFG_TX_WB_DONE_MASK		BIT(6)
+#define GLOBAL_CFG_MAX_ISSUE_NUM_MASK		GENMASK(5, 4)
+#define GLOBAL_CFG_RX_DMA_BUSY_MASK		BIT(3)
+#define GLOBAL_CFG_RX_DMA_EN_MASK		BIT(2)
+#define GLOBAL_CFG_TX_DMA_BUSY_MASK		BIT(1)
+#define GLOBAL_CFG_TX_DMA_EN_MASK		BIT(0)
+
+#define REG_FWD_DSCP_BASE			0x0010
+#define REG_FWD_BUF_BASE			0x0014
+
+#define REG_HW_FWD_DSCP_CFG			0x0018
+#define HW_FWD_DSCP_PAYLOAD_SIZE_MASK		GENMASK(29, 28)
+#define HW_FWD_DSCP_SCATTER_LEN_MASK		GENMASK(17, 16)
+#define HW_FWD_DSCP_MIN_SCATTER_LEN_MASK	GENMASK(15, 0)
+
+#define REG_INT_STATUS(_n)		\
+	(((_n) == 4) ? 0x0730 :		\
+	 ((_n) == 3) ? 0x0724 :		\
+	 ((_n) == 2) ? 0x0720 :		\
+	 ((_n) == 1) ? 0x0024 : 0x0020)
+
+#define REG_INT_ENABLE(_b, _n)		\
+	(((_n) == 4) ? 0x0750 + ((_b) << 5) :	\
+	 ((_n) == 3) ? 0x0744 + ((_b) << 5) :	\
+	 ((_n) == 2) ? 0x0740 + ((_b) << 5) :	\
+	 ((_n) == 1) ? 0x002c + ((_b) << 3) :	\
+		       0x0028 + ((_b) << 3))
+
+/* QDMA_CSR_INT_ENABLE1 */
+#define RX15_COHERENT_INT_MASK		BIT(31)
+#define RX14_COHERENT_INT_MASK		BIT(30)
+#define RX13_COHERENT_INT_MASK		BIT(29)
+#define RX12_COHERENT_INT_MASK		BIT(28)
+#define RX11_COHERENT_INT_MASK		BIT(27)
+#define RX10_COHERENT_INT_MASK		BIT(26)
+#define RX9_COHERENT_INT_MASK		BIT(25)
+#define RX8_COHERENT_INT_MASK		BIT(24)
+#define RX7_COHERENT_INT_MASK		BIT(23)
+#define RX6_COHERENT_INT_MASK		BIT(22)
+#define RX5_COHERENT_INT_MASK		BIT(21)
+#define RX4_COHERENT_INT_MASK		BIT(20)
+#define RX3_COHERENT_INT_MASK		BIT(19)
+#define RX2_COHERENT_INT_MASK		BIT(18)
+#define RX1_COHERENT_INT_MASK		BIT(17)
+#define RX0_COHERENT_INT_MASK		BIT(16)
+#define TX7_COHERENT_INT_MASK		BIT(15)
+#define TX6_COHERENT_INT_MASK		BIT(14)
+#define TX5_COHERENT_INT_MASK		BIT(13)
+#define TX4_COHERENT_INT_MASK		BIT(12)
+#define TX3_COHERENT_INT_MASK		BIT(11)
+#define TX2_COHERENT_INT_MASK		BIT(10)
+#define TX1_COHERENT_INT_MASK		BIT(9)
+#define TX0_COHERENT_INT_MASK		BIT(8)
+#define CNT_OVER_FLOW_INT_MASK		BIT(7)
+#define IRQ1_FULL_INT_MASK		BIT(5)
+#define IRQ1_INT_MASK			BIT(4)
+#define HWFWD_DSCP_LOW_INT_MASK		BIT(3)
+#define HWFWD_DSCP_EMPTY_INT_MASK	BIT(2)
+#define IRQ0_FULL_INT_MASK		BIT(1)
+#define IRQ0_INT_MASK			BIT(0)
+
+#define RX_COHERENT_LOW_INT_MASK				\
+	(RX15_COHERENT_INT_MASK | RX14_COHERENT_INT_MASK |	\
+	 RX13_COHERENT_INT_MASK | RX12_COHERENT_INT_MASK |	\
+	 RX11_COHERENT_INT_MASK | RX10_COHERENT_INT_MASK |	\
+	 RX9_COHERENT_INT_MASK | RX8_COHERENT_INT_MASK |	\
+	 RX7_COHERENT_INT_MASK | RX6_COHERENT_INT_MASK |	\
+	 RX5_COHERENT_INT_MASK | RX4_COHERENT_INT_MASK |	\
+	 RX3_COHERENT_INT_MASK | RX2_COHERENT_INT_MASK |	\
+	 RX1_COHERENT_INT_MASK | RX0_COHERENT_INT_MASK)
+
+#define RX_COHERENT_LOW_OFFSET	__ffs(RX_COHERENT_LOW_INT_MASK)
+#define INT_RX0_MASK(_n)					\
+	(((_n) << RX_COHERENT_LOW_OFFSET) & RX_COHERENT_LOW_INT_MASK)
+
+#define TX_COHERENT_LOW_INT_MASK				\
+	(TX7_COHERENT_INT_MASK | TX6_COHERENT_INT_MASK |	\
+	 TX5_COHERENT_INT_MASK | TX4_COHERENT_INT_MASK |	\
+	 TX3_COHERENT_INT_MASK | TX2_COHERENT_INT_MASK |	\
+	 TX1_COHERENT_INT_MASK | TX0_COHERENT_INT_MASK)
+
+#define TX_DONE_INT_MASK(_n)					\
+	((_n) ? IRQ1_INT_MASK | IRQ1_FULL_INT_MASK		\
+	      : IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
+
+#define INT_TX_MASK						\
+	(IRQ1_INT_MASK | IRQ1_FULL_INT_MASK |			\
+	 IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
+
+/* QDMA_CSR_INT_ENABLE2 */
+#define RX15_NO_CPU_DSCP_INT_MASK	BIT(31)
+#define RX14_NO_CPU_DSCP_INT_MASK	BIT(30)
+#define RX13_NO_CPU_DSCP_INT_MASK	BIT(29)
+#define RX12_NO_CPU_DSCP_INT_MASK	BIT(28)
+#define RX11_NO_CPU_DSCP_INT_MASK	BIT(27)
+#define RX10_NO_CPU_DSCP_INT_MASK	BIT(26)
+#define RX9_NO_CPU_DSCP_INT_MASK	BIT(25)
+#define RX8_NO_CPU_DSCP_INT_MASK	BIT(24)
+#define RX7_NO_CPU_DSCP_INT_MASK	BIT(23)
+#define RX6_NO_CPU_DSCP_INT_MASK	BIT(22)
+#define RX5_NO_CPU_DSCP_INT_MASK	BIT(21)
+#define RX4_NO_CPU_DSCP_INT_MASK	BIT(20)
+#define RX3_NO_CPU_DSCP_INT_MASK	BIT(19)
+#define RX2_NO_CPU_DSCP_INT_MASK	BIT(18)
+#define RX1_NO_CPU_DSCP_INT_MASK	BIT(17)
+#define RX0_NO_CPU_DSCP_INT_MASK	BIT(16)
+#define RX15_DONE_INT_MASK		BIT(15)
+#define RX14_DONE_INT_MASK		BIT(14)
+#define RX13_DONE_INT_MASK		BIT(13)
+#define RX12_DONE_INT_MASK		BIT(12)
+#define RX11_DONE_INT_MASK		BIT(11)
+#define RX10_DONE_INT_MASK		BIT(10)
+#define RX9_DONE_INT_MASK		BIT(9)
+#define RX8_DONE_INT_MASK		BIT(8)
+#define RX7_DONE_INT_MASK		BIT(7)
+#define RX6_DONE_INT_MASK		BIT(6)
+#define RX5_DONE_INT_MASK		BIT(5)
+#define RX4_DONE_INT_MASK		BIT(4)
+#define RX3_DONE_INT_MASK		BIT(3)
+#define RX2_DONE_INT_MASK		BIT(2)
+#define RX1_DONE_INT_MASK		BIT(1)
+#define RX0_DONE_INT_MASK		BIT(0)
+
+#define RX_NO_CPU_DSCP_LOW_INT_MASK					\
+	(RX15_NO_CPU_DSCP_INT_MASK | RX14_NO_CPU_DSCP_INT_MASK |	\
+	 RX13_NO_CPU_DSCP_INT_MASK | RX12_NO_CPU_DSCP_INT_MASK |	\
+	 RX11_NO_CPU_DSCP_INT_MASK | RX10_NO_CPU_DSCP_INT_MASK |	\
+	 RX9_NO_CPU_DSCP_INT_MASK | RX8_NO_CPU_DSCP_INT_MASK |		\
+	 RX7_NO_CPU_DSCP_INT_MASK | RX6_NO_CPU_DSCP_INT_MASK |		\
+	 RX5_NO_CPU_DSCP_INT_MASK | RX4_NO_CPU_DSCP_INT_MASK |		\
+	 RX3_NO_CPU_DSCP_INT_MASK | RX2_NO_CPU_DSCP_INT_MASK |		\
+	 RX1_NO_CPU_DSCP_INT_MASK | RX0_NO_CPU_DSCP_INT_MASK)
+
+#define RX_DONE_LOW_INT_MASK				\
+	(RX15_DONE_INT_MASK | RX14_DONE_INT_MASK |	\
+	 RX13_DONE_INT_MASK | RX12_DONE_INT_MASK |	\
+	 RX11_DONE_INT_MASK | RX10_DONE_INT_MASK |	\
+	 RX9_DONE_INT_MASK | RX8_DONE_INT_MASK |	\
+	 RX7_DONE_INT_MASK | RX6_DONE_INT_MASK |	\
+	 RX5_DONE_INT_MASK | RX4_DONE_INT_MASK |	\
+	 RX3_DONE_INT_MASK | RX2_DONE_INT_MASK |	\
+	 RX1_DONE_INT_MASK | RX0_DONE_INT_MASK)
+
+#define RX_NO_CPU_DSCP_LOW_OFFSET	__ffs(RX_NO_CPU_DSCP_LOW_INT_MASK)
+#define INT_RX1_MASK(_n)							\
+	((((_n) << RX_NO_CPU_DSCP_LOW_OFFSET) & RX_NO_CPU_DSCP_LOW_INT_MASK) |	\
+	 (RX_DONE_LOW_INT_MASK & (_n)))
+
+/* QDMA_CSR_INT_ENABLE3 */
+#define RX31_NO_CPU_DSCP_INT_MASK	BIT(31)
+#define RX30_NO_CPU_DSCP_INT_MASK	BIT(30)
+#define RX29_NO_CPU_DSCP_INT_MASK	BIT(29)
+#define RX28_NO_CPU_DSCP_INT_MASK	BIT(28)
+#define RX27_NO_CPU_DSCP_INT_MASK	BIT(27)
+#define RX26_NO_CPU_DSCP_INT_MASK	BIT(26)
+#define RX25_NO_CPU_DSCP_INT_MASK	BIT(25)
+#define RX24_NO_CPU_DSCP_INT_MASK	BIT(24)
+#define RX23_NO_CPU_DSCP_INT_MASK	BIT(23)
+#define RX22_NO_CPU_DSCP_INT_MASK	BIT(22)
+#define RX21_NO_CPU_DSCP_INT_MASK	BIT(21)
+#define RX20_NO_CPU_DSCP_INT_MASK	BIT(20)
+#define RX19_NO_CPU_DSCP_INT_MASK	BIT(19)
+#define RX18_NO_CPU_DSCP_INT_MASK	BIT(18)
+#define RX17_NO_CPU_DSCP_INT_MASK	BIT(17)
+#define RX16_NO_CPU_DSCP_INT_MASK	BIT(16)
+#define RX31_DONE_INT_MASK		BIT(15)
+#define RX30_DONE_INT_MASK		BIT(14)
+#define RX29_DONE_INT_MASK		BIT(13)
+#define RX28_DONE_INT_MASK		BIT(12)
+#define RX27_DONE_INT_MASK		BIT(11)
+#define RX26_DONE_INT_MASK		BIT(10)
+#define RX25_DONE_INT_MASK		BIT(9)
+#define RX24_DONE_INT_MASK		BIT(8)
+#define RX23_DONE_INT_MASK		BIT(7)
+#define RX22_DONE_INT_MASK		BIT(6)
+#define RX21_DONE_INT_MASK		BIT(5)
+#define RX20_DONE_INT_MASK		BIT(4)
+#define RX19_DONE_INT_MASK		BIT(3)
+#define RX18_DONE_INT_MASK		BIT(2)
+#define RX17_DONE_INT_MASK		BIT(1)
+#define RX16_DONE_INT_MASK		BIT(0)
+
+#define RX_NO_CPU_DSCP_HIGH_INT_MASK					\
+	(RX31_NO_CPU_DSCP_INT_MASK | RX30_NO_CPU_DSCP_INT_MASK |	\
+	 RX29_NO_CPU_DSCP_INT_MASK | RX28_NO_CPU_DSCP_INT_MASK |	\
+	 RX27_NO_CPU_DSCP_INT_MASK | RX26_NO_CPU_DSCP_INT_MASK |	\
+	 RX25_NO_CPU_DSCP_INT_MASK | RX24_NO_CPU_DSCP_INT_MASK |	\
+	 RX23_NO_CPU_DSCP_INT_MASK | RX22_NO_CPU_DSCP_INT_MASK |	\
+	 RX21_NO_CPU_DSCP_INT_MASK | RX20_NO_CPU_DSCP_INT_MASK |	\
+	 RX19_NO_CPU_DSCP_INT_MASK | RX18_NO_CPU_DSCP_INT_MASK |	\
+	 RX17_NO_CPU_DSCP_INT_MASK | RX16_NO_CPU_DSCP_INT_MASK)
+
+#define RX_DONE_HIGH_INT_MASK				\
+	(RX31_DONE_INT_MASK | RX30_DONE_INT_MASK |	\
+	 RX29_DONE_INT_MASK | RX28_DONE_INT_MASK |	\
+	 RX27_DONE_INT_MASK | RX26_DONE_INT_MASK |	\
+	 RX25_DONE_INT_MASK | RX24_DONE_INT_MASK |	\
+	 RX23_DONE_INT_MASK | RX22_DONE_INT_MASK |	\
+	 RX21_DONE_INT_MASK | RX20_DONE_INT_MASK |	\
+	 RX19_DONE_INT_MASK | RX18_DONE_INT_MASK |	\
+	 RX17_DONE_INT_MASK | RX16_DONE_INT_MASK)
+
+#define RX_DONE_HIGH_OFFSET	fls(RX_DONE_HIGH_INT_MASK)
+#define RX_DONE_INT_MASK	\
+	((RX_DONE_HIGH_INT_MASK << RX_DONE_HIGH_OFFSET) | RX_DONE_LOW_INT_MASK)
+
+#define INT_RX2_MASK(_n)				\
+	((RX_NO_CPU_DSCP_HIGH_INT_MASK & (_n)) |	\
+	 (((_n) >> RX_DONE_HIGH_OFFSET) & RX_DONE_HIGH_INT_MASK))
+
+/* QDMA_CSR_INT_ENABLE4 */
+#define RX31_COHERENT_INT_MASK		BIT(31)
+#define RX30_COHERENT_INT_MASK		BIT(30)
+#define RX29_COHERENT_INT_MASK		BIT(29)
+#define RX28_COHERENT_INT_MASK		BIT(28)
+#define RX27_COHERENT_INT_MASK		BIT(27)
+#define RX26_COHERENT_INT_MASK		BIT(26)
+#define RX25_COHERENT_INT_MASK		BIT(25)
+#define RX24_COHERENT_INT_MASK		BIT(24)
+#define RX23_COHERENT_INT_MASK		BIT(23)
+#define RX22_COHERENT_INT_MASK		BIT(22)
+#define RX21_COHERENT_INT_MASK		BIT(21)
+#define RX20_COHERENT_INT_MASK		BIT(20)
+#define RX19_COHERENT_INT_MASK		BIT(19)
+#define RX18_COHERENT_INT_MASK		BIT(18)
+#define RX17_COHERENT_INT_MASK		BIT(17)
+#define RX16_COHERENT_INT_MASK		BIT(16)
+
+#define RX_COHERENT_HIGH_INT_MASK				\
+	(RX31_COHERENT_INT_MASK | RX30_COHERENT_INT_MASK |	\
+	 RX29_COHERENT_INT_MASK | RX28_COHERENT_INT_MASK |	\
+	 RX27_COHERENT_INT_MASK | RX26_COHERENT_INT_MASK |	\
+	 RX25_COHERENT_INT_MASK | RX24_COHERENT_INT_MASK |	\
+	 RX23_COHERENT_INT_MASK | RX22_COHERENT_INT_MASK |	\
+	 RX21_COHERENT_INT_MASK | RX20_COHERENT_INT_MASK |	\
+	 RX19_COHERENT_INT_MASK | RX18_COHERENT_INT_MASK |	\
+	 RX17_COHERENT_INT_MASK | RX16_COHERENT_INT_MASK)
+
+#define INT_RX3_MASK(_n)	(RX_COHERENT_HIGH_INT_MASK & (_n))
+
+/* QDMA_CSR_INT_ENABLE5 */
+#define TX31_COHERENT_INT_MASK		BIT(31)
+#define TX30_COHERENT_INT_MASK		BIT(30)
+#define TX29_COHERENT_INT_MASK		BIT(29)
+#define TX28_COHERENT_INT_MASK		BIT(28)
+#define TX27_COHERENT_INT_MASK		BIT(27)
+#define TX26_COHERENT_INT_MASK		BIT(26)
+#define TX25_COHERENT_INT_MASK		BIT(25)
+#define TX24_COHERENT_INT_MASK		BIT(24)
+#define TX23_COHERENT_INT_MASK		BIT(23)
+#define TX22_COHERENT_INT_MASK		BIT(22)
+#define TX21_COHERENT_INT_MASK		BIT(21)
+#define TX20_COHERENT_INT_MASK		BIT(20)
+#define TX19_COHERENT_INT_MASK		BIT(19)
+#define TX18_COHERENT_INT_MASK		BIT(18)
+#define TX17_COHERENT_INT_MASK		BIT(17)
+#define TX16_COHERENT_INT_MASK		BIT(16)
+#define TX15_COHERENT_INT_MASK		BIT(15)
+#define TX14_COHERENT_INT_MASK		BIT(14)
+#define TX13_COHERENT_INT_MASK		BIT(13)
+#define TX12_COHERENT_INT_MASK		BIT(12)
+#define TX11_COHERENT_INT_MASK		BIT(11)
+#define TX10_COHERENT_INT_MASK		BIT(10)
+#define TX9_COHERENT_INT_MASK		BIT(9)
+#define TX8_COHERENT_INT_MASK		BIT(8)
+
+#define TX_COHERENT_HIGH_INT_MASK				\
+	(TX31_COHERENT_INT_MASK | TX30_COHERENT_INT_MASK |	\
+	 TX29_COHERENT_INT_MASK | TX28_COHERENT_INT_MASK |	\
+	 TX27_COHERENT_INT_MASK | TX26_COHERENT_INT_MASK |	\
+	 TX25_COHERENT_INT_MASK | TX24_COHERENT_INT_MASK |	\
+	 TX23_COHERENT_INT_MASK | TX22_COHERENT_INT_MASK |	\
+	 TX21_COHERENT_INT_MASK | TX20_COHERENT_INT_MASK |	\
+	 TX19_COHERENT_INT_MASK | TX18_COHERENT_INT_MASK |	\
+	 TX17_COHERENT_INT_MASK | TX16_COHERENT_INT_MASK |	\
+	 TX15_COHERENT_INT_MASK | TX14_COHERENT_INT_MASK |	\
+	 TX13_COHERENT_INT_MASK | TX12_COHERENT_INT_MASK |	\
+	 TX11_COHERENT_INT_MASK | TX10_COHERENT_INT_MASK |	\
+	 TX9_COHERENT_INT_MASK | TX8_COHERENT_INT_MASK)
+
+#define REG_TX_IRQ_BASE(_n)		((_n) ? 0x0048 : 0x0050)
+
+#define REG_TX_IRQ_CFG(_n)		((_n) ? 0x004c : 0x0054)
+#define TX_IRQ_THR_MASK			GENMASK(27, 16)
+#define TX_IRQ_DEPTH_MASK		GENMASK(11, 0)
+
+#define REG_IRQ_CLEAR_LEN(_n)		((_n) ? 0x0064 : 0x0058)
+#define IRQ_CLEAR_LEN_MASK		GENMASK(7, 0)
+
+#define REG_IRQ_STATUS(_n)		((_n) ? 0x0068 : 0x005c)
+#define IRQ_ENTRY_LEN_MASK		GENMASK(27, 16)
+#define IRQ_HEAD_IDX_MASK		GENMASK(11, 0)
+
+#define REG_TX_RING_BASE(_n)	\
+	(((_n) < 8) ? 0x0100 + ((_n) << 5) : 0x0b00 + (((_n) - 8) << 5))
+
+#define REG_TX_RING_BLOCKING(_n)	\
+	(((_n) < 8) ? 0x0104 + ((_n) << 5) : 0x0b04 + (((_n) - 8) << 5))
+
+#define TX_RING_IRQ_BLOCKING_MAP_MASK			BIT(6)
+#define TX_RING_IRQ_BLOCKING_CFG_MASK			BIT(4)
+#define TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK		BIT(2)
+#define TX_RING_IRQ_BLOCKING_MAX_TH_TXRING_EN_MASK	BIT(1)
+#define TX_RING_IRQ_BLOCKING_MIN_TH_TXRING_EN_MASK	BIT(0)
+
+#define REG_TX_CPU_IDX(_n)	\
+	(((_n) < 8) ? 0x0108 + ((_n) << 5) : 0x0b08 + (((_n) - 8) << 5))
+
+#define TX_RING_CPU_IDX_MASK		GENMASK(15, 0)
+
+#define REG_TX_DMA_IDX(_n)	\
+	(((_n) < 8) ? 0x010c + ((_n) << 5) : 0x0b0c + (((_n) - 8) << 5))
+
+#define TX_RING_DMA_IDX_MASK		GENMASK(15, 0)
+
+#define IRQ_RING_IDX_MASK		GENMASK(20, 16)
+#define IRQ_DESC_IDX_MASK		GENMASK(15, 0)
+
+#define REG_RX_RING_BASE(_n)	\
+	(((_n) < 16) ? 0x0200 + ((_n) << 5) : 0x0e00 + (((_n) - 16) << 5))
+
+#define REG_RX_RING_SIZE(_n)	\
+	(((_n) < 16) ? 0x0204 + ((_n) << 5) : 0x0e04 + (((_n) - 16) << 5))
+
+#define RX_RING_THR_MASK		GENMASK(31, 16)
+#define RX_RING_SIZE_MASK		GENMASK(15, 0)
+
+#define REG_RX_CPU_IDX(_n)	\
+	(((_n) < 16) ? 0x0208 + ((_n) << 5) : 0x0e08 + (((_n) - 16) << 5))
+
+#define RX_RING_CPU_IDX_MASK		GENMASK(15, 0)
+
+#define REG_RX_DMA_IDX(_n)	\
+	(((_n) < 16) ? 0x020c + ((_n) << 5) : 0x0e0c + (((_n) - 16) << 5))
+
+#define REG_RX_DELAY_INT_IDX(_n)	\
+	(((_n) < 16) ? 0x0210 + ((_n) << 5) : 0x0e10 + (((_n) - 16) << 5))
+
+#define REG_RX_SCATTER_CFG(_n)	\
+	(((_n) < 16) ? 0x0214 + ((_n) << 5) : 0x0e14 + (((_n) - 16) << 5))
+
+#define RX_DELAY_INT_MASK		GENMASK(15, 0)
+
+#define RX_RING_DMA_IDX_MASK		GENMASK(15, 0)
+
+#define RX_RING_SG_EN_MASK		BIT(0)
+
+#define REG_INGRESS_TRTCM_CFG		0x0070
+#define INGRESS_TRTCM_EN_MASK		BIT(31)
+#define INGRESS_TRTCM_MODE_MASK		BIT(30)
+#define INGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define INGRESS_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define REG_QUEUE_CLOSE_CFG(_n)		(0x00a0 + ((_n) & 0xfc))
+#define TXQ_DISABLE_CHAN_QUEUE_MASK(_n, _m)	BIT((_m) + (((_n) & 0x3) << 3))
+
+#define REG_TXQ_DIS_CFG_BASE(_n)	((_n) ? 0x20a0 : 0x00a0)
+#define REG_TXQ_DIS_CFG(_n, _m)		(REG_TXQ_DIS_CFG_BASE((_n)) + (_m) << 2)
+
+#define REG_CNTR_CFG(_n)		(0x0400 + ((_n) << 3))
+#define CNTR_EN_MASK			BIT(31)
+#define CNTR_ALL_CHAN_EN_MASK		BIT(30)
+#define CNTR_ALL_QUEUE_EN_MASK		BIT(29)
+#define CNTR_ALL_DSCP_RING_EN_MASK	BIT(28)
+#define CNTR_SRC_MASK			GENMASK(27, 24)
+#define CNTR_DSCP_RING_MASK		GENMASK(20, 16)
+#define CNTR_CHAN_MASK			GENMASK(7, 3)
+#define CNTR_QUEUE_MASK			GENMASK(2, 0)
+
+#define REG_CNTR_VAL(_n)		(0x0404 + ((_n) << 3))
+
+#define REG_LMGR_INIT_CFG		0x1000
+#define LMGR_INIT_START			BIT(31)
+#define LMGR_SRAM_MODE_MASK		BIT(30)
+#define HW_FWD_PKTSIZE_OVERHEAD_MASK	GENMASK(27, 20)
+#define HW_FWD_DESC_NUM_MASK		GENMASK(16, 0)
+
+#define REG_FWD_DSCP_LOW_THR		0x1004
+#define FWD_DSCP_LOW_THR_MASK		GENMASK(17, 0)
+
+#define REG_EGRESS_RATE_METER_CFG		0x100c
+#define EGRESS_RATE_METER_EN_MASK		BIT(31)
+#define EGRESS_RATE_METER_EQ_RATE_EN_MASK	BIT(17)
+#define EGRESS_RATE_METER_WINDOW_SZ_MASK	GENMASK(16, 12)
+#define EGRESS_RATE_METER_TIMESLICE_MASK	GENMASK(10, 0)
+
+#define REG_EGRESS_TRTCM_CFG		0x1010
+#define EGRESS_TRTCM_EN_MASK		BIT(31)
+#define EGRESS_TRTCM_MODE_MASK		BIT(30)
+#define EGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define EGRESS_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define TRTCM_PARAM_RW_MASK		BIT(31)
+#define TRTCM_PARAM_RW_DONE_MASK	BIT(30)
+#define TRTCM_PARAM_TYPE_MASK		GENMASK(29, 28)
+#define TRTCM_METER_GROUP_MASK		GENMASK(27, 26)
+#define TRTCM_PARAM_INDEX_MASK		GENMASK(23, 17)
+#define TRTCM_PARAM_RATE_TYPE_MASK	BIT(16)
+
+#define REG_TRTCM_CFG_PARAM(_n)		((_n) + 0x4)
+#define REG_TRTCM_DATA_LOW(_n)		((_n) + 0x8)
+#define REG_TRTCM_DATA_HIGH(_n)		((_n) + 0xc)
+
+#define RATE_LIMIT_PARAM_RW_MASK	BIT(31)
+#define RATE_LIMIT_PARAM_RW_DONE_MASK	BIT(30)
+#define RATE_LIMIT_PARAM_TYPE_MASK	GENMASK(29, 28)
+#define RATE_LIMIT_METER_GROUP_MASK	GENMASK(27, 26)
+#define RATE_LIMIT_PARAM_INDEX_MASK	GENMASK(23, 16)
+
+#define REG_TXWRR_MODE_CFG		0x1020
+#define TWRR_WEIGHT_SCALE_MASK		BIT(31)
+#define TWRR_WEIGHT_BASE_MASK		BIT(3)
+
+#define REG_TXWRR_WEIGHT_CFG		0x1024
+#define TWRR_RW_CMD_MASK		BIT(31)
+#define TWRR_RW_CMD_DONE		BIT(30)
+#define TWRR_CHAN_IDX_MASK		GENMASK(23, 19)
+#define TWRR_QUEUE_IDX_MASK		GENMASK(18, 16)
+#define TWRR_VALUE_MASK			GENMASK(15, 0)
+
+#define REG_PSE_BUF_USAGE_CFG		0x1028
+#define PSE_BUF_ESTIMATE_EN_MASK	BIT(29)
+
+#define REG_CHAN_QOS_MODE(_n)		(0x1040 + ((_n) << 2))
+#define CHAN_QOS_MODE_MASK(_n)		GENMASK(2 + ((_n) << 2), (_n) << 2)
+
+#define REG_GLB_TRTCM_CFG		0x1080
+#define GLB_TRTCM_EN_MASK		BIT(31)
+#define GLB_TRTCM_MODE_MASK		BIT(30)
+#define GLB_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define GLB_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define REG_TXQ_CNGST_CFG		0x10a0
+#define TXQ_CNGST_DROP_EN		BIT(31)
+#define TXQ_CNGST_DEI_DROP_EN		BIT(30)
+
+#define REG_SLA_TRTCM_CFG		0x1150
+#define SLA_TRTCM_EN_MASK		BIT(31)
+#define SLA_TRTCM_MODE_MASK		BIT(30)
+#define SLA_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define SLA_FAST_TICK_MASK		GENMASK(15, 0)
+
+/* CTRL */
+#define QDMA_DESC_DONE_MASK		BIT(31)
+#define QDMA_DESC_DROP_MASK		BIT(30) /* tx: drop - rx: overflow */
+#define QDMA_DESC_MORE_MASK		BIT(29) /* more SG elements */
+#define QDMA_DESC_DEI_MASK		BIT(25)
+#define QDMA_DESC_NO_DROP_MASK		BIT(24)
+#define QDMA_DESC_LEN_MASK		GENMASK(15, 0)
+/* DATA */
+#define QDMA_DESC_NEXT_ID_MASK		GENMASK(15, 0)
+/* TX MSG0 */
+#define QDMA_ETH_TXMSG_MIC_IDX_MASK	BIT(30)
+#define QDMA_ETH_TXMSG_SP_TAG_MASK	GENMASK(29, 14)
+#define QDMA_ETH_TXMSG_ICO_MASK		BIT(13)
+#define QDMA_ETH_TXMSG_UCO_MASK		BIT(12)
+#define QDMA_ETH_TXMSG_TCO_MASK		BIT(11)
+#define QDMA_ETH_TXMSG_TSO_MASK		BIT(10)
+#define QDMA_ETH_TXMSG_FAST_MASK	BIT(9)
+#define QDMA_ETH_TXMSG_OAM_MASK		BIT(8)
+#define QDMA_ETH_TXMSG_CHAN_MASK	GENMASK(7, 3)
+#define QDMA_ETH_TXMSG_QUEUE_MASK	GENMASK(2, 0)
+/* TX MSG1 */
+#define QDMA_ETH_TXMSG_NO_DROP		BIT(31)
+#define QDMA_ETH_TXMSG_METER_MASK	GENMASK(30, 24)	/* 0x7f no meters */
+#define QDMA_ETH_TXMSG_FPORT_MASK	GENMASK(23, 20)
+#define QDMA_ETH_TXMSG_NBOQ_MASK	GENMASK(19, 15)
+#define QDMA_ETH_TXMSG_HWF_MASK		BIT(14)
+#define QDMA_ETH_TXMSG_HOP_MASK		BIT(13)
+#define QDMA_ETH_TXMSG_PTP_MASK		BIT(12)
+#define QDMA_ETH_TXMSG_ACNT_G1_MASK	GENMASK(10, 6)	/* 0x1f do not count */
+#define QDMA_ETH_TXMSG_ACNT_G0_MASK	GENMASK(5, 0)	/* 0x3f do not count */
+
+/* RX MSG0 */
+#define QDMA_ETH_RXMSG_SPTAG		GENMASK(21, 14)
+/* RX MSG1 */
+#define QDMA_ETH_RXMSG_DEI_MASK		BIT(31)
+#define QDMA_ETH_RXMSG_IP6_MASK		BIT(30)
+#define QDMA_ETH_RXMSG_IP4_MASK		BIT(29)
+#define QDMA_ETH_RXMSG_IP4F_MASK	BIT(28)
+#define QDMA_ETH_RXMSG_L4_VALID_MASK	BIT(27)
+#define QDMA_ETH_RXMSG_L4F_MASK		BIT(26)
+#define QDMA_ETH_RXMSG_SPORT_MASK	GENMASK(25, 21)
+#define QDMA_ETH_RXMSG_CRSN_MASK	GENMASK(20, 16)
+#define QDMA_ETH_RXMSG_PPE_ENTRY_MASK	GENMASK(15, 0)
+
+struct airoha_qdma_desc {
+	__le32 rsv;
+	__le32 ctrl;
+	__le32 addr;
+	__le32 data;
+	__le32 msg0;
+	__le32 msg1;
+	__le32 msg2;
+	__le32 msg3;
+};
+
+/* CTRL0 */
+#define QDMA_FWD_DESC_CTX_MASK		BIT(31)
+#define QDMA_FWD_DESC_RING_MASK		GENMASK(30, 28)
+#define QDMA_FWD_DESC_IDX_MASK		GENMASK(27, 16)
+#define QDMA_FWD_DESC_LEN_MASK		GENMASK(15, 0)
+/* CTRL1 */
+#define QDMA_FWD_DESC_FIRST_IDX_MASK	GENMASK(15, 0)
+/* CTRL2 */
+#define QDMA_FWD_DESC_MORE_PKT_NUM_MASK	GENMASK(2, 0)
+
+struct airoha_qdma_fwd_desc {
+	__le32 addr;
+	__le32 ctrl0;
+	__le32 ctrl1;
+	__le32 ctrl2;
+	__le32 msg0;
+	__le32 msg1;
+	__le32 rsv0;
+	__le32 rsv1;
+};
+
+#endif /* AIROHA_REGS_H */
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 63c8a2328142..86fd08f375df 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -5,9 +5,6 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#ifdef CONFIG_RFS_ACCEL
-#include <linux/cpu_rmap.h>
-#endif /* CONFIG_RFS_ACCEL */
 #include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -74,7 +71,7 @@ static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	if (threshold < time_since_last_napi && napi_scheduled) {
 		netdev_err(dev,
 			   "napi handler hasn't been called for a long time but is scheduled\n");
-			   reset_reason = ENA_REGS_RESET_SUSPECTED_POLL_STARVATION;
+		reset_reason = ENA_REGS_RESET_SUSPECTED_POLL_STARVATION;
 	}
 schedule_reset:
 	/* Change the state of the device to trigger reset
@@ -162,30 +159,6 @@ int ena_xmit_common(struct ena_adapter *adapter,
 	return 0;
 }
 
-static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
-{
-#ifdef CONFIG_RFS_ACCEL
-	u32 i;
-	int rc;
-
-	adapter->netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(adapter->num_io_queues);
-	if (!adapter->netdev->rx_cpu_rmap)
-		return -ENOMEM;
-	for (i = 0; i < adapter->num_io_queues; i++) {
-		int irq_idx = ENA_IO_IRQ_IDX(i);
-
-		rc = irq_cpu_rmap_add(adapter->netdev->rx_cpu_rmap,
-				      pci_irq_vector(adapter->pdev, irq_idx));
-		if (rc) {
-			free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-			adapter->netdev->rx_cpu_rmap = NULL;
-			return rc;
-		}
-	}
-#endif /* CONFIG_RFS_ACCEL */
-	return 0;
-}
-
 static void ena_init_io_rings_common(struct ena_adapter *adapter,
 				     struct ena_ring *ring, u16 qid)
 {
@@ -1596,7 +1569,7 @@ static int ena_enable_msix(struct ena_adapter *adapter)
 		adapter->num_io_queues = irq_cnt - ENA_ADMIN_MSIX_VEC;
 	}
 
-	if (ena_init_rx_cpu_rmap(adapter))
+	if (netif_enable_cpu_rmap(adapter->netdev, adapter->num_io_queues))
 		netif_warn(adapter, probe, adapter->netdev,
 			   "Failed to map IRQs to CPUs\n");
 
@@ -1742,16 +1715,13 @@ static void ena_free_io_irq(struct ena_adapter *adapter)
 	struct ena_irq *irq;
 	int i;
 
-#ifdef CONFIG_RFS_ACCEL
-	if (adapter->msix_vecs >= 1) {
-		free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-		adapter->netdev->rx_cpu_rmap = NULL;
-	}
-#endif /* CONFIG_RFS_ACCEL */
-
 	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) {
+		struct ena_napi *ena_napi;
+
 		irq = &adapter->irq_tbl[i];
 		irq_set_affinity_hint(irq->vector, NULL);
+		ena_napi = irq->data;
+		netif_napi_set_irq(&ena_napi->napi, -1);
 		free_irq(irq->vector, irq->data);
 	}
 }
@@ -1807,7 +1777,7 @@ static void ena_init_napi_in_range(struct ena_adapter *adapter,
 		if (ENA_IS_XDP_INDEX(adapter, i))
 			napi_handler = ena_xdp_io_poll;
 
-		netif_napi_add(adapter->netdev, &napi->napi, napi_handler);
+		netif_napi_add_config(adapter->netdev, &napi->napi, napi_handler, i);
 
 		if (!ENA_IS_XDP_INDEX(adapter, i))
 			napi->rx_ring = rx_ring;
@@ -3275,7 +3245,7 @@ static int ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 
 	netif_carrier_off(netdev);
 
-	del_timer_sync(&adapter->timer_service);
+	timer_delete_sync(&adapter->timer_service);
 
 	dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
 	adapter->dev_up_before_reset = dev_up;
@@ -3697,7 +3667,8 @@ static void ena_update_host_info(struct ena_admin_host_info *host_info,
 
 static void ena_timer_service(struct timer_list *t)
 {
-	struct ena_adapter *adapter = from_timer(adapter, t, timer_service);
+	struct ena_adapter *adapter = timer_container_of(adapter, t,
+							 timer_service);
 	u8 *debug_area = adapter->ena_dev->host_attr.debug_area_virt_addr;
 	struct ena_admin_host_info *host_info =
 		adapter->ena_dev->host_attr.host_info;
@@ -4095,7 +4066,7 @@ err_free_msix:
 	ena_free_mgmnt_irq(adapter);
 	ena_disable_msix(adapter);
 err_worker_destroy:
-	del_timer(&adapter->timer_service);
+	timer_delete(&adapter->timer_service);
 err_device_destroy:
 	ena_com_delete_host_info(ena_dev);
 	ena_com_admin_destroy(ena_dev);
@@ -4131,17 +4102,10 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 	ena_dev = adapter->ena_dev;
 	netdev = adapter->netdev;
 
-#ifdef CONFIG_RFS_ACCEL
-	if ((adapter->msix_vecs >= 1) && (netdev->rx_cpu_rmap)) {
-		free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-		netdev->rx_cpu_rmap = NULL;
-	}
-
-#endif /* CONFIG_RFS_ACCEL */
 	/* Make sure timer and reset routine won't be called after
 	 * freeing device resources.
 	 */
-	del_timer_sync(&adapter->timer_service);
+	timer_delete_sync(&adapter->timer_service);
 	cancel_work_sync(&adapter->reset_task);
 
 	rtnl_lock(); /* lock released inside the below if-else block */
diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c
index 1ca26a8c40eb..ce9445425045 100644
--- a/drivers/net/ethernet/amd/a2065.c
+++ b/drivers/net/ethernet/amd/a2065.c
@@ -486,7 +486,7 @@ static int lance_close(struct net_device *dev)
 	volatile struct lance_regs *ll = lp->ll;
 
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->multicast_timer);
+	timer_delete_sync(&lp->multicast_timer);
 
 	/* Stop the card */
 	ll->rap = LE_CSR0;
@@ -636,7 +636,7 @@ static void lance_set_multicast(struct net_device *dev)
 
 static void lance_set_multicast_retry(struct timer_list *t)
 {
-	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+	struct lance_private *lp = timer_container_of(lp, t, multicast_timer);
 
 	lance_set_multicast(lp->dev);
 }
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index f64f96fa17cf..76e8c13d5985 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1173,7 +1173,7 @@ static int amd8111e_close(struct net_device *dev)
 
 	/* Delete ipg timer */
 	if (lp->options & OPTION_DYN_IPG_ENABLE)
-		del_timer_sync(&lp->ipg_data.ipg_timer);
+		timer_delete_sync(&lp->ipg_data.ipg_timer);
 
 	spin_unlock_irq(&lp->lock);
 	free_irq(dev->irq, dev);
@@ -1598,7 +1598,7 @@ static int __maybe_unused amd8111e_suspend(struct device *dev_d)
 	/* stop chip */
 	spin_lock_irq(&lp->lock);
 	if (lp->options & OPTION_DYN_IPG_ENABLE)
-		del_timer_sync(&lp->ipg_data.ipg_timer);
+		timer_delete_sync(&lp->ipg_data.ipg_timer);
 	amd8111e_stop_chip(lp);
 	spin_unlock_irq(&lp->lock);
 
@@ -1641,7 +1641,8 @@ static int __maybe_unused amd8111e_resume(struct device *dev_d)
 
 static void amd8111e_config_ipg(struct timer_list *t)
 {
-	struct amd8111e_priv *lp = from_timer(lp, t, ipg_data.ipg_timer);
+	struct amd8111e_priv *lp = timer_container_of(lp, t,
+						      ipg_data.ipg_timer);
 	struct ipg_info *ipg_data = &lp->ipg_data;
 	void __iomem *mmio = lp->mmio;
 	unsigned int prev_col_cnt = ipg_data->col_cnt;
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 0671a066913b..9d35ac348ebe 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -571,7 +571,7 @@ static struct db_dest *au1000_GetFreeDB(struct au1000_private *aup)
 	return pDB;
 }
 
-void au1000_ReleaseDB(struct au1000_private *aup, struct db_dest *pDB)
+static void au1000_ReleaseDB(struct au1000_private *aup, struct db_dest *pDB)
 {
 	struct db_dest *pDBfree = aup->pDBfree;
 	if (pDBfree)
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index ec8df05e7bf6..8d05a0c5f2d5 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -842,7 +842,7 @@ static int lance_close(struct net_device *dev)
 	volatile struct lance_regs *ll = lp->ll;
 
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->multicast_timer);
+	timer_delete_sync(&lp->multicast_timer);
 
 	/* Stop the card */
 	writereg(&ll->rap, LE_CSR0);
@@ -1004,7 +1004,7 @@ static void lance_set_multicast(struct net_device *dev)
 
 static void lance_set_multicast_retry(struct timer_list *t)
 {
-	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+	struct lance_private *lp = timer_container_of(lp, t, multicast_timer);
 	struct net_device *dev = lp->dev;
 
 	lance_set_multicast(dev);
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 72db9f9e7bee..9eaefa0f5e80 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -462,7 +462,7 @@ static void pcnet32_netif_start(struct net_device *dev)
 	val = lp->a->read_csr(ioaddr, CSR3);
 	val &= 0x00ff;
 	lp->a->write_csr(ioaddr, CSR3, val);
-	napi_enable(&lp->napi);
+	napi_enable_locked(&lp->napi);
 }
 
 /*
@@ -889,6 +889,7 @@ static int pcnet32_set_ringparam(struct net_device *dev,
 	if (netif_running(dev))
 		pcnet32_netif_stop(dev);
 
+	netdev_lock(dev);
 	spin_lock_irqsave(&lp->lock, flags);
 	lp->a->write_csr(ioaddr, CSR0, CSR0_STOP);	/* stop the chip */
 
@@ -920,6 +921,7 @@ static int pcnet32_set_ringparam(struct net_device *dev,
 	}
 
 	spin_unlock_irqrestore(&lp->lock, flags);
+	netdev_unlock(dev);
 
 	netif_info(lp, drv, dev, "Ring Param Settings: RX: %d, TX: %d\n",
 		   lp->rx_ring_size, lp->tx_ring_size);
@@ -985,6 +987,7 @@ static int pcnet32_loopback_test(struct net_device *dev, uint64_t * data1)
 	if (netif_running(dev))
 		pcnet32_netif_stop(dev);
 
+	netdev_lock(dev);
 	spin_lock_irqsave(&lp->lock, flags);
 	lp->a->write_csr(ioaddr, CSR0, CSR0_STOP);	/* stop the chip */
 
@@ -1122,6 +1125,7 @@ clean_up:
 		lp->a->write_bcr(ioaddr, 20, 4);	/* return to 16bit mode */
 	}
 	spin_unlock_irqrestore(&lp->lock, flags);
+	netdev_unlock(dev);
 
 	return rc;
 }				/* end pcnet32_loopback_test  */
@@ -2101,6 +2105,7 @@ static int pcnet32_open(struct net_device *dev)
 		return -EAGAIN;
 	}
 
+	netdev_lock(dev);
 	spin_lock_irqsave(&lp->lock, flags);
 	/* Check for a valid station address */
 	if (!is_valid_ether_addr(dev->dev_addr)) {
@@ -2266,7 +2271,7 @@ static int pcnet32_open(struct net_device *dev)
 		goto err_free_ring;
 	}
 
-	napi_enable(&lp->napi);
+	napi_enable_locked(&lp->napi);
 
 	/* Re-initialize the PCNET32, and start it when done. */
 	lp->a->write_csr(ioaddr, 1, (lp->init_dma_addr & 0xffff));
@@ -2300,6 +2305,7 @@ static int pcnet32_open(struct net_device *dev)
 		     lp->a->read_csr(ioaddr, CSR0));
 
 	spin_unlock_irqrestore(&lp->lock, flags);
+	netdev_unlock(dev);
 
 	return 0;		/* Always succeed */
 
@@ -2315,6 +2321,7 @@ err_free_ring:
 
 err_free_irq:
 	spin_unlock_irqrestore(&lp->lock, flags);
+	netdev_unlock(dev);
 	free_irq(dev->irq, dev);
 	return rc;
 }
@@ -2623,7 +2630,7 @@ static int pcnet32_close(struct net_device *dev)
 	struct pcnet32_private *lp = netdev_priv(dev);
 	unsigned long flags;
 
-	del_timer_sync(&lp->watchdog_timer);
+	timer_delete_sync(&lp->watchdog_timer);
 
 	netif_stop_queue(dev);
 	napi_disable(&lp->napi);
@@ -2898,7 +2905,7 @@ static void pcnet32_check_media(struct net_device *dev, int verbose)
 
 static void pcnet32_watchdog(struct timer_list *t)
 {
-	struct pcnet32_private *lp = from_timer(lp, t, watchdog_timer);
+	struct pcnet32_private *lp = timer_container_of(lp, t, watchdog_timer);
 	struct net_device *dev = lp->dev;
 	unsigned long flags;
 
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index c83a0a80d533..097bb092bdb8 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -5,11 +5,6 @@
 
 #include "core.h"
 
-struct pdsc_wait_context {
-	struct pdsc_qcq *qcq;
-	struct completion wait_completion;
-};
-
 static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 {
 	union pds_core_notifyq_comp *comp;
@@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 		q_info = &q->info[q->tail_idx];
 		q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
 
-		/* Copy out the completion data */
-		memcpy(q_info->dest, comp, sizeof(*comp));
-
-		complete_all(&q_info->wc->wait_completion);
+		if (!completion_done(&q_info->completion)) {
+			memcpy(q_info->dest, comp, sizeof(*comp));
+			complete(&q_info->completion);
+		}
 
 		if (cq->tail_idx == cq->num_descs - 1)
 			cq->done_color = !cq->done_color;
@@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 static int __pdsc_adminq_post(struct pdsc *pdsc,
 			      struct pdsc_qcq *qcq,
 			      union pds_core_adminq_cmd *cmd,
-			      union pds_core_adminq_comp *comp,
-			      struct pdsc_wait_context *wc)
+			      union pds_core_adminq_comp *comp)
 {
 	struct pdsc_queue *q = &qcq->q;
 	struct pdsc_q_info *q_info;
@@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 	/* Post the request */
 	index = q->head_idx;
 	q_info = &q->info[index];
-	q_info->wc = wc;
 	q_info->dest = comp;
 	memcpy(q_info->desc, cmd, sizeof(*cmd));
+	reinit_completion(&q_info->completion);
 
 	dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n",
 		q->head_idx, q->tail_idx);
@@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		     union pds_core_adminq_comp *comp,
 		     bool fast_poll)
 {
-	struct pdsc_wait_context wc = {
-		.wait_completion =
-			COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion),
-	};
-	unsigned long poll_interval = 1;
+	unsigned long poll_interval = 200;
 	unsigned long poll_jiffies;
 	unsigned long time_limit;
 	unsigned long time_start;
 	unsigned long time_done;
 	unsigned long remaining;
+	struct completion *wc;
 	int err = 0;
 	int index;
 
@@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		return -ENXIO;
 	}
 
-	wc.qcq = &pdsc->adminqcq;
-	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
+	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp);
 	if (index < 0) {
 		err = index;
 		goto err_out;
 	}
 
+	wc = &pdsc->adminqcq.q.info[index].completion;
 	time_start = jiffies;
 	time_limit = time_start + HZ * pdsc->devcmd_timeout;
 	do {
 		/* Timeslice the actual wait to catch IO errors etc early */
-		poll_jiffies = msecs_to_jiffies(poll_interval);
-		remaining = wait_for_completion_timeout(&wc.wait_completion,
-							poll_jiffies);
+		poll_jiffies = usecs_to_jiffies(poll_interval);
+		remaining = wait_for_completion_timeout(wc, poll_jiffies);
 		if (remaining)
 			break;
 
@@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n",
 		__func__, jiffies_to_msecs(time_done - time_start));
 
-	/* Check the results */
-	if (time_after_eq(time_done, time_limit))
+	/* Check the results and clear an un-completed timeout */
+	if (time_after_eq(time_done, time_limit) && !completion_done(wc)) {
 		err = -ETIMEDOUT;
+		complete(wc);
+	}
 
 	dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index);
 	dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1,
diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index 2babea110991..92f359f2b449 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev,
 	dev_dbg(pf->dev, "%s: %s opcode %d\n",
 		__func__, dev_name(&padev->aux_dev.dev), req->opcode);
 
-	if (pf->state)
-		return -ENXIO;
-
 	/* Wrap the client's request */
 	cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
 	cmd.client_request.client_id = cpu_to_le16(padev->client_id);
@@ -175,34 +172,31 @@ static struct pds_auxiliary_dev *pdsc_auxbus_dev_register(struct pdsc *cf,
 	return padev;
 }
 
-int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf)
+void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
+			 struct pds_auxiliary_dev **pd_ptr)
 {
 	struct pds_auxiliary_dev *padev;
-	int err = 0;
 
-	if (!cf)
-		return -ENODEV;
+	if (!*pd_ptr)
+		return;
 
 	mutex_lock(&pf->config_lock);
 
-	padev = pf->vfs[cf->vf_id].padev;
-	if (padev) {
-		pds_client_unregister(pf, padev->client_id);
-		auxiliary_device_delete(&padev->aux_dev);
-		auxiliary_device_uninit(&padev->aux_dev);
-		padev->client_id = 0;
-	}
-	pf->vfs[cf->vf_id].padev = NULL;
+	padev = *pd_ptr;
+	pds_client_unregister(pf, padev->client_id);
+	auxiliary_device_delete(&padev->aux_dev);
+	auxiliary_device_uninit(&padev->aux_dev);
+	*pd_ptr = NULL;
 
 	mutex_unlock(&pf->config_lock);
-	return err;
 }
 
-int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
+int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf,
+			enum pds_core_vif_types vt,
+			struct pds_auxiliary_dev **pd_ptr)
 {
 	struct pds_auxiliary_dev *padev;
 	char devname[PDS_DEVNAME_LEN];
-	enum pds_core_vif_types vt;
 	unsigned long mask;
 	u16 vt_support;
 	int client_id;
@@ -211,6 +205,9 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 	if (!cf)
 		return -ENODEV;
 
+	if (vt >= PDS_DEV_TYPE_MAX)
+		return -EINVAL;
+
 	mutex_lock(&pf->config_lock);
 
 	mask = BIT_ULL(PDSC_S_FW_DEAD) |
@@ -222,17 +219,10 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 		goto out_unlock;
 	}
 
-	/* We only support vDPA so far, so it is the only one to
-	 * be verified that it is available in the Core device and
-	 * enabled in the devlink param.  In the future this might
-	 * become a loop for several VIF types.
-	 */
-
 	/* Verify that the type is supported and enabled.  It is not
-	 * an error if there is no auxbus device support for this
-	 * VF, it just means something else needs to happen with it.
+	 * an error if the firmware doesn't support the feature, the
+	 * driver just won't set up an auxiliary_device for it.
 	 */
-	vt = PDS_DEV_TYPE_VDPA;
 	vt_support = !!le16_to_cpu(pf->dev_ident.vif_types[vt]);
 	if (!(vt_support &&
 	      pf->viftype_status[vt].supported &&
@@ -258,7 +248,7 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 		err = PTR_ERR(padev);
 		goto out_unlock;
 	}
-	pf->vfs[cf->vf_id].padev = padev;
+	*pd_ptr = padev;
 
 out_unlock:
 	mutex_unlock(&pf->config_lock);
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 536635e57727..076dfe2910c7 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa)
 	q->base = base;
 	q->base_pa = base_pa;
 
-	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++)
+	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) {
 		cur->desc = base + (i * q->desc_size);
+		init_completion(&cur->completion);
+	}
 }
 
 static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa)
@@ -325,10 +327,7 @@ static int pdsc_core_init(struct pdsc *pdsc)
 	size_t sz;
 	int err;
 
-	/* Scale the descriptor ring length based on number of CPUs and VFs */
-	numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus());
-	numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev);
-	numdescs = roundup_pow_of_two(numdescs);
+	numdescs = PDSC_ADMINQ_MAX_LENGTH;
 	err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq",
 			     PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR,
 			     numdescs,
@@ -402,6 +401,10 @@ err_out_uninit:
 }
 
 static struct pdsc_viftype pdsc_viftype_defaults[] = {
+	[PDS_DEV_TYPE_FWCTL] = { .name = PDS_DEV_TYPE_FWCTL_STR,
+				 .enabled = true,
+				 .vif_id = PDS_DEV_TYPE_FWCTL,
+				 .dl_id = -1 },
 	[PDS_DEV_TYPE_VDPA] = { .name = PDS_DEV_TYPE_VDPA_STR,
 				.vif_id = PDS_DEV_TYPE_VDPA,
 				.dl_id = DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET },
@@ -412,7 +415,8 @@ static int pdsc_viftypes_init(struct pdsc *pdsc)
 {
 	enum pds_core_vif_types vt;
 
-	pdsc->viftype_status = kzalloc(sizeof(pdsc_viftype_defaults),
+	pdsc->viftype_status = kcalloc(ARRAY_SIZE(pdsc_viftype_defaults),
+				       sizeof(*pdsc->viftype_status),
 				       GFP_KERNEL);
 	if (!pdsc->viftype_status)
 		return -ENOMEM;
@@ -428,6 +432,7 @@ static int pdsc_viftypes_init(struct pdsc *pdsc)
 
 		/* See what the Core device has for support */
 		vt_support = !!le16_to_cpu(pdsc->dev_ident.vif_types[vt]);
+
 		dev_dbg(pdsc->dev, "VIF %s is %ssupported\n",
 			pdsc->viftype_status[vt].name,
 			vt_support ? "" : "not ");
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 14522d6d5f86..0b53a1fab46d 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -16,7 +16,7 @@
 
 #define PDSC_WATCHDOG_SECS	5
 #define PDSC_QUEUE_NAME_MAX_SZ  16
-#define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
+#define PDSC_ADMINQ_MAX_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false
 #define PDSC_TEARDOWN_REMOVING	true
@@ -96,7 +96,7 @@ struct pdsc_q_info {
 	unsigned int bytes;
 	unsigned int nbufs;
 	struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS];
-	struct pdsc_wait_context *wc;
+	struct completion completion;
 	void *dest;
 };
 
@@ -156,6 +156,7 @@ struct pdsc {
 	struct dentry *dentry;
 	struct device *dev;
 	struct pdsc_dev_bar bars[PDS_CORE_BARS_MAX];
+	struct pds_auxiliary_dev *padev;
 	struct pdsc_vf *vfs;
 	int num_vfs;
 	int vf_id;
@@ -303,8 +304,11 @@ void pdsc_health_thread(struct work_struct *work);
 int pdsc_register_notify(struct notifier_block *nb);
 void pdsc_unregister_notify(struct notifier_block *nb);
 void pdsc_notify(unsigned long event, void *data);
-int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf);
-int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf);
+int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf,
+			enum pds_core_vif_types vt,
+			struct pds_auxiliary_dev **pd_ptr);
+void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
+			 struct pds_auxiliary_dev **pd_ptr);
 
 void pdsc_process_adminq(struct pdsc_qcq *qcq);
 void pdsc_work_thread(struct work_struct *work);
diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index ac37a4e738ae..04c5e3abd8d7 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -154,8 +154,9 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 		debugfs_create_u32("index", 0400, intr_dentry, &intr->index);
 		debugfs_create_u32("vector", 0400, intr_dentry, &intr->vector);
 
-		intr_ctrl_regset = kzalloc(sizeof(*intr_ctrl_regset),
-					   GFP_KERNEL);
+		intr_ctrl_regset = devm_kzalloc(pdsc->dev,
+						sizeof(*intr_ctrl_regset),
+						GFP_KERNEL);
 		if (!intr_ctrl_regset)
 			return;
 		intr_ctrl_regset->regs = intr_ctrl_regs;
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 2681889162a2..d8dc39da4161 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -56,8 +56,11 @@ int pdsc_dl_enable_set(struct devlink *dl, u32 id,
 	for (vf_id = 0; vf_id < pdsc->num_vfs; vf_id++) {
 		struct pdsc *vf = pdsc->vfs[vf_id].vf;
 
-		err = ctx->val.vbool ? pdsc_auxbus_dev_add(vf, pdsc) :
-				       pdsc_auxbus_dev_del(vf, pdsc);
+		if (ctx->val.vbool)
+			err = pdsc_auxbus_dev_add(vf, pdsc, vt_entry->vif_id,
+						  &pdsc->vfs[vf_id].padev);
+		else
+			pdsc_auxbus_dev_del(vf, pdsc, &pdsc->vfs[vf_id].padev);
 	}
 
 	return err;
@@ -102,7 +105,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 		.fw_control.opcode = PDS_CORE_CMD_FW_CONTROL,
 		.fw_control.oper = PDS_CORE_FW_GET_LIST,
 	};
-	struct pds_core_fw_list_info fw_list;
+	struct pds_core_fw_list_info fw_list = {};
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
 	char buf[32];
@@ -115,10 +118,8 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	if (!err)
 		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
-	if (err && err != -EIO)
-		return err;
 
-	listlen = fw_list.num_fw_slots;
+	listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
 	for (i = 0; i < listlen; i++) {
 		if (i < ARRAY_SIZE(fw_slotnames))
 			strscpy(buf, fw_slotnames[i], sizeof(buf));
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 660268ff9562..9b81e1c260c2 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -23,7 +23,7 @@ MODULE_DEVICE_TABLE(pci, pdsc_id_table);
 
 static void pdsc_wdtimer_cb(struct timer_list *t)
 {
-	struct pdsc *pdsc = from_timer(pdsc, t, wdtimer);
+	struct pdsc *pdsc = timer_container_of(pdsc, t, wdtimer);
 
 	dev_dbg(pdsc->dev, "%s: jiffies %ld\n", __func__, jiffies);
 	mod_timer(&pdsc->wdtimer,
@@ -190,7 +190,8 @@ static int pdsc_init_vf(struct pdsc *vf)
 	devl_unlock(dl);
 
 	pf->vfs[vf->vf_id].vf = vf;
-	err = pdsc_auxbus_dev_add(vf, pf);
+	err = pdsc_auxbus_dev_add(vf, pf, PDS_DEV_TYPE_VDPA,
+				  &pf->vfs[vf->vf_id].padev);
 	if (err) {
 		devl_lock(dl);
 		devl_unregister(dl);
@@ -264,6 +265,10 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 
 	mutex_unlock(&pdsc->config_lock);
 
+	err = pdsc_auxbus_dev_add(pdsc, pdsc, PDS_DEV_TYPE_FWCTL, &pdsc->padev);
+	if (err)
+		goto err_out_stop;
+
 	dl = priv_to_devlink(pdsc);
 	devl_lock(dl);
 	err = devl_params_register(dl, pdsc_dl_params,
@@ -272,7 +277,7 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 		devl_unlock(dl);
 		dev_warn(pdsc->dev, "Failed to register devlink params: %pe\n",
 			 ERR_PTR(err));
-		goto err_out_stop;
+		goto err_out_del_dev;
 	}
 
 	hr = devl_health_reporter_create(dl, &pdsc_fw_reporter_ops, 0, pdsc);
@@ -295,6 +300,8 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 err_out_unreg_params:
 	devlink_params_unregister(dl, pdsc_dl_params,
 				  ARRAY_SIZE(pdsc_dl_params));
+err_out_del_dev:
+	pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev);
 err_out_stop:
 	pdsc_stop(pdsc);
 err_out_teardown:
@@ -417,7 +424,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf)) {
-			pdsc_auxbus_dev_del(pdsc, pf);
+			pdsc_auxbus_dev_del(pdsc, pf, &pf->vfs[pdsc->vf_id].padev);
 			pf->vfs[pdsc->vf_id].vf = NULL;
 		}
 	} else {
@@ -426,6 +433,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 		 * shut themselves down.
 		 */
 		pdsc_sriov_configure(pdev, 0);
+		pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev);
 
 		timer_shutdown_sync(&pdsc->wdtimer);
 		if (pdsc->wq)
@@ -482,7 +490,10 @@ static void pdsc_reset_prepare(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf))
-			pdsc_auxbus_dev_del(pdsc, pf);
+			pdsc_auxbus_dev_del(pdsc, pf,
+					    &pf->vfs[pdsc->vf_id].padev);
+	} else {
+		pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev);
 	}
 
 	pdsc_unmap_bars(pdsc);
@@ -527,7 +538,11 @@ static void pdsc_reset_done(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf))
-			pdsc_auxbus_dev_add(pdsc, pf);
+			pdsc_auxbus_dev_add(pdsc, pf, PDS_DEV_TYPE_VDPA,
+					    &pf->vfs[pdsc->vf_id].padev);
+	} else {
+		pdsc_auxbus_dev_add(pdsc, pdsc, PDS_DEV_TYPE_FWCTL,
+				    &pdsc->padev);
 	}
 }
 
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index 0f98b92408ed..0b273327f5a6 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -963,7 +963,7 @@ static int lance_close(struct net_device *dev)
 	struct lance_private *lp = netdev_priv(dev);
 
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->multicast_timer);
+	timer_delete_sync(&lp->multicast_timer);
 
 	STOP_LANCE(lp);
 
@@ -1246,7 +1246,7 @@ static void lance_set_multicast(struct net_device *dev)
 
 static void lance_set_multicast_retry(struct timer_list *t)
 {
-	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+	struct lance_private *lp = timer_container_of(lp, t, multicast_timer);
 	struct net_device *dev = lp->dev;
 
 	lance_set_multicast(dev);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 3b70f6737633..9316de4126cf 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #ifndef __XGBE_COMMON_H__
@@ -900,6 +791,11 @@
 #define PCS_V2_RV_WINDOW_SELECT		0x1064
 #define PCS_V2_YC_WINDOW_DEF		0x18060
 #define PCS_V2_YC_WINDOW_SELECT		0x18064
+#define PCS_V3_RN_WINDOW_DEF		0xf8078
+#define PCS_V3_RN_WINDOW_SELECT		0xf807c
+
+#define PCS_RN_SMN_BASE_ADDR		0x11e00000
+#define PCS_RN_PORT_ADDR_SIZE		0x100000
 
 /* PCS register entry bit positions and sizes */
 #define PCS_V2_WINDOW_DEF_OFFSET_INDEX	6
@@ -1373,6 +1269,8 @@
 #define MDIO_VEND2_CTRL1_SS13		BIT(13)
 #endif
 
+#define XGBE_VEND2_MAC_AUTO_SW		BIT(9)
+
 /* MDIO mask values */
 #define XGBE_AN_CL73_INT_CMPLT		BIT(0)
 #define XGBE_AN_CL73_INC_LINK		BIT(1)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c b/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
index c68ace804e37..1474df5544fa 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index b0a6c96b6ef4..d9157c4acde9 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/debugfs.h>
@@ -505,21 +396,6 @@ void xgbe_debugfs_exit(struct xgbe_prv_data *pdata)
 
 void xgbe_debugfs_rename(struct xgbe_prv_data *pdata)
 {
-	char *buf;
-
-	if (!pdata->xgbe_debugfs)
-		return;
-
-	buf = kasprintf(GFP_KERNEL, "amd-xgbe-%s", pdata->netdev->name);
-	if (!buf)
-		return;
-
-	if (!strcmp(pdata->xgbe_debugfs->d_name.name, buf))
-		goto out;
-
-	debugfs_rename(pdata->xgbe_debugfs->d_parent, pdata->xgbe_debugfs,
-		       pdata->xgbe_debugfs->d_parent, buf);
-
-out:
-	kfree(buf);
+	debugfs_change_name(pdata->xgbe_debugfs,
+			    "amd-xgbe-%s", pdata->netdev->name);
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index 230726d7b74f..7c8a19988a52 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include "xgbe.h"
@@ -373,8 +264,13 @@ static int xgbe_map_rx_buffer(struct xgbe_prv_data *pdata,
 	}
 
 	/* Set up the header page info */
-	xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
-			     XGBE_SKB_ALLOC_SIZE);
+	if (pdata->netdev->features & NETIF_F_RXCSUM) {
+		xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+				     XGBE_SKB_ALLOC_SIZE);
+	} else {
+		xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+				     pdata->rx_buf_size);
+	}
 
 	/* Set up the buffer page info */
 	xgbe_set_buffer_data(&rdata->rx.buf, &ring->rx_buf_pa,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index f393228d41c7..466b5f6e5578 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/phy.h>
@@ -120,9 +11,11 @@
 #include <linux/bitrev.h>
 #include <linux/crc32.h>
 #include <linux/crc32poly.h>
+#include <linux/pci.h>
 
 #include "xgbe.h"
 #include "xgbe-common.h"
+#include "xgbe-smn.h"
 
 static inline unsigned int xgbe_get_max_frame(struct xgbe_prv_data *pdata)
 {
@@ -320,6 +213,18 @@ static void xgbe_config_sph_mode(struct xgbe_prv_data *pdata)
 	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, HDSMS, XGBE_SPH_HDSMS_SIZE);
 }
 
+static void xgbe_disable_sph_mode(struct xgbe_prv_data *pdata)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		if (!pdata->channel[i]->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(pdata->channel[i], DMA_CH_CR, SPH, 0);
+	}
+}
+
 static int xgbe_write_rss_reg(struct xgbe_prv_data *pdata, unsigned int type,
 			      unsigned int index, unsigned int val)
 {
@@ -1150,18 +1055,19 @@ static int xgbe_set_gpio(struct xgbe_prv_data *pdata, unsigned int gpio)
 	return 0;
 }
 
-static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
-				 int mmd_reg)
+static unsigned int xgbe_get_mmd_address(struct xgbe_prv_data *pdata,
+					 int mmd_reg)
 {
-	unsigned long flags;
-	unsigned int mmd_address, index, offset;
-	int mmd_data;
-
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	return (mmd_reg & XGBE_ADDR_C45) ?
+		mmd_reg & ~XGBE_ADDR_C45 :
+		(pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+}
 
+static void xgbe_get_pcs_index_and_offset(struct xgbe_prv_data *pdata,
+					  unsigned int mmd_address,
+					  unsigned int *index,
+					  unsigned int *offset)
+{
 	/* The PCS registers are accessed using mmio. The underlying
 	 * management interface uses indirect addressing to access the MMD
 	 * register sets. This requires accessing of the PCS register in two
@@ -1172,8 +1078,98 @@ static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
 	 * offset 1 bit and reading 16 bits of data.
 	 */
 	mmd_address <<= 1;
-	index = mmd_address & ~pdata->xpcs_window_mask;
-	offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+	*index = mmd_address & ~pdata->xpcs_window_mask;
+	*offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+}
+
+static int xgbe_read_mmd_regs_v3(struct xgbe_prv_data *pdata, int prtad,
+				 int mmd_reg)
+{
+	unsigned int mmd_address, index, offset;
+	u32 smn_address;
+	int mmd_data;
+	int ret;
+
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
+
+	smn_address = pdata->smn_base + pdata->xpcs_window_sel_reg;
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret)
+		return ret;
+
+	ret = amd_smn_read(0, pdata->smn_base + offset, &mmd_data);
+	if (ret)
+		return ret;
+
+	mmd_data = (offset % 4) ? FIELD_GET(XGBE_GEN_HI_MASK, mmd_data) :
+				  FIELD_GET(XGBE_GEN_LO_MASK, mmd_data);
+
+	return mmd_data;
+}
+
+static void xgbe_write_mmd_regs_v3(struct xgbe_prv_data *pdata, int prtad,
+				   int mmd_reg, int mmd_data)
+{
+	unsigned int pci_mmd_data, hi_mask, lo_mask;
+	unsigned int mmd_address, index, offset;
+	struct pci_dev *dev;
+	u32 smn_address;
+	int ret;
+
+	dev = pdata->pcidev;
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
+
+	smn_address = pdata->smn_base + pdata->xpcs_window_sel_reg;
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", index);
+		return;
+	}
+
+	ret = amd_smn_read(0, pdata->smn_base + offset, &pci_mmd_data);
+	if (ret) {
+		pci_err(dev, "Failed to read data\n");
+		return;
+	}
+
+	if (offset % 4) {
+		hi_mask = FIELD_PREP(XGBE_GEN_HI_MASK, mmd_data);
+		lo_mask = FIELD_GET(XGBE_GEN_LO_MASK, pci_mmd_data);
+	} else {
+		hi_mask = FIELD_PREP(XGBE_GEN_HI_MASK,
+				     FIELD_GET(XGBE_GEN_HI_MASK, pci_mmd_data));
+		lo_mask = FIELD_GET(XGBE_GEN_LO_MASK, mmd_data);
+	}
+
+	pci_mmd_data = hi_mask | lo_mask;
+
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", index);
+		return;
+	}
+
+	ret = amd_smn_write(0, (pdata->smn_base + offset), pci_mmd_data);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", pci_mmd_data);
+		return;
+	}
+}
+
+static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
+				 int mmd_reg)
+{
+	unsigned int mmd_address, index, offset;
+	unsigned long flags;
+	int mmd_data;
+
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
 
 	spin_lock_irqsave(&pdata->xpcs_lock, flags);
 	XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
@@ -1189,23 +1185,9 @@ static void xgbe_write_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
 	unsigned long flags;
 	unsigned int mmd_address, index, offset;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
-	/* The PCS registers are accessed using mmio. The underlying
-	 * management interface uses indirect addressing to access the MMD
-	 * register sets. This requires accessing of the PCS register in two
-	 * phases, an address phase and a data phase.
-	 *
-	 * The mmio interface is based on 16-bit offsets and values. All
-	 * register offsets must therefore be adjusted by left shifting the
-	 * offset 1 bit and writing 16 bits of data.
-	 */
-	mmd_address <<= 1;
-	index = mmd_address & ~pdata->xpcs_window_mask;
-	offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
 
 	spin_lock_irqsave(&pdata->xpcs_lock, flags);
 	XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
@@ -1220,10 +1202,7 @@ static int xgbe_read_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad,
 	unsigned int mmd_address;
 	int mmd_data;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
 	/* The PCS registers are accessed using mmio. The underlying APB3
 	 * management interface uses indirect addressing to access the MMD
@@ -1248,10 +1227,7 @@ static void xgbe_write_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad,
 	unsigned int mmd_address;
 	unsigned long flags;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
 	/* The PCS registers are accessed using mmio. The underlying APB3
 	 * management interface uses indirect addressing to access the MMD
@@ -1278,6 +1254,9 @@ static int xgbe_read_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	case XGBE_XPCS_ACCESS_V2:
 	default:
 		return xgbe_read_mmd_regs_v2(pdata, prtad, mmd_reg);
+
+	case XGBE_XPCS_ACCESS_V3:
+		return xgbe_read_mmd_regs_v3(pdata, prtad, mmd_reg);
 	}
 }
 
@@ -1288,6 +1267,9 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	case XGBE_XPCS_ACCESS_V1:
 		return xgbe_write_mmd_regs_v1(pdata, prtad, mmd_reg, mmd_data);
 
+	case XGBE_XPCS_ACCESS_V3:
+		return xgbe_write_mmd_regs_v3(pdata, prtad, mmd_reg, mmd_data);
+
 	case XGBE_XPCS_ACCESS_V2:
 	default:
 		return xgbe_write_mmd_regs_v2(pdata, prtad, mmd_reg, mmd_data);
@@ -3545,8 +3527,12 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
 	xgbe_config_tx_coalesce(pdata);
 	xgbe_config_rx_buffer_size(pdata);
 	xgbe_config_tso_mode(pdata);
-	xgbe_config_sph_mode(pdata);
-	xgbe_config_rss(pdata);
+
+	if (pdata->netdev->features & NETIF_F_RXCSUM) {
+		xgbe_config_sph_mode(pdata);
+		xgbe_config_rss(pdata);
+	}
+
 	desc_if->wrapper_tx_desc_init(pdata);
 	desc_if->wrapper_rx_desc_init(pdata);
 	xgbe_enable_dma_interrupts(pdata);
@@ -3702,5 +3688,9 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
 	hw_if->disable_vxlan = xgbe_disable_vxlan;
 	hw_if->set_vxlan_id = xgbe_set_vxlan_id;
 
+	/* For Split Header*/
+	hw_if->enable_sph = xgbe_config_sph_mode;
+	hw_if->disable_sph = xgbe_disable_sph_mode;
+
 	DBGPR("<--xgbe_init_function_ptrs\n");
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 5475867708f4..65447f9a0a59 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
@@ -643,7 +534,8 @@ static irqreturn_t xgbe_dma_isr(int irq, void *data)
 
 static void xgbe_tx_timer(struct timer_list *t)
 {
-	struct xgbe_channel *channel = from_timer(channel, t, tx_timer);
+	struct xgbe_channel *channel = timer_container_of(channel, t,
+							  tx_timer);
 	struct xgbe_prv_data *pdata = channel->pdata;
 	struct napi_struct *napi;
 
@@ -681,7 +573,8 @@ static void xgbe_service(struct work_struct *work)
 
 static void xgbe_service_timer(struct timer_list *t)
 {
-	struct xgbe_prv_data *pdata = from_timer(pdata, t, service_timer);
+	struct xgbe_prv_data *pdata = timer_container_of(pdata, t,
+							 service_timer);
 	struct xgbe_channel *channel;
 	unsigned int i;
 
@@ -728,7 +621,7 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata)
 	struct xgbe_channel *channel;
 	unsigned int i;
 
-	del_timer_sync(&pdata->service_timer);
+	timer_delete_sync(&pdata->service_timer);
 
 	for (i = 0; i < pdata->channel_count; i++) {
 		channel = pdata->channel[i];
@@ -736,7 +629,7 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata)
 			break;
 
 		/* Deactivate the Tx timer */
-		del_timer_sync(&channel->tx_timer);
+		timer_delete_sync(&channel->tx_timer);
 		channel->tx_timer_active = 0;
 	}
 }
@@ -2257,10 +2150,17 @@ static int xgbe_set_features(struct net_device *netdev,
 	if (ret)
 		return ret;
 
-	if ((features & NETIF_F_RXCSUM) && !rxcsum)
+	if ((features & NETIF_F_RXCSUM) && !rxcsum) {
+		hw_if->enable_sph(pdata);
+		hw_if->enable_vxlan(pdata);
 		hw_if->enable_rx_csum(pdata);
-	else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+		schedule_work(&pdata->restart_work);
+	} else if (!(features & NETIF_F_RXCSUM) && rxcsum) {
+		hw_if->disable_sph(pdata);
+		hw_if->disable_vxlan(pdata);
 		hw_if->disable_rx_csum(pdata);
+		schedule_work(&pdata->restart_work);
+	}
 
 	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
 		hw_if->enable_rx_vlan_stripping(pdata);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 4431ab1c18b3..be0d2c7d08dc 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/spinlock.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
index 7a833894f52a..d40011e8ddf2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index 0e8698928e4d..4ebdd123c435 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 07f4f3418d01..1a37ec45e650 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/interrupt.h>
@@ -375,6 +266,10 @@ static void xgbe_an37_set(struct xgbe_prv_data *pdata, bool enable,
 		reg |= MDIO_VEND2_CTRL1_AN_RESTART;
 
 	XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_CTRL1, reg);
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL);
+	reg |= XGBE_VEND2_MAC_AUTO_SW;
+	XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL, reg);
 }
 
 static void xgbe_an37_restart(struct xgbe_prv_data *pdata)
@@ -1003,6 +898,11 @@ static void xgbe_an37_init(struct xgbe_prv_data *pdata)
 
 	netif_dbg(pdata, link, pdata->netdev, "CL37 AN (%s) initialized\n",
 		  (pdata->an_mode == XGBE_AN_MODE_CL37) ? "BaseX" : "SGMII");
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1);
+	reg &= ~MDIO_AN_CTRL1_ENABLE;
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_CTRL1, reg);
+
 }
 
 static void xgbe_an73_init(struct xgbe_prv_data *pdata)
@@ -1404,6 +1304,10 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata)
 
 	pdata->phy.link = pdata->phy_if.phy_impl.link_status(pdata,
 							     &an_restart);
+	/* bail out if the link status register read fails */
+	if (pdata->phy.link < 0)
+		return;
+
 	if (an_restart) {
 		xgbe_phy_config_aneg(pdata);
 		goto adjust_link;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index c636999a6a84..097ec5e4f261 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -1,123 +1,15 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/log2.h>
+#include "xgbe-smn.h"
 
 #include "xgbe.h"
 #include "xgbe-common.h"
@@ -207,14 +99,14 @@ out:
 
 static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	struct xgbe_prv_data *pdata;
-	struct device *dev = &pdev->dev;
 	void __iomem * const *iomap_table;
-	struct pci_dev *rdev;
+	unsigned int port_addr_size, reg;
+	struct device *dev = &pdev->dev;
+	struct xgbe_prv_data *pdata;
 	unsigned int ma_lo, ma_hi;
-	unsigned int reg;
-	int bar_mask;
-	int ret;
+	struct pci_dev *rdev;
+	int bar_mask, ret;
+	u32 address;
 
 	pdata = xgbe_alloc_pdata(dev);
 	if (IS_ERR(pdata)) {
@@ -274,20 +166,31 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	/* Set the PCS indirect addressing definition registers */
 	rdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0));
-	if (rdev &&
-	    (rdev->vendor == PCI_VENDOR_ID_AMD) && (rdev->device == 0x15d0)) {
-		pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF;
-		pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT;
-	} else if (rdev && (rdev->vendor == PCI_VENDOR_ID_AMD) &&
-		   (rdev->device == 0x14b5)) {
-		pdata->xpcs_window_def_reg = PCS_V2_YC_WINDOW_DEF;
-		pdata->xpcs_window_sel_reg = PCS_V2_YC_WINDOW_SELECT;
-
-		/* Yellow Carp devices do not need cdr workaround */
-		pdata->vdata->an_cdr_workaround = 0;
-
-		/* Yellow Carp devices do not need rrc */
-		pdata->vdata->enable_rrc = 0;
+	if (rdev && rdev->vendor == PCI_VENDOR_ID_AMD) {
+		switch (rdev->device) {
+		case XGBE_RV_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT;
+			break;
+		case XGBE_YC_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V2_YC_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_YC_WINDOW_SELECT;
+
+			/* Yellow Carp devices do not need cdr workaround */
+			pdata->vdata->an_cdr_workaround = 0;
+
+			/* Yellow Carp devices do not need rrc */
+			pdata->vdata->enable_rrc = 0;
+			break;
+		case XGBE_RN_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V3_RN_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V3_RN_WINDOW_SELECT;
+			break;
+		default:
+			pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
+			break;
+		}
 	} else {
 		pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
 		pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
@@ -295,7 +198,22 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_dev_put(rdev);
 
 	/* Configure the PCS indirect addressing support */
-	reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg);
+	if (pdata->vdata->xpcs_access == XGBE_XPCS_ACCESS_V3) {
+		reg = XP_IOREAD(pdata, XP_PROP_0);
+		port_addr_size = PCS_RN_PORT_ADDR_SIZE *
+				 XP_GET_BITS(reg, XP_PROP_0, PORT_ID);
+		pdata->smn_base = PCS_RN_SMN_BASE_ADDR + port_addr_size;
+
+		address = pdata->smn_base + (pdata->xpcs_window_def_reg);
+		ret = amd_smn_read(0, address, &reg);
+		if (ret) {
+			pci_err(pdata->pcidev, "Failed to read data\n");
+			goto err_pci_enable;
+		}
+	} else {
+		reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg);
+	}
+
 	pdata->xpcs_window = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, OFFSET);
 	pdata->xpcs_window <<= 6;
 	pdata->xpcs_window_size = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, SIZE);
@@ -473,6 +391,22 @@ static int __maybe_unused xgbe_pci_resume(struct device *dev)
 	return ret;
 }
 
+static struct xgbe_version_data xgbe_v3 = {
+	.init_function_ptrs_phy_impl	= xgbe_init_function_ptrs_phy_v2,
+	.xpcs_access			= XGBE_XPCS_ACCESS_V3,
+	.mmc_64bit			= 1,
+	.tx_max_fifo_size		= 65536,
+	.rx_max_fifo_size		= 65536,
+	.tx_tstamp_workaround		= 1,
+	.ecc_support			= 1,
+	.i2c_support			= 1,
+	.irq_reissue_support		= 1,
+	.tx_desc_prefetch		= 5,
+	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 0,
+	.enable_rrc			= 0,
+};
+
 static struct xgbe_version_data xgbe_v2a = {
 	.init_function_ptrs_phy_impl	= xgbe_init_function_ptrs_phy_v2,
 	.xpcs_access			= XGBE_XPCS_ACCESS_V2,
@@ -510,6 +444,8 @@ static const struct pci_device_id xgbe_pci_table[] = {
 	  .driver_data = (kernel_ulong_t)&xgbe_v2a },
 	{ PCI_VDEVICE(AMD, 0x1459),
 	  .driver_data = (kernel_ulong_t)&xgbe_v2b },
+	{ PCI_VDEVICE(AMD, 0x1641),
+	  .driver_data = (kernel_ulong_t)&xgbe_v3 },
 	/* Last entry must be zero */
 	{ 0, }
 };
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c
index d16eae415f72..2e6b8ffe785c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 6a716337f48b..23c39e92e783 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
@@ -923,7 +814,6 @@ static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	unsigned int phy_id = phy_data->phydev->phy_id;
 
@@ -945,14 +835,7 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 	phy_write(phy_data->phydev, 0x04, 0x0d01);
 	phy_write(phy_data->phydev, 0x00, 0x9140);
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       supported);
-	linkmode_set_bit_array(phy_gbit_features_array,
-			       ARRAY_SIZE(phy_gbit_features_array),
-			       supported);
-
-	linkmode_copy(phy_data->phydev->supported, supported);
+	linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES);
 
 	phy_support_asym_pause(phy_data->phydev);
 
@@ -964,7 +847,6 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom;
 	unsigned int phy_id = phy_data->phydev->phy_id;
@@ -1028,13 +910,7 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 	reg = phy_read(phy_data->phydev, 0x00);
 	phy_write(phy_data->phydev, 0x00, reg & ~0x00800);
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       supported);
-	linkmode_set_bit_array(phy_gbit_features_array,
-			       ARRAY_SIZE(phy_gbit_features_array),
-			       supported);
-	linkmode_copy(phy_data->phydev->supported, supported);
+	linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES);
 	phy_support_asym_pause(phy_data->phydev);
 
 	netif_dbg(pdata, drv, pdata->netdev,
@@ -2870,8 +2746,7 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed)
 static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int reg;
-	int ret;
+	int reg, ret;
 
 	*an_restart = 0;
 
@@ -2905,11 +2780,20 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			return 0;
 	}
 
-	/* Link status is latched low, so read once to clear
-	 * and then read again to get current state
-	 */
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
 	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (reg < 0)
+		return reg;
+
+	/* Link status is latched low so that momentary link drops
+	 * can be detected. If link was already down read again
+	 * to get the latest state.
+	 */
+
+	if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) {
+		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+		if (reg < 0)
+			return reg;
+	}
 
 	if (pdata->en_rx_adap) {
 		/* if the link is available and adaptation is done,
@@ -2928,9 +2812,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			xgbe_phy_set_mode(pdata, phy_data->cur_mode);
 		}
 
-		/* check again for the link and adaptation status */
-		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
-		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done)
+		if (pdata->rx_adapt_done)
 			return 1;
 	} else if (reg & MDIO_STAT1_LSTATUS)
 		return 1;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
index 4365bd62942c..47d53e59ccf6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
index 7051bd7cf6dc..978c4dd01fa0 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #include <linux/clk.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-smn.h b/drivers/net/ethernet/amd/xgbe/xgbe-smn.h
new file mode 100644
index 000000000000..c6ae127ced03
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-smn.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause) */
+/*
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
+ *
+ * Author: Raju Rangoju <Raju.Rangoju@amd.com>
+ */
+
+#ifndef __SMN_H__
+#define __SMN_H__
+
+#ifdef CONFIG_AMD_NB
+
+#include <asm/amd/nb.h>
+
+#else
+
+static inline int amd_smn_write(u16 node, u32 address, u32 value)
+{
+	return -ENODEV;
+}
+
+static inline int amd_smn_read(u16 node, u32 address, u32 *value)
+{
+	return -ENODEV;
+}
+
+#endif
+#endif
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index d85386cac8d1..057379cd43ba 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -1,117 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
 /*
- * AMD 10Gb Ethernet driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * This file incorporates work covered by the following copyright and
- * permission notice:
- *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
- *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
- *     Inc. unless otherwise expressly agreed to in writing between Synopsys
- *     and you.
- *
- *     The Software IS NOT an item of Licensed Software or Licensed Product
- *     under any End User Software License Agreement or Agreement for Licensed
- *     Product with Synopsys or any supplement thereto.  Permission is hereby
- *     granted, free of charge, to any person obtaining a copy of this software
- *     annotated with this license and the Software, to deal in the Software
- *     without restriction, including without limitation the rights to use,
- *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
- *     of the Software, and to permit persons to whom the Software is furnished
- *     to do so, subject to the following conditions:
- *
- *     The above copyright notice and this permission notice shall be included
- *     in all copies or substantial portions of the Software.
- *
- *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
- *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
- *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
- *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
- *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
- *     THE POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
  */
 
 #ifndef __XGBE_H__
@@ -292,12 +183,12 @@
 #define XGBE_LINK_TIMEOUT		5
 #define XGBE_KR_TRAINING_WAIT_ITER	50
 
-#define XGBE_SGMII_AN_LINK_STATUS	BIT(1)
+#define XGBE_SGMII_AN_LINK_DUPLEX	BIT(1)
 #define XGBE_SGMII_AN_LINK_SPEED	(BIT(2) | BIT(3))
 #define XGBE_SGMII_AN_LINK_SPEED_10	0x00
 #define XGBE_SGMII_AN_LINK_SPEED_100	0x04
 #define XGBE_SGMII_AN_LINK_SPEED_1000	0x08
-#define XGBE_SGMII_AN_LINK_DUPLEX	BIT(4)
+#define XGBE_SGMII_AN_LINK_STATUS	BIT(4)
 
 /* ECC correctable error notification window (seconds) */
 #define XGBE_ECC_LIMIT			60
@@ -347,6 +238,15 @@
 		    (_src)->link_modes._sname,		\
 		    __ETHTOOL_LINK_MODE_MASK_NBITS)
 
+/* XGBE PCI device id */
+#define XGBE_RV_PCI_DEVICE_ID	0x15d0
+#define XGBE_YC_PCI_DEVICE_ID	0x14b5
+#define XGBE_RN_PCI_DEVICE_ID	0x1630
+
+ /* Generic low and high masks */
+#define XGBE_GEN_HI_MASK	GENMASK(31, 16)
+#define XGBE_GEN_LO_MASK	GENMASK(15, 0)
+
 struct xgbe_prv_data;
 
 struct xgbe_packet_data {
@@ -565,6 +465,7 @@ enum xgbe_speed {
 enum xgbe_xpcs_access {
 	XGBE_XPCS_ACCESS_V1 = 0,
 	XGBE_XPCS_ACCESS_V2,
+	XGBE_XPCS_ACCESS_V3,
 };
 
 enum xgbe_an_mode {
@@ -865,6 +766,10 @@ struct xgbe_hw_if {
 	void (*enable_vxlan)(struct xgbe_prv_data *);
 	void (*disable_vxlan)(struct xgbe_prv_data *);
 	void (*set_vxlan_id)(struct xgbe_prv_data *);
+
+	/* For Split Header */
+	void (*enable_sph)(struct xgbe_prv_data *pdata);
+	void (*disable_sph)(struct xgbe_prv_data *pdata);
 };
 
 /* This structure represents implementation specific routines for an
@@ -1056,6 +961,7 @@ struct xgbe_prv_data {
 	struct device *dev;
 	struct platform_device *phy_platdev;
 	struct device *phy_dev;
+	unsigned int smn_base;
 
 	/* Version related data */
 	struct xgbe_version_data *vdata;
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
index 2a91c84aebdb..d7ca847d44c7 100644
--- a/drivers/net/ethernet/apm/xgene-v2/main.c
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -9,8 +9,6 @@
 
 #include "main.h"
 
-static const struct acpi_device_id xge_acpi_match[];
-
 static int xge_get_resources(struct xge_pdata *pdata)
 {
 	struct platform_device *pdev;
@@ -731,7 +729,7 @@ MODULE_DEVICE_TABLE(acpi, xge_acpi_match);
 static struct platform_driver xge_driver = {
 	.driver = {
 		   .name = "xgene-enet-v2",
-		   .acpi_match_table = ACPI_PTR(xge_acpi_match),
+		   .acpi_match_table = xge_acpi_match,
 	},
 	.probe = xge_probe,
 	.remove = xge_remove,
diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
index eba06831aec2..6a17045a5f62 100644
--- a/drivers/net/ethernet/apm/xgene-v2/mdio.c
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -97,7 +97,6 @@ void xge_mdio_remove(struct net_device *ndev)
 
 int xge_mdio_config(struct net_device *ndev)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct xge_pdata *pdata = netdev_priv(ndev);
 	struct device *dev = &pdata->pdev->dev;
 	struct mii_bus *mdio_bus;
@@ -137,17 +136,12 @@ int xge_mdio_config(struct net_device *ndev)
 		goto err;
 	}
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_AUI_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_BNC_BIT, mask);
-
-	linkmode_andnot(phydev->supported, phydev->supported, mask);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Full_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+
 	pdata->phy_speed = SPEED_UNKNOWN;
 
 	return 0;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index e641dbbea1e2..b854b6b42d77 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -421,18 +421,12 @@ static void xgene_enet_configure_clock(struct xgene_enet_pdata *pdata)
 
 	if (dev->of_node) {
 		struct clk *parent = clk_get_parent(pdata->clk);
+		long rate = rgmii_clock(pdata->phy_speed);
 
-		switch (pdata->phy_speed) {
-		case SPEED_10:
-			clk_set_rate(parent, 2500000);
-			break;
-		case SPEED_100:
-			clk_set_rate(parent, 25000000);
-			break;
-		default:
-			clk_set_rate(parent, 125000000);
-			break;
-		}
+		if (rate < 0)
+			rate = 125000000;
+
+		clk_set_rate(parent, rate);
 	}
 #ifdef CONFIG_ACPI
 	else {
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
index 86607b79c09f..cc3b1631c905 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
@@ -6,8 +6,14 @@
  *	    Keyur Chudgar <kchudgar@apm.com>
  */
 
-#include <linux/of_gpio.h>
-#include <linux/gpio.h>
+#include <linux/acpi.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/io.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
 #include "xgene_enet_main.h"
 #include "xgene_enet_hw.h"
 #include "xgene_enet_xgmac.h"
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 785f4b4ff758..b3bf8d6f88e8 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -20,7 +20,6 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/crc32.h>
-#include <linux/crc32poly.h>
 #include <linux/bitrev.h>
 #include <linux/ethtool.h>
 #include <linux/slab.h>
@@ -461,7 +460,7 @@ static int bmac_suspend(struct macio_dev *mdev, pm_message_t state)
 	/* prolly should wait for dma to finish & turn off the chip */
 	spin_lock_irqsave(&bp->lock, flags);
 	if (bp->timeout_active) {
-		del_timer(&bp->tx_timeout);
+		timer_delete(&bp->tx_timeout);
 		bp->timeout_active = 0;
 	}
 	disable_irq(dev->irq);
@@ -546,7 +545,7 @@ static inline void bmac_set_timeout(struct net_device *dev)
 
 	spin_lock_irqsave(&bp->lock, flags);
 	if (bp->timeout_active)
-		del_timer(&bp->tx_timeout);
+		timer_delete(&bp->tx_timeout);
 	bp->tx_timeout.expires = jiffies + TX_TIMEOUT;
 	add_timer(&bp->tx_timeout);
 	bp->timeout_active = 1;
@@ -755,7 +754,7 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id)
 		XXDEBUG(("bmac_txdma_intr\n"));
 	}
 
-	/*     del_timer(&bp->tx_timeout); */
+	/*     timer_delete(&bp->tx_timeout); */
 	/*     bp->timeout_active = 0; */
 
 	while (1) {
@@ -796,59 +795,6 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id)
 }
 
 #ifndef SUNHME_MULTICAST
-/* Real fast bit-reversal algorithm, 6-bit values */
-static int reverse6[64] = {
-	0x0,0x20,0x10,0x30,0x8,0x28,0x18,0x38,
-	0x4,0x24,0x14,0x34,0xc,0x2c,0x1c,0x3c,
-	0x2,0x22,0x12,0x32,0xa,0x2a,0x1a,0x3a,
-	0x6,0x26,0x16,0x36,0xe,0x2e,0x1e,0x3e,
-	0x1,0x21,0x11,0x31,0x9,0x29,0x19,0x39,
-	0x5,0x25,0x15,0x35,0xd,0x2d,0x1d,0x3d,
-	0x3,0x23,0x13,0x33,0xb,0x2b,0x1b,0x3b,
-	0x7,0x27,0x17,0x37,0xf,0x2f,0x1f,0x3f
-};
-
-static unsigned int
-crc416(unsigned int curval, unsigned short nxtval)
-{
-	unsigned int counter, cur = curval, next = nxtval;
-	int high_crc_set, low_data_set;
-
-	/* Swap bytes */
-	next = ((next & 0x00FF) << 8) | (next >> 8);
-
-	/* Compute bit-by-bit */
-	for (counter = 0; counter < 16; ++counter) {
-		/* is high CRC bit set? */
-		if ((cur & 0x80000000) == 0) high_crc_set = 0;
-		else high_crc_set = 1;
-
-		cur = cur << 1;
-
-		if ((next & 0x0001) == 0) low_data_set = 0;
-		else low_data_set = 1;
-
-		next = next >> 1;
-
-		/* do the XOR */
-		if (high_crc_set ^ low_data_set) cur = cur ^ CRC32_POLY_BE;
-	}
-	return cur;
-}
-
-static unsigned int
-bmac_crc(unsigned short *address)
-{
-	unsigned int newcrc;
-
-	XXDEBUG(("bmac_crc: addr=%#04x, %#04x, %#04x\n", *address, address[1], address[2]));
-	newcrc = crc416(0xffffffff, *address);	/* address bits 47 - 32 */
-	newcrc = crc416(newcrc, address[1]);	/* address bits 31 - 16 */
-	newcrc = crc416(newcrc, address[2]);	/* address bits 15 - 0  */
-
-	return(newcrc);
-}
-
 /*
  * Add requested mcast addr to BMac's hash table filter.
  *
@@ -861,8 +807,7 @@ bmac_addhash(struct bmac_data *bp, unsigned char *addr)
 	unsigned short	 mask;
 
 	if (!(*addr)) return;
-	crc = bmac_crc((unsigned short *)addr) & 0x3f; /* Big-endian alert! */
-	crc = reverse6[crc];	/* Hyperfast bit-reversing algorithm */
+	crc = crc32(~0, addr, ETH_ALEN) >> 26;
 	if (bp->hash_use_count[crc]++) return; /* This bit is already set */
 	mask = crc % 16;
 	mask = (unsigned char)1 << mask;
@@ -876,8 +821,7 @@ bmac_removehash(struct bmac_data *bp, unsigned char *addr)
 	unsigned char mask;
 
 	/* Now, delete the address from the filter copy, as indicated */
-	crc = bmac_crc((unsigned short *)addr) & 0x3f; /* Big-endian alert! */
-	crc = reverse6[crc];	/* Hyperfast bit-reversing algorithm */
+	crc = crc32(~0, addr, ETH_ALEN) >> 26;
 	if (bp->hash_use_count[crc] == 0) return; /* That bit wasn't in use! */
 	if (--bp->hash_use_count[crc]) return; /* That bit is still in use */
 	mask = crc % 16;
@@ -1466,7 +1410,7 @@ bmac_output(struct sk_buff *skb, struct net_device *dev)
 
 static void bmac_tx_timeout(struct timer_list *t)
 {
-	struct bmac_data *bp = from_timer(bp, t, tx_timeout);
+	struct bmac_data *bp = timer_container_of(bp, t, tx_timeout);
 	struct net_device *dev = macio_get_drvdata(bp->mdev);
 	volatile struct dbdma_regs __iomem *td = bp->tx_dma;
 	volatile struct dbdma_regs __iomem *rd = bp->rx_dma;
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index e6350971c707..af26905e44e3 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -523,7 +523,7 @@ static inline void mace_set_timeout(struct net_device *dev)
     struct mace_data *mp = netdev_priv(dev);
 
     if (mp->timeout_active)
-	del_timer(&mp->tx_timeout);
+	timer_delete(&mp->tx_timeout);
     mp->tx_timeout.expires = jiffies + TX_TIMEOUT;
     add_timer(&mp->tx_timeout);
     mp->timeout_active = 1;
@@ -676,7 +676,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
 
     i = mp->tx_empty;
     while (in_8(&mb->pr) & XMTSV) {
-	del_timer(&mp->tx_timeout);
+	timer_delete(&mp->tx_timeout);
 	mp->timeout_active = 0;
 	/*
 	 * Clear any interrupt indication associated with this status
@@ -805,7 +805,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
 
 static void mace_tx_timeout(struct timer_list *t)
 {
-    struct mace_data *mp = from_timer(mp, t, tx_timeout);
+    struct mace_data *mp = timer_container_of(mp, t, tx_timeout);
     struct net_device *dev = macio_get_drvdata(mp->mdev);
     volatile struct mace __iomem *mb = mp->mace;
     volatile struct dbdma_regs __iomem *td = mp->tx_dma;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
index 414b2e448d59..787ea91802e7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
@@ -113,19 +113,9 @@ static const struct hwmon_ops aq_hwmon_ops = {
 	.read_string = aq_hwmon_read_string,
 };
 
-static u32 aq_hwmon_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	0,
-};
-
-static const struct hwmon_channel_info aq_hwmon_temp = {
-	.type = hwmon_temp,
-	.config = aq_hwmon_temp_config,
-};
-
 static const struct hwmon_channel_info * const aq_hwmon_info[] = {
-	&aq_hwmon_temp,
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_LABEL),
 	NULL,
 };
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index c1d1673c5749..b565189e5913 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -123,7 +123,6 @@ static netdev_tx_t aq_ndev_start_xmit(struct sk_buff *skb, struct net_device *nd
 	}
 #endif
 
-	skb_tx_timestamp(skb);
 	return aq_nic_xmit(aq_nic, skb);
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index fe0e3e2a8117..b24eaa5283fa 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -254,7 +254,7 @@ static void aq_nic_service_task(struct work_struct *work)
 
 static void aq_nic_service_timer_cb(struct timer_list *t)
 {
-	struct aq_nic_s *self = from_timer(self, t, service_timer);
+	struct aq_nic_s *self = timer_container_of(self, t, service_timer);
 
 	mod_timer(&self->service_timer,
 		  jiffies + AQ_CFG_SERVICE_TIMER_INTERVAL);
@@ -264,7 +264,7 @@ static void aq_nic_service_timer_cb(struct timer_list *t)
 
 static void aq_nic_polling_timer_cb(struct timer_list *t)
 {
-	struct aq_nic_s *self = from_timer(self, t, polling_timer);
+	struct aq_nic_s *self = timer_container_of(self, t, polling_timer);
 	unsigned int i = 0U;
 
 	for (i = 0U; self->aq_vecs > i; ++i)
@@ -898,6 +898,8 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 
 	frags = aq_nic_map_skb(self, skb, ring);
 
+	skb_tx_timestamp(skb);
+
 	if (likely(frags)) {
 		err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw,
 						       ring, frags);
@@ -1389,13 +1391,13 @@ int aq_nic_stop(struct aq_nic_s *self)
 	netif_tx_disable(self->ndev);
 	netif_carrier_off(self->ndev);
 
-	del_timer_sync(&self->service_timer);
+	timer_delete_sync(&self->service_timer);
 	cancel_work_sync(&self->service_task);
 
 	self->aq_hw_ops->hw_irq_disable(self->aq_hw, AQ_CFG_IRQ_MASK);
 
 	if (self->aq_nic_cfg.is_polling)
-		del_timer_sync(&self->polling_timer);
+		timer_delete_sync(&self->polling_timer);
 	else
 		aq_pci_func_free_irqs(self);
 
@@ -1441,7 +1443,9 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down)
 	aq_ptp_ring_free(self);
 	aq_ptp_free(self);
 
-	if (likely(self->aq_fw_ops->deinit) && link_down) {
+	/* May be invoked during hot unplug. */
+	if (pci_device_is_present(self->pdev) &&
+	    likely(self->aq_fw_ops->deinit) && link_down) {
 		mutex_lock(&self->fwreq_mutex);
 		self->aq_fw_ops->deinit(self->aq_hw);
 		mutex_unlock(&self->fwreq_mutex);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index f5901f8e3907..f6b990b7f5b4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -226,7 +226,6 @@ struct __packed offload_info {
 	struct offload_port_info ports;
 	struct offload_ka_info kas;
 	struct offload_rr_info rrs;
-	u8 buf[];
 };
 
 struct __packed hw_atl_utils_fw_rpc {
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 3d4c3d8698e2..d8e6f23e1432 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1391,7 +1391,7 @@ static void ag71xx_hw_disable(struct ag71xx *ag)
 	ag71xx_dma_reset(ag);
 
 	napi_disable(&ag->napi);
-	del_timer_sync(&ag->oom_timer);
+	timer_delete_sync(&ag->oom_timer);
 
 	ag71xx_rings_cleanup(ag);
 }
@@ -1563,7 +1563,7 @@ err_drop:
 
 static void ag71xx_oom_timer_handler(struct timer_list *t)
 {
-	struct ag71xx *ag = from_timer(ag, t, oom_timer);
+	struct ag71xx *ag = timer_container_of(ag, t, oom_timer);
 
 	napi_schedule(&ag->napi);
 }
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index c571614b1d50..ef1a51347351 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -231,8 +231,8 @@ static u32 atl1c_wait_until_idle(struct atl1c_hw *hw, u32 modu_ctrl)
  */
 static void atl1c_phy_config(struct timer_list *t)
 {
-	struct atl1c_adapter *adapter = from_timer(adapter, t,
-						   phy_config_timer);
+	struct atl1c_adapter *adapter = timer_container_of(adapter, t,
+							   phy_config_timer);
 	struct atl1c_hw *hw = &adapter->hw;
 	unsigned long flags;
 
@@ -357,7 +357,7 @@ static void atl1c_common_task(struct work_struct *work)
 
 static void atl1c_del_timer(struct atl1c_adapter *adapter)
 {
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 }
 
 
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 9b778b34b67e..40290028580b 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -115,8 +115,8 @@ static inline void atl1e_irq_reset(struct atl1e_adapter *adapter)
  */
 static void atl1e_phy_config(struct timer_list *t)
 {
-	struct atl1e_adapter *adapter = from_timer(adapter, t,
-						   phy_config_timer);
+	struct atl1e_adapter *adapter = timer_container_of(adapter, t,
+							   phy_config_timer);
 	struct atl1e_hw *hw = &adapter->hw;
 	unsigned long flags;
 
@@ -232,7 +232,7 @@ static void atl1e_link_chg_event(struct atl1e_adapter *adapter)
 
 static void atl1e_del_timer(struct atl1e_adapter *adapter)
 {
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 }
 
 static void atl1e_cancel_work(struct atl1e_adapter *adapter)
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 3afd3627ce48..98a4d089270e 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1861,14 +1861,21 @@ static u16 atl1_alloc_rx_buffers(struct atl1_adapter *adapter)
 			break;
 		}
 
-		buffer_info->alloced = 1;
-		buffer_info->skb = skb;
-		buffer_info->length = (u16) adapter->rx_buffer_len;
 		page = virt_to_page(skb->data);
 		offset = offset_in_page(skb->data);
 		buffer_info->dma = dma_map_page(&pdev->dev, page, offset,
 						adapter->rx_buffer_len,
 						DMA_FROM_DEVICE);
+		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
+			kfree_skb(skb);
+			adapter->soft_stats.rx_dropped++;
+			break;
+		}
+
+		buffer_info->alloced = 1;
+		buffer_info->skb = skb;
+		buffer_info->length = (u16)adapter->rx_buffer_len;
+
 		rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
 		rfd_desc->buf_len = cpu_to_le16(adapter->rx_buffer_len);
 		rfd_desc->coalese = 0;
@@ -2183,8 +2190,8 @@ static int atl1_tx_csum(struct atl1_adapter *adapter, struct sk_buff *skb,
 	return 0;
 }
 
-static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
-	struct tx_packet_desc *ptpd)
+static bool atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
+			struct tx_packet_desc *ptpd)
 {
 	struct atl1_tpd_ring *tpd_ring = &adapter->tpd_ring;
 	struct atl1_buffer *buffer_info;
@@ -2194,6 +2201,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 	unsigned int nr_frags;
 	unsigned int f;
 	int retval;
+	u16 first_mapped;
 	u16 next_to_use;
 	u16 data_len;
 	u8 hdr_len;
@@ -2201,6 +2209,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 	buf_len -= skb->data_len;
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	next_to_use = atomic_read(&tpd_ring->next_to_use);
+	first_mapped = next_to_use;
 	buffer_info = &tpd_ring->buffer_info[next_to_use];
 	BUG_ON(buffer_info->skb);
 	/* put skb in last TPD */
@@ -2216,6 +2225,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		buffer_info->dma = dma_map_page(&adapter->pdev->dev, page,
 						offset, hdr_len,
 						DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto dma_err;
 
 		if (++next_to_use == tpd_ring->count)
 			next_to_use = 0;
@@ -2242,6 +2253,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 								page, offset,
 								buffer_info->length,
 								DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      buffer_info->dma))
+					goto dma_err;
 				if (++next_to_use == tpd_ring->count)
 					next_to_use = 0;
 			}
@@ -2254,6 +2268,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		buffer_info->dma = dma_map_page(&adapter->pdev->dev, page,
 						offset, buf_len,
 						DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto dma_err;
 		if (++next_to_use == tpd_ring->count)
 			next_to_use = 0;
 	}
@@ -2277,6 +2293,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 			buffer_info->dma = skb_frag_dma_map(&adapter->pdev->dev,
 				frag, i * ATL1_MAX_TX_BUF_LEN,
 				buffer_info->length, DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev,
+					      buffer_info->dma))
+				goto dma_err;
 
 			if (++next_to_use == tpd_ring->count)
 				next_to_use = 0;
@@ -2285,6 +2304,22 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 
 	/* last tpd's buffer-info */
 	buffer_info->skb = skb;
+
+	return true;
+
+ dma_err:
+	while (first_mapped != next_to_use) {
+		buffer_info = &tpd_ring->buffer_info[first_mapped];
+		dma_unmap_page(&adapter->pdev->dev,
+			       buffer_info->dma,
+			       buffer_info->length,
+			       DMA_TO_DEVICE);
+		buffer_info->dma = 0;
+
+		if (++first_mapped == tpd_ring->count)
+			first_mapped = 0;
+	}
+	return false;
 }
 
 static void atl1_tx_queue(struct atl1_adapter *adapter, u16 count,
@@ -2355,10 +2390,8 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 
 	len = skb_headlen(skb);
 
-	if (unlikely(skb->len <= 0)) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	if (unlikely(skb->len <= 0))
+		goto drop_packet;
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
@@ -2371,10 +2404,9 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	if (mss) {
 		if (skb->protocol == htons(ETH_P_IP)) {
 			proto_hdr_len = skb_tcp_all_headers(skb);
-			if (unlikely(proto_hdr_len > len)) {
-				dev_kfree_skb_any(skb);
-				return NETDEV_TX_OK;
-			}
+			if (unlikely(proto_hdr_len > len))
+				goto drop_packet;
+
 			/* need additional TPD ? */
 			if (proto_hdr_len != len)
 				count += (len - proto_hdr_len +
@@ -2406,23 +2438,26 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	}
 
 	tso = atl1_tso(adapter, skb, ptpd);
-	if (tso < 0) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	if (tso < 0)
+		goto drop_packet;
 
 	if (!tso) {
 		ret_val = atl1_tx_csum(adapter, skb, ptpd);
-		if (ret_val < 0) {
-			dev_kfree_skb_any(skb);
-			return NETDEV_TX_OK;
-		}
+		if (ret_val < 0)
+			goto drop_packet;
 	}
 
-	atl1_tx_map(adapter, skb, ptpd);
+	if (!atl1_tx_map(adapter, skb, ptpd))
+		goto drop_packet;
+
 	atl1_tx_queue(adapter, count, ptpd);
 	atl1_update_mailbox(adapter);
 	return NETDEV_TX_OK;
+
+drop_packet:
+	adapter->soft_stats.tx_errors++;
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
 }
 
 static int atl1_rings_clean(struct napi_struct *napi, int budget)
@@ -2556,8 +2591,8 @@ static irqreturn_t atl1_intr(int irq, void *data)
  */
 static void atl1_phy_config(struct timer_list *t)
 {
-	struct atl1_adapter *adapter = from_timer(adapter, t,
-						  phy_config_timer);
+	struct atl1_adapter *adapter = timer_container_of(adapter, t,
+							  phy_config_timer);
 	struct atl1_hw *hw = &adapter->hw;
 	unsigned long flags;
 
@@ -2641,7 +2676,7 @@ static void atl1_down(struct atl1_adapter *adapter)
 
 	napi_disable(&adapter->napi);
 	netif_stop_queue(netdev);
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 	adapter->phy_timer_pending = false;
 
 	atlx_irq_disable(adapter);
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index fa9a4919f25d..280e2f5f4aa5 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -752,8 +752,8 @@ static void atl2_down(struct atl2_adapter *adapter)
 
 	atl2_irq_disable(adapter);
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 	clear_bit(0, &adapter->cfg_phy);
 
 	netif_carrier_off(netdev);
@@ -1010,7 +1010,8 @@ static void atl2_tx_timeout(struct net_device *netdev, unsigned int txqueue)
  */
 static void atl2_watchdog(struct timer_list *t)
 {
-	struct atl2_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct atl2_adapter *adapter = timer_container_of(adapter, t,
+							  watchdog_timer);
 
 	if (!test_bit(__ATL2_DOWN, &adapter->flags)) {
 		u32 drop_rxd, drop_rxs;
@@ -1035,8 +1036,8 @@ static void atl2_watchdog(struct timer_list *t)
  */
 static void atl2_phy_config(struct timer_list *t)
 {
-	struct atl2_adapter *adapter = from_timer(adapter, t,
-						  phy_config_timer);
+	struct atl2_adapter *adapter = timer_container_of(adapter, t,
+							  phy_config_timer);
 	struct atl2_hw *hw = &adapter->hw;
 	unsigned long flags;
 
@@ -1468,8 +1469,8 @@ static void atl2_remove(struct pci_dev *pdev)
 	 * explicitly disable watchdog tasks from being rescheduled  */
 	set_bit(__ATL2_DOWN, &adapter->flags);
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_config_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_config_timer);
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->link_chg_task);
 
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index eeec8bf17cf4..81a74e07464f 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -96,7 +96,6 @@ config BNX2
 config CNIC
 	tristate "QLogic CNIC support"
 	depends on PCI && (IPV6 || IPV6=n)
-	depends on MMU
 	select BNX2
 	select UIO
 	help
@@ -123,6 +122,7 @@ config TIGON3
 	tristate "Broadcom Tigon3 support"
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	select CRC32
 	select PHYLIB
 	help
 	  This driver supports Broadcom Tigon3 based gigabit Ethernet cards.
@@ -143,7 +143,7 @@ config BNX2X
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select FW_LOADER
 	select ZLIB_INFLATE
-	select LIBCRC32C
+	select CRC32
 	select MDIO
 	help
 	  This driver supports Broadcom NetXtremeII 10 gigabit Ethernet cards.
@@ -207,7 +207,7 @@ config BNXT
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select FW_LOADER
-	select LIBCRC32C
+	select CRC32
 	select NET_DEVLINK
 	select PAGE_POOL
 	select DIMLIB
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index a68fab1b05f0..fd35f4b4dc50 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -141,7 +141,7 @@ void bcmasp_flush_rx_port(struct bcmasp_intf *intf)
 		return;
 	}
 
-	rx_ctrl_core_wl(priv, mask, priv->hw_info->rx_ctrl_flush);
+	rx_ctrl_core_wl(priv, mask, ASP_RX_CTRL_FLUSH);
 }
 
 static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv,
@@ -518,7 +518,7 @@ void bcmasp_netfilt_suspend(struct bcmasp_intf *intf)
 	int ret, i;
 
 	/* Write all filters to HW */
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		/* If the filter does not match the port, skip programming. */
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
@@ -551,7 +551,7 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 	struct bcmasp_priv *priv = intf->parent;
 	int j = 0, i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -577,7 +577,7 @@ int bcmasp_netfilt_get_active(struct bcmasp_intf *intf)
 	struct bcmasp_priv *priv = intf->parent;
 	int cnt = 0, i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -602,7 +602,7 @@ bool bcmasp_netfilt_check_dup(struct bcmasp_intf *intf,
 	size_t fs_size = 0;
 	int i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -670,7 +670,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
 	int i, open_index = -1;
 
 	/* Check whether we exceed the filter table capacity */
-	if (loc != RX_CLS_LOC_ANY && loc >= NUM_NET_FILTERS)
+	if (loc != RX_CLS_LOC_ANY && loc >= priv->num_net_filters)
 		return ERR_PTR(-EINVAL);
 
 	/* If the filter location is busy (already claimed) and we are initializing
@@ -686,7 +686,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
 	/* Initialize the loop index based on the desired location or from 0 */
 	i = loc == RX_CLS_LOC_ANY ? 0 : loc;
 
-	for ( ; i < NUM_NET_FILTERS; i++) {
+	for ( ; i < priv->num_net_filters; i++) {
 		/* Found matching network filter */
 		if (!init &&
 		    priv->net_filters[i].claimed &&
@@ -779,7 +779,7 @@ static void bcmasp_en_mda_filter(struct bcmasp_intf *intf, bool en,
 	priv->mda_filters[i].en = en;
 	priv->mda_filters[i].port = intf->port;
 
-	rx_filter_core_wl(priv, ((intf->channel + 8) |
+	rx_filter_core_wl(priv, ((intf->channel + priv->tx_chan_offset) |
 			  (en << ASP_RX_FILTER_MDA_CFG_EN_SHIFT) |
 			  ASP_RX_FILTER_MDA_CFG_UMC_SEL(intf->port)),
 			  ASP_RX_FILTER_MDA_CFG(i));
@@ -865,7 +865,7 @@ void bcmasp_disable_all_filters(struct bcmasp_intf *intf)
 	res_count = bcmasp_total_res_mda_cnt(intf->parent);
 
 	/* Disable all filters held by this port */
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		if (priv->mda_filters[i].en &&
 		    priv->mda_filters[i].port == intf->port)
 			bcmasp_en_mda_filter(intf, 0, i);
@@ -909,7 +909,7 @@ int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
 
 	res_count = bcmasp_total_res_mda_cnt(intf->parent);
 
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		/* If filter not enabled or belongs to another port skip */
 		if (!priv->mda_filters[i].en ||
 		    priv->mda_filters[i].port != intf->port)
@@ -924,7 +924,7 @@ int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
 	}
 
 	/* Create new filter if possible */
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		if (priv->mda_filters[i].en)
 			continue;
 
@@ -944,12 +944,12 @@ static void bcmasp_core_init_filters(struct bcmasp_priv *priv)
 	/* Disable all filters and reset software view since the HW
 	 * can lose context while in deep sleep suspend states
 	 */
-	for (i = 0; i < NUM_MDA_FILTERS; i++) {
+	for (i = 0; i < priv->num_mda_filters; i++) {
 		rx_filter_core_wl(priv, 0x0, ASP_RX_FILTER_MDA_CFG(i));
 		priv->mda_filters[i].en = 0;
 	}
 
-	for (i = 0; i < NUM_NET_FILTERS; i++)
+	for (i = 0; i < priv->num_net_filters; i++)
 		rx_filter_core_wl(priv, 0x0, ASP_RX_FILTER_NET_CFG(i));
 
 	/* Top level filter enable bit should be enabled at all times, set
@@ -966,18 +966,8 @@ static void bcmasp_core_init_filters(struct bcmasp_priv *priv)
 /* ASP core initialization */
 static void bcmasp_core_init(struct bcmasp_priv *priv)
 {
-	tx_analytics_core_wl(priv, 0x0, ASP_TX_ANALYTICS_CTRL);
-	rx_analytics_core_wl(priv, 0x4, ASP_RX_ANALYTICS_CTRL);
-
-	rx_edpkt_core_wl(priv, (ASP_EDPKT_HDR_SZ_128 << ASP_EDPKT_HDR_SZ_SHIFT),
-			 ASP_EDPKT_HDR_CFG);
-	rx_edpkt_core_wl(priv,
-			 (ASP_EDPKT_ENDI_BT_SWP_WD << ASP_EDPKT_ENDI_DESC_SHIFT),
-			 ASP_EDPKT_ENDI);
-
 	rx_edpkt_core_wl(priv, 0x1b, ASP_EDPKT_BURST_BUF_PSCAL_TOUT);
 	rx_edpkt_core_wl(priv, 0x3e8, ASP_EDPKT_BURST_BUF_WRITE_TOUT);
-	rx_edpkt_core_wl(priv, 0x3e8, ASP_EDPKT_BURST_BUF_READ_TOUT);
 
 	rx_edpkt_core_wl(priv, ASP_EDPKT_ENABLE_EN, ASP_EDPKT_ENABLE);
 
@@ -1020,6 +1010,18 @@ static void bcmasp_core_clock_select_one(struct bcmasp_priv *priv, bool slow)
 	ctrl_core_wl(priv, reg, ASP_CTRL_CORE_CLOCK_SELECT);
 }
 
+static void bcmasp_core_clock_select_one_ctrl2(struct bcmasp_priv *priv, bool slow)
+{
+	u32 reg;
+
+	reg = ctrl2_core_rl(priv, ASP_CTRL2_CORE_CLOCK_SELECT);
+	if (slow)
+		reg &= ~ASP_CTRL2_CORE_CLOCK_SELECT_MAIN;
+	else
+		reg |= ASP_CTRL2_CORE_CLOCK_SELECT_MAIN;
+	ctrl2_core_wl(priv, reg, ASP_CTRL2_CORE_CLOCK_SELECT);
+}
+
 static void bcmasp_core_clock_set_ll(struct bcmasp_priv *priv, u32 clr, u32 set)
 {
 	u32 reg;
@@ -1108,7 +1110,7 @@ static int bcmasp_get_and_request_irq(struct bcmasp_priv *priv, int i)
 	return irq;
 }
 
-static void bcmasp_init_wol_shared(struct bcmasp_priv *priv)
+static void bcmasp_init_wol(struct bcmasp_priv *priv)
 {
 	struct platform_device *pdev = priv->pdev;
 	struct device *dev = &pdev->dev;
@@ -1125,7 +1127,7 @@ static void bcmasp_init_wol_shared(struct bcmasp_priv *priv)
 	device_set_wakeup_capable(&pdev->dev, 1);
 }
 
-static void bcmasp_enable_wol_shared(struct bcmasp_intf *intf, bool en)
+void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en)
 {
 	struct bcmasp_priv *priv = intf->parent;
 	struct device *dev = &priv->pdev->dev;
@@ -1154,54 +1156,12 @@ static void bcmasp_enable_wol_shared(struct bcmasp_intf *intf, bool en)
 	}
 }
 
-static void bcmasp_wol_irq_destroy_shared(struct bcmasp_priv *priv)
+static void bcmasp_wol_irq_destroy(struct bcmasp_priv *priv)
 {
 	if (priv->wol_irq > 0)
 		free_irq(priv->wol_irq, priv);
 }
 
-static void bcmasp_init_wol_per_intf(struct bcmasp_priv *priv)
-{
-	struct platform_device *pdev = priv->pdev;
-	struct device *dev = &pdev->dev;
-	struct bcmasp_intf *intf;
-	int irq;
-
-	list_for_each_entry(intf, &priv->intfs, list) {
-		irq = bcmasp_get_and_request_irq(priv, intf->port + 1);
-		if (irq < 0) {
-			dev_warn(dev, "Failed to init WoL irq(port %d): %d\n",
-				 intf->port, irq);
-			continue;
-		}
-
-		intf->wol_irq = irq;
-		intf->wol_irq_enabled = false;
-		device_set_wakeup_capable(&pdev->dev, 1);
-	}
-}
-
-static void bcmasp_enable_wol_per_intf(struct bcmasp_intf *intf, bool en)
-{
-	struct device *dev = &intf->parent->pdev->dev;
-
-	if (en ^ intf->wol_irq_enabled)
-		irq_set_irq_wake(intf->wol_irq, en);
-
-	intf->wol_irq_enabled = en;
-	device_set_wakeup_enable(dev, en);
-}
-
-static void bcmasp_wol_irq_destroy_per_intf(struct bcmasp_priv *priv)
-{
-	struct bcmasp_intf *intf;
-
-	list_for_each_entry(intf, &priv->intfs, list) {
-		if (intf->wol_irq > 0)
-			free_irq(intf->wol_irq, priv);
-	}
-}
-
 static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en)
 {
 	u32 reg, phy_lpi_overwrite;
@@ -1220,70 +1180,53 @@ static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en)
 	usleep_range(50, 100);
 }
 
-static struct bcmasp_hw_info v20_hw_info = {
-	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH,
-	.umac2fb = UMAC2FB_OFFSET,
-	.rx_ctrl_fb_out_frame_count = ASP_RX_CTRL_FB_OUT_FRAME_COUNT,
-	.rx_ctrl_fb_filt_out_frame_count = ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT,
-	.rx_ctrl_fb_rx_fifo_depth = ASP_RX_CTRL_FB_RX_FIFO_DEPTH,
-};
-
-static const struct bcmasp_plat_data v20_plat_data = {
-	.init_wol = bcmasp_init_wol_per_intf,
-	.enable_wol = bcmasp_enable_wol_per_intf,
-	.destroy_wol = bcmasp_wol_irq_destroy_per_intf,
-	.core_clock_select = bcmasp_core_clock_select_one,
-	.hw_info = &v20_hw_info,
-};
-
-static struct bcmasp_hw_info v21_hw_info = {
-	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH_2_1,
-	.umac2fb = UMAC2FB_OFFSET_2_1,
-	.rx_ctrl_fb_out_frame_count = ASP_RX_CTRL_FB_OUT_FRAME_COUNT_2_1,
-	.rx_ctrl_fb_filt_out_frame_count =
-		ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT_2_1,
-	.rx_ctrl_fb_rx_fifo_depth = ASP_RX_CTRL_FB_RX_FIFO_DEPTH_2_1,
-};
-
 static const struct bcmasp_plat_data v21_plat_data = {
-	.init_wol = bcmasp_init_wol_shared,
-	.enable_wol = bcmasp_enable_wol_shared,
-	.destroy_wol = bcmasp_wol_irq_destroy_shared,
 	.core_clock_select = bcmasp_core_clock_select_one,
-	.hw_info = &v21_hw_info,
+	.num_mda_filters = 32,
+	.num_net_filters = 32,
+	.tx_chan_offset = 8,
+	.rx_ctrl_offset = 0x0,
 };
 
 static const struct bcmasp_plat_data v22_plat_data = {
-	.init_wol = bcmasp_init_wol_shared,
-	.enable_wol = bcmasp_enable_wol_shared,
-	.destroy_wol = bcmasp_wol_irq_destroy_shared,
 	.core_clock_select = bcmasp_core_clock_select_many,
-	.hw_info = &v21_hw_info,
 	.eee_fixup = bcmasp_eee_fixup,
+	.num_mda_filters = 32,
+	.num_net_filters = 32,
+	.tx_chan_offset = 8,
+	.rx_ctrl_offset = 0x0,
+};
+
+static const struct bcmasp_plat_data v30_plat_data = {
+	.core_clock_select = bcmasp_core_clock_select_one_ctrl2,
+	.num_mda_filters = 20,
+	.num_net_filters = 16,
+	.tx_chan_offset = 0,
+	.rx_ctrl_offset = 0x10000,
 };
 
 static void bcmasp_set_pdata(struct bcmasp_priv *priv, const struct bcmasp_plat_data *pdata)
 {
-	priv->init_wol = pdata->init_wol;
-	priv->enable_wol = pdata->enable_wol;
-	priv->destroy_wol = pdata->destroy_wol;
 	priv->core_clock_select = pdata->core_clock_select;
 	priv->eee_fixup = pdata->eee_fixup;
-	priv->hw_info = pdata->hw_info;
+	priv->num_mda_filters = pdata->num_mda_filters;
+	priv->num_net_filters = pdata->num_net_filters;
+	priv->tx_chan_offset = pdata->tx_chan_offset;
+	priv->rx_ctrl_offset = pdata->rx_ctrl_offset;
 }
 
 static const struct of_device_id bcmasp_of_match[] = {
-	{ .compatible = "brcm,asp-v2.0", .data = &v20_plat_data },
 	{ .compatible = "brcm,asp-v2.1", .data = &v21_plat_data },
 	{ .compatible = "brcm,asp-v2.2", .data = &v22_plat_data },
+	{ .compatible = "brcm,asp-v3.0", .data = &v30_plat_data },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, bcmasp_of_match);
 
 static const struct of_device_id bcmasp_mdio_of_match[] = {
-	{ .compatible = "brcm,asp-v2.2-mdio", },
 	{ .compatible = "brcm,asp-v2.1-mdio", },
-	{ .compatible = "brcm,asp-v2.0-mdio", },
+	{ .compatible = "brcm,asp-v2.2-mdio", },
+	{ .compatible = "brcm,asp-v3.0-mdio", },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, bcmasp_mdio_of_match);
@@ -1365,6 +1308,17 @@ static int bcmasp_probe(struct platform_device *pdev)
 	 * how many interfaces come up.
 	 */
 	bcmasp_core_init(priv);
+
+	priv->mda_filters = devm_kcalloc(dev, priv->num_mda_filters,
+					 sizeof(*priv->mda_filters), GFP_KERNEL);
+	if (!priv->mda_filters)
+		return -ENOMEM;
+
+	priv->net_filters = devm_kcalloc(dev, priv->num_net_filters,
+					 sizeof(*priv->net_filters), GFP_KERNEL);
+	if (!priv->net_filters)
+		return -ENOMEM;
+
 	bcmasp_core_init_filters(priv);
 
 	ports_node = of_find_node_by_name(dev->of_node, "ethernet-ports");
@@ -1387,7 +1341,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 	}
 
 	/* Check and enable WoL */
-	priv->init_wol(priv);
+	bcmasp_init_wol(priv);
 
 	/* Drop the clock reference count now and let ndo_open()/ndo_close()
 	 * manage it for us from now on.
@@ -1404,7 +1358,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 		if (ret) {
 			netdev_err(intf->ndev,
 				   "failed to register net_device: %d\n", ret);
-			priv->destroy_wol(priv);
+			bcmasp_wol_irq_destroy(priv);
 			bcmasp_remove_intfs(priv);
 			goto of_put_exit;
 		}
@@ -1425,7 +1379,7 @@ static void bcmasp_remove(struct platform_device *pdev)
 	if (!priv)
 		return;
 
-	priv->destroy_wol(priv);
+	bcmasp_wol_irq_destroy(priv);
 	bcmasp_remove_intfs(priv);
 }
 
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index f93cb3da44b0..74adfdb50e11 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -53,22 +53,15 @@
 #define ASP_RX_CTRL_FB_0_FRAME_COUNT		0x14
 #define ASP_RX_CTRL_FB_1_FRAME_COUNT		0x18
 #define ASP_RX_CTRL_FB_8_FRAME_COUNT		0x1c
-/* asp2.1 diverges offsets here */
-/* ASP2.0 */
-#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT		0x20
-#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT	0x24
-#define ASP_RX_CTRL_FLUSH			0x28
-#define  ASP_CTRL_UMAC0_FLUSH_MASK		(BIT(0) | BIT(12))
-#define  ASP_CTRL_UMAC1_FLUSH_MASK		(BIT(1) | BIT(13))
-#define  ASP_CTRL_SPB_FLUSH_MASK		(BIT(8) | BIT(20))
-#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH		0x30
-/* ASP2.1 */
-#define ASP_RX_CTRL_FB_9_FRAME_COUNT_2_1	0x20
-#define ASP_RX_CTRL_FB_10_FRAME_COUNT_2_1	0x24
-#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT_2_1	0x28
-#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT_2_1	0x2c
-#define ASP_RX_CTRL_FLUSH_2_1			0x30
-#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH_2_1	0x38
+#define ASP_RX_CTRL_FB_9_FRAME_COUNT		0x20
+#define ASP_RX_CTRL_FB_10_FRAME_COUNT		0x24
+#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT		0x28
+#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT	0x2c
+#define ASP_RX_CTRL_FLUSH			0x30
+#define  ASP_CTRL_UMAC0_FLUSH_MASK             (BIT(0) | BIT(12))
+#define  ASP_CTRL_UMAC1_FLUSH_MASK             (BIT(1) | BIT(13))
+#define  ASP_CTRL_SPB_FLUSH_MASK               (BIT(8) | BIT(20))
+#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH		0x38
 
 #define ASP_RX_FILTER_OFFSET			0x80000
 #define  ASP_RX_FILTER_BLK_CTRL			0x0
@@ -345,11 +338,6 @@ struct bcmasp_intf {
 
 	u32				wolopts;
 	u8				sopass[SOPASS_MAX];
-	/* Used if per intf wol irq */
-	int				wol_irq;
-	unsigned int			wol_irq_enabled:1;
-
-	struct ethtool_keee		eee;
 };
 
 #define NUM_NET_FILTERS				32
@@ -372,21 +360,13 @@ struct bcmasp_mda_filter {
 	u8		mask[ETH_ALEN];
 };
 
-struct bcmasp_hw_info {
-	u32		rx_ctrl_flush;
-	u32		umac2fb;
-	u32		rx_ctrl_fb_out_frame_count;
-	u32		rx_ctrl_fb_filt_out_frame_count;
-	u32		rx_ctrl_fb_rx_fifo_depth;
-};
-
 struct bcmasp_plat_data {
-	void (*init_wol)(struct bcmasp_priv *priv);
-	void (*enable_wol)(struct bcmasp_intf *intf, bool en);
-	void (*destroy_wol)(struct bcmasp_priv *priv);
 	void (*core_clock_select)(struct bcmasp_priv *priv, bool slow);
 	void (*eee_fixup)(struct bcmasp_intf *priv, bool en);
-	struct bcmasp_hw_info		*hw_info;
+	unsigned int num_mda_filters;
+	unsigned int num_net_filters;
+	unsigned int tx_chan_offset;
+	unsigned int rx_ctrl_offset;
 };
 
 struct bcmasp_priv {
@@ -401,18 +381,18 @@ struct bcmasp_priv {
 	int				wol_irq;
 	unsigned long			wol_irq_enabled_mask;
 
-	void (*init_wol)(struct bcmasp_priv *priv);
-	void (*enable_wol)(struct bcmasp_intf *intf, bool en);
-	void (*destroy_wol)(struct bcmasp_priv *priv);
 	void (*core_clock_select)(struct bcmasp_priv *priv, bool slow);
 	void (*eee_fixup)(struct bcmasp_intf *intf, bool en);
+	unsigned int			num_mda_filters;
+	unsigned int			num_net_filters;
+	unsigned int			tx_chan_offset;
+	unsigned int			rx_ctrl_offset;
 
 	void __iomem			*base;
-	struct	bcmasp_hw_info		*hw_info;
 
 	struct list_head		intfs;
 
-	struct bcmasp_mda_filter	mda_filters[NUM_MDA_FILTERS];
+	struct bcmasp_mda_filter	*mda_filters;
 
 	/* MAC destination address filters lock */
 	spinlock_t			mda_lock;
@@ -420,7 +400,7 @@ struct bcmasp_priv {
 	/* Protects accesses to ASP_CTRL_CLOCK_CTRL */
 	spinlock_t			clk_lock;
 
-	struct bcmasp_net_filter	net_filters[NUM_NET_FILTERS];
+	struct bcmasp_net_filter	*net_filters;
 
 	/* Network filter lock */
 	struct mutex			net_lock;
@@ -510,8 +490,8 @@ BCMASP_FP_IO_MACRO_Q(rx_edpkt_cfg);
 #define  PKT_OFFLOAD_EPKT_IP(x)		((x) << 21)
 #define  PKT_OFFLOAD_EPKT_TP(x)		((x) << 19)
 #define  PKT_OFFLOAD_EPKT_LEN(x)	((x) << 16)
-#define  PKT_OFFLOAD_EPKT_CSUM_L3	BIT(15)
-#define  PKT_OFFLOAD_EPKT_CSUM_L2	BIT(14)
+#define  PKT_OFFLOAD_EPKT_CSUM_L4	BIT(15)
+#define  PKT_OFFLOAD_EPKT_CSUM_L3	BIT(14)
 #define  PKT_OFFLOAD_EPKT_ID(x)		((x) << 12)
 #define  PKT_OFFLOAD_EPKT_SEQ(x)	((x) << 10)
 #define  PKT_OFFLOAD_EPKT_TS(x)		((x) << 8)
@@ -543,12 +523,27 @@ BCMASP_CORE_IO_MACRO(intr2, ASP_INTR2_OFFSET);
 BCMASP_CORE_IO_MACRO(wakeup_intr2, ASP_WAKEUP_INTR2_OFFSET);
 BCMASP_CORE_IO_MACRO(tx_analytics, ASP_TX_ANALYTICS_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_analytics, ASP_RX_ANALYTICS_OFFSET);
-BCMASP_CORE_IO_MACRO(rx_ctrl, ASP_RX_CTRL_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_filter, ASP_RX_FILTER_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_edpkt, ASP_EDPKT_OFFSET);
 BCMASP_CORE_IO_MACRO(ctrl, ASP_CTRL_OFFSET);
 BCMASP_CORE_IO_MACRO(ctrl2, ASP_CTRL2_OFFSET);
 
+#define BCMASP_CORE_IO_MACRO_OFFSET(name, offset)			\
+static inline u32 name##_core_rl(struct bcmasp_priv *priv,		\
+				 u32 off)				\
+{									\
+	u32 reg = readl_relaxed(priv->base + priv->name##_offset +	\
+				(offset) + off);			\
+	return reg;							\
+}									\
+static inline void name##_core_wl(struct bcmasp_priv *priv,		\
+				  u32 val, u32 off)			\
+{									\
+	writel_relaxed(val, priv->base + priv->name##_offset +		\
+		       (offset) + off);					\
+}
+BCMASP_CORE_IO_MACRO_OFFSET(rx_ctrl, ASP_RX_CTRL_OFFSET);
+
 struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
 					    struct device_node *ndev_dn, int i);
 
@@ -601,5 +596,5 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 
 void bcmasp_netfilt_suspend(struct bcmasp_intf *intf);
 
-void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable);
+void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en);
 #endif
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index 9da5ae29a105..4381a4cfd8c6 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -10,7 +10,6 @@
 #include "bcmasp_intf_defs.h"
 
 enum bcmasp_stat_type {
-	BCMASP_STAT_RX_EDPKT,
 	BCMASP_STAT_RX_CTRL,
 	BCMASP_STAT_RX_CTRL_PER_INTF,
 	BCMASP_STAT_SOFT,
@@ -33,8 +32,6 @@ struct bcmasp_stats {
 	.reg_offset = offset, \
 }
 
-#define STAT_BCMASP_RX_EDPKT(str, offset) \
-	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_EDPKT, offset)
 #define STAT_BCMASP_RX_CTRL(str, offset) \
 	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_CTRL, offset)
 #define STAT_BCMASP_RX_CTRL_PER_INTF(str, offset) \
@@ -42,11 +39,6 @@ struct bcmasp_stats {
 
 /* Must match the order of struct bcmasp_mib_counters */
 static const struct bcmasp_stats bcmasp_gstrings_stats[] = {
-	/* EDPKT counters */
-	STAT_BCMASP_RX_EDPKT("RX Time Stamp", ASP_EDPKT_RX_TS_COUNTER),
-	STAT_BCMASP_RX_EDPKT("RX PKT Count", ASP_EDPKT_RX_PKT_CNT),
-	STAT_BCMASP_RX_EDPKT("RX PKT Buffered", ASP_EDPKT_HDR_EXTR_CNT),
-	STAT_BCMASP_RX_EDPKT("RX PKT Pushed to DRAM", ASP_EDPKT_HDR_OUT_CNT),
 	/* ASP RX control */
 	STAT_BCMASP_RX_CTRL_PER_INTF("Frames From Unimac",
 				     ASP_RX_CTRL_UMAC_0_FRAME_COUNT),
@@ -71,23 +63,6 @@ static const struct bcmasp_stats bcmasp_gstrings_stats[] = {
 
 #define BCMASP_STATS_LEN	ARRAY_SIZE(bcmasp_gstrings_stats)
 
-static u16 bcmasp_stat_fixup_offset(struct bcmasp_intf *intf,
-				    const struct bcmasp_stats *s)
-{
-	struct bcmasp_priv *priv = intf->parent;
-
-	if (!strcmp("Frames Out(Buffer)", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_out_frame_count;
-
-	if (!strcmp("Frames Out(Filters)", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_filt_out_frame_count;
-
-	if (!strcmp("RX Buffer FIFO Depth", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_rx_fifo_depth;
-
-	return s->reg_offset;
-}
-
 static int bcmasp_get_sset_count(struct net_device *dev, int string_set)
 {
 	switch (string_set) {
@@ -126,13 +101,10 @@ static void bcmasp_update_mib_counters(struct bcmasp_intf *intf)
 		char *p;
 
 		s = &bcmasp_gstrings_stats[i];
-		offset = bcmasp_stat_fixup_offset(intf, s);
+		offset = s->reg_offset;
 		switch (s->type) {
 		case BCMASP_STAT_SOFT:
 			continue;
-		case BCMASP_STAT_RX_EDPKT:
-			val = rx_edpkt_core_rl(intf->parent, offset);
-			break;
 		case BCMASP_STAT_RX_CTRL:
 			val = rx_ctrl_core_rl(intf->parent, offset);
 			break;
@@ -215,7 +187,7 @@ static int bcmasp_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 		memcpy(intf->sopass, wol->sopass, sizeof(wol->sopass));
 
 	mutex_lock(&priv->wol_lock);
-	priv->enable_wol(intf, !!intf->wolopts);
+	bcmasp_enable_wol(intf, !!intf->wolopts);
 	mutex_unlock(&priv->wol_lock);
 
 	return 0;
@@ -289,7 +261,7 @@ static int bcmasp_flow_get(struct bcmasp_intf *intf, struct ethtool_rxnfc *cmd)
 
 	memcpy(&cmd->fs, &nfilter->fs, sizeof(nfilter->fs));
 
-	cmd->data = NUM_NET_FILTERS;
+	cmd->data = intf->parent->num_net_filters;
 
 	return 0;
 }
@@ -336,7 +308,7 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		break;
 	case ETHTOOL_GRXCLSRLALL:
 		err = bcmasp_netfilt_get_all_active(intf, rule_locs, &cmd->rule_cnt);
-		cmd->data = NUM_NET_FILTERS;
+		cmd->data = intf->parent->num_net_filters;
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -348,58 +320,19 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	return err;
 }
 
-void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable)
-{
-	u32 reg;
-
-	reg = umac_rl(intf, UMC_EEE_CTRL);
-	if (enable)
-		reg |= EEE_EN;
-	else
-		reg &= ~EEE_EN;
-	umac_wl(intf, reg, UMC_EEE_CTRL);
-
-	intf->eee.eee_enabled = enable;
-}
-
 static int bcmasp_get_eee(struct net_device *dev, struct ethtool_keee *e)
 {
-	struct bcmasp_intf *intf = netdev_priv(dev);
-	struct ethtool_keee *p = &intf->eee;
-
 	if (!dev->phydev)
 		return -ENODEV;
 
-	e->tx_lpi_enabled = p->tx_lpi_enabled;
-	e->tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER);
-
 	return phy_ethtool_get_eee(dev->phydev, e);
 }
 
 static int bcmasp_set_eee(struct net_device *dev, struct ethtool_keee *e)
 {
-	struct bcmasp_intf *intf = netdev_priv(dev);
-	struct ethtool_keee *p = &intf->eee;
-	int ret;
-
 	if (!dev->phydev)
 		return -ENODEV;
 
-	if (!p->eee_enabled) {
-		bcmasp_eee_enable_set(intf, false);
-	} else {
-		ret = phy_init_eee(dev->phydev, 0);
-		if (ret) {
-			netif_err(intf, hw, dev,
-				  "EEE initialization failed: %d\n", ret);
-			return ret;
-		}
-
-		umac_wl(intf, e->tx_lpi_timer, UMC_EEE_LPI_TIMER);
-		intf->eee.tx_lpi_enabled = e->tx_lpi_enabled;
-		bcmasp_eee_enable_set(intf, true);
-	}
-
 	return phy_ethtool_set_eee(dev->phydev, e);
 }
 
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index cfd50efbdbc0..0d61b8580d72 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -180,14 +180,14 @@ static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
 	case htons(ETH_P_IP):
 		header |= PKT_OFFLOAD_HDR_SIZE_2((ip_hdrlen(skb) >> 8) & 0xf);
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_2(ip_hdrlen(skb) & 0xff);
-		epkt |= PKT_OFFLOAD_EPKT_IP(0) | PKT_OFFLOAD_EPKT_CSUM_L2;
+		epkt |= PKT_OFFLOAD_EPKT_IP(0);
 		ip_proto = ip_hdr(skb)->protocol;
 		header_cnt += 2;
 		break;
 	case htons(ETH_P_IPV6):
 		header |= PKT_OFFLOAD_HDR_SIZE_2((IP6_HLEN >> 8) & 0xf);
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_2(IP6_HLEN & 0xff);
-		epkt |= PKT_OFFLOAD_EPKT_IP(1) | PKT_OFFLOAD_EPKT_CSUM_L2;
+		epkt |= PKT_OFFLOAD_EPKT_IP(1);
 		ip_proto = ipv6_hdr(skb)->nexthdr;
 		header_cnt += 2;
 		break;
@@ -198,12 +198,12 @@ static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
 	switch (ip_proto) {
 	case IPPROTO_TCP:
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_3(tcp_hdrlen(skb));
-		epkt |= PKT_OFFLOAD_EPKT_TP(0) | PKT_OFFLOAD_EPKT_CSUM_L3;
+		epkt |= PKT_OFFLOAD_EPKT_TP(0) | PKT_OFFLOAD_EPKT_CSUM_L4;
 		header_cnt++;
 		break;
 	case IPPROTO_UDP:
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_3(UDP_HLEN);
-		epkt |= PKT_OFFLOAD_EPKT_TP(1) | PKT_OFFLOAD_EPKT_CSUM_L3;
+		epkt |= PKT_OFFLOAD_EPKT_TP(1) | PKT_OFFLOAD_EPKT_CSUM_L4;
 		header_cnt++;
 		break;
 	default:
@@ -619,7 +619,6 @@ static void bcmasp_adj_link(struct net_device *dev)
 	struct phy_device *phydev = dev->phydev;
 	u32 cmd_bits = 0, reg;
 	int changed = 0;
-	bool active;
 
 	if (intf->old_link != phydev->link) {
 		changed = 1;
@@ -677,8 +676,13 @@ static void bcmasp_adj_link(struct net_device *dev)
 		}
 		umac_wl(intf, reg, UMC_CMD);
 
-		active = phy_init_eee(phydev, 0) >= 0;
-		bcmasp_eee_enable_set(intf, active);
+		umac_wl(intf, phydev->eee_cfg.tx_lpi_timer, UMC_EEE_LPI_TIMER);
+		reg = umac_rl(intf, UMC_EEE_CTRL);
+		if (phydev->enable_tx_lpi)
+			reg |= EEE_EN;
+		else
+			reg &= ~EEE_EN;
+		umac_wl(intf, reg, UMC_EEE_CTRL);
 	}
 
 	reg = rgmii_rl(intf, RGMII_OOB_CNTRL);
@@ -814,9 +818,7 @@ static void bcmasp_init_tx(struct bcmasp_intf *intf)
 	/* Tx SPB */
 	tx_spb_ctrl_wl(intf, ((intf->channel + 8) << TX_SPB_CTRL_XF_BID_SHIFT),
 		       TX_SPB_CTRL_XF_CTRL2);
-	tx_pause_ctrl_wl(intf, (1 << (intf->channel + 8)), TX_PAUSE_MAP_VECTOR);
 	tx_spb_top_wl(intf, 0x1e, TX_SPB_TOP_BLKOUT);
-	tx_spb_top_wl(intf, 0x0, TX_SPB_TOP_SPRE_BW_CTRL);
 
 	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_READ);
 	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_BASE);
@@ -1055,6 +1057,9 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 
 		/* Indicate that the MAC is responsible for PHY PM */
 		phydev->mac_managed_pm = true;
+
+		/* Set phylib's copy of the LPI timer */
+		phydev->eee_cfg.tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER);
 	}
 
 	umac_reset(intf);
@@ -1178,7 +1183,7 @@ static void bcmasp_map_res(struct bcmasp_priv *priv, struct bcmasp_intf *intf)
 {
 	/* Per port */
 	intf->res.umac = priv->base + UMC_OFFSET(intf);
-	intf->res.umac2fb = priv->base + (priv->hw_info->umac2fb +
+	intf->res.umac2fb = priv->base + (UMAC2FB_OFFSET + priv->rx_ctrl_offset +
 					  (intf->port * 0x4));
 	intf->res.rgmii = priv->base + RGMII_OFFSET(intf);
 
@@ -1193,7 +1198,6 @@ static void bcmasp_map_res(struct bcmasp_priv *priv, struct bcmasp_intf *intf)
 	intf->rx_edpkt_cfg = priv->base + RX_EDPKT_CFG_OFFSET(intf);
 }
 
-#define MAX_IRQ_STR_LEN		64
 struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
 					    struct device_node *ndev_dn, int i)
 {
@@ -1331,7 +1335,8 @@ static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf)
 				     ASP_WAKEUP_INTR2_MASK_CLEAR);
 	}
 
-	if (intf->eee.eee_enabled && intf->parent->eee_fixup)
+	if (ndev->phydev && ndev->phydev->eee_cfg.eee_enabled &&
+	    intf->parent->eee_fixup)
 		intf->parent->eee_fixup(intf, true);
 
 	netif_dbg(intf, wol, ndev, "entered WOL mode\n");
@@ -1373,7 +1378,8 @@ static void bcmasp_resume_from_wol(struct bcmasp_intf *intf)
 {
 	u32 reg;
 
-	if (intf->eee.eee_enabled && intf->parent->eee_fixup)
+	if (intf->ndev->phydev && intf->ndev->phydev->eee_cfg.eee_enabled &&
+	    intf->parent->eee_fixup)
 		intf->parent->eee_fixup(intf, false);
 
 	reg = umac_rl(intf, UMC_MPD_CTRL);
@@ -1404,9 +1410,6 @@ int bcmasp_interface_resume(struct bcmasp_intf *intf)
 
 	bcmasp_resume_from_wol(intf);
 
-	if (intf->eee.eee_enabled)
-		bcmasp_eee_enable_set(intf, true);
-
 	netif_device_attach(dev);
 
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
index ad742612895f..af7418348e81 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
@@ -118,8 +118,7 @@
 #define  UMC_PSW_MS			0x624
 #define  UMC_PSW_LS			0x628
 
-#define UMAC2FB_OFFSET_2_1		0x9f044
-#define UMAC2FB_OFFSET			0x9f03c
+#define UMAC2FB_OFFSET			0x9f044
 #define  UMAC2FB_CFG			0x0
 #define   UMAC2FB_CFG_OPUT_EN		BIT(0)
 #define   UMAC2FB_CFG_VLAN_EN		BIT(1)
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index e5809ad5eb82..8267417b3750 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -575,7 +575,7 @@ static void b44_check_phy(struct b44 *bp)
 
 static void b44_timer(struct timer_list *t)
 {
-	struct b44 *bp = from_timer(bp, t, timer);
+	struct b44 *bp = timer_container_of(bp, t, timer);
 
 	spin_lock_irq(&bp->lock);
 
@@ -1628,7 +1628,7 @@ static int b44_close(struct net_device *dev)
 
 	napi_disable(&bp->napi);
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 
 	spin_lock_irq(&bp->lock);
 
@@ -2473,7 +2473,7 @@ static int b44_suspend(struct ssb_device *sdev, pm_message_t state)
 	if (!netif_running(dev))
 		return 0;
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 
 	spin_lock_irq(&bp->lock);
 
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 65e3a0656a4c..92204fea1f08 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -286,7 +286,7 @@ static int bcm_enet_refill_rx(struct net_device *dev, bool napi_mode)
  */
 static void bcm_enet_refill_rx_timer(struct timer_list *t)
 {
-	struct bcm_enet_priv *priv = from_timer(priv, t, rx_timeout);
+	struct bcm_enet_priv *priv = timer_container_of(priv, t, rx_timeout);
 	struct net_device *dev = priv->net_dev;
 
 	spin_lock(&priv->rx_lock);
@@ -1195,7 +1195,7 @@ static int bcm_enet_stop(struct net_device *dev)
 	napi_disable(&priv->napi);
 	if (priv->has_phy)
 		phy_stop(dev->phydev);
-	del_timer_sync(&priv->rx_timeout);
+	timer_delete_sync(&priv->rx_timeout);
 
 	/* mask all interrupts */
 	enet_writel(priv, 0, ENET_IRMASK_REG);
@@ -2001,7 +2001,7 @@ static inline int bcm_enet_port_is_rgmii(int portid)
  */
 static void swphy_poll_timer(struct timer_list *t)
 {
-	struct bcm_enet_priv *priv = from_timer(priv, t, swphy_poll);
+	struct bcm_enet_priv *priv = timer_container_of(priv, t, swphy_poll);
 	unsigned int i;
 
 	for (i = 0; i < priv->num_ports; i++) {
@@ -2346,10 +2346,10 @@ static int bcm_enetsw_stop(struct net_device *dev)
 	priv = netdev_priv(dev);
 	kdev = &priv->pdev->dev;
 
-	del_timer_sync(&priv->swphy_poll);
+	timer_delete_sync(&priv->swphy_poll);
 	netif_stop_queue(dev);
 	napi_disable(&priv->napi);
-	del_timer_sync(&priv->rx_timeout);
+	timer_delete_sync(&priv->rx_timeout);
 
 	/* mask all interrupts */
 	enet_dmac_writel(priv, 0, ENETDMAC_IRMASK, priv->rx_chan);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 42672c63f108..bc4e1f3b3752 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1933,7 +1933,11 @@ static int bcm_sysport_open(struct net_device *dev)
 	unsigned int i;
 	int ret;
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		netdev_err(dev, "could not enable priv clock\n");
+		return ret;
+	}
 
 	/* Reset UniMAC */
 	umac_reset(priv);
@@ -2591,7 +2595,11 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 		goto err_deregister_notifier;
 	}
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "could not enable priv clock\n");
+		goto err_deregister_netdev;
+	}
 
 	priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK;
 	dev_info(&pdev->dev,
@@ -2605,6 +2613,8 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_deregister_netdev:
+	unregister_netdev(dev);
 err_deregister_notifier:
 	unregister_netdevice_notifier(&priv->netdev_notifier);
 err_deregister_fixed_link:
@@ -2774,7 +2784,12 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 	if (!netif_running(dev))
 		return 0;
 
-	clk_prepare_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		netdev_err(dev, "could not enable priv clock\n");
+		return ret;
+	}
+
 	if (priv->wolopts)
 		clk_disable_unprepare(priv->wol_clk);
 
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index ecce23cecbea..4e266ce41180 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -171,6 +171,7 @@ static int platform_phy_connect(struct bgmac *bgmac)
 static int bgmac_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
+	struct device_node *phy_node;
 	struct bgmac *bgmac;
 	struct resource *regs;
 	int ret;
@@ -236,7 +237,9 @@ static int bgmac_probe(struct platform_device *pdev)
 	bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset;
 	bgmac->get_bus_clock = platform_bgmac_get_bus_clock;
 	bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32;
-	if (of_parse_phandle(np, "phy-handle", 0)) {
+	phy_node = of_parse_phandle(np, "phy-handle", 0);
+	if (phy_node) {
+		of_node_put(phy_node);
 		bgmac->phy_connect = platform_phy_connect;
 	} else {
 		bgmac->phy_connect = bgmac_phy_connect_direct;
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index a461ec612e95..3e9c57196a39 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1446,7 +1446,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac)
 	struct phy_device *phy_dev;
 	int err;
 
-	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
+	phy_dev = fixed_phy_register(&fphy_status, NULL);
 	if (IS_ERR(phy_dev)) {
 		dev_err(bgmac->dev, "Failed to register fixed PHY device\n");
 		return PTR_ERR(phy_dev);
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index d73ef262991d..6fee9a41839c 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -328,8 +328,7 @@
 #define BGMAC_RX_FRAME_OFFSET			30		/* There are 2 unused bytes between header and real data */
 #define BGMAC_RX_BUF_OFFSET			(NET_SKB_PAD + NET_IP_ALIGN - \
 						 BGMAC_RX_FRAME_OFFSET)
-/* Jumbo frame size with FCS */
-#define BGMAC_RX_MAX_FRAME_SIZE			9724
+#define BGMAC_RX_MAX_FRAME_SIZE			1536
 #define BGMAC_RX_BUF_SIZE			(BGMAC_RX_FRAME_OFFSET + BGMAC_RX_MAX_FRAME_SIZE)
 #define BGMAC_RX_ALLOC_SIZE			(SKB_DATA_ALIGN(BGMAC_RX_BUF_SIZE + BGMAC_RX_BUF_OFFSET) + \
 						 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 6ec773e61182..cb1011f6fd30 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -6163,7 +6163,7 @@ bnx2_5708_serdes_timer(struct bnx2 *bp)
 static void
 bnx2_timer(struct timer_list *t)
 {
-	struct bnx2 *bp = from_timer(bp, t, timer);
+	struct bnx2 *bp = timer_container_of(bp, t, timer);
 
 	if (!netif_running(bp->dev))
 		return;
@@ -6400,7 +6400,7 @@ bnx2_open(struct net_device *dev)
 				rc = bnx2_request_irq(bp);
 
 			if (rc) {
-				del_timer_sync(&bp->timer);
+				timer_delete_sync(&bp->timer);
 				goto open_err;
 			}
 			bnx2_enable_int(bp);
@@ -6752,7 +6752,7 @@ bnx2_close(struct net_device *dev)
 	bnx2_disable_int_sync(bp);
 	bnx2_napi_disable(bp);
 	netif_tx_disable(dev);
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 	bnx2_shutdown_chip(bp);
 	bnx2_free_irq(bp);
 	bnx2_free_skbs(bp);
@@ -8602,7 +8602,7 @@ bnx2_remove_one(struct pci_dev *pdev)
 
 	unregister_netdev(dev);
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 	cancel_work_sync(&bp->reset_task);
 
 	pci_iounmap(bp->pdev, bp->regview);
@@ -8629,7 +8629,7 @@ bnx2_suspend(struct device *device)
 		cancel_work_sync(&bp->reset_task);
 		bnx2_netif_stop(bp, true);
 		netif_device_detach(dev);
-		del_timer_sync(&bp->timer);
+		timer_delete_sync(&bp->timer);
 		bnx2_shutdown_chip(bp);
 		__bnx2_free_irq(bp);
 		bnx2_free_skbs(bp);
@@ -8687,7 +8687,7 @@ static pci_ers_result_t bnx2_io_error_detected(struct pci_dev *pdev,
 
 	if (netif_running(dev)) {
 		bnx2_netif_stop(bp, true);
-		del_timer_sync(&bp->timer);
+		timer_delete_sync(&bp->timer);
 		bnx2_reset_nic(bp, BNX2_DRV_MSG_CODE_RESET);
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index a8e07e51418f..e59530357e2c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3059,7 +3059,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
 
 	bp->rx_mode = BNX2X_RX_MODE_NONE;
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 
 	if (IS_PF(bp) && !BP_NOMCP(bp)) {
 		/* Set ALWAYS_ALIVE bit in shmem */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 678829646cec..c9a1a1d504c0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -5783,7 +5783,7 @@ void bnx2x_drv_pulse(struct bnx2x *bp)
 
 static void bnx2x_timer(struct timer_list *t)
 {
-	struct bnx2x *bp = from_timer(bp, t, timer);
+	struct bnx2x *bp = timer_container_of(bp, t, timer);
 
 	if (!netif_running(bp->dev))
 		return;
@@ -14140,7 +14140,7 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp)
 	bnx2x_tx_disable(bp);
 	netdev_reset_tc(bp->dev);
 
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 	cancel_delayed_work_sync(&bp->sp_task);
 	cancel_delayed_work_sync(&bp->period_task);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 8e04552d2216..02c8213915a5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -2593,7 +2593,7 @@ void bnx2x_init_rx_mode_obj(struct bnx2x *bp,
 /********************* Multicast verbs: SET, CLEAR ****************************/
 static inline u8 bnx2x_mcast_bin_from_mac(u8 *mac)
 {
-	return (crc32c_le(0, mac, ETH_ALEN) >> 24) & 0xff;
+	return (crc32c(0, mac, ETH_ALEN) >> 24) & 0xff;
 }
 
 struct bnx2x_mcast_mac_elem {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4ec4934a4edd..ae89a981e052 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -54,7 +54,10 @@
 #include <net/pkt_cls.h>
 #include <net/page_pool/helpers.h>
 #include <linux/align.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
+#include <linux/pci-tph.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -76,12 +79,12 @@
 #define BNXT_DEF_MSG_ENABLE	(NETIF_MSG_DRV | NETIF_MSG_HW | \
 				 NETIF_MSG_TX_ERR)
 
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Broadcom NetXtreme network driver");
 
 #define BNXT_RX_OFFSET (NET_SKB_PAD + NET_IP_ALIGN)
 #define BNXT_RX_DMA_OFFSET NET_SKB_PAD
-#define BNXT_RX_COPY_THRESH 256
 
 #define BNXT_TX_PUSH_THRESH 164
 
@@ -486,6 +489,17 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	txr = &bp->tx_ring[bp->tx_ring_map[i]];
 	prod = txr->tx_prod;
 
+#if (MAX_SKB_FRAGS > TX_MAX_FRAGS)
+	if (skb_shinfo(skb)->nr_frags > TX_MAX_FRAGS) {
+		netdev_warn_once(dev, "SKB has too many (%d) fragments, max supported is %d.  SKB will be linearized.\n",
+				 skb_shinfo(skb)->nr_frags, TX_MAX_FRAGS);
+		if (skb_linearize(skb)) {
+			dev_kfree_skb_any(skb);
+			dev_core_stats_tx_dropped_inc(dev);
+			return NETDEV_TX_OK;
+		}
+	}
+#endif
 	free_size = bnxt_tx_avail(bp, txr);
 	if (unlikely(free_size < skb_shinfo(skb)->nr_frags + 2)) {
 		/* We must have raced with NAPI cleanup */
@@ -565,7 +579,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					TX_BD_FLAGS_LHINT_512_AND_SMALLER |
 					TX_BD_FLAGS_COAL_NOW |
 					TX_BD_FLAGS_PACKET_END |
-					(2 << TX_BD_FLAGS_BD_CNT_SHIFT));
+					TX_BD_CNT(2));
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			tx_push1->tx_bd_hsize_lflags =
@@ -640,7 +654,7 @@ normal_tx:
 
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
 	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
-		((last_frag + 2) << TX_BD_FLAGS_BD_CNT_SHIFT);
+		TX_BD_CNT(last_frag + 2);
 
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
 	txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 2 + last_frag);
@@ -773,7 +787,7 @@ tx_free:
 	dev_kfree_skb_any(skb);
 tx_kick_pending:
 	if (BNXT_TX_PTP_IS_SET(lflags)) {
-		txr->tx_buf_ring[txr->tx_prod].is_ts_pkt = 0;
+		txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].is_ts_pkt = 0;
 		atomic64_inc(&bp->ptp_cfg->stats.ts_err);
 		if (!(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
 			/* set SKB to err so PTP worker will clean up */
@@ -781,7 +795,7 @@ tx_kick_pending:
 	}
 	if (txr->kick_pending)
 		bnxt_txr_db_kick(bp, txr, txr->tx_prod);
-	txr->tx_buf_ring[txr->tx_prod].skb = NULL;
+	txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].skb = NULL;
 	dev_core_stats_tx_dropped_inc(dev);
 	return NETDEV_TX_OK;
 }
@@ -879,9 +893,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 		bnapi->events &= ~BNXT_TX_CMP_EVENT;
 }
 
-static bool bnxt_separate_head_pool(void)
+static bool bnxt_separate_head_pool(struct bnxt_rx_ring_info *rxr)
 {
-	return PAGE_SIZE > BNXT_RX_PAGE_SIZE;
+	return rxr->need_head_pool || PAGE_SIZE > BNXT_RX_PAGE_SIZE;
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
@@ -905,6 +919,20 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 	return page;
 }
 
+static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping,
+					 struct bnxt_rx_ring_info *rxr,
+					 gfp_t gfp)
+{
+	netmem_ref netmem;
+
+	netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
+	if (!netmem)
+		return 0;
+
+	*mapping = page_pool_get_dma_addr_netmem(netmem);
+	return netmem;
+}
+
 static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping,
 				       struct bnxt_rx_ring_info *rxr,
 				       gfp_t gfp)
@@ -985,21 +1013,19 @@ static inline u16 bnxt_find_next_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx)
 	return next;
 }
 
-static inline int bnxt_alloc_rx_page(struct bnxt *bp,
-				     struct bnxt_rx_ring_info *rxr,
-				     u16 prod, gfp_t gfp)
+static int bnxt_alloc_rx_netmem(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
+				u16 prod, gfp_t gfp)
 {
 	struct rx_bd *rxbd =
 		&rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
 	struct bnxt_sw_rx_agg_bd *rx_agg_buf;
-	struct page *page;
-	dma_addr_t mapping;
 	u16 sw_prod = rxr->rx_sw_agg_prod;
 	unsigned int offset = 0;
+	dma_addr_t mapping;
+	netmem_ref netmem;
 
-	page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
-
-	if (!page)
+	netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, gfp);
+	if (!netmem)
 		return -ENOMEM;
 
 	if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
@@ -1009,7 +1035,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 	rx_agg_buf = &rxr->rx_agg_ring[sw_prod];
 	rxr->rx_sw_agg_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
 
-	rx_agg_buf->page = page;
+	rx_agg_buf->netmem = netmem;
 	rx_agg_buf->offset = offset;
 	rx_agg_buf->mapping = mapping;
 	rxbd->rx_bd_haddr = cpu_to_le64(mapping);
@@ -1053,11 +1079,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 		p5_tpa = true;
 
 	for (i = 0; i < agg_bufs; i++) {
-		u16 cons;
-		struct rx_agg_cmp *agg;
 		struct bnxt_sw_rx_agg_bd *cons_rx_buf, *prod_rx_buf;
+		struct rx_agg_cmp *agg;
 		struct rx_bd *prod_bd;
-		struct page *page;
+		netmem_ref netmem;
+		u16 cons;
 
 		if (p5_tpa)
 			agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, start + i);
@@ -1074,11 +1100,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 		cons_rx_buf = &rxr->rx_agg_ring[cons];
 
 		/* It is possible for sw_prod to be equal to cons, so
-		 * set cons_rx_buf->page to NULL first.
+		 * set cons_rx_buf->netmem to 0 first.
 		 */
-		page = cons_rx_buf->page;
-		cons_rx_buf->page = NULL;
-		prod_rx_buf->page = page;
+		netmem = cons_rx_buf->netmem;
+		cons_rx_buf->netmem = 0;
+		prod_rx_buf->netmem = netmem;
 		prod_rx_buf->offset = cons_rx_buf->offset;
 
 		prod_rx_buf->mapping = cons_rx_buf->mapping;
@@ -1204,29 +1230,35 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
 	return skb;
 }
 
-static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
-			       struct bnxt_cp_ring_info *cpr,
-			       struct skb_shared_info *shinfo,
-			       u16 idx, u32 agg_bufs, bool tpa,
-			       struct xdp_buff *xdp)
+static u32 __bnxt_rx_agg_netmems(struct bnxt *bp,
+				 struct bnxt_cp_ring_info *cpr,
+				 u16 idx, u32 agg_bufs, bool tpa,
+				 struct sk_buff *skb,
+				 struct xdp_buff *xdp)
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
-	struct pci_dev *pdev = bp->pdev;
-	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
-	u16 prod = rxr->rx_agg_prod;
+	struct skb_shared_info *shinfo;
+	struct bnxt_rx_ring_info *rxr;
 	u32 i, total_frag_len = 0;
 	bool p5_tpa = false;
+	u16 prod;
+
+	rxr = bnapi->rx_ring;
+	prod = rxr->rx_agg_prod;
 
 	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
 		p5_tpa = true;
 
+	if (skb)
+		shinfo = skb_shinfo(skb);
+	else
+		shinfo = xdp_get_shared_info_from_buff(xdp);
+
 	for (i = 0; i < agg_bufs; i++) {
-		skb_frag_t *frag = &shinfo->frags[i];
-		u16 cons, frag_len;
-		struct rx_agg_cmp *agg;
 		struct bnxt_sw_rx_agg_bd *cons_rx_buf;
-		struct page *page;
-		dma_addr_t mapping;
+		struct rx_agg_cmp *agg;
+		u16 cons, frag_len;
+		netmem_ref netmem;
 
 		if (p5_tpa)
 			agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, i);
@@ -1237,27 +1269,41 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 			    RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT;
 
 		cons_rx_buf = &rxr->rx_agg_ring[cons];
-		skb_frag_fill_page_desc(frag, cons_rx_buf->page,
-					cons_rx_buf->offset, frag_len);
-		shinfo->nr_frags = i + 1;
+		if (skb) {
+			skb_add_rx_frag_netmem(skb, i, cons_rx_buf->netmem,
+					       cons_rx_buf->offset,
+					       frag_len, BNXT_RX_PAGE_SIZE);
+		} else {
+			skb_frag_t *frag = &shinfo->frags[i];
+
+			skb_frag_fill_netmem_desc(frag, cons_rx_buf->netmem,
+						  cons_rx_buf->offset,
+						  frag_len);
+			shinfo->nr_frags = i + 1;
+		}
 		__clear_bit(cons, rxr->rx_agg_bmap);
 
-		/* It is possible for bnxt_alloc_rx_page() to allocate
+		/* It is possible for bnxt_alloc_rx_netmem() to allocate
 		 * a sw_prod index that equals the cons index, so we
 		 * need to clear the cons entry now.
 		 */
-		mapping = cons_rx_buf->mapping;
-		page = cons_rx_buf->page;
-		cons_rx_buf->page = NULL;
+		netmem = cons_rx_buf->netmem;
+		cons_rx_buf->netmem = 0;
 
-		if (xdp && page_is_pfmemalloc(page))
+		if (xdp && netmem_is_pfmemalloc(netmem))
 			xdp_buff_set_frag_pfmemalloc(xdp);
 
-		if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_ATOMIC) != 0) {
+		if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_ATOMIC) != 0) {
+			if (skb) {
+				skb->len -= frag_len;
+				skb->data_len -= frag_len;
+				skb->truesize -= BNXT_RX_PAGE_SIZE;
+			}
+
 			--shinfo->nr_frags;
-			cons_rx_buf->page = page;
+			cons_rx_buf->netmem = netmem;
 
-			/* Update prod since possibly some pages have been
+			/* Update prod since possibly some netmems have been
 			 * allocated already.
 			 */
 			rxr->rx_agg_prod = prod;
@@ -1265,8 +1311,8 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 			return 0;
 		}
 
-		dma_sync_single_for_cpu(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
-					bp->rx_dir);
+		page_pool_dma_sync_netmem_for_cpu(rxr->page_pool, netmem, 0,
+						  BNXT_RX_PAGE_SIZE);
 
 		total_frag_len += frag_len;
 		prod = NEXT_RX_AGG(prod);
@@ -1275,32 +1321,28 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 	return total_frag_len;
 }
 
-static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
-					     struct bnxt_cp_ring_info *cpr,
-					     struct sk_buff *skb, u16 idx,
-					     u32 agg_bufs, bool tpa)
+static struct sk_buff *bnxt_rx_agg_netmems_skb(struct bnxt *bp,
+					       struct bnxt_cp_ring_info *cpr,
+					       struct sk_buff *skb, u16 idx,
+					       u32 agg_bufs, bool tpa)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	u32 total_frag_len = 0;
 
-	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx,
-					     agg_bufs, tpa, NULL);
+	total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
+					       skb, NULL);
 	if (!total_frag_len) {
 		skb_mark_for_recycle(skb);
 		dev_kfree_skb(skb);
 		return NULL;
 	}
 
-	skb->data_len += total_frag_len;
-	skb->len += total_frag_len;
-	skb->truesize += BNXT_RX_PAGE_SIZE * agg_bufs;
 	return skb;
 }
 
-static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
-				 struct bnxt_cp_ring_info *cpr,
-				 struct xdp_buff *xdp, u16 idx,
-				 u32 agg_bufs, bool tpa)
+static u32 bnxt_rx_agg_netmems_xdp(struct bnxt *bp,
+				   struct bnxt_cp_ring_info *cpr,
+				   struct xdp_buff *xdp, u16 idx,
+				   u32 agg_bufs, bool tpa)
 {
 	struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp);
 	u32 total_frag_len = 0;
@@ -1308,8 +1350,8 @@ static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
 	if (!xdp_buff_has_frags(xdp))
 		shinfo->nr_frags = 0;
 
-	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo,
-					     idx, agg_bufs, tpa, xdp);
+	total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
+					       NULL, xdp);
 	if (total_frag_len) {
 		xdp_buff_set_frags_flag(xdp);
 		shinfo->nr_frags = agg_bufs;
@@ -1343,13 +1385,13 @@ static struct sk_buff *bnxt_copy_data(struct bnxt_napi *bnapi, u8 *data,
 	if (!skb)
 		return NULL;
 
-	dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copy_thresh,
+	dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copybreak,
 				bp->rx_dir);
 
 	memcpy(skb->data - NET_IP_ALIGN, data - NET_IP_ALIGN,
 	       len + NET_IP_ALIGN);
 
-	dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copy_thresh,
+	dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copybreak,
 				   bp->rx_dir);
 
 	skb_put(skb, len);
@@ -1531,7 +1573,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		if (TPA_START_IS_IPV6(tpa_start1))
 			tpa_info->gso_type = SKB_GSO_TCPV6;
 		/* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */
-		else if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP &&
+		else if (!BNXT_CHIP_P4_PLUS(bp) &&
 			 TPA_START_HASH_TYPE(tpa_start) == 3)
 			tpa_info->gso_type = SKB_GSO_TCPV6;
 		tpa_info->rss_hash =
@@ -1842,7 +1884,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		return NULL;
 	}
 
-	if (len <= bp->rx_copy_thresh) {
+	if (len <= bp->rx_copybreak) {
 		skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping);
 		if (!skb) {
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
@@ -1881,7 +1923,8 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 	}
 
 	if (agg_bufs) {
-		skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true);
+		skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, idx, agg_bufs,
+					      true);
 		if (!skb) {
 			/* Page reuse already handled by bnxt_rx_pages(). */
 			cpr->sw_stats->rx.rx_oom_discards += 1;
@@ -2001,6 +2044,7 @@ static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
 	}
 	return skb;
 vlan_err:
+	skb_mark_for_recycle(skb);
 	dev_kfree_skb(skb);
 	return NULL;
 }
@@ -2039,6 +2083,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct rx_cmp_ext *rxcmp1;
 	u32 tmp_raw_cons = *raw_cons;
 	u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
+	struct skb_shared_info *sinfo;
 	struct bnxt_sw_rx_bd *rx_buf;
 	unsigned int len;
 	u8 *data_ptr, agg_bufs, cmp_type;
@@ -2160,11 +2205,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	if (bnxt_xdp_attached(bp, rxr)) {
 		bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
 		if (agg_bufs) {
-			u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
-							     cp_cons, agg_bufs,
-							     false);
+			u32 frag_len = bnxt_rx_agg_netmems_xdp(bp, cpr, &xdp,
+							       cp_cons,
+							       agg_bufs,
+							       false);
 			if (!frag_len)
 				goto oom_next_rx;
+
 		}
 		xdp_active = true;
 	}
@@ -2174,9 +2221,15 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			rc = 1;
 			goto next_rx;
 		}
+		if (xdp_buff_has_frags(&xdp)) {
+			sinfo = xdp_get_shared_info_from_buff(&xdp);
+			agg_bufs = sinfo->nr_frags;
+		} else {
+			agg_bufs = 0;
+		}
 	}
 
-	if (len <= bp->rx_copy_thresh) {
+	if (len <= bp->rx_copybreak) {
 		if (!xdp_active)
 			skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr);
 		else
@@ -2207,11 +2260,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 	if (agg_bufs) {
 		if (!xdp_active) {
-			skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false);
+			skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, cp_cons,
+						      agg_bufs, false);
 			if (!skb)
 				goto oom_next_rx;
 		} else {
-			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1);
+			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs,
+						 rxr->page_pool, &xdp);
 			if (!skb) {
 				/* we should be able to free the old skb here */
 				bnxt_xdp_buff_frags_free(rxr, &xdp);
@@ -2226,15 +2281,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) {
 			type = bnxt_rss_ext_op(bp, rxcmp);
 		} else {
-			u32 hash_type = RX_CMP_HASH_TYPE(rxcmp);
+			u32 itypes = RX_CMP_ITYPES(rxcmp);
 
-			/* RSS profiles 1 and 3 with extract code 0 for inner
-			 * 4-tuple
-			 */
-			if (hash_type != 1 && hash_type != 3)
-				type = PKT_HASH_TYPE_L3;
-			else
+			if (itypes == RX_CMP_FLAGS_ITYPE_TCP ||
+			    itypes == RX_CMP_FLAGS_ITYPE_UDP)
 				type = PKT_HASH_TYPE_L4;
+			else
+				type = PKT_HASH_TYPE_L3;
 		}
 		skb_set_hash(skb, le32_to_cpu(rxcmp->rx_cmp_rss_hash), type);
 	}
@@ -2857,6 +2910,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 	}
 	__bnxt_queue_sp_work(bp);
 async_event_process_exit:
+	bnxt_ulp_async_events(bp, cmpl);
 	return 0;
 }
 
@@ -2899,6 +2953,13 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 	return 0;
 }
 
+static bool bnxt_vnic_is_active(struct bnxt *bp)
+{
+	struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
+
+	return vnic->fw_vnic_id != INVALID_HW_RING_ID && vnic->mru > 0;
+}
+
 static irqreturn_t bnxt_msix(int irq, void *dev_instance)
 {
 	struct bnxt_napi *bnapi = dev_instance;
@@ -2928,6 +2989,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	u32 raw_cons = cpr->cp_raw_cons;
+	bool flush_xdp = false;
 	u32 cons;
 	int rx_pkts = 0;
 	u8 event = 0;
@@ -2981,6 +3043,8 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			else
 				rc = bnxt_force_rx_discard(bp, cpr, &raw_cons,
 							   &event);
+			if (event & BNXT_REDIRECT_EVENT)
+				flush_xdp = true;
 			if (likely(rc >= 0))
 				rx_pkts += rc;
 			/* Increment rx_pkts when rc is -ENOMEM to count towards
@@ -3005,7 +3069,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
-	if (event & BNXT_REDIRECT_EVENT) {
+	if (flush_xdp) {
 		xdp_do_flush();
 		event &= ~BNXT_REDIRECT_EVENT;
 	}
@@ -3166,7 +3230,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 			break;
 		}
 	}
-	if (bp->flags & BNXT_FLAG_DIM) {
+	if ((bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) {
 		struct dim_sample dim_sample = {};
 
 		dim_update_sample(cpr->event_ctr,
@@ -3297,7 +3361,7 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 poll_done:
 	cpr_rx = &cpr->cp_ring_arr[0];
 	if (cpr_rx->cp_ring_type == BNXT_NQ_HDL_TYPE_RX &&
-	    (bp->flags & BNXT_FLAG_DIM)) {
+	    (bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) {
 		struct dim_sample dim_sample = {};
 
 		dim_update_sample(cpr->event_ctr,
@@ -3309,75 +3373,85 @@ poll_done:
 	return work_done;
 }
 
-static void bnxt_free_tx_skbs(struct bnxt *bp)
+static void bnxt_free_one_tx_ring_skbs(struct bnxt *bp,
+				       struct bnxt_tx_ring_info *txr, int idx)
 {
 	int i, max_idx;
 	struct pci_dev *pdev = bp->pdev;
 
-	if (!bp->tx_ring)
-		return;
-
 	max_idx = bp->tx_nr_pages * TX_DESC_CNT;
-	for (i = 0; i < bp->tx_nr_rings; i++) {
-		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		int j;
 
-		if (!txr->tx_buf_ring)
+	for (i = 0; i < max_idx;) {
+		struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[i];
+		struct sk_buff *skb;
+		int j, last;
+
+		if (idx  < bp->tx_nr_rings_xdp &&
+		    tx_buf->action == XDP_REDIRECT) {
+			dma_unmap_single(&pdev->dev,
+					 dma_unmap_addr(tx_buf, mapping),
+					 dma_unmap_len(tx_buf, len),
+					 DMA_TO_DEVICE);
+			xdp_return_frame(tx_buf->xdpf);
+			tx_buf->action = 0;
+			tx_buf->xdpf = NULL;
+			i++;
 			continue;
+		}
 
-		for (j = 0; j < max_idx;) {
-			struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j];
-			struct sk_buff *skb;
-			int k, last;
-
-			if (i < bp->tx_nr_rings_xdp &&
-			    tx_buf->action == XDP_REDIRECT) {
-				dma_unmap_single(&pdev->dev,
-					dma_unmap_addr(tx_buf, mapping),
-					dma_unmap_len(tx_buf, len),
-					DMA_TO_DEVICE);
-				xdp_return_frame(tx_buf->xdpf);
-				tx_buf->action = 0;
-				tx_buf->xdpf = NULL;
-				j++;
-				continue;
-			}
+		skb = tx_buf->skb;
+		if (!skb) {
+			i++;
+			continue;
+		}
 
-			skb = tx_buf->skb;
-			if (!skb) {
-				j++;
-				continue;
-			}
+		tx_buf->skb = NULL;
 
-			tx_buf->skb = NULL;
+		if (tx_buf->is_push) {
+			dev_kfree_skb(skb);
+			i += 2;
+			continue;
+		}
 
-			if (tx_buf->is_push) {
-				dev_kfree_skb(skb);
-				j += 2;
-				continue;
-			}
+		dma_unmap_single(&pdev->dev,
+				 dma_unmap_addr(tx_buf, mapping),
+				 skb_headlen(skb),
+				 DMA_TO_DEVICE);
 
-			dma_unmap_single(&pdev->dev,
-					 dma_unmap_addr(tx_buf, mapping),
-					 skb_headlen(skb),
-					 DMA_TO_DEVICE);
+		last = tx_buf->nr_frags;
+		i += 2;
+		for (j = 0; j < last; j++, i++) {
+			int ring_idx = i & bp->tx_ring_mask;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[j];
 
-			last = tx_buf->nr_frags;
-			j += 2;
-			for (k = 0; k < last; k++, j++) {
-				int ring_idx = j & bp->tx_ring_mask;
-				skb_frag_t *frag = &skb_shinfo(skb)->frags[k];
-
-				tx_buf = &txr->tx_buf_ring[ring_idx];
-				dma_unmap_page(
-					&pdev->dev,
-					dma_unmap_addr(tx_buf, mapping),
-					skb_frag_size(frag), DMA_TO_DEVICE);
-			}
-			dev_kfree_skb(skb);
+			tx_buf = &txr->tx_buf_ring[ring_idx];
+			dma_unmap_page(&pdev->dev,
+				       dma_unmap_addr(tx_buf, mapping),
+				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
-		netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, i));
+		dev_kfree_skb(skb);
 	}
+	netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, idx));
+}
+
+static void bnxt_free_tx_skbs(struct bnxt *bp)
+{
+	int i;
+
+	if (!bp->tx_ring)
+		return;
+
+	for (i = 0; i < bp->tx_nr_rings; i++) {
+		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
+
+		if (!txr->tx_buf_ring)
+			continue;
+
+		bnxt_free_one_tx_ring_skbs(bp, txr, i);
+	}
+
+	if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
+		bnxt_ptp_free_txts_skbs(bp->ptp_cfg);
 }
 
 static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
@@ -3409,27 +3483,23 @@ static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info
 
 	for (i = 0; i < max_idx; i++) {
 		struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i];
-		struct page *page = rx_agg_buf->page;
+		netmem_ref netmem = rx_agg_buf->netmem;
 
-		if (!page)
+		if (!netmem)
 			continue;
 
-		rx_agg_buf->page = NULL;
+		rx_agg_buf->netmem = 0;
 		__clear_bit(i, rxr->rx_agg_bmap);
 
-		page_pool_recycle_direct(rxr->page_pool, page);
+		page_pool_recycle_direct_netmem(rxr->page_pool, netmem);
 	}
 }
 
-static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr)
+static void bnxt_free_one_tpa_info_data(struct bnxt *bp,
+					struct bnxt_rx_ring_info *rxr)
 {
-	struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr];
-	struct bnxt_tpa_idx_map *map;
 	int i;
 
-	if (!rxr->rx_tpa)
-		goto skip_rx_tpa_free;
-
 	for (i = 0; i < bp->max_tpa; i++) {
 		struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i];
 		u8 *data = tpa_info->data;
@@ -3440,6 +3510,17 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr)
 		tpa_info->data = NULL;
 		page_pool_free_va(rxr->head_pool, data, false);
 	}
+}
+
+static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp,
+				       struct bnxt_rx_ring_info *rxr)
+{
+	struct bnxt_tpa_idx_map *map;
+
+	if (!rxr->rx_tpa)
+		goto skip_rx_tpa_free;
+
+	bnxt_free_one_tpa_info_data(bp, rxr);
 
 skip_rx_tpa_free:
 	if (!rxr->rx_buf_ring)
@@ -3467,7 +3548,7 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
 		return;
 
 	for (i = 0; i < bp->rx_nr_rings; i++)
-		bnxt_free_one_rx_ring_skbs(bp, i);
+		bnxt_free_one_rx_ring_skbs(bp, &bp->rx_ring[i]);
 }
 
 static void bnxt_free_skbs(struct bnxt *bp)
@@ -3608,29 +3689,64 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 	return 0;
 }
 
+static void bnxt_free_one_tpa_info(struct bnxt *bp,
+				   struct bnxt_rx_ring_info *rxr)
+{
+	int i;
+
+	kfree(rxr->rx_tpa_idx_map);
+	rxr->rx_tpa_idx_map = NULL;
+	if (rxr->rx_tpa) {
+		for (i = 0; i < bp->max_tpa; i++) {
+			kfree(rxr->rx_tpa[i].agg_arr);
+			rxr->rx_tpa[i].agg_arr = NULL;
+		}
+	}
+	kfree(rxr->rx_tpa);
+	rxr->rx_tpa = NULL;
+}
+
 static void bnxt_free_tpa_info(struct bnxt *bp)
 {
-	int i, j;
+	int i;
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 
-		kfree(rxr->rx_tpa_idx_map);
-		rxr->rx_tpa_idx_map = NULL;
-		if (rxr->rx_tpa) {
-			for (j = 0; j < bp->max_tpa; j++) {
-				kfree(rxr->rx_tpa[j].agg_arr);
-				rxr->rx_tpa[j].agg_arr = NULL;
-			}
-		}
-		kfree(rxr->rx_tpa);
-		rxr->rx_tpa = NULL;
+		bnxt_free_one_tpa_info(bp, rxr);
 	}
 }
 
+static int bnxt_alloc_one_tpa_info(struct bnxt *bp,
+				   struct bnxt_rx_ring_info *rxr)
+{
+	struct rx_agg_cmp *agg;
+	int i;
+
+	rxr->rx_tpa = kcalloc(bp->max_tpa, sizeof(struct bnxt_tpa_info),
+			      GFP_KERNEL);
+	if (!rxr->rx_tpa)
+		return -ENOMEM;
+
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
+		return 0;
+	for (i = 0; i < bp->max_tpa; i++) {
+		agg = kcalloc(MAX_SKB_FRAGS, sizeof(*agg), GFP_KERNEL);
+		if (!agg)
+			return -ENOMEM;
+		rxr->rx_tpa[i].agg_arr = agg;
+	}
+	rxr->rx_tpa_idx_map = kzalloc(sizeof(*rxr->rx_tpa_idx_map),
+				      GFP_KERNEL);
+	if (!rxr->rx_tpa_idx_map)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int bnxt_alloc_tpa_info(struct bnxt *bp)
 {
-	int i, j;
+	int i, rc;
 
 	bp->max_tpa = MAX_TPA;
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
@@ -3641,25 +3757,10 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
-		struct rx_agg_cmp *agg;
 
-		rxr->rx_tpa = kcalloc(bp->max_tpa, sizeof(struct bnxt_tpa_info),
-				      GFP_KERNEL);
-		if (!rxr->rx_tpa)
-			return -ENOMEM;
-
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
-			continue;
-		for (j = 0; j < bp->max_tpa; j++) {
-			agg = kcalloc(MAX_SKB_FRAGS, sizeof(*agg), GFP_KERNEL);
-			if (!agg)
-				return -ENOMEM;
-			rxr->rx_tpa[j].agg_arr = agg;
-		}
-		rxr->rx_tpa_idx_map = kzalloc(sizeof(*rxr->rx_tpa_idx_map),
-					      GFP_KERNEL);
-		if (!rxr->rx_tpa_idx_map)
-			return -ENOMEM;
+		rc = bnxt_alloc_one_tpa_info(bp, rxr);
+		if (rc)
+			return rc;
 	}
 	return 0;
 }
@@ -3683,7 +3784,7 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 			xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 		page_pool_destroy(rxr->page_pool);
-		if (rxr->page_pool != rxr->head_pool)
+		if (bnxt_separate_head_pool(rxr))
 			page_pool_destroy(rxr->head_pool);
 		rxr->page_pool = rxr->head_pool = NULL;
 
@@ -3714,15 +3815,19 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 	pp.dev = &bp->pdev->dev;
 	pp.dma_dir = bp->rx_dir;
 	pp.max_len = PAGE_SIZE;
-	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV |
+		   PP_FLAG_ALLOW_UNREADABLE_NETMEM;
+	pp.queue_idx = rxr->bnapi->index;
 
 	pool = page_pool_create(&pp);
 	if (IS_ERR(pool))
 		return PTR_ERR(pool);
 	rxr->page_pool = pool;
 
-	if (bnxt_separate_head_pool()) {
+	rxr->need_head_pool = page_pool_is_unreadable(pool);
+	if (bnxt_separate_head_pool(rxr)) {
 		pp.pool_size = max(bp->rx_ring_size, 1024);
+		pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
 		pool = page_pool_create(&pp);
 		if (IS_ERR(pool))
 			goto err_destroy_pp;
@@ -3737,6 +3842,19 @@ err_destroy_pp:
 	return PTR_ERR(pool);
 }
 
+static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
+{
+	u16 mem_size;
+
+	rxr->rx_agg_bmap_size = bp->rx_agg_ring_mask + 1;
+	mem_size = rxr->rx_agg_bmap_size / 8;
+	rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL);
+	if (!rxr->rx_agg_bmap)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int bnxt_alloc_rx_rings(struct bnxt *bp)
 {
 	int numa_node = dev_to_node(&bp->pdev->dev);
@@ -3781,19 +3899,15 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 
 		ring->grp_idx = i;
 		if (agg_rings) {
-			u16 mem_size;
-
 			ring = &rxr->rx_agg_ring_struct;
 			rc = bnxt_alloc_ring(bp, &ring->ring_mem);
 			if (rc)
 				return rc;
 
 			ring->grp_idx = i;
-			rxr->rx_agg_bmap_size = bp->rx_agg_ring_mask + 1;
-			mem_size = rxr->rx_agg_bmap_size / 8;
-			rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL);
-			if (!rxr->rx_agg_bmap)
-				return -ENOMEM;
+			rc = bnxt_alloc_rx_agg_bmap(bp, rxr);
+			if (rc)
+				return rc;
 		}
 	}
 	if (bp->flags & BNXT_FLAG_TPA)
@@ -4125,6 +4239,8 @@ static void bnxt_reset_rx_ring_struct(struct bnxt *bp,
 
 	rxr->page_pool->p.napi = NULL;
 	rxr->page_pool = NULL;
+	rxr->head_pool->p.napi = NULL;
+	rxr->head_pool = NULL;
 	memset(&rxr->xdp_rxq, 0, sizeof(struct xdp_rxq_info));
 
 	ring = &rxr->rx_ring_struct;
@@ -4249,16 +4365,16 @@ static void bnxt_alloc_one_rx_ring_skb(struct bnxt *bp,
 	rxr->rx_prod = prod;
 }
 
-static void bnxt_alloc_one_rx_ring_page(struct bnxt *bp,
-					struct bnxt_rx_ring_info *rxr,
-					int ring_nr)
+static void bnxt_alloc_one_rx_ring_netmem(struct bnxt *bp,
+					  struct bnxt_rx_ring_info *rxr,
+					  int ring_nr)
 {
 	u32 prod;
 	int i;
 
 	prod = rxr->rx_agg_prod;
 	for (i = 0; i < bp->rx_agg_ring_size; i++) {
-		if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_KERNEL)) {
+		if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_KERNEL)) {
 			netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d pages only\n",
 				    ring_nr, i, bp->rx_ring_size);
 			break;
@@ -4268,32 +4384,43 @@ static void bnxt_alloc_one_rx_ring_page(struct bnxt *bp,
 	rxr->rx_agg_prod = prod;
 }
 
+static int bnxt_alloc_one_tpa_info_data(struct bnxt *bp,
+					struct bnxt_rx_ring_info *rxr)
+{
+	dma_addr_t mapping;
+	u8 *data;
+	int i;
+
+	for (i = 0; i < bp->max_tpa; i++) {
+		data = __bnxt_alloc_rx_frag(bp, &mapping, rxr,
+					    GFP_KERNEL);
+		if (!data)
+			return -ENOMEM;
+
+		rxr->rx_tpa[i].data = data;
+		rxr->rx_tpa[i].data_ptr = data + bp->rx_offset;
+		rxr->rx_tpa[i].mapping = mapping;
+	}
+
+	return 0;
+}
+
 static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr)
 {
 	struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr];
-	int i;
+	int rc;
 
 	bnxt_alloc_one_rx_ring_skb(bp, rxr, ring_nr);
 
 	if (!(bp->flags & BNXT_FLAG_AGG_RINGS))
 		return 0;
 
-	bnxt_alloc_one_rx_ring_page(bp, rxr, ring_nr);
+	bnxt_alloc_one_rx_ring_netmem(bp, rxr, ring_nr);
 
 	if (rxr->rx_tpa) {
-		dma_addr_t mapping;
-		u8 *data;
-
-		for (i = 0; i < bp->max_tpa; i++) {
-			data = __bnxt_alloc_rx_frag(bp, &mapping, rxr,
-						    GFP_KERNEL);
-			if (!data)
-				return -ENOMEM;
-
-			rxr->rx_tpa[i].data = data;
-			rxr->rx_tpa[i].data_ptr = data + bp->rx_offset;
-			rxr->rx_tpa[i].mapping = mapping;
-		}
+		rc = bnxt_alloc_one_tpa_info_data(bp, rxr);
+		if (rc)
+			return rc;
 	}
 	return 0;
 }
@@ -4556,6 +4683,17 @@ void bnxt_set_tpa_flags(struct bnxt *bp)
 		bp->flags |= BNXT_FLAG_GRO;
 }
 
+static void bnxt_init_ring_params(struct bnxt *bp)
+{
+	unsigned int rx_size;
+
+	bp->rx_copybreak = BNXT_DEFAULT_RX_COPYBREAK;
+	/* Try to fit 4 chunks into a 4k page */
+	rx_size = SZ_1K -
+		NET_SKB_PAD - SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	bp->dev->cfg->hds_thresh = max(BNXT_DEFAULT_RX_COPYBREAK, rx_size);
+}
+
 /* bp->rx_ring_size, bp->tx_ring_size, dev->mtu, BNXT_FLAG_{G|L}RO flags must
  * be set on entry.
  */
@@ -4570,12 +4708,11 @@ void bnxt_set_ring_params(struct bnxt *bp)
 	rx_space = rx_size + ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-	bp->rx_copy_thresh = BNXT_RX_COPY_THRESH;
 	ring_size = bp->rx_ring_size;
 	bp->rx_agg_ring_size = 0;
 	bp->rx_agg_nr_pages = 0;
 
-	if (bp->flags & BNXT_FLAG_TPA)
+	if (bp->flags & BNXT_FLAG_TPA || bp->flags & BNXT_FLAG_HDS)
 		agg_factor = min_t(u32, 4, 65536 / BNXT_RX_PAGE_SIZE);
 
 	bp->flags &= ~BNXT_FLAG_JUMBO;
@@ -4615,7 +4752,10 @@ void bnxt_set_ring_params(struct bnxt *bp)
 				  ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) -
 				  SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 		} else {
-			rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN);
+			rx_size = max3(BNXT_DEFAULT_RX_COPYBREAK,
+				       bp->rx_copybreak,
+				       bp->dev->cfg_pending->hds_thresh);
+			rx_size = SKB_DATA_ALIGN(rx_size + NET_IP_ALIGN);
 			rx_space = rx_size + NET_SKB_PAD +
 				SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 		}
@@ -4656,7 +4796,7 @@ void bnxt_set_ring_params(struct bnxt *bp)
 /* Changing allocation mode of RX rings.
  * TODO: Update when extending xdp_rxq_info to support allocation modes.
  */
-int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
+static void __bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 {
 	struct net_device *dev = bp->dev;
 
@@ -4677,15 +4817,30 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 			bp->rx_skb_func = bnxt_rx_page_skb;
 		}
 		bp->rx_dir = DMA_BIDIRECTIONAL;
-		/* Disable LRO or GRO_HW */
-		netdev_update_features(dev);
 	} else {
 		dev->max_mtu = bp->max_mtu;
 		bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE;
 		bp->rx_dir = DMA_FROM_DEVICE;
 		bp->rx_skb_func = bnxt_rx_skb;
 	}
-	return 0;
+}
+
+void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
+{
+	__bnxt_set_rx_skb_mode(bp, page_mode);
+
+	if (!page_mode) {
+		int rx, tx;
+
+		bnxt_get_max_rings(bp, &rx, &tx, true);
+		if (rx > 1) {
+			bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS;
+			bp->dev->hw_features |= NETIF_F_LRO;
+		}
+	}
+
+	/* Update LRO and GRO_HW availability */
+	netdev_update_features(bp->dev);
 }
 
 static void bnxt_free_vnic_attributes(struct bnxt *bp)
@@ -5156,8 +5311,10 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all)
 {
 	int i;
 
-	/* Under rtnl_lock and all our NAPIs have been disabled.  It's
-	 * safe to delete the hash table.
+	netdev_assert_locked(bp->dev);
+
+	/* Under netdev instance lock and all our NAPIs have been disabled.
+	 * It's safe to delete the hash table.
 	 */
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
 		struct hlist_head *head;
@@ -5485,6 +5642,8 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size,
 	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
 		flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT |
 			 FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT;
+	if (bp->fw_cap & BNXT_FW_CAP_NPAR_1_2)
+		flags |= FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT;
 	req->flags = cpu_to_le32(flags);
 	req->ver_maj_8b = DRV_VER_MAJ;
 	req->ver_min_8b = DRV_VER_MIN;
@@ -6512,6 +6671,7 @@ static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp)
 
 static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
+	u16 hds_thresh = (u16)bp->dev->cfg_pending->hds_thresh;
 	struct hwrm_vnic_plcmodes_cfg_input *req;
 	int rc;
 
@@ -6521,16 +6681,14 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 
 	req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT);
 	req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID);
+	req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size);
 
-	if (BNXT_RX_PAGE_MODE(bp)) {
-		req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size);
-	} else {
+	if (!BNXT_RX_PAGE_MODE(bp) && (bp->flags & BNXT_FLAG_AGG_RINGS)) {
 		req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
 					  VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
 		req->enables |=
 			cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
-		req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
-		req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
+		req->hds_threshold = cpu_to_le16(hds_thresh);
 	}
 	req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
 	return hwrm_req_send(bp, req);
@@ -6856,6 +7014,30 @@ static void bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 	hwrm_req_drop(bp, req);
 }
 
+static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type,
+				       struct hwrm_ring_alloc_input *req,
+				       struct bnxt_ring_struct *ring)
+{
+	struct bnxt_ring_grp_info *grp_info = &bp->grp_info[ring->grp_idx];
+	u32 enables = RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID |
+		      RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID;
+
+	if (ring_type == HWRM_RING_ALLOC_AGG) {
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
+		req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id);
+		req->rx_buf_size = cpu_to_le16(BNXT_RX_PAGE_SIZE);
+		enables |= RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID;
+	} else {
+		req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size);
+		if (NET_IP_ALIGN == 2)
+			req->flags =
+				cpu_to_le16(RING_ALLOC_REQ_FLAGS_RX_SOP_PAD);
+	}
+	req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
+	req->nq_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id);
+	req->enables |= cpu_to_le32(enables);
+}
+
 static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 				    struct bnxt_ring_struct *ring,
 				    u32 ring_type, u32 map_index)
@@ -6907,37 +7089,13 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 		break;
 	}
 	case HWRM_RING_ALLOC_RX:
-		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
-		req->length = cpu_to_le32(bp->rx_ring_mask + 1);
-		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			u16 flags = 0;
-
-			/* Association of rx ring with stats context */
-			grp_info = &bp->grp_info[ring->grp_idx];
-			req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size);
-			req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
-			req->enables |= cpu_to_le32(
-				RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID);
-			if (NET_IP_ALIGN == 2)
-				flags = RING_ALLOC_REQ_FLAGS_RX_SOP_PAD;
-			req->flags = cpu_to_le16(flags);
-		}
-		break;
 	case HWRM_RING_ALLOC_AGG:
-		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
-			/* Association of agg ring with rx ring */
-			grp_info = &bp->grp_info[ring->grp_idx];
-			req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id);
-			req->rx_buf_size = cpu_to_le16(BNXT_RX_PAGE_SIZE);
-			req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
-			req->enables |= cpu_to_le32(
-				RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID |
-				RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID);
-		} else {
-			req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
-		}
-		req->length = cpu_to_le32(bp->rx_agg_ring_mask + 1);
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
+		req->length = (ring_type == HWRM_RING_ALLOC_RX) ?
+			      cpu_to_le32(bp->rx_ring_mask + 1) :
+			      cpu_to_le32(bp->rx_agg_ring_mask + 1);
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+			bnxt_set_rx_ring_params_p5(bp, ring_type, req, ring);
 		break;
 	case HWRM_RING_ALLOC_CMPL:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
@@ -7118,6 +7276,39 @@ static int bnxt_hwrm_rx_agg_ring_alloc(struct bnxt *bp,
 	return 0;
 }
 
+static int bnxt_hwrm_cp_ring_alloc_p5(struct bnxt *bp,
+				      struct bnxt_cp_ring_info *cpr)
+{
+	const u32 type = HWRM_RING_ALLOC_CMPL;
+	struct bnxt_napi *bnapi = cpr->bnapi;
+	struct bnxt_ring_struct *ring;
+	u32 map_idx = bnapi->index;
+	int rc;
+
+	ring = &cpr->cp_ring_struct;
+	ring->handle = BNXT_SET_NQ_HDL(cpr);
+	rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+	if (rc)
+		return rc;
+	bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id);
+	bnxt_db_cq(bp, &cpr->cp_db, cpr->cp_raw_cons);
+	return 0;
+}
+
+static int bnxt_hwrm_tx_ring_alloc(struct bnxt *bp,
+				   struct bnxt_tx_ring_info *txr, u32 tx_idx)
+{
+	struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
+	const u32 type = HWRM_RING_ALLOC_TX;
+	int rc;
+
+	rc = hwrm_ring_alloc_send_msg(bp, ring, type, tx_idx);
+	if (rc)
+		return rc;
+	bnxt_set_db(bp, &txr->tx_db, type, tx_idx, ring->fw_ring_id);
+	return 0;
+}
+
 static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 {
 	bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS);
@@ -7154,33 +7345,17 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		}
 	}
 
-	type = HWRM_RING_ALLOC_TX;
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		struct bnxt_ring_struct *ring;
-		u32 map_idx;
 
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			struct bnxt_cp_ring_info *cpr2 = txr->tx_cpr;
-			struct bnxt_napi *bnapi = txr->bnapi;
-			u32 type2 = HWRM_RING_ALLOC_CMPL;
-
-			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_SET_NQ_HDL(cpr2);
-			map_idx = bnapi->index;
-			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
+			rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr);
 			if (rc)
 				goto err_out;
-			bnxt_set_db(bp, &cpr2->cp_db, type2, map_idx,
-				    ring->fw_ring_id);
-			bnxt_db_cq(bp, &cpr2->cp_db, cpr2->cp_raw_cons);
 		}
-		ring = &txr->tx_ring_struct;
-		map_idx = i;
-		rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+		rc = bnxt_hwrm_tx_ring_alloc(bp, txr, i);
 		if (rc)
 			goto err_out;
-		bnxt_set_db(bp, &txr->tx_db, type, map_idx, ring->fw_ring_id);
 	}
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
@@ -7193,20 +7368,9 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		if (!agg_rings)
 			bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			struct bnxt_cp_ring_info *cpr2 = rxr->rx_cpr;
-			struct bnxt_napi *bnapi = rxr->bnapi;
-			u32 type2 = HWRM_RING_ALLOC_CMPL;
-			struct bnxt_ring_struct *ring;
-			u32 map_idx = bnapi->index;
-
-			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_SET_NQ_HDL(cpr2);
-			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
+			rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr);
 			if (rc)
 				goto err_out;
-			bnxt_set_db(bp, &cpr2->cp_db, type2, map_idx,
-				    ring->fw_ring_id);
-			bnxt_db_cq(bp, &cpr2->cp_db, cpr2->cp_raw_cons);
 		}
 	}
 
@@ -7221,6 +7385,26 @@ err_out:
 	return rc;
 }
 
+static void bnxt_cancel_dim(struct bnxt *bp)
+{
+	int i;
+
+	/* DIM work is initialized in bnxt_enable_napi().  Proceed only
+	 * if NAPI is enabled.
+	 */
+	if (!bp->bnapi || test_bit(BNXT_STATE_NAPI_DISABLED, &bp->state))
+		return;
+
+	/* Make sure NAPI sees that the VNIC is disabled */
+	synchronize_net();
+	for (i = 0; i < bp->rx_nr_rings; i++) {
+		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
+		struct bnxt_napi *bnapi = rxr->bnapi;
+
+		cancel_work_sync(&bnapi->cp_ring.dim.work);
+	}
+}
+
 static int hwrm_ring_free_send_msg(struct bnxt *bp,
 				   struct bnxt_ring_struct *ring,
 				   u32 ring_type, int cmpl_ring_id)
@@ -7254,6 +7438,23 @@ exit:
 	return 0;
 }
 
+static void bnxt_hwrm_tx_ring_free(struct bnxt *bp,
+				   struct bnxt_tx_ring_info *txr,
+				   bool close_path)
+{
+	struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
+	u32 cmpl_ring_id;
+
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	cmpl_ring_id = close_path ? bnxt_cp_ring_for_tx(bp, txr) :
+		       INVALID_HW_RING_ID;
+	hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_TX,
+				cmpl_ring_id);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
 static void bnxt_hwrm_rx_ring_free(struct bnxt *bp,
 				   struct bnxt_rx_ring_info *rxr,
 				   bool close_path)
@@ -7298,6 +7499,33 @@ static void bnxt_hwrm_rx_agg_ring_free(struct bnxt *bp,
 	bp->grp_info[grp_idx].agg_fw_ring_id = INVALID_HW_RING_ID;
 }
 
+static void bnxt_hwrm_cp_ring_free(struct bnxt *bp,
+				   struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_ring_struct *ring;
+
+	ring = &cpr->cp_ring_struct;
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_L2_CMPL,
+				INVALID_HW_RING_ID);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
+static void bnxt_clear_one_cp_ring(struct bnxt *bp, struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
+	int i, size = ring->ring_mem.page_size;
+
+	cpr->cp_raw_cons = 0;
+	cpr->toggle = 0;
+
+	for (i = 0; i < bp->cp_nr_pages; i++)
+		if (cpr->cp_desc_ring[i])
+			memset(cpr->cp_desc_ring[i], 0, size);
+}
+
 static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 {
 	u32 type;
@@ -7306,21 +7534,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	if (!bp->bnapi)
 		return;
 
-	for (i = 0; i < bp->tx_nr_rings; i++) {
-		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-
-		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
-			u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
-
-			hwrm_ring_free_send_msg(bp, ring,
-						RING_FREE_REQ_RING_TYPE_TX,
-						close_path ? cmpl_ring_id :
-						INVALID_HW_RING_ID);
-			ring->fw_ring_id = INVALID_HW_RING_ID;
-		}
-	}
+	for (i = 0; i < bp->tx_nr_rings; i++)
+		bnxt_hwrm_tx_ring_free(bp, &bp->tx_ring[i], close_path);
 
+	bnxt_cancel_dim(bp);
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		bnxt_hwrm_rx_ring_free(bp, &bp->rx_ring[i], close_path);
 		bnxt_hwrm_rx_agg_ring_free(bp, &bp->rx_ring[i], close_path);
@@ -7342,17 +7559,9 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_ring_struct *ring;
 		int j;
 
-		for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++) {
-			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
+		for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++)
+			bnxt_hwrm_cp_ring_free(bp, &cpr->cp_ring_arr[j]);
 
-			ring = &cpr2->cp_ring_struct;
-			if (ring->fw_ring_id == INVALID_HW_RING_ID)
-				continue;
-			hwrm_ring_free_send_msg(bp, ring,
-						RING_FREE_REQ_RING_TYPE_L2_CMPL,
-						INVALID_HW_RING_ID);
-			ring->fw_ring_id = INVALID_HW_RING_ID;
-		}
 		ring = &cpr->cp_ring_struct;
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
 			hwrm_ring_free_send_msg(bp, ring, type,
@@ -8234,16 +8443,20 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 	if (rc)
 		goto func_qcfg_exit;
 
+	flags = le16_to_cpu(resp->flags);
 #ifdef CONFIG_BNXT_SRIOV
 	if (BNXT_VF(bp)) {
 		struct bnxt_vf_info *vf = &bp->vf;
 
 		vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK;
+		if (flags & FUNC_QCFG_RESP_FLAGS_TRUSTED_VF)
+			vf->flags |= BNXT_VF_TRUST;
+		else
+			vf->flags &= ~BNXT_VF_TRUST;
 	} else {
 		bp->pf.registered_vfs = le16_to_cpu(resp->registered_vfs);
 	}
 #endif
-	flags = le16_to_cpu(resp->flags);
 	if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED |
 		     FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED)) {
 		bp->fw_cap |= BNXT_FW_CAP_LLDP_AGENT;
@@ -8261,6 +8474,7 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 
 	switch (resp->port_partition_type) {
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2:
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5:
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0:
 		bp->port_partition_type = resp->port_partition_type;
@@ -8320,7 +8534,7 @@ static int bnxt_alloc_all_ctx_pg_info(struct bnxt *bp, int ctx_max)
 		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
 		int n = 1;
 
-		if (!ctxm->max_entries)
+		if (!ctxm->max_entries || ctxm->pg_info)
 			continue;
 
 		if (ctxm->instance_bmap)
@@ -8924,8 +9138,8 @@ static int bnxt_backing_store_cfg_v2(struct bnxt *bp, u32 ena)
 				continue;
 			}
 			bnxt_bs_trace_init(bp, ctxm);
-			last_type = type;
 		}
+		last_type = type;
 	}
 
 	if (last_type == BNXT_CTX_INV) {
@@ -9072,10 +9286,18 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	ena = 0;
 	if ((bp->flags & BNXT_FLAG_ROCE_CAP) && !is_kdump_kernel()) {
 		pg_lvl = 2;
-		extra_qps = min_t(u32, 65536, max_qps - l2_qps - qp1_qps);
-		/* allocate extra qps if fw supports RoCE fast qp destroy feature */
-		extra_qps += fast_qpmd_qps;
-		extra_srqs = min_t(u32, 8192, max_srqs - srqs);
+		if (BNXT_SW_RES_LMT(bp)) {
+			extra_qps = max_qps - l2_qps - qp1_qps;
+			extra_srqs = max_srqs - srqs;
+		} else {
+			extra_qps = min_t(u32, 65536,
+					  max_qps - l2_qps - qp1_qps);
+			/* allocate extra qps if fw supports RoCE fast qp
+			 * destroy feature
+			 */
+			extra_qps += fast_qpmd_qps;
+			extra_srqs = min_t(u32, 8192, max_srqs - srqs);
+		}
 		if (fast_qpmd_qps)
 			ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD;
 	}
@@ -9111,14 +9333,20 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 		goto skip_rdma;
 
 	ctxm = &ctx->ctx_arr[BNXT_CTX_MRAV];
-	/* 128K extra is needed to accommodate static AH context
-	 * allocation by f/w.
-	 */
-	num_mr = min_t(u32, ctxm->max_entries / 2, 1024 * 256);
-	num_ah = min_t(u32, num_mr, 1024 * 128);
-	ctxm->split_entry_cnt = BNXT_CTX_MRAV_AV_SPLIT_ENTRY + 1;
-	if (!ctxm->mrav_av_entries || ctxm->mrav_av_entries > num_ah)
-		ctxm->mrav_av_entries = num_ah;
+	if (BNXT_SW_RES_LMT(bp) &&
+	    ctxm->split_entry_cnt == BNXT_CTX_MRAV_AV_SPLIT_ENTRY + 1) {
+		num_ah = ctxm->mrav_av_entries;
+		num_mr = ctxm->max_entries - num_ah;
+	} else {
+		/* 128K extra is needed to accommodate static AH context
+		 * allocation by f/w.
+		 */
+		num_mr = min_t(u32, ctxm->max_entries / 2, 1024 * 256);
+		num_ah = min_t(u32, num_mr, 1024 * 128);
+		ctxm->split_entry_cnt = BNXT_CTX_MRAV_AV_SPLIT_ENTRY + 1;
+		if (!ctxm->mrav_av_entries || ctxm->mrav_av_entries > num_ah)
+			ctxm->mrav_av_entries = num_ah;
+	}
 
 	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, num_mr + num_ah, 2);
 	if (rc)
@@ -9411,6 +9639,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_LIVEPATCH;
+	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_NPAR_1_2;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_DFLT_VLAN_TPID_PCP;
 	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED)
@@ -9425,6 +9655,9 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->flags |= BNXT_FLAG_UDP_GSO_CAP;
 	if (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_TX_TS_CMP;
+	if (flags_ext2 &
+	    FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS;
 	if (BNXT_PF(bp) &&
 	    (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_ROCE_VF_RESC_MGMT_SUPPORTED;
@@ -9884,7 +10117,7 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	struct hwrm_ver_get_input *req;
 	u16 fw_maj, fw_min, fw_bld, fw_rsv;
 	u32 dev_caps_cfg, hwrm_ver;
-	int rc, len;
+	int rc, len, max_tmo_secs;
 
 	rc = hwrm_req_init(bp, req, HWRM_VER_GET);
 	if (rc)
@@ -9957,9 +10190,14 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	bp->hwrm_cmd_max_timeout = le16_to_cpu(resp->max_req_timeout) * 1000;
 	if (!bp->hwrm_cmd_max_timeout)
 		bp->hwrm_cmd_max_timeout = HWRM_CMD_MAX_TIMEOUT;
-	else if (bp->hwrm_cmd_max_timeout > HWRM_CMD_MAX_TIMEOUT)
-		netdev_warn(bp->dev, "Device requests max timeout of %d seconds, may trigger hung task watchdog\n",
-			    bp->hwrm_cmd_max_timeout / 1000);
+	max_tmo_secs = bp->hwrm_cmd_max_timeout / 1000;
+#ifdef CONFIG_DETECT_HUNG_TASK
+	if (bp->hwrm_cmd_max_timeout > HWRM_CMD_MAX_TIMEOUT ||
+	    max_tmo_secs > CONFIG_DEFAULT_HUNG_TASK_TIMEOUT) {
+		netdev_warn(bp->dev, "Device requests max timeout of %d seconds, may trigger hung task watchdog (kernel default %ds)\n",
+			    max_tmo_secs, CONFIG_DEFAULT_HUNG_TASK_TIMEOUT);
+	}
+#endif
 
 	if (resp->hwrm_intf_maj_8b >= 1) {
 		bp->hwrm_max_req_len = le16_to_cpu(resp->max_req_win_len);
@@ -10545,6 +10783,72 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 	bp->num_rss_ctx--;
 }
 
+static bool bnxt_vnic_has_rx_ring(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				  int rxr_id)
+{
+	u16 tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+	int i, vnic_rx;
+
+	/* Ntuple VNIC always has all the rx rings. Any change of ring id
+	 * must be updated because a future filter may use it.
+	 */
+	if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
+		return true;
+
+	for (i = 0; i < tbl_size; i++) {
+		if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+			vnic_rx = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
+		else
+			vnic_rx = bp->rss_indir_tbl[i];
+
+		if (rxr_id == vnic_rx)
+			return true;
+	}
+
+	return false;
+}
+
+static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				u16 mru, int rxr_id)
+{
+	int rc;
+
+	if (!bnxt_vnic_has_rx_ring(bp, vnic, rxr_id))
+		return 0;
+
+	if (mru) {
+		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+				   vnic->vnic_id, rc);
+			return rc;
+		}
+	}
+	vnic->mru = mru;
+	bnxt_hwrm_vnic_update(bp, vnic,
+			      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+	return 0;
+}
+
+static int bnxt_set_rss_ctx_vnic_mru(struct bnxt *bp, u16 mru, int rxr_id)
+{
+	struct ethtool_rxfh_context *ctx;
+	unsigned long context;
+	int rc;
+
+	xa_for_each(&bp->dev->ethtool->rss_ctx, context, ctx) {
+		struct bnxt_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx);
+		struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, rxr_id);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
 {
 	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
@@ -11116,6 +11420,155 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 	return 0;
 }
 
+static void bnxt_tx_queue_stop(struct bnxt *bp, int idx)
+{
+	struct bnxt_tx_ring_info *txr;
+	struct netdev_queue *txq;
+	struct bnxt_napi *bnapi;
+	int i;
+
+	bnapi = bp->bnapi[idx];
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		WRITE_ONCE(txr->dev_state, BNXT_DEV_STATE_CLOSING);
+		synchronize_net();
+
+		if (!(bnapi->flags & BNXT_NAPI_FLAG_XDP)) {
+			txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
+			if (txq) {
+				__netif_tx_lock_bh(txq);
+				netif_tx_stop_queue(txq);
+				__netif_tx_unlock_bh(txq);
+			}
+		}
+
+		if (!bp->tph_mode)
+			continue;
+
+		bnxt_hwrm_tx_ring_free(bp, txr, true);
+		bnxt_hwrm_cp_ring_free(bp, txr->tx_cpr);
+		bnxt_free_one_tx_ring_skbs(bp, txr, txr->txq_index);
+		bnxt_clear_one_cp_ring(bp, txr->tx_cpr);
+	}
+}
+
+static int bnxt_tx_queue_start(struct bnxt *bp, int idx)
+{
+	struct bnxt_tx_ring_info *txr;
+	struct netdev_queue *txq;
+	struct bnxt_napi *bnapi;
+	int rc, i;
+
+	bnapi = bp->bnapi[idx];
+	/* All rings have been reserved and previously allocated.
+	 * Reallocating with the same parameters should never fail.
+	 */
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		if (!bp->tph_mode)
+			goto start_tx;
+
+		rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr);
+		if (rc)
+			return rc;
+
+		rc = bnxt_hwrm_tx_ring_alloc(bp, txr, false);
+		if (rc)
+			return rc;
+
+		txr->tx_prod = 0;
+		txr->tx_cons = 0;
+		txr->tx_hw_cons = 0;
+start_tx:
+		WRITE_ONCE(txr->dev_state, 0);
+		synchronize_net();
+
+		if (bnapi->flags & BNXT_NAPI_FLAG_XDP)
+			continue;
+
+		txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
+		if (txq)
+			netif_tx_start_queue(txq);
+	}
+
+	return 0;
+}
+
+static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify,
+				     const cpumask_t *mask)
+{
+	struct bnxt_irq *irq;
+	u16 tag;
+	int err;
+
+	irq = container_of(notify, struct bnxt_irq, affinity_notify);
+
+	if (!irq->bp->tph_mode)
+		return;
+
+	cpumask_copy(irq->cpu_mask, mask);
+
+	if (irq->ring_nr >= irq->bp->rx_nr_rings)
+		return;
+
+	if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM,
+				cpumask_first(irq->cpu_mask), &tag))
+		return;
+
+	if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag))
+		return;
+
+	netdev_lock(irq->bp->dev);
+	if (netif_running(irq->bp->dev)) {
+		err = netdev_rx_queue_restart(irq->bp->dev, irq->ring_nr);
+		if (err)
+			netdev_err(irq->bp->dev,
+				   "RX queue restart failed: err=%d\n", err);
+	}
+	netdev_unlock(irq->bp->dev);
+}
+
+static void bnxt_irq_affinity_release(struct kref *ref)
+{
+	struct irq_affinity_notify *notify =
+		container_of(ref, struct irq_affinity_notify, kref);
+	struct bnxt_irq *irq;
+
+	irq = container_of(notify, struct bnxt_irq, affinity_notify);
+
+	if (!irq->bp->tph_mode)
+		return;
+
+	if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, 0)) {
+		netdev_err(irq->bp->dev,
+			   "Setting ST=0 for MSIX entry %d failed\n",
+			   irq->msix_nr);
+		return;
+	}
+}
+
+static void bnxt_release_irq_notifier(struct bnxt_irq *irq)
+{
+	irq_set_affinity_notifier(irq->vector, NULL);
+}
+
+static void bnxt_register_irq_notifier(struct bnxt *bp, struct bnxt_irq *irq)
+{
+	struct irq_affinity_notify *notify;
+
+	irq->bp = bp;
+
+	/* Nothing to do if TPH is not enabled */
+	if (!bp->tph_mode)
+		return;
+
+	/* Register IRQ affinity notifier */
+	notify = &irq->affinity_notify;
+	notify->irq = irq->vector;
+	notify->notify = bnxt_irq_affinity_notify;
+	notify->release = bnxt_irq_affinity_release;
+
+	irq_set_affinity_notifier(irq->vector, notify);
+}
+
 static void bnxt_free_irq(struct bnxt *bp)
 {
 	struct bnxt_irq *irq;
@@ -11138,11 +11591,18 @@ static void bnxt_free_irq(struct bnxt *bp)
 				free_cpumask_var(irq->cpu_mask);
 				irq->have_cpumask = 0;
 			}
+
+			bnxt_release_irq_notifier(irq);
+
 			free_irq(irq->vector, bp->bnapi[i]);
 		}
 
 		irq->requested = 0;
 	}
+
+	/* Disable TPH support */
+	pcie_disable_tph(bp->pdev);
+	bp->tph_mode = 0;
 }
 
 static int bnxt_request_irq(struct bnxt *bp)
@@ -11162,6 +11622,12 @@ static int bnxt_request_irq(struct bnxt *bp)
 #ifdef CONFIG_RFS_ACCEL
 	rmap = bp->dev->rx_cpu_rmap;
 #endif
+
+	/* Enable TPH support as part of IRQ request */
+	rc = pcie_enable_tph(bp->pdev, PCI_TPH_ST_IV_MODE);
+	if (!rc)
+		bp->tph_mode = PCI_TPH_ST_IV_MODE;
+
 	for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
@@ -11180,13 +11646,16 @@ static int bnxt_request_irq(struct bnxt *bp)
 		if (rc)
 			break;
 
-		netif_napi_set_irq(&bp->bnapi[i]->napi, irq->vector);
+		netif_napi_set_irq_locked(&bp->bnapi[i]->napi, irq->vector);
 		irq->requested = 1;
 
 		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
 			int numa_node = dev_to_node(&bp->pdev->dev);
+			u16 tag;
 
 			irq->have_cpumask = 1;
+			irq->msix_nr = map_idx;
+			irq->ring_nr = i;
 			cpumask_set_cpu(cpumask_local_spread(i, numa_node),
 					irq->cpu_mask);
 			rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask);
@@ -11196,6 +11665,16 @@ static int bnxt_request_irq(struct bnxt *bp)
 					    irq->vector);
 				break;
 			}
+
+			bnxt_register_irq_notifier(bp, irq);
+
+			/* Init ST table entry */
+			if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM,
+						cpumask_first(irq->cpu_mask),
+						&tag))
+				continue;
+
+			pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag);
 		}
 	}
 	return rc;
@@ -11216,9 +11695,9 @@ static void bnxt_del_napi(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 
-		__netif_napi_del(&bnapi->napi);
+		__netif_napi_del_locked(&bnapi->napi);
 	}
-	/* We called __netif_napi_del(), we need
+	/* We called __netif_napi_del_locked(), we need
 	 * to respect an RCU grace period before freeing napi structures.
 	 */
 	synchronize_net();
@@ -11235,14 +11714,17 @@ static void bnxt_init_napi(struct bnxt *bp)
 		poll_fn = bnxt_poll_p5;
 	else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		cp_nr_rings--;
+
+	set_bit(BNXT_STATE_NAPI_DISABLED, &bp->state);
+
 	for (i = 0; i < cp_nr_rings; i++) {
 		bnapi = bp->bnapi[i];
-		netif_napi_add_config(bp->dev, &bnapi->napi, poll_fn,
-				      bnapi->index);
+		netif_napi_add_config_locked(bp->dev, &bnapi->napi, poll_fn,
+					     bnapi->index);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bnapi = bp->bnapi[cp_nr_rings];
-		netif_napi_add(bp->dev, &bnapi->napi, bnxt_poll_nitroa0);
+		netif_napi_add_locked(bp->dev, &bnapi->napi, bnxt_poll_nitroa0);
 	}
 }
 
@@ -11263,9 +11745,7 @@ static void bnxt_disable_napi(struct bnxt *bp)
 			cpr->sw_stats->tx.tx_resets++;
 		if (bnapi->in_reset)
 			cpr->sw_stats->rx.rx_resets++;
-		napi_disable(&bnapi->napi);
-		if (bnapi->rx_ring)
-			cancel_work_sync(&cpr->dim.work);
+		napi_disable_locked(&bnapi->napi);
 	}
 }
 
@@ -11287,7 +11767,7 @@ static void bnxt_enable_napi(struct bnxt *bp)
 			INIT_WORK(&cpr->dim.work, bnxt_dim_work);
 			cpr->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 		}
-		napi_enable(&bnapi->napi);
+		napi_enable_locked(&bnapi->napi);
 	}
 }
 
@@ -11485,6 +11965,26 @@ hwrm_phy_qcaps_exit:
 	return rc;
 }
 
+static void bnxt_hwrm_mac_qcaps(struct bnxt *bp)
+{
+	struct hwrm_port_mac_qcaps_output *resp;
+	struct hwrm_port_mac_qcaps_input *req;
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10a03)
+		return;
+
+	rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_QCAPS);
+	if (rc)
+		return;
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
+	if (!rc)
+		bp->mac_flags = resp->flags;
+	hwrm_req_drop(bp, req);
+}
+
 static bool bnxt_support_dropped(u16 advertising, u16 supported)
 {
 	u16 diff = advertising ^ supported;
@@ -11936,11 +12436,15 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 {
 	struct hwrm_func_drv_if_change_output *resp;
 	struct hwrm_func_drv_if_change_input *req;
-	bool fw_reset = !bp->irq_tbl;
 	bool resc_reinit = false;
+	bool caps_change = false;
 	int rc, retry = 0;
+	bool fw_reset;
 	u32 flags = 0;
 
+	fw_reset = (bp->fw_reset_state == BNXT_FW_RESET_STATE_ABORT);
+	bp->fw_reset_state = 0;
+
 	if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
 		return 0;
 
@@ -11993,8 +12497,11 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 		return -ENODEV;
 	}
-	if (resc_reinit || fw_reset) {
-		if (fw_reset) {
+	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE)
+		caps_change = true;
+
+	if (resc_reinit || fw_reset || caps_change) {
+		if (fw_reset || caps_change) {
 			set_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 				bnxt_ulp_irq_stop(bp);
@@ -12006,13 +12513,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 				set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 				return rc;
 			}
+			/* IRQ will be initialized later in bnxt_request_irq()*/
 			bnxt_clear_int_mode(bp);
-			rc = bnxt_init_int_mode(bp);
-			if (rc) {
-				clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
-				netdev_err(bp->dev, "init int mode failed\n");
-				return rc;
-			}
 		}
 		rc = bnxt_cancel_reservations(bp, fw_reset);
 	}
@@ -12411,8 +12913,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	/* VF-reps may need to be re-opened after the PF is re-opened */
 	if (BNXT_PF(bp))
 		bnxt_vf_reps_open(bp);
-	if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
-		WRITE_ONCE(bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
 	bnxt_ptp_init_rtc(bp, true);
 	bnxt_ptp_cfg_tstamp_filters(bp);
 	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
@@ -12430,7 +12930,6 @@ open_err_free_mem:
 	return rc;
 }
 
-/* rtnl_lock held */
 int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -12441,14 +12940,14 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		rc = __bnxt_open_nic(bp, irq_re_init, link_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "nic open fail (rc: %x)\n", rc);
-		dev_close(bp->dev);
+		netif_close(bp->dev);
 	}
 	return rc;
 }
 
-/* rtnl_lock held, open the NIC half way by allocating all resources, but
- * NAPI, IRQ, and TX are not enabled.  This is mainly used for offline
- * self tests.
+/* netdev instance lock held, open the NIC half way by allocating all
+ * resources, but NAPI, IRQ, and TX are not enabled.  This is mainly used
+ * for offline self tests.
  */
 int bnxt_half_open_nic(struct bnxt *bp)
 {
@@ -12479,12 +12978,12 @@ int bnxt_half_open_nic(struct bnxt *bp)
 half_open_err:
 	bnxt_free_skbs(bp);
 	bnxt_free_mem(bp, true);
-	dev_close(bp->dev);
+	netif_close(bp->dev);
 	return rc;
 }
 
-/* rtnl_lock held, this call can only be made after a previous successful
- * call to bnxt_half_open_nic().
+/* netdev instance lock held, this call can only be made after a previous
+ * successful call to bnxt_half_open_nic().
  */
 void bnxt_half_close_nic(struct bnxt *bp)
 {
@@ -12573,7 +13072,7 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 
 	bnxt_debug_dev_exit(bp);
 	bnxt_disable_napi(bp);
-	del_timer_sync(&bp->timer);
+	timer_delete_sync(&bp->timer);
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
@@ -12593,10 +13092,11 @@ void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		/* If we get here, it means firmware reset is in progress
 		 * while we are trying to close.  We can safely proceed with
-		 * the close because we are holding rtnl_lock().  Some firmware
-		 * messages may fail as we proceed to close.  We set the
-		 * ABORT_ERR flag here so that the FW reset thread will later
-		 * abort when it gets the rtnl_lock() and sees the flag.
+		 * the close because we are holding netdev instance lock.
+		 * Some firmware messages may fail as we proceed to close.
+		 * We set the ABORT_ERR flag here so that the FW reset thread
+		 * will later abort when it gets the netdev instance lock
+		 * and sees the flag.
 		 */
 		netdev_warn(bp->dev, "FW reset in progress during close, FW reset will be aborted\n");
 		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
@@ -12687,7 +13187,7 @@ static int bnxt_hwrm_port_phy_write(struct bnxt *bp, u16 phy_addr, u16 reg,
 	return hwrm_req_send(bp, req);
 }
 
-/* rtnl_lock held */
+/* netdev instance lock held */
 static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct mii_ioctl_data *mdio = if_mii(ifr);
@@ -13564,7 +14064,7 @@ fw_reset:
 
 static void bnxt_timer(struct timer_list *t)
 {
-	struct bnxt *bp = from_timer(bp, t, timer);
+	struct bnxt *bp = timer_container_of(bp, t, timer);
 	struct net_device *dev = bp->dev;
 
 	if (!netif_running(dev) || !test_bit(BNXT_STATE_OPEN, &bp->state))
@@ -13606,20 +14106,36 @@ bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
 
-static void bnxt_rtnl_lock_sp(struct bnxt *bp)
+static void bnxt_lock_sp(struct bnxt *bp)
 {
 	/* We are called from bnxt_sp_task which has BNXT_STATE_IN_SP_TASK
 	 * set.  If the device is being closed, bnxt_close() may be holding
-	 * rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear.  So we
-	 * must clear BNXT_STATE_IN_SP_TASK before holding rtnl().
+	 * netdev instance lock and waiting for BNXT_STATE_IN_SP_TASK to clear.
+	 * So we must clear BNXT_STATE_IN_SP_TASK before holding netdev
+	 * instance lock.
 	 */
 	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	netdev_lock(bp->dev);
+}
+
+static void bnxt_unlock_sp(struct bnxt *bp)
+{
+	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	netdev_unlock(bp->dev);
+}
+
+/* Same as bnxt_lock_sp() with additional rtnl_lock */
+static void bnxt_rtnl_lock_sp(struct bnxt *bp)
+{
+	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
 	rtnl_lock();
+	netdev_lock(bp->dev);
 }
 
 static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
 {
 	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	netdev_unlock(bp->dev);
 	rtnl_unlock();
 }
 
@@ -13663,7 +14179,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 			bnxt_reset_task(bp, true);
 			break;
 		}
-		bnxt_free_one_rx_ring_skbs(bp, i);
+		bnxt_free_one_rx_ring_skbs(bp, rxr);
 		rxr->rx_prod = 0;
 		rxr->rx_agg_prod = 0;
 		rxr->rx_sw_agg_prod = 0;
@@ -13734,7 +14250,7 @@ static bool is_bnxt_fw_ok(struct bnxt *bp)
 	return false;
 }
 
-/* rtnl_lock is acquired before calling this function */
+/* netdev instance lock is acquired before calling this function */
 static void bnxt_force_fw_reset(struct bnxt *bp)
 {
 	struct bnxt_fw_health *fw_health = bp->fw_health;
@@ -13777,9 +14293,9 @@ void bnxt_fw_exception(struct bnxt *bp)
 	netdev_warn(bp->dev, "Detected firmware fatal condition, initiating reset\n");
 	set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
 	bnxt_ulp_stop(bp);
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	bnxt_force_fw_reset(bp);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 /* Returns the number of registered VFs, or 1 if VF configuration is pending, or
@@ -13809,7 +14325,7 @@ static int bnxt_get_registered_vfs(struct bnxt *bp)
 void bnxt_fw_reset(struct bnxt *bp)
 {
 	bnxt_ulp_stop(bp);
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (test_bit(BNXT_STATE_OPEN, &bp->state) &&
 	    !test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
@@ -13832,7 +14348,7 @@ void bnxt_fw_reset(struct bnxt *bp)
 			netdev_err(bp->dev, "Firmware reset aborted, rc = %d\n",
 				   n);
 			clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-			dev_close(bp->dev);
+			netif_close(bp->dev);
 			goto fw_reset_exit;
 		} else if (n > 0) {
 			u16 vf_tmo_dsecs = n * 10;
@@ -13855,7 +14371,7 @@ void bnxt_fw_reset(struct bnxt *bp)
 		bnxt_queue_fw_reset_work(bp, tmo);
 	}
 fw_reset_exit:
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 static void bnxt_chk_missed_irq(struct bnxt *bp)
@@ -14054,7 +14570,7 @@ static void bnxt_sp_task(struct work_struct *work)
 static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 				int *max_cp);
 
-/* Under rtnl_lock */
+/* Under netdev instance lock */
 int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp)
 {
@@ -14446,8 +14962,8 @@ static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
 		bnxt_dl_health_fw_status_update(bp, false);
-	bp->fw_reset_state = 0;
-	dev_close(bp->dev);
+	bp->fw_reset_state = BNXT_FW_RESET_STATE_ABORT;
+	netif_close(bp->dev);
 }
 
 static void bnxt_fw_reset_task(struct work_struct *work)
@@ -14482,10 +14998,10 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			return;
 		}
 		bp->fw_reset_timestamp = jiffies;
-		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
 			bnxt_fw_reset_abort(bp, rc);
-			rtnl_unlock();
+			netdev_unlock(bp->dev);
 			goto ulp_start;
 		}
 		bnxt_fw_reset_close(bp);
@@ -14496,7 +15012,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
 			tmo = bp->fw_reset_min_dsecs * HZ / 10;
 		}
-		rtnl_unlock();
+		netdev_unlock(bp->dev);
 		bnxt_queue_fw_reset_work(bp, tmo);
 		return;
 	}
@@ -14574,10 +15090,12 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bnxt_queue_fw_reset_work(bp, HZ / 10);
 			return;
 		}
+		netdev_lock(bp->dev);
 		rc = bnxt_open(bp->dev);
 		if (rc) {
 			netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
 			bnxt_fw_reset_abort(bp, rc);
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			goto ulp_start;
 		}
@@ -14597,13 +15115,14 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bnxt_dl_health_fw_recovery_done(bp);
 			bnxt_dl_health_fw_status_update(bp, true);
 		}
+		netdev_unlock(bp->dev);
 		rtnl_unlock();
 		bnxt_ulp_start(bp, 0);
 		bnxt_reenable_sriov(bp);
-		rtnl_lock();
+		netdev_lock(bp->dev);
 		bnxt_vf_reps_alloc(bp);
 		bnxt_vf_reps_open(bp);
-		rtnl_unlock();
+		netdev_unlock(bp->dev);
 		break;
 	}
 	return;
@@ -14616,9 +15135,9 @@ fw_reset_abort_status:
 		netdev_err(bp->dev, "fw_health_status 0x%x\n", sts);
 	}
 fw_reset_abort:
-	rtnl_lock();
+	netdev_lock(bp->dev);
 	bnxt_fw_reset_abort(bp, rc);
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 ulp_start:
 	bnxt_ulp_start(bp, rc);
 }
@@ -14710,13 +15229,14 @@ init_err:
 	return rc;
 }
 
-/* rtnl_lock held */
 static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 {
 	struct sockaddr *addr = p;
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
+	netdev_assert_locked(dev);
+
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
@@ -14737,11 +15257,12 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 	return rc;
 }
 
-/* rtnl_lock held */
 static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
+	netdev_assert_locked(dev);
+
 	if (netif_running(dev))
 		bnxt_close_nic(bp, true, false);
 
@@ -15236,6 +15757,9 @@ static void bnxt_get_queue_stats_rx(struct net_device *dev, int i,
 	struct bnxt_cp_ring_info *cpr;
 	u64 *sw;
 
+	if (!bp->bnapi)
+		return;
+
 	cpr = &bp->bnapi[i]->cp_ring;
 	sw = cpr->stats.sw_stats;
 
@@ -15259,6 +15783,9 @@ static void bnxt_get_queue_stats_tx(struct net_device *dev, int i,
 	struct bnxt_napi *bnapi;
 	u64 *sw;
 
+	if (!bp->tx_ring)
+		return;
+
 	bnapi = bp->tx_ring[bp->tx_ring_map[i]].bnapi;
 	sw = bnapi->cp_ring.stats.sw_stats;
 
@@ -15293,19 +15820,6 @@ static const struct netdev_stat_ops bnxt_stat_ops = {
 	.get_base_stats		= bnxt_get_base_stats,
 };
 
-static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
-{
-	u16 mem_size;
-
-	rxr->rx_agg_bmap_size = bp->rx_agg_ring_mask + 1;
-	mem_size = rxr->rx_agg_bmap_size / 8;
-	rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL);
-	if (!rxr->rx_agg_bmap)
-		return -ENOMEM;
-
-	return 0;
-}
-
 static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 {
 	struct bnxt_rx_ring_info *rxr, *clone;
@@ -15313,6 +15827,9 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_ring_struct *ring;
 	int rc;
 
+	if (!bp->rx_ring)
+		return -ENETDOWN;
+
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
 	memcpy(clone, rxr, sizeof(*rxr));
@@ -15323,6 +15840,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	clone->rx_agg_prod = 0;
 	clone->rx_sw_agg_prod = 0;
 	clone->rx_next_cons = 0;
+	clone->need_head_pool = false;
 
 	rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid);
 	if (rc)
@@ -15354,15 +15872,25 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 			goto err_free_rx_agg_ring;
 	}
 
+	if (bp->flags & BNXT_FLAG_TPA) {
+		rc = bnxt_alloc_one_tpa_info(bp, clone);
+		if (rc)
+			goto err_free_tpa_info;
+	}
+
 	bnxt_init_one_rx_ring_rxbd(bp, clone);
 	bnxt_init_one_rx_agg_ring_rxbd(bp, clone);
 
 	bnxt_alloc_one_rx_ring_skb(bp, clone, idx);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
-		bnxt_alloc_one_rx_ring_page(bp, clone, idx);
+		bnxt_alloc_one_rx_ring_netmem(bp, clone, idx);
+	if (bp->flags & BNXT_FLAG_TPA)
+		bnxt_alloc_one_tpa_info_data(bp, clone);
 
 	return 0;
 
+err_free_tpa_info:
+	bnxt_free_one_tpa_info(bp, clone);
 err_free_rx_agg_ring:
 	bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem);
 err_free_rx_ring:
@@ -15370,9 +15898,11 @@ err_free_rx_ring:
 err_rxq_info_unreg:
 	xdp_rxq_info_unreg(&clone->xdp_rxq);
 err_page_pool_destroy:
-	clone->page_pool->p.napi = NULL;
 	page_pool_destroy(clone->page_pool);
+	if (bnxt_separate_head_pool(clone))
+		page_pool_destroy(clone->head_pool);
 	clone->page_pool = NULL;
+	clone->head_pool = NULL;
 	return rc;
 }
 
@@ -15382,13 +15912,16 @@ static void bnxt_queue_mem_free(struct net_device *dev, void *qmem)
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_ring_struct *ring;
 
-	bnxt_free_one_rx_ring(bp, rxr);
-	bnxt_free_one_rx_agg_ring(bp, rxr);
+	bnxt_free_one_rx_ring_skbs(bp, rxr);
+	bnxt_free_one_tpa_info(bp, rxr);
 
 	xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 	page_pool_destroy(rxr->page_pool);
+	if (bnxt_separate_head_pool(rxr))
+		page_pool_destroy(rxr->head_pool);
 	rxr->page_pool = NULL;
+	rxr->head_pool = NULL;
 
 	ring = &rxr->rx_ring_struct;
 	bnxt_free_ring(bp, &ring->ring_mem);
@@ -15461,7 +15994,9 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_rx_ring_info *rxr, *clone;
 	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_vnic_info *vnic;
+	struct bnxt_napi *bnapi;
 	int i, rc;
+	u16 mru;
 
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
@@ -15470,43 +16005,64 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	rxr->rx_agg_prod = clone->rx_agg_prod;
 	rxr->rx_sw_agg_prod = clone->rx_sw_agg_prod;
 	rxr->rx_next_cons = clone->rx_next_cons;
+	rxr->rx_tpa = clone->rx_tpa;
+	rxr->rx_tpa_idx_map = clone->rx_tpa_idx_map;
 	rxr->page_pool = clone->page_pool;
+	rxr->head_pool = clone->head_pool;
 	rxr->xdp_rxq = clone->xdp_rxq;
+	rxr->need_head_pool = clone->need_head_pool;
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
 
+	bnapi = rxr->bnapi;
+	cpr = &bnapi->cp_ring;
+
+	/* All rings have been reserved and previously allocated.
+	 * Reallocating with the same parameters should never fail.
+	 */
 	rc = bnxt_hwrm_rx_ring_alloc(bp, rxr);
 	if (rc)
-		return rc;
+		goto err_reset;
+
+	if (bp->tph_mode) {
+		rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr);
+		if (rc)
+			goto err_reset;
+	}
+
 	rc = bnxt_hwrm_rx_agg_ring_alloc(bp, rxr);
 	if (rc)
-		goto err_free_hwrm_rx_ring;
+		goto err_reset;
 
 	bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 
-	cpr = &rxr->bnapi->cp_ring;
-	cpr->sw_stats->rx.rx_resets++;
+	if (bp->flags & BNXT_FLAG_SHARED_RINGS) {
+		rc = bnxt_tx_queue_start(bp, idx);
+		if (rc)
+			goto err_reset;
+	}
+
+	napi_enable_locked(&bnapi->napi);
+	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
 
-	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+	mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
+	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
-		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
-		if (rc) {
-			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
-				   vnic->vnic_id, rc);
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, idx);
+		if (rc)
 			return rc;
-		}
-		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
 	}
+	return bnxt_set_rss_ctx_vnic_mru(bp, mru, idx);
 
-	return 0;
-
-err_free_hwrm_rx_ring:
-	bnxt_hwrm_rx_ring_free(bp, rxr, false);
+err_reset:
+	netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n",
+		   rc);
+	napi_enable_locked(&bnapi->napi);
+	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
+	netif_close(dev);
 	return rc;
 }
 
@@ -15514,21 +16070,43 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_rx_ring_info *rxr;
+	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_vnic_info *vnic;
+	struct bnxt_napi *bnapi;
 	int i;
 
-	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
-		vnic->mru = 0;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
-	}
 
+		bnxt_set_vnic_mru_p5(bp, vnic, 0, idx);
+	}
+	bnxt_set_rss_ctx_vnic_mru(bp, 0, idx);
+	/* Make sure NAPI sees that the VNIC is disabled */
+	synchronize_net();
 	rxr = &bp->rx_ring[idx];
+	bnapi = rxr->bnapi;
+	cpr = &bnapi->cp_ring;
+	cancel_work_sync(&cpr->dim.work);
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
-	rxr->rx_next_cons = 0;
 	page_pool_disable_direct_recycling(rxr->page_pool);
+	if (bnxt_separate_head_pool(rxr))
+		page_pool_disable_direct_recycling(rxr->head_pool);
+
+	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
+		bnxt_tx_queue_stop(bp, idx);
+
+	/* Disable NAPI now after freeing the rings because HWRM_RING_FREE
+	 * completion is handled in NAPI to guarantee no more DMA on that ring
+	 * after seeing the completion.
+	 */
+	napi_disable_locked(&bnapi->napi);
+
+	if (bp->tph_mode) {
+		bnxt_hwrm_cp_ring_free(bp, rxr->rx_cpr);
+		bnxt_clear_one_cp_ring(bp, rxr->rx_cpr);
+	}
+	bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons);
 
 	memcpy(qmem, rxr, sizeof(*rxr));
 	bnxt_init_rx_ring_struct(bp, qmem);
@@ -15554,8 +16132,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	bnxt_rdma_aux_device_del(bp);
 
-	bnxt_ptp_clear(bp);
 	unregister_netdev(dev);
+	bnxt_ptp_clear(bp);
 
 	bnxt_rdma_aux_device_uninit(bp);
 
@@ -15607,6 +16185,10 @@ static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt)
 		bp->dev->priv_flags |= IFF_SUPP_NOFCS;
 	else
 		bp->dev->priv_flags &= ~IFF_SUPP_NOFCS;
+
+	bp->mac_flags = 0;
+	bnxt_hwrm_mac_qcaps(bp);
+
 	if (!fw_dflt)
 		return 0;
 
@@ -15844,7 +16426,7 @@ int bnxt_restore_pf_fw_resources(struct bnxt *bp)
 {
 	int rc;
 
-	ASSERT_RTNL();
+	netdev_ops_assert_locked(bp->dev);
 	bnxt_hwrm_func_qcaps(bp);
 
 	if (netif_running(bp->dev))
@@ -15857,7 +16439,7 @@ int bnxt_restore_pf_fw_resources(struct bnxt *bp)
 
 	if (netif_running(bp->dev)) {
 		if (rc)
-			dev_close(bp->dev);
+			netif_close(bp->dev);
 		else
 			rc = bnxt_open_nic(bp, true, false);
 	}
@@ -16135,8 +16717,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (bp->max_fltr < BNXT_MAX_FLTR)
 		bp->max_fltr = BNXT_MAX_FLTR;
 	bnxt_init_l2_fltr_tbl(bp);
-	bnxt_set_rx_skb_mode(bp, false);
+	__bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
+	bnxt_init_ring_params(bp);
 	bnxt_set_ring_params(bp);
 	bnxt_rdma_aux_device_init(bp);
 	rc = bnxt_set_dflt_rings(bp, true);
@@ -16193,6 +16776,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		bp->rss_cap |= BNXT_RSS_CAP_MULTI_RSS_CTX;
 	if (BNXT_SUPPORTS_QUEUE_API(bp))
 		dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops;
+	dev->request_ops_lock = true;
 
 	rc = register_netdev(dev);
 	if (rc)
@@ -16244,12 +16828,13 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 		return;
 
 	rtnl_lock();
+	netdev_lock(dev);
 	bp = netdev_priv(dev);
 	if (!bp)
 		goto shutdown_exit;
 
 	if (netif_running(dev))
-		dev_close(dev);
+		netif_close(dev);
 
 	bnxt_ptp_clear(bp);
 	bnxt_clear_int_mode(bp);
@@ -16261,6 +16846,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 	}
 
 shutdown_exit:
+	netdev_unlock(dev);
 	rtnl_unlock();
 }
 
@@ -16273,7 +16859,7 @@ static int bnxt_suspend(struct device *device)
 
 	bnxt_ulp_stop(bp);
 
-	rtnl_lock();
+	netdev_lock(dev);
 	if (netif_running(dev)) {
 		netif_device_detach(dev);
 		rc = bnxt_close(dev);
@@ -16282,7 +16868,7 @@ static int bnxt_suspend(struct device *device)
 	bnxt_ptp_clear(bp);
 	pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp, false);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return rc;
 }
 
@@ -16293,6 +16879,7 @@ static int bnxt_resume(struct device *device)
 	int rc = 0;
 
 	rtnl_lock();
+	netdev_lock(dev);
 	rc = pci_enable_device(bp->pdev);
 	if (rc) {
 		netdev_err(dev, "Cannot re-enable PCI device during resume, err = %d\n",
@@ -16335,6 +16922,7 @@ static int bnxt_resume(struct device *device)
 	}
 
 resume_exit:
+	netdev_unlock(bp->dev);
 	rtnl_unlock();
 	bnxt_ulp_start(bp, rc);
 	if (!rc)
@@ -16370,7 +16958,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 
 	bnxt_ulp_stop(bp);
 
-	rtnl_lock();
+	netdev_lock(netdev);
 	netif_device_detach(netdev);
 
 	if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
@@ -16379,7 +16967,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	}
 
 	if (abort || state == pci_channel_io_perm_failure) {
-		rtnl_unlock();
+		netdev_unlock(netdev);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -16398,7 +16986,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	if (pci_is_enabled(pdev))
 		pci_disable_device(pdev);
 	bnxt_free_ctx_mem(bp, false);
-	rtnl_unlock();
+	netdev_unlock(netdev);
 
 	/* Request a slot slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -16428,7 +17016,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 	    test_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state))
 		msleep(900);
 
-	rtnl_lock();
+	netdev_lock(netdev);
 
 	if (pci_enable_device(pdev)) {
 		dev_err(&pdev->dev,
@@ -16474,16 +17062,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		if (!err)
 			result = PCI_ERS_RESULT_RECOVERED;
 
+		/* IRQ will be initialized later in bnxt_io_resume */
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
-		err = bnxt_init_int_mode(bp);
-		bnxt_ulp_irq_restart(bp, err);
 	}
 
 reset_exit:
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	bnxt_clear_reservations(bp, true);
-	rtnl_unlock();
+	netdev_unlock(netdev);
 
 	return result;
 }
@@ -16503,18 +17090,23 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 
 	netdev_info(bp->dev, "PCI Slot Resume\n");
 	rtnl_lock();
+	netdev_lock(netdev);
 
 	err = bnxt_hwrm_func_qcaps(bp);
 	if (!err) {
-		if (netif_running(netdev))
+		if (netif_running(netdev)) {
 			err = bnxt_open(netdev);
-		else
+		} else {
 			err = bnxt_reserve_rings(bp, true);
+			if (!err)
+				err = bnxt_init_int_mode(bp);
+		}
 	}
 
 	if (!err)
 		netif_device_attach(netdev);
 
+	netdev_unlock(netdev);
 	rtnl_unlock();
 	bnxt_ulp_start(bp, err);
 	if (!err)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 23f1aff214b4..fda0d3cc6227 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -34,6 +34,9 @@
 #include <linux/firmware/broadcom/tee_bnxt_fw.h>
 #endif
 
+#define BNXT_DEFAULT_RX_COPYBREAK 256
+#define BNXT_MAX_RX_COPYBREAK 1024
+
 extern struct list_head bnxt_block_cb_list;
 
 struct page_pool;
@@ -79,6 +82,12 @@ struct tx_bd {
 #define TX_OPAQUE_PROD(bp, opq)	((TX_OPAQUE_IDX(opq) + TX_OPAQUE_BDS(opq)) &\
 				 (bp)->tx_ring_mask)
 
+#define TX_BD_CNT(n)	(((n) << TX_BD_FLAGS_BD_CNT_SHIFT) & TX_BD_FLAGS_BD_CNT)
+
+#define TX_MAX_BD_CNT	32
+
+#define TX_MAX_FRAGS		(TX_MAX_BD_CNT - 2)
+
 struct tx_bd_ext {
 	__le32 tx_bd_hsize_lflags;
 	#define TX_BD_FLAGS_TCP_UDP_CHKSUM			(1 << 0)
@@ -267,6 +276,9 @@ struct rx_cmp {
 	(((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_RSS_HASH_TYPE) >>\
 	  RX_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK)
 
+#define RX_CMP_ITYPES(rxcmp)					\
+	(le32_to_cpu((rxcmp)->rx_cmp_len_flags_type) & RX_CMP_FLAGS_ITYPES_MASK)
+
 #define RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp)				\
 	((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_V3_RSS_EXT_OP_LEGACY) >>\
 	 RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT)
@@ -378,7 +390,7 @@ struct rx_agg_cmp {
 	u32 rx_agg_cmp_opaque;
 	__le32 rx_agg_cmp_v;
 	#define RX_AGG_CMP_V					(1 << 0)
-	#define RX_AGG_CMP_AGG_ID				(0xffff << 16)
+	#define RX_AGG_CMP_AGG_ID				(0x0fff << 16)
 	 #define RX_AGG_CMP_AGG_ID_SHIFT			 16
 	__le32 rx_agg_cmp_unused;
 };
@@ -416,7 +428,7 @@ struct rx_tpa_start_cmp {
 	 #define RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT	 7
 	#define RX_TPA_START_CMP_AGG_ID				(0x7f << 25)
 	 #define RX_TPA_START_CMP_AGG_ID_SHIFT			 25
-	#define RX_TPA_START_CMP_AGG_ID_P5			(0xffff << 16)
+	#define RX_TPA_START_CMP_AGG_ID_P5			(0x0fff << 16)
 	 #define RX_TPA_START_CMP_AGG_ID_SHIFT_P5		 16
 	#define RX_TPA_START_CMP_METADATA1			(0xf << 28)
 	 #define RX_TPA_START_CMP_METADATA1_SHIFT		 28
@@ -540,7 +552,7 @@ struct rx_tpa_end_cmp {
 	 #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT		 16
 	#define RX_TPA_END_CMP_AGG_ID				(0x7f << 25)
 	 #define RX_TPA_END_CMP_AGG_ID_SHIFT			 25
-	#define RX_TPA_END_CMP_AGG_ID_P5			(0xffff << 16)
+	#define RX_TPA_END_CMP_AGG_ID_P5			(0x0fff << 16)
 	 #define RX_TPA_END_CMP_AGG_ID_SHIFT_P5			 16
 
 	__le32 rx_tpa_end_cmp_tsdelta;
@@ -891,7 +903,7 @@ struct bnxt_sw_rx_bd {
 };
 
 struct bnxt_sw_rx_agg_bd {
-	struct page		*page;
+	netmem_ref		netmem;
 	unsigned int		offset;
 	dma_addr_t		mapping;
 };
@@ -1094,6 +1106,7 @@ struct bnxt_rx_ring_info {
 
 	unsigned long		*rx_agg_bmap;
 	u16			rx_agg_bmap_size;
+	bool                    need_head_pool;
 
 	dma_addr_t		rx_desc_mapping[MAX_RX_PAGES];
 	dma_addr_t		rx_agg_desc_mapping[MAX_RX_AGG_PAGES];
@@ -1228,6 +1241,11 @@ struct bnxt_irq {
 	u8		have_cpumask:1;
 	char		name[IFNAMSIZ + BNXT_IRQ_NAME_EXTRA];
 	cpumask_var_t	cpu_mask;
+
+	struct bnxt	*bp;
+	int		msix_nr;
+	int		ring_nr;
+	struct irq_affinity_notify affinity_notify;
 };
 
 #define HWRM_RING_ALLOC_TX	0x1
@@ -2238,8 +2256,6 @@ struct bnxt {
 	#define BNXT_FLAG_TPA		(BNXT_FLAG_LRO | BNXT_FLAG_GRO)
 	#define BNXT_FLAG_JUMBO		0x10
 	#define BNXT_FLAG_STRIP_VLAN	0x20
-	#define BNXT_FLAG_AGG_RINGS	(BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \
-					 BNXT_FLAG_LRO)
 	#define BNXT_FLAG_RFS		0x100
 	#define BNXT_FLAG_SHARED_RINGS	0x200
 	#define BNXT_FLAG_PORT_STATS	0x400
@@ -2260,6 +2276,9 @@ struct bnxt {
 	#define BNXT_FLAG_ROCE_MIRROR_CAP	0x4000000
 	#define BNXT_FLAG_TX_COAL_CMPL	0x8000000
 	#define BNXT_FLAG_PORT_STATS_EXT	0x10000000
+	#define BNXT_FLAG_HDS		0x20000000
+	#define BNXT_FLAG_AGG_RINGS	(BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \
+					 BNXT_FLAG_LRO | BNXT_FLAG_HDS)
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
 					    BNXT_FLAG_RFS |		\
@@ -2267,6 +2286,11 @@ struct bnxt {
 
 #define BNXT_PF(bp)		(!((bp)->flags & BNXT_FLAG_VF))
 #define BNXT_VF(bp)		((bp)->flags & BNXT_FLAG_VF)
+#ifdef CONFIG_BNXT_SRIOV
+#define	BNXT_VF_IS_TRUSTED(bp)	((bp)->vf.flags & BNXT_VF_TRUST)
+#else
+#define	BNXT_VF_IS_TRUSTED(bp)	0
+#endif
 #define BNXT_NPAR(bp)		((bp)->port_partition_type)
 #define BNXT_MH(bp)		((bp)->flags & BNXT_FLAG_MULTI_HOST)
 #define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp) && !BNXT_MH(bp))
@@ -2339,7 +2363,7 @@ struct bnxt {
 	enum dma_data_direction	rx_dir;
 	u32			rx_ring_size;
 	u32			rx_agg_ring_size;
-	u32			rx_copy_thresh;
+	u32			rx_copybreak;
 	u32			rx_ring_mask;
 	u32			rx_agg_ring_mask;
 	int			rx_nr_pages;
@@ -2398,6 +2422,8 @@ struct bnxt {
 	u8			max_q;
 	u8			num_tc;
 
+	u8			tph_mode;
+
 	unsigned int		current_interval;
 #define BNXT_TIMER_INTERVAL	HZ
 
@@ -2479,6 +2505,8 @@ struct bnxt {
 	#define BNXT_FW_CAP_CFA_NTUPLE_RX_EXT_IP_PROTO	BIT_ULL(38)
 	#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3	BIT_ULL(39)
 	#define BNXT_FW_CAP_VNIC_RE_FLUSH		BIT_ULL(40)
+	#define BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS	BIT_ULL(41)
+	#define BNXT_FW_CAP_NPAR_1_2			BIT_ULL(42)
 
 	u32			fw_dbg_cap;
 
@@ -2498,6 +2526,8 @@ struct bnxt {
 	((bp)->fw_cap & BNXT_FW_CAP_ENABLE_RDMA_SRIOV)
 #define BNXT_ROCE_VF_RESC_CAP(bp)	\
 	((bp)->fw_cap & BNXT_FW_CAP_ROCE_VF_RESC_MGMT_SUPPORTED)
+#define BNXT_SW_RES_LMT(bp)		\
+	((bp)->fw_cap & BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS)
 
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
@@ -2585,6 +2615,7 @@ struct bnxt {
 #define BNXT_FW_RESET_STATE_POLL_FW	4
 #define BNXT_FW_RESET_STATE_OPENING	5
 #define BNXT_FW_RESET_STATE_POLL_FW_DOWN	6
+#define BNXT_FW_RESET_STATE_ABORT	7
 
 	u16			fw_reset_min_dsecs;
 #define BNXT_DFLT_FW_RST_MIN_DSECS	20
@@ -2657,6 +2688,11 @@ struct bnxt {
 #define BNXT_PHY_FL_BANK_SEL		(PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED << 8)
 #define BNXT_PHY_FL_SPEEDS2		(PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED << 8)
 
+	/* copied from flags in hwrm_port_mac_qcaps_output */
+	u8			mac_flags;
+#define BNXT_MAC_FL_NO_MAC_LPBK		\
+	PORT_MAC_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED
+
 	u8			num_tests;
 	struct bnxt_test_info	*test_info;
 
@@ -2669,6 +2705,7 @@ struct bnxt {
 #define BNXT_DUMP_LIVE		0
 #define BNXT_DUMP_CRASH		1
 #define BNXT_DUMP_DRIVER	2
+#define BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE	3
 
 	struct bpf_prog		*xdp_prog;
 
@@ -2759,6 +2796,8 @@ struct bnxt {
 #define SFF_MODULE_ID_QSFP28			0x11
 #define BNXT_MAX_PHY_I2C_RESP_SIZE		64
 
+#define BNXT_HDS_THRESHOLD_MAX			1023
+
 static inline u32 bnxt_tx_avail(struct bnxt *bp,
 				const struct bnxt_tx_ring_info *txr)
 {
@@ -2843,7 +2882,7 @@ u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx);
 bool bnxt_bs_trace_avail(struct bnxt *bp, u16 type);
 void bnxt_set_tpa_flags(struct bnxt *bp);
 void bnxt_set_ring_params(struct bnxt *);
-int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
+void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
 void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index 7236d8e548ab..ce97befd3cb3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -110,20 +110,30 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg,
 			}
 		}
 
+		if (cmn_req->req_type ==
+				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
+			info->dest_buf_size += len;
+
 		if (info->dest_buf) {
 			if ((info->seg_start + off + len) <=
 			    BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
-				memcpy(info->dest_buf + off, dma_buf, len);
+				u16 copylen = min_t(u16, len,
+						    info->dest_buf_size - off);
+
+				memcpy(info->dest_buf + off, dma_buf, copylen);
+				if (copylen < len)
+					break;
 			} else {
 				rc = -ENOBUFS;
+				if (cmn_req->req_type ==
+				    cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) {
+					kfree(info->dest_buf);
+					info->dest_buf = NULL;
+				}
 				break;
 			}
 		}
 
-		if (cmn_req->req_type ==
-				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
-			info->dest_buf_size += len;
-
 		if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE))
 			break;
 
@@ -159,8 +169,8 @@ static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp,
 	return rc;
 }
 
-static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
-					   u16 segment_id)
+static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 dump_type,
+					   u16 component_id, u16 segment_id)
 {
 	struct hwrm_dbg_coredump_initiate_input *req;
 	int rc;
@@ -172,6 +182,8 @@ static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
 	hwrm_req_timeout(bp, req, bp->hwrm_cmd_max_timeout);
 	req->component_id = cpu_to_le16(component_id);
 	req->segment_id = cpu_to_le16(segment_id);
+	if (dump_type == BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE)
+		req->seg_flags = DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE;
 
 	return hwrm_req_send(bp, req);
 }
@@ -450,7 +462,8 @@ static int __bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf,
 
 		start = jiffies;
 
-		rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id);
+		rc = bnxt_hwrm_dbg_coredump_initiate(bp, dump_type, comp_id,
+						     seg_id);
 		if (rc) {
 			netdev_err(bp->dev,
 				   "Failed to initiate coredump for seg = %d\n",
@@ -493,9 +506,16 @@ err:
 					  start_utc, coredump.total_segs + 1,
 					  rc);
 	kfree(coredump.data);
-	*dump_len += sizeof(struct bnxt_coredump_record);
-	if (rc == -ENOBUFS)
+	if (!rc) {
+		*dump_len += sizeof(struct bnxt_coredump_record);
+		/* The actual coredump length can be smaller than the FW
+		 * reported length earlier.  Use the ethtool provided length.
+		 */
+		if (buf_len)
+			*dump_len = buf_len;
+	} else if (rc == -ENOBUFS) {
 		netdev_err(bp->dev, "Firmware returned large coredump buffer\n");
+	}
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index ef8288fd68f4..777880594a04 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
 #include <net/devlink.h>
+#include <net/netdev_lock.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
@@ -439,14 +440,17 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
 		bnxt_ulp_stop(bp);
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (bnxt_sriov_cfg(bp)) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "reload is unsupported while VFs are allocated or being configured");
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			bnxt_ulp_start(bp, 0);
 			return -EOPNOTSUPP;
 		}
 		if (bp->dev->reg_state == NETREG_UNREGISTERED) {
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			bnxt_ulp_start(bp, 0);
 			return -ENODEV;
@@ -458,7 +462,8 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 		if (rc) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to deregister");
 			if (netif_running(bp->dev))
-				dev_close(bp->dev);
+				netif_close(bp->dev);
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			break;
 		}
@@ -479,7 +484,9 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 			return -EPERM;
 		}
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (bp->dev->reg_state == NETREG_UNREGISTERED) {
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			return -ENODEV;
 		}
@@ -493,6 +500,7 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 		if (rc) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to activate firmware");
 			clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state);
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 		}
 		break;
@@ -511,6 +519,8 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc = 0;
 
+	netdev_assert_locked(bp->dev);
+
 	*actions_performed = 0;
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
@@ -535,6 +545,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		if (!netif_running(bp->dev))
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Device is closed, not waiting for reset notice that will never come");
+		netdev_unlock(bp->dev);
 		rtnl_unlock();
 		while (test_bit(BNXT_STATE_FW_ACTIVATE, &bp->state)) {
 			if (time_after(jiffies, timeout)) {
@@ -550,6 +561,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 			msleep(50);
 		}
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (!rc)
 			*actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
 		clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state);
@@ -568,8 +580,9 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		}
 		*actions_performed |= BIT(action);
 	} else if (netif_running(bp->dev)) {
-		dev_close(bp->dev);
+		netif_close(bp->dev);
 	}
+	netdev_unlock(bp->dev);
 	rtnl_unlock();
 	if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT)
 		bnxt_ulp_start(bp, rc);
@@ -666,6 +679,8 @@ static const struct bnxt_dl_nvm_param nvm_params[] = {
 	 NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10, 4},
 	{DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
 	 NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7, 4},
+	{DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, NVM_OFF_SUPPORT_RDMA,
+	 BNXT_NVM_FUNC_CFG, 1, 1},
 	{BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK,
 	 BNXT_NVM_SHARED_CFG, 1, 1},
 };
@@ -1010,37 +1025,19 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 
 }
 
-static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
-			     union devlink_param_value *val)
+static int __bnxt_hwrm_nvm_req(struct bnxt *bp,
+			       const struct bnxt_dl_nvm_param *nvm, void *msg,
+			       union devlink_param_value *val)
 {
 	struct hwrm_nvm_get_variable_input *req = msg;
-	struct bnxt_dl_nvm_param nvm_param;
 	struct hwrm_err_output *resp;
 	union bnxt_nvm_data *data;
 	dma_addr_t data_dma_addr;
-	int idx = 0, rc, i;
-
-	/* Get/Set NVM CFG parameter is supported only on PFs */
-	if (BNXT_VF(bp)) {
-		hwrm_req_drop(bp, req);
-		return -EPERM;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
-		if (nvm_params[i].id == param_id) {
-			nvm_param = nvm_params[i];
-			break;
-		}
-	}
+	int idx = 0, rc;
 
-	if (i == ARRAY_SIZE(nvm_params)) {
-		hwrm_req_drop(bp, req);
-		return -EOPNOTSUPP;
-	}
-
-	if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)
+	if (nvm->dir_type == BNXT_NVM_PORT_CFG)
 		idx = bp->pf.port_id;
-	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
+	else if (nvm->dir_type == BNXT_NVM_FUNC_CFG)
 		idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
 
 	data = hwrm_req_dma_slice(bp, req, sizeof(*data), &data_dma_addr);
@@ -1051,23 +1048,23 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	}
 
 	req->dest_data_addr = cpu_to_le64(data_dma_addr);
-	req->data_len = cpu_to_le16(nvm_param.nvm_num_bits);
-	req->option_num = cpu_to_le16(nvm_param.offset);
+	req->data_len = cpu_to_le16(nvm->nvm_num_bits);
+	req->option_num = cpu_to_le16(nvm->offset);
 	req->index_0 = cpu_to_le16(idx);
 	if (idx)
 		req->dimensions = cpu_to_le16(1);
 
 	resp = hwrm_req_hold(bp, req);
 	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) {
-		bnxt_copy_to_nvm_data(data, val, nvm_param.nvm_num_bits,
-				      nvm_param.dl_num_bytes);
+		bnxt_copy_to_nvm_data(data, val, nvm->nvm_num_bits,
+				      nvm->dl_num_bytes);
 		rc = hwrm_req_send(bp, msg);
 	} else {
 		rc = hwrm_req_send_silent(bp, msg);
 		if (!rc) {
 			bnxt_copy_from_nvm_data(val, data,
-						nvm_param.nvm_num_bits,
-						nvm_param.dl_num_bytes);
+						nvm->nvm_num_bits,
+						nvm->dl_num_bytes);
 		} else {
 			if (resp->cmd_err ==
 				NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST)
@@ -1080,6 +1077,27 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	return rc;
 }
 
+static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
+			     union devlink_param_value *val)
+{
+	struct hwrm_nvm_get_variable_input *req = msg;
+	const struct bnxt_dl_nvm_param *nvm_param;
+	int i;
+
+	/* Get/Set NVM CFG parameter is supported only on PFs */
+	if (BNXT_VF(bp)) {
+		hwrm_req_drop(bp, req);
+		return -EPERM;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
+		nvm_param = &nvm_params[i];
+		if (nvm_param->id == param_id)
+			return __bnxt_hwrm_nvm_req(bp, nvm_param, msg, val);
+	}
+	return -EOPNOTSUPP;
+}
+
 static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
 				 struct devlink_param_gset_ctx *ctx)
 {
@@ -1116,6 +1134,32 @@ static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
 	return bnxt_hwrm_nvm_req(bp, id, req, &ctx->val);
 }
 
+static int bnxt_dl_roce_validate(struct devlink *dl, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	const struct bnxt_dl_nvm_param nvm_roce_cap = {0, NVM_OFF_RDMA_CAPABLE,
+		BNXT_NVM_SHARED_CFG, 1, 1};
+	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+	struct hwrm_nvm_get_variable_input *req;
+	union devlink_param_value roce_cap;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_NVM_GET_VARIABLE);
+	if (rc)
+		return rc;
+
+	if (__bnxt_hwrm_nvm_req(bp, &nvm_roce_cap, req, &roce_cap)) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to verify if device is RDMA Capable");
+		return -EINVAL;
+	}
+	if (!roce_cap.vbool) {
+		NL_SET_ERR_MSG_MOD(extack, "Device does not support RDMA");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int bnxt_dl_msix_validate(struct devlink *dl, u32 id,
 				 union devlink_param_value val,
 				 struct netlink_ext_ack *extack)
@@ -1180,6 +1224,10 @@ static const struct devlink_param bnxt_dl_params[] = {
 			      BIT(DEVLINK_PARAM_CMODE_PERMANENT),
 			      bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
 			      bnxt_dl_msix_validate),
+	DEVLINK_PARAM_GENERIC(ENABLE_ROCE,
+			      BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			      bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
+			      bnxt_dl_roce_validate),
 	DEVLINK_PARAM_DRIVER(BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK,
 			     "gre_ver_check", DEVLINK_PARAM_TYPE_BOOL,
 			     BIT(DEVLINK_PARAM_CMODE_PERMANENT),
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index b8105065367b..7f45dcd7b287 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -41,8 +41,10 @@ static inline void bnxt_dl_set_remote_reset(struct devlink *dl, bool value)
 #define NVM_OFF_MSIX_VEC_PER_PF_MAX	108
 #define NVM_OFF_MSIX_VEC_PER_PF_MIN	114
 #define NVM_OFF_IGNORE_ARI		164
+#define NVM_OFF_RDMA_CAPABLE		161
 #define NVM_OFF_DIS_GRE_VER_CHECK	171
 #define NVM_OFF_ENABLE_SRIOV		401
+#define NVM_OFF_SUPPORT_RDMA		506
 #define NVM_OFF_NVM_CFG_VER		602
 
 #define BNXT_NVM_CFG_VER_BITS		8
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index f1f6bb328a55..f5d490bf997e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -24,6 +24,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
 #include <linux/timecounter.h>
+#include <net/netdev_queues.h>
 #include <net/netlink.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -833,6 +834,8 @@ static void bnxt_get_ringparam(struct net_device *dev,
 	ering->rx_pending = bp->rx_ring_size;
 	ering->rx_jumbo_pending = bp->rx_agg_ring_size;
 	ering->tx_pending = bp->tx_ring_size;
+
+	kernel_ering->hds_thresh_max = BNXT_HDS_THRESHOLD_MAX;
 }
 
 static int bnxt_set_ringparam(struct net_device *dev,
@@ -840,16 +843,35 @@ static int bnxt_set_ringparam(struct net_device *dev,
 			      struct kernel_ethtool_ringparam *kernel_ering,
 			      struct netlink_ext_ack *extack)
 {
+	u8 tcp_data_split = kernel_ering->tcp_data_split;
 	struct bnxt *bp = netdev_priv(dev);
+	u8 hds_config_mod;
 
 	if ((ering->rx_pending > BNXT_MAX_RX_DESC_CNT) ||
 	    (ering->tx_pending > BNXT_MAX_TX_DESC_CNT) ||
 	    (ering->tx_pending < BNXT_MIN_TX_DESC_CNT))
 		return -EINVAL;
 
+	hds_config_mod = tcp_data_split != dev->cfg->hds_config;
+	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_DISABLED && hds_config_mod)
+		return -EINVAL;
+
+	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
+	    hds_config_mod && BNXT_RX_PAGE_MODE(bp)) {
+		NL_SET_ERR_MSG_MOD(extack, "tcp-data-split is disallowed when XDP is attached");
+		return -EINVAL;
+	}
+
 	if (netif_running(dev))
 		bnxt_close_nic(bp, false, false);
 
+	if (hds_config_mod) {
+		if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED)
+			bp->flags |= BNXT_FLAG_HDS;
+		else if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN)
+			bp->flags &= ~BNXT_FLAG_HDS;
+	}
+
 	bp->rx_ring_size = ering->rx_pending;
 	bp->tx_ring_size = ering->tx_pending;
 	bnxt_set_ring_params(bp);
@@ -1187,10 +1209,14 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		}
 	}
 
-	if (fltr->base.flags & BNXT_ACT_DROP)
+	if (fltr->base.flags & BNXT_ACT_DROP) {
 		fs->ring_cookie = RX_CLS_FLOW_DISC;
-	else
+	} else if (fltr->base.flags & BNXT_ACT_RSS_CTX) {
+		fs->flow_type |= FLOW_RSS;
+		cmd->rss_context = fltr->base.fw_vnic_id;
+	} else {
 		fs->ring_cookie = fltr->base.rxq;
+	}
 	rc = 0;
 
 fltr_err:
@@ -2036,6 +2062,17 @@ static int bnxt_get_regs_len(struct net_device *dev)
 	return reg_len;
 }
 
+#define BNXT_PCIE_32B_ENTRY(start, end)			\
+	 { offsetof(struct pcie_ctx_hw_stats, start),	\
+	   offsetof(struct pcie_ctx_hw_stats, end) }
+
+static const struct {
+	u16 start;
+	u16 end;
+} bnxt_pcie_32b_entries[] = {
+	BNXT_PCIE_32B_ENTRY(pcie_ltssm_histogram[0], pcie_ltssm_histogram[3]),
+};
+
 static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 			  void *_p)
 {
@@ -2046,7 +2083,8 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	int rc;
 
 	regs->version = 0;
-	bnxt_dbg_hwrm_rd_reg(bp, 0, BNXT_PXP_REG_LEN / 4, _p);
+	if (!(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_REG_ACCESS_RESTRICTED))
+		bnxt_dbg_hwrm_rd_reg(bp, 0, BNXT_PXP_REG_LEN / 4, _p);
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED))
 		return;
@@ -2067,12 +2105,27 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	req->pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr);
 	rc = hwrm_req_send(bp, req);
 	if (!rc) {
-		__le64 *src = (__le64 *)hw_pcie_stats;
-		u64 *dst = (u64 *)(_p + BNXT_PXP_REG_LEN);
-		int i;
-
-		for (i = 0; i < sizeof(*hw_pcie_stats) / sizeof(__le64); i++)
-			dst[i] = le64_to_cpu(src[i]);
+		u8 *dst = (u8 *)(_p + BNXT_PXP_REG_LEN);
+		u8 *src = (u8 *)hw_pcie_stats;
+		int i, j;
+
+		for (i = 0, j = 0; i < sizeof(*hw_pcie_stats); ) {
+			if (i >= bnxt_pcie_32b_entries[j].start &&
+			    i <= bnxt_pcie_32b_entries[j].end) {
+				u32 *dst32 = (u32 *)(dst + i);
+
+				*dst32 = le32_to_cpu(*(__le32 *)(src + i));
+				i += 4;
+				if (i > bnxt_pcie_32b_entries[j].end &&
+				    j < ARRAY_SIZE(bnxt_pcie_32b_entries) - 1)
+					j++;
+			} else {
+				u64 *dst64 = (u64 *)(dst + i);
+
+				*dst64 = le64_to_cpu(*(__le64 *)(src + i));
+				i += 8;
+			}
+		}
 	}
 	hwrm_req_drop(bp, req);
 }
@@ -4157,7 +4210,7 @@ err:
 static void bnxt_get_pkgver(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	char buf[FW_VER_STR_LEN];
+	char buf[FW_VER_STR_LEN - 5];
 	int len;
 
 	if (!bnxt_get_pkginfo(dev, buf, sizeof(buf))) {
@@ -4323,6 +4376,45 @@ static int bnxt_get_eee(struct net_device *dev, struct ethtool_keee *edata)
 	return 0;
 }
 
+static int bnxt_set_tunable(struct net_device *dev,
+			    const struct ethtool_tunable *tuna,
+			    const void *data)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	u32 rx_copybreak;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		rx_copybreak = *(u32 *)data;
+		if (rx_copybreak > BNXT_MAX_RX_COPYBREAK)
+			return -ERANGE;
+		if (rx_copybreak != bp->rx_copybreak) {
+			if (netif_running(dev))
+				return -EBUSY;
+			bp->rx_copybreak = rx_copybreak;
+		}
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int bnxt_get_tunable(struct net_device *dev,
+			    const struct ethtool_tunable *tuna, void *data)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)data = bp->rx_copybreak;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int bnxt_read_sfp_module_eeprom_info(struct bnxt *bp, u16 i2c_addr,
 					    u16 page_number, u8 bank,
 					    u16 start_addr, u16 data_length,
@@ -4371,6 +4463,9 @@ static int bnxt_get_module_info(struct net_device *dev,
 	struct bnxt *bp = netdev_priv(dev);
 	int rc;
 
+	if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp))
+		return -EPERM;
+
 	/* No point in going further if phy status indicates
 	 * module is not inserted or if it is powered down or
 	 * if it is of type 10GBase-T
@@ -4422,6 +4517,9 @@ static int bnxt_get_module_eeprom(struct net_device *dev,
 	u16  start = eeprom->offset, length = eeprom->len;
 	int rc = 0;
 
+	if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp))
+		return -EPERM;
+
 	memset(data, 0, eeprom->len);
 
 	/* Read A0 portion of the EEPROM */
@@ -4469,13 +4567,19 @@ static int bnxt_get_module_status(struct bnxt *bp, struct netlink_ext_ack *extac
 	return -EINVAL;
 }
 
-static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
-					  const struct ethtool_module_eeprom *page_data,
-					  struct netlink_ext_ack *extack)
+static int
+bnxt_mod_eeprom_by_page_precheck(struct bnxt *bp,
+				 const struct ethtool_module_eeprom *page_data,
+				 struct netlink_ext_ack *extack)
 {
-	struct bnxt *bp = netdev_priv(dev);
 	int rc;
 
+	if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Module read/write not permitted on untrusted VF");
+		return -EPERM;
+	}
+
 	rc = bnxt_get_module_status(bp, extack);
 	if (rc)
 		return rc;
@@ -4489,6 +4593,19 @@ static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
 		NL_SET_ERR_MSG_MOD(extack, "Firmware not capable for bank selection");
 		return -EINVAL;
 	}
+	return 0;
+}
+
+static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
+					  const struct ethtool_module_eeprom *page_data,
+					  struct netlink_ext_ack *extack)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
+	rc = bnxt_mod_eeprom_by_page_precheck(bp, page_data, extack);
+	if (rc)
+		return rc;
 
 	rc = bnxt_read_sfp_module_eeprom_info(bp, page_data->i2c_address << 1,
 					      page_data->page, page_data->bank,
@@ -4502,6 +4619,62 @@ static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
 	return page_data->length;
 }
 
+static int bnxt_write_sfp_module_eeprom_info(struct bnxt *bp,
+					     const struct ethtool_module_eeprom *page)
+{
+	struct hwrm_port_phy_i2c_write_input *req;
+	int bytes_written = 0;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_I2C_WRITE);
+	if (rc)
+		return rc;
+
+	hwrm_req_hold(bp, req);
+	req->i2c_slave_addr = page->i2c_address << 1;
+	req->page_number = cpu_to_le16(page->page);
+	req->bank_number = page->bank;
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	req->enables = cpu_to_le32(PORT_PHY_I2C_WRITE_REQ_ENABLES_PAGE_OFFSET |
+				   PORT_PHY_I2C_WRITE_REQ_ENABLES_BANK_NUMBER);
+
+	while (bytes_written < page->length) {
+		u16 xfer_size;
+
+		xfer_size = min_t(u16, page->length - bytes_written,
+				  BNXT_MAX_PHY_I2C_RESP_SIZE);
+		req->page_offset = cpu_to_le16(page->offset + bytes_written);
+		req->data_length = xfer_size;
+		memcpy(req->data, page->data + bytes_written, xfer_size);
+		rc = hwrm_req_send(bp, req);
+		if (rc)
+			break;
+		bytes_written += xfer_size;
+	}
+
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+static int bnxt_set_module_eeprom_by_page(struct net_device *dev,
+					  const struct ethtool_module_eeprom *page_data,
+					  struct netlink_ext_ack *extack)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
+	rc = bnxt_mod_eeprom_by_page_precheck(bp, page_data, extack);
+	if (rc)
+		return rc;
+
+	rc = bnxt_write_sfp_module_eeprom_info(bp, page_data);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Module`s eeprom write failed");
+		return rc;
+	}
+	return page_data->length;
+}
+
 static int bnxt_nway_reset(struct net_device *dev)
 {
 	int rc = 0;
@@ -4773,7 +4946,8 @@ static int bnxt_run_loopback(struct bnxt *bp)
 	cpr = &rxr->bnapi->cp_ring;
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		cpr = rxr->rx_cpr;
-	pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh);
+	pkt_size = min(bp->dev->mtu + ETH_HLEN, max(BNXT_DEFAULT_RX_COPYBREAK,
+						    bp->rx_copybreak));
 	skb = netdev_alloc_skb(bp->dev, pkt_size);
 	if (!skb)
 		return -ENOMEM;
@@ -4843,6 +5017,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 	if (!bp->num_tests || !BNXT_PF(bp))
 		return;
 
+	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (etest->flags & ETH_TEST_FL_OFFLINE &&
 	    bnxt_ulp_registered(bp->edev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
@@ -4850,7 +5025,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		return;
 	}
 
-	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (!netif_running(dev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
 		return;
@@ -4883,35 +5057,44 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		bnxt_close_nic(bp, true, false);
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 
-		buf[BNXT_MACLPBK_TEST_IDX] = 1;
-		bnxt_hwrm_mac_loopback(bp, true);
-		msleep(250);
 		rc = bnxt_half_open_nic(bp);
 		if (rc) {
-			bnxt_hwrm_mac_loopback(bp, false);
 			etest->flags |= ETH_TEST_FL_FAILED;
 			return;
 		}
+		buf[BNXT_MACLPBK_TEST_IDX] = 1;
+		if (bp->mac_flags & BNXT_MAC_FL_NO_MAC_LPBK)
+			goto skip_mac_loopback;
+
+		bnxt_hwrm_mac_loopback(bp, true);
+		msleep(250);
 		if (bnxt_run_loopback(bp))
 			etest->flags |= ETH_TEST_FL_FAILED;
 		else
 			buf[BNXT_MACLPBK_TEST_IDX] = 0;
 
 		bnxt_hwrm_mac_loopback(bp, false);
+skip_mac_loopback:
+		buf[BNXT_PHYLPBK_TEST_IDX] = 1;
+		if (bp->phy_flags & BNXT_PHY_FL_NO_PHY_LPBK)
+			goto skip_phy_loopback;
+
 		bnxt_hwrm_phy_loopback(bp, true, false);
 		msleep(1000);
-		if (bnxt_run_loopback(bp)) {
-			buf[BNXT_PHYLPBK_TEST_IDX] = 1;
+		if (bnxt_run_loopback(bp))
 			etest->flags |= ETH_TEST_FL_FAILED;
-		}
+		else
+			buf[BNXT_PHYLPBK_TEST_IDX] = 0;
+skip_phy_loopback:
+		buf[BNXT_EXTLPBK_TEST_IDX] = 1;
 		if (do_ext_lpbk) {
 			etest->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE;
 			bnxt_hwrm_phy_loopback(bp, true, true);
 			msleep(1000);
-			if (bnxt_run_loopback(bp)) {
-				buf[BNXT_EXTLPBK_TEST_IDX] = 1;
+			if (bnxt_run_loopback(bp))
 				etest->flags |= ETH_TEST_FL_FAILED;
-			}
+			else
+				buf[BNXT_EXTLPBK_TEST_IDX] = 0;
 		}
 		bnxt_hwrm_phy_loopback(bp, false, false);
 		bnxt_half_close_nic(bp);
@@ -4989,8 +5172,9 @@ static int bnxt_set_dump(struct net_device *dev, struct ethtool_dump *dump)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (dump->flag > BNXT_DUMP_DRIVER) {
-		netdev_info(dev, "Supports only Live(0), Crash(1), Driver(2) dumps.\n");
+	if (dump->flag > BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE) {
+		netdev_info(dev,
+			    "Supports only Live(0), Crash(1), Driver(2), Live with cached context(3) dumps.\n");
 		return -EINVAL;
 	}
 
@@ -5305,6 +5489,8 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 				     ETHTOOL_COALESCE_STATS_BLOCK_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX |
 				     ETHTOOL_COALESCE_USE_CQE,
+	.supported_ring_params	= ETHTOOL_RING_USE_TCP_DATA_SPLIT |
+				  ETHTOOL_RING_USE_HDS_THRS,
 	.get_link_ksettings	= bnxt_get_link_ksettings,
 	.set_link_ksettings	= bnxt_set_link_ksettings,
 	.get_fec_stats		= bnxt_get_fec_stats,
@@ -5346,9 +5532,12 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_link_ext_stats	= bnxt_get_link_ext_stats,
 	.get_eee		= bnxt_get_eee,
 	.set_eee		= bnxt_set_eee,
+	.get_tunable		= bnxt_get_tunable,
+	.set_tunable		= bnxt_set_tunable,
 	.get_module_info	= bnxt_get_module_info,
 	.get_module_eeprom	= bnxt_get_module_eeprom,
 	.get_module_eeprom_by_page = bnxt_get_module_eeprom_by_page,
+	.set_module_eeprom_by_page = bnxt_set_module_eeprom_by_page,
 	.nway_reset		= bnxt_nway_reset,
 	.set_phys_id		= bnxt_set_phys_id,
 	.self_test		= bnxt_self_test,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 5f8de1634378..549231703bce 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -2,7 +2,7 @@
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
  * Copyright (c) 2014-2018 Broadcom Limited
- * Copyright (c) 2018-2024 Broadcom Inc.
+ * Copyright (c) 2018-2025 Broadcom Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -438,6 +438,7 @@ struct cmd_nums {
 	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
 	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
 	#define HWRM_MFG_TESTS                            0x21bUL
+	#define HWRM_MFG_WRITE_CERT_NVM                   0x21cUL
 	#define HWRM_PORT_POE_CFG                         0x230UL
 	#define HWRM_PORT_POE_QCFG                        0x231UL
 	#define HWRM_UDCC_QCAPS                           0x258UL
@@ -514,6 +515,8 @@ struct cmd_nums {
 	#define HWRM_TFC_TBL_SCOPE_CONFIG_GET             0x39aUL
 	#define HWRM_TFC_RESC_USAGE_QUERY                 0x39bUL
 	#define HWRM_TFC_GLOBAL_ID_FREE                   0x39cUL
+	#define HWRM_TFC_TCAM_PRI_UPDATE                  0x39dUL
+	#define HWRM_TFC_HOT_UPGRADE_PROCESS              0x3a0UL
 	#define HWRM_SV                                   0x400UL
 	#define HWRM_DBG_SERDES_TEST                      0xff0eUL
 	#define HWRM_DBG_LOG_BUFFER_FLUSH                 0xff0fUL
@@ -629,8 +632,8 @@ struct hwrm_err_output {
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 3
-#define HWRM_VERSION_RSVD 85
-#define HWRM_VERSION_STR "1.10.3.85"
+#define HWRM_VERSION_RSVD 97
+#define HWRM_VERSION_STR "1.10.3.97"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -1905,11 +1908,15 @@ struct hwrm_func_qcaps_output {
 	__le32	roce_vf_max_srq;
 	__le32	roce_vf_max_gid;
 	__le32	flags_ext3;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP     0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_REQUIRE_L2_FILTER          0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MAX_ROCE_VFS_SUPPORTED     0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP            0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_REQUIRE_L2_FILTER                 0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MAX_ROCE_VFS_SUPPORTED            0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RX_RATE_PROFILE_SEL_SUPPORTED     0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_BIDI_OPT_SUPPORTED                0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MIRROR_ON_ROCE_SUPPORTED          0x20UL
 	__le16	max_roce_vfs;
-	u8	unused_3[5];
+	__le16	max_crypto_rx_flow_filters;
+	u8	unused_3[3];
 	u8	valid;
 };
 
@@ -1924,7 +1931,7 @@ struct hwrm_func_qcfg_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcfg_output (size:1280b/160B) */
+/* hwrm_func_qcfg_output (size:1344b/168B) */
 struct hwrm_func_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -2087,14 +2094,18 @@ struct hwrm_func_qcfg_output {
 	__le16	host_mtu;
 	__le16	flags2;
 	#define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED     0x1UL
-	u8	unused_4[2];
+	__le16	stag_vid;
 	u8	port_kdnet_mode;
 	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL
 	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED  0x1UL
 	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_LAST    FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED
 	u8	kdnet_pcie_function;
 	__le16	port_kdnet_fid;
-	u8	unused_5[2];
+	u8	unused_5;
+	u8	roce_bidi_opt_mode;
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DISABLED      0x1UL
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DEDICATED     0x2UL
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_SHARED        0x4UL
 	__le32	num_ktls_tx_key_ctxs;
 	__le32	num_ktls_rx_key_ctxs;
 	u8	lag_id;
@@ -2112,7 +2123,8 @@ struct hwrm_func_qcfg_output {
 	__le16	xid_partition_cfg;
 	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_TX_CK     0x1UL
 	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_RX_CK     0x2UL
-	u8	unused_7;
+	__le16	mirror_vnic_id;
+	u8	unused_7[7];
 	u8	valid;
 };
 
@@ -3965,7 +3977,7 @@ struct ts_split_entries {
 	__le32	region_num_entries;
 	u8	tsid;
 	u8	lkup_static_bkt_cnt_exp[2];
-	u8	rsvd;
+	u8	locked;
 	__le32	rsvd2[2];
 };
 
@@ -5483,6 +5495,37 @@ struct hwrm_port_phy_qcaps_output {
 	u8	valid;
 };
 
+/* hwrm_port_phy_i2c_write_input (size:832b/104B) */
+struct hwrm_port_phy_i2c_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_PAGE_OFFSET     0x1UL
+	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_BANK_NUMBER     0x2UL
+	__le16	port_id;
+	u8	i2c_slave_addr;
+	u8	bank_number;
+	__le16	page_number;
+	__le16	page_offset;
+	u8	data_length;
+	u8	unused_1[7];
+	__le32	data[16];
+};
+
+/* hwrm_port_phy_i2c_write_output (size:128b/16B) */
+struct hwrm_port_phy_i2c_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
 /* hwrm_port_phy_i2c_read_input (size:320b/40B) */
 struct hwrm_port_phy_i2c_read_input {
 	__le16	req_type;
@@ -6610,8 +6653,9 @@ struct hwrm_vnic_alloc_input {
 	__le32	flags;
 	#define VNIC_ALLOC_REQ_FLAGS_DEFAULT                  0x1UL
 	#define VNIC_ALLOC_REQ_FLAGS_VIRTIO_NET_FID_VALID     0x2UL
+	#define VNIC_ALLOC_REQ_FLAGS_VNIC_ID_VALID            0x4UL
 	__le16	virtio_net_fid;
-	u8	unused_0[2];
+	__le16	vnic_id;
 };
 
 /* hwrm_vnic_alloc_output (size:128b/16B) */
@@ -6710,6 +6754,7 @@ struct hwrm_vnic_cfg_input {
 	#define VNIC_CFG_REQ_ENABLES_QUEUE_ID                 0x80UL
 	#define VNIC_CFG_REQ_ENABLES_RX_CSUM_V2_MODE          0x100UL
 	#define VNIC_CFG_REQ_ENABLES_L2_CQE_MODE              0x200UL
+	#define VNIC_CFG_REQ_ENABLES_RAW_QP_ID                0x400UL
 	__le16	vnic_id;
 	__le16	dflt_ring_grp;
 	__le16	rss_rule;
@@ -6729,7 +6774,7 @@ struct hwrm_vnic_cfg_input {
 	#define VNIC_CFG_REQ_L2_CQE_MODE_COMPRESSED 0x1UL
 	#define VNIC_CFG_REQ_L2_CQE_MODE_MIXED      0x2UL
 	#define VNIC_CFG_REQ_L2_CQE_MODE_LAST      VNIC_CFG_REQ_L2_CQE_MODE_MIXED
-	u8	unused0[4];
+	__le32	raw_qp_id;
 };
 
 /* hwrm_vnic_cfg_output (size:128b/16B) */
@@ -7082,6 +7127,15 @@ struct hwrm_vnic_plcmodes_cfg_output {
 	u8	valid;
 };
 
+/* hwrm_vnic_plcmodes_cfg_cmd_err (size:64b/8B) */
+struct hwrm_vnic_plcmodes_cfg_cmd_err {
+	u8	code;
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_UNKNOWN               0x0UL
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD 0x1UL
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_LAST                 VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD
+	u8	unused_0[7];
+};
+
 /* hwrm_vnic_rss_cos_lb_ctx_alloc_input (size:128b/16B) */
 struct hwrm_vnic_rss_cos_lb_ctx_alloc_input {
 	__le16	req_type;
@@ -7131,15 +7185,16 @@ struct hwrm_ring_alloc_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le32	enables;
-	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG           0x2UL
-	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID      0x8UL
-	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID           0x20UL
-	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID       0x40UL
-	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID       0x80UL
-	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID      0x100UL
-	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID                0x200UL
-	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE         0x400UL
-	#define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID     0x800UL
+	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG              0x2UL
+	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID         0x8UL
+	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID              0x20UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID          0x40UL
+	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID          0x80UL
+	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID         0x100UL
+	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID                   0x200UL
+	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE            0x400UL
+	#define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID        0x800UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RATE_PROFILE_VALID     0x1000UL
 	u8	ring_type;
 	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
 	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
@@ -7226,7 +7281,11 @@ struct hwrm_ring_alloc_input {
 	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RE_CFA  0x3UL
 	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE 0x4UL
 	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_LAST   RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE
-	u8	unused_4[2];
+	u8	rx_rate_profile_sel;
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_DEFAULT   0x0UL
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE 0x1UL
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_LAST     RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE
+	u8	unused_4;
 	__le64	cq_handle;
 };
 
@@ -9122,6 +9181,39 @@ struct pcie_ctx_hw_stats {
 	__le64	pcie_recovery_histogram;
 };
 
+/* pcie_ctx_hw_stats_v2 (size:4096b/512B) */
+struct pcie_ctx_hw_stats_v2 {
+	__le64	pcie_pl_signal_integrity;
+	__le64	pcie_dl_signal_integrity;
+	__le64	pcie_tl_signal_integrity;
+	__le64	pcie_link_integrity;
+	__le64	pcie_tx_traffic_rate;
+	__le64	pcie_rx_traffic_rate;
+	__le64	pcie_tx_dllp_statistics;
+	__le64	pcie_rx_dllp_statistics;
+	__le64	pcie_equalization_time;
+	__le32	pcie_ltssm_histogram[4];
+	__le64	pcie_recovery_histogram;
+	__le32	pcie_tl_credit_nph_histogram[8];
+	__le32	pcie_tl_credit_ph_histogram[8];
+	__le32	pcie_tl_credit_pd_histogram[8];
+	__le32	pcie_cmpl_latest_times[4];
+	__le32	pcie_cmpl_longest_time;
+	__le32	pcie_cmpl_shortest_time;
+	__le32	unused_0[2];
+	__le32	pcie_cmpl_latest_headers[4][4];
+	__le32	pcie_cmpl_longest_headers[4][4];
+	__le32	pcie_cmpl_shortest_headers[4][4];
+	__le32	pcie_wr_latency_histogram[12];
+	__le32	pcie_wr_latency_all_normal_count;
+	__le32	unused_1;
+	__le64	pcie_posted_packet_count;
+	__le64	pcie_non_posted_packet_count;
+	__le64	pcie_other_packet_count;
+	__le64	pcie_blocked_packet_count;
+	__le64	pcie_cmpl_packet_count;
+};
+
 /* hwrm_stat_generic_qstats_input (size:256b/32B) */
 struct hwrm_stat_generic_qstats_input {
 	__le16	req_type;
@@ -9317,6 +9409,9 @@ struct hwrm_struct_hdr {
 	#define STRUCT_HDR_STRUCT_ID_LAST                 STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND
 	__le16	len;
 	u8	version;
+	#define STRUCT_HDR_VERSION_0 0x0UL
+	#define STRUCT_HDR_VERSION_1 0x1UL
+	#define STRUCT_HDR_VERSION_LAST STRUCT_HDR_VERSION_1
 	u8	count;
 	__le16	subtype;
 	__le16	next_offset;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
index 15ca51b5d204..fb5f5b063c3d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
@@ -58,7 +58,7 @@ void hwrm_update_token(struct bnxt *bp, u16 seq, enum bnxt_hwrm_wait_state s);
 
 #define BNXT_HWRM_MAX_REQ_LEN		(bp->hwrm_max_req_len)
 #define BNXT_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
-#define HWRM_CMD_MAX_TIMEOUT		40000U
+#define HWRM_CMD_MAX_TIMEOUT		60000U
 #define SHORT_HWRM_CMD_TIMEOUT		20
 #define HWRM_CMD_TIMEOUT		(bp->hwrm_cmd_timeout)
 #define HWRM_RESET_TIMEOUT		((HWRM_CMD_TIMEOUT) * 4)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 2d4e19b96ee7..0669d43472f5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -794,6 +794,27 @@ next_slot:
 	return HZ;
 }
 
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp)
+{
+	struct bnxt_ptp_tx_req *txts_req;
+	u16 cons = ptp->txts_cons;
+
+	/* make sure ptp aux worker finished with
+	 * possible BNXT_STATE_OPEN set
+	 */
+	ptp_cancel_worker_sync(ptp->ptp_clock);
+
+	ptp->tx_avail = BNXT_MAX_TX_TS;
+	while (cons != ptp->txts_prod) {
+		txts_req = &ptp->txts_req[cons];
+		if (!IS_ERR_OR_NULL(txts_req->tx_skb))
+			dev_kfree_skb_any(txts_req->tx_skb);
+		cons = NEXT_TXTS(cons);
+	}
+	ptp->txts_cons = cons;
+	ptp_schedule_worker(ptp->ptp_clock, 0);
+}
+
 int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod)
 {
 	spin_lock_bh(&ptp->ptp_tx_lock);
@@ -1105,7 +1126,6 @@ out:
 void bnxt_ptp_clear(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-	int i;
 
 	if (!ptp)
 		return;
@@ -1117,12 +1137,5 @@ void bnxt_ptp_clear(struct bnxt *bp)
 	kfree(ptp->ptp_info.pin_config);
 	ptp->ptp_info.pin_config = NULL;
 
-	for (i = 0; i < BNXT_MAX_TX_TS; i++) {
-		if (ptp->txts_req[i].tx_skb) {
-			dev_kfree_skb_any(ptp->txts_req[i].tx_skb);
-			ptp->txts_req[i].tx_skb = NULL;
-		}
-	}
-
 	bnxt_unmap_ptp_regs(bp);
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index a95f05e9c579..0481161d26ef 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -162,6 +162,7 @@ int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
 void bnxt_ptp_reapply_pps(struct bnxt *bp);
 int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
 int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp);
 int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod);
 void bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb, u16 prod);
 int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 12b6ed51fd88..5ddddd89052f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -946,7 +946,9 @@ void bnxt_sriov_disable(struct bnxt *bp)
 
 	/* Reclaim all resources for the PF. */
 	rtnl_lock();
+	netdev_lock(bp->dev);
 	bnxt_restore_pf_fw_resources(bp);
+	netdev_unlock(bp->dev);
 	rtnl_unlock();
 }
 
@@ -956,17 +958,21 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	struct bnxt *bp = netdev_priv(dev);
 
 	rtnl_lock();
+	netdev_lock(dev);
 	if (!netif_running(dev)) {
 		netdev_warn(dev, "Reject SRIOV config request since if is down!\n");
+		netdev_unlock(dev);
 		rtnl_unlock();
 		return 0;
 	}
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		netdev_warn(dev, "Reject SRIOV config request when FW reset is in progress\n");
+		netdev_unlock(dev);
 		rtnl_unlock();
 		return 0;
 	}
 	bp->sriov_cfg = true;
+	netdev_unlock(dev);
 	rtnl_unlock();
 
 	if (pci_vfs_assigned(bp->pdev)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index b771c84cdd89..2450a369b792 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -20,6 +20,7 @@
 #include <asm/byteorder.h>
 #include <linux/bitmap.h>
 #include <linux/auxiliary_bus.h>
+#include <net/netdev_lock.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -112,7 +113,7 @@ int bnxt_register_dev(struct bnxt_en_dev *edev,
 	struct bnxt_ulp *ulp;
 	int rc = 0;
 
-	rtnl_lock();
+	netdev_lock(dev);
 	mutex_lock(&edev->en_dev_lock);
 	if (!bp->irq_tbl) {
 		rc = -ENODEV;
@@ -138,7 +139,7 @@ int bnxt_register_dev(struct bnxt_en_dev *edev,
 	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
 exit:
 	mutex_unlock(&edev->en_dev_lock);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return rc;
 }
 EXPORT_SYMBOL(bnxt_register_dev);
@@ -148,10 +149,9 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_ulp *ulp;
-	int i = 0;
 
 	ulp = edev->ulp_tbl;
-	rtnl_lock();
+	netdev_lock(dev);
 	mutex_lock(&edev->en_dev_lock);
 	if (ulp->msix_requested)
 		edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
@@ -164,12 +164,8 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	synchronize_rcu();
 	ulp->max_async_event_id = 0;
 	ulp->async_events_bmap = NULL;
-	while (atomic_read(&ulp->ref_count) != 0 && i < 10) {
-		msleep(100);
-		i++;
-	}
 	mutex_unlock(&edev->en_dev_lock);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return;
 }
 EXPORT_SYMBOL(bnxt_unregister_dev);
@@ -208,7 +204,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev,
 
 	rc = hwrm_req_replace(bp, req, fw_msg->msg, fw_msg->msg_len);
 	if (rc)
-		return rc;
+		goto drop_req;
 
 	hwrm_req_timeout(bp, req, fw_msg->timeout);
 	resp = hwrm_req_hold(bp, req);
@@ -220,6 +216,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev,
 
 		memcpy(fw_msg->resp, resp, resp_len);
 	}
+drop_req:
 	hwrm_req_drop(bp, req);
 	return rc;
 }
@@ -234,10 +231,9 @@ void bnxt_ulp_stop(struct bnxt *bp)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    (edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_stop_exit;
 
 	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
 	if (aux_priv) {
@@ -253,6 +249,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
 			adrv->suspend(adev, pm);
 		}
 	}
+ulp_stop_exit:
 	mutex_unlock(&edev->en_dev_lock);
 }
 
@@ -261,19 +258,13 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 	struct bnxt_aux_priv *aux_priv = bp->aux_priv;
 	struct bnxt_en_dev *edev = bp->edev;
 
-	if (!edev)
-		return;
-
-	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
-
-	if (err)
+	if (!edev || err)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_start_exit;
 
 	if (edev->ulp_tbl->msix_requested)
 		bnxt_fill_msix_vecs(bp, edev->msix_entries);
@@ -290,6 +281,8 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 			adrv->resume(adev);
 		}
 	}
+ulp_start_exit:
+	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
 	mutex_unlock(&edev->en_dev_lock);
 }
 
@@ -297,6 +290,7 @@ void bnxt_ulp_irq_stop(struct bnxt *bp)
 {
 	struct bnxt_en_dev *edev = bp->edev;
 	struct bnxt_ulp_ops *ops;
+	bool reset = false;
 
 	if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED))
 		return;
@@ -307,10 +301,12 @@ void bnxt_ulp_irq_stop(struct bnxt *bp)
 		if (!ulp->msix_requested)
 			return;
 
-		ops = rtnl_dereference(ulp->ulp_ops);
+		ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev);
 		if (!ops || !ops->ulp_irq_stop)
 			return;
-		ops->ulp_irq_stop(ulp->handle);
+		if (test_bit(BNXT_STATE_FW_RESET_DET, &bp->state))
+			reset = true;
+		ops->ulp_irq_stop(ulp->handle, reset);
 	}
 }
 
@@ -329,7 +325,7 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 		if (!ulp->msix_requested)
 			return;
 
-		ops = rtnl_dereference(ulp->ulp_ops);
+		ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev);
 		if (!ops || !ops->ulp_irq_restart)
 			return;
 
@@ -345,9 +341,36 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 	}
 }
 
-int bnxt_register_async_events(struct bnxt_en_dev *edev,
-			       unsigned long *events_bmap,
-			       u16 max_id)
+void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl)
+{
+	u16 event_id = le16_to_cpu(cmpl->event_id);
+	struct bnxt_en_dev *edev = bp->edev;
+	struct bnxt_ulp_ops *ops;
+	struct bnxt_ulp *ulp;
+
+	if (!bnxt_ulp_registered(edev))
+		return;
+	ulp = edev->ulp_tbl;
+
+	rcu_read_lock();
+
+	ops = rcu_dereference(ulp->ulp_ops);
+	if (!ops || !ops->ulp_async_notifier)
+		goto exit_unlock_rcu;
+	if (!ulp->async_events_bmap || event_id > ulp->max_async_event_id)
+		goto exit_unlock_rcu;
+
+	/* Read max_async_event_id first before testing the bitmap. */
+	smp_rmb();
+
+	if (test_bit(event_id, ulp->async_events_bmap))
+		ops->ulp_async_notifier(ulp->handle, cmpl);
+exit_unlock_rcu:
+	rcu_read_unlock();
+}
+
+void bnxt_register_async_events(struct bnxt_en_dev *edev,
+				unsigned long *events_bmap, u16 max_id)
 {
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
@@ -359,7 +382,6 @@ int bnxt_register_async_events(struct bnxt_en_dev *edev,
 	smp_wmb();
 	ulp->max_async_event_id = max_id;
 	bnxt_hwrm_func_drv_rgtr(bp, events_bmap, max_id + 1, true);
-	return 0;
 }
 EXPORT_SYMBOL(bnxt_register_async_events);
 
@@ -416,6 +438,8 @@ static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp)
 		edev->flags |= BNXT_EN_FLAG_VF;
 	if (BNXT_ROCE_VF_RESC_CAP(bp))
 		edev->flags |= BNXT_EN_FLAG_ROCE_VF_RES_MGMT;
+	if (BNXT_SW_RES_LMT(bp))
+		edev->flags |= BNXT_EN_FLAG_SW_RES_LMT;
 
 	edev->chip_num = bp->chip_num;
 	edev->hw_ring_stats_size = bp->hw_ring_stats_size;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 5d6aac60f236..7b9dd8ebe4bc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -10,9 +10,6 @@
 #ifndef BNXT_ULP_H
 #define BNXT_ULP_H
 
-#define BNXT_ROCE_ULP	0
-#define BNXT_MAX_ULP	1
-
 #define BNXT_MIN_ROCE_CP_RINGS	2
 #define BNXT_MIN_ROCE_STAT_CTXS	1
 
@@ -30,7 +27,9 @@ struct bnxt_msix_entry {
 };
 
 struct bnxt_ulp_ops {
-	void (*ulp_irq_stop)(void *);
+	/* async_notifier() cannot sleep (in BH context) */
+	void (*ulp_async_notifier)(void *, struct hwrm_async_event_cmpl *);
+	void (*ulp_irq_stop)(void *, bool);
 	void (*ulp_irq_restart)(void *, struct bnxt_msix_entry *);
 };
 
@@ -48,7 +47,6 @@ struct bnxt_ulp {
 	unsigned long	*async_events_bmap;
 	u16		max_async_event_id;
 	u16		msix_requested;
-	atomic_t	ref_count;
 };
 
 struct bnxt_en_dev {
@@ -65,6 +63,8 @@ struct bnxt_en_dev {
 	#define BNXT_EN_FLAG_VF			0x10
 #define BNXT_EN_VF(edev)	((edev)->flags & BNXT_EN_FLAG_VF)
 	#define BNXT_EN_FLAG_ROCE_VF_RES_MGMT	0x20
+	#define BNXT_EN_FLAG_SW_RES_LMT		0x40
+#define BNXT_EN_SW_RES_LMT(edev) ((edev)->flags & BNXT_EN_FLAG_SW_RES_LMT)
 
 	struct bnxt_ulp			*ulp_tbl;
 	int				l2_db_size;	/* Doorbell BAR size in
@@ -124,6 +124,6 @@ int bnxt_register_dev(struct bnxt_en_dev *edev, struct bnxt_ulp_ops *ulp_ops,
 		      void *handle);
 void bnxt_unregister_dev(struct bnxt_en_dev *edev);
 int bnxt_send_msg(struct bnxt_en_dev *edev, struct bnxt_fw_msg *fw_msg);
-int bnxt_register_async_events(struct bnxt_en_dev *edev,
-			       unsigned long *events_bmap, u16 max_id);
+void bnxt_register_async_events(struct bnxt_en_dev *edev,
+				unsigned long *events_bmap, u16 max_id);
 #endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 1467b94a6427..619f0844e778 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -257,8 +257,7 @@ bool bnxt_dev_is_vf_rep(struct net_device *dev)
 
 /* Called when the parent PF interface is closed:
  * As the mode transition from SWITCHDEV to LEGACY
- * happens under the rtnl_lock() this routine is safe
- * under the rtnl_lock()
+ * happens under the netdev instance lock this routine is safe
  */
 void bnxt_vf_reps_close(struct bnxt *bp)
 {
@@ -278,8 +277,7 @@ void bnxt_vf_reps_close(struct bnxt *bp)
 
 /* Called when the parent PF interface is opened (re-opened):
  * As the mode transition from SWITCHDEV to LEGACY
- * happen under the rtnl_lock() this routine is safe
- * under the rtnl_lock()
+ * happen under the netdev instance lock this routine is safe
  */
 void bnxt_vf_reps_open(struct bnxt *bp)
 {
@@ -348,7 +346,7 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 	/* Ensure that parent PF's and VF-reps' RX/TX has been quiesced
 	 * before proceeding with VF-rep cleanup.
 	 */
-	rtnl_lock();
+	netdev_lock(bp->dev);
 	if (netif_running(bp->dev)) {
 		bnxt_close_nic(bp, false, false);
 		closed = true;
@@ -365,10 +363,10 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 		bnxt_open_nic(bp, false, false);
 		bp->eswitch_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
 	}
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 
-	/* Need to call vf_reps_destroy() outside of rntl_lock
-	 * as unregister_netdev takes rtnl_lock
+	/* Need to call vf_reps_destroy() outside of netdev instance lock
+	 * as unregister_netdev takes it
 	 */
 	__bnxt_vf_reps_destroy(bp);
 }
@@ -376,7 +374,7 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 /* Free the VF-Reps in firmware, during firmware hot-reset processing.
  * Note that the VF-Rep netdevs are still active (not unregistered) during
  * this process. As the mode transition from SWITCHDEV to LEGACY happens
- * under the rtnl_lock() this routine is safe under the rtnl_lock().
+ * under the netdev instance lock this routine is safe.
  */
 void bnxt_vf_reps_free(struct bnxt *bp)
 {
@@ -413,7 +411,7 @@ static int bnxt_alloc_vf_rep(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
 /* Allocate the VF-Reps in firmware, during firmware hot-reset processing.
  * Note that the VF-Rep netdevs are still active (not unregistered) during
  * this process. As the mode transition from SWITCHDEV to LEGACY happens
- * under the rtnl_lock() this routine is safe under the rtnl_lock().
+ * under the netdev instance lock this routine is safe.
  */
 int bnxt_vf_reps_alloc(struct bnxt *bp)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index f88b641533fc..4a6d8cb9f970 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -15,6 +15,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
+#include <net/netdev_lock.h>
 #include <net/page_pool/helpers.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -48,8 +49,7 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 		tx_buf->page = virt_to_head_page(xdp->data);
 
 	txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
-	flags = (len << TX_BD_LEN_SHIFT) |
-		((num_frags + 1) << TX_BD_FLAGS_BD_CNT_SHIFT) |
+	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_CNT(num_frags + 1) |
 		bnxt_lhint_arr[len >> 9];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 	txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 1 + num_frags);
@@ -382,19 +382,24 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 	return nxmit;
 }
 
-/* Under rtnl_lock */
 static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 {
 	struct net_device *dev = bp->dev;
 	int tx_xdp = 0, tx_cp, rc, tc;
 	struct bpf_prog *old;
 
+	netdev_assert_locked(dev);
+
 	if (prog && !prog->aux->xdp_has_frags &&
 	    bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) {
 		netdev_warn(dev, "MTU %d larger than %d without XDP frag support.\n",
 			    bp->dev->mtu, BNXT_MAX_PAGE_MODE_MTU);
 		return -EOPNOTSUPP;
 	}
+	if (prog && bp->flags & BNXT_FLAG_HDS) {
+		netdev_warn(dev, "XDP is disallowed when HDS is enabled.\n");
+		return -EOPNOTSUPP;
+	}
 	if (!(bp->flags & BNXT_FLAG_SHARED_RINGS)) {
 		netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n");
 		return -EOPNOTSUPP;
@@ -420,17 +425,10 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 
 	if (prog) {
 		bnxt_set_rx_skb_mode(bp, true);
-		xdp_features_set_redirect_target(dev, true);
+		xdp_features_set_redirect_target_locked(dev, true);
 	} else {
-		int rx, tx;
-
-		xdp_features_clear_redirect_target(dev);
+		xdp_features_clear_redirect_target_locked(dev);
 		bnxt_set_rx_skb_mode(bp, false);
-		bnxt_get_max_rings(bp, &rx, &tx, true);
-		if (rx > 1) {
-			bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS;
-			bp->dev->hw_features |= NETIF_F_LRO;
-		}
 	}
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;
@@ -463,23 +461,16 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 
 struct sk_buff *
 bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
-		   struct page_pool *pool, struct xdp_buff *xdp,
-		   struct rx_cmp_ext *rxcmp1)
+		   struct page_pool *pool, struct xdp_buff *xdp)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
 	if (!skb)
 		return NULL;
-	skb_checksum_none_assert(skb);
-	if (RX_CMP_L4_CS_OK(rxcmp1)) {
-		if (bp->dev->features & NETIF_F_RXCSUM) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = RX_CMP_ENCAP(rxcmp1);
-		}
-	}
+
 	xdp_update_skb_shared_info(skb, num_frags,
 				   sinfo->xdp_frags_size,
-				   BNXT_RX_PAGE_SIZE * sinfo->nr_frags,
+				   BNXT_RX_PAGE_SIZE * num_frags,
 				   xdp_buff_is_frag_pfmemalloc(xdp));
 	return skb;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 0122782400b8..220285e190fc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -33,6 +33,5 @@ void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
 			      struct xdp_buff *xdp);
 struct sk_buff *bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb,
 				   u8 num_frags, struct page_pool *pool,
-				   struct xdp_buff *xdp,
-				   struct rx_cmp_ext *rxcmp1);
+				   struct xdp_buff *xdp);
 #endif
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 3e93f957430b..fa0077bc67b7 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) controller driver
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #define pr_fmt(fmt)				"bcmgenet: " fmt
@@ -41,15 +41,13 @@
 
 #include "bcmgenet.h"
 
-/* Maximum number of hardware queues, downsized if needed */
-#define GENET_MAX_MQ_CNT	4
-
 /* Default highest priority queue for multi queue support */
-#define GENET_Q0_PRIORITY	0
+#define GENET_Q1_PRIORITY	0
+#define GENET_Q0_PRIORITY	1
 
-#define GENET_Q16_RX_BD_CNT	\
+#define GENET_Q0_RX_BD_CNT	\
 	(TOTAL_DESC - priv->hw_params->rx_queues * priv->hw_params->rx_bds_per_q)
-#define GENET_Q16_TX_BD_CNT	\
+#define GENET_Q0_TX_BD_CNT	\
 	(TOTAL_DESC - priv->hw_params->tx_queues * priv->hw_params->tx_bds_per_q)
 
 #define RX_BUF_LENGTH		2048
@@ -104,7 +102,7 @@ static inline void dmadesc_set_addr(struct bcmgenet_priv *priv,
 	 * the platform is explicitly configured for 64-bits/LPAE.
 	 */
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	if (priv->hw_params->flags & GENET_HAS_40BITS)
+	if (bcmgenet_has_40bits(priv))
 		bcmgenet_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI);
 #endif
 }
@@ -446,33 +444,48 @@ static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index)
 	u32 offset;
 	u32 reg;
 
-	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	reg |= (1 << (f_index % 32));
-	bcmgenet_hfb_reg_writel(priv, reg, offset);
-	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-	reg |= RBUF_HFB_EN;
-	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		reg |= (1 << ((f_index % 32) + RBUF_HFB_FILTER_EN_SHIFT)) |
+			RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	} else {
+		offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
+		reg = bcmgenet_hfb_reg_readl(priv, offset);
+		reg |= (1 << (f_index % 32));
+		bcmgenet_hfb_reg_writel(priv, reg, offset);
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		reg |= RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	}
 }
 
 static void bcmgenet_hfb_disable_filter(struct bcmgenet_priv *priv, u32 f_index)
 {
 	u32 offset, reg, reg1;
 
-	offset = HFB_FLT_ENABLE_V3PLUS;
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	reg1 = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
-	if  (f_index < 32) {
-		reg1 &= ~(1 << (f_index % 32));
-		bcmgenet_hfb_reg_writel(priv, reg1, offset + sizeof(u32));
-	} else {
-		reg &= ~(1 << (f_index % 32));
-		bcmgenet_hfb_reg_writel(priv, reg, offset);
-	}
-	if (!reg && !reg1) {
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
 		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-		reg &= ~RBUF_HFB_EN;
+		reg &= ~(1 << ((f_index % 32) + RBUF_HFB_FILTER_EN_SHIFT));
+		if (!(reg & RBUF_HFB_FILTER_EN_MASK))
+			reg &= ~RBUF_HFB_EN;
 		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	} else {
+		offset = HFB_FLT_ENABLE_V3PLUS;
+		reg = bcmgenet_hfb_reg_readl(priv, offset);
+		reg1 = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
+		if  (f_index < 32) {
+			reg1 &= ~(1 << (f_index % 32));
+			bcmgenet_hfb_reg_writel(priv, reg1, offset + sizeof(u32));
+		} else {
+			reg &= ~(1 << (f_index % 32));
+			bcmgenet_hfb_reg_writel(priv, reg, offset);
+		}
+		if (!reg && !reg1) {
+			reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+			reg &= ~RBUF_HFB_EN;
+			bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+		}
 	}
 }
 
@@ -482,6 +495,9 @@ static void bcmgenet_hfb_set_filter_rx_queue_mapping(struct bcmgenet_priv *priv,
 	u32 offset;
 	u32 reg;
 
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
+		return;
+
 	offset = f_index / 8;
 	reg = bcmgenet_rdma_readl(priv, DMA_INDEX2RING_0 + offset);
 	reg &= ~(0xF << (4 * (f_index % 8)));
@@ -495,9 +511,13 @@ static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv,
 	u32 offset;
 	u32 reg;
 
-	offset = HFB_FLT_LEN_V3PLUS +
-		 ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4) *
-		 sizeof(u32);
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
+		offset = HFB_FLT_LEN_V2;
+	else
+		offset = HFB_FLT_LEN_V3PLUS;
+
+	offset += sizeof(u32) *
+		  ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4);
 	reg = bcmgenet_hfb_reg_readl(priv, offset);
 	reg &= ~(0xFF << (8 * (f_index % 4)));
 	reg |= ((f_length & 0xFF) << (8 * (f_index % 4)));
@@ -579,13 +599,13 @@ static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 					     struct bcmgenet_rxnfc_rule *rule)
 {
 	struct ethtool_rx_flow_spec *fs = &rule->fs;
-	u32 offset = 0, f_length = 0, f;
+	u32 offset = 0, f_length = 0, f, q;
 	u8 val_8, mask_8;
 	__be16 val_16;
 	u16 mask_16;
 	size_t size;
 
-	f = fs->location;
+	f = fs->location + 1;
 	if (fs->flow_type & FLOW_MAC_EXT) {
 		bcmgenet_hfb_insert_data(priv, f, 0,
 					 &fs->h_ext.h_dest, &fs->m_ext.h_dest,
@@ -667,19 +687,16 @@ static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 	}
 
 	bcmgenet_hfb_set_filter_length(priv, f, 2 * f_length);
-	if (!fs->ring_cookie || fs->ring_cookie == RX_CLS_FLOW_WAKE) {
-		/* Ring 0 flows can be handled by the default Descriptor Ring
-		 * We'll map them to ring 0, but don't enable the filter
-		 */
-		bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, 0);
-		rule->state = BCMGENET_RXNFC_STATE_DISABLED;
-	} else {
+	if (fs->ring_cookie == RX_CLS_FLOW_WAKE)
+		q = 0;
+	else if (fs->ring_cookie == RX_CLS_FLOW_DISC)
+		q = priv->hw_params->rx_queues + 1;
+	else
 		/* Other Rx rings are direct mapped here */
-		bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f,
-							 fs->ring_cookie);
-		bcmgenet_hfb_enable_filter(priv, f);
-		rule->state = BCMGENET_RXNFC_STATE_ENABLED;
-	}
+		q = fs->ring_cookie;
+	bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, q);
+	bcmgenet_hfb_enable_filter(priv, f);
+	rule->state = BCMGENET_RXNFC_STATE_ENABLED;
 }
 
 /* bcmgenet_hfb_clear
@@ -690,6 +707,7 @@ static void bcmgenet_hfb_clear_filter(struct bcmgenet_priv *priv, u32 f_index)
 {
 	u32 base, i;
 
+	bcmgenet_hfb_set_filter_length(priv, f_index, 0);
 	base = f_index * priv->hw_params->hfb_filter_size;
 	for (i = 0; i < priv->hw_params->hfb_filter_size; i++)
 		bcmgenet_hfb_writel(priv, 0x0, (base + i) * sizeof(u32));
@@ -699,22 +717,23 @@ static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv)
 {
 	u32 i;
 
-	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
-		return;
-
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_CTRL);
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS);
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS + 4);
-
-	for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
-		bcmgenet_rdma_writel(priv, 0x0, i);
+	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
 
-	for (i = 0; i < (priv->hw_params->hfb_filter_cnt / 4); i++)
-		bcmgenet_hfb_reg_writel(priv, 0x0,
-					HFB_FLT_LEN_V3PLUS + i * sizeof(u32));
+	if (!GENET_IS_V1(priv) && !GENET_IS_V2(priv)) {
+		bcmgenet_hfb_reg_writel(priv, 0,
+					HFB_FLT_ENABLE_V3PLUS);
+		bcmgenet_hfb_reg_writel(priv, 0,
+					HFB_FLT_ENABLE_V3PLUS + 4);
+		for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
+			bcmgenet_rdma_writel(priv, 0, i);
+	}
 
 	for (i = 0; i < priv->hw_params->hfb_filter_cnt; i++)
 		bcmgenet_hfb_clear_filter(priv, i);
+
+	/* Enable filter 0 to send default flow to ring 0 */
+	bcmgenet_hfb_set_filter_length(priv, 0, 4);
+	bcmgenet_hfb_enable_filter(priv, 0);
 }
 
 static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
@@ -722,9 +741,6 @@ static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
 	int i;
 
 	INIT_LIST_HEAD(&priv->rxnfc_list);
-	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
-		return;
-
 	for (i = 0; i < MAX_NUM_OF_FS_RULES; i++) {
 		INIT_LIST_HEAD(&priv->rxnfc_rules[i].list);
 		priv->rxnfc_rules[i].state = BCMGENET_RXNFC_STATE_UNUSED;
@@ -819,20 +835,16 @@ static int bcmgenet_get_coalesce(struct net_device *dev,
 	unsigned int i;
 
 	ec->tx_max_coalesced_frames =
-		bcmgenet_tdma_ring_readl(priv, DESC_INDEX,
-					 DMA_MBUF_DONE_THRESH);
+		bcmgenet_tdma_ring_readl(priv, 0, DMA_MBUF_DONE_THRESH);
 	ec->rx_max_coalesced_frames =
-		bcmgenet_rdma_ring_readl(priv, DESC_INDEX,
-					 DMA_MBUF_DONE_THRESH);
+		bcmgenet_rdma_ring_readl(priv, 0, DMA_MBUF_DONE_THRESH);
 	ec->rx_coalesce_usecs =
-		bcmgenet_rdma_readl(priv, DMA_RING16_TIMEOUT) * 8192 / 1000;
+		bcmgenet_rdma_readl(priv, DMA_RING0_TIMEOUT) * 8192 / 1000;
 
-	for (i = 0; i < priv->hw_params->rx_queues; i++) {
+	for (i = 0; i <= priv->hw_params->rx_queues; i++) {
 		ring = &priv->rx_rings[i];
 		ec->use_adaptive_rx_coalesce |= ring->dim.use_dim;
 	}
-	ring = &priv->rx_rings[DESC_INDEX];
-	ec->use_adaptive_rx_coalesce |= ring->dim.use_dim;
 
 	return 0;
 }
@@ -902,17 +914,13 @@ static int bcmgenet_set_coalesce(struct net_device *dev,
 	/* Program all TX queues with the same values, as there is no
 	 * ethtool knob to do coalescing on a per-queue basis
 	 */
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
+	for (i = 0; i <= priv->hw_params->tx_queues; i++)
 		bcmgenet_tdma_ring_writel(priv, i,
 					  ec->tx_max_coalesced_frames,
 					  DMA_MBUF_DONE_THRESH);
-	bcmgenet_tdma_ring_writel(priv, DESC_INDEX,
-				  ec->tx_max_coalesced_frames,
-				  DMA_MBUF_DONE_THRESH);
 
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		bcmgenet_set_ring_rx_coalesce(&priv->rx_rings[i], ec);
-	bcmgenet_set_ring_rx_coalesce(&priv->rx_rings[DESC_INDEX], ec);
 
 	return 0;
 }
@@ -961,12 +969,13 @@ static int bcmgenet_set_pauseparam(struct net_device *dev,
 
 /* standard ethtool support functions. */
 enum bcmgenet_stat_type {
-	BCMGENET_STAT_NETDEV = -1,
+	BCMGENET_STAT_RTNL = -1,
 	BCMGENET_STAT_MIB_RX,
 	BCMGENET_STAT_MIB_TX,
 	BCMGENET_STAT_RUNT,
 	BCMGENET_STAT_MISC,
 	BCMGENET_STAT_SOFT,
+	BCMGENET_STAT_SOFT64,
 };
 
 struct bcmgenet_stats {
@@ -976,13 +985,15 @@ struct bcmgenet_stats {
 	enum bcmgenet_stat_type type;
 	/* reg offset from UMAC base for misc counters */
 	u16 reg_offset;
+	/* sync for u64 stats counters */
+	int syncp_offset;
 };
 
-#define STAT_NETDEV(m) { \
+#define STAT_RTNL(m) { \
 	.stat_string = __stringify(m), \
-	.stat_sizeof = sizeof(((struct net_device_stats *)0)->m), \
-	.stat_offset = offsetof(struct net_device_stats, m), \
-	.type = BCMGENET_STAT_NETDEV, \
+	.stat_sizeof = sizeof(((struct rtnl_link_stats64 *)0)->m), \
+	.stat_offset = offsetof(struct rtnl_link_stats64, m), \
+	.type = BCMGENET_STAT_RTNL, \
 }
 
 #define STAT_GENET_MIB(str, m, _type) { \
@@ -992,6 +1003,14 @@ struct bcmgenet_stats {
 	.type = _type, \
 }
 
+#define STAT_GENET_SOFT_MIB64(str, s, m) { \
+	.stat_string = str, \
+	.stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->s.m), \
+	.stat_offset = offsetof(struct bcmgenet_priv, s.m), \
+	.type = BCMGENET_STAT_SOFT64, \
+	.syncp_offset = offsetof(struct bcmgenet_priv, s.syncp), \
+}
+
 #define STAT_GENET_MIB_RX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_RX)
 #define STAT_GENET_MIB_TX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_TX)
 #define STAT_GENET_RUNT(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_RUNT)
@@ -1006,18 +1025,38 @@ struct bcmgenet_stats {
 }
 
 #define STAT_GENET_Q(num) \
-	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_packets", \
-			tx_rings[num].packets), \
-	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_bytes", \
-			tx_rings[num].bytes), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_bytes", \
-			rx_rings[num].bytes),	 \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_packets", \
-			rx_rings[num].packets), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_errors", \
-			rx_rings[num].errors), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_dropped", \
-			rx_rings[num].dropped)
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_packets", \
+			tx_rings[num].stats64, packets), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_bytes", \
+			tx_rings[num].stats64, bytes), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_errors", \
+			tx_rings[num].stats64, errors), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_dropped", \
+			tx_rings[num].stats64, dropped), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_bytes", \
+			rx_rings[num].stats64, bytes),	 \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_packets", \
+			rx_rings[num].stats64, packets), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_errors", \
+			rx_rings[num].stats64, errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_dropped", \
+			rx_rings[num].stats64, dropped), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_multicast", \
+			rx_rings[num].stats64, multicast), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_missed", \
+			rx_rings[num].stats64, missed), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_length_errors", \
+			rx_rings[num].stats64, length_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_over_errors", \
+			rx_rings[num].stats64, over_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_crc_errors", \
+			rx_rings[num].stats64, crc_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_frame_errors", \
+			rx_rings[num].stats64, frame_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_fragmented_errors", \
+			rx_rings[num].stats64, fragmented_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_broadcast", \
+			rx_rings[num].stats64, broadcast)
 
 /* There is a 0xC gap between the end of RX and beginning of TX stats and then
  * between the end of TX stats and the beginning of the RX RUNT
@@ -1029,15 +1068,20 @@ struct bcmgenet_stats {
  */
 static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	/* general stats */
-	STAT_NETDEV(rx_packets),
-	STAT_NETDEV(tx_packets),
-	STAT_NETDEV(rx_bytes),
-	STAT_NETDEV(tx_bytes),
-	STAT_NETDEV(rx_errors),
-	STAT_NETDEV(tx_errors),
-	STAT_NETDEV(rx_dropped),
-	STAT_NETDEV(tx_dropped),
-	STAT_NETDEV(multicast),
+	STAT_RTNL(rx_packets),
+	STAT_RTNL(tx_packets),
+	STAT_RTNL(rx_bytes),
+	STAT_RTNL(tx_bytes),
+	STAT_RTNL(rx_errors),
+	STAT_RTNL(tx_errors),
+	STAT_RTNL(rx_dropped),
+	STAT_RTNL(tx_dropped),
+	STAT_RTNL(multicast),
+	STAT_RTNL(rx_missed_errors),
+	STAT_RTNL(rx_length_errors),
+	STAT_RTNL(rx_over_errors),
+	STAT_RTNL(rx_crc_errors),
+	STAT_RTNL(rx_frame_errors),
 	/* UniMAC RSV counters */
 	STAT_GENET_MIB_RX("rx_64_octets", mib.rx.pkt_cnt.cnt_64),
 	STAT_GENET_MIB_RX("rx_65_127_oct", mib.rx.pkt_cnt.cnt_127),
@@ -1120,11 +1164,25 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	STAT_GENET_Q(1),
 	STAT_GENET_Q(2),
 	STAT_GENET_Q(3),
-	STAT_GENET_Q(16),
+	STAT_GENET_Q(4),
 };
 
 #define BCMGENET_STATS_LEN	ARRAY_SIZE(bcmgenet_gstrings_stats)
 
+#define BCMGENET_STATS64_ADD(stats, m, v) \
+	do { \
+		u64_stats_update_begin(&stats->syncp); \
+		u64_stats_add(&stats->m, v); \
+		u64_stats_update_end(&stats->syncp); \
+	} while (0)
+
+#define BCMGENET_STATS64_INC(stats, m) \
+	do { \
+		u64_stats_update_begin(&stats->syncp); \
+		u64_stats_inc(&stats->m); \
+		u64_stats_update_end(&stats->syncp); \
+	} while (0)
+
 static void bcmgenet_get_drvinfo(struct net_device *dev,
 				 struct ethtool_drvinfo *info)
 {
@@ -1208,8 +1266,9 @@ static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
 
 		s = &bcmgenet_gstrings_stats[i];
 		switch (s->type) {
-		case BCMGENET_STAT_NETDEV:
+		case BCMGENET_STAT_RTNL:
 		case BCMGENET_STAT_SOFT:
+		case BCMGENET_STAT_SOFT64:
 			continue;
 		case BCMGENET_STAT_RUNT:
 			offset += BCMGENET_STAT_OFFSET;
@@ -1247,28 +1306,40 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 				       u64 *data)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct rtnl_link_stats64 stats64;
+	struct u64_stats_sync *syncp;
+	unsigned int start;
 	int i;
 
 	if (netif_running(dev))
 		bcmgenet_update_mib_counters(priv);
 
-	dev->netdev_ops->ndo_get_stats(dev);
+	dev_get_stats(dev, &stats64);
 
 	for (i = 0; i < BCMGENET_STATS_LEN; i++) {
 		const struct bcmgenet_stats *s;
 		char *p;
 
 		s = &bcmgenet_gstrings_stats[i];
-		if (s->type == BCMGENET_STAT_NETDEV)
-			p = (char *)&dev->stats;
-		else
-			p = (char *)priv;
-		p += s->stat_offset;
-		if (sizeof(unsigned long) != sizeof(u32) &&
-		    s->stat_sizeof == sizeof(unsigned long))
-			data[i] = *(unsigned long *)p;
-		else
-			data[i] = *(u32 *)p;
+		p = (char *)priv;
+
+		if (s->type == BCMGENET_STAT_SOFT64) {
+			syncp = (struct u64_stats_sync *)(p + s->syncp_offset);
+			do {
+				start = u64_stats_fetch_begin(syncp);
+				data[i] = u64_stats_read((u64_stats_t *)(p + s->stat_offset));
+			} while (u64_stats_fetch_retry(syncp, start));
+		} else {
+			if (s->type == BCMGENET_STAT_RTNL)
+				p = (char *)&stats64;
+
+			p += s->stat_offset;
+			if (sizeof(unsigned long) != sizeof(u32) &&
+				s->stat_sizeof == sizeof(unsigned long))
+				data[i] = *(unsigned long *)p;
+			else
+				data[i] = *(u32 *)p;
+		}
 	}
 }
 
@@ -1438,7 +1509,8 @@ static int bcmgenet_insert_flow(struct net_device *dev,
 	}
 
 	if (cmd->fs.ring_cookie > priv->hw_params->rx_queues &&
-	    cmd->fs.ring_cookie != RX_CLS_FLOW_WAKE) {
+	    cmd->fs.ring_cookie != RX_CLS_FLOW_WAKE &&
+	    cmd->fs.ring_cookie != RX_CLS_FLOW_DISC) {
 		netdev_err(dev, "rxnfc: Unsupported action (%llu)\n",
 			   cmd->fs.ring_cookie);
 		return -EINVAL;
@@ -1472,10 +1544,10 @@ static int bcmgenet_insert_flow(struct net_device *dev,
 		loc_rule = &priv->rxnfc_rules[cmd->fs.location];
 	}
 	if (loc_rule->state == BCMGENET_RXNFC_STATE_ENABLED)
-		bcmgenet_hfb_disable_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_disable_filter(priv, cmd->fs.location + 1);
 	if (loc_rule->state != BCMGENET_RXNFC_STATE_UNUSED) {
 		list_del(&loc_rule->list);
-		bcmgenet_hfb_clear_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_clear_filter(priv, cmd->fs.location + 1);
 	}
 	loc_rule->state = BCMGENET_RXNFC_STATE_UNUSED;
 	memcpy(&loc_rule->fs, &cmd->fs,
@@ -1505,10 +1577,10 @@ static int bcmgenet_delete_flow(struct net_device *dev,
 	}
 
 	if (rule->state == BCMGENET_RXNFC_STATE_ENABLED)
-		bcmgenet_hfb_disable_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_disable_filter(priv, cmd->fs.location + 1);
 	if (rule->state != BCMGENET_RXNFC_STATE_UNUSED) {
 		list_del(&rule->list);
-		bcmgenet_hfb_clear_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_clear_filter(priv, cmd->fs.location + 1);
 	}
 	rule->state = BCMGENET_RXNFC_STATE_UNUSED;
 	memset(&rule->fs, 0, sizeof(struct ethtool_rx_flow_spec));
@@ -1651,9 +1723,9 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 
 	case GENET_POWER_PASSIVE:
 		/* Power down LED */
-		if (priv->hw_params->flags & GENET_HAS_EXT) {
+		if (bcmgenet_has_ext(priv)) {
 			reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-			if (GENET_IS_V5(priv) && !priv->ephy_16nm)
+			if (GENET_IS_V5(priv) && !bcmgenet_has_ephy_16nm(priv))
 				reg |= EXT_PWR_DOWN_PHY_EN |
 				       EXT_PWR_DOWN_PHY_RD |
 				       EXT_PWR_DOWN_PHY_SD |
@@ -1676,13 +1748,14 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 	return ret;
 }
 
-static void bcmgenet_power_up(struct bcmgenet_priv *priv,
-			      enum bcmgenet_power_mode mode)
+static int bcmgenet_power_up(struct bcmgenet_priv *priv,
+			     enum bcmgenet_power_mode mode)
 {
+	int ret = 0;
 	u32 reg;
 
-	if (!(priv->hw_params->flags & GENET_HAS_EXT))
-		return;
+	if (!bcmgenet_has_ext(priv))
+		return ret;
 
 	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
 
@@ -1690,7 +1763,7 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 	case GENET_POWER_PASSIVE:
 		reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS |
 			 EXT_ENERGY_DET_MASK);
-		if (GENET_IS_V5(priv) && !priv->ephy_16nm) {
+		if (GENET_IS_V5(priv) && !bcmgenet_has_ephy_16nm(priv)) {
 			reg &= ~(EXT_PWR_DOWN_PHY_EN |
 				 EXT_PWR_DOWN_PHY_RD |
 				 EXT_PWR_DOWN_PHY_SD |
@@ -1718,11 +1791,13 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 		}
 		break;
 	case GENET_POWER_WOL_MAGIC:
-		bcmgenet_wol_power_up_cfg(priv, mode);
-		return;
+		ret = bcmgenet_wol_power_up_cfg(priv, mode);
+		break;
 	default:
 		break;
 	}
+
+	return ret;
 }
 
 static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
@@ -1759,18 +1834,6 @@ static struct enet_cb *bcmgenet_put_txcb(struct bcmgenet_priv *priv,
 	return tx_cb_ptr;
 }
 
-static inline void bcmgenet_rx_ring16_int_disable(struct bcmgenet_rx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_RXDMA_DONE,
-				 INTRL2_CPU_MASK_SET);
-}
-
-static inline void bcmgenet_rx_ring16_int_enable(struct bcmgenet_rx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_RXDMA_DONE,
-				 INTRL2_CPU_MASK_CLEAR);
-}
-
 static inline void bcmgenet_rx_ring_int_disable(struct bcmgenet_rx_ring *ring)
 {
 	bcmgenet_intrl2_1_writel(ring->priv,
@@ -1785,18 +1848,6 @@ static inline void bcmgenet_rx_ring_int_enable(struct bcmgenet_rx_ring *ring)
 				 INTRL2_CPU_MASK_CLEAR);
 }
 
-static inline void bcmgenet_tx_ring16_int_disable(struct bcmgenet_tx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_DONE,
-				 INTRL2_CPU_MASK_SET);
-}
-
-static inline void bcmgenet_tx_ring16_int_enable(struct bcmgenet_tx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_DONE,
-				 INTRL2_CPU_MASK_CLEAR);
-}
-
 static inline void bcmgenet_tx_ring_int_enable(struct bcmgenet_tx_ring *ring)
 {
 	bcmgenet_intrl2_1_writel(ring->priv, 1 << ring->index,
@@ -1868,6 +1919,7 @@ static struct sk_buff *bcmgenet_free_rx_cb(struct device *dev,
 static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 					  struct bcmgenet_tx_ring *ring)
 {
+	struct bcmgenet_tx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	unsigned int txbds_processed = 0;
 	unsigned int bytes_compl = 0;
@@ -1877,12 +1929,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	struct sk_buff *skb;
 
 	/* Clear status before servicing to reduce spurious interrupts */
-	if (ring->index == DESC_INDEX)
-		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE,
-					 INTRL2_CPU_CLEAR);
-	else
-		bcmgenet_intrl2_1_writel(priv, (1 << ring->index),
-					 INTRL2_CPU_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, (1 << ring->index), INTRL2_CPU_CLEAR);
 
 	/* Compute how many buffers are transmitted since last xmit call */
 	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX)
@@ -1913,22 +1960,51 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	ring->free_bds += txbds_processed;
 	ring->c_index = c_index;
 
-	ring->packets += pkts_compl;
-	ring->bytes += bytes_compl;
+	u64_stats_update_begin(&stats->syncp);
+	u64_stats_add(&stats->packets, pkts_compl);
+	u64_stats_add(&stats->bytes, bytes_compl);
+	u64_stats_update_end(&stats->syncp);
 
-	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue),
+	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->index),
 				  pkts_compl, bytes_compl);
 
 	return txbds_processed;
 }
 
 static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
-				struct bcmgenet_tx_ring *ring)
+				struct bcmgenet_tx_ring *ring,
+				bool all)
 {
-	unsigned int released;
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device *kdev = &priv->pdev->dev;
+	unsigned int released, drop, wr_ptr;
+	struct enet_cb *cb_ptr;
+	struct sk_buff *skb;
 
 	spin_lock_bh(&ring->lock);
 	released = __bcmgenet_tx_reclaim(dev, ring);
+	if (all) {
+		skb = NULL;
+		drop = (ring->prod_index - ring->c_index) & DMA_C_INDEX_MASK;
+		released += drop;
+		ring->prod_index = ring->c_index & DMA_C_INDEX_MASK;
+		while (drop--) {
+			cb_ptr = bcmgenet_put_txcb(priv, ring);
+			skb = cb_ptr->skb;
+			bcmgenet_free_tx_cb(kdev, cb_ptr);
+			if (skb && cb_ptr == GENET_CB(skb)->first_cb) {
+				dev_consume_skb_any(skb);
+				skb = NULL;
+			}
+		}
+		if (skb)
+			dev_consume_skb_any(skb);
+		bcmgenet_tdma_ring_writel(priv, ring->index,
+					  ring->prod_index, TDMA_PROD_INDEX);
+		wr_ptr = ring->write_ptr * WORDS_PER_BD(priv);
+		bcmgenet_tdma_ring_writel(priv, ring->index, wr_ptr,
+					  TDMA_WRITE_PTR);
+	}
 	spin_unlock_bh(&ring->lock);
 
 	return released;
@@ -1944,14 +2020,14 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 	spin_lock(&ring->lock);
 	work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
 	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
-		txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
+		txq = netdev_get_tx_queue(ring->priv->dev, ring->index);
 		netif_tx_wake_queue(txq);
 	}
 	spin_unlock(&ring->lock);
 
 	if (work_done == 0) {
 		napi_complete(napi);
-		ring->int_enable(ring);
+		bcmgenet_tx_ring_int_enable(ring);
 
 		return 0;
 	}
@@ -1962,22 +2038,21 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 static void bcmgenet_tx_reclaim_all(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int i;
-
-	if (netif_is_multiqueue(dev)) {
-		for (i = 0; i < priv->hw_params->tx_queues; i++)
-			bcmgenet_tx_reclaim(dev, &priv->tx_rings[i]);
-	}
+	int i = 0;
 
-	bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]);
+	do {
+		bcmgenet_tx_reclaim(dev, &priv->tx_rings[i++], true);
+	} while (i <= priv->hw_params->tx_queues && netif_is_multiqueue(dev));
 }
 
 /* Reallocate the SKB to put enough headroom in front of it and insert
  * the transmit checksum offsets in the descriptors
  */
 static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					struct bcmgenet_tx_ring *ring)
 {
+	struct bcmgenet_tx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct status_64 *status = NULL;
 	struct sk_buff *new_skb;
@@ -1994,7 +2069,7 @@ static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev,
 		if (!new_skb) {
 			dev_kfree_skb_any(skb);
 			priv->mib.tx_realloc_tsb_failed++;
-			dev->stats.tx_dropped++;
+			BCMGENET_STATS64_INC(stats, dropped);
 			return NULL;
 		}
 		dev_consume_skb_any(skb);
@@ -2057,19 +2132,14 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	index = skb_get_queue_mapping(skb);
 	/* Mapping strategy:
-	 * queue_mapping = 0, unclassified, packet xmited through ring16
-	 * queue_mapping = 1, goes to ring 0. (highest priority queue
-	 * queue_mapping = 2, goes to ring 1.
-	 * queue_mapping = 3, goes to ring 2.
-	 * queue_mapping = 4, goes to ring 3.
+	 * queue_mapping = 0, unclassified, packet xmited through ring 0
+	 * queue_mapping = 1, goes to ring 1. (highest priority queue)
+	 * queue_mapping = 2, goes to ring 2.
+	 * queue_mapping = 3, goes to ring 3.
+	 * queue_mapping = 4, goes to ring 4.
 	 */
-	if (index == 0)
-		index = DESC_INDEX;
-	else
-		index -= 1;
-
 	ring = &priv->tx_rings[index];
-	txq = netdev_get_tx_queue(dev, ring->queue);
+	txq = netdev_get_tx_queue(dev, index);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
@@ -2087,7 +2157,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	GENET_CB(skb)->bytes_sent = skb->len;
 
 	/* add the Transmit Status Block */
-	skb = bcmgenet_add_tsb(dev, skb);
+	skb = bcmgenet_add_tsb(dev, skb, ring);
 	if (!skb) {
 		ret = NETDEV_TX_OK;
 		goto out;
@@ -2229,6 +2299,7 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv,
 static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 				     unsigned int budget)
 {
+	struct bcmgenet_rx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = ring->priv;
 	struct net_device *dev = priv->dev;
 	struct enet_cb *cb;
@@ -2242,15 +2313,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	unsigned int discards;
 
 	/* Clear status before servicing to reduce spurious interrupts */
-	if (ring->index == DESC_INDEX) {
-		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE,
-					 INTRL2_CPU_CLEAR);
-	} else {
-		mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
-		bcmgenet_intrl2_1_writel(priv,
-					 mask,
-					 INTRL2_CPU_CLEAR);
-	}
+	mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
+	bcmgenet_intrl2_1_writel(priv, mask, INTRL2_CPU_CLEAR);
 
 	p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX);
 
@@ -2258,7 +2322,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		   DMA_P_INDEX_DISCARD_CNT_MASK;
 	if (discards > ring->old_discards) {
 		discards = discards - ring->old_discards;
-		ring->errors += discards;
+		BCMGENET_STATS64_ADD(stats, missed, discards);
 		ring->old_discards += discards;
 
 		/* Clear HW register when we reach 75% of maximum 0xFFFF */
@@ -2284,7 +2348,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		skb = bcmgenet_rx_refill(priv, cb);
 
 		if (unlikely(!skb)) {
-			ring->dropped++;
+			BCMGENET_STATS64_INC(stats, dropped);
 			goto next;
 		}
 
@@ -2311,8 +2375,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 		if (unlikely(len > RX_BUF_LENGTH)) {
 			netif_err(priv, rx_status, dev, "oversized packet\n");
-			dev->stats.rx_length_errors++;
-			dev->stats.rx_errors++;
+			BCMGENET_STATS64_INC(stats, length_errors);
 			dev_kfree_skb_any(skb);
 			goto next;
 		}
@@ -2320,7 +2383,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
 			netif_err(priv, rx_status, dev,
 				  "dropping fragmented packet!\n");
-			ring->errors++;
+			BCMGENET_STATS64_INC(stats, fragmented_errors);
 			dev_kfree_skb_any(skb);
 			goto next;
 		}
@@ -2333,15 +2396,22 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 						DMA_RX_RXER))) {
 			netif_err(priv, rx_status, dev, "dma_flag=0x%x\n",
 				  (unsigned int)dma_flag);
+			u64_stats_update_begin(&stats->syncp);
 			if (dma_flag & DMA_RX_CRC_ERROR)
-				dev->stats.rx_crc_errors++;
+				u64_stats_inc(&stats->crc_errors);
 			if (dma_flag & DMA_RX_OV)
-				dev->stats.rx_over_errors++;
+				u64_stats_inc(&stats->over_errors);
 			if (dma_flag & DMA_RX_NO)
-				dev->stats.rx_frame_errors++;
+				u64_stats_inc(&stats->frame_errors);
 			if (dma_flag & DMA_RX_LG)
-				dev->stats.rx_length_errors++;
-			dev->stats.rx_errors++;
+				u64_stats_inc(&stats->length_errors);
+			if ((dma_flag & (DMA_RX_CRC_ERROR |
+						DMA_RX_OV |
+						DMA_RX_NO |
+						DMA_RX_LG |
+						DMA_RX_RXER)) == DMA_RX_RXER)
+				u64_stats_inc(&stats->errors);
+			u64_stats_update_end(&stats->syncp);
 			dev_kfree_skb_any(skb);
 			goto next;
 		} /* error packet */
@@ -2361,10 +2431,15 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 		/*Finish setting up the received SKB and send it to the kernel*/
 		skb->protocol = eth_type_trans(skb, priv->dev);
-		ring->packets++;
-		ring->bytes += len;
+
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->packets);
+		u64_stats_add(&stats->bytes, len);
 		if (dma_flag & DMA_RX_MULT)
-			dev->stats.multicast++;
+			u64_stats_inc(&stats->multicast);
+		else if (dma_flag & DMA_RX_BRDCAST)
+			u64_stats_inc(&stats->broadcast);
+		u64_stats_update_end(&stats->syncp);
 
 		/* Notify kernel */
 		napi_gro_receive(&ring->napi, skb);
@@ -2399,7 +2474,7 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-		ring->int_enable(ring);
+		bcmgenet_rx_ring_int_enable(ring);
 	}
 
 	if (ring->dim.use_dim) {
@@ -2523,7 +2598,7 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
 	} else if (priv->ext_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
 	} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
-		if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
+		if (bcmgenet_has_moca_link_det(priv))
 			int0_enable |= UMAC_IRQ_LINK_EVENT;
 	}
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
@@ -2588,8 +2663,8 @@ static void init_umac(struct bcmgenet_priv *priv)
 	}
 
 	/* Enable MDIO interrupts on GENET v3+ */
-	if (priv->hw_params->flags & GENET_HAS_MDIO_INTR)
-		int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
+	if (bcmgenet_has_mdio_intr(priv))
+		int0_enable |= UMAC_IRQ_MDIO_EVENT;
 
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 
@@ -2639,15 +2714,6 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	spin_lock_init(&ring->lock);
 	ring->priv = priv;
 	ring->index = index;
-	if (index == DESC_INDEX) {
-		ring->queue = 0;
-		ring->int_enable = bcmgenet_tx_ring16_int_enable;
-		ring->int_disable = bcmgenet_tx_ring16_int_disable;
-	} else {
-		ring->queue = index + 1;
-		ring->int_enable = bcmgenet_tx_ring_int_enable;
-		ring->int_disable = bcmgenet_tx_ring_int_disable;
-	}
 	ring->cbs = priv->tx_cbs + start_ptr;
 	ring->size = size;
 	ring->clean_ptr = start_ptr;
@@ -2658,8 +2724,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	ring->end_ptr = end_ptr - 1;
 	ring->prod_index = 0;
 
-	/* Set flow period for ring != 16 */
-	if (index != DESC_INDEX)
+	/* Set flow period for ring != 0 */
+	if (index)
 		flow_period_val = ENET_MAX_MTU_SIZE << 16;
 
 	bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_PROD_INDEX);
@@ -2697,13 +2763,6 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 
 	ring->priv = priv;
 	ring->index = index;
-	if (index == DESC_INDEX) {
-		ring->int_enable = bcmgenet_rx_ring16_int_enable;
-		ring->int_disable = bcmgenet_rx_ring16_int_disable;
-	} else {
-		ring->int_enable = bcmgenet_rx_ring_int_enable;
-		ring->int_disable = bcmgenet_rx_ring_int_disable;
-	}
 	ring->cbs = priv->rx_cbs + start_ptr;
 	ring->size = size;
 	ring->c_index = 0;
@@ -2749,15 +2808,11 @@ static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_enable(&ring->napi);
-		ring->int_enable(ring);
+		bcmgenet_tx_ring_int_enable(ring);
 	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	napi_enable(&ring->napi);
-	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
@@ -2765,13 +2820,10 @@ static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_disable(&ring->napi);
 	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	napi_disable(&ring->napi);
 }
 
 static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv)
@@ -2779,82 +2831,104 @@ static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		netif_napi_del(&ring->napi);
 	}
+}
 
-	ring = &priv->tx_rings[DESC_INDEX];
-	netif_napi_del(&ring->napi);
+static int bcmgenet_tdma_disable(struct bcmgenet_priv *priv)
+{
+	int timeout = 0;
+	u32 reg, mask;
+
+	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+	mask = (1 << (priv->hw_params->tx_queues + 1)) - 1;
+	mask = (mask << DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+	reg &= ~mask;
+	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
+	/* Check DMA status register to confirm DMA is disabled */
+	while (timeout++ < DMA_TIMEOUT_VAL) {
+		reg = bcmgenet_tdma_readl(priv, DMA_STATUS);
+		if ((reg & mask) == mask)
+			return 0;
+
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int bcmgenet_rdma_disable(struct bcmgenet_priv *priv)
+{
+	int timeout = 0;
+	u32 reg, mask;
+
+	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+	mask = (1 << (priv->hw_params->rx_queues + 1)) - 1;
+	mask = (mask << DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+	reg &= ~mask;
+	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+	/* Check DMA status register to confirm DMA is disabled */
+	while (timeout++ < DMA_TIMEOUT_VAL) {
+		reg = bcmgenet_rdma_readl(priv, DMA_STATUS);
+		if ((reg & mask) == mask)
+			return 0;
+
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
 }
 
 /* Initialize Tx queues
  *
- * Queues 0-3 are priority-based, each one has 32 descriptors,
- * with queue 0 being the highest priority queue.
+ * Queues 1-4 are priority-based, each one has 32 descriptors,
+ * with queue 1 being the highest priority queue.
  *
- * Queue 16 is the default Tx queue with
- * GENET_Q16_TX_BD_CNT = 256 - 4 * 32 = 128 descriptors.
+ * Queue 0 is the default Tx queue with
+ * GENET_Q0_TX_BD_CNT = 256 - 4 * 32 = 128 descriptors.
  *
  * The transmit control block pool is then partitioned as follows:
- * - Tx queue 0 uses tx_cbs[0..31]
- * - Tx queue 1 uses tx_cbs[32..63]
- * - Tx queue 2 uses tx_cbs[64..95]
- * - Tx queue 3 uses tx_cbs[96..127]
- * - Tx queue 16 uses tx_cbs[128..255]
+ * - Tx queue 0 uses tx_cbs[0..127]
+ * - Tx queue 1 uses tx_cbs[128..159]
+ * - Tx queue 2 uses tx_cbs[160..191]
+ * - Tx queue 3 uses tx_cbs[192..223]
+ * - Tx queue 4 uses tx_cbs[224..255]
  */
 static void bcmgenet_init_tx_queues(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 i, dma_enable;
-	u32 dma_ctrl, ring_cfg;
-	u32 dma_priority[3] = {0, 0, 0};
-
-	dma_ctrl = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	dma_enable = dma_ctrl & DMA_EN;
-	dma_ctrl &= ~DMA_EN;
-	bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
-
-	dma_ctrl = 0;
-	ring_cfg = 0;
+	unsigned int start = 0, end = GENET_Q0_TX_BD_CNT;
+	u32 i, ring_mask, dma_priority[3] = {0, 0, 0};
 
 	/* Enable strict priority arbiter mode */
 	bcmgenet_tdma_writel(priv, DMA_ARBITER_SP, DMA_ARB_CTRL);
 
 	/* Initialize Tx priority queues */
-	for (i = 0; i < priv->hw_params->tx_queues; i++) {
-		bcmgenet_init_tx_ring(priv, i, priv->hw_params->tx_bds_per_q,
-				      i * priv->hw_params->tx_bds_per_q,
-				      (i + 1) * priv->hw_params->tx_bds_per_q);
-		ring_cfg |= (1 << i);
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
+	for (i = 0; i <= priv->hw_params->tx_queues; i++) {
+		bcmgenet_init_tx_ring(priv, i, end - start, start, end);
+		start = end;
+		end += priv->hw_params->tx_bds_per_q;
 		dma_priority[DMA_PRIO_REG_INDEX(i)] |=
-			((GENET_Q0_PRIORITY + i) << DMA_PRIO_REG_SHIFT(i));
+			(i ? GENET_Q1_PRIORITY : GENET_Q0_PRIORITY)
+			<< DMA_PRIO_REG_SHIFT(i);
 	}
 
-	/* Initialize Tx default queue 16 */
-	bcmgenet_init_tx_ring(priv, DESC_INDEX, GENET_Q16_TX_BD_CNT,
-			      priv->hw_params->tx_queues *
-			      priv->hw_params->tx_bds_per_q,
-			      TOTAL_DESC);
-	ring_cfg |= (1 << DESC_INDEX);
-	dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
-	dma_priority[DMA_PRIO_REG_INDEX(DESC_INDEX)] |=
-		((GENET_Q0_PRIORITY + priv->hw_params->tx_queues) <<
-		 DMA_PRIO_REG_SHIFT(DESC_INDEX));
-
 	/* Set Tx queue priorities */
 	bcmgenet_tdma_writel(priv, dma_priority[0], DMA_PRIORITY_0);
 	bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1);
 	bcmgenet_tdma_writel(priv, dma_priority[2], DMA_PRIORITY_2);
 
-	/* Enable Tx queues */
-	bcmgenet_tdma_writel(priv, ring_cfg, DMA_RING_CFG);
+	/* Configure Tx queues as descriptor rings */
+	ring_mask = (1 << (priv->hw_params->tx_queues + 1)) - 1;
+	bcmgenet_tdma_writel(priv, ring_mask, DMA_RING_CFG);
 
-	/* Enable Tx DMA */
-	if (dma_enable)
-		dma_ctrl |= DMA_EN;
-	bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
+	/* Enable Tx rings */
+	ring_mask <<= DMA_RING_BUF_EN_SHIFT;
+	bcmgenet_tdma_writel(priv, ring_mask, DMA_CTRL);
 }
 
 static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
@@ -2862,15 +2936,11 @@ static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_enable(&ring->napi);
-		ring->int_enable(ring);
+		bcmgenet_rx_ring_int_enable(ring);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	napi_enable(&ring->napi);
-	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
@@ -2878,15 +2948,11 @@ static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_disable(&ring->napi);
 		cancel_work_sync(&ring->dim.dim.work);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	napi_disable(&ring->napi);
-	cancel_work_sync(&ring->dim.dim.work);
 }
 
 static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
@@ -2894,13 +2960,10 @@ static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		netif_napi_del(&ring->napi);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	netif_napi_del(&ring->napi);
 }
 
 /* Initialize Rx queues
@@ -2908,57 +2971,32 @@ static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
  * Queues 0-15 are priority queues. Hardware Filtering Block (HFB) can be
  * used to direct traffic to these queues.
  *
- * Queue 16 is the default Rx queue with GENET_Q16_RX_BD_CNT descriptors.
+ * Queue 0 is also the default Rx queue with GENET_Q0_RX_BD_CNT descriptors.
  */
 static int bcmgenet_init_rx_queues(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 i;
-	u32 dma_enable;
-	u32 dma_ctrl;
-	u32 ring_cfg;
+	unsigned int start = 0, end = GENET_Q0_RX_BD_CNT;
+	u32 i, ring_mask;
 	int ret;
 
-	dma_ctrl = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	dma_enable = dma_ctrl & DMA_EN;
-	dma_ctrl &= ~DMA_EN;
-	bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);
-
-	dma_ctrl = 0;
-	ring_cfg = 0;
-
 	/* Initialize Rx priority queues */
-	for (i = 0; i < priv->hw_params->rx_queues; i++) {
-		ret = bcmgenet_init_rx_ring(priv, i,
-					    priv->hw_params->rx_bds_per_q,
-					    i * priv->hw_params->rx_bds_per_q,
-					    (i + 1) *
-					    priv->hw_params->rx_bds_per_q);
+	for (i = 0; i <= priv->hw_params->rx_queues; i++) {
+		ret = bcmgenet_init_rx_ring(priv, i, end - start, start, end);
 		if (ret)
 			return ret;
 
-		ring_cfg |= (1 << i);
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
+		start = end;
+		end += priv->hw_params->rx_bds_per_q;
 	}
 
-	/* Initialize Rx default queue 16 */
-	ret = bcmgenet_init_rx_ring(priv, DESC_INDEX, GENET_Q16_RX_BD_CNT,
-				    priv->hw_params->rx_queues *
-				    priv->hw_params->rx_bds_per_q,
-				    TOTAL_DESC);
-	if (ret)
-		return ret;
-
-	ring_cfg |= (1 << DESC_INDEX);
-	dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
-
-	/* Enable rings */
-	bcmgenet_rdma_writel(priv, ring_cfg, DMA_RING_CFG);
+	/* Configure Rx queues as descriptor rings */
+	ring_mask = (1 << (priv->hw_params->rx_queues + 1)) - 1;
+	bcmgenet_rdma_writel(priv, ring_mask, DMA_RING_CFG);
 
-	/* Configure ring as descriptor ring and re-enable DMA if enabled */
-	if (dma_enable)
-		dma_ctrl |= DMA_EN;
-	bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);
+	/* Enable Rx rings */
+	ring_mask <<= DMA_RING_BUF_EN_SHIFT;
+	bcmgenet_rdma_writel(priv, ring_mask, DMA_CTRL);
 
 	return 0;
 }
@@ -2966,26 +3004,9 @@ static int bcmgenet_init_rx_queues(struct net_device *dev)
 static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
 {
 	int ret = 0;
-	int timeout = 0;
-	u32 reg;
-	u32 dma_ctrl;
-	int i;
 
 	/* Disable TDMA to stop add more frames in TX DMA */
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~DMA_EN;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
-	/* Check TDMA status register to confirm TDMA is disabled */
-	while (timeout++ < DMA_TIMEOUT_VAL) {
-		reg = bcmgenet_tdma_readl(priv, DMA_STATUS);
-		if (reg & DMA_DISABLED)
-			break;
-
-		udelay(1);
-	}
-
-	if (timeout == DMA_TIMEOUT_VAL) {
+	if (-ETIMEDOUT == bcmgenet_tdma_disable(priv)) {
 		netdev_warn(priv->dev, "Timed out while disabling TX DMA\n");
 		ret = -ETIMEDOUT;
 	}
@@ -2994,39 +3015,11 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
 	usleep_range(10000, 20000);
 
 	/* Disable RDMA */
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~DMA_EN;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	timeout = 0;
-	/* Check RDMA status register to confirm RDMA is disabled */
-	while (timeout++ < DMA_TIMEOUT_VAL) {
-		reg = bcmgenet_rdma_readl(priv, DMA_STATUS);
-		if (reg & DMA_DISABLED)
-			break;
-
-		udelay(1);
-	}
-
-	if (timeout == DMA_TIMEOUT_VAL) {
+	if (-ETIMEDOUT == bcmgenet_rdma_disable(priv)) {
 		netdev_warn(priv->dev, "Timed out while disabling RX DMA\n");
 		ret = -ETIMEDOUT;
 	}
 
-	dma_ctrl = 0;
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	dma_ctrl = 0;
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
 	return ret;
 }
 
@@ -3038,32 +3031,53 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 	bcmgenet_fini_rx_napi(priv);
 	bcmgenet_fini_tx_napi(priv);
 
-	for (i = 0; i < priv->num_tx_bds; i++)
-		dev_kfree_skb(bcmgenet_free_tx_cb(&priv->pdev->dev,
-						  priv->tx_cbs + i));
-
-	for (i = 0; i < priv->hw_params->tx_queues; i++) {
-		txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[i].queue);
+	for (i = 0; i <= priv->hw_params->tx_queues; i++) {
+		txq = netdev_get_tx_queue(priv->dev, i);
 		netdev_tx_reset_queue(txq);
 	}
 
-	txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[DESC_INDEX].queue);
-	netdev_tx_reset_queue(txq);
-
 	bcmgenet_free_rx_buffers(priv);
 	kfree(priv->rx_cbs);
 	kfree(priv->tx_cbs);
 }
 
 /* init_edma: Initialize DMA control register */
-static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
+static int bcmgenet_init_dma(struct bcmgenet_priv *priv, bool flush_rx)
 {
-	int ret;
-	unsigned int i;
 	struct enet_cb *cb;
+	unsigned int i;
+	int ret;
+	u32 reg;
 
 	netif_dbg(priv, hw, priv->dev, "%s\n", __func__);
 
+	/* Disable TX DMA */
+	ret = bcmgenet_tdma_disable(priv);
+	if (ret) {
+		netdev_err(priv->dev, "failed to halt Tx DMA\n");
+		return ret;
+	}
+
+	/* Disable RX DMA */
+	ret = bcmgenet_rdma_disable(priv);
+	if (ret) {
+		netdev_err(priv->dev, "failed to halt Rx DMA\n");
+		return ret;
+	}
+
+	/* Flush TX queues */
+	bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
+	udelay(10);
+	bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);
+
+	if (flush_rx) {
+		reg = bcmgenet_rbuf_ctrl_get(priv);
+		bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0));
+		udelay(10);
+		bcmgenet_rbuf_ctrl_set(priv, reg);
+		udelay(10);
+	}
+
 	/* Initialize common Rx ring structures */
 	priv->rx_bds = priv->base + priv->hw_params->rdma_offset;
 	priv->num_rx_bds = TOTAL_DESC;
@@ -3113,6 +3127,15 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
 	/* Initialize Tx queues */
 	bcmgenet_init_tx_queues(priv->dev);
 
+	/* Enable RX/TX DMA */
+	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+	reg |= DMA_EN;
+	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+	reg |= DMA_EN;
+	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
 	return 0;
 }
 
@@ -3142,7 +3165,7 @@ static void bcmgenet_irq_task(struct work_struct *work)
 
 }
 
-/* bcmgenet_isr1: handle Rx and Tx priority queues */
+/* bcmgenet_isr1: handle Rx and Tx queues */
 static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 {
 	struct bcmgenet_priv *priv = dev_id;
@@ -3161,7 +3184,7 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 		  "%s: IRQ=0x%x\n", __func__, status);
 
 	/* Check Rx priority queue interrupts */
-	for (index = 0; index < priv->hw_params->rx_queues; index++) {
+	for (index = 0; index <= priv->hw_params->rx_queues; index++) {
 		if (!(status & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
 			continue;
 
@@ -3169,20 +3192,20 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 		rx_ring->dim.event_ctr++;
 
 		if (likely(napi_schedule_prep(&rx_ring->napi))) {
-			rx_ring->int_disable(rx_ring);
+			bcmgenet_rx_ring_int_disable(rx_ring);
 			__napi_schedule_irqoff(&rx_ring->napi);
 		}
 	}
 
 	/* Check Tx priority queue interrupts */
-	for (index = 0; index < priv->hw_params->tx_queues; index++) {
+	for (index = 0; index <= priv->hw_params->tx_queues; index++) {
 		if (!(status & BIT(index)))
 			continue;
 
 		tx_ring = &priv->tx_rings[index];
 
 		if (likely(napi_schedule_prep(&tx_ring->napi))) {
-			tx_ring->int_disable(tx_ring);
+			bcmgenet_tx_ring_int_disable(tx_ring);
 			__napi_schedule_irqoff(&tx_ring->napi);
 		}
 	}
@@ -3190,12 +3213,10 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-/* bcmgenet_isr0: handle Rx and Tx default queues + other stuff */
+/* bcmgenet_isr0: handle other stuff */
 static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 {
 	struct bcmgenet_priv *priv = dev_id;
-	struct bcmgenet_rx_ring *rx_ring;
-	struct bcmgenet_tx_ring *tx_ring;
 	unsigned int status;
 	unsigned long flags;
 
@@ -3209,29 +3230,8 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	netif_dbg(priv, intr, priv->dev,
 		  "IRQ=0x%x\n", status);
 
-	if (status & UMAC_IRQ_RXDMA_DONE) {
-		rx_ring = &priv->rx_rings[DESC_INDEX];
-		rx_ring->dim.event_ctr++;
-
-		if (likely(napi_schedule_prep(&rx_ring->napi))) {
-			rx_ring->int_disable(rx_ring);
-			__napi_schedule_irqoff(&rx_ring->napi);
-		}
-	}
-
-	if (status & UMAC_IRQ_TXDMA_DONE) {
-		tx_ring = &priv->tx_rings[DESC_INDEX];
-
-		if (likely(napi_schedule_prep(&tx_ring->napi))) {
-			tx_ring->int_disable(tx_ring);
-			__napi_schedule_irqoff(&tx_ring->napi);
-		}
-	}
-
-	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
-		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
+	if (bcmgenet_has_mdio_intr(priv) && status & UMAC_IRQ_MDIO_EVENT)
 		wake_up(&priv->wq);
-	}
 
 	/* all other interested interrupts handled in bottom half */
 	status &= (UMAC_IRQ_LINK_EVENT | UMAC_IRQ_PHY_DET_R);
@@ -3285,56 +3285,6 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv,
 	put_unaligned_be16(addr_tmp, &addr[4]);
 }
 
-/* Returns a reusable dma control register value */
-static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx)
-{
-	unsigned int i;
-	u32 reg;
-	u32 dma_ctrl;
-
-	/* disable DMA */
-	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
-	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
-	udelay(10);
-	bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);
-
-	if (flush_rx) {
-		reg = bcmgenet_rbuf_ctrl_get(priv);
-		bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0));
-		udelay(10);
-		bcmgenet_rbuf_ctrl_set(priv, reg);
-		udelay(10);
-	}
-
-	return dma_ctrl;
-}
-
-static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl)
-{
-	u32 reg;
-
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg |= dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg |= dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-}
-
 static void bcmgenet_netif_start(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -3358,7 +3308,6 @@ static void bcmgenet_netif_start(struct net_device *dev)
 static int bcmgenet_open(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	unsigned long dma_ctrl;
 	int ret;
 
 	netif_dbg(priv, ifup, dev, "bcmgenet_open\n");
@@ -3384,22 +3333,16 @@ static int bcmgenet_open(struct net_device *dev)
 
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
 
-	/* Disable RX/TX DMA and flush TX and RX queues */
-	dma_ctrl = bcmgenet_dma_disable(priv, true);
+	/* HFB init */
+	bcmgenet_hfb_init(priv);
 
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
-	ret = bcmgenet_init_dma(priv);
+	ret = bcmgenet_init_dma(priv, true);
 	if (ret) {
 		netdev_err(dev, "failed to initialize DMA\n");
 		goto err_clk_disable;
 	}
 
-	/* Always enable ring 16 - descriptor ring */
-	bcmgenet_enable_dma(priv, dma_ctrl);
-
-	/* HFB init */
-	bcmgenet_hfb_init(priv);
-
 	ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED,
 			  dev->name, priv);
 	if (ret < 0) {
@@ -3446,19 +3389,21 @@ static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
-	bcmgenet_disable_tx_napi(priv);
 	netif_tx_disable(dev);
 
 	/* Disable MAC receive */
+	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
 	umac_enable_set(priv, CMD_RX_EN, false);
 
+	if (stop_phy)
+		phy_stop(dev->phydev);
+
 	bcmgenet_dma_teardown(priv);
 
 	/* Disable MAC transmit. TX DMA disabled must be done before this */
 	umac_enable_set(priv, CMD_TX_EN, false);
 
-	if (stop_phy)
-		phy_stop(dev->phydev);
+	bcmgenet_disable_tx_napi(priv);
 	bcmgenet_disable_rx_napi(priv);
 	bcmgenet_intr_disable(priv);
 
@@ -3506,16 +3451,11 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 	if (!netif_msg_tx_err(priv))
 		return;
 
-	txq = netdev_get_tx_queue(priv->dev, ring->queue);
+	txq = netdev_get_tx_queue(priv->dev, ring->index);
 
 	spin_lock(&ring->lock);
-	if (ring->index == DESC_INDEX) {
-		intsts = ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
-		intmsk = UMAC_IRQ_TXDMA_DONE | UMAC_IRQ_TXDMA_MBDONE;
-	} else {
-		intsts = ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
-		intmsk = 1 << ring->index;
-	}
+	intsts = ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
+	intmsk = 1 << ring->index;
 	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX);
 	p_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_PROD_INDEX);
 	txq_stopped = netif_tx_queue_stopped(txq);
@@ -3529,7 +3469,7 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 		  "(sw)c_index: %d (hw)c_index: %d\n"
 		  "(sw)clean_p: %d (sw)write_p: %d\n"
 		  "(sw)cb_ptr: %d (sw)end_ptr: %d\n",
-		  ring->index, ring->queue,
+		  ring->index, ring->index,
 		  txq_stopped ? "stopped" : "active",
 		  intsts & intmsk ? "enabled" : "disabled",
 		  free_bds, ring->size,
@@ -3542,30 +3482,25 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 static void bcmgenet_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 int0_enable = 0;
 	u32 int1_enable = 0;
 	unsigned int q;
 
 	netif_dbg(priv, tx_err, dev, "bcmgenet_timeout\n");
 
-	for (q = 0; q < priv->hw_params->tx_queues; q++)
+	for (q = 0; q <= priv->hw_params->tx_queues; q++)
 		bcmgenet_dump_tx_queue(&priv->tx_rings[q]);
-	bcmgenet_dump_tx_queue(&priv->tx_rings[DESC_INDEX]);
 
 	bcmgenet_tx_reclaim_all(dev);
 
-	for (q = 0; q < priv->hw_params->tx_queues; q++)
+	for (q = 0; q <= priv->hw_params->tx_queues; q++)
 		int1_enable |= (1 << q);
 
-	int0_enable = UMAC_IRQ_TXDMA_DONE;
-
 	/* Re-enable TX interrupts if disabled */
-	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 
 	netif_trans_update(dev);
 
-	dev->stats.tx_errors++;
+	BCMGENET_STATS64_INC((&priv->tx_rings[txqueue].stats64), errors);
 
 	netif_tx_wake_all_queues(dev);
 }
@@ -3654,47 +3589,72 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p)
 	return 0;
 }
 
-static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
+static void bcmgenet_get_stats64(struct net_device *dev,
+				 struct rtnl_link_stats64 *stats)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	unsigned long tx_bytes = 0, tx_packets = 0;
-	unsigned long rx_bytes = 0, rx_packets = 0;
-	unsigned long rx_errors = 0, rx_dropped = 0;
-	struct bcmgenet_tx_ring *tx_ring;
-	struct bcmgenet_rx_ring *rx_ring;
+	struct bcmgenet_tx_stats64 *tx_stats;
+	struct bcmgenet_rx_stats64 *rx_stats;
+	u64 rx_length_errors, rx_over_errors;
+	u64 rx_missed, rx_fragmented_errors;
+	u64 rx_crc_errors, rx_frame_errors;
+	u64 tx_errors, tx_dropped;
+	u64 rx_errors, rx_dropped;
+	u64 tx_bytes, tx_packets;
+	u64 rx_bytes, rx_packets;
+	unsigned int start;
 	unsigned int q;
-
-	for (q = 0; q < priv->hw_params->tx_queues; q++) {
-		tx_ring = &priv->tx_rings[q];
-		tx_bytes += tx_ring->bytes;
-		tx_packets += tx_ring->packets;
+	u64 multicast;
+
+	for (q = 0; q <= priv->hw_params->tx_queues; q++) {
+		tx_stats = &priv->tx_rings[q].stats64;
+		do {
+			start = u64_stats_fetch_begin(&tx_stats->syncp);
+			tx_bytes = u64_stats_read(&tx_stats->bytes);
+			tx_packets = u64_stats_read(&tx_stats->packets);
+			tx_errors = u64_stats_read(&tx_stats->errors);
+			tx_dropped = u64_stats_read(&tx_stats->dropped);
+		} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
+
+		stats->tx_bytes += tx_bytes;
+		stats->tx_packets += tx_packets;
+		stats->tx_errors += tx_errors;
+		stats->tx_dropped += tx_dropped;
 	}
-	tx_ring = &priv->tx_rings[DESC_INDEX];
-	tx_bytes += tx_ring->bytes;
-	tx_packets += tx_ring->packets;
-
-	for (q = 0; q < priv->hw_params->rx_queues; q++) {
-		rx_ring = &priv->rx_rings[q];
 
-		rx_bytes += rx_ring->bytes;
-		rx_packets += rx_ring->packets;
-		rx_errors += rx_ring->errors;
-		rx_dropped += rx_ring->dropped;
+	for (q = 0; q <= priv->hw_params->rx_queues; q++) {
+		rx_stats = &priv->rx_rings[q].stats64;
+		do {
+			start = u64_stats_fetch_begin(&rx_stats->syncp);
+			rx_bytes = u64_stats_read(&rx_stats->bytes);
+			rx_packets = u64_stats_read(&rx_stats->packets);
+			rx_errors = u64_stats_read(&rx_stats->errors);
+			rx_dropped = u64_stats_read(&rx_stats->dropped);
+			rx_missed = u64_stats_read(&rx_stats->missed);
+			rx_length_errors = u64_stats_read(&rx_stats->length_errors);
+			rx_over_errors = u64_stats_read(&rx_stats->over_errors);
+			rx_crc_errors = u64_stats_read(&rx_stats->crc_errors);
+			rx_frame_errors = u64_stats_read(&rx_stats->frame_errors);
+			rx_fragmented_errors = u64_stats_read(&rx_stats->fragmented_errors);
+			multicast = u64_stats_read(&rx_stats->multicast);
+		} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
+
+		rx_errors += rx_length_errors;
+		rx_errors += rx_crc_errors;
+		rx_errors += rx_frame_errors;
+		rx_errors += rx_fragmented_errors;
+
+		stats->rx_bytes += rx_bytes;
+		stats->rx_packets += rx_packets;
+		stats->rx_errors += rx_errors;
+		stats->rx_dropped += rx_dropped;
+		stats->rx_missed_errors += rx_missed;
+		stats->rx_length_errors += rx_length_errors;
+		stats->rx_over_errors += rx_over_errors;
+		stats->rx_crc_errors += rx_crc_errors;
+		stats->rx_frame_errors += rx_frame_errors;
+		stats->multicast += multicast;
 	}
-	rx_ring = &priv->rx_rings[DESC_INDEX];
-	rx_bytes += rx_ring->bytes;
-	rx_packets += rx_ring->packets;
-	rx_errors += rx_ring->errors;
-	rx_dropped += rx_ring->dropped;
-
-	dev->stats.tx_bytes = tx_bytes;
-	dev->stats.tx_packets = tx_packets;
-	dev->stats.rx_bytes = rx_bytes;
-	dev->stats.rx_packets = rx_packets;
-	dev->stats.rx_errors = rx_errors;
-	dev->stats.rx_missed_errors = rx_errors;
-	dev->stats.rx_dropped = rx_dropped;
-	return &dev->stats;
 }
 
 static int bcmgenet_change_carrier(struct net_device *dev, bool new_carrier)
@@ -3722,132 +3682,113 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_set_mac_address	= bcmgenet_set_mac_addr,
 	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_features	= bcmgenet_set_features,
-	.ndo_get_stats		= bcmgenet_get_stats,
+	.ndo_get_stats64	= bcmgenet_get_stats64,
 	.ndo_change_carrier	= bcmgenet_change_carrier,
 };
 
-/* Array of GENET hardware parameters/characteristics */
-static struct bcmgenet_hw_params bcmgenet_hw_params[] = {
-	[GENET_V1] = {
-		.tx_queues = 0,
-		.tx_bds_per_q = 0,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 16,
-		.bp_in_mask = 0xffff,
-		.hfb_filter_cnt = 16,
-		.qtag_mask = 0x1F,
-		.hfb_offset = 0x1000,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x3000,
-		.words_per_bd = 2,
-	},
-	[GENET_V2] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 16,
-		.bp_in_mask = 0xffff,
-		.hfb_filter_cnt = 16,
-		.qtag_mask = 0x1F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x1000,
-		.hfb_reg_offset = 0x2000,
-		.rdma_offset = 0x3000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 2,
-		.flags = GENET_HAS_EXT,
-	},
-	[GENET_V3] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x10000,
-		.tdma_offset = 0x11000,
-		.words_per_bd = 2,
-		.flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR |
-			 GENET_HAS_MOCA_LINK_DET,
-	},
-	[GENET_V4] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 3,
-		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
-			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
-	},
-	[GENET_V5] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 3,
-		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
-			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
-	},
+/* GENET hardware parameters/characteristics */
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v1 = {
+	.tx_queues = 0,
+	.tx_bds_per_q = 0,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 16,
+	.bp_in_mask = 0xffff,
+	.hfb_filter_cnt = 16,
+	.hfb_filter_size = 64,
+	.qtag_mask = 0x1F,
+	.hfb_offset = 0x1000,
+	.hfb_reg_offset = GENET_RBUF_OFF + RBUF_HFB_CTRL_V1,
+	.rdma_offset = 0x2000,
+	.tdma_offset = 0x3000,
+	.words_per_bd = 2,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v2 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 16,
+	.bp_in_mask = 0xffff,
+	.hfb_filter_cnt = 16,
+	.hfb_filter_size = 64,
+	.qtag_mask = 0x1F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x1000,
+	.hfb_reg_offset = 0x2000,
+	.rdma_offset = 0x3000,
+	.tdma_offset = 0x4000,
+	.words_per_bd = 2,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v3 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 17,
+	.bp_in_mask = 0x1ffff,
+	.hfb_filter_cnt = 48,
+	.hfb_filter_size = 128,
+	.qtag_mask = 0x3F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x8000,
+	.hfb_reg_offset = 0xfc00,
+	.rdma_offset = 0x10000,
+	.tdma_offset = 0x11000,
+	.words_per_bd = 2,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v4 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 17,
+	.bp_in_mask = 0x1ffff,
+	.hfb_filter_cnt = 48,
+	.hfb_filter_size = 128,
+	.qtag_mask = 0x3F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x8000,
+	.hfb_reg_offset = 0xfc00,
+	.rdma_offset = 0x2000,
+	.tdma_offset = 0x4000,
+	.words_per_bd = 3,
 };
 
 /* Infer hardware parameters from the detected GENET version */
 static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 {
-	struct bcmgenet_hw_params *params;
+	const struct bcmgenet_hw_params *params;
 	u32 reg;
 	u8 major;
 	u16 gphy_rev;
 
-	if (GENET_IS_V5(priv) || GENET_IS_V4(priv)) {
-		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
-		genet_dma_ring_regs = genet_dma_ring_regs_v4;
-	} else if (GENET_IS_V3(priv)) {
+	/* default to latest values */
+	params = &bcmgenet_hw_params_v4;
+	bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
+	genet_dma_ring_regs = genet_dma_ring_regs_v4;
+	if (GENET_IS_V3(priv)) {
+		params = &bcmgenet_hw_params_v3;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	} else if (GENET_IS_V2(priv)) {
+		params = &bcmgenet_hw_params_v2;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v2;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	} else if (GENET_IS_V1(priv)) {
+		params = &bcmgenet_hw_params_v1;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v1;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	}
-
-	/* enum genet_version starts at 1 */
-	priv->hw_params = &bcmgenet_hw_params[priv->version];
-	params = priv->hw_params;
+	priv->hw_params = params;
 
 	/* Read GENET HW version */
 	reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL);
 	major = (reg >> 24 & 0x0f);
-	if (major == 6)
+	if (major == 6 || major == 7)
 		major = 5;
 	else if (major == 5)
 		major = 4;
@@ -3898,7 +3839,7 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	}
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	if (!(params->flags & GENET_HAS_40BITS))
+	if (!bcmgenet_has_40bits(priv))
 		pr_warn("GENET does not support 40-bits PA\n");
 #endif
 
@@ -3923,7 +3864,7 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 struct bcmgenet_plat_data {
 	enum bcmgenet_version version;
 	u32 dma_max_burst_length;
-	bool ephy_16nm;
+	u32 flags;
 };
 
 static const struct bcmgenet_plat_data v1_plat_data = {
@@ -3934,32 +3875,43 @@ static const struct bcmgenet_plat_data v1_plat_data = {
 static const struct bcmgenet_plat_data v2_plat_data = {
 	.version = GENET_V2,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_EXT,
 };
 
 static const struct bcmgenet_plat_data v3_plat_data = {
 	.version = GENET_V3,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR |
+		 GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data v4_plat_data = {
 	.version = GENET_V4,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data v5_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data bcm2711_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = 0x08,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data bcm7712_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
-	.ephy_16nm = true,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET |
+		 GENET_HAS_EPHY_16NM,
 };
 
 static const struct of_device_id bcmgenet_match[] = {
@@ -4057,7 +4009,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	if (pdata) {
 		priv->version = pdata->version;
 		priv->dma_max_burst_length = pdata->dma_max_burst_length;
-		priv->ephy_16nm = pdata->ephy_16nm;
+		priv->flags = pdata->flags;
 	} else {
 		priv->version = pd->genet_version;
 		priv->dma_max_burst_length = DMA_MAX_BURST_LENGTH;
@@ -4077,7 +4029,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	bcmgenet_set_hw_params(priv);
 
 	err = -EIO;
-	if (priv->hw_params->flags & GENET_HAS_40BITS)
+	if (bcmgenet_has_40bits(priv))
 		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
 	if (err)
 		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
@@ -4132,16 +4084,13 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	if (err)
 		goto err_clk_disable;
 
-	/* setup number of real queues  + 1 (GENET_V1 has 0 hardware queues
-	 * just the ring 16 descriptor based TX
-	 */
+	/* setup number of real queues + 1 */
 	netif_set_real_num_tx_queues(priv->dev, priv->hw_params->tx_queues + 1);
 	netif_set_real_num_rx_queues(priv->dev, priv->hw_params->rx_queues + 1);
 
 	/* Set default coalescing parameters */
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		priv->rx_rings[i].rx_max_coalesced_frames = 1;
-	priv->rx_rings[DESC_INDEX].rx_max_coalesced_frames = 1;
 
 	/* libphy will determine the link state */
 	netif_carrier_off(dev);
@@ -4205,9 +4154,22 @@ static int bcmgenet_resume_noirq(struct device *d)
 		reg = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT);
 		if (reg & UMAC_IRQ_WAKE_EVENT)
 			pm_wakeup_event(&priv->pdev->dev, 0);
+
+		/* From WOL-enabled suspend, switch to regular clock */
+		if (!bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC))
+			return 0;
+
+		/* Failed so fall through to reset MAC */
 	}
 
-	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT, INTRL2_CPU_CLEAR);
+	/* If this is an internal GPHY, power it back on now, before UniMAC is
+	 * brought out of reset as absolutely no UniMAC activity is allowed
+	 */
+	if (priv->internal_phy)
+		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
+
+	/* take MAC out of reset */
+	bcmgenet_umac_reset(priv);
 
 	return 0;
 }
@@ -4217,23 +4179,46 @@ static int bcmgenet_resume(struct device *d)
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct bcmgenet_rxnfc_rule *rule;
-	unsigned long dma_ctrl;
 	int ret;
+	u32 reg;
 
 	if (!netif_running(dev))
 		return 0;
 
-	/* From WOL-enabled suspend, switch to regular clock */
-	if (device_may_wakeup(d) && priv->wolopts)
-		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
-
-	/* If this is an internal GPHY, power it back on now, before UniMAC is
-	 * brought out of reset as absolutely no UniMAC activity is allowed
-	 */
-	if (priv->internal_phy)
-		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
-
-	bcmgenet_umac_reset(priv);
+	if (device_may_wakeup(d) && priv->wolopts) {
+		reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+		if (reg & CMD_RX_EN) {
+			/* Successfully exited WoL, just resume data flows */
+			list_for_each_entry(rule, &priv->rxnfc_list, list)
+				if (rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+					bcmgenet_hfb_enable_filter(priv,
+							rule->fs.location + 1);
+			bcmgenet_hfb_enable_filter(priv, 0);
+			bcmgenet_set_rx_mode(dev);
+			bcmgenet_enable_rx_napi(priv);
+
+			/* Reinitialize Tx flows */
+			bcmgenet_tdma_disable(priv);
+			bcmgenet_init_tx_queues(priv->dev);
+			reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+			reg |= DMA_EN;
+			bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+			bcmgenet_enable_tx_napi(priv);
+
+			bcmgenet_link_intr_enable(priv);
+			phy_start_machine(dev->phydev);
+
+			netif_device_attach(dev);
+			enable_irq(priv->irq1);
+			return 0;
+		}
+		/* MAC was reset so complete bcmgenet_netif_stop() */
+		umac_enable_set(priv, CMD_RX_EN | CMD_TX_EN, false);
+		bcmgenet_rdma_disable(priv);
+		bcmgenet_intr_disable(priv);
+		bcmgenet_fini_dma(priv);
+		enable_irq(priv->irq1);
+	}
 
 	init_umac(priv);
 
@@ -4254,19 +4239,13 @@ static int bcmgenet_resume(struct device *d)
 		if (rule->state != BCMGENET_RXNFC_STATE_UNUSED)
 			bcmgenet_hfb_create_rxnfc_filter(priv, rule);
 
-	/* Disable RX/TX DMA and flush TX queues */
-	dma_ctrl = bcmgenet_dma_disable(priv, false);
-
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
-	ret = bcmgenet_init_dma(priv);
+	ret = bcmgenet_init_dma(priv, false);
 	if (ret) {
 		netdev_err(dev, "failed to initialize DMA\n");
 		goto out_clk_disable;
 	}
 
-	/* Always enable ring 16 - descriptor ring */
-	bcmgenet_enable_dma(priv, dma_ctrl);
-
 	if (!device_may_wakeup(d))
 		phy_resume(dev->phydev);
 
@@ -4287,19 +4266,52 @@ static int bcmgenet_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_rxnfc_rule *rule;
+	u32 reg, hfb_enable = 0;
 
 	if (!netif_running(dev))
 		return 0;
 
 	netif_device_detach(dev);
 
-	bcmgenet_netif_stop(dev, true);
+	if (device_may_wakeup(d) && priv->wolopts) {
+		netif_tx_disable(dev);
+
+		/* Suspend non-wake Rx data flows */
+		if (priv->wolopts & WAKE_FILTER)
+			list_for_each_entry(rule, &priv->rxnfc_list, list)
+				if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE &&
+				    rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+					hfb_enable |= 1 << rule->fs.location;
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
+			reg &= ~RBUF_HFB_FILTER_EN_MASK;
+			reg |= hfb_enable << (RBUF_HFB_FILTER_EN_SHIFT + 1);
+		} else {
+			bcmgenet_hfb_reg_writel(priv, hfb_enable << 1,
+						HFB_FLT_ENABLE_V3PLUS + 4);
+		}
+		if (!hfb_enable)
+			reg &= ~RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
-	if (!device_may_wakeup(d))
-		phy_suspend(dev->phydev);
+		/* Clear any old filter matches so only new matches wake */
+		bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
+		bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
 
-	/* Disable filtering */
-	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
+		if (-ETIMEDOUT == bcmgenet_tdma_disable(priv))
+			netdev_warn(priv->dev,
+				    "Timed out while disabling TX DMA\n");
+
+		bcmgenet_disable_tx_napi(priv);
+		bcmgenet_disable_rx_napi(priv);
+		disable_irq(priv->irq1);
+		bcmgenet_tx_reclaim_all(dev);
+		bcmgenet_fini_tx_napi(priv);
+	} else {
+		/* Teardown the interface */
+		bcmgenet_netif_stop(dev, true);
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 43b923c48b14..5ec3979779ec 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #ifndef __BCMGENET_H__
@@ -18,6 +18,9 @@
 
 #include "../unimac.h"
 
+/* Maximum number of hardware queues, downsized if needed */
+#define GENET_MAX_MQ_CNT	4
+
 /* total number of Buffer Descriptors, same for Rx/Tx */
 #define TOTAL_DESC				256
 
@@ -152,6 +155,30 @@ struct bcmgenet_mib_counters {
 	u32	tx_realloc_tsb_failed;
 };
 
+struct bcmgenet_tx_stats64 {
+	struct u64_stats_sync syncp;
+	u64_stats_t	packets;
+	u64_stats_t	bytes;
+	u64_stats_t	errors;
+	u64_stats_t	dropped;
+};
+
+struct bcmgenet_rx_stats64 {
+	struct u64_stats_sync syncp;
+	u64_stats_t	bytes;
+	u64_stats_t	packets;
+	u64_stats_t	errors;
+	u64_stats_t	dropped;
+	u64_stats_t	multicast;
+	u64_stats_t	broadcast;
+	u64_stats_t	missed;
+	u64_stats_t	length_errors;
+	u64_stats_t	over_errors;
+	u64_stats_t	crc_errors;
+	u64_stats_t	frame_errors;
+	u64_stats_t	fragmented_errors;
+};
+
 #define UMAC_MIB_START			0x400
 
 #define UMAC_MDIO_CMD			0x614
@@ -271,6 +298,8 @@ struct bcmgenet_mib_counters {
 /* Only valid for GENETv3+ */
 #define UMAC_IRQ_MDIO_DONE		(1 << 23)
 #define UMAC_IRQ_MDIO_ERROR		(1 << 24)
+#define UMAC_IRQ_MDIO_EVENT		(UMAC_IRQ_MDIO_DONE | \
+					 UMAC_IRQ_MDIO_ERROR)
 
 /* INTRL2 instance 1 definitions */
 #define UMAC_IRQ1_TX_INTR_MASK		0xFFFF
@@ -476,6 +505,7 @@ enum bcmgenet_version {
 #define GENET_HAS_EXT		(1 << 1)
 #define GENET_HAS_MDIO_INTR	(1 << 2)
 #define GENET_HAS_MOCA_LINK_DET	(1 << 3)
+#define GENET_HAS_EPHY_16NM	(1 << 4)
 
 /* BCMGENET hardware parameters, keep this structure nicely aligned
  * since it is going to be used in hot paths
@@ -496,7 +526,6 @@ struct bcmgenet_hw_params {
 	u32		rdma_offset;
 	u32		tdma_offset;
 	u32		words_per_bd;
-	u32		flags;
 };
 
 struct bcmgenet_skb_cb {
@@ -510,10 +539,8 @@ struct bcmgenet_skb_cb {
 struct bcmgenet_tx_ring {
 	spinlock_t	lock;		/* ring lock */
 	struct napi_struct napi;	/* NAPI per tx queue */
-	unsigned long	packets;
-	unsigned long	bytes;
+	struct bcmgenet_tx_stats64 stats64;
 	unsigned int	index;		/* ring index */
-	unsigned int	queue;		/* queue index */
 	struct enet_cb	*cbs;		/* tx ring buffer control block*/
 	unsigned int	size;		/* size of each tx ring */
 	unsigned int    clean_ptr;      /* Tx ring clean pointer */
@@ -523,8 +550,6 @@ struct bcmgenet_tx_ring {
 	unsigned int	prod_index;	/* Tx ring producer index SW copy */
 	unsigned int	cb_ptr;		/* Tx ring initial CB ptr */
 	unsigned int	end_ptr;	/* Tx ring end CB ptr */
-	void (*int_enable)(struct bcmgenet_tx_ring *);
-	void (*int_disable)(struct bcmgenet_tx_ring *);
 	struct bcmgenet_priv *priv;
 };
 
@@ -538,10 +563,7 @@ struct bcmgenet_net_dim {
 
 struct bcmgenet_rx_ring {
 	struct napi_struct napi;	/* Rx NAPI struct */
-	unsigned long	bytes;
-	unsigned long	packets;
-	unsigned long	errors;
-	unsigned long	dropped;
+	struct bcmgenet_rx_stats64 stats64;
 	unsigned int	index;		/* Rx ring index */
 	struct enet_cb	*cbs;		/* Rx ring buffer control block */
 	unsigned int	size;		/* Rx ring size */
@@ -553,8 +575,6 @@ struct bcmgenet_rx_ring {
 	struct bcmgenet_net_dim dim;
 	u32		rx_max_coalesced_frames;
 	u32		rx_coalesce_usecs;
-	void (*int_enable)(struct bcmgenet_rx_ring *);
-	void (*int_disable)(struct bcmgenet_rx_ring *);
 	struct bcmgenet_priv *priv;
 };
 
@@ -583,7 +603,7 @@ struct bcmgenet_priv {
 	struct enet_cb *tx_cbs;
 	unsigned int num_tx_bds;
 
-	struct bcmgenet_tx_ring tx_rings[DESC_INDEX + 1];
+	struct bcmgenet_tx_ring tx_rings[GENET_MAX_MQ_CNT + 1];
 
 	/* receive variables */
 	void __iomem *rx_bds;
@@ -593,10 +613,11 @@ struct bcmgenet_priv {
 	struct bcmgenet_rxnfc_rule rxnfc_rules[MAX_NUM_OF_FS_RULES];
 	struct list_head rxnfc_list;
 
-	struct bcmgenet_rx_ring rx_rings[DESC_INDEX + 1];
+	struct bcmgenet_rx_ring rx_rings[GENET_MAX_MQ_CNT + 1];
 
 	/* other misc variables */
-	struct bcmgenet_hw_params *hw_params;
+	const struct bcmgenet_hw_params *hw_params;
+	u32 flags;
 	unsigned autoneg_pause:1;
 	unsigned tx_pause:1;
 	unsigned rx_pause:1;
@@ -615,7 +636,6 @@ struct bcmgenet_priv {
 	phy_interface_t phy_interface;
 	int phy_addr;
 	int ext_phy;
-	bool ephy_16nm;
 
 	/* Interrupt variables */
 	struct work_struct bcmgenet_irq_work;
@@ -643,13 +663,37 @@ struct bcmgenet_priv {
 	struct clk *clk_wol;
 	u32 wolopts;
 	u8 sopass[SOPASS_MAX];
-	bool wol_active;
 
 	struct bcmgenet_mib_counters mib;
 
 	struct ethtool_keee eee;
 };
 
+static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_40BITS);
+}
+
+static inline bool bcmgenet_has_ext(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_EXT);
+}
+
+static inline bool bcmgenet_has_mdio_intr(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_MDIO_INTR);
+}
+
+static inline bool bcmgenet_has_moca_link_det(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_MOCA_LINK_DET);
+}
+
+static inline bool bcmgenet_has_ephy_16nm(struct bcmgenet_priv *priv)
+{
+	return !!(priv->flags & GENET_HAS_EPHY_16NM);
+}
+
 #define GENET_IO_MACRO(name, offset)					\
 static inline u32 bcmgenet_##name##_readl(struct bcmgenet_priv *priv,	\
 					u32 off)			\
@@ -702,8 +746,8 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol);
 int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol);
 int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode);
-void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
-			       enum bcmgenet_power_mode mode);
+int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
+			      enum bcmgenet_power_mode mode);
 
 void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 			     bool tx_lpi_enabled);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 0715ea5bf13e..8fb551288298 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #define pr_fmt(fmt)				"bcmgenet_wol: " fmt
@@ -41,9 +41,12 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
+	u32 phy_wolopts = 0;
 
-	if (dev->phydev)
+	if (dev->phydev) {
 		phy_ethtool_get_wol(dev->phydev, wol);
+		phy_wolopts = wol->wolopts;
+	}
 
 	/* MAC is not wake-up capable, return what the PHY does */
 	if (!device_can_wakeup(kdev))
@@ -51,9 +54,14 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	/* Overlay MAC capabilities with that of the PHY queried before */
 	wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
-	wol->wolopts = priv->wolopts;
-	memset(wol->sopass, 0, sizeof(wol->sopass));
+	wol->wolopts |= priv->wolopts;
+
+	/* Return the PHY configured magic password */
+	if (phy_wolopts & WAKE_MAGICSECURE)
+		return;
 
+	/* Otherwise the MAC one */
+	memset(wol->sopass, 0, sizeof(wol->sopass));
 	if (wol->wolopts & WAKE_MAGICSECURE)
 		memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
@@ -70,7 +78,7 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	/* Try Wake-on-LAN from the PHY first */
 	if (dev->phydev) {
 		ret = phy_ethtool_set_wol(dev->phydev, wol);
-		if (ret != -EOPNOTSUPP)
+		if (ret != -EOPNOTSUPP && wol->wolopts)
 			return ret;
 	}
 
@@ -137,8 +145,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
 	struct net_device *dev = priv->dev;
-	struct bcmgenet_rxnfc_rule *rule;
-	u32 reg, hfb_ctrl_reg, hfb_enable = 0;
+	u32 reg, hfb_ctrl_reg;
 	int retries = 0;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
@@ -146,18 +153,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		return -EINVAL;
 	}
 
-	/* Can't suspend with WoL if MAC is still in reset */
-	spin_lock_bh(&priv->reg_lock);
-	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-	if (reg & CMD_SW_RESET)
-		reg &= ~CMD_SW_RESET;
-
-	/* disable RX */
-	reg &= ~CMD_RX_EN;
-	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
-	spin_unlock_bh(&priv->reg_lock);
-	mdelay(10);
-
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 		reg |= MPD_EN;
@@ -169,13 +164,8 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	}
 
 	hfb_ctrl_reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-	if (priv->wolopts & WAKE_FILTER) {
-		list_for_each_entry(rule, &priv->rxnfc_list, list)
-			if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE)
-				hfb_enable |= (1 << rule->fs.location);
-		reg = (hfb_ctrl_reg & ~RBUF_HFB_EN) | RBUF_ACPI_EN;
-		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
-	}
+	reg = hfb_ctrl_reg | RBUF_ACPI_EN;
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
 	/* Do not leave UniMAC in MPD mode only */
 	retries = bcmgenet_poll_wol_status(priv);
@@ -190,15 +180,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	netif_dbg(priv, wol, dev, "MPD WOL-ready status set after %d msec\n",
 		  retries);
 
-	clk_prepare_enable(priv->clk_wol);
-	priv->wol_active = 1;
+	/* Disable phy status updates while suspending */
+	mutex_lock(&dev->phydev->lock);
+	dev->phydev->state = PHY_READY;
+	mutex_unlock(&dev->phydev->lock);
 
-	if (hfb_enable) {
-		bcmgenet_hfb_reg_writel(priv, hfb_enable,
-					HFB_FLT_ENABLE_V3PLUS + 4);
-		hfb_ctrl_reg = RBUF_HFB_EN | RBUF_ACPI_EN;
-		bcmgenet_hfb_reg_writel(priv, hfb_ctrl_reg, HFB_CTRL);
-	}
+	clk_prepare_enable(priv->clk_wol);
 
 	/* Enable CRC forward */
 	spin_lock_bh(&priv->reg_lock);
@@ -206,13 +193,17 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	priv->crc_fwd_en = 1;
 	reg |= CMD_CRC_FWD;
 
+	/* Can't suspend with WoL if MAC is still in reset */
+	if (reg & CMD_SW_RESET)
+		reg &= ~CMD_SW_RESET;
+
 	/* Receiver must be enabled for WOL MP detection */
 	reg |= CMD_RX_EN;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
 
 	reg = UMAC_IRQ_MPD_R;
-	if (hfb_enable)
+	if (hfb_ctrl_reg & RBUF_HFB_EN)
 		reg |=  UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM;
 
 	bcmgenet_intrl2_0_writel(priv, reg, INTRL2_CPU_MASK_CLEAR);
@@ -220,40 +211,42 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	return 0;
 }
 
-void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
-			       enum bcmgenet_power_mode mode)
+int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
+			      enum bcmgenet_power_mode mode)
 {
+	struct net_device *dev = priv->dev;
 	u32 reg;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
 		netif_err(priv, wol, priv->dev, "invalid mode: %d\n", mode);
-		return;
+		return -EINVAL;
 	}
 
-	if (!priv->wol_active)
-		return;	/* failed to suspend so skip the rest */
-
-	priv->wol_active = 0;
 	clk_disable_unprepare(priv->clk_wol);
 	priv->crc_fwd_en = 0;
 
+	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT,
+				 INTRL2_CPU_MASK_SET);
+	if (bcmgenet_has_mdio_intr(priv))
+		bcmgenet_intrl2_0_writel(priv,
+					 UMAC_IRQ_MDIO_EVENT,
+					 INTRL2_CPU_MASK_CLEAR);
+
 	/* Disable Magic Packet Detection */
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 		if (!(reg & MPD_EN))
-			return;	/* already reset so skip the rest */
+			return -EPERM;	/* already reset so skip the rest */
 		reg &= ~(MPD_EN | MPD_PW_EN);
 		bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 	}
 
-	/* Disable WAKE_FILTER Detection */
-	if (priv->wolopts & WAKE_FILTER) {
-		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-		if (!(reg & RBUF_ACPI_EN))
-			return;	/* already reset so skip the rest */
-		reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN);
-		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
-	}
+	/* Disable ACPI mode */
+	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	if (!(reg & RBUF_ACPI_EN))
+		return -EPERM;	/* already reset so skip the rest */
+	reg &= ~RBUF_ACPI_EN;
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
 	/* Disable CRC Forward */
 	spin_lock_bh(&priv->reg_lock);
@@ -261,4 +254,14 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg &= ~CMD_CRC_FWD;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
+
+	/* Resume link status tracking */
+	mutex_lock(&dev->phydev->lock);
+	if (dev->phydev->link)
+		dev->phydev->state = PHY_RUNNING;
+	else
+		dev->phydev->state = PHY_NOLINK;
+	mutex_unlock(&dev->phydev->lock);
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index c4a3698cef66..b6437ba7a2eb 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET MDIO routines
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #include <linux/acpi.h>
@@ -154,7 +154,7 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	u32 reg = 0;
 
 	/* EXT_GPHY_CTRL is only valid for GENETv4 and onward */
-	if (GENET_IS_V4(priv) || priv->ephy_16nm) {
+	if (GENET_IS_V4(priv) || bcmgenet_has_ephy_16nm(priv)) {
 		reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
 		if (enable) {
 			reg &= ~EXT_CK25_DIS;
@@ -184,7 +184,7 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
-	if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
+	if (bcmgenet_has_moca_link_det(priv))
 		fixed_phy_set_link_update(priv->dev->phydev,
 					  bcmgenet_fixed_phy_link_update);
 }
@@ -625,7 +625,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 			.asym_pause = 0,
 		};
 
-		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
+		phydev = fixed_phy_register(&fphy_status, NULL);
 		if (IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register fixed PHY device\n");
 			return PTR_ERR(phydev);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 9cc8db10a8d6..91104cc2c238 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -54,7 +54,8 @@
 #include <linux/ssb/ssb_driver_gige.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
-#include <linux/crc32poly.h>
+#include <linux/crc32.h>
+#include <linux/dmi.h>
 
 #include <net/checksum.h>
 #include <net/gso.h>
@@ -7424,7 +7425,7 @@ static void tg3_napi_enable(struct tg3 *tp)
 
 	for (i = 0; i < tp->irq_cnt; i++) {
 		tnapi = &tp->napi[i];
-		napi_enable(&tnapi->napi);
+		napi_enable_locked(&tnapi->napi);
 		if (tnapi->tx_buffers) {
 			netif_queue_set_napi(tp->dev, txq_idx,
 					     NETDEV_QUEUE_TYPE_TX,
@@ -7445,9 +7446,10 @@ static void tg3_napi_init(struct tg3 *tp)
 	int i;
 
 	for (i = 0; i < tp->irq_cnt; i++) {
-		netif_napi_add(tp->dev, &tp->napi[i].napi,
-			       i ? tg3_poll_msix : tg3_poll);
-		netif_napi_set_irq(&tp->napi[i].napi, tp->napi[i].irq_vec);
+		netif_napi_add_locked(tp->dev, &tp->napi[i].napi,
+				      i ? tg3_poll_msix : tg3_poll);
+		netif_napi_set_irq_locked(&tp->napi[i].napi,
+					  tp->napi[i].irq_vec);
 	}
 }
 
@@ -9807,26 +9809,7 @@ static void tg3_setup_rxbd_thresholds(struct tg3 *tp)
 
 static inline u32 calc_crc(unsigned char *buf, int len)
 {
-	u32 reg;
-	u32 tmp;
-	int j, k;
-
-	reg = 0xffffffff;
-
-	for (j = 0; j < len; j++) {
-		reg ^= buf[j];
-
-		for (k = 0; k < 8; k++) {
-			tmp = reg & 0x01;
-
-			reg >>= 1;
-
-			if (tmp)
-				reg ^= CRC32_POLY_LE;
-		}
-	}
-
-	return ~reg;
+	return ~crc32(~0, buf, len);
 }
 
 static void tg3_set_multi(struct tg3 *tp, unsigned int accept_all)
@@ -11079,7 +11062,7 @@ static void tg3_chk_missed_msi(struct tg3 *tp)
 
 static void tg3_timer(struct timer_list *t)
 {
-	struct tg3 *tp = from_timer(tp, t, timer);
+	struct tg3 *tp = timer_container_of(tp, t, timer);
 
 	spin_lock(&tp->lock);
 
@@ -11250,7 +11233,7 @@ static void tg3_timer_start(struct tg3 *tp)
 
 static void tg3_timer_stop(struct tg3 *tp)
 {
-	del_timer_sync(&tp->timer);
+	timer_delete_sync(&tp->timer);
 }
 
 /* Restart hardware after configuration changes, self-test, etc.
@@ -11259,6 +11242,8 @@ static void tg3_timer_stop(struct tg3 *tp)
 static int tg3_restart_hw(struct tg3 *tp, bool reset_phy)
 	__releases(tp->lock)
 	__acquires(tp->lock)
+	__releases(tp->dev->lock)
+	__acquires(tp->dev->lock)
 {
 	int err;
 
@@ -11271,7 +11256,9 @@ static int tg3_restart_hw(struct tg3 *tp, bool reset_phy)
 		tg3_timer_stop(tp);
 		tp->irq_sync = 0;
 		tg3_napi_enable(tp);
+		netdev_unlock(tp->dev);
 		dev_close(tp->dev);
+		netdev_lock(tp->dev);
 		tg3_full_lock(tp, 0);
 	}
 	return err;
@@ -11299,6 +11286,7 @@ static void tg3_reset_task(struct work_struct *work)
 
 	tg3_netif_stop(tp);
 
+	netdev_lock(tp->dev);
 	tg3_full_lock(tp, 1);
 
 	if (tg3_flag(tp, TX_RECOVERY_PENDING)) {
@@ -11318,12 +11306,14 @@ static void tg3_reset_task(struct work_struct *work)
 		 * call cancel_work_sync() and wait forever.
 		 */
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
+		netdev_unlock(tp->dev);
 		dev_close(tp->dev);
 		goto out;
 	}
 
 	tg3_netif_start(tp);
 	tg3_full_unlock(tp);
+	netdev_unlock(tp->dev);
 	tg3_phy_start(tp);
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
 out:
@@ -11683,9 +11673,11 @@ static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq,
 	if (err)
 		goto out_ints_fini;
 
+	netdev_lock(dev);
 	tg3_napi_init(tp);
 
 	tg3_napi_enable(tp);
+	netdev_unlock(dev);
 
 	for (i = 0; i < tp->irq_cnt; i++) {
 		err = tg3_request_irq(tp, i);
@@ -12569,6 +12561,7 @@ static int tg3_set_ringparam(struct net_device *dev,
 		irq_sync = 1;
 	}
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, irq_sync);
 
 	tp->rx_pending = ering->rx_pending;
@@ -12597,6 +12590,7 @@ static int tg3_set_ringparam(struct net_device *dev,
 	}
 
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (irq_sync && !err)
 		tg3_phy_start(tp);
@@ -12678,6 +12672,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 			irq_sync = 1;
 		}
 
+		netdev_lock(dev);
 		tg3_full_lock(tp, irq_sync);
 
 		if (epause->autoneg)
@@ -12707,6 +12702,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 		}
 
 		tg3_full_unlock(tp);
+		netdev_unlock(dev);
 	}
 
 	tp->phy_flags |= TG3_PHYFLG_USER_CONFIGURED;
@@ -13911,6 +13907,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 			data[TG3_INTERRUPT_TEST] = 1;
 		}
 
+		netdev_lock(dev);
 		tg3_full_lock(tp, 0);
 
 		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
@@ -13922,6 +13919,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 		}
 
 		tg3_full_unlock(tp);
+		netdev_unlock(dev);
 
 		if (irq_sync && !err2)
 			tg3_phy_start(tp);
@@ -14365,6 +14363,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 
 	tg3_set_mtu(dev, tp, new_mtu);
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, 1);
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
@@ -14384,6 +14383,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 		tg3_netif_start(tp);
 
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (!err)
 		tg3_phy_start(tp);
@@ -18164,6 +18164,7 @@ static int tg3_resume(struct device *device)
 
 	netif_device_attach(dev);
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, 0);
 
 	tg3_ape_driver_state_change(tp, RESET_KIND_INIT);
@@ -18180,6 +18181,7 @@ static int tg3_resume(struct device *device)
 
 out:
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (!err)
 		tg3_phy_start(tp);
@@ -18192,6 +18194,50 @@ unlock:
 
 static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume);
 
+/* Systems where ACPI _PTS (Prepare To Sleep) S5 will result in a fatal
+ * PCIe AER event on the tg3 device if the tg3 device is not, or cannot
+ * be, powered down.
+ */
+static const struct dmi_system_id tg3_restart_aer_quirk_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R440"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R540"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R640"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R650"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R740"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R750"),
+		},
+	},
+	{}
+};
+
 static void tg3_shutdown(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
@@ -18208,6 +18254,19 @@ static void tg3_shutdown(struct pci_dev *pdev)
 
 	if (system_state == SYSTEM_POWER_OFF)
 		tg3_power_down(tp);
+	else if (system_state == SYSTEM_RESTART &&
+		 dmi_first_match(tg3_restart_aer_quirk_table) &&
+		 pdev->current_state != PCI_D3cold &&
+		 pdev->current_state != PCI_UNKNOWN) {
+		/* Disable PCIe AER on the tg3 to avoid a fatal
+		 * error during this system restart.
+		 */
+		pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL,
+					   PCI_EXP_DEVCTL_CERE |
+					   PCI_EXP_DEVCTL_NFERE |
+					   PCI_EXP_DEVCTL_FERE |
+					   PCI_EXP_DEVCTL_URRE);
+	}
 
 	rtnl_unlock();
 
@@ -18260,7 +18319,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 done:
 	if (state == pci_channel_io_perm_failure) {
 		if (netdev) {
+			netdev_lock(netdev);
 			tg3_napi_enable(tp);
+			netdev_unlock(netdev);
 			dev_close(netdev);
 		}
 		err = PCI_ERS_RESULT_DISCONNECT;
@@ -18314,7 +18375,9 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev)
 
 done:
 	if (rc != PCI_ERS_RESULT_RECOVERED && netdev && netif_running(netdev)) {
+		netdev_lock(netdev);
 		tg3_napi_enable(tp);
+		netdev_unlock(netdev);
 		dev_close(netdev);
 	}
 	rtnl_unlock();
@@ -18340,12 +18403,14 @@ static void tg3_io_resume(struct pci_dev *pdev)
 	if (!netdev || !netif_running(netdev))
 		goto done;
 
+	netdev_lock(netdev);
 	tg3_full_lock(tp, 0);
 	tg3_ape_driver_state_change(tp, RESET_KIND_INIT);
 	tg3_flag_set(tp, INIT_COMPLETE);
 	err = tg3_restart_hw(tp, true);
 	if (err) {
 		tg3_full_unlock(tp);
+		netdev_unlock(netdev);
 		netdev_err(netdev, "Cannot restart hardware after reset.\n");
 		goto done;
 	}
@@ -18357,6 +18422,7 @@ static void tg3_io_resume(struct pci_dev *pdev)
 	tg3_netif_start(tp);
 
 	tg3_full_unlock(tp);
+	netdev_unlock(netdev);
 
 	tg3_phy_start(tp);
 
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 9c80ab07a735..92c7639d1fc7 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -314,13 +314,13 @@ bfa_ioc_sm_getattr(struct bfa_ioc *ioc, enum ioc_event event)
 {
 	switch (event) {
 	case IOC_E_FWRSP_GETATTR:
-		del_timer(&ioc->ioc_timer);
+		timer_delete(&ioc->ioc_timer);
 		bfa_fsm_set_state(ioc, bfa_ioc_sm_op);
 		break;
 
 	case IOC_E_PFFAILED:
 	case IOC_E_HWERROR:
-		del_timer(&ioc->ioc_timer);
+		timer_delete(&ioc->ioc_timer);
 		fallthrough;
 	case IOC_E_TIMEOUT:
 		ioc->cbfn->enable_cbfn(ioc->bfa, BFA_STATUS_IOC_FAILURE);
@@ -330,7 +330,7 @@ bfa_ioc_sm_getattr(struct bfa_ioc *ioc, enum ioc_event event)
 		break;
 
 	case IOC_E_DISABLE:
-		del_timer(&ioc->ioc_timer);
+		timer_delete(&ioc->ioc_timer);
 		bfa_fsm_set_state(ioc, bfa_ioc_sm_disabling);
 		break;
 
@@ -659,13 +659,13 @@ bfa_iocpf_sm_mismatch(struct bfa_iocpf *iocpf, enum iocpf_event event)
 		break;
 
 	case IOCPF_E_DISABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_reset);
 		bfa_ioc_pf_disabled(ioc);
 		break;
 
 	case IOCPF_E_STOP:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_reset);
 		break;
 
@@ -741,7 +741,7 @@ bfa_iocpf_sm_hwinit(struct bfa_iocpf *iocpf, enum iocpf_event event)
 		break;
 
 	case IOCPF_E_DISABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_ioc_sync_leave(ioc);
 		bfa_nw_ioc_hw_sem_release(ioc);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_disabled);
@@ -774,13 +774,13 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	switch (event) {
 	case IOCPF_E_FWRSP_ENABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_nw_ioc_hw_sem_release(ioc);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_ready);
 		break;
 
 	case IOCPF_E_INITFAIL:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		fallthrough;
 
 	case IOCPF_E_TIMEOUT:
@@ -791,7 +791,7 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 		break;
 
 	case IOCPF_E_DISABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_nw_ioc_hw_sem_release(ioc);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_disabling);
 		break;
@@ -844,12 +844,12 @@ bfa_iocpf_sm_disabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	switch (event) {
 	case IOCPF_E_FWRSP_DISABLE:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_disabling_sync);
 		break;
 
 	case IOCPF_E_FAIL:
-		del_timer(&ioc->iocpf_timer);
+		timer_delete(&ioc->iocpf_timer);
 		fallthrough;
 
 	case IOCPF_E_TIMEOUT:
@@ -1210,7 +1210,7 @@ bfa_nw_ioc_hw_sem_release(struct bfa_ioc *ioc)
 static void
 bfa_ioc_hw_sem_get_cancel(struct bfa_ioc *ioc)
 {
-	del_timer(&ioc->sem_timer);
+	timer_delete(&ioc->sem_timer);
 }
 
 /* Initialize LPU local memory (aka secondary memory / SRAM) */
@@ -1982,7 +1982,7 @@ bfa_ioc_hb_monitor(struct bfa_ioc *ioc)
 static void
 bfa_ioc_hb_stop(struct bfa_ioc *ioc)
 {
-	del_timer(&ioc->hb_timer);
+	timer_delete(&ioc->hb_timer);
 }
 
 /* Initiate a full firmware download. */
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index ece6f3b48327..9bed33295839 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -19,6 +19,7 @@
 #include <linux/ip.h>
 #include <linux/prefetch.h>
 #include <linux/module.h>
+#include <net/gro.h>
 
 #include "bnad.h"
 #include "bna.h"
@@ -1687,7 +1688,8 @@ err_return:
 static void
 bnad_ioc_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.ioc_timer);
+	struct bnad *bnad = timer_container_of(bnad, t,
+					       bna.ioceth.ioc.ioc_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1698,7 +1700,8 @@ bnad_ioc_timeout(struct timer_list *t)
 static void
 bnad_ioc_hb_check(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.hb_timer);
+	struct bnad *bnad = timer_container_of(bnad, t,
+					       bna.ioceth.ioc.hb_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1709,7 +1712,8 @@ bnad_ioc_hb_check(struct timer_list *t)
 static void
 bnad_iocpf_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.iocpf_timer);
+	struct bnad *bnad = timer_container_of(bnad, t,
+					       bna.ioceth.ioc.iocpf_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1720,7 +1724,8 @@ bnad_iocpf_timeout(struct timer_list *t)
 static void
 bnad_iocpf_sem_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.sem_timer);
+	struct bnad *bnad = timer_container_of(bnad, t,
+					       bna.ioceth.ioc.sem_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1734,7 +1739,7 @@ bnad_iocpf_sem_timeout(struct timer_list *t)
  *	Time	CPU m	CPU n
  *	0       1 = test_bit
  *	1			clear_bit
- *	2			del_timer_sync
+ *	2			timer_delete_sync
  *	3	mod_timer
  */
 
@@ -1742,7 +1747,7 @@ bnad_iocpf_sem_timeout(struct timer_list *t)
 static void
 bnad_dim_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, dim_timer);
+	struct bnad *bnad = timer_container_of(bnad, t, dim_timer);
 	struct bnad_rx_info *rx_info;
 	struct bnad_rx_ctrl *rx_ctrl;
 	int i, j;
@@ -1775,7 +1780,7 @@ bnad_dim_timeout(struct timer_list *t)
 static void
 bnad_stats_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = from_timer(bnad, t, stats_timer);
+	struct bnad *bnad = timer_container_of(bnad, t, stats_timer);
 	unsigned long flags;
 
 	if (!netif_running(bnad->netdev) ||
@@ -1836,7 +1841,7 @@ bnad_stats_timer_stop(struct bnad *bnad)
 		to_del = 1;
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 	if (to_del)
-		del_timer_sync(&bnad->stats_timer);
+		timer_delete_sync(&bnad->stats_timer);
 }
 
 /* Utilities */
@@ -2159,7 +2164,7 @@ bnad_destroy_rx(struct bnad *bnad, u32 rx_id)
 		}
 		spin_unlock_irqrestore(&bnad->bna_lock, flags);
 		if (to_del)
-			del_timer_sync(&bnad->dim_timer);
+			timer_delete_sync(&bnad->dim_timer);
 	}
 
 	init_completion(&bnad->bnad_completions.rx_comp);
@@ -3725,9 +3730,9 @@ probe_uninit:
 	bnad_res_free(bnad, &bnad->mod_res_info[0], BNA_MOD_RES_T_MAX);
 disable_ioceth:
 	bnad_ioceth_disable(bnad);
-	del_timer_sync(&bnad->bna.ioceth.ioc.ioc_timer);
-	del_timer_sync(&bnad->bna.ioceth.ioc.sem_timer);
-	del_timer_sync(&bnad->bna.ioceth.ioc.hb_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.ioc_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.sem_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.hb_timer);
 	spin_lock_irqsave(&bnad->bna_lock, flags);
 	bna_uninit(bna);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
@@ -3768,9 +3773,9 @@ bnad_pci_remove(struct pci_dev *pdev)
 
 	mutex_lock(&bnad->conf_mutex);
 	bnad_ioceth_disable(bnad);
-	del_timer_sync(&bnad->bna.ioceth.ioc.ioc_timer);
-	del_timer_sync(&bnad->bna.ioceth.ioc.sem_timer);
-	del_timer_sync(&bnad->bna.ioceth.ioc.hb_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.ioc_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.sem_timer);
+	timer_delete_sync(&bnad->bna.ioceth.ioc.hb_timer);
 	spin_lock_irqsave(&bnad->bna_lock, flags);
 	bna_uninit(bna);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index d1ad6c9f8140..216e25f26dbb 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -373,7 +373,7 @@ static int bnad_set_coalesce(struct net_device *netdev,
 			}
 			spin_unlock_irqrestore(&bnad->bna_lock, flags);
 			if (to_del)
-				del_timer_sync(&bnad->dim_timer);
+				timer_delete_sync(&bnad->dim_timer);
 			spin_lock_irqsave(&bnad->bna_lock, flags);
 			bnad_rx_coalescing_timeo_set(bnad);
 		}
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 5740c98d8c9f..c9a5c8beb2fa 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -951,75 +951,73 @@ struct macb_tx_skb {
  * device stats by a periodic timer.
  */
 struct macb_stats {
-	u32	rx_pause_frames;
-	u32	tx_ok;
-	u32	tx_single_cols;
-	u32	tx_multiple_cols;
-	u32	rx_ok;
-	u32	rx_fcs_errors;
-	u32	rx_align_errors;
-	u32	tx_deferred;
-	u32	tx_late_cols;
-	u32	tx_excessive_cols;
-	u32	tx_underruns;
-	u32	tx_carrier_errors;
-	u32	rx_resource_errors;
-	u32	rx_overruns;
-	u32	rx_symbol_errors;
-	u32	rx_oversize_pkts;
-	u32	rx_jabbers;
-	u32	rx_undersize_pkts;
-	u32	sqe_test_errors;
-	u32	rx_length_mismatch;
-	u32	tx_pause_frames;
+	u64	rx_pause_frames;
+	u64	tx_ok;
+	u64	tx_single_cols;
+	u64	tx_multiple_cols;
+	u64	rx_ok;
+	u64	rx_fcs_errors;
+	u64	rx_align_errors;
+	u64	tx_deferred;
+	u64	tx_late_cols;
+	u64	tx_excessive_cols;
+	u64	tx_underruns;
+	u64	tx_carrier_errors;
+	u64	rx_resource_errors;
+	u64	rx_overruns;
+	u64	rx_symbol_errors;
+	u64	rx_oversize_pkts;
+	u64	rx_jabbers;
+	u64	rx_undersize_pkts;
+	u64	sqe_test_errors;
+	u64	rx_length_mismatch;
+	u64	tx_pause_frames;
 };
 
 struct gem_stats {
-	u32	tx_octets_31_0;
-	u32	tx_octets_47_32;
-	u32	tx_frames;
-	u32	tx_broadcast_frames;
-	u32	tx_multicast_frames;
-	u32	tx_pause_frames;
-	u32	tx_64_byte_frames;
-	u32	tx_65_127_byte_frames;
-	u32	tx_128_255_byte_frames;
-	u32	tx_256_511_byte_frames;
-	u32	tx_512_1023_byte_frames;
-	u32	tx_1024_1518_byte_frames;
-	u32	tx_greater_than_1518_byte_frames;
-	u32	tx_underrun;
-	u32	tx_single_collision_frames;
-	u32	tx_multiple_collision_frames;
-	u32	tx_excessive_collisions;
-	u32	tx_late_collisions;
-	u32	tx_deferred_frames;
-	u32	tx_carrier_sense_errors;
-	u32	rx_octets_31_0;
-	u32	rx_octets_47_32;
-	u32	rx_frames;
-	u32	rx_broadcast_frames;
-	u32	rx_multicast_frames;
-	u32	rx_pause_frames;
-	u32	rx_64_byte_frames;
-	u32	rx_65_127_byte_frames;
-	u32	rx_128_255_byte_frames;
-	u32	rx_256_511_byte_frames;
-	u32	rx_512_1023_byte_frames;
-	u32	rx_1024_1518_byte_frames;
-	u32	rx_greater_than_1518_byte_frames;
-	u32	rx_undersized_frames;
-	u32	rx_oversize_frames;
-	u32	rx_jabbers;
-	u32	rx_frame_check_sequence_errors;
-	u32	rx_length_field_frame_errors;
-	u32	rx_symbol_errors;
-	u32	rx_alignment_errors;
-	u32	rx_resource_errors;
-	u32	rx_overruns;
-	u32	rx_ip_header_checksum_errors;
-	u32	rx_tcp_checksum_errors;
-	u32	rx_udp_checksum_errors;
+	u64	tx_octets;
+	u64	tx_frames;
+	u64	tx_broadcast_frames;
+	u64	tx_multicast_frames;
+	u64	tx_pause_frames;
+	u64	tx_64_byte_frames;
+	u64	tx_65_127_byte_frames;
+	u64	tx_128_255_byte_frames;
+	u64	tx_256_511_byte_frames;
+	u64	tx_512_1023_byte_frames;
+	u64	tx_1024_1518_byte_frames;
+	u64	tx_greater_than_1518_byte_frames;
+	u64	tx_underrun;
+	u64	tx_single_collision_frames;
+	u64	tx_multiple_collision_frames;
+	u64	tx_excessive_collisions;
+	u64	tx_late_collisions;
+	u64	tx_deferred_frames;
+	u64	tx_carrier_sense_errors;
+	u64	rx_octets;
+	u64	rx_frames;
+	u64	rx_broadcast_frames;
+	u64	rx_multicast_frames;
+	u64	rx_pause_frames;
+	u64	rx_64_byte_frames;
+	u64	rx_65_127_byte_frames;
+	u64	rx_128_255_byte_frames;
+	u64	rx_256_511_byte_frames;
+	u64	rx_512_1023_byte_frames;
+	u64	rx_1024_1518_byte_frames;
+	u64	rx_greater_than_1518_byte_frames;
+	u64	rx_undersized_frames;
+	u64	rx_oversize_frames;
+	u64	rx_jabbers;
+	u64	rx_frame_check_sequence_errors;
+	u64	rx_length_field_frame_errors;
+	u64	rx_symbol_errors;
+	u64	rx_alignment_errors;
+	u64	rx_resource_errors;
+	u64	rx_overruns;
+	u64	rx_ip_header_checksum_errors;
+	u64	rx_tcp_checksum_errors;
+	u64	rx_udp_checksum_errors;
 };
 
 /* Describes the name and offset of an individual statistic register, as
@@ -1027,7 +1025,7 @@ struct gem_stats {
  * this register should contribute to.
  */
 struct gem_statistic {
-	char stat_string[ETH_GSTRING_LEN];
+	char stat_string[ETH_GSTRING_LEN] __nonstring;
 	int offset;
 	u32 stat_bits;
 };
@@ -1279,6 +1277,8 @@ struct macb {
 	struct clk		*rx_clk;
 	struct clk		*tsu_clk;
 	struct net_device	*dev;
+	/* Protects hw_stats and ethtool_stats */
+	spinlock_t		stats_lock;
 	union {
 		struct macb_stats	macb;
 		struct gem_stats	gem;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index daa416fb1724..d1f1ae5ea161 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -17,8 +17,6 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
-#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -26,7 +24,6 @@
 #include <linux/platform_device.h>
 #include <linux/phylink.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/ip.h>
@@ -530,19 +527,9 @@ static void macb_set_tx_clk(struct macb *bp, int speed)
 	if (bp->phy_interface == PHY_INTERFACE_MODE_MII)
 		return;
 
-	switch (speed) {
-	case SPEED_10:
-		rate = 2500000;
-		break;
-	case SPEED_100:
-		rate = 25000000;
-		break;
-	case SPEED_1000:
-		rate = 125000000;
-		break;
-	default:
+	rate = rgmii_clock(speed);
+	if (rate < 0)
 		return;
-	}
 
 	rate_rounded = clk_round_rate(bp->tx_clk, rate);
 	if (rate_rounded < 0)
@@ -578,6 +565,7 @@ static void macb_usx_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode,
 }
 
 static void macb_usx_pcs_get_state(struct phylink_pcs *pcs,
+				   unsigned int neg_mode,
 				   struct phylink_link_state *state)
 {
 	struct macb *bp = container_of(pcs, struct macb, phylink_usx_pcs);
@@ -608,7 +596,7 @@ static int macb_usx_pcs_config(struct phylink_pcs *pcs,
 	return 0;
 }
 
-static void macb_pcs_get_state(struct phylink_pcs *pcs,
+static void macb_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 			       struct phylink_link_state *state)
 {
 	state->link = 0;
@@ -862,9 +850,7 @@ static int macb_mii_probe(struct net_device *dev)
 	struct macb *bp = netdev_priv(dev);
 
 	bp->phylink_sgmii_pcs.ops = &macb_phylink_pcs_ops;
-	bp->phylink_sgmii_pcs.neg_mode = true;
 	bp->phylink_usx_pcs.ops = &macb_phylink_usx_pcs_ops;
-	bp->phylink_usx_pcs.neg_mode = true;
 
 	bp->phylink_config.dev = &dev->dev;
 	bp->phylink_config.type = PHYLINK_NETDEV;
@@ -999,8 +985,8 @@ err_out:
 
 static void macb_update_stats(struct macb *bp)
 {
-	u32 *p = &bp->hw_stats.macb.rx_pause_frames;
-	u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+	u64 *p = &bp->hw_stats.macb.rx_pause_frames;
+	u64 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
 	int offset = MACB_PFR;
 
 	WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
@@ -1011,22 +997,15 @@ static void macb_update_stats(struct macb *bp)
 
 static int macb_halt_tx(struct macb *bp)
 {
-	unsigned long	halt_time, timeout;
-	u32		status;
+	u32 status;
 
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT));
 
-	timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT);
-	do {
-		halt_time = jiffies;
-		status = macb_readl(bp, TSR);
-		if (!(status & MACB_BIT(TGO)))
-			return 0;
-
-		udelay(250);
-	} while (time_before(halt_time, timeout));
-
-	return -ETIMEDOUT;
+	/* Poll TSR until TGO is cleared or timeout. */
+	return read_poll_timeout_atomic(macb_readl, status,
+					!(status & MACB_BIT(TGO)),
+					250, MACB_HALT_TIMEOUT, false,
+					bp, TSR);
 }
 
 static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budget)
@@ -1090,15 +1069,18 @@ static void macb_tx_error_task(struct work_struct *work)
 						      tx_error_task);
 	bool			halt_timeout = false;
 	struct macb		*bp = queue->bp;
+	u32			queue_index;
+	u32			packets = 0;
+	u32			bytes = 0;
 	struct macb_tx_skb	*tx_skb;
 	struct macb_dma_desc	*desc;
 	struct sk_buff		*skb;
 	unsigned int		tail;
 	unsigned long		flags;
 
+	queue_index = queue - bp->queues;
 	netdev_vdbg(bp->dev, "macb_tx_error_task: q = %u, t = %u, h = %u\n",
-		    (unsigned int)(queue - bp->queues),
-		    queue->tx_tail, queue->tx_head);
+		    queue_index, queue->tx_tail, queue->tx_head);
 
 	/* Prevent the queue NAPI TX poll from running, as it calls
 	 * macb_tx_complete(), which in turn may call netif_wake_subqueue().
@@ -1151,8 +1133,10 @@ static void macb_tx_error_task(struct work_struct *work)
 					    skb->data);
 				bp->dev->stats.tx_packets++;
 				queue->stats.tx_packets++;
+				packets++;
 				bp->dev->stats.tx_bytes += skb->len;
 				queue->stats.tx_bytes += skb->len;
+				bytes += skb->len;
 			}
 		} else {
 			/* "Buffers exhausted mid-frame" errors may only happen
@@ -1169,6 +1153,9 @@ static void macb_tx_error_task(struct work_struct *work)
 		macb_tx_unmap(bp, tx_skb, 0);
 	}
 
+	netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index),
+				  packets, bytes);
+
 	/* Set end of TX queue */
 	desc = macb_tx_desc(queue, 0);
 	macb_set_addr(bp, desc, 0);
@@ -1239,6 +1226,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 	unsigned int tail;
 	unsigned int head;
 	int packets = 0;
+	u32 bytes = 0;
 
 	spin_lock(&queue->tx_ptr_lock);
 	head = queue->tx_head;
@@ -1280,6 +1268,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 				bp->dev->stats.tx_bytes += skb->len;
 				queue->stats.tx_bytes += skb->len;
 				packets++;
+				bytes += skb->len;
 			}
 
 			/* Now we can safely release resources */
@@ -1294,6 +1283,9 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 		}
 	}
 
+	netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index),
+				  packets, bytes);
+
 	queue->tx_tail = tail;
 	if (__netif_subqueue_stopped(bp->dev, queue_index) &&
 	    CIRC_CNT(queue->tx_head, queue->tx_tail,
@@ -1987,10 +1979,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 
 		if (status & MACB_BIT(ISR_ROVR)) {
 			/* We missed at least one packet */
+			spin_lock(&bp->stats_lock);
 			if (macb_is_gem(bp))
 				bp->hw_stats.gem.rx_overruns++;
 			else
 				bp->hw_stats.macb.rx_overruns++;
+			spin_unlock(&bp->stats_lock);
 
 			if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
 				queue_writel(queue, ISR, MACB_BIT(ISR_ROVR));
@@ -2395,6 +2389,8 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Make newly initialized descriptor visible to hardware */
 	wmb();
 	skb_tx_timestamp(skb);
+	netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index),
+			     skb->len);
 
 	spin_lock_irq(&bp->lock);
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
@@ -3030,6 +3026,7 @@ static int macb_close(struct net_device *dev)
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		napi_disable(&queue->napi_rx);
 		napi_disable(&queue->napi_tx);
+		netdev_tx_reset_queue(netdev_get_tx_queue(dev, q));
 	}
 
 	phylink_stop(bp->phylink);
@@ -3080,7 +3077,7 @@ static void gem_update_stats(struct macb *bp)
 	unsigned int i, q, idx;
 	unsigned long *stat;
 
-	u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
+	u64 *p = &bp->hw_stats.gem.tx_octets;
 
 	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
 		u32 offset = gem_statistics[i].offset;
@@ -3093,7 +3090,7 @@ static void gem_update_stats(struct macb *bp)
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
 			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
-			*(++p) += val;
+			*(p++) += ((u64)val) << 32;
 		}
 	}
 
@@ -3103,15 +3100,13 @@ static void gem_update_stats(struct macb *bp)
 			bp->ethtool_stats[idx++] = *stat;
 }
 
-static struct net_device_stats *gem_get_stats(struct macb *bp)
+static void gem_get_stats(struct macb *bp, struct rtnl_link_stats64 *nstat)
 {
 	struct gem_stats *hwstat = &bp->hw_stats.gem;
-	struct net_device_stats *nstat = &bp->dev->stats;
 
-	if (!netif_running(bp->dev))
-		return nstat;
-
-	gem_update_stats(bp);
+	spin_lock_irq(&bp->stats_lock);
+	if (netif_running(bp->dev))
+		gem_update_stats(bp);
 
 	nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
 			    hwstat->rx_alignment_errors +
@@ -3140,19 +3135,19 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	nstat->tx_aborted_errors = hwstat->tx_excessive_collisions;
 	nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underrun;
-
-	return nstat;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static void gem_get_ethtool_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
-	struct macb *bp;
+	struct macb *bp = netdev_priv(dev);
 
-	bp = netdev_priv(dev);
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	memcpy(data, &bp->ethtool_stats, sizeof(u64)
 			* (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES));
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static int gem_get_sset_count(struct net_device *dev, int sset)
@@ -3192,16 +3187,20 @@ static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 	}
 }
 
-static struct net_device_stats *macb_get_stats(struct net_device *dev)
+static void macb_get_stats(struct net_device *dev,
+			   struct rtnl_link_stats64 *nstat)
 {
 	struct macb *bp = netdev_priv(dev);
-	struct net_device_stats *nstat = &bp->dev->stats;
 	struct macb_stats *hwstat = &bp->hw_stats.macb;
 
-	if (macb_is_gem(bp))
-		return gem_get_stats(bp);
+	netdev_stats_to_stats64(nstat, &bp->dev->stats);
+	if (macb_is_gem(bp)) {
+		gem_get_stats(bp, nstat);
+		return;
+	}
 
 	/* read stats from hardware */
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 
 	/* Convert HW stats into netdevice stats */
@@ -3235,8 +3234,171 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 	nstat->tx_carrier_errors = hwstat->tx_carrier_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underruns;
 	/* Don't know about heartbeat or window errors... */
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void macb_get_pause_stats(struct net_device *dev,
+				 struct ethtool_pause_stats *pause_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	spin_lock_irq(&bp->stats_lock);
+	macb_update_stats(bp);
+	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
+	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void gem_get_pause_stats(struct net_device *dev,
+				struct ethtool_pause_stats *pause_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	spin_lock_irq(&bp->stats_lock);
+	gem_update_stats(bp);
+	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
+	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
+	spin_unlock_irq(&bp->stats_lock);
+}
 
-	return nstat;
+static void macb_get_eth_mac_stats(struct net_device *dev,
+				   struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	spin_lock_irq(&bp->stats_lock);
+	macb_update_stats(bp);
+	mac_stats->FramesTransmittedOK = hwstat->tx_ok;
+	mac_stats->SingleCollisionFrames = hwstat->tx_single_cols;
+	mac_stats->MultipleCollisionFrames = hwstat->tx_multiple_cols;
+	mac_stats->FramesReceivedOK = hwstat->rx_ok;
+	mac_stats->FrameCheckSequenceErrors = hwstat->rx_fcs_errors;
+	mac_stats->AlignmentErrors = hwstat->rx_align_errors;
+	mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred;
+	mac_stats->LateCollisions = hwstat->tx_late_cols;
+	mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_cols;
+	mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underruns;
+	mac_stats->CarrierSenseErrors = hwstat->tx_carrier_errors;
+	mac_stats->FramesLostDueToIntMACRcvError = hwstat->rx_overruns;
+	mac_stats->InRangeLengthErrors = hwstat->rx_length_mismatch;
+	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_pkts;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void gem_get_eth_mac_stats(struct net_device *dev,
+				  struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	spin_lock_irq(&bp->stats_lock);
+	gem_update_stats(bp);
+	mac_stats->FramesTransmittedOK = hwstat->tx_frames;
+	mac_stats->SingleCollisionFrames = hwstat->tx_single_collision_frames;
+	mac_stats->MultipleCollisionFrames =
+		hwstat->tx_multiple_collision_frames;
+	mac_stats->FramesReceivedOK = hwstat->rx_frames;
+	mac_stats->FrameCheckSequenceErrors =
+		hwstat->rx_frame_check_sequence_errors;
+	mac_stats->AlignmentErrors = hwstat->rx_alignment_errors;
+	mac_stats->OctetsTransmittedOK = hwstat->tx_octets;
+	mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred_frames;
+	mac_stats->LateCollisions = hwstat->tx_late_collisions;
+	mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_collisions;
+	mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underrun;
+	mac_stats->CarrierSenseErrors = hwstat->tx_carrier_sense_errors;
+	mac_stats->OctetsReceivedOK = hwstat->rx_octets;
+	mac_stats->MulticastFramesXmittedOK = hwstat->tx_multicast_frames;
+	mac_stats->BroadcastFramesXmittedOK = hwstat->tx_broadcast_frames;
+	mac_stats->MulticastFramesReceivedOK = hwstat->rx_multicast_frames;
+	mac_stats->BroadcastFramesReceivedOK = hwstat->rx_broadcast_frames;
+	mac_stats->InRangeLengthErrors = hwstat->rx_length_field_frame_errors;
+	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_frames;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+/* TODO: Report SQE test errors when added to phy_stats */
+static void macb_get_eth_phy_stats(struct net_device *dev,
+				   struct ethtool_eth_phy_stats *phy_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	spin_lock_irq(&bp->stats_lock);
+	macb_update_stats(bp);
+	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void gem_get_eth_phy_stats(struct net_device *dev,
+				  struct ethtool_eth_phy_stats *phy_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	spin_lock_irq(&bp->stats_lock);
+	gem_update_stats(bp);
+	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static void macb_get_rmon_stats(struct net_device *dev,
+				struct ethtool_rmon_stats *rmon_stats,
+				const struct ethtool_rmon_hist_range **ranges)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	spin_lock_irq(&bp->stats_lock);
+	macb_update_stats(bp);
+	rmon_stats->undersize_pkts = hwstat->rx_undersize_pkts;
+	rmon_stats->oversize_pkts = hwstat->rx_oversize_pkts;
+	rmon_stats->jabbers = hwstat->rx_jabbers;
+	spin_unlock_irq(&bp->stats_lock);
+}
+
+static const struct ethtool_rmon_hist_range gem_rmon_ranges[] = {
+	{   64,    64 },
+	{   65,   127 },
+	{  128,   255 },
+	{  256,   511 },
+	{  512,  1023 },
+	{ 1024,  1518 },
+	{ 1519, 16384 },
+	{ },
+};
+
+static void gem_get_rmon_stats(struct net_device *dev,
+			       struct ethtool_rmon_stats *rmon_stats,
+			       const struct ethtool_rmon_hist_range **ranges)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	spin_lock_irq(&bp->stats_lock);
+	gem_update_stats(bp);
+	rmon_stats->undersize_pkts = hwstat->rx_undersized_frames;
+	rmon_stats->oversize_pkts = hwstat->rx_oversize_frames;
+	rmon_stats->jabbers = hwstat->rx_jabbers;
+	rmon_stats->hist[0] = hwstat->rx_64_byte_frames;
+	rmon_stats->hist[1] = hwstat->rx_65_127_byte_frames;
+	rmon_stats->hist[2] = hwstat->rx_128_255_byte_frames;
+	rmon_stats->hist[3] = hwstat->rx_256_511_byte_frames;
+	rmon_stats->hist[4] = hwstat->rx_512_1023_byte_frames;
+	rmon_stats->hist[5] = hwstat->rx_1024_1518_byte_frames;
+	rmon_stats->hist[6] = hwstat->rx_greater_than_1518_byte_frames;
+	rmon_stats->hist_tx[0] = hwstat->tx_64_byte_frames;
+	rmon_stats->hist_tx[1] = hwstat->tx_65_127_byte_frames;
+	rmon_stats->hist_tx[2] = hwstat->tx_128_255_byte_frames;
+	rmon_stats->hist_tx[3] = hwstat->tx_256_511_byte_frames;
+	rmon_stats->hist_tx[4] = hwstat->tx_512_1023_byte_frames;
+	rmon_stats->hist_tx[5] = hwstat->tx_1024_1518_byte_frames;
+	rmon_stats->hist_tx[6] = hwstat->tx_greater_than_1518_byte_frames;
+	spin_unlock_irq(&bp->stats_lock);
+	*ranges = gem_rmon_ranges;
 }
 
 static int macb_get_regs_len(struct net_device *netdev)
@@ -3765,6 +3927,10 @@ static const struct ethtool_ops macb_ethtool_ops = {
 	.get_regs		= macb_get_regs,
 	.get_link		= ethtool_op_get_link,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_pause_stats	= macb_get_pause_stats,
+	.get_eth_mac_stats	= macb_get_eth_mac_stats,
+	.get_eth_phy_stats	= macb_get_eth_phy_stats,
+	.get_rmon_stats		= macb_get_rmon_stats,
 	.get_wol		= macb_get_wol,
 	.set_wol		= macb_set_wol,
 	.get_link_ksettings     = macb_get_link_ksettings,
@@ -3783,6 +3949,10 @@ static const struct ethtool_ops gem_ethtool_ops = {
 	.get_ethtool_stats	= gem_get_ethtool_stats,
 	.get_strings		= gem_get_ethtool_strings,
 	.get_sset_count		= gem_get_sset_count,
+	.get_pause_stats	= gem_get_pause_stats,
+	.get_eth_mac_stats	= gem_get_eth_mac_stats,
+	.get_eth_phy_stats	= gem_get_eth_phy_stats,
+	.get_rmon_stats		= gem_get_rmon_stats,
 	.get_link_ksettings     = macb_get_link_ksettings,
 	.set_link_ksettings     = macb_set_link_ksettings,
 	.get_ringparam		= macb_get_ringparam,
@@ -3919,7 +4089,7 @@ static const struct net_device_ops macb_netdev_ops = {
 	.ndo_stop		= macb_close,
 	.ndo_start_xmit		= macb_start_xmit,
 	.ndo_set_rx_mode	= macb_set_rx_mode,
-	.ndo_get_stats		= macb_get_stats,
+	.ndo_get_stats64	= macb_get_stats,
 	.ndo_eth_ioctl		= macb_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= macb_change_mtu,
@@ -4580,7 +4750,7 @@ static const struct net_device_ops at91ether_netdev_ops = {
 	.ndo_open		= at91ether_open,
 	.ndo_stop		= at91ether_close,
 	.ndo_start_xmit		= at91ether_start_xmit,
-	.ndo_get_stats		= macb_get_stats,
+	.ndo_get_stats64	= macb_get_stats,
 	.ndo_set_rx_mode	= macb_set_rx_mode,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_eth_ioctl		= macb_ioctl,
@@ -5106,13 +5276,18 @@ static int macb_probe(struct platform_device *pdev)
 		}
 	}
 	spin_lock_init(&bp->lock);
+	spin_lock_init(&bp->stats_lock);
 
 	/* setup capabilities */
 	macb_configure_caps(bp, macb_config);
 
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 	if (GEM_BFEXT(DAW64, gem_readl(bp, DCFG6))) {
-		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
+		if (err) {
+			dev_err(&pdev->dev, "failed to set DMA mask\n");
+			goto err_out_free_netdev;
+		}
 		bp->hw_dma_cap |= HW_DMA_CAP_64B;
 	}
 #endif
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index ca742cc146d7..7dae5aad3689 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -70,8 +70,8 @@ config LIQUIDIO
 	depends on 64BIT && PCI
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	select CRC32
 	select FW_LOADER
-	select LIBCRC32C
 	select LIQUIDIO_CORE
 	select NET_DEVLINK
 	help
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 9ad49aea2673..ff8f2f9f9cae 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -49,7 +49,7 @@ static int cn23xx_pf_soft_reset(struct octeon_device *oct)
 	lio_pci_readq(oct, CN23XX_RST_SOFT_RST);
 	lio_pci_writeq(oct, 1, CN23XX_RST_SOFT_RST);
 
-	/* Wait for 100ms as Octeon resets. */
+	/* Wait for 100ms as Octeon resets */
 	mdelay(100);
 
 	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1)) {
@@ -61,7 +61,7 @@ static int cn23xx_pf_soft_reset(struct octeon_device *oct)
 	dev_dbg(&oct->pci_dev->dev, "OCTEON[%d]: Reset completed\n",
 		oct->octeon_id);
 
-	/* restore the  reset value*/
+	/* Restore the reset value */
 	octeon_write_csr64(oct, CN23XX_WIN_WR_MASK_REG, 0xFF);
 
 	return 0;
@@ -121,7 +121,7 @@ u32 cn23xx_pf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us)
 	oqticks_per_us /= 1024;
 
 	/* time_intr is in microseconds. The next 2 steps gives the oq ticks
-	 *  corressponding to time_intr.
+	 * corresponding to time_intr.
 	 */
 	oqticks_per_us *= time_intr_in_us;
 	oqticks_per_us /= 1000;
@@ -136,11 +136,11 @@ static void cn23xx_setup_global_mac_regs(struct octeon_device *oct)
 	u64 reg_val;
 	u64 temp;
 
-	/* programming SRN and TRS for each MAC(0..3)  */
+	/* Programming SRN and TRS for each MAC(0..3) */
 
 	dev_dbg(&oct->pci_dev->dev, "%s:Using pcie port %d\n",
 		__func__, mac_no);
-	/* By default, mapping all 64 IOQs to  a single MACs */
+	/* By default, map all 64 IOQs to a single MAC */
 
 	reg_val =
 	    octeon_read_csr64(oct, CN23XX_SLI_PKT_MAC_RINFO64(mac_no, pf_num));
@@ -164,7 +164,7 @@ static void cn23xx_setup_global_mac_regs(struct octeon_device *oct)
 	temp = oct->sriov_info.max_vfs & 0xff;
 	reg_val |= (temp << CN23XX_PKT_MAC_CTL_RINFO_NVFS_BIT_POS);
 
-	/* write these settings to MAC register */
+	/* Write these settings to MAC register */
 	octeon_write_csr64(oct, CN23XX_SLI_PKT_MAC_RINFO64(mac_no, pf_num),
 			   reg_val);
 
@@ -183,10 +183,10 @@ static int cn23xx_reset_io_queues(struct octeon_device *oct)
 	srn = oct->sriov_info.pf_srn;
 	ern = srn + oct->sriov_info.num_pf_rings;
 
-	/*As per HRM reg description, s/w cant write 0 to ENB. */
-	/*to make the queue off, need to set the RST bit. */
+	/* As per HRM reg description, s/w can't write 0 to ENB. */
+	/* We need to set the RST bit, to turn the queue off. */
 
-	/* Reset the Enable bit for all the 64 IQs.  */
+	/* Reset the enable bit for all the 64 IQs. */
 	for (q_no = srn; q_no < ern; q_no++) {
 		/* set RST bit to 1. This bit applies to both IQ and OQ */
 		d64 = octeon_read_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -194,7 +194,7 @@ static int cn23xx_reset_io_queues(struct octeon_device *oct)
 		octeon_write_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no), d64);
 	}
 
-	/*wait until the RST bit is clear or the RST and quite bits are set*/
+	/* Wait until the RST bit is clear or the RST and quiet bits are set */
 	for (q_no = srn; q_no < ern; q_no++) {
 		u64 reg_val = octeon_read_csr64(oct,
 					CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -245,15 +245,15 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 	if (cn23xx_reset_io_queues(oct))
 		return -1;
 
-	/** Set the MAC_NUM and PVF_NUM in IQ_PKT_CONTROL reg
-	 * for all queues.Only PF can set these bits.
+	/* Set the MAC_NUM and PVF_NUM in IQ_PKT_CONTROL reg
+	 * for all queues. Only PF can set these bits.
 	 * bits 29:30 indicate the MAC num.
 	 * bits 32:47 indicate the PVF num.
 	 */
 	for (q_no = 0; q_no < ern; q_no++) {
 		reg_val = (u64)oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
 
-		/* for VF assigned queues. */
+		/* For VF assigned queues. */
 		if (q_no < oct->sriov_info.pf_srn) {
 			vf_num = q_no / oct->sriov_info.rings_per_vf;
 			vf_num += 1; /* VF1, VF2,........ */
@@ -268,7 +268,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 				   reg_val);
 	}
 
-	/* Select ES, RO, NS, RDSIZE,DPTR Fomat#0 for
+	/* Select ES, RO, NS, RDSIZE,DPTR Format#0 for
 	 * pf queues
 	 */
 	for (q_no = srn; q_no < ern; q_no++) {
@@ -289,7 +289,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 		octeon_write_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no),
 				   reg_val);
 
-		/* Set WMARK level for triggering PI_INT */
+		/* Set WMARK level to trigger PI_INT */
 		/* intr_threshold = CN23XX_DEF_IQ_INTR_THRESHOLD & */
 		intr_threshold = CFG_GET_IQ_INTR_PKT(cn23xx->conf) &
 				 CN23XX_PKT_IN_DONE_WMARK_MASK;
@@ -354,7 +354,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 		/* set the ES bit */
 		reg_val |= (CN23XX_PKT_OUTPUT_CTL_ES);
 
-		/* write all the selected settings */
+		/* Write all the selected settings */
 		octeon_write_csr(oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no), reg_val);
 
 		/* Enabling these interrupt in oct->fn_list.enable_interrupt()
@@ -373,7 +373,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 	/** Setting the water mark level for pko back pressure **/
 	writeq(0x40, (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_OQ_WMARK);
 
-	/** Disabling setting OQs in reset when ring has no dorebells
+	/* Disabling setting OQs in reset when ring has no doorbells
 	 * enabling this will cause of head of line blocking
 	 */
 	/* Do it only for pass1.1. and pass1.2 */
@@ -383,7 +383,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 				     CN23XX_SLI_GBL_CONTROL) | 0x2,
 		       (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_GBL_CONTROL);
 
-	/** Enable channel-level backpressure */
+	/** Enable channel-level backpressure **/
 	if (oct->pf_num)
 		writeq(0xffffffffffffffffULL,
 		       (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_OUT_BP_EN2_W1S);
@@ -396,7 +396,7 @@ static int cn23xx_setup_pf_device_regs(struct octeon_device *oct)
 {
 	cn23xx_enable_error_reporting(oct);
 
-	/* program the MAC(0..3)_RINFO before setting up input/output regs */
+	/* Program the MAC(0..3)_RINFO before setting up input/output regs */
 	cn23xx_setup_global_mac_regs(oct);
 
 	if (cn23xx_pf_setup_global_input_regs(oct))
@@ -410,7 +410,7 @@ static int cn23xx_setup_pf_device_regs(struct octeon_device *oct)
 	octeon_write_csr64(oct, CN23XX_SLI_WINDOW_CTL,
 			   CN23XX_SLI_WINDOW_CTL_DEFAULT);
 
-	/* set SLI_PKT_IN_JABBER to handle large VXLAN packets */
+	/* Set SLI_PKT_IN_JABBER to handle large VXLAN packets */
 	octeon_write_csr64(oct, CN23XX_SLI_PKT_IN_JABBER, CN23XX_INPUT_JABBER);
 	return 0;
 }
@@ -574,7 +574,7 @@ static int cn23xx_setup_pf_mbox(struct octeon_device *oct)
 		mbox->mbox_read_reg = (u8 *)oct->mmio[0].hw_addr +
 				      CN23XX_SLI_PKT_PF_VF_MBOX_SIG(q_no, 1);
 
-		/*Mail Box Thread creation*/
+		/* Mail Box Thread creation */
 		INIT_DELAYED_WORK(&mbox->mbox_poll_wk.work,
 				  cn23xx_pf_mbox_thread);
 		mbox->mbox_poll_wk.ctxptr = (void *)mbox;
@@ -626,7 +626,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 	ern = srn + oct->num_iqs;
 
 	for (q_no = srn; q_no < ern; q_no++) {
-		/* set the corresponding IQ IS_64B bit */
+		/* Set the corresponding IQ IS_64B bit */
 		if (oct->io_qmask.iq64B & BIT_ULL(q_no - srn)) {
 			reg_val = octeon_read_csr64(
 			    oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -635,7 +635,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 			    oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no), reg_val);
 		}
 
-		/* set the corresponding IQ ENB bit */
+		/* Set the corresponding IQ ENB bit */
 		if (oct->io_qmask.iq & BIT_ULL(q_no - srn)) {
 			/* IOQs are in reset by default in PEM2 mode,
 			 * clearing reset bit
@@ -681,7 +681,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 	}
 	for (q_no = srn; q_no < ern; q_no++) {
 		u32 reg_val;
-		/* set the corresponding OQ ENB bit */
+		/* Set the corresponding OQ ENB bit */
 		if (oct->io_qmask.oq & BIT_ULL(q_no - srn)) {
 			reg_val = octeon_read_csr(
 			    oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no));
@@ -707,7 +707,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 	for (q_no = srn; q_no < ern; q_no++) {
 		loop = HZ;
 
-		/* start the Reset for a particular ring */
+		/* Start the Reset for a particular ring */
 		WRITE_ONCE(d64, octeon_read_csr64(
 			   oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no)));
 		WRITE_ONCE(d64, READ_ONCE(d64) &
@@ -740,7 +740,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 		loop = HZ;
 
 		/* Wait until hardware indicates that the particular IQ
-		 * is out of reset.It given that SLI_PKT_RING_RST is
+		 * is out of reset. Given that SLI_PKT_RING_RST is
 		 * common for both IQs and OQs
 		 */
 		WRITE_ONCE(d64, octeon_read_csr64(
@@ -760,7 +760,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 			schedule_timeout_uninterruptible(1);
 		}
 
-		/* clear the SLI_PKT(0..63)_CNTS[CNT] reg value */
+		/* Clear the SLI_PKT(0..63)_CNTS[CNT] reg value */
 		WRITE_ONCE(d32, octeon_read_csr(
 					oct, CN23XX_SLI_OQ_PKTS_SENT(q_no)));
 		octeon_write_csr(oct, CN23XX_SLI_OQ_PKTS_SENT(q_no),
@@ -793,7 +793,7 @@ static u64 cn23xx_pf_msix_interrupt_handler(void *dev)
 	if (!pkts_sent || (pkts_sent == 0xFFFFFFFFFFFFFFFFULL))
 		return ret;
 
-	/* Write count reg in sli_pkt_cnts to clear these int.*/
+	/* Write count reg in sli_pkt_cnts to clear these int. */
 	if ((pkts_sent & CN23XX_INTR_PO_INT) ||
 	    (pkts_sent & CN23XX_INTR_PI_INT)) {
 		if (pkts_sent & CN23XX_INTR_PO_INT)
@@ -908,7 +908,7 @@ static u32 cn23xx_bar1_idx_read(struct octeon_device *oct, u32 idx)
 	    oct, CN23XX_PEM_BAR1_INDEX_REG(oct->pcie_port, idx));
 }
 
-/* always call with lock held */
+/* Always call with lock held */
 static u32 cn23xx_update_read_index(struct octeon_instr_queue *iq)
 {
 	u32 new_idx;
@@ -919,7 +919,7 @@ static u32 cn23xx_update_read_index(struct octeon_instr_queue *iq)
 	iq->pkt_in_done = pkt_in_done;
 
 	/* Modulo of the new index with the IQ size will give us
-	 * the new index.  The iq->reset_instr_cnt is always zero for
+	 * the new index. The iq->reset_instr_cnt is always zero for
 	 * cn23xx, so no extra adjustments are needed.
 	 */
 	new_idx = (iq->octeon_read_index +
@@ -934,8 +934,8 @@ static void cn23xx_enable_pf_interrupt(struct octeon_device *oct, u8 intr_flag)
 	struct octeon_cn23xx_pf *cn23xx = (struct octeon_cn23xx_pf *)oct->chip;
 	u64 intr_val = 0;
 
-	/*  Divide the single write to multiple writes based on the flag. */
-	/* Enable Interrupt */
+	/* Divide the single write to multiple writes based on the flag. */
+	/* Enable Interrupts */
 	if (intr_flag == OCTEON_ALL_INTR) {
 		writeq(cn23xx->intr_mask64, cn23xx->intr_enb_reg64);
 	} else if (intr_flag & OCTEON_OUTPUT_INTR) {
@@ -990,7 +990,7 @@ static int cn23xx_get_pf_num(struct octeon_device *oct)
 
 	ret = 0;
 
-	/** Read Function Dependency Link reg to get the function number */
+	/* Read Function Dependency Link reg to get the function number */
 	if (pci_read_config_dword(oct->pci_dev, CN23XX_PCIE_SRIOV_FDL,
 				  &fdl_bit) == 0) {
 		oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) &
@@ -1003,13 +1003,13 @@ static int cn23xx_get_pf_num(struct octeon_device *oct)
 		 * In this case, read the PF number from the
 		 * SLI_PKT0_INPUT_CONTROL reg (written by f/w)
 		 */
-		pkt0_in_ctl = octeon_read_csr64(oct,
-						CN23XX_SLI_IQ_PKT_CONTROL64(0));
+		pkt0_in_ctl =
+			octeon_read_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(0));
 		pfnum = (pkt0_in_ctl >> CN23XX_PKT_INPUT_CTL_PF_NUM_POS) &
 			CN23XX_PKT_INPUT_CTL_PF_NUM_MASK;
 		mac = (octeon_read_csr(oct, CN23XX_SLI_MAC_NUMBER)) & 0xff;
 
-		/* validate PF num by reading RINFO; f/w writes RINFO.trs == 1*/
+		/* Validate PF num by reading RINFO; f/w writes RINFO.trs == 1 */
 		d64 = octeon_read_csr64(oct,
 					CN23XX_SLI_PKT_MAC_RINFO64(mac, pfnum));
 		trs = (int)(d64 >> CN23XX_PKT_MAC_CTL_RINFO_TRS_BIT_POS) & 0xff;
@@ -1252,9 +1252,9 @@ int cn23xx_fw_loaded(struct octeon_device *oct)
 	u64 val;
 
 	/* If there's more than one active PF on this NIC, then that
-	 * implies that the NIC firmware is loaded and running.  This check
+	 * implies that the NIC firmware is loaded and running. This check
 	 * prevents a rare false negative that might occur if we only relied
-	 * on checking the SCR2_BIT_FW_LOADED flag.  The false negative would
+	 * on checking the SCR2_BIT_FW_LOADED flag. The false negative would
 	 * happen if the PF driver sees SCR2_BIT_FW_LOADED as cleared even
 	 * though the firmware was already loaded but still booting and has yet
 	 * to set SCR2_BIT_FW_LOADED.
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 6b6cb73482d7..1753bb87dfbd 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1433,22 +1433,6 @@ int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout)
 }
 EXPORT_SYMBOL_GPL(octeon_wait_for_ddr_init);
 
-/* Get the octeon id assigned to the octeon device passed as argument.
- *  This function is exported to other modules.
- *  @param dev - octeon device pointer passed as a void *.
- *  @return octeon device id
- */
-int lio_get_device_id(void *dev)
-{
-	struct octeon_device *octeon_dev = (struct octeon_device *)dev;
-	u32 i;
-
-	for (i = 0; i < MAX_OCTEON_DEVICES; i++)
-		if (octeon_device[i] == octeon_dev)
-			return octeon_dev->octeon_id;
-	return -1;
-}
-
 void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq)
 {
 	u64 instr_cnt;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index d26364c2ac81..19344b21f8fb 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -705,13 +705,6 @@ octeon_get_dispatch(struct octeon_device *octeon_dev, u16 opcode,
  */
 struct octeon_device *lio_get_device(u32 octeon_id);
 
-/** Get the octeon id assigned to the octeon device passed as argument.
- *  This function is exported to other modules.
- *  @param dev - octeon device pointer passed as a void *.
- *  @return octeon device id
- */
-int lio_get_device_id(void *dev);
-
 /** Read windowed register.
  *  @param  oct   -  pointer to the Octeon device.
  *  @param  addr  -  Address of the register to read.
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 06397cc8bb36..5211759bfe47 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1389,11 +1389,9 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 		this_cpu_inc(nic->pnicvf->drv_stats->tx_tso);
 	}
 
-	/* Check if timestamp is requested */
-	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
-		skb_tx_timestamp(skb);
+	/* Check if hw timestamp is requested */
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		return;
-	}
 
 	/* Tx timestamping not supported along with TSO, so ignore request */
 	if (skb_shinfo(skb)->gso_size)
@@ -1472,6 +1470,8 @@ static inline void nicvf_sq_doorbell(struct nicvf *nic, struct sk_buff *skb,
 
 	netdev_tx_sent_queue(txq, skb->len);
 
+	skb_tx_timestamp(skb);
+
 	/* make sure all memory stores are done before ringing doorbell */
 	smp_wmb();
 
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 608cc6af5af1..3b7ad744b2dd 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1605,10 +1605,10 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return dev_err_probe(dev, err, "Failed to enable PCI device\n");
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
-		goto err_disable_device;
+		goto err_zero_drv_data;
 	}
 
 	/* MAP configuration registers */
@@ -1616,7 +1616,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!bgx->reg_base) {
 		dev_err(dev, "BGX: Cannot map CSR memory space, aborting\n");
 		err = -ENOMEM;
-		goto err_release_regions;
+		goto err_zero_drv_data;
 	}
 
 	set_max_bgx_per_node(pdev);
@@ -1688,10 +1688,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 err_enable:
 	bgx_vnic[bgx->bgx_id] = NULL;
 	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
-err_release_regions:
-	pci_release_regions(pdev);
-err_disable_device:
-	pci_disable_device(pdev);
+err_zero_drv_data:
 	pci_set_drvdata(pdev, NULL);
 	return err;
 }
@@ -1710,8 +1707,6 @@ static void bgx_remove(struct pci_dev *pdev)
 	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
 
 	bgx_vnic[bgx->bgx_id] = NULL;
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 3b7068832f95..4a0e2d2eb60a 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -351,7 +351,7 @@ static void set_msglevel(struct net_device *dev, u32 val)
 	adapter->msg_enable = val;
 }
 
-static const char stats_strings[][ETH_GSTRING_LEN] = {
+static const char stats_strings[][ETH_GSTRING_LEN] __nonstring_array = {
 	"TxOctetsOK",
 	"TxOctetsBad",
 	"TxUnicastFramesOK",
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 861edff5ed89..5f354cf62cdd 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1922,7 +1922,7 @@ send:
 static void sge_tx_reclaim_cb(struct timer_list *t)
 {
 	int i;
-	struct sge *sge = from_timer(sge, t, tx_reclaim_timer);
+	struct sge *sge = timer_container_of(sge, t, tx_reclaim_timer);
 
 	for (i = 0; i < SGE_CMDQ_N; ++i) {
 		struct cmdQ *q = &sge->cmdQ[i];
@@ -1984,9 +1984,9 @@ void t1_sge_stop(struct sge *sge)
 	readl(sge->adapter->regs + A_SG_CONTROL); /* flush */
 
 	if (is_T2(sge->adapter))
-		del_timer_sync(&sge->espibug_timer);
+		timer_delete_sync(&sge->espibug_timer);
 
-	del_timer_sync(&sge->tx_reclaim_timer);
+	timer_delete_sync(&sge->tx_reclaim_timer);
 	if (sge->tx_sched)
 		tx_sched_stop(sge);
 
@@ -2017,7 +2017,7 @@ void t1_sge_start(struct sge *sge)
  */
 static void espibug_workaround_t204(struct timer_list *t)
 {
-	struct sge *sge = from_timer(sge, t, espibug_timer);
+	struct sge *sge = timer_container_of(sge, t, espibug_timer);
 	struct adapter *adapter = sge->adapter;
 	unsigned int nports = adapter->params.nports;
 	u32 seop[MAX_NPORTS];
@@ -2060,7 +2060,7 @@ static void espibug_workaround_t204(struct timer_list *t)
 
 static void espibug_workaround(struct timer_list *t)
 {
-	struct sge *sge = from_timer(sge, t, espibug_timer);
+	struct sge *sge = timer_container_of(sge, t, espibug_timer);
 	struct adapter *adapter = sge->adapter;
 
 	if (netif_running(adapter->port[0].dev)) {
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index 6268f96cb4aa..b59735d0e065 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -2906,7 +2906,7 @@ void t3_sge_err_intr_handler(struct adapter *adapter)
  */
 static void sge_timer_tx(struct timer_list *t)
 {
-	struct sge_qset *qs = from_timer(qs, t, tx_reclaim_timer);
+	struct sge_qset *qs = timer_container_of(qs, t, tx_reclaim_timer);
 	struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
 	unsigned int tbd[SGE_TXQ_PER_SET] = {0, 0};
@@ -2947,7 +2947,7 @@ static void sge_timer_tx(struct timer_list *t)
 static void sge_timer_rx(struct timer_list *t)
 {
 	spinlock_t *lock;
-	struct sge_qset *qs = from_timer(qs, t, rx_reclaim_timer);
+	struct sge_qset *qs = timer_container_of(qs, t, rx_reclaim_timer);
 	struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
 	u32 status;
@@ -3223,9 +3223,9 @@ void t3_stop_sge_timers(struct adapter *adap)
 		struct sge_qset *q = &adap->sge.qs[i];
 
 		if (q->tx_reclaim_timer.function)
-			del_timer_sync(&q->tx_reclaim_timer);
+			timer_delete_sync(&q->tx_reclaim_timer);
 		if (q->rx_reclaim_timer.function)
-			del_timer_sync(&q->rx_reclaim_timer);
+			timer_delete_sync(&q->rx_reclaim_timer);
 	}
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 75bd69ff61a8..95e6f015a6af 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1211,9 +1211,6 @@ struct adapter {
 	struct timer_list flower_stats_timer;
 	struct work_struct flower_stats_work;
 
-	/* Ethtool Dump */
-	struct ethtool_dump eth_dump;
-
 	/* HMA */
 	struct hma_data hma;
 
@@ -1233,6 +1230,10 @@ struct adapter {
 
 	/* Ethtool n-tuple */
 	struct cxgb4_ethtool_filter *ethtool_filters;
+
+	/* Ethtool Dump */
+	/* Must be last - ends in a flex-array member. */
+	struct ethtool_dump eth_dump;
 };
 
 /* Support for "sched-class" command to allow a TX Scheduling Class to be
@@ -2076,7 +2077,7 @@ void t4_idma_monitor(struct adapter *adapter,
 		     struct sge_idma_monitor_state *idma,
 		     int hz, int ticks);
 int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf,
-		      unsigned int naddr, u8 *addr);
+		      u8 start, unsigned int naddr, u8 *addr);
 void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs,
 		    u32 start_index, bool sleep_ok);
 void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 7f3f5afa864f..1546c3db08f0 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -2270,6 +2270,7 @@ int cxgb4_init_ethtool_filters(struct adapter *adap)
 		eth_filter->port[i].bmap = bitmap_zalloc(nentries, GFP_KERNEL);
 		if (!eth_filter->port[i].bmap) {
 			ret = -ENOMEM;
+			kvfree(eth_filter->port[i].loc_array);
 			goto free_eth_finfo;
 		}
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 97a261d5357e..51395c96b2e9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1799,7 +1799,10 @@ void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid,
 	struct adapter *adap = container_of(t, struct adapter, tids);
 	struct sk_buff *skb;
 
-	WARN_ON(tid_out_of_range(&adap->tids, tid));
+	if (tid_out_of_range(&adap->tids, tid)) {
+		dev_err(adap->pdev_dev, "tid %d out of range\n", tid);
+		return;
+	}
 
 	if (t->tid_tab[tid - adap->tids.tid_base]) {
 		t->tid_tab[tid - adap->tids.tid_base] = NULL;
@@ -3234,7 +3237,7 @@ static int cxgb4_mgmt_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
 
 	dev_info(pi->adapter->pdev_dev,
 		 "Setting MAC %pM on VF %d\n", mac, vf);
-	ret = t4_set_vf_mac_acl(adap, vf + 1, 1, mac);
+	ret = t4_set_vf_mac_acl(adap, vf + 1, pi->lport, 1, mac);
 	if (!ret)
 		ether_addr_copy(adap->vfinfo[vf].vf_mac_addr, mac);
 	return ret;
@@ -6477,10 +6480,11 @@ static const struct tlsdev_ops cxgb4_ktls_ops = {
 
 #if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
 
-static int cxgb4_xfrm_add_state(struct xfrm_state *x,
+static int cxgb4_xfrm_add_state(struct net_device *dev,
+				struct xfrm_state *x,
 				struct netlink_ext_ack *extack)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 	int ret;
 
 	if (!mutex_trylock(&uld_mutex)) {
@@ -6491,7 +6495,8 @@ static int cxgb4_xfrm_add_state(struct xfrm_state *x,
 	if (ret)
 		goto out_unlock;
 
-	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(x, extack);
+	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(dev, x,
+									extack);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
@@ -6499,9 +6504,9 @@ out_unlock:
 	return ret;
 }
 
-static void cxgb4_xfrm_del_state(struct xfrm_state *x)
+static void cxgb4_xfrm_del_state(struct net_device *dev, struct xfrm_state *x)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 
 	if (!mutex_trylock(&uld_mutex)) {
 		dev_dbg(adap->pdev_dev,
@@ -6511,15 +6516,15 @@ static void cxgb4_xfrm_del_state(struct xfrm_state *x)
 	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
 		goto out_unlock;
 
-	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(x);
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(dev, x);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
 }
 
-static void cxgb4_xfrm_free_state(struct xfrm_state *x)
+static void cxgb4_xfrm_free_state(struct net_device *dev, struct xfrm_state *x)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 
 	if (!mutex_trylock(&uld_mutex)) {
 		dev_dbg(adap->pdev_dev,
@@ -6529,36 +6534,19 @@ static void cxgb4_xfrm_free_state(struct xfrm_state *x)
 	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
 		goto out_unlock;
 
-	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(x);
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(dev, x);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
 }
 
-static bool cxgb4_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
-{
-	struct adapter *adap = netdev2adap(x->xso.dev);
-	bool ret = false;
-
-	if (!mutex_trylock(&uld_mutex)) {
-		dev_dbg(adap->pdev_dev,
-			"crypto uld critical resource is under use\n");
-		return ret;
-	}
-	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
-		goto out_unlock;
-
-	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_offload_ok(skb, x);
-
-out_unlock:
-	mutex_unlock(&uld_mutex);
-	return ret;
-}
-
 static void cxgb4_advance_esn_state(struct xfrm_state *x)
 {
 	struct adapter *adap = netdev2adap(x->xso.dev);
 
+	if (x->xso.dir != XFRM_DEV_OFFLOAD_IN)
+		return;
+
 	if (!mutex_trylock(&uld_mutex)) {
 		dev_dbg(adap->pdev_dev,
 			"crypto uld critical resource is under use\n");
@@ -6577,7 +6565,6 @@ static const struct xfrmdev_ops cxgb4_xfrmdev_ops = {
 	.xdo_dev_state_add      = cxgb4_xfrm_add_state,
 	.xdo_dev_state_delete   = cxgb4_xfrm_del_state,
 	.xdo_dev_state_free     = cxgb4_xfrm_free_state,
-	.xdo_dev_offload_ok     = cxgb4_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = cxgb4_advance_esn_state,
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 69d045d769c4..0765d000eaef 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -1051,7 +1051,7 @@ static void ch_flower_stats_handler(struct work_struct *work)
 
 static void ch_flower_stats_cb(struct timer_list *t)
 {
-	struct adapter *adap = from_timer(adap, t, flower_stats_timer);
+	struct adapter *adap = timer_container_of(adap, t, flower_stats_timer);
 
 	schedule_work(&adap->flower_stats_work);
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
index b08356060fb4..7bab8da8f6e6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
@@ -29,7 +29,7 @@ static int cxgb4_thermal_get_temp(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static struct thermal_zone_device_ops cxgb4_thermal_ops = {
+static const struct thermal_zone_device_ops cxgb4_thermal_ops = {
 	.get_temp = cxgb4_thermal_get_temp,
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index a7d76a8ed050..64402e3646b3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1533,7 +1533,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 		q = &adap->sge.ethtxq[qidx + pi->first_qset];
 	}
-	skb_tx_timestamp(skb);
 
 	reclaim_completed_tx(adap, &q->q, -1, true);
 	cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
@@ -1706,6 +1705,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	cpl->len = htons(skb->len);
 	cpl->ctrl1 = cpu_to_be64(cntrl);
 
+	skb_tx_timestamp(skb);
+
 	if (immediate) {
 		cxgb4_inline_tx_skb(skb, &q->q, sgl);
 		dev_consume_skb_any(skb);
@@ -2268,7 +2269,6 @@ static int ethofld_hard_xmit(struct net_device *dev,
 
 	d = &eosw_txq->desc[eosw_txq->last_pidx];
 	skb = d->skb;
-	skb_tx_timestamp(skb);
 
 	wr = (struct fw_eth_tx_eo_wr *)&eohw_txq->q.desc[eohw_txq->q.pidx];
 	if (unlikely(eosw_txq->state != CXGB4_EO_STATE_ACTIVE &&
@@ -2373,6 +2373,7 @@ write_wr_headers:
 		eohw_txq->vlan_ins++;
 
 	txq_advance(&eohw_txq->q, ndesc);
+	skb_tx_timestamp(skb);
 	cxgb4_ring_tx_db(adap, &eohw_txq->q, ndesc);
 	eosw_txq_advance_index(&eosw_txq->last_pidx, 1, eosw_txq->ndesc);
 
@@ -4233,7 +4234,7 @@ static void sge_rx_timer_cb(struct timer_list *t)
 {
 	unsigned long m;
 	unsigned int i;
-	struct adapter *adap = from_timer(adap, t, sge.rx_timer);
+	struct adapter *adap = timer_container_of(adap, t, sge.rx_timer);
 	struct sge *s = &adap->sge;
 
 	for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++)
@@ -4268,7 +4269,7 @@ done:
 
 static void sge_tx_timer_cb(struct timer_list *t)
 {
-	struct adapter *adap = from_timer(adap, t, sge.tx_timer);
+	struct adapter *adap = timer_container_of(adap, t, sge.tx_timer);
 	struct sge *s = &adap->sge;
 	unsigned long m, period;
 	unsigned int i, budget;
@@ -4996,9 +4997,9 @@ void t4_sge_stop(struct adapter *adap)
 	struct sge *s = &adap->sge;
 
 	if (s->rx_timer.function)
-		del_timer_sync(&s->rx_timer);
+		timer_delete_sync(&s->rx_timer);
 	if (s->tx_timer.function)
-		del_timer_sync(&s->tx_timer);
+		timer_delete_sync(&s->tx_timer);
 
 	if (is_offload(adap)) {
 		struct sge_uld_txq_info *txq_info;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 76de55306c4d..175bf9b13058 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -10215,11 +10215,12 @@ out:
  *	t4_set_vf_mac_acl - Set MAC address for the specified VF
  *	@adapter: The adapter
  *	@vf: one of the VFs instantiated by the specified PF
+ *	@start: The start port id associated with specified VF
  *	@naddr: the number of MAC addresses
  *	@addr: the MAC address(es) to be set to the specified VF
  */
 int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf,
-		      unsigned int naddr, u8 *addr)
+		      u8 start, unsigned int naddr, u8 *addr)
 {
 	struct fw_acl_mac_cmd cmd;
 
@@ -10234,7 +10235,7 @@ int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf,
 	cmd.en_to_len16 = cpu_to_be32((unsigned int)FW_LEN16(cmd));
 	cmd.nmac = naddr;
 
-	switch (adapter->pf) {
+	switch (start) {
 	case 3:
 		memcpy(cmd.macaddr3, addr, sizeof(cmd.macaddr3));
 		break;
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 5b1d746e6563..4e6ecb9c8dcc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -2062,7 +2062,7 @@ irq_handler_t t4vf_intr_handler(struct adapter *adapter)
  */
 static void sge_rx_timer_cb(struct timer_list *t)
 {
-	struct adapter *adapter = from_timer(adapter, t, sge.rx_timer);
+	struct adapter *adapter = timer_container_of(adapter, t, sge.rx_timer);
 	struct sge *s = &adapter->sge;
 	unsigned int i;
 
@@ -2121,7 +2121,7 @@ static void sge_rx_timer_cb(struct timer_list *t)
  */
 static void sge_tx_timer_cb(struct timer_list *t)
 {
-	struct adapter *adapter = from_timer(adapter, t, sge.tx_timer);
+	struct adapter *adapter = timer_container_of(adapter, t, sge.tx_timer);
 	struct sge *s = &adapter->sge;
 	unsigned int i, budget;
 
@@ -2609,9 +2609,9 @@ void t4vf_sge_stop(struct adapter *adapter)
 	struct sge *s = &adapter->sge;
 
 	if (s->rx_timer.function)
-		del_timer_sync(&s->rx_timer);
+		timer_delete_sync(&s->rx_timer);
 	if (s->tx_timer.function)
-		del_timer_sync(&s->tx_timer);
+		timer_delete_sync(&s->tx_timer);
 }
 
 /**
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
index c7338ac6a5bb..ecd9a0bd5e18 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
@@ -71,21 +71,22 @@
 static LIST_HEAD(uld_ctx_list);
 static DEFINE_MUTEX(dev_mutex);
 
-static bool ch_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
 static int ch_ipsec_uld_state_change(void *handle, enum cxgb4_state new_state);
 static int ch_ipsec_xmit(struct sk_buff *skb, struct net_device *dev);
 static void *ch_ipsec_uld_add(const struct cxgb4_lld_info *infop);
 static void ch_ipsec_advance_esn_state(struct xfrm_state *x);
-static void ch_ipsec_xfrm_free_state(struct xfrm_state *x);
-static void ch_ipsec_xfrm_del_state(struct xfrm_state *x);
-static int ch_ipsec_xfrm_add_state(struct xfrm_state *x,
+static void ch_ipsec_xfrm_free_state(struct net_device *dev,
+				     struct xfrm_state *x);
+static void ch_ipsec_xfrm_del_state(struct net_device *dev,
+				    struct xfrm_state *x);
+static int ch_ipsec_xfrm_add_state(struct net_device *dev,
+				   struct xfrm_state *x,
 				   struct netlink_ext_ack *extack);
 
 static const struct xfrmdev_ops ch_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_add      = ch_ipsec_xfrm_add_state,
 	.xdo_dev_state_delete   = ch_ipsec_xfrm_del_state,
 	.xdo_dev_state_free     = ch_ipsec_xfrm_free_state,
-	.xdo_dev_offload_ok     = ch_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = ch_ipsec_advance_esn_state,
 };
 
@@ -225,7 +226,8 @@ out:
  * returns 0 on success, negative error if failed to send message to FPGA
  * positive error if FPGA returned a bad response
  */
-static int ch_ipsec_xfrm_add_state(struct xfrm_state *x,
+static int ch_ipsec_xfrm_add_state(struct net_device *dev,
+				   struct xfrm_state *x,
 				   struct netlink_ext_ack *extack)
 {
 	struct ipsec_sa_entry *sa_entry;
@@ -304,14 +306,16 @@ out:
 	return res;
 }
 
-static void ch_ipsec_xfrm_del_state(struct xfrm_state *x)
+static void ch_ipsec_xfrm_del_state(struct net_device *dev,
+				    struct xfrm_state *x)
 {
 	/* do nothing */
 	if (!x->xso.offload_handle)
 		return;
 }
 
-static void ch_ipsec_xfrm_free_state(struct xfrm_state *x)
+static void ch_ipsec_xfrm_free_state(struct net_device *dev,
+				     struct xfrm_state *x)
 {
 	struct ipsec_sa_entry *sa_entry;
 
@@ -323,20 +327,6 @@ static void ch_ipsec_xfrm_free_state(struct xfrm_state *x)
 	module_put(THIS_MODULE);
 }
 
-static bool ch_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
-{
-	if (x->props.family == AF_INET) {
-		/* Offload with IP options is not supported yet */
-		if (ip_hdr(skb)->ihl > 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-	return true;
-}
-
 static void ch_ipsec_advance_esn_state(struct xfrm_state *x)
 {
 	/* do nothing */
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index e8e460a92e0e..4e2096e49684 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -1640,6 +1640,7 @@ static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info,
 	cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr);
 	sgl_sdesc->skb = skb;
 	chcr_txq_advance(&q->q, ndesc);
+	skb_tx_timestamp(skb);
 	cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc);
 	return 0;
 }
@@ -1903,7 +1904,6 @@ static int chcr_ktls_sw_fallback(struct sk_buff *skb,
 	th = tcp_hdr(nskb);
 	skb_offset = skb_tcp_all_headers(nskb);
 	data_len = nskb->len - skb_offset;
-	skb_tx_timestamp(nskb);
 
 	if (chcr_ktls_tunnel_pkt(tx_info, nskb, q))
 		goto out;
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
index 96fd31d75dfd..daa1ebaef511 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
@@ -346,8 +346,9 @@ static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl,
 	 * driver. Once driver synthesizes cpl_pass_accept_req the skb will go
 	 * through the regular cpl_pass_accept_req processing in TOM.
 	 */
-	skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req)
-			- pktshift, GFP_ATOMIC);
+	skb = alloc_skb(size_add(gl->tot_len,
+				 sizeof(struct cpl_pass_accept_req)) -
+			pktshift, GFP_ATOMIC);
 	if (unlikely(!skb))
 		return NULL;
 	__skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req)
diff --git a/drivers/net/ethernet/cisco/enic/Kconfig b/drivers/net/ethernet/cisco/enic/Kconfig
index ad80c0fa96a6..96709875fe4f 100644
--- a/drivers/net/ethernet/cisco/enic/Kconfig
+++ b/drivers/net/ethernet/cisco/enic/Kconfig
@@ -6,5 +6,6 @@
 config ENIC
 	tristate "Cisco VIC Ethernet NIC Support"
 	depends on PCI
+	select PAGE_POOL
 	help
 	  This enables the support for the Cisco VIC Ethernet card.
diff --git a/drivers/net/ethernet/cisco/enic/Makefile b/drivers/net/ethernet/cisco/enic/Makefile
index c3b6febfdbe4..a96b8332e6e2 100644
--- a/drivers/net/ethernet/cisco/enic/Makefile
+++ b/drivers/net/ethernet/cisco/enic/Makefile
@@ -3,5 +3,5 @@ obj-$(CONFIG_ENIC) := enic.o
 
 enic-y := enic_main.o vnic_cq.o vnic_intr.o vnic_wq.o \
 	enic_res.o enic_dev.o enic_pp.o vnic_dev.o vnic_rq.o vnic_vic.o \
-	enic_ethtool.o enic_api.o enic_clsf.o
+	enic_ethtool.o enic_api.o enic_clsf.o enic_rq.o enic_wq.o
 
diff --git a/drivers/net/ethernet/cisco/enic/cq_desc.h b/drivers/net/ethernet/cisco/enic/cq_desc.h
index 462c5435a206..bfb3f14e89f5 100644
--- a/drivers/net/ethernet/cisco/enic/cq_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_desc.h
@@ -40,28 +40,7 @@ struct cq_desc {
 #define CQ_DESC_COMP_NDX_BITS    12
 #define CQ_DESC_COMP_NDX_MASK    ((1 << CQ_DESC_COMP_NDX_BITS) - 1)
 
-static inline void cq_desc_dec(const struct cq_desc *desc_arg,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index)
-{
-	const struct cq_desc *desc = desc_arg;
-	const u8 type_color = desc->type_color;
-
-	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
-
-	/*
-	 * Make sure color bit is read from desc *before* other fields
-	 * are read from desc.  Hardware guarantees color bit is last
-	 * bit (byte) written.  Adding the rmb() prevents the compiler
-	 * and/or CPU from reordering the reads which would potentially
-	 * result in reading stale values.
-	 */
-
-	rmb();
-
-	*type = type_color & CQ_DESC_TYPE_MASK;
-	*q_number = le16_to_cpu(desc->q_number) & CQ_DESC_Q_NUM_MASK;
-	*completed_index = le16_to_cpu(desc->completed_index) &
-		CQ_DESC_COMP_NDX_MASK;
-}
+#define CQ_DESC_32_FI_MASK (BIT(0) | BIT(1))
+#define CQ_DESC_64_FI_MASK (BIT(0) | BIT(1))
 
 #endif /* _CQ_DESC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
index d25426470a29..50787cff29db 100644
--- a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
@@ -17,12 +17,22 @@ struct cq_enet_wq_desc {
 	u8 type_color;
 };
 
-static inline void cq_enet_wq_desc_dec(struct cq_enet_wq_desc *desc,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index)
-{
-	cq_desc_dec((struct cq_desc *)desc, type,
-		color, q_number, completed_index);
-}
+/*
+ * Defines and Capabilities for CMD_CQ_ENTRY_SIZE_SET
+ */
+#define VNIC_RQ_ALL (~0ULL)
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_16 0
+#define VNIC_RQ_CQ_ENTRY_SIZE_32 1
+#define VNIC_RQ_CQ_ENTRY_SIZE_64 2
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_16_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_16)
+#define VNIC_RQ_CQ_ENTRY_SIZE_32_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_32)
+#define VNIC_RQ_CQ_ENTRY_SIZE_64_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_64)
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_ALL_BIT  (VNIC_RQ_CQ_ENTRY_SIZE_16_CAPABLE | \
+					VNIC_RQ_CQ_ENTRY_SIZE_32_CAPABLE | \
+					VNIC_RQ_CQ_ENTRY_SIZE_64_CAPABLE)
 
 /* Completion queue descriptor: Ethernet receive queue, 16B */
 struct cq_enet_rq_desc {
@@ -36,6 +46,45 @@ struct cq_enet_rq_desc {
 	u8 type_color;
 };
 
+/* Completion queue descriptor: Ethernet receive queue, 32B */
+struct cq_enet_rq_desc_32 {
+	__le16 completed_index_flags;
+	__le16 q_number_rss_type_flags;
+	__le32 rss_hash;
+	__le16 bytes_written_flags;
+	__le16 vlan;
+	__le16 checksum_fcoe;
+	u8 flags;
+	u8 fetch_index_flags;
+	__le32 time_stamp;
+	__le16 time_stamp2;
+	__le16 pie_info;
+	__le32 pie_info2;
+	__le16 pie_info3;
+	u8 pie_info4;
+	u8 type_color;
+};
+
+/* Completion queue descriptor: Ethernet receive queue, 64B */
+struct cq_enet_rq_desc_64 {
+	__le16 completed_index_flags;
+	__le16 q_number_rss_type_flags;
+	__le32 rss_hash;
+	__le16 bytes_written_flags;
+	__le16 vlan;
+	__le16 checksum_fcoe;
+	u8 flags;
+	u8 fetch_index_flags;
+	__le32 time_stamp;
+	__le16 time_stamp2;
+	__le16 pie_info;
+	__le32 pie_info2;
+	__le16 pie_info3;
+	u8 pie_info4;
+	u8 reserved[32];
+	u8 type_color;
+};
+
 #define CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT          (0x1 << 12)
 #define CQ_ENET_RQ_DESC_FLAGS_FCOE                  (0x1 << 13)
 #define CQ_ENET_RQ_DESC_FLAGS_EOP                   (0x1 << 14)
@@ -88,85 +137,4 @@ struct cq_enet_rq_desc {
 #define CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT         (0x1 << 6)
 #define CQ_ENET_RQ_DESC_FLAGS_FCS_OK                (0x1 << 7)
 
-static inline void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index,
-	u8 *ingress_port, u8 *fcoe, u8 *eop, u8 *sop, u8 *rss_type,
-	u8 *csum_not_calc, u32 *rss_hash, u16 *bytes_written, u8 *packet_error,
-	u8 *vlan_stripped, u16 *vlan_tci, u16 *checksum, u8 *fcoe_sof,
-	u8 *fcoe_fc_crc_ok, u8 *fcoe_enc_error, u8 *fcoe_eof,
-	u8 *tcp_udp_csum_ok, u8 *udp, u8 *tcp, u8 *ipv4_csum_ok,
-	u8 *ipv6, u8 *ipv4, u8 *ipv4_fragment, u8 *fcs_ok)
-{
-	u16 completed_index_flags;
-	u16 q_number_rss_type_flags;
-	u16 bytes_written_flags;
-
-	cq_desc_dec((struct cq_desc *)desc, type,
-		color, q_number, completed_index);
-
-	completed_index_flags = le16_to_cpu(desc->completed_index_flags);
-	q_number_rss_type_flags =
-		le16_to_cpu(desc->q_number_rss_type_flags);
-	bytes_written_flags = le16_to_cpu(desc->bytes_written_flags);
-
-	*ingress_port = (completed_index_flags &
-		CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT) ? 1 : 0;
-	*fcoe = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_FCOE) ?
-		1 : 0;
-	*eop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_EOP) ?
-		1 : 0;
-	*sop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_SOP) ?
-		1 : 0;
-
-	*rss_type = (u8)((q_number_rss_type_flags >> CQ_DESC_Q_NUM_BITS) &
-		CQ_ENET_RQ_DESC_RSS_TYPE_MASK);
-	*csum_not_calc = (q_number_rss_type_flags &
-		CQ_ENET_RQ_DESC_FLAGS_CSUM_NOT_CALC) ? 1 : 0;
-
-	*rss_hash = le32_to_cpu(desc->rss_hash);
-
-	*bytes_written = bytes_written_flags &
-		CQ_ENET_RQ_DESC_BYTES_WRITTEN_MASK;
-	*packet_error = (bytes_written_flags &
-		CQ_ENET_RQ_DESC_FLAGS_TRUNCATED) ? 1 : 0;
-	*vlan_stripped = (bytes_written_flags &
-		CQ_ENET_RQ_DESC_FLAGS_VLAN_STRIPPED) ? 1 : 0;
-
-	/*
-	 * Tag Control Information(16) = user_priority(3) + cfi(1) + vlan(12)
-	 */
-	*vlan_tci = le16_to_cpu(desc->vlan);
-
-	if (*fcoe) {
-		*fcoe_sof = (u8)(le16_to_cpu(desc->checksum_fcoe) &
-			CQ_ENET_RQ_DESC_FCOE_SOF_MASK);
-		*fcoe_fc_crc_ok = (desc->flags &
-			CQ_ENET_RQ_DESC_FCOE_FC_CRC_OK) ? 1 : 0;
-		*fcoe_enc_error = (desc->flags &
-			CQ_ENET_RQ_DESC_FCOE_ENC_ERROR) ? 1 : 0;
-		*fcoe_eof = (u8)((le16_to_cpu(desc->checksum_fcoe) >>
-			CQ_ENET_RQ_DESC_FCOE_EOF_SHIFT) &
-			CQ_ENET_RQ_DESC_FCOE_EOF_MASK);
-		*checksum = 0;
-	} else {
-		*fcoe_sof = 0;
-		*fcoe_fc_crc_ok = 0;
-		*fcoe_enc_error = 0;
-		*fcoe_eof = 0;
-		*checksum = le16_to_cpu(desc->checksum_fcoe);
-	}
-
-	*tcp_udp_csum_ok =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP_UDP_CSUM_OK) ? 1 : 0;
-	*udp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_UDP) ? 1 : 0;
-	*tcp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP) ? 1 : 0;
-	*ipv4_csum_ok =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_CSUM_OK) ? 1 : 0;
-	*ipv6 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV6) ? 1 : 0;
-	*ipv4 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4) ? 1 : 0;
-	*ipv4_fragment =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT) ? 1 : 0;
-	*fcs_ok = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_FCS_OK) ? 1 : 0;
-}
-
 #endif /* _CQ_ENET_DESC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 10b7e02ba4d0..301b3f3114af 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -17,6 +17,7 @@
 #include "vnic_nic.h"
 #include "vnic_rss.h"
 #include <linux/irq.h>
+#include <net/page_pool/helpers.h>
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
@@ -25,11 +26,19 @@
 
 #define ENIC_WQ_MAX		256
 #define ENIC_RQ_MAX		256
+#define ENIC_RQ_MIN_DEFAULT	8
 
 #define ENIC_WQ_NAPI_BUDGET	256
 
 #define ENIC_AIC_LARGE_PKT_DIFF	3
 
+enum ext_cq {
+	ENIC_RQ_CQ_ENTRY_SIZE_16,
+	ENIC_RQ_CQ_ENTRY_SIZE_32,
+	ENIC_RQ_CQ_ENTRY_SIZE_64,
+	ENIC_RQ_CQ_ENTRY_SIZE_MAX,
+};
+
 struct enic_msix_entry {
 	int requested;
 	char devname[IFNAMSIZ + 8];
@@ -75,6 +84,10 @@ struct enic_rx_coal {
 #define ENIC_SET_INSTANCE		(1 << 3)
 #define ENIC_SET_HOST			(1 << 4)
 
+#define MAX_TSO			BIT(16)
+#define WQ_ENET_MAX_DESC_LEN	BIT(WQ_ENET_LEN_BITS)
+#define ENIC_DESC_MAX_SPLITS	(MAX_TSO / WQ_ENET_MAX_DESC_LEN + 1)
+
 struct enic_port_profile {
 	u32 set;
 	u8 request;
@@ -158,6 +171,7 @@ struct enic_rq_stats {
 	u64 pkt_truncated;		/* truncated pkts */
 	u64 no_skb;			/* out of skbs */
 	u64 desc_skip;			/* Rx pkt went into later buffer */
+	u64 pp_alloc_fail;		/* page pool alloc failure */
 };
 
 struct enic_wq {
@@ -169,6 +183,7 @@ struct enic_wq {
 struct enic_rq {
 	struct vnic_rq vrq;
 	struct enic_rq_stats stats;
+	struct page_pool *pool;
 } ____cacheline_aligned;
 
 /* Per-instance private data structure */
@@ -223,9 +238,9 @@ struct enic {
 	unsigned int cq_avail;
 	unsigned int cq_count;
 	struct enic_rfs_flw_tbl rfs_h;
-	u32 rx_copybreak;
 	u8 rss_key[ENIC_RSS_LEN];
 	struct vnic_gen_stats gen_stats;
+	enum ext_cq ext_cq;
 };
 
 static inline struct net_device *vnic_get_netdev(struct vnic_dev *vdev)
@@ -347,5 +362,6 @@ int enic_is_valid_vf(struct enic *enic, int vf);
 int enic_is_dynamic(struct enic *enic);
 void enic_set_ethtool_ops(struct net_device *netdev);
 int __enic_set_rsskey(struct enic *enic);
+void enic_ext_cq(struct enic *enic);
 
 #endif /* _ENIC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c
index 9900993b6aea..837f954873ee 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.c
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.c
@@ -125,7 +125,7 @@ struct enic_rfs_fltr_node *htbl_fltr_search(struct enic *enic, u16 fltr_id)
 #ifdef CONFIG_RFS_ACCEL
 void enic_flow_may_expire(struct timer_list *t)
 {
-	struct enic *enic = from_timer(enic, t, rfs_h.rfs_may_expire);
+	struct enic *enic = timer_container_of(enic, t, rfs_h.rfs_may_expire);
 	bool res;
 	int j;
 
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.h b/drivers/net/ethernet/cisco/enic/enic_clsf.h
index 8c4ce50da6e1..5f5284102fb0 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.h
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.h
@@ -26,7 +26,7 @@ static inline void enic_rfs_timer_start(struct enic *enic)
 
 static inline void enic_rfs_timer_stop(struct enic *enic)
 {
-	del_timer_sync(&enic->rfs_h.rfs_may_expire);
+	timer_delete_sync(&enic->rfs_h.rfs_may_expire);
 }
 #else
 static inline void enic_rfs_timer_start(struct enic *enic) {}
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index d607b4f0542c..529160926a96 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -222,9 +222,9 @@ static void enic_get_ringparam(struct net_device *netdev,
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_enet_config *c = &enic->config;
 
-	ring->rx_max_pending = ENIC_MAX_RQ_DESCS;
+	ring->rx_max_pending = c->max_rq_ring;
 	ring->rx_pending = c->rq_desc_count;
-	ring->tx_max_pending = ENIC_MAX_WQ_DESCS;
+	ring->tx_max_pending = c->max_wq_ring;
 	ring->tx_pending = c->wq_desc_count;
 }
 
@@ -252,18 +252,18 @@ static int enic_set_ringparam(struct net_device *netdev,
 	}
 	rx_pending = c->rq_desc_count;
 	tx_pending = c->wq_desc_count;
-	if (ring->rx_pending > ENIC_MAX_RQ_DESCS ||
+	if (ring->rx_pending > c->max_rq_ring ||
 	    ring->rx_pending < ENIC_MIN_RQ_DESCS) {
 		netdev_info(netdev, "rx pending (%u) not in range [%u,%u]",
 			    ring->rx_pending, ENIC_MIN_RQ_DESCS,
-			    ENIC_MAX_RQ_DESCS);
+	      c->max_rq_ring);
 		return -EINVAL;
 	}
-	if (ring->tx_pending > ENIC_MAX_WQ_DESCS ||
+	if (ring->tx_pending > c->max_wq_ring ||
 	    ring->tx_pending < ENIC_MIN_WQ_DESCS) {
 		netdev_info(netdev, "tx pending (%u) not in range [%u,%u]",
 			    ring->tx_pending, ENIC_MIN_WQ_DESCS,
-			    ENIC_MAX_WQ_DESCS);
+			c->max_wq_ring);
 		return -EINVAL;
 	}
 	if (running)
@@ -608,43 +608,6 @@ static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	return ret;
 }
 
-static int enic_get_tunable(struct net_device *dev,
-			    const struct ethtool_tunable *tuna, void *data)
-{
-	struct enic *enic = netdev_priv(dev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		*(u32 *)data = enic->rx_copybreak;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
-static int enic_set_tunable(struct net_device *dev,
-			    const struct ethtool_tunable *tuna,
-			    const void *data)
-{
-	struct enic *enic = netdev_priv(dev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		enic->rx_copybreak = *(u32 *)data;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
 static u32 enic_get_rxfh_key_size(struct net_device *netdev)
 {
 	return ENIC_RSS_LEN;
@@ -727,8 +690,6 @@ static const struct ethtool_ops enic_ethtool_ops = {
 	.get_coalesce = enic_get_coalesce,
 	.set_coalesce = enic_set_coalesce,
 	.get_rxnfc = enic_get_rxnfc,
-	.get_tunable = enic_get_tunable,
-	.set_tunable = enic_set_tunable,
 	.get_rxfh_key_size = enic_get_rxfh_key_size,
 	.get_rxfh = enic_get_rxfh,
 	.set_rxfh = enic_set_rxfh,
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 9913952ccb42..6bc8dfdb3d4b 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -58,18 +58,15 @@
 #include "enic_dev.h"
 #include "enic_pp.h"
 #include "enic_clsf.h"
+#include "enic_rq.h"
+#include "enic_wq.h"
 
 #define ENIC_NOTIFY_TIMER_PERIOD	(2 * HZ)
-#define WQ_ENET_MAX_DESC_LEN		(1 << WQ_ENET_LEN_BITS)
-#define MAX_TSO				(1 << 16)
-#define ENIC_DESC_MAX_SPLITS		(MAX_TSO / WQ_ENET_MAX_DESC_LEN + 1)
 
 #define PCI_DEVICE_ID_CISCO_VIC_ENET         0x0043  /* ethernet vnic */
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_DYN     0x0044  /* enet dynamic vnic */
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_VF      0x0071  /* enet SRIOV VF */
 
-#define RX_COPYBREAK_DEFAULT		256
-
 /* Supported devices */
 static const struct pci_device_id enic_id_table[] = {
 	{ PCI_VDEVICE(CISCO, PCI_DEVICE_ID_CISCO_VIC_ENET) },
@@ -109,7 +106,7 @@ static struct enic_intr_mod_table mod_table[ENIC_MAX_COALESCE_TIMERS + 1] = {
 static struct enic_intr_mod_range mod_range[ENIC_MAX_LINK_SPEEDS] = {
 	{0,  0}, /* 0  - 4  Gbps */
 	{0,  3}, /* 4  - 10 Gbps */
-	{3,  6}, /* 10 - 40 Gbps */
+	{3,  6}, /* 10+ Gbps */
 };
 
 static void enic_init_affinity_hint(struct enic *enic)
@@ -322,54 +319,6 @@ int enic_is_valid_vf(struct enic *enic, int vf)
 #endif
 }
 
-static void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
-{
-	struct enic *enic = vnic_dev_priv(wq->vdev);
-
-	if (buf->sop)
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_TO_DEVICE);
-	else
-		dma_unmap_page(&enic->pdev->dev, buf->dma_addr, buf->len,
-			       DMA_TO_DEVICE);
-
-	if (buf->os_buf)
-		dev_kfree_skb_any(buf->os_buf);
-}
-
-static void enic_wq_free_buf(struct vnic_wq *wq,
-	struct cq_desc *cq_desc, struct vnic_wq_buf *buf, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(wq->vdev);
-
-	enic->wq[wq->index].stats.cq_work++;
-	enic->wq[wq->index].stats.cq_bytes += buf->len;
-	enic_free_wq_buf(wq, buf);
-}
-
-static int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(vdev);
-
-	spin_lock(&enic->wq[q_number].lock);
-
-	vnic_wq_service(&enic->wq[q_number].vwq, cq_desc,
-		completed_index, enic_wq_free_buf,
-		opaque);
-
-	if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number)) &&
-	    vnic_wq_desc_avail(&enic->wq[q_number].vwq) >=
-	    (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)) {
-		netif_wake_subqueue(enic->netdev, q_number);
-		enic->wq[q_number].stats.wake++;
-	}
-
-	spin_unlock(&enic->wq[q_number].lock);
-
-	return 0;
-}
-
 static bool enic_log_q_error(struct enic *enic)
 {
 	unsigned int i;
@@ -428,6 +377,36 @@ static void enic_mtu_check(struct enic *enic)
 	}
 }
 
+static void enic_set_rx_coal_setting(struct enic *enic)
+{
+	unsigned int speed;
+	int index = -1;
+	struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting;
+
+	/* 1. Read the link speed from fw
+	 * 2. Pick the default range for the speed
+	 * 3. Update it in enic->rx_coalesce_setting
+	 */
+	speed = vnic_dev_port_speed(enic->vdev);
+	if (speed > ENIC_LINK_SPEED_10G)
+		index = ENIC_LINK_40G_INDEX;
+	else if (speed > ENIC_LINK_SPEED_4G)
+		index = ENIC_LINK_10G_INDEX;
+	else
+		index = ENIC_LINK_4G_INDEX;
+
+	rx_coal->small_pkt_range_start = mod_range[index].small_pkt_range_start;
+	rx_coal->large_pkt_range_start = mod_range[index].large_pkt_range_start;
+	rx_coal->range_end = ENIC_RX_COALESCE_RANGE_END;
+
+	/* Start with the value provided by UCSM */
+	for (index = 0; index < enic->rq_count; index++)
+		enic->cq[index].cur_rx_coal_timeval =
+				enic->config.intr_timer_usec;
+
+	rx_coal->use_adaptive_rx_coalesce = 1;
+}
+
 static void enic_link_check(struct enic *enic)
 {
 	int link_status = vnic_dev_link_status(enic->vdev);
@@ -436,6 +415,7 @@ static void enic_link_check(struct enic *enic)
 	if (link_status && !carrier_ok) {
 		netdev_info(enic->netdev, "Link UP\n");
 		netif_carrier_on(enic->netdev);
+		enic_set_rx_coal_setting(enic);
 	} else if (!link_status && carrier_ok) {
 		netdev_info(enic->netdev, "Link DOWN\n");
 		netif_carrier_off(enic->netdev);
@@ -1282,243 +1262,6 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-
-	if (!buf->os_buf)
-		return;
-
-	dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-			 DMA_FROM_DEVICE);
-	dev_kfree_skb_any(buf->os_buf);
-	buf->os_buf = NULL;
-}
-
-static int enic_rq_alloc_buf(struct vnic_rq *rq)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-	struct net_device *netdev = enic->netdev;
-	struct sk_buff *skb;
-	unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
-	unsigned int os_buf_index = 0;
-	dma_addr_t dma_addr;
-	struct vnic_rq_buf *buf = rq->to_use;
-
-	if (buf->os_buf) {
-		enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
-				   buf->len);
-
-		return 0;
-	}
-	skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!skb) {
-		enic->rq[rq->index].stats.no_skb++;
-		return -ENOMEM;
-	}
-
-	dma_addr = dma_map_single(&enic->pdev->dev, skb->data, len,
-				  DMA_FROM_DEVICE);
-	if (unlikely(enic_dma_map_check(enic, dma_addr))) {
-		dev_kfree_skb(skb);
-		return -ENOMEM;
-	}
-
-	enic_queue_rq_desc(rq, skb, os_buf_index,
-		dma_addr, len);
-
-	return 0;
-}
-
-static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
-				      u32 pkt_len)
-{
-	if (ENIC_LARGE_PKT_THRESHOLD <= pkt_len)
-		pkt_size->large_pkt_bytes_cnt += pkt_len;
-	else
-		pkt_size->small_pkt_bytes_cnt += pkt_len;
-}
-
-static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb,
-			     struct vnic_rq_buf *buf, u16 len)
-{
-	struct enic *enic = netdev_priv(netdev);
-	struct sk_buff *new_skb;
-
-	if (len > enic->rx_copybreak)
-		return false;
-	new_skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!new_skb)
-		return false;
-	dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr, len,
-				DMA_FROM_DEVICE);
-	memcpy(new_skb->data, (*skb)->data, len);
-	*skb = new_skb;
-
-	return true;
-}
-
-static void enic_rq_indicate_buf(struct vnic_rq *rq,
-	struct cq_desc *cq_desc, struct vnic_rq_buf *buf,
-	int skipped, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-	struct net_device *netdev = enic->netdev;
-	struct sk_buff *skb;
-	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
-	struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats;
-
-	u8 type, color, eop, sop, ingress_port, vlan_stripped;
-	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
-	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
-	u8 ipv6, ipv4, ipv4_fragment, fcs_ok, rss_type, csum_not_calc;
-	u8 packet_error;
-	u16 q_number, completed_index, bytes_written, vlan_tci, checksum;
-	u32 rss_hash;
-	bool outer_csum_ok = true, encap = false;
-
-	rqstats->packets++;
-	if (skipped) {
-		rqstats->desc_skip++;
-		return;
-	}
-
-	skb = buf->os_buf;
-
-	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc,
-		&type, &color, &q_number, &completed_index,
-		&ingress_port, &fcoe, &eop, &sop, &rss_type,
-		&csum_not_calc, &rss_hash, &bytes_written,
-		&packet_error, &vlan_stripped, &vlan_tci, &checksum,
-		&fcoe_sof, &fcoe_fc_crc_ok, &fcoe_enc_error,
-		&fcoe_eof, &tcp_udp_csum_ok, &udp, &tcp,
-		&ipv4_csum_ok, &ipv6, &ipv4, &ipv4_fragment,
-		&fcs_ok);
-
-	if (packet_error) {
-
-		if (!fcs_ok) {
-			if (bytes_written > 0)
-				rqstats->bad_fcs++;
-			else if (bytes_written == 0)
-				rqstats->pkt_truncated++;
-		}
-
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(skb);
-		buf->os_buf = NULL;
-
-		return;
-	}
-
-	if (eop && bytes_written > 0) {
-
-		/* Good receive
-		 */
-		rqstats->bytes += bytes_written;
-		if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) {
-			buf->os_buf = NULL;
-			dma_unmap_single(&enic->pdev->dev, buf->dma_addr,
-					 buf->len, DMA_FROM_DEVICE);
-		}
-		prefetch(skb->data - NET_IP_ALIGN);
-
-		skb_put(skb, bytes_written);
-		skb->protocol = eth_type_trans(skb, netdev);
-		skb_record_rx_queue(skb, q_number);
-		if ((netdev->features & NETIF_F_RXHASH) && rss_hash &&
-		    (type == 3)) {
-			switch (rss_type) {
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
-				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
-				rqstats->l4_rss_hash++;
-				break;
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
-				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
-				rqstats->l3_rss_hash++;
-				break;
-			}
-		}
-		if (enic->vxlan.vxlan_udp_port_number) {
-			switch (enic->vxlan.patch_level) {
-			case 0:
-				if (fcoe) {
-					encap = true;
-					outer_csum_ok = fcoe_fc_crc_ok;
-				}
-				break;
-			case 2:
-				if ((type == 7) &&
-				    (rss_hash & BIT(0))) {
-					encap = true;
-					outer_csum_ok = (rss_hash & BIT(1)) &&
-							(rss_hash & BIT(2));
-				}
-				break;
-			}
-		}
-
-		/* Hardware does not provide whole packet checksum. It only
-		 * provides pseudo checksum. Since hw validates the packet
-		 * checksum but not provide us the checksum value. use
-		 * CHECSUM_UNNECESSARY.
-		 *
-		 * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is
-		 * inner csum_ok. outer_csum_ok is set by hw when outer udp
-		 * csum is correct or is zero.
-		 */
-		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
-		    tcp_udp_csum_ok && outer_csum_ok &&
-		    (ipv4_csum_ok || ipv6)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = encap;
-			if (encap)
-				rqstats->csum_unnecessary_encap++;
-			else
-				rqstats->csum_unnecessary++;
-		}
-
-		if (vlan_stripped) {
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
-			rqstats->vlan_stripped++;
-		}
-		skb_mark_napi_id(skb, &enic->napi[rq->index]);
-		if (!(netdev->features & NETIF_F_GRO))
-			netif_receive_skb(skb);
-		else
-			napi_gro_receive(&enic->napi[q_number], skb);
-		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
-			enic_intr_update_pkt_size(&cq->pkt_size_counter,
-						  bytes_written);
-	} else {
-
-		/* Buffer overflow
-		 */
-		rqstats->pkt_truncated++;
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(skb);
-		buf->os_buf = NULL;
-	}
-}
-
-static int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(vdev);
-
-	vnic_rq_service(&enic->rq[q_number].vrq, cq_desc,
-		completed_index, VNIC_RQ_RETURN_DESC,
-		enic_rq_indicate_buf, opaque);
-
-	return 0;
-}
-
 static void enic_set_int_moderation(struct enic *enic, struct vnic_rq *rq)
 {
 	unsigned int intr = enic_msix_rq_intr(enic, rq->index);
@@ -1589,12 +1332,10 @@ static int enic_poll(struct napi_struct *napi, int budget)
 	unsigned int  work_done, rq_work_done = 0, wq_work_done;
 	int err;
 
-	wq_work_done = vnic_cq_service(&enic->cq[cq_wq], wq_work_to_do,
-				       enic_wq_service, NULL);
+	wq_work_done = enic_wq_cq_service(enic, cq_wq, wq_work_to_do);
 
 	if (budget > 0)
-		rq_work_done = vnic_cq_service(&enic->cq[cq_rq],
-			rq_work_to_do, enic_rq_service, NULL);
+		rq_work_done = enic_rq_cq_service(enic, cq_rq, rq_work_to_do);
 
 	/* Accumulate intr event credits for this polling
 	 * cycle.  An intr event is the completion of a
@@ -1693,8 +1434,8 @@ static int enic_poll_msix_wq(struct napi_struct *napi, int budget)
 	wq_irq = wq->index;
 	cq = enic_cq_wq(enic, wq_irq);
 	intr = enic_msix_wq_intr(enic, wq_irq);
-	wq_work_done = vnic_cq_service(&enic->cq[cq], wq_work_to_do,
-				       enic_wq_service, NULL);
+
+	wq_work_done = enic_wq_cq_service(enic, cq, wq_work_to_do);
 
 	vnic_intr_return_credits(&enic->intr[intr], wq_work_done,
 				 0 /* don't unmask intr */,
@@ -1723,8 +1464,7 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget)
 	 */
 
 	if (budget > 0)
-		work_done = vnic_cq_service(&enic->cq[cq],
-			work_to_do, enic_rq_service, NULL);
+		work_done = enic_rq_cq_service(enic, cq, work_to_do);
 
 	/* Return intr event credits for this polling
 	 * cycle.  An intr event is the completion of a
@@ -1770,7 +1510,7 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget)
 
 static void enic_notify_timer(struct timer_list *t)
 {
-	struct enic *enic = from_timer(enic, t, notify_timer);
+	struct enic *enic = timer_container_of(enic, t, notify_timer);
 
 	enic_notify_check(enic);
 
@@ -1901,36 +1641,6 @@ static void enic_synchronize_irqs(struct enic *enic)
 	}
 }
 
-static void enic_set_rx_coal_setting(struct enic *enic)
-{
-	unsigned int speed;
-	int index = -1;
-	struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting;
-
-	/* 1. Read the link speed from fw
-	 * 2. Pick the default range for the speed
-	 * 3. Update it in enic->rx_coalesce_setting
-	 */
-	speed = vnic_dev_port_speed(enic->vdev);
-	if (ENIC_LINK_SPEED_10G < speed)
-		index = ENIC_LINK_40G_INDEX;
-	else if (ENIC_LINK_SPEED_4G < speed)
-		index = ENIC_LINK_10G_INDEX;
-	else
-		index = ENIC_LINK_4G_INDEX;
-
-	rx_coal->small_pkt_range_start = mod_range[index].small_pkt_range_start;
-	rx_coal->large_pkt_range_start = mod_range[index].large_pkt_range_start;
-	rx_coal->range_end = ENIC_RX_COALESCE_RANGE_END;
-
-	/* Start with the value provided by UCSM */
-	for (index = 0; index < enic->rq_count; index++)
-		enic->cq[index].cur_rx_coal_timeval =
-				enic->config.intr_timer_usec;
-
-	rx_coal->use_adaptive_rx_coalesce = 1;
-}
-
 static int enic_dev_notify_set(struct enic *enic)
 {
 	int err;
@@ -1971,6 +1681,17 @@ static int enic_open(struct net_device *netdev)
 	struct enic *enic = netdev_priv(netdev);
 	unsigned int i;
 	int err, ret;
+	unsigned int max_pkt_len = netdev->mtu + VLAN_ETH_HLEN;
+	struct page_pool_params pp_params = {
+		.order = get_order(max_pkt_len),
+		.pool_size = enic->config.rq_desc_count,
+		.nid = dev_to_node(&enic->pdev->dev),
+		.dev = &enic->pdev->dev,
+		.dma_dir = DMA_FROM_DEVICE,
+		.max_len = (max_pkt_len > PAGE_SIZE) ? max_pkt_len : PAGE_SIZE,
+		.netdev = netdev,
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+	};
 
 	err = enic_request_intr(enic);
 	if (err) {
@@ -1988,6 +1709,16 @@ static int enic_open(struct net_device *netdev)
 	}
 
 	for (i = 0; i < enic->rq_count; i++) {
+		/* create a page pool for each RQ */
+		pp_params.napi = &enic->napi[i];
+		pp_params.queue_idx = i;
+		enic->rq[i].pool = page_pool_create(&pp_params);
+		if (IS_ERR(enic->rq[i].pool)) {
+			err = PTR_ERR(enic->rq[i].pool);
+			enic->rq[i].pool = NULL;
+			goto err_out_free_rq;
+		}
+
 		/* enable rq before updating rq desc */
 		vnic_rq_enable(&enic->rq[i].vrq);
 		vnic_rq_fill(&enic->rq[i].vrq, enic_rq_alloc_buf);
@@ -2028,8 +1759,11 @@ static int enic_open(struct net_device *netdev)
 err_out_free_rq:
 	for (i = 0; i < enic->rq_count; i++) {
 		ret = vnic_rq_disable(&enic->rq[i].vrq);
-		if (!ret)
+		if (!ret) {
 			vnic_rq_clean(&enic->rq[i].vrq, enic_free_rq_buf);
+			page_pool_destroy(enic->rq[i].pool);
+			enic->rq[i].pool = NULL;
+		}
 	}
 	enic_dev_notify_unset(enic);
 err_out_free_intr:
@@ -2053,7 +1787,7 @@ static int enic_stop(struct net_device *netdev)
 
 	enic_synchronize_irqs(enic);
 
-	del_timer_sync(&enic->notify_timer);
+	timer_delete_sync(&enic->notify_timer);
 	enic_rfs_flw_tbl_free(enic);
 
 	enic_dev_disable(enic);
@@ -2087,8 +1821,11 @@ static int enic_stop(struct net_device *netdev)
 
 	for (i = 0; i < enic->wq_count; i++)
 		vnic_wq_clean(&enic->wq[i].vwq, enic_free_wq_buf);
-	for (i = 0; i < enic->rq_count; i++)
+	for (i = 0; i < enic->rq_count; i++) {
 		vnic_rq_clean(&enic->rq[i].vrq, enic_free_rq_buf);
+		page_pool_destroy(enic->rq[i].pool);
+		enic->rq[i].pool = NULL;
+	}
 	for (i = 0; i < enic->cq_count; i++)
 		vnic_cq_clean(&enic->cq[i]);
 	for (i = 0; i < enic->intr_count; i++)
@@ -2127,10 +1864,10 @@ static int enic_change_mtu(struct net_device *netdev, int new_mtu)
 	if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic))
 		return -EOPNOTSUPP;
 
-	if (netdev->mtu > enic->port_mtu)
+	if (new_mtu > enic->port_mtu)
 		netdev_warn(netdev,
 			    "interface MTU (%d) set higher than port MTU (%d)\n",
-			    netdev->mtu, enic->port_mtu);
+			    new_mtu, enic->port_mtu);
 
 	return _enic_change_mtu(netdev, new_mtu);
 }
@@ -2404,6 +2141,7 @@ static void enic_reset(struct work_struct *work)
 	enic_init_vnic_resources(enic);
 	enic_set_rss_nic_cfg(enic);
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
+	enic_ext_cq(enic);
 	enic_open(enic->netdev);
 
 	/* Allow infiniband to fiddle with the device again */
@@ -2430,6 +2168,7 @@ static void enic_tx_hang_reset(struct work_struct *work)
 	enic_init_vnic_resources(enic);
 	enic_set_rss_nic_cfg(enic);
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
+	enic_ext_cq(enic);
 	enic_open(enic->netdev);
 
 	/* Allow infiniband to fiddle with the device again */
@@ -2557,7 +2296,8 @@ static int enic_adjust_resources(struct enic *enic)
 		 * used based on which resource is the most constrained
 		 */
 		wq_avail = min(enic->wq_avail, ENIC_WQ_MAX);
-		rq_default = netif_get_num_default_rss_queues();
+		rq_default = max(netif_get_num_default_rss_queues(),
+				 ENIC_RQ_MIN_DEFAULT);
 		rq_avail = min3(enic->rq_avail, ENIC_RQ_MAX, rq_default);
 		max_queues = min(enic->cq_avail,
 				 enic->intr_avail - ENIC_MSIX_RESERVED_INTR);
@@ -2598,6 +2338,7 @@ static void enic_get_queue_stats_rx(struct net_device *dev, int idx,
 	rxs->hw_drop_overruns = rqstats->pkt_truncated;
 	rxs->csum_unnecessary = rqstats->csum_unnecessary +
 				rqstats->csum_unnecessary_encap;
+	rxs->alloc_fail = rqstats->pp_alloc_fail;
 }
 
 static void enic_get_queue_stats_tx(struct net_device *dev, int idx,
@@ -2625,6 +2366,7 @@ static void enic_get_base_stats(struct net_device *dev,
 	rxs->hw_drops = 0;
 	rxs->hw_drop_overruns = 0;
 	rxs->csum_unnecessary = 0;
+	rxs->alloc_fail = 0;
 	txs->bytes = 0;
 	txs->packets = 0;
 	txs->csum_none = 0;
@@ -2802,6 +2544,8 @@ static int enic_dev_init(struct enic *enic)
 
 	enic_get_res_counts(enic);
 
+	enic_ext_cq(enic);
+
 	err = enic_alloc_enic_resources(enic);
 	if (err) {
 		dev_err(dev, "Failed to allocate enic resources\n");
@@ -3063,7 +2807,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	timer_setup(&enic->notify_timer, enic_notify_timer, 0);
 
 	enic_rfs_flw_tbl_init(enic);
-	enic_set_rx_coal_setting(enic);
 	INIT_WORK(&enic->reset, enic_reset);
 	INIT_WORK(&enic->tx_hang_reset, enic_tx_hang_reset);
 	INIT_WORK(&enic->change_mtu_work, enic_change_mtu_work);
@@ -3179,7 +2922,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(dev, "Cannot register net device, aborting\n");
 		goto err_out_dev_deinit;
 	}
-	enic->rx_copybreak = RX_COPYBREAK_DEFAULT;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/cisco/enic/enic_res.c b/drivers/net/ethernet/cisco/enic/enic_res.c
index 126125199833..bbd3143ed73e 100644
--- a/drivers/net/ethernet/cisco/enic/enic_res.c
+++ b/drivers/net/ethernet/cisco/enic/enic_res.c
@@ -59,31 +59,38 @@ int enic_get_vnic_config(struct enic *enic)
 	GET_CONFIG(intr_timer_usec);
 	GET_CONFIG(loop_tag);
 	GET_CONFIG(num_arfs);
+	GET_CONFIG(max_rq_ring);
+	GET_CONFIG(max_wq_ring);
+	GET_CONFIG(max_cq_ring);
+
+	if (!c->max_wq_ring)
+		c->max_wq_ring = ENIC_MAX_WQ_DESCS_DEFAULT;
+	if (!c->max_rq_ring)
+		c->max_rq_ring = ENIC_MAX_RQ_DESCS_DEFAULT;
+	if (!c->max_cq_ring)
+		c->max_cq_ring = ENIC_MAX_CQ_DESCS_DEFAULT;
 
 	c->wq_desc_count =
-		min_t(u32, ENIC_MAX_WQ_DESCS,
-		max_t(u32, ENIC_MIN_WQ_DESCS,
-		c->wq_desc_count));
+		min_t(u32, c->max_wq_ring,
+		      max_t(u32, ENIC_MIN_WQ_DESCS, c->wq_desc_count));
 	c->wq_desc_count &= 0xffffffe0; /* must be aligned to groups of 32 */
 
 	c->rq_desc_count =
-		min_t(u32, ENIC_MAX_RQ_DESCS,
-		max_t(u32, ENIC_MIN_RQ_DESCS,
-		c->rq_desc_count));
+		min_t(u32, c->max_rq_ring,
+		      max_t(u32, ENIC_MIN_RQ_DESCS, c->rq_desc_count));
 	c->rq_desc_count &= 0xffffffe0; /* must be aligned to groups of 32 */
 
 	if (c->mtu == 0)
 		c->mtu = 1500;
-	c->mtu = min_t(u16, ENIC_MAX_MTU,
-		max_t(u16, ENIC_MIN_MTU,
-		c->mtu));
+	c->mtu = min_t(u16, ENIC_MAX_MTU, max_t(u16, ENIC_MIN_MTU, c->mtu));
 
 	c->intr_timer_usec = min_t(u32, c->intr_timer_usec,
 		vnic_dev_get_intr_coal_timer_max(enic->vdev));
 
 	dev_info(enic_get_dev(enic),
-		"vNIC MAC addr %pM wq/rq %d/%d mtu %d\n",
-		enic->mac_addr, c->wq_desc_count, c->rq_desc_count, c->mtu);
+		 "vNIC MAC addr %pM wq/rq %d/%d max wq/rq/cq %d/%d/%d mtu %d\n",
+		 enic->mac_addr, c->wq_desc_count, c->rq_desc_count,
+		 c->max_wq_ring, c->max_rq_ring, c->max_cq_ring, c->mtu);
 
 	dev_info(enic_get_dev(enic), "vNIC csum tx/rx %s/%s "
 		"tso/lro %s/%s rss %s intr mode %s type %s timer %d usec "
@@ -312,6 +319,7 @@ void enic_init_vnic_resources(struct enic *enic)
 int enic_alloc_vnic_resources(struct enic *enic)
 {
 	enum vnic_dev_intr_mode intr_mode;
+	int rq_cq_desc_size;
 	unsigned int i;
 	int err;
 
@@ -326,6 +334,24 @@ int enic_alloc_vnic_resources(struct enic *enic)
 		intr_mode == VNIC_DEV_INTR_MODE_MSIX ? "MSI-X" :
 		"unknown");
 
+	switch (enic->ext_cq) {
+	case ENIC_RQ_CQ_ENTRY_SIZE_16:
+		rq_cq_desc_size = 16;
+		break;
+	case ENIC_RQ_CQ_ENTRY_SIZE_32:
+		rq_cq_desc_size = 32;
+		break;
+	case ENIC_RQ_CQ_ENTRY_SIZE_64:
+		rq_cq_desc_size = 64;
+		break;
+	default:
+		dev_err(enic_get_dev(enic),
+			"Unable to determine rq cq desc size: %d",
+			enic->ext_cq);
+		err = -ENODEV;
+		goto err_out;
+	}
+
 	/* Allocate queue resources
 	 */
 
@@ -348,8 +374,8 @@ int enic_alloc_vnic_resources(struct enic *enic)
 	for (i = 0; i < enic->cq_count; i++) {
 		if (i < enic->rq_count)
 			err = vnic_cq_alloc(enic->vdev, &enic->cq[i], i,
-				enic->config.rq_desc_count,
-				sizeof(struct cq_enet_rq_desc));
+					enic->config.rq_desc_count,
+					rq_cq_desc_size);
 		else
 			err = vnic_cq_alloc(enic->vdev, &enic->cq[i], i,
 				enic->config.wq_desc_count,
@@ -380,6 +406,39 @@ int enic_alloc_vnic_resources(struct enic *enic)
 
 err_out_cleanup:
 	enic_free_vnic_resources(enic);
-
+err_out:
 	return err;
 }
+
+/*
+ * CMD_CQ_ENTRY_SIZE_SET can fail on older hw generations that don't support
+ * that command
+ */
+void enic_ext_cq(struct enic *enic)
+{
+	u64 a0 = CMD_CQ_ENTRY_SIZE_SET, a1 = 0;
+	int wait = 1000;
+	int ret;
+
+	spin_lock_bh(&enic->devcmd_lock);
+	ret = vnic_dev_cmd(enic->vdev, CMD_CAPABILITY, &a0, &a1, wait);
+	if (ret || a0) {
+		dev_info(&enic->pdev->dev,
+			 "CMD_CQ_ENTRY_SIZE_SET not supported.");
+		enic->ext_cq = ENIC_RQ_CQ_ENTRY_SIZE_16;
+		goto out;
+	}
+	a1 &= VNIC_RQ_CQ_ENTRY_SIZE_ALL_BIT;
+	enic->ext_cq = fls(a1) - 1;
+	a0 = VNIC_RQ_ALL;
+	a1 = enic->ext_cq;
+	ret = vnic_dev_cmd(enic->vdev, CMD_CQ_ENTRY_SIZE_SET, &a0, &a1, wait);
+	if (ret) {
+		dev_info(&enic->pdev->dev, "CMD_CQ_ENTRY_SIZE_SET failed.");
+		enic->ext_cq = ENIC_RQ_CQ_ENTRY_SIZE_16;
+	}
+out:
+	spin_unlock_bh(&enic->devcmd_lock);
+	dev_info(&enic->pdev->dev, "CQ entry size set to %d bytes",
+		 16 << enic->ext_cq);
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_res.h b/drivers/net/ethernet/cisco/enic/enic_res.h
index b8ee42d297aa..02dca1ae4a22 100644
--- a/drivers/net/ethernet/cisco/enic/enic_res.h
+++ b/drivers/net/ethernet/cisco/enic/enic_res.h
@@ -12,10 +12,13 @@
 #include "vnic_wq.h"
 #include "vnic_rq.h"
 
-#define ENIC_MIN_WQ_DESCS		64
-#define ENIC_MAX_WQ_DESCS		4096
-#define ENIC_MIN_RQ_DESCS		64
-#define ENIC_MAX_RQ_DESCS		4096
+#define ENIC_MIN_WQ_DESCS 64
+#define ENIC_MAX_WQ_DESCS_DEFAULT 4096
+#define ENIC_MAX_WQ_DESCS 16384
+#define ENIC_MIN_RQ_DESCS 64
+#define ENIC_MAX_RQ_DESCS 16384
+#define ENIC_MAX_RQ_DESCS_DEFAULT 4096
+#define ENIC_MAX_CQ_DESCS_DEFAULT (64 * 1024)
 
 #define ENIC_MIN_MTU			ETH_MIN_MTU
 #define ENIC_MAX_MTU			9000
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.c b/drivers/net/ethernet/cisco/enic/enic_rq.c
new file mode 100644
index 000000000000..ccbf5c9a21d0
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.c
@@ -0,0 +1,436 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2024 Cisco Systems, Inc.  All rights reserved.
+
+#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
+#include <net/busy_poll.h>
+#include "enic.h"
+#include "enic_res.h"
+#include "enic_rq.h"
+#include "vnic_rq.h"
+#include "cq_enet_desc.h"
+
+#define ENIC_LARGE_PKT_THRESHOLD                1000
+
+static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
+				      u32 pkt_len)
+{
+	if (pkt_len > ENIC_LARGE_PKT_THRESHOLD)
+		pkt_size->large_pkt_bytes_cnt += pkt_len;
+	else
+		pkt_size->small_pkt_bytes_cnt += pkt_len;
+}
+
+static void enic_rq_cq_desc_dec(void *cq_desc, u8 cq_desc_size, u8 *type,
+				u8 *color, u16 *q_number, u16 *completed_index)
+{
+	/* type_color is the last field for all cq structs */
+	u8 type_color;
+
+	switch (cq_desc_size) {
+	case VNIC_RQ_CQ_ENTRY_SIZE_16: {
+		struct cq_enet_rq_desc *desc =
+			(struct cq_enet_rq_desc *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
+
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		break;
+	}
+	case VNIC_RQ_CQ_ENTRY_SIZE_32: {
+		struct cq_enet_rq_desc_32 *desc =
+			(struct cq_enet_rq_desc_32 *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
+
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		*completed_index |= (desc->fetch_index_flags & CQ_DESC_32_FI_MASK) <<
+				CQ_DESC_COMP_NDX_BITS;
+		break;
+	}
+	case VNIC_RQ_CQ_ENTRY_SIZE_64: {
+		struct cq_enet_rq_desc_64 *desc =
+			(struct cq_enet_rq_desc_64 *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
+
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		*completed_index |= (desc->fetch_index_flags & CQ_DESC_64_FI_MASK) <<
+				CQ_DESC_COMP_NDX_BITS;
+		break;
+	}
+	}
+
+	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
+	*type = type_color & CQ_DESC_TYPE_MASK;
+}
+
+static void enic_rq_set_skb_flags(struct vnic_rq *vrq, u8 type, u32 rss_hash,
+				  u8 rss_type, u8 fcoe, u8 fcoe_fc_crc_ok,
+				  u8 vlan_stripped, u8 csum_not_calc,
+				  u8 tcp_udp_csum_ok, u8 ipv6, u8 ipv4_csum_ok,
+				  u16 vlan_tci, struct sk_buff *skb)
+{
+	struct enic *enic = vnic_dev_priv(vrq->vdev);
+	struct net_device *netdev = enic->netdev;
+	struct enic_rq_stats *rqstats =  &enic->rq[vrq->index].stats;
+	bool outer_csum_ok = true, encap = false;
+
+	if ((netdev->features & NETIF_F_RXHASH) && rss_hash && type == 3) {
+		switch (rss_type) {
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
+			skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
+			rqstats->l4_rss_hash++;
+			break;
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
+			skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
+			rqstats->l3_rss_hash++;
+			break;
+		}
+	}
+	if (enic->vxlan.vxlan_udp_port_number) {
+		switch (enic->vxlan.patch_level) {
+		case 0:
+			if (fcoe) {
+				encap = true;
+				outer_csum_ok = fcoe_fc_crc_ok;
+			}
+			break;
+		case 2:
+			if (type == 7 && (rss_hash & BIT(0))) {
+				encap = true;
+				outer_csum_ok = (rss_hash & BIT(1)) &&
+						(rss_hash & BIT(2));
+			}
+			break;
+		}
+	}
+
+	/* Hardware does not provide whole packet checksum. It only
+	 * provides pseudo checksum. Since hw validates the packet
+	 * checksum but not provide us the checksum value. use
+	 * CHECSUM_UNNECESSARY.
+	 *
+	 * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is
+	 * inner csum_ok. outer_csum_ok is set by hw when outer udp
+	 * csum is correct or is zero.
+	 */
+	if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
+	    tcp_udp_csum_ok && outer_csum_ok && (ipv4_csum_ok || ipv6)) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->csum_level = encap;
+		if (encap)
+			rqstats->csum_unnecessary_encap++;
+		else
+			rqstats->csum_unnecessary++;
+	}
+
+	if (vlan_stripped) {
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
+		rqstats->vlan_stripped++;
+	}
+}
+
+/*
+ * cq_enet_rq_desc accesses section uses only the 1st 15 bytes of the cq which
+ * is identical for all type (16,32 and 64 byte) of cqs.
+ */
+static void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc, u8 *ingress_port,
+				u8 *fcoe, u8 *eop, u8 *sop, u8 *rss_type,
+				u8 *csum_not_calc, u32 *rss_hash,
+				u16 *bytes_written, u8 *packet_error,
+				u8 *vlan_stripped, u16 *vlan_tci,
+				u16 *checksum, u8 *fcoe_sof,
+				u8 *fcoe_fc_crc_ok, u8 *fcoe_enc_error,
+				u8 *fcoe_eof, u8 *tcp_udp_csum_ok, u8 *udp,
+				u8 *tcp, u8 *ipv4_csum_ok, u8 *ipv6, u8 *ipv4,
+				u8 *ipv4_fragment, u8 *fcs_ok)
+{
+	u16 completed_index_flags;
+	u16 q_number_rss_type_flags;
+	u16 bytes_written_flags;
+
+	completed_index_flags = le16_to_cpu(desc->completed_index_flags);
+	q_number_rss_type_flags =
+		le16_to_cpu(desc->q_number_rss_type_flags);
+	bytes_written_flags = le16_to_cpu(desc->bytes_written_flags);
+
+	*ingress_port = (completed_index_flags &
+		CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT) ? 1 : 0;
+	*fcoe = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_FCOE) ?
+		1 : 0;
+	*eop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_EOP) ?
+		1 : 0;
+	*sop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_SOP) ?
+		1 : 0;
+
+	*rss_type = (u8)((q_number_rss_type_flags >> CQ_DESC_Q_NUM_BITS) &
+		CQ_ENET_RQ_DESC_RSS_TYPE_MASK);
+	*csum_not_calc = (q_number_rss_type_flags &
+		CQ_ENET_RQ_DESC_FLAGS_CSUM_NOT_CALC) ? 1 : 0;
+
+	*rss_hash = le32_to_cpu(desc->rss_hash);
+
+	*bytes_written = bytes_written_flags &
+		CQ_ENET_RQ_DESC_BYTES_WRITTEN_MASK;
+	*packet_error = (bytes_written_flags &
+		CQ_ENET_RQ_DESC_FLAGS_TRUNCATED) ? 1 : 0;
+	*vlan_stripped = (bytes_written_flags &
+		CQ_ENET_RQ_DESC_FLAGS_VLAN_STRIPPED) ? 1 : 0;
+
+	/*
+	 * Tag Control Information(16) = user_priority(3) + cfi(1) + vlan(12)
+	 */
+	*vlan_tci = le16_to_cpu(desc->vlan);
+
+	if (*fcoe) {
+		*fcoe_sof = (u8)(le16_to_cpu(desc->checksum_fcoe) &
+			CQ_ENET_RQ_DESC_FCOE_SOF_MASK);
+		*fcoe_fc_crc_ok = (desc->flags &
+			CQ_ENET_RQ_DESC_FCOE_FC_CRC_OK) ? 1 : 0;
+		*fcoe_enc_error = (desc->flags &
+			CQ_ENET_RQ_DESC_FCOE_ENC_ERROR) ? 1 : 0;
+		*fcoe_eof = (u8)((le16_to_cpu(desc->checksum_fcoe) >>
+			CQ_ENET_RQ_DESC_FCOE_EOF_SHIFT) &
+			CQ_ENET_RQ_DESC_FCOE_EOF_MASK);
+		*checksum = 0;
+	} else {
+		*fcoe_sof = 0;
+		*fcoe_fc_crc_ok = 0;
+		*fcoe_enc_error = 0;
+		*fcoe_eof = 0;
+		*checksum = le16_to_cpu(desc->checksum_fcoe);
+	}
+
+	*tcp_udp_csum_ok =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP_UDP_CSUM_OK) ? 1 : 0;
+	*udp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_UDP) ? 1 : 0;
+	*tcp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP) ? 1 : 0;
+	*ipv4_csum_ok =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_CSUM_OK) ? 1 : 0;
+	*ipv6 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV6) ? 1 : 0;
+	*ipv4 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4) ? 1 : 0;
+	*ipv4_fragment =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT) ? 1 : 0;
+	*fcs_ok = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_FCS_OK) ? 1 : 0;
+}
+
+static bool enic_rq_pkt_error(struct vnic_rq *vrq, u8 packet_error, u8 fcs_ok,
+			      u16 bytes_written)
+{
+	struct enic *enic = vnic_dev_priv(vrq->vdev);
+	struct enic_rq_stats *rqstats = &enic->rq[vrq->index].stats;
+
+	if (packet_error) {
+		if (!fcs_ok) {
+			if (bytes_written > 0)
+				rqstats->bad_fcs++;
+			else if (bytes_written == 0)
+				rqstats->pkt_truncated++;
+		}
+		return true;
+	}
+	return false;
+}
+
+int enic_rq_alloc_buf(struct vnic_rq *rq)
+{
+	struct enic *enic = vnic_dev_priv(rq->vdev);
+	struct net_device *netdev = enic->netdev;
+	struct enic_rq *erq = &enic->rq[rq->index];
+	struct enic_rq_stats *rqstats = &erq->stats;
+	unsigned int offset = 0;
+	unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
+	unsigned int os_buf_index = 0;
+	dma_addr_t dma_addr;
+	struct vnic_rq_buf *buf = rq->to_use;
+	struct page *page;
+	unsigned int truesize = len;
+
+	if (buf->os_buf) {
+		enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
+				   buf->len);
+
+		return 0;
+	}
+
+	page = page_pool_dev_alloc(erq->pool, &offset, &truesize);
+	if (unlikely(!page)) {
+		rqstats->pp_alloc_fail++;
+		return -ENOMEM;
+	}
+	buf->offset = offset;
+	buf->truesize = truesize;
+	dma_addr = page_pool_get_dma_addr(page) + offset;
+	enic_queue_rq_desc(rq, (void *)page, os_buf_index, dma_addr, len);
+
+	return 0;
+}
+
+void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
+{
+	struct enic *enic = vnic_dev_priv(rq->vdev);
+	struct enic_rq *erq = &enic->rq[rq->index];
+
+	if (!buf->os_buf)
+		return;
+
+	page_pool_put_full_page(erq->pool, (struct page *)buf->os_buf, true);
+	buf->os_buf = NULL;
+}
+
+static void enic_rq_indicate_buf(struct enic *enic, struct vnic_rq *rq,
+				 struct vnic_rq_buf *buf, void *cq_desc,
+				 u8 type, u16 q_number, u16 completed_index)
+{
+	struct sk_buff *skb;
+	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
+	struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats;
+	struct napi_struct *napi;
+
+	u8 eop, sop, ingress_port, vlan_stripped;
+	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
+	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
+	u8 ipv6, ipv4, ipv4_fragment, fcs_ok, rss_type, csum_not_calc;
+	u8 packet_error;
+	u16 bytes_written, vlan_tci, checksum;
+	u32 rss_hash;
+
+	rqstats->packets++;
+
+	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, &ingress_port,
+			    &fcoe, &eop, &sop, &rss_type, &csum_not_calc,
+			    &rss_hash, &bytes_written, &packet_error,
+			    &vlan_stripped, &vlan_tci, &checksum, &fcoe_sof,
+			    &fcoe_fc_crc_ok, &fcoe_enc_error, &fcoe_eof,
+			    &tcp_udp_csum_ok, &udp, &tcp, &ipv4_csum_ok, &ipv6,
+			    &ipv4, &ipv4_fragment, &fcs_ok);
+
+	if (enic_rq_pkt_error(rq, packet_error, fcs_ok, bytes_written))
+		return;
+
+	if (eop && bytes_written > 0) {
+		/* Good receive
+		 */
+		rqstats->bytes += bytes_written;
+		napi = &enic->napi[rq->index];
+		skb = napi_get_frags(napi);
+		if (unlikely(!skb)) {
+			net_warn_ratelimited("%s: skb alloc error rq[%d], desc[%d]\n",
+					     enic->netdev->name, rq->index,
+					     completed_index);
+			rqstats->no_skb++;
+			return;
+		}
+
+		prefetch(skb->data - NET_IP_ALIGN);
+
+		dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr,
+					bytes_written, DMA_FROM_DEVICE);
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				(struct page *)buf->os_buf, buf->offset,
+				bytes_written, buf->truesize);
+		skb_record_rx_queue(skb, q_number);
+		enic_rq_set_skb_flags(rq, type, rss_hash, rss_type, fcoe,
+				      fcoe_fc_crc_ok, vlan_stripped,
+				      csum_not_calc, tcp_udp_csum_ok, ipv6,
+				      ipv4_csum_ok, vlan_tci, skb);
+		skb_mark_for_recycle(skb);
+		napi_gro_frags(napi);
+		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
+			enic_intr_update_pkt_size(&cq->pkt_size_counter,
+						  bytes_written);
+		buf->os_buf = NULL;
+		buf->dma_addr = 0;
+		buf = buf->next;
+	} else {
+		/* Buffer overflow
+		 */
+		rqstats->pkt_truncated++;
+	}
+}
+
+static void enic_rq_service(struct enic *enic, void *cq_desc, u8 type,
+			    u16 q_number, u16 completed_index)
+{
+	struct enic_rq_stats *rqstats = &enic->rq[q_number].stats;
+	struct vnic_rq *vrq = &enic->rq[q_number].vrq;
+	struct vnic_rq_buf *vrq_buf = vrq->to_clean;
+	int skipped;
+
+	while (1) {
+		skipped = (vrq_buf->index != completed_index);
+		if (!skipped)
+			enic_rq_indicate_buf(enic, vrq, vrq_buf, cq_desc, type,
+					     q_number, completed_index);
+		else
+			rqstats->desc_skip++;
+
+		vrq->ring.desc_avail++;
+		vrq->to_clean = vrq_buf->next;
+		vrq_buf = vrq_buf->next;
+		if (!skipped)
+			break;
+	}
+}
+
+unsigned int enic_rq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do)
+{
+	struct vnic_cq *cq = &enic->cq[cq_index];
+	void *cq_desc = vnic_cq_to_clean(cq);
+	u16 q_number, completed_index;
+	unsigned int work_done = 0;
+	u8 type, color;
+
+	enic_rq_cq_desc_dec(cq_desc, enic->ext_cq, &type, &color, &q_number,
+			    &completed_index);
+
+	while (color != cq->last_color) {
+		enic_rq_service(enic, cq_desc, type, q_number, completed_index);
+		vnic_cq_inc_to_clean(cq);
+
+		if (++work_done >= work_to_do)
+			break;
+
+		cq_desc = vnic_cq_to_clean(cq);
+		enic_rq_cq_desc_dec(cq_desc, enic->ext_cq, &type, &color,
+				    &q_number, &completed_index);
+	}
+
+	return work_done;
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.h b/drivers/net/ethernet/cisco/enic/enic_rq.h
new file mode 100644
index 000000000000..98476a7297af
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright 2024 Cisco Systems, Inc.  All rights reserved.
+ */
+
+unsigned int enic_rq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do);
+int enic_rq_alloc_buf(struct vnic_rq *rq);
+void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf);
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.c b/drivers/net/ethernet/cisco/enic/enic_wq.c
new file mode 100644
index 000000000000..07936f8b4231
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2025 Cisco Systems, Inc.  All rights reserved.
+
+#include <net/netdev_queues.h>
+#include "enic_res.h"
+#include "enic.h"
+#include "enic_wq.h"
+
+#define ENET_CQ_DESC_COMP_NDX_BITS 14
+#define ENET_CQ_DESC_COMP_NDX_MASK GENMASK(ENET_CQ_DESC_COMP_NDX_BITS - 1, 0)
+
+static void enic_wq_cq_desc_dec(const struct cq_desc *desc_arg, bool ext_wq,
+				u8 *type, u8 *color, u16 *q_number,
+				u16 *completed_index)
+{
+	const struct cq_desc *desc = desc_arg;
+	const u8 type_color = desc->type_color;
+
+	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
+
+	/*
+	 * Make sure color bit is read from desc *before* other fields
+	 * are read from desc.  Hardware guarantees color bit is last
+	 * bit (byte) written.  Adding the rmb() prevents the compiler
+	 * and/or CPU from reordering the reads which would potentially
+	 * result in reading stale values.
+	 */
+	rmb();
+
+	*type = type_color & CQ_DESC_TYPE_MASK;
+	*q_number = le16_to_cpu(desc->q_number) & CQ_DESC_Q_NUM_MASK;
+
+	if (ext_wq)
+		*completed_index = le16_to_cpu(desc->completed_index) &
+			ENET_CQ_DESC_COMP_NDX_MASK;
+	else
+		*completed_index = le16_to_cpu(desc->completed_index) &
+			CQ_DESC_COMP_NDX_MASK;
+}
+
+void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
+{
+	struct enic *enic = vnic_dev_priv(wq->vdev);
+
+	if (buf->sop)
+		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
+				 DMA_TO_DEVICE);
+	else
+		dma_unmap_page(&enic->pdev->dev, buf->dma_addr, buf->len,
+			       DMA_TO_DEVICE);
+
+	if (buf->os_buf)
+		dev_kfree_skb_any(buf->os_buf);
+}
+
+static void enic_wq_free_buf(struct vnic_wq *wq, struct cq_desc *cq_desc,
+			     struct vnic_wq_buf *buf, void *opaque)
+{
+	struct enic *enic = vnic_dev_priv(wq->vdev);
+
+	enic->wq[wq->index].stats.cq_work++;
+	enic->wq[wq->index].stats.cq_bytes += buf->len;
+	enic_free_wq_buf(wq, buf);
+}
+
+static void enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
+			    u8 type, u16 q_number, u16 completed_index)
+{
+	struct enic *enic = vnic_dev_priv(vdev);
+
+	spin_lock(&enic->wq[q_number].lock);
+
+	vnic_wq_service(&enic->wq[q_number].vwq, cq_desc,
+			completed_index, enic_wq_free_buf, NULL);
+
+	if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number))
+	    && vnic_wq_desc_avail(&enic->wq[q_number].vwq) >=
+	    (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)) {
+		netif_wake_subqueue(enic->netdev, q_number);
+		enic->wq[q_number].stats.wake++;
+	}
+
+	spin_unlock(&enic->wq[q_number].lock);
+}
+
+unsigned int enic_wq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do)
+{
+	struct vnic_cq *cq = &enic->cq[cq_index];
+	u16 q_number, completed_index;
+	unsigned int work_done = 0;
+	struct cq_desc *cq_desc;
+	u8 type, color;
+	bool ext_wq;
+
+	ext_wq = cq->ring.size > ENIC_MAX_WQ_DESCS_DEFAULT;
+
+	cq_desc = (struct cq_desc *)vnic_cq_to_clean(cq);
+	enic_wq_cq_desc_dec(cq_desc, ext_wq, &type, &color,
+			    &q_number, &completed_index);
+
+	while (color != cq->last_color) {
+		enic_wq_service(cq->vdev, cq_desc, type, q_number,
+				completed_index);
+
+		vnic_cq_inc_to_clean(cq);
+
+		if (++work_done >= work_to_do)
+			break;
+
+		cq_desc = (struct cq_desc *)vnic_cq_to_clean(cq);
+		enic_wq_cq_desc_dec(cq_desc, ext_wq, &type, &color,
+				    &q_number, &completed_index);
+	}
+
+	return work_done;
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.h b/drivers/net/ethernet/cisco/enic/enic_wq.h
new file mode 100644
index 000000000000..12acb3f2fbc9
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright 2025 Cisco Systems, Inc.  All rights reserved.
+ */
+
+void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf);
+unsigned int enic_wq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_cq.h b/drivers/net/ethernet/cisco/enic/vnic_cq.h
index eed5bf59e5d2..0e37f5d5e527 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_cq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_cq.h
@@ -56,45 +56,18 @@ struct vnic_cq {
 	ktime_t prev_ts;
 };
 
-static inline unsigned int vnic_cq_service(struct vnic_cq *cq,
-	unsigned int work_to_do,
-	int (*q_service)(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque),
-	void *opaque)
+static inline void *vnic_cq_to_clean(struct vnic_cq *cq)
 {
-	struct cq_desc *cq_desc;
-	unsigned int work_done = 0;
-	u16 q_number, completed_index;
-	u8 type, color;
-
-	cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
-		cq->ring.desc_size * cq->to_clean);
-	cq_desc_dec(cq_desc, &type, &color,
-		&q_number, &completed_index);
-
-	while (color != cq->last_color) {
-
-		if ((*q_service)(cq->vdev, cq_desc, type,
-			q_number, completed_index, opaque))
-			break;
-
-		cq->to_clean++;
-		if (cq->to_clean == cq->ring.desc_count) {
-			cq->to_clean = 0;
-			cq->last_color = cq->last_color ? 0 : 1;
-		}
-
-		cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
-			cq->ring.desc_size * cq->to_clean);
-		cq_desc_dec(cq_desc, &type, &color,
-			&q_number, &completed_index);
+	return ((u8 *)cq->ring.descs + cq->ring.desc_size * cq->to_clean);
+}
 
-		work_done++;
-		if (work_done >= work_to_do)
-			break;
+static inline void vnic_cq_inc_to_clean(struct vnic_cq *cq)
+{
+	cq->to_clean++;
+	if (cq->to_clean == cq->ring.desc_count) {
+		cq->to_clean = 0;
+		cq->last_color = cq->last_color ? 0 : 1;
 	}
-
-	return work_done;
 }
 
 void vnic_cq_free(struct vnic_cq *cq);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
index db56d778877a..605ef17f967e 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
@@ -436,6 +436,25 @@ enum vnic_devcmd_cmd {
 	 * in: (u16) a2 = unsigned short int port information
 	 */
 	CMD_OVERLAY_OFFLOAD_CFG = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 73),
+
+	/*
+	 * Set extended CQ field in MREGS of RQ (or all RQs)
+	 * for given vNIC
+	 * in: (u64) a0 = RQ selection (VNIC_RQ_ALL for all RQs)
+	 *     (u32) a1 = CQ entry size
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_16 --> 16 bytes
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_32 --> 32 bytes
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_64 --> 64 bytes
+	 *
+	 * Capability query:
+	 * out: (u32) a0 = errno, 0:valid cmd
+	 *      (u32) a1 = value consisting of supported entries
+	 *         bit 0: 16 bytes
+	 *         bit 1: 32 bytes
+	 *         bit 2: 64 bytes
+	 */
+	CMD_CQ_ENTRY_SIZE_SET = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 90),
+
 };
 
 /* CMD_ENABLE2 flags */
diff --git a/drivers/net/ethernet/cisco/enic/vnic_enet.h b/drivers/net/ethernet/cisco/enic/vnic_enet.h
index 5acc236069de..9e8e86262a3f 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_enet.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_enet.h
@@ -21,6 +21,11 @@ struct vnic_enet_config {
 	u16 loop_tag;
 	u16 vf_rq_count;
 	u16 num_arfs;
+	u8 reserved[66];
+	u32 max_rq_ring;	// MAX RQ ring size
+	u32 max_wq_ring;	// MAX WQ ring size
+	u32 max_cq_ring;	// MAX CQ ring size
+	u32 rdma_rsvd_lkey;	// Reserved (privileged) LKey
 };
 
 #define VENETF_TSO		0x1	/* TSO enabled */
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.h b/drivers/net/ethernet/cisco/enic/vnic_rq.h
index 0bc595abc03b..a1cdd729caec 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.h
@@ -50,7 +50,7 @@ struct vnic_rq_ctrl {
 	(VNIC_RQ_BUF_BLK_ENTRIES(entries) * sizeof(struct vnic_rq_buf))
 #define VNIC_RQ_BUF_BLKS_NEEDED(entries) \
 	DIV_ROUND_UP(entries, VNIC_RQ_BUF_BLK_ENTRIES(entries))
-#define VNIC_RQ_BUF_BLKS_MAX VNIC_RQ_BUF_BLKS_NEEDED(4096)
+#define VNIC_RQ_BUF_BLKS_MAX VNIC_RQ_BUF_BLKS_NEEDED(16384)
 
 struct vnic_rq_buf {
 	struct vnic_rq_buf *next;
@@ -61,6 +61,8 @@ struct vnic_rq_buf {
 	unsigned int index;
 	void *desc;
 	uint64_t wr_id;
+	unsigned int offset;
+	unsigned int truesize;
 };
 
 enum enic_poll_state {
diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.h b/drivers/net/ethernet/cisco/enic/vnic_wq.h
index 75c526911074..3bb4758100ba 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_wq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_wq.h
@@ -62,7 +62,7 @@ struct vnic_wq_buf {
 	(VNIC_WQ_BUF_BLK_ENTRIES(entries) * sizeof(struct vnic_wq_buf))
 #define VNIC_WQ_BUF_BLKS_NEEDED(entries) \
 	DIV_ROUND_UP(entries, VNIC_WQ_BUF_BLK_ENTRIES(entries))
-#define VNIC_WQ_BUF_BLKS_MAX VNIC_WQ_BUF_BLKS_NEEDED(4096)
+#define VNIC_WQ_BUF_BLKS_MAX VNIC_WQ_BUF_BLKS_NEEDED(16384)
 
 struct vnic_wq {
 	unsigned int index;
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 991e3839858b..6a2004bbe87f 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -40,6 +40,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <net/gro.h>
 
 #include "gemini.h"
 
@@ -1143,6 +1144,7 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	struct gmac_txdesc *txd;
 	skb_frag_t *skb_frag;
 	dma_addr_t mapping;
+	bool tcp = false;
 	void *buffer;
 	u16 mss;
 	int ret;
@@ -1150,6 +1152,13 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	word1 = skb->len;
 	word3 = SOF_BIT;
 
+	/* Determine if we are doing TCP */
+	if (skb->protocol == htons(ETH_P_IP))
+		tcp = (ip_hdr(skb)->protocol == IPPROTO_TCP);
+	else
+		/* IPv6 */
+		tcp = (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP);
+
 	mss = skb_shinfo(skb)->gso_size;
 	if (mss) {
 		/* This means we are dealing with TCP and skb->len is the
@@ -1162,8 +1171,26 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 			   mss, skb->len);
 		word1 |= TSS_MTU_ENABLE_BIT;
 		word3 |= mss;
+	} else if (tcp) {
+		/* Even if we are not using TSO, use the hardware offloader
+		 * for transferring the TCP frame: this hardware has partial
+		 * TCP awareness (called TOE - TCP Offload Engine) and will
+		 * according to the datasheet put packets belonging to the
+		 * same TCP connection in the same queue for the TOE/TSO
+		 * engine to process. The engine will deal with chopping
+		 * up frames that exceed ETH_DATA_LEN which the
+		 * checksumming engine cannot handle (see below) into
+		 * manageable chunks. It flawlessly deals with quite big
+		 * frames and frames containing custom DSA EtherTypes.
+		 */
+		mss = netdev->mtu + skb_tcp_all_headers(skb);
+		mss = min(mss, skb->len);
+		netdev_dbg(netdev, "TOE/TSO len %04x mtu %04x mss %04x\n",
+			   skb->len, netdev->mtu, mss);
+		word1 |= TSS_MTU_ENABLE_BIT;
+		word3 |= mss;
 	} else if (skb->len >= ETH_FRAME_LEN) {
-		/* Hardware offloaded checksumming isn't working on frames
+		/* Hardware offloaded checksumming isn't working on non-TCP frames
 		 * bigger than 1514 bytes. A hypothesis about this is that the
 		 * checksum buffer is only 1518 bytes, so when the frames get
 		 * bigger they get truncated, or the last few bytes get
@@ -1180,21 +1207,16 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	}
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		int tcp = 0;
-
 		/* We do not switch off the checksumming on non TCP/UDP
 		 * frames: as is shown from tests, the checksumming engine
 		 * is smart enough to see that a frame is not actually TCP
 		 * or UDP and then just pass it through without any changes
 		 * to the frame.
 		 */
-		if (skb->protocol == htons(ETH_P_IP)) {
+		if (skb->protocol == htons(ETH_P_IP))
 			word1 |= TSS_IP_CHKSUM_BIT;
-			tcp = ip_hdr(skb)->protocol == IPPROTO_TCP;
-		} else { /* IPv6 */
+		else
 			word1 |= TSS_IPV6_ENABLE_BIT;
-			tcp = ipv6_hdr(skb)->nexthdr == IPPROTO_TCP;
-		}
 
 		word1 |= tcp ? TSS_TCP_CHKSUM_BIT : TSS_UDP_CHKSUM_BIT;
 	}
@@ -1833,9 +1855,8 @@ static int gmac_open(struct net_device *netdev)
 	gmac_enable_tx_rx(netdev);
 	netif_tx_start_all_queues(netdev);
 
-	hrtimer_init(&port->rx_coalesce_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	port->rx_coalesce_timer.function = &gmac_coalesce_delay_expired;
+	hrtimer_setup(&port->rx_coalesce_timer, &gmac_coalesce_delay_expired, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	netdev_dbg(netdev, "opened\n");
 
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 8735e333034c..b87eaf0c250c 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1777,10 +1777,11 @@ static void dm9000_drv_remove(struct platform_device *pdev)
 
 	unregister_netdev(ndev);
 	dm9000_release_board(pdev, dm);
-	free_netdev(ndev);		/* free device structure */
 	if (dm->power_supply)
 		regulator_disable(dm->power_supply);
 
+	free_netdev(ndev);		/* free device structure */
+
 	dev_dbg(&pdev->dev, "released and freed device\n");
 }
 
diff --git a/drivers/net/ethernet/dec/tulip/21142.c b/drivers/net/ethernet/dec/tulip/21142.c
index 369858272650..76767dec216d 100644
--- a/drivers/net/ethernet/dec/tulip/21142.c
+++ b/drivers/net/ethernet/dec/tulip/21142.c
@@ -216,7 +216,7 @@ void t21142_lnk_change(struct net_device *dev, int csr5)
 		    (csr12 & 2) == 2) ||
 		   (tp->nway && (csr5 & (TPLnkFail)))) {
 		/* Link blew? Maybe restart NWay. */
-		del_timer_sync(&tp->timer);
+		timer_delete_sync(&tp->timer);
 		t21142_start_nway(dev);
 		tp->timer.expires = RUN_AT(3*HZ);
 		add_timer(&tp->timer);
@@ -226,7 +226,7 @@ void t21142_lnk_change(struct net_device *dev, int csr5)
 				 medianame[dev->if_port],
 				 (csr12 & 2) ? "failed" : "good");
 		if ((csr12 & 2)  &&  ! tp->medialock) {
-			del_timer_sync(&tp->timer);
+			timer_delete_sync(&tp->timer);
 			t21142_start_nway(dev);
 			tp->timer.expires = RUN_AT(3*HZ);
 			add_timer(&tp->timer);
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index 0a161a4db242..f9504f340c4a 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -963,7 +963,7 @@ static void de_next_media (struct de_private *de, const u32 *media,
 
 static void de21040_media_timer (struct timer_list *t)
 {
-	struct de_private *de = from_timer(de, t, media_timer);
+	struct de_private *de = timer_container_of(de, t, media_timer);
 	struct net_device *dev = de->dev;
 	u32 status = dr32(SIAStatus);
 	unsigned int carrier;
@@ -1044,7 +1044,7 @@ static unsigned int de_ok_to_advertise (struct de_private *de, u32 new_media)
 
 static void de21041_media_timer (struct timer_list *t)
 {
-	struct de_private *de = from_timer(de, t, media_timer);
+	struct de_private *de = timer_container_of(de, t, media_timer);
 	struct net_device *dev = de->dev;
 	u32 status = dr32(SIAStatus);
 	unsigned int carrier;
@@ -1428,7 +1428,7 @@ static int de_close (struct net_device *dev)
 
 	netif_dbg(de, ifdown, dev, "disabling interface\n");
 
-	del_timer_sync(&de->media_timer);
+	timer_delete_sync(&de->media_timer);
 
 	spin_lock_irqsave(&de->lock, flags);
 	de_stop_hw(de);
@@ -1452,7 +1452,7 @@ static void de_tx_timeout (struct net_device *dev, unsigned int txqueue)
 		   dr32(MacStatus), dr32(MacMode), dr32(SIAStatus),
 		   de->rx_tail, de->tx_head, de->tx_tail);
 
-	del_timer_sync(&de->media_timer);
+	timer_delete_sync(&de->media_timer);
 
 	disable_irq(irq);
 	spin_lock_irq(&de->lock);
@@ -2126,7 +2126,7 @@ static int __maybe_unused de_suspend(struct device *dev_d)
 	if (netif_running (dev)) {
 		const int irq = pdev->irq;
 
-		del_timer_sync(&de->media_timer);
+		timer_delete_sync(&de->media_timer);
 
 		disable_irq(irq);
 		spin_lock_irq(&de->lock);
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 3188ba7b450f..2d3bd343b6e6 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -745,7 +745,7 @@ static int dmfe_stop(struct net_device *dev)
 	netif_stop_queue(dev);
 
 	/* deleted timer */
-	del_timer_sync(&db->timer);
+	timer_delete_sync(&db->timer);
 
 	/* Reset & stop DM910X board */
 	dw32(DCR0, DM910X_RESET);
@@ -1115,7 +1115,7 @@ static const struct ethtool_ops netdev_ethtool_ops = {
 
 static void dmfe_timer(struct timer_list *t)
 {
-	struct dmfe_board_info *db = from_timer(db, t, timer);
+	struct dmfe_board_info *db = timer_container_of(db, t, timer);
 	struct net_device *dev = pci_get_drvdata(db->pdev);
 	void __iomem *ioaddr = db->ioaddr;
 	u32 tmp_cr8;
diff --git a/drivers/net/ethernet/dec/tulip/interrupt.c b/drivers/net/ethernet/dec/tulip/interrupt.c
index 54560f9a1651..0a12cb9b3ba7 100644
--- a/drivers/net/ethernet/dec/tulip/interrupt.c
+++ b/drivers/net/ethernet/dec/tulip/interrupt.c
@@ -104,7 +104,7 @@ int tulip_refill_rx(struct net_device *dev)
 
 void oom_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, oom_timer);
+	struct tulip_private *tp = timer_container_of(tp, t, oom_timer);
 
 	napi_schedule(&tp->napi);
 }
@@ -699,8 +699,8 @@ irqreturn_t tulip_interrupt(int irq, void *dev_instance)
 				tulip_start_rxtx(tp);
 			}
 			/*
-			 * NB: t21142_lnk_change() does a del_timer_sync(), so be careful if this
-			 * call is ever done under the spinlock
+			 * NB: t21142_lnk_change() does a timer_delete_sync(), so be careful
+			 * if this call is ever done under the spinlock
 			 */
 			if (csr5 & (TPLnkPass | TPLnkFail | 0x08000000)) {
 				if (tp->link_change)
diff --git a/drivers/net/ethernet/dec/tulip/pnic.c b/drivers/net/ethernet/dec/tulip/pnic.c
index 653bde48ef44..1de5ed967070 100644
--- a/drivers/net/ethernet/dec/tulip/pnic.c
+++ b/drivers/net/ethernet/dec/tulip/pnic.c
@@ -86,7 +86,7 @@ void pnic_lnk_change(struct net_device *dev, int csr5)
 
 void pnic_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
diff --git a/drivers/net/ethernet/dec/tulip/pnic2.c b/drivers/net/ethernet/dec/tulip/pnic2.c
index 72a09156b48b..39c410bf224e 100644
--- a/drivers/net/ethernet/dec/tulip/pnic2.c
+++ b/drivers/net/ethernet/dec/tulip/pnic2.c
@@ -78,7 +78,7 @@
 
 void pnic2_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
@@ -323,7 +323,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5)
 		if (tulip_debug > 2)
 			netdev_dbg(dev, "Ugh! Link blew?\n");
 
-		del_timer_sync(&tp->timer);
+		timer_delete_sync(&tp->timer);
 		pnic2_start_nway(dev);
 		tp->timer.expires = RUN_AT(3*HZ);
 		add_timer(&tp->timer);
@@ -348,7 +348,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5)
 
                 /* if failed then try doing an nway to get in sync */
 		if ((csr12 & 2)  &&  ! tp->medialock) {
-			del_timer_sync(&tp->timer);
+			timer_delete_sync(&tp->timer);
 			pnic2_start_nway(dev);
 			tp->timer.expires = RUN_AT(3*HZ);
 			add_timer(&tp->timer);
@@ -372,7 +372,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5)
 
                 /* if failed, try doing an nway to get in sync */
 		if ((csr12 & 4)  &&  ! tp->medialock) {
-			del_timer_sync(&tp->timer);
+			timer_delete_sync(&tp->timer);
 			pnic2_start_nway(dev);
 			tp->timer.expires = RUN_AT(3*HZ);
 			add_timer(&tp->timer);
diff --git a/drivers/net/ethernet/dec/tulip/timer.c b/drivers/net/ethernet/dec/tulip/timer.c
index 642e9dfc5451..ca0c509b601c 100644
--- a/drivers/net/ethernet/dec/tulip/timer.c
+++ b/drivers/net/ethernet/dec/tulip/timer.c
@@ -139,7 +139,7 @@ void tulip_media_task(struct work_struct *work)
 
 void mxic_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
@@ -156,7 +156,7 @@ void mxic_timer(struct timer_list *t)
 
 void comet_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 	int next_tick = 2*HZ;
 
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 27e01d780cd0..5b7e6eb080f3 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -114,7 +114,7 @@ int tulip_debug = 1;
 
 static void tulip_timer(struct timer_list *t)
 {
-	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct tulip_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 
 	if (netif_running(dev))
@@ -747,9 +747,9 @@ static void tulip_down (struct net_device *dev)
 	napi_disable(&tp->napi);
 #endif
 
-	del_timer_sync (&tp->timer);
+	timer_delete_sync(&tp->timer);
 #ifdef CONFIG_TULIP_NAPI
-	del_timer_sync (&tp->oom_timer);
+	timer_delete_sync(&tp->oom_timer);
 #endif
 	spin_lock_irqsave (&tp->lock, flags);
 
@@ -1177,7 +1177,6 @@ static void set_rx_mode(struct net_device *dev)
 	iowrite32(csr6, ioaddr + CSR6);
 }
 
-#ifdef CONFIG_TULIP_MWI
 static void tulip_mwi_config(struct pci_dev *pdev, struct net_device *dev)
 {
 	struct tulip_private *tp = netdev_priv(dev);
@@ -1251,7 +1250,6 @@ out:
 		netdev_dbg(dev, "MWI config cacheline=%d, csr0=%08x\n",
 			   cache, csr0);
 }
-#endif
 
 /*
  *	Chips that have the MRM/reserved bit quirk and the burst quirk. That
@@ -1413,7 +1411,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* grab all resources from both PIO and MMIO regions, as we
 	 * don't want anyone else messing around with our hardware */
-	if (pci_request_regions(pdev, DRV_NAME))
+	if (pcim_request_all_regions(pdev, DRV_NAME))
 		return -ENODEV;
 
 	ioaddr = pcim_iomap(pdev, TULIP_BAR, tulip_tbl[chip_idx].io_size);
@@ -1463,10 +1461,9 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&tp->media_work, tulip_tbl[tp->chip_id].media_task);
 
-#ifdef CONFIG_TULIP_MWI
-	if (!force_csr0 && (tp->flags & HAS_PCI_MWI))
+	if (IS_ENABLED(CONFIG_TULIP_MWI) && !force_csr0 &&
+	    (tp->flags & HAS_PCI_MWI))
 		tulip_mwi_config (pdev, dev);
-#endif
 
 	/* Stop the chip's Tx and Rx processes. */
 	tulip_stop_rxtx(tp);
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index ff080ab0f116..6e4d8d31aba9 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -656,7 +656,7 @@ static int uli526x_stop(struct net_device *dev)
 	netif_stop_queue(dev);
 
 	/* deleted timer */
-	del_timer_sync(&db->timer);
+	timer_delete_sync(&db->timer);
 
 	/* Reset & stop ULI526X board */
 	uw32(DCR0, ULI526X_RESET);
@@ -1014,7 +1014,7 @@ static const struct ethtool_ops netdev_ethtool_ops = {
 
 static void uli526x_timer(struct timer_list *t)
 {
-	struct uli526x_board_info *db = from_timer(db, t, timer);
+	struct uli526x_board_info *db = timer_container_of(db, t, timer);
 	struct net_device *dev = pci_get_drvdata(db->pdev);
 	struct uli_phy_ops *phy = &db->phy;
 	void __iomem *ioaddr = db->ioaddr;
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 37fba39c0056..a24a25a5f73d 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -375,7 +375,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENOMEM;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
-	if (pci_request_regions(pdev, DRV_NAME))
+	if (pcim_request_all_regions(pdev, DRV_NAME))
 		goto err_out_netdev;
 
 	ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size);
@@ -763,7 +763,7 @@ static inline void update_csr6(struct net_device *dev, int new)
 
 static void netdev_timer(struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, timer);
+	struct netdev_private *np = timer_container_of(np, t, timer);
 	struct net_device *dev = pci_get_drvdata(np->pci_dev);
 	void __iomem *ioaddr = np->base_addr;
 
@@ -1509,7 +1509,7 @@ static int netdev_close(struct net_device *dev)
 	}
 #endif /* __i386__ debugging only */
 
-	del_timer_sync(&np->timer);
+	timer_delete_sync(&np->timer);
 
 	free_rxtx_rings(np);
 	free_ringdesc(np);
@@ -1560,7 +1560,7 @@ static int __maybe_unused w840_suspend(struct device *dev_d)
 
 	rtnl_lock();
 	if (netif_running (dev)) {
-		del_timer_sync(&np->timer);
+		timer_delete_sync(&np->timer);
 
 		spin_lock_irq(&np->lock);
 		netif_device_detach(dev);
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index d0ea92607870..da9b7715df05 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -146,6 +146,8 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 	np->ioaddr = ioaddr;
 	np->chip_id = chip_idx;
 	np->pdev = pdev;
+
+	spin_lock_init(&np->stats_lock);
 	spin_lock_init (&np->tx_lock);
 	spin_lock_init (&np->rx_lock);
 
@@ -352,7 +354,7 @@ parse_eeprom (struct net_device *dev)
 	eth_hw_addr_set(dev, psrom->mac_addr);
 
 	if (np->chip_id == CHIP_IP1000A) {
-		np->led_mode = psrom->led_mode;
+		np->led_mode = le16_to_cpu(psrom->led_mode);
 		return 0;
 	}
 
@@ -648,7 +650,7 @@ static int rio_open(struct net_device *dev)
 static void
 rio_timer (struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, timer);
+	struct netdev_private *np = timer_container_of(np, t, timer);
 	struct net_device *dev = pci_get_drvdata(np->pdev);
 	unsigned int entry;
 	int next_tick = 1*HZ;
@@ -865,7 +867,6 @@ tx_error (struct net_device *dev, int tx_status)
 	frame_id = (tx_status & 0xffff0000);
 	printk (KERN_ERR "%s: Transmit error, TxStatus %4.4x, FrameId %d.\n",
 		dev->name, tx_status, frame_id);
-	dev->stats.tx_errors++;
 	/* Ttransmit Underrun */
 	if (tx_status & 0x10) {
 		dev->stats.tx_fifo_errors++;
@@ -902,9 +903,15 @@ tx_error (struct net_device *dev, int tx_status)
 		rio_set_led_mode(dev);
 		/* Let TxStartThresh stay default value */
 	}
+
+	spin_lock(&np->stats_lock);
 	/* Maximum Collisions */
 	if (tx_status & 0x08)
 		dev->stats.collisions++;
+
+	dev->stats.tx_errors++;
+	spin_unlock(&np->stats_lock);
+
 	/* Restart the Tx */
 	dw32(MACCtrl, dr16(MACCtrl) | TxEnable);
 }
@@ -1073,7 +1080,9 @@ get_stats (struct net_device *dev)
 	int i;
 #endif
 	unsigned int stat_reg;
+	unsigned long flags;
 
+	spin_lock_irqsave(&np->stats_lock, flags);
 	/* All statistics registers need to be acknowledged,
 	   else statistic overflow could cause problems */
 
@@ -1123,6 +1132,9 @@ get_stats (struct net_device *dev)
 	dr16(TCPCheckSumErrors);
 	dr16(UDPCheckSumErrors);
 	dr16(IPCheckSumErrors);
+
+	spin_unlock_irqrestore(&np->stats_lock, flags);
+
 	return &dev->stats;
 }
 
@@ -1778,7 +1790,7 @@ rio_close (struct net_device *dev)
 	rio_hw_stop(dev);
 
 	free_irq(pdev->irq, dev);
-	del_timer_sync (&np->timer);
+	timer_delete_sync(&np->timer);
 
 	free_list(dev);
 
@@ -1818,7 +1830,7 @@ static int rio_suspend(struct device *device)
 		return 0;
 
 	netif_device_detach(dev);
-	del_timer_sync(&np->timer);
+	timer_delete_sync(&np->timer);
 	rio_hw_stop(dev);
 
 	return 0;
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 195dc6cfd895..ba679025e866 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -329,18 +329,18 @@ enum _pcs_anlpar {
 };
 
 typedef struct t_SROM {
-	u16 config_param;	/* 0x00 */
-	u16 asic_ctrl;		/* 0x02 */
-	u16 sub_vendor_id;	/* 0x04 */
-	u16 sub_system_id;	/* 0x06 */
-	u16 pci_base_1;		/* 0x08 (IP1000A only) */
-	u16 pci_base_2;		/* 0x0a (IP1000A only) */
-	u16 led_mode;		/* 0x0c (IP1000A only) */
-	u16 reserved1[9];	/* 0x0e-0x1f */
+	__le16 config_param;	/* 0x00 */
+	__le16 asic_ctrl;	/* 0x02 */
+	__le16 sub_vendor_id;	/* 0x04 */
+	__le16 sub_system_id;	/* 0x06 */
+	__le16 pci_base_1;	/* 0x08 (IP1000A only) */
+	__le16 pci_base_2;	/* 0x0a (IP1000A only) */
+	__le16 led_mode;	/* 0x0c (IP1000A only) */
+	__le16 reserved1[9];	/* 0x0e-0x1f */
 	u8 mac_addr[6];		/* 0x20-0x25 */
 	u8 reserved2[10];	/* 0x26-0x2f */
 	u8 sib[204];		/* 0x30-0xfb */
-	u32 crc;		/* 0xfc-0xff */
+	__le32 crc;		/* 0xfc-0xff */
 } SROM_t, *PSROM_t;
 
 /* Ioctl custom data */
@@ -372,6 +372,8 @@ struct netdev_private {
 	struct pci_dev *pdev;
 	void __iomem *ioaddr;
 	void __iomem *eeprom_addr;
+	// To ensure synchronization when stats are updated.
+	spinlock_t stats_lock;
 	spinlock_t tx_lock;
 	spinlock_t rx_lock;
 	unsigned int rx_buf_sz;		/* Based on MTU+slack. */
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index 44af1d13d931..67275aa4f65b 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -416,8 +416,7 @@ static int ec_bhf_open(struct net_device *net_dev)
 
 	netif_start_queue(net_dev);
 
-	hrtimer_init(&priv->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	priv->hrtimer.function = ec_bhf_timer_fun;
+	hrtimer_setup(&priv->hrtimer, ec_bhf_timer_fun, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_start(&priv->hrtimer, polling_frequency, HRTIMER_MODE_REL);
 
 	return 0;
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index e48b861e4ce1..270ff9aab335 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -562,7 +562,7 @@ struct be_adapter {
 	struct be_dma_mem mbox_mem_alloced;
 
 	struct be_mcc_obj mcc_obj;
-	struct mutex mcc_lock;	/* For serializing mcc cmds to BE card */
+	spinlock_t mcc_lock;	/* For serializing mcc cmds to BE card */
 	spinlock_t mcc_cq_lock;
 
 	u16 cfg_num_rx_irqs;		/* configured via set-channels */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 61adcebeef01..d730af4a50c7 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -575,7 +575,7 @@ int be_process_mcc(struct be_adapter *adapter)
 /* Wait till no more pending mcc requests are present */
 static int be_mcc_wait_compl(struct be_adapter *adapter)
 {
-#define mcc_timeout		12000 /* 12s timeout */
+#define mcc_timeout		120000 /* 12s timeout */
 	int i, status = 0;
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
@@ -589,7 +589,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 
 		if (atomic_read(&mcc_obj->q.used) == 0)
 			break;
-		usleep_range(500, 1000);
+		udelay(100);
 	}
 	if (i == mcc_timeout) {
 		dev_err(&adapter->pdev->dev, "FW not responding\n");
@@ -866,7 +866,7 @@ static bool use_mcc(struct be_adapter *adapter)
 static int be_cmd_lock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter)) {
-		mutex_lock(&adapter->mcc_lock);
+		spin_lock_bh(&adapter->mcc_lock);
 		return 0;
 	} else {
 		return mutex_lock_interruptible(&adapter->mbox_lock);
@@ -877,7 +877,7 @@ static int be_cmd_lock(struct be_adapter *adapter)
 static void be_cmd_unlock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter))
-		return mutex_unlock(&adapter->mcc_lock);
+		return spin_unlock_bh(&adapter->mcc_lock);
 	else
 		return mutex_unlock(&adapter->mbox_lock);
 }
@@ -1047,7 +1047,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	struct be_cmd_req_mac_query *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1076,7 +1076,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1088,7 +1088,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	struct be_cmd_req_pmac_add *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1113,7 +1113,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
@@ -1131,7 +1131,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	if (pmac_id == -1)
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1151,7 +1151,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1414,7 +1414,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	struct be_dma_mem *q_mem = &rxq->dma_mem;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1444,7 +1444,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1508,7 +1508,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	struct be_cmd_req_q_destroy *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1525,7 +1525,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	q->created = false;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1593,7 +1593,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	struct be_cmd_req_hdr *hdr;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1609,7 +1609,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	/* version 1 of the cmd is not supported only by BE2 */
 	if (BE2_chip(adapter))
 		hdr->version = 0;
-	if (BE3_chip(adapter) || lancer_chip(adapter))
+	else if (BE3_chip(adapter) || lancer_chip(adapter))
 		hdr->version = 1;
 	else
 		hdr->version = 2;
@@ -1621,7 +1621,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1637,7 +1637,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 			    CMD_SUBSYSTEM_ETH))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1660,7 +1660,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1697,7 +1697,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	struct be_cmd_req_link_status *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	if (link_status)
 		*link_status = LINK_DOWN;
@@ -1736,7 +1736,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1747,7 +1747,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 	struct be_cmd_req_get_cntl_addnl_attribs *req;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1762,7 +1762,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1811,7 +1811,7 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 	if (!get_fat_cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	while (total_size) {
 		buf_size = min(total_size, (u32)60 * 1024);
@@ -1849,9 +1849,9 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
 			  get_fat_cmd.va, get_fat_cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1862,7 +1862,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 	struct be_cmd_req_get_fw_version *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1885,7 +1885,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 			sizeof(adapter->fw_on_flash));
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1899,7 +1899,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 	struct be_cmd_req_modify_eq_delay *req;
 	int status = 0, i;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1922,7 +1922,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1949,7 +1949,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 	struct be_cmd_req_vlan_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1971,7 +1971,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1982,7 +1982,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 	struct be_cmd_req_rx_filter *req = mem->va;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2015,7 +2015,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2046,7 +2046,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2066,7 +2066,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_FEATURE_NOT_SUPPORTED)
 		return  -EOPNOTSUPP;
@@ -2085,7 +2085,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2108,7 +2108,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2189,7 +2189,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 	if (!(be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2214,7 +2214,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2226,7 +2226,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	struct be_cmd_req_enable_disable_beacon *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2247,7 +2247,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2258,7 +2258,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	struct be_cmd_req_get_beacon_state *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2282,7 +2282,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2306,7 +2306,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2328,7 +2328,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		memcpy(data, resp->page_data + off, len);
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
@@ -2345,7 +2345,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	void *ctxt = NULL;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2387,7 +2387,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(60000)))
@@ -2406,7 +2406,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2460,7 +2460,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2478,7 +2478,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2491,7 +2491,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	struct lancer_cmd_resp_read_object *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2525,7 +2525,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	}
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2537,7 +2537,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	struct be_cmd_write_flashrom *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2562,7 +2562,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(40000)))
@@ -2573,7 +2573,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2584,7 +2584,7 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2611,11 +2611,15 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 		memcpy(flashed_crc, req->crc, 4);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
-static char flash_cookie[2][16] = {"*** SE FLAS", "H DIRECTORY *** "};
+/*
+ * Since the cookie is text, add a parsing-skipped space to keep it from
+ * ever being matched on storage holding this source file.
+ */
+static const char flash_cookie[32] __nonstring = "*** SE FLAS" "H DIRECTORY *** ";
 
 static bool phy_flashing_required(struct be_adapter *adapter)
 {
@@ -3217,7 +3221,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	struct be_cmd_req_acpi_wol_magic_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3234,7 +3238,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3249,7 +3253,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3272,7 +3276,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(SET_LB_MODE_TIMEOUT)))
@@ -3281,7 +3285,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3298,7 +3302,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3324,7 +3328,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 	if (status)
 		goto err;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	wait_for_completion(&adapter->et_cmd_compl);
 	resp = embedded_payload(wrb);
@@ -3332,7 +3336,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 
 	return status;
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3348,7 +3352,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3382,7 +3386,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3393,7 +3397,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	struct be_cmd_req_seeprom_read *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3409,7 +3413,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3424,7 +3428,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3469,7 +3473,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 	}
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3479,7 +3483,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	struct be_cmd_req_set_qos *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3499,7 +3503,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3611,7 +3615,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	struct be_cmd_req_get_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3643,7 +3647,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3655,7 +3659,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 	struct be_cmd_req_set_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3675,7 +3679,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3707,7 +3711,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3771,7 +3775,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 	}
 
 out:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
 			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
@@ -3831,7 +3835,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	if (!cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3853,7 +3857,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 err:
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3889,7 +3893,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3930,7 +3934,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3944,7 +3948,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	int status;
 	u16 vid;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3991,7 +3995,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4190,7 +4194,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 	struct be_cmd_req_set_ext_fat_caps *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4206,7 +4210,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4684,7 +4688,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 	if (iface == 0xFFFFFFFF)
 		return -1;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4701,7 +4705,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4735,7 +4739,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	struct be_cmd_resp_get_iface_list *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4756,7 +4760,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4850,7 +4854,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	if (BEx_chip(adapter))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4868,7 +4872,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	req->enable = 1;
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4941,7 +4945,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 	u32 link_config = 0;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4969,7 +4973,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5000,8 +5004,7 @@ int be_cmd_set_features(struct be_adapter *adapter)
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	if (mutex_lock_interruptible(&adapter->mcc_lock))
-		return -1;
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5039,7 +5042,7 @@ err:
 		dev_info(&adapter->pdev->dev,
 			 "Adapter does not support HW error recovery\n");
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5053,7 +5056,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	struct be_cmd_resp_hdr *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5076,7 +5079,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	memcpy(wrb_payload, resp, sizeof(*resp) + resp->response_length);
 	be_dws_le_to_cpu(wrb_payload, sizeof(*resp) + resp->response_length);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 EXPORT_SYMBOL(be_roce_mcc_cmd);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index d70818f06be7..5e2d3ddb5d43 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1415,7 +1415,7 @@ struct flash_section_entry {
 } __packed;
 
 struct flash_section_info {
-	u8 cookie[32];
+	u8 cookie[32] __nonstring;
 	struct flash_section_hdr fsec_hdr;
 	struct flash_section_entry fsec_entry[32];
 } __packed;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 875fe379eea2..3d2e21592119 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5667,8 +5667,8 @@ static int be_drv_init(struct be_adapter *adapter)
 	}
 
 	mutex_init(&adapter->mbox_lock);
-	mutex_init(&adapter->mcc_lock);
 	mutex_init(&adapter->rx_filter_lock);
+	spin_lock_init(&adapter->mcc_lock);
 	spin_lock_init(&adapter->mcc_cq_lock);
 	init_completion(&adapter->et_cmd_compl);
 
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 95a5295d0361..eba73246f986 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -67,6 +67,8 @@
 #define TSNEP_TX_TYPE_XDP_NDO_MAP_PAGE	(TSNEP_TX_TYPE_XDP_NDO | TSNEP_TX_TYPE_MAP_PAGE)
 #define TSNEP_TX_TYPE_XDP		(TSNEP_TX_TYPE_XDP_TX | TSNEP_TX_TYPE_XDP_NDO)
 #define TSNEP_TX_TYPE_XSK		BIT(12)
+#define TSNEP_TX_TYPE_TSTAMP		BIT(13)
+#define TSNEP_TX_TYPE_SKB_TSTAMP	(TSNEP_TX_TYPE_SKB | TSNEP_TX_TYPE_TSTAMP)
 
 #define TSNEP_XDP_TX		BIT(0)
 #define TSNEP_XDP_REDIRECT	BIT(1)
@@ -221,20 +223,19 @@ static void tsnep_phy_link_status_change(struct net_device *netdev)
 
 static int tsnep_phy_loopback(struct tsnep_adapter *adapter, bool enable)
 {
-	int retval;
-
-	retval = phy_loopback(adapter->phydev, enable);
+	int speed;
 
-	/* PHY link state change is not signaled if loopback is enabled, it
-	 * would delay a working loopback anyway, let's ensure that loopback
-	 * is working immediately by setting link mode directly
-	 */
-	if (!retval && enable) {
-		netif_carrier_on(adapter->netdev);
-		tsnep_set_link_mode(adapter);
+	if (enable) {
+		if (adapter->phydev->autoneg == AUTONEG_DISABLE &&
+		    adapter->phydev->speed == SPEED_100)
+			speed = SPEED_100;
+		else
+			speed = SPEED_1000;
+	} else {
+		speed = 0;
 	}
 
-	return retval;
+	return phy_loopback(adapter->phydev, enable, speed);
 }
 
 static int tsnep_phy_open(struct tsnep_adapter *adapter)
@@ -387,8 +388,7 @@ static void tsnep_tx_activate(struct tsnep_tx *tx, int index, int length,
 	if (entry->skb) {
 		entry->properties = length & TSNEP_DESC_LENGTH_MASK;
 		entry->properties |= TSNEP_DESC_INTERRUPT_FLAG;
-		if ((entry->type & TSNEP_TX_TYPE_SKB) &&
-		    (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS))
+		if ((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP)
 			entry->properties |= TSNEP_DESC_EXTENDED_WRITEBACK_FLAG;
 
 		/* toggle user flag to prevent false acknowledge
@@ -480,7 +480,8 @@ static int tsnep_tx_map_frag(skb_frag_t *frag, struct tsnep_tx_entry *entry,
 	return mapped;
 }
 
-static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
+static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count,
+			bool do_tstamp)
 {
 	struct device *dmadev = tx->adapter->dmadev;
 	struct tsnep_tx_entry *entry;
@@ -506,6 +507,9 @@ static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
 				entry->type = TSNEP_TX_TYPE_SKB_INLINE;
 				mapped = 0;
 			}
+
+			if (do_tstamp)
+				entry->type |= TSNEP_TX_TYPE_TSTAMP;
 		} else {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
@@ -559,11 +563,12 @@ static int tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count)
 static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 					 struct tsnep_tx *tx)
 {
-	int count = 1;
 	struct tsnep_tx_entry *entry;
+	bool do_tstamp = false;
+	int count = 1;
 	int length;
-	int i;
 	int retval;
+	int i;
 
 	if (skb_shinfo(skb)->nr_frags > 0)
 		count += skb_shinfo(skb)->nr_frags;
@@ -580,7 +585,13 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 	entry = &tx->entry[tx->write];
 	entry->skb = skb;
 
-	retval = tsnep_tx_map(skb, tx, count);
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    tx->adapter->hwtstamp_config.tx_type == HWTSTAMP_TX_ON) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		do_tstamp = true;
+	}
+
+	retval = tsnep_tx_map(skb, tx, count, do_tstamp);
 	if (retval < 0) {
 		tsnep_tx_unmap(tx, tx->write, count);
 		dev_kfree_skb_any(entry->skb);
@@ -592,9 +603,6 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 	}
 	length = retval;
 
-	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)
-		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-
 	for (i = 0; i < count; i++)
 		tsnep_tx_activate(tx, (tx->write + i) & TSNEP_RING_MASK, length,
 				  i == count - 1);
@@ -845,15 +853,14 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
 
 		length = tsnep_tx_unmap(tx, tx->read, count);
 
-		if ((entry->type & TSNEP_TX_TYPE_SKB) &&
-		    (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) &&
+		if (((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP) &&
 		    (__le32_to_cpu(entry->desc_wb->properties) &
 		     TSNEP_DESC_EXTENDED_WRITEBACK_FLAG)) {
 			struct skb_shared_hwtstamps hwtstamps;
 			u64 timestamp;
 
-			if (skb_shinfo(entry->skb)->tx_flags &
-			    SKBTX_HW_TSTAMP_USE_CYCLES)
+			if (entry->skb->sk &&
+			    READ_ONCE(entry->skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC)
 				timestamp =
 					__le64_to_cpu(entry->desc_wb->counter);
 			else
@@ -1966,23 +1973,41 @@ failed:
 
 static void tsnep_queue_enable(struct tsnep_queue *queue)
 {
+	struct tsnep_adapter *adapter = queue->adapter;
+
+	netif_napi_set_irq(&queue->napi, queue->irq);
 	napi_enable(&queue->napi);
-	tsnep_enable_irq(queue->adapter, queue->irq_mask);
+	tsnep_enable_irq(adapter, queue->irq_mask);
 
-	if (queue->tx)
+	if (queue->tx) {
+		netif_queue_set_napi(adapter->netdev, queue->tx->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, &queue->napi);
 		tsnep_tx_enable(queue->tx);
+	}
 
-	if (queue->rx)
+	if (queue->rx) {
+		netif_queue_set_napi(adapter->netdev, queue->rx->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, &queue->napi);
 		tsnep_rx_enable(queue->rx);
+	}
 }
 
 static void tsnep_queue_disable(struct tsnep_queue *queue)
 {
-	if (queue->tx)
+	struct tsnep_adapter *adapter = queue->adapter;
+
+	if (queue->rx)
+		netif_queue_set_napi(adapter->netdev, queue->rx->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, NULL);
+
+	if (queue->tx) {
 		tsnep_tx_disable(queue->tx, &queue->napi);
+		netif_queue_set_napi(adapter->netdev, queue->tx->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, NULL);
+	}
 
 	napi_disable(&queue->napi);
-	tsnep_disable_irq(queue->adapter, queue->irq_mask);
+	tsnep_disable_irq(adapter, queue->irq_mask);
 
 	/* disable RX after NAPI polling has been disabled, because RX can be
 	 * enabled during NAPI polling
diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig
index c699bd6bcbb9..474073c7f94d 100644
--- a/drivers/net/ethernet/faraday/Kconfig
+++ b/drivers/net/ethernet/faraday/Kconfig
@@ -31,6 +31,7 @@ config FTGMAC100
 	depends on ARM || COMPILE_TEST
 	depends on !64BIT || BROKEN
 	select PHYLIB
+	select FIXED_PHY
 	select MDIO_ASPEED if MACH_ASPEED_G6
 	select CRC32
 	help
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 17ec35e75a65..a98d5af3f9e3 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1906,7 +1906,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 			goto err_phy_connect;
 		}
 
-		phydev = fixed_phy_register(PHY_POLL, &ncsi_phy_status, np);
+		phydev = fixed_phy_register(&ncsi_phy_status, np);
 		if (IS_ERR(phydev)) {
 			dev_err(&pdev->dev, "failed to register fixed PHY device\n");
 			err = PTR_ERR(phydev);
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index ed18450fd2cc..6ac8547ef9b8 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -1074,7 +1074,7 @@ static void allocate_rx_buffers(struct net_device *dev)
 
 static void netdev_timer(struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, timer);
+	struct netdev_private *np = timer_container_of(np, t, timer);
 	struct net_device *dev = np->mii.dev;
 	void __iomem *ioaddr = np->mem;
 	int old_crvalue = np->crvalue;
@@ -1163,7 +1163,7 @@ static void enable_rxtx(struct net_device *dev)
 
 static void reset_timer(struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, reset_timer);
+	struct netdev_private *np = timer_container_of(np, t, reset_timer);
 	struct net_device *dev = np->mii.dev;
 	unsigned long flags;
 
@@ -1900,8 +1900,8 @@ static int netdev_close(struct net_device *dev)
 	/* Stop the chip's Tx and Rx processes. */
 	stop_nic_rxtx(ioaddr, 0);
 
-	del_timer_sync(&np->timer);
-	del_timer_sync(&np->reset_timer);
+	timer_delete_sync(&np->timer);
+	timer_delete_sync(&np->reset_timer);
 
 	free_irq(np->pci_dev->irq, dev);
 
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index 75401d2a5fb4..bbef47c3480c 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -71,7 +71,6 @@ config FSL_XGMAC_MDIO
 	tristate "Freescale XGMAC MDIO"
 	select PHYLIB
 	depends on OF
-	select MDIO_DEVRES
 	select OF_MDIO
 	help
 	  This driver supports the MDIO bus on the Fman 10G Ethernet MACs, and
@@ -81,8 +80,7 @@ config UCC_GETH
 	tristate "Freescale QE Gigabit Ethernet"
 	depends on QUICC_ENGINE && PPC32
 	select FSL_PQ_MDIO
-	select PHYLIB
-	select FIXED_PHY
+	select PHYLINK
 	help
 	  This driver supports the Gigabit Ethernet mode of the QUICC Engine,
 	  which is available on some Freescale SOCs.
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index bf5baef5c3e0..23c23cca2620 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2281,7 +2281,7 @@ static int dpaa_a050385_wa_xdpf(struct dpaa_priv *priv,
 	new_xdpf->len = xdpf->len;
 	new_xdpf->headroom = priv->tx_headroom;
 	new_xdpf->frame_sz = DPAA_BP_RAW_SIZE;
-	new_xdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+	new_xdpf->mem_type = MEM_TYPE_PAGE_ORDER0;
 
 	/* Release the initial buffer */
 	xdp_return_frame_rx_napi(xdpf);
@@ -3089,15 +3089,25 @@ static int dpaa_xdp_xmit(struct net_device *net_dev, int n,
 	return nxmit;
 }
 
-static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int dpaa_hwtstamp_get(struct net_device *dev,
+			     struct kernel_hwtstamp_config *config)
 {
 	struct dpaa_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config config;
 
-	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
-		return -EFAULT;
+	config->tx_type = priv->tx_tstamp ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config->rx_filter = priv->rx_tstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
-	switch (config.tx_type) {
+	return 0;
+}
+
+static int dpaa_hwtstamp_set(struct net_device *dev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct dpaa_priv *priv = netdev_priv(dev);
+
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		/* Couldn't disable rx/tx timestamping separately.
 		 * Do nothing here.
@@ -3112,7 +3122,7 @@ static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		return -ERANGE;
 	}
 
-	if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
 		/* Couldn't disable rx/tx timestamping separately.
 		 * Do nothing here.
 		 */
@@ -3121,28 +3131,17 @@ static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
 		priv->rx_tstamp = true;
 		/* TS is set for all frame types, not only those requested */
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
-	return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
-			-EFAULT : 0;
+	return 0;
 }
 
 static int dpaa_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd)
 {
-	int ret = -EINVAL;
 	struct dpaa_priv *priv = netdev_priv(net_dev);
 
-	if (cmd == SIOCGMIIREG) {
-		if (net_dev->phydev)
-			return phylink_mii_ioctl(priv->mac_dev->phylink, rq,
-						 cmd);
-	}
-
-	if (cmd == SIOCSHWTSTAMP)
-		return dpaa_ts_ioctl(net_dev, rq, cmd);
-
-	return ret;
+	return phylink_mii_ioctl(priv->mac_dev->phylink, rq, cmd);
 }
 
 static const struct net_device_ops dpaa_ops = {
@@ -3160,6 +3159,8 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_change_mtu = dpaa_change_mtu,
 	.ndo_bpf = dpaa_xdp,
 	.ndo_xdp_xmit = dpaa_xdp_xmit,
+	.ndo_hwtstamp_get = dpaa_hwtstamp_get,
+	.ndo_hwtstamp_set = dpaa_hwtstamp_set,
 };
 
 static int dpaa_napi_add(struct net_device *net_dev)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 29886a8ba73f..b82f121cadad 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2585,40 +2585,52 @@ static int dpaa2_eth_set_features(struct net_device *net_dev,
 	return 0;
 }
 
-static int dpaa2_eth_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int dpaa2_eth_hwtstamp_set(struct net_device *dev,
+				  struct kernel_hwtstamp_config *config,
+				  struct netlink_ext_ack *extack)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config config;
 
 	if (!dpaa2_ptp)
 		return -EINVAL;
 
-	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 	case HWTSTAMP_TX_ON:
 	case HWTSTAMP_TX_ONESTEP_SYNC:
-		priv->tx_tstamp_type = config.tx_type;
+		priv->tx_tstamp_type = config->tx_type;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
 		priv->rx_tstamp = false;
 	} else {
 		priv->rx_tstamp = true;
 		/* TS is set for all frame types, not only those requested */
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
 	if (priv->tx_tstamp_type == HWTSTAMP_TX_ONESTEP_SYNC)
 		dpaa2_ptp_onestep_reg_update_method(priv);
 
-	return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
-			-EFAULT : 0;
+	return 0;
+}
+
+static int dpaa2_eth_hwtstamp_get(struct net_device *dev,
+				  struct kernel_hwtstamp_config *config)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+
+	if (!dpaa2_ptp)
+		return -EINVAL;
+
+	config->tx_type = priv->tx_tstamp_type;
+	config->rx_filter = priv->rx_tstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
+
+	return 0;
 }
 
 static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
@@ -2626,9 +2638,6 @@ static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	struct dpaa2_eth_priv *priv = netdev_priv(dev);
 	int err;
 
-	if (cmd == SIOCSHWTSTAMP)
-		return dpaa2_eth_ts_ioctl(dev, rq, cmd);
-
 	mutex_lock(&priv->mac_lock);
 
 	if (dpaa2_eth_is_type_phy(priv)) {
@@ -3034,7 +3043,9 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_xsk_wakeup = dpaa2_xsk_wakeup,
 	.ndo_setup_tc = dpaa2_eth_setup_tc,
 	.ndo_vlan_rx_add_vid = dpaa2_eth_rx_add_vid,
-	.ndo_vlan_rx_kill_vid = dpaa2_eth_rx_kill_vid
+	.ndo_vlan_rx_kill_vid = dpaa2_eth_rx_kill_vid,
+	.ndo_hwtstamp_get = dpaa2_eth_hwtstamp_get,
+	.ndo_hwtstamp_set = dpaa2_eth_hwtstamp_set,
 };
 
 static void dpaa2_eth_cdan_cb(struct dpaa2_io_notification_ctx *ctx)
@@ -3928,6 +3939,7 @@ static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv,
 					 MEM_TYPE_PAGE_ORDER0, NULL);
 	if (err) {
 		dev_err(dev, "xdp_rxq_info_reg_mem_model failed\n");
+		xdp_rxq_info_unreg(&fq->channel->xdp_rxq);
 		return err;
 	}
 
@@ -4421,17 +4433,25 @@ static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv)
 			return -EINVAL;
 		}
 		if (err)
-			return err;
+			goto out;
 	}
 
 	err = dpni_get_qdid(priv->mc_io, 0, priv->mc_token,
 			    DPNI_QUEUE_TX, &priv->tx_qdid);
 	if (err) {
 		dev_err(dev, "dpni_get_qdid() failed\n");
-		return err;
+		goto out;
 	}
 
 	return 0;
+
+out:
+	while (i--) {
+		if (priv->fq[i].type == DPAA2_RX_FQ &&
+		    xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq))
+			xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq);
+	}
+	return err;
 }
 
 /* Allocate rings for storing incoming frame descriptors */
@@ -4814,6 +4834,17 @@ static void dpaa2_eth_del_ch_napi(struct dpaa2_eth_priv *priv)
 	}
 }
 
+static void dpaa2_eth_free_rx_xdp_rxq(struct dpaa2_eth_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_fqs; i++) {
+		if (priv->fq[i].type == DPAA2_RX_FQ &&
+		    xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq))
+			xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq);
+	}
+}
+
 static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 {
 	struct device *dev;
@@ -5017,6 +5048,7 @@ err_alloc_percpu_extras:
 	free_percpu(priv->percpu_stats);
 err_alloc_percpu_stats:
 	dpaa2_eth_del_ch_napi(priv);
+	dpaa2_eth_free_rx_xdp_rxq(priv);
 err_bind:
 	dpaa2_eth_free_dpbps(priv);
 err_dpbp_setup:
@@ -5069,6 +5101,7 @@ static void dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 	free_percpu(priv->percpu_extras);
 
 	dpaa2_eth_del_ch_napi(priv);
+	dpaa2_eth_free_rx_xdp_rxq(priv);
 	dpaa2_eth_free_dpbps(priv);
 	dpaa2_eth_free_dpio(priv);
 	dpaa2_eth_free_dpni(priv);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index a293b08f36d4..147a93bf9fa9 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -780,13 +780,14 @@ struct ethsw_dump_ctx {
 static int dpaa2_switch_fdb_dump_nl(struct fdb_dump_entry *entry,
 				    struct ethsw_dump_ctx *dump)
 {
+	struct ndo_fdb_dump_context *ctx = (void *)dump->cb->ctx;
 	int is_dynamic = entry->type & DPSW_FDB_ENTRY_DINAMIC;
 	u32 portid = NETLINK_CB(dump->cb->skb).portid;
 	u32 seq = dump->cb->nlh->nlmsg_seq;
 	struct nlmsghdr *nlh;
 	struct ndmsg *ndm;
 
-	if (dump->idx < dump->cb->args[2])
+	if (dump->idx < ctx->fdb_idx)
 		goto skip;
 
 	nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH,
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
index 6c2779047dcd..54b0f0a5a6bb 100644
--- a/drivers/net/ethernet/freescale/enetc/Kconfig
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config FSL_ENETC_CORE
 	tristate
+	select NXP_NETC_LIB if NXP_NTMP
 	help
 	  This module supports common functionality between the PF and VF
 	  drivers for the NXP ENETC controller.
@@ -15,10 +16,19 @@ config NXP_ENETC_PF_COMMON
 
 	  If compiled as module (M), the module name is nxp-enetc-pf-common.
 
+config NXP_NETC_LIB
+	tristate
+	help
+	  This module provides common functionalities for both ENETC and NETC
+	  Switch, such as NETC Table Management Protocol (NTMP) 2.0, common tc
+	  flower and debugfs interfaces and so on.
+
+config NXP_NTMP
+	bool
+
 config FSL_ENETC
 	tristate "ENETC PF driver"
 	depends on PCI_MSI
-	select MDIO_DEVRES
 	select FSL_ENETC_CORE
 	select FSL_ENETC_IERB
 	select FSL_ENETC_MDIO
@@ -36,10 +46,10 @@ config FSL_ENETC
 config NXP_ENETC4
 	tristate "ENETC4 PF driver"
 	depends on PCI_MSI
-	select MDIO_DEVRES
 	select FSL_ENETC_CORE
 	select FSL_ENETC_MDIO
 	select NXP_ENETC_PF_COMMON
+	select NXP_NTMP
 	select PHYLINK
 	select DIMLIB
 	help
@@ -73,7 +83,7 @@ config FSL_ENETC_IERB
 
 config FSL_ENETC_MDIO
 	tristate "ENETC MDIO driver"
-	depends on PCI && MDIO_DEVRES && MDIO_BUS
+	depends on PCI && PHYLIB
 	help
 	  This driver supports NXP ENETC Central MDIO controller as a PCIe
 	  physical function (PF) device.
diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile
index 6fd27ee4fcd1..f1c5ad45fd76 100644
--- a/drivers/net/ethernet/freescale/enetc/Makefile
+++ b/drivers/net/ethernet/freescale/enetc/Makefile
@@ -6,6 +6,9 @@ fsl-enetc-core-y := enetc.o enetc_cbdr.o enetc_ethtool.o
 obj-$(CONFIG_NXP_ENETC_PF_COMMON) += nxp-enetc-pf-common.o
 nxp-enetc-pf-common-y := enetc_pf_common.o
 
+obj-$(CONFIG_NXP_NETC_LIB) += nxp-netc-lib.o
+nxp-netc-lib-y := ntmp.o
+
 obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o
 fsl-enetc-y := enetc_pf.o
 fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o
@@ -13,6 +16,7 @@ fsl-enetc-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o
 
 obj-$(CONFIG_NXP_ENETC4) += nxp-enetc4.o
 nxp-enetc4-y := enetc4_pf.o
+nxp-enetc4-$(CONFIG_DEBUG_FS) += enetc4_debugfs.o
 
 obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o
 fsl-enetc-vf-y := enetc_vf.o
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 35634c516e26..dcc3fbac3481 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -29,10 +29,49 @@ EXPORT_SYMBOL_GPL(enetc_port_mac_wr);
 static void enetc_change_preemptible_tcs(struct enetc_ndev_priv *priv,
 					 u8 preemptible_tcs)
 {
+	if (!(priv->si->hw_features & ENETC_SI_F_QBU))
+		return;
+
 	priv->preemptible_tcs = preemptible_tcs;
 	enetc_mm_commit_preemptible_tcs(priv);
 }
 
+static int enetc_mac_addr_hash_idx(const u8 *addr)
+{
+	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
+	u64 mask = 0;
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		mask |= BIT_ULL(i * 6);
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
+
+	return res;
+}
+
+void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+				  const unsigned char *addr)
+{
+	int idx = enetc_mac_addr_hash_idx(addr);
+
+	/* add hash table entry */
+	__set_bit(idx, filter->mac_hash_table);
+	filter->mac_addr_cnt++;
+}
+EXPORT_SYMBOL_GPL(enetc_add_mac_addr_ht_filter);
+
+void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
+{
+	filter->mac_addr_cnt = 0;
+
+	bitmap_zero(filter->mac_hash_table,
+		    ENETC_MADDR_HASH_TBL_SZ);
+}
+EXPORT_SYMBOL_GPL(enetc_reset_mac_addr_filter);
+
 static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv)
 {
 	int num_tx_rings = priv->num_tx_rings;
@@ -143,6 +182,45 @@ static int enetc_ptp_parse(struct sk_buff *skb, u8 *udp,
 	return 0;
 }
 
+static bool enetc_tx_csum_offload_check(struct sk_buff *skb)
+{
+	switch (skb->csum_offset) {
+	case offsetof(struct tcphdr, check):
+	case offsetof(struct udphdr, check):
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool enetc_skb_is_ipv6(struct sk_buff *skb)
+{
+	return vlan_get_protocol(skb) == htons(ETH_P_IPV6);
+}
+
+static bool enetc_skb_is_tcp(struct sk_buff *skb)
+{
+	return skb->csum_offset == offsetof(struct tcphdr, check);
+}
+
+/**
+ * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame
+ * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located
+ * @count: Number of Tx buffer descriptors which need to be unmapped
+ * @i: Index of the last successfully mapped Tx buffer descriptor
+ */
+static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i)
+{
+	while (count--) {
+		struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i];
+
+		enetc_free_tx_frame(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	}
+}
+
 static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 {
 	bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false;
@@ -160,6 +238,29 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 	dma_addr_t dma;
 	u8 flags = 0;
 
+	enetc_clear_tx_bd(&temp_bd);
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		/* Can not support TSD and checksum offload at the same time */
+		if (priv->active_offloads & ENETC_F_TXCSUM &&
+		    enetc_tx_csum_offload_check(skb) && !tx_ring->tsd_enable) {
+			temp_bd.l3_aux0 = FIELD_PREP(ENETC_TX_BD_L3_START,
+						     skb_network_offset(skb));
+			temp_bd.l3_aux1 = FIELD_PREP(ENETC_TX_BD_L3_HDR_LEN,
+						     skb_network_header_len(skb) / 4);
+			temp_bd.l3_aux1 |= FIELD_PREP(ENETC_TX_BD_L3T,
+						      enetc_skb_is_ipv6(skb));
+			if (enetc_skb_is_tcp(skb))
+				temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T,
+							    ENETC_TXBD_L4T_TCP);
+			else
+				temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T,
+							    ENETC_TXBD_L4T_UDP);
+			flags |= ENETC_TXBD_FLAGS_CSUM_LSO | ENETC_TXBD_FLAGS_L4CS;
+		} else if (skb_checksum_help(skb)) {
+			return 0;
+		}
+	}
+
 	i = tx_ring->next_to_use;
 	txbd = ENETC_TXBD(*tx_ring, i);
 	prefetchw(txbd);
@@ -170,7 +271,6 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 
 	temp_bd.addr = cpu_to_le64(dma);
 	temp_bd.buf_len = cpu_to_le16(len);
-	temp_bd.lstatus = 0;
 
 	tx_swbd = &tx_ring->tx_swbd[i];
 	tx_swbd->dma = dma;
@@ -233,9 +333,11 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 		}
 
 		if (do_onestep_tstamp) {
-			u32 lo, hi, val;
-			u64 sec, nsec;
+			__be32 new_sec_l, new_nsec;
+			u32 lo, hi, nsec, val;
+			__be16 new_sec_h;
 			u8 *data;
+			u64 sec;
 
 			lo = enetc_rd_hot(hw, ENETC_SICTR0);
 			hi = enetc_rd_hot(hw, ENETC_SICTR1);
@@ -249,13 +351,38 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 			/* Update originTimestamp field of Sync packet
 			 * - 48 bits seconds field
 			 * - 32 bits nanseconds field
+			 *
+			 * In addition, the UDP checksum needs to be updated
+			 * by software after updating originTimestamp field,
+			 * otherwise the hardware will calculate the wrong
+			 * checksum when updating the correction field and
+			 * update it to the packet.
 			 */
 			data = skb_mac_header(skb);
-			*(__be16 *)(data + offset2) =
-				htons((sec >> 32) & 0xffff);
-			*(__be32 *)(data + offset2 + 2) =
-				htonl(sec & 0xffffffff);
-			*(__be32 *)(data + offset2 + 6) = htonl(nsec);
+			new_sec_h = htons((sec >> 32) & 0xffff);
+			new_sec_l = htonl(sec & 0xffffffff);
+			new_nsec = htonl(nsec);
+			if (udp) {
+				struct udphdr *uh = udp_hdr(skb);
+				__be32 old_sec_l, old_nsec;
+				__be16 old_sec_h;
+
+				old_sec_h = *(__be16 *)(data + offset2);
+				inet_proto_csum_replace2(&uh->check, skb, old_sec_h,
+							 new_sec_h, false);
+
+				old_sec_l = *(__be32 *)(data + offset2 + 2);
+				inet_proto_csum_replace4(&uh->check, skb, old_sec_l,
+							 new_sec_l, false);
+
+				old_nsec = *(__be32 *)(data + offset2 + 6);
+				inet_proto_csum_replace4(&uh->check, skb, old_nsec,
+							 new_nsec, false);
+			}
+
+			*(__be16 *)(data + offset2) = new_sec_h;
+			*(__be32 *)(data + offset2 + 2) = new_sec_l;
+			*(__be32 *)(data + offset2 + 6) = new_nsec;
 
 			/* Configure single-step register */
 			val = ENETC_PM0_SINGLE_STEP_EN;
@@ -326,25 +453,20 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 dma_err:
 	dev_err(tx_ring->dev, "DMA map error");
 
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }
 
-static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
-				 struct enetc_tx_swbd *tx_swbd,
-				 union enetc_tx_bd *txbd, int *i, int hdr_len,
-				 int data_len)
+static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+				struct enetc_tx_swbd *tx_swbd,
+				union enetc_tx_bd *txbd, int *i, int hdr_len,
+				int data_len)
 {
 	union enetc_tx_bd txbd_tmp;
 	u8 flags = 0, e_flags = 0;
 	dma_addr_t addr;
+	int count = 1;
 
 	enetc_clear_tx_bd(&txbd_tmp);
 	addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE;
@@ -387,7 +509,10 @@ static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
 		/* Write the BD */
 		txbd_tmp.ext.e_flags = e_flags;
 		*txbd = txbd_tmp;
+		count++;
 	}
+
+	return count;
 }
 
 static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb,
@@ -486,8 +611,233 @@ static void enetc_tso_complete_csum(struct enetc_bdr *tx_ring, struct tso_t *tso
 	}
 }
 
+static int enetc_lso_count_descs(const struct sk_buff *skb)
+{
+	/* 4 BDs: 1 BD for LSO header + 1 BD for extended BD + 1 BD
+	 * for linear area data but not include LSO header, namely
+	 * skb_headlen(skb) - lso_hdr_len (it may be 0, but that's
+	 * okay, we only need to consider the worst case). And 1 BD
+	 * for gap.
+	 */
+	return skb_shinfo(skb)->nr_frags + 4;
+}
+
+static int enetc_lso_get_hdr_len(const struct sk_buff *skb)
+{
+	int hdr_len, tlen;
+
+	tlen = skb_is_gso_tcp(skb) ? tcp_hdrlen(skb) : sizeof(struct udphdr);
+	hdr_len = skb_transport_offset(skb) + tlen;
+
+	return hdr_len;
+}
+
+static void enetc_lso_start(struct sk_buff *skb, struct enetc_lso_t *lso)
+{
+	lso->lso_seg_size = skb_shinfo(skb)->gso_size;
+	lso->ipv6 = enetc_skb_is_ipv6(skb);
+	lso->tcp = skb_is_gso_tcp(skb);
+	lso->l3_hdr_len = skb_network_header_len(skb);
+	lso->l3_start = skb_network_offset(skb);
+	lso->hdr_len = enetc_lso_get_hdr_len(skb);
+	lso->total_len = skb->len - lso->hdr_len;
+}
+
+static void enetc_lso_map_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+			      int *i, struct enetc_lso_t *lso)
+{
+	union enetc_tx_bd txbd_tmp, *txbd;
+	struct enetc_tx_swbd *tx_swbd;
+	u16 frm_len, frm_len_ext;
+	u8 flags, e_flags = 0;
+	dma_addr_t addr;
+	char *hdr;
+
+	/* Get the first BD of the LSO BDs chain */
+	txbd = ENETC_TXBD(*tx_ring, *i);
+	tx_swbd = &tx_ring->tx_swbd[*i];
+	prefetchw(txbd);
+
+	/* Prepare LSO header: MAC + IP + TCP/UDP */
+	hdr = tx_ring->tso_headers + *i * TSO_HEADER_SIZE;
+	memcpy(hdr, skb->data, lso->hdr_len);
+	addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE;
+
+	/* {frm_len_ext, frm_len} indicates the total length of
+	 * large transmit data unit. frm_len contains the 16 least
+	 * significant bits and frm_len_ext contains the 4 most
+	 * significant bits.
+	 */
+	frm_len = lso->total_len & 0xffff;
+	frm_len_ext = (lso->total_len >> 16) & 0xf;
+
+	/* Set the flags of the first BD */
+	flags = ENETC_TXBD_FLAGS_EX | ENETC_TXBD_FLAGS_CSUM_LSO |
+		ENETC_TXBD_FLAGS_LSO | ENETC_TXBD_FLAGS_L4CS;
+
+	enetc_clear_tx_bd(&txbd_tmp);
+	txbd_tmp.addr = cpu_to_le64(addr);
+	txbd_tmp.hdr_len = cpu_to_le16(lso->hdr_len);
+
+	/* first BD needs frm_len and offload flags set */
+	txbd_tmp.frm_len = cpu_to_le16(frm_len);
+	txbd_tmp.flags = flags;
+
+	txbd_tmp.l3_aux0 = FIELD_PREP(ENETC_TX_BD_L3_START, lso->l3_start);
+	/* l3_hdr_size in 32-bits (4 bytes) */
+	txbd_tmp.l3_aux1 = FIELD_PREP(ENETC_TX_BD_L3_HDR_LEN,
+				      lso->l3_hdr_len / 4);
+	if (lso->ipv6)
+		txbd_tmp.l3_aux1 |= ENETC_TX_BD_L3T;
+	else
+		txbd_tmp.l3_aux0 |= ENETC_TX_BD_IPCS;
+
+	txbd_tmp.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T, lso->tcp ?
+				     ENETC_TXBD_L4T_TCP : ENETC_TXBD_L4T_UDP);
+
+	/* For the LSO header we do not set the dma address since
+	 * we do not want it unmapped when we do cleanup. We still
+	 * set len so that we count the bytes sent.
+	 */
+	tx_swbd->len = lso->hdr_len;
+	tx_swbd->do_twostep_tstamp = false;
+	tx_swbd->check_wb = false;
+
+	/* Actually write the header in the BD */
+	*txbd = txbd_tmp;
+
+	/* Get the next BD, and the next BD is extended BD */
+	enetc_bdr_idx_inc(tx_ring, i);
+	txbd = ENETC_TXBD(*tx_ring, *i);
+	tx_swbd = &tx_ring->tx_swbd[*i];
+	prefetchw(txbd);
+
+	enetc_clear_tx_bd(&txbd_tmp);
+	if (skb_vlan_tag_present(skb)) {
+		/* Setup the VLAN fields */
+		txbd_tmp.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb));
+		txbd_tmp.ext.tpid = ENETC_TPID_8021Q;
+		e_flags = ENETC_TXBD_E_FLAGS_VLAN_INS;
+	}
+
+	/* Write the BD */
+	txbd_tmp.ext.e_flags = e_flags;
+	txbd_tmp.ext.lso_sg_size = cpu_to_le16(lso->lso_seg_size);
+	txbd_tmp.ext.frm_len_ext = cpu_to_le16(frm_len_ext);
+	*txbd = txbd_tmp;
+}
+
+static int enetc_lso_map_data(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+			      int *i, struct enetc_lso_t *lso, int *count)
+{
+	union enetc_tx_bd txbd_tmp, *txbd = NULL;
+	struct enetc_tx_swbd *tx_swbd;
+	skb_frag_t *frag;
+	dma_addr_t dma;
+	u8 flags = 0;
+	int len, f;
+
+	len = skb_headlen(skb) - lso->hdr_len;
+	if (len > 0) {
+		dma = dma_map_single(tx_ring->dev, skb->data + lso->hdr_len,
+				     len, DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_ring->dev, dma))
+			return -ENOMEM;
+
+		enetc_bdr_idx_inc(tx_ring, i);
+		txbd = ENETC_TXBD(*tx_ring, *i);
+		tx_swbd = &tx_ring->tx_swbd[*i];
+		prefetchw(txbd);
+		*count += 1;
+
+		enetc_clear_tx_bd(&txbd_tmp);
+		txbd_tmp.addr = cpu_to_le64(dma);
+		txbd_tmp.buf_len = cpu_to_le16(len);
+
+		tx_swbd->dma = dma;
+		tx_swbd->len = len;
+		tx_swbd->is_dma_page = 0;
+		tx_swbd->dir = DMA_TO_DEVICE;
+	}
+
+	frag = &skb_shinfo(skb)->frags[0];
+	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++, frag++) {
+		if (txbd)
+			*txbd = txbd_tmp;
+
+		len = skb_frag_size(frag);
+		dma = skb_frag_dma_map(tx_ring->dev, frag);
+		if (dma_mapping_error(tx_ring->dev, dma))
+			return -ENOMEM;
+
+		/* Get the next BD */
+		enetc_bdr_idx_inc(tx_ring, i);
+		txbd = ENETC_TXBD(*tx_ring, *i);
+		tx_swbd = &tx_ring->tx_swbd[*i];
+		prefetchw(txbd);
+		*count += 1;
+
+		enetc_clear_tx_bd(&txbd_tmp);
+		txbd_tmp.addr = cpu_to_le64(dma);
+		txbd_tmp.buf_len = cpu_to_le16(len);
+
+		tx_swbd->dma = dma;
+		tx_swbd->len = len;
+		tx_swbd->is_dma_page = 1;
+		tx_swbd->dir = DMA_TO_DEVICE;
+	}
+
+	/* Last BD needs 'F' bit set */
+	flags |= ENETC_TXBD_FLAGS_F;
+	txbd_tmp.flags = flags;
+	*txbd = txbd_tmp;
+
+	tx_swbd->is_eof = 1;
+	tx_swbd->skb = skb;
+
+	return 0;
+}
+
+static int enetc_lso_hw_offload(struct enetc_bdr *tx_ring, struct sk_buff *skb)
+{
+	struct enetc_tx_swbd *tx_swbd;
+	struct enetc_lso_t lso = {0};
+	int err, i, count = 0;
+
+	/* Initialize the LSO handler */
+	enetc_lso_start(skb, &lso);
+	i = tx_ring->next_to_use;
+
+	enetc_lso_map_hdr(tx_ring, skb, &i, &lso);
+	/* First BD and an extend BD */
+	count += 2;
+
+	err = enetc_lso_map_data(tx_ring, skb, &i, &lso, &count);
+	if (err)
+		goto dma_err;
+
+	/* Go to the next BD */
+	enetc_bdr_idx_inc(tx_ring, &i);
+	tx_ring->next_to_use = i;
+	enetc_update_tx_ring_tail(tx_ring);
+
+	return count;
+
+dma_err:
+	do {
+		tx_swbd = &tx_ring->tx_swbd[i];
+		enetc_free_tx_frame(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	} while (--count);
+
+	return 0;
+}
+
 static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 {
+	struct enetc_ndev_priv *priv = netdev_priv(tx_ring->ndev);
 	int hdr_len, total_len, data_len;
 	struct enetc_tx_swbd *tx_swbd;
 	union enetc_tx_bd *txbd;
@@ -519,9 +869,9 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 
 		/* compute the csum over the L4 header */
 		csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos);
-		enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len);
+		count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd,
+					      &i, hdr_len, data_len);
 		bd_data_num = 0;
-		count++;
 
 		while (data_len > 0) {
 			int size;
@@ -545,15 +895,20 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 			err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd,
 						    tso.data, size,
 						    size == data_len);
-			if (err)
+			if (err) {
+				if (i == 0)
+					i = tx_ring->bd_count;
+				i--;
+
 				goto err_map_data;
+			}
 
 			data_len -= size;
 			count++;
 			bd_data_num++;
 			tso_build_data(skb, &tso, size);
 
-			if (unlikely(bd_data_num >= ENETC_MAX_SKB_FRAGS && data_len))
+			if (unlikely(bd_data_num >= priv->max_frags && data_len))
 				goto err_chained_bd;
 		}
 
@@ -575,13 +930,7 @@ err_map_data:
 	dev_err(tx_ring->dev, "DMA map error");
 
 err_chained_bd:
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }
@@ -591,7 +940,7 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_bdr *tx_ring;
-	int count, err;
+	int count;
 
 	/* Queue one-step Sync packet if already locked */
 	if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) {
@@ -605,16 +954,28 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 	tx_ring = priv->tx_ring[skb->queue_mapping];
 
 	if (skb_is_gso(skb)) {
-		if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) {
-			netif_stop_subqueue(ndev, tx_ring->index);
-			return NETDEV_TX_BUSY;
-		}
+		/* LSO data unit lengths of up to 256KB are supported */
+		if (priv->active_offloads & ENETC_F_LSO &&
+		    (skb->len - enetc_lso_get_hdr_len(skb)) <=
+		    ENETC_LSO_MAX_DATA_LEN) {
+			if (enetc_bd_unused(tx_ring) < enetc_lso_count_descs(skb)) {
+				netif_stop_subqueue(ndev, tx_ring->index);
+				return NETDEV_TX_BUSY;
+			}
 
-		enetc_lock_mdio();
-		count = enetc_map_tx_tso_buffs(tx_ring, skb);
-		enetc_unlock_mdio();
+			count = enetc_lso_hw_offload(tx_ring, skb);
+		} else {
+			if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) {
+				netif_stop_subqueue(ndev, tx_ring->index);
+				return NETDEV_TX_BUSY;
+			}
+
+			enetc_lock_mdio();
+			count = enetc_map_tx_tso_buffs(tx_ring, skb);
+			enetc_unlock_mdio();
+		}
 	} else {
-		if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS))
+		if (unlikely(skb_shinfo(skb)->nr_frags > priv->max_frags))
 			if (unlikely(skb_linearize(skb)))
 				goto drop_packet_err;
 
@@ -624,11 +985,6 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 			return NETDEV_TX_BUSY;
 		}
 
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			err = skb_checksum_help(skb);
-			if (err)
-				goto drop_packet_err;
-		}
 		enetc_lock_mdio();
 		count = enetc_map_tx_buffs(tx_ring, skb);
 		enetc_unlock_mdio();
@@ -637,7 +993,7 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 	if (unlikely(!count))
 		goto drop_packet_err;
 
-	if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED)
+	if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED(priv->max_frags))
 		netif_stop_subqueue(ndev, tx_ring->index);
 
 	return NETDEV_TX_OK;
@@ -905,7 +1261,8 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
 	if (unlikely(tx_frm_cnt && netif_carrier_ok(ndev) &&
 		     __netif_subqueue_stopped(ndev, tx_ring->index) &&
 		     !test_bit(ENETC_TX_DOWN, &priv->flags) &&
-		     (enetc_bd_unused(tx_ring) >= ENETC_TXBDS_MAX_NEEDED))) {
+		     (enetc_bd_unused(tx_ring) >=
+		      ENETC_TXBDS_MAX_NEEDED(priv->max_frags)))) {
 		netif_wake_subqueue(ndev, tx_ring->index);
 	}
 
@@ -1529,6 +1886,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first,
 	}
 }
 
+static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first,
+				 int rx_ring_last)
+{
+	while (rx_ring_first != rx_ring_last) {
+		enetc_flip_rx_buff(rx_ring,
+				   &rx_ring->rx_swbd[rx_ring_first]);
+		enetc_bdr_idx_inc(rx_ring, &rx_ring_first);
+	}
+}
+
 static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				   struct napi_struct *napi, int work_limit,
 				   struct bpf_prog *prog)
@@ -1547,11 +1914,10 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 
 	while (likely(rx_frm_cnt < work_limit)) {
 		union enetc_rx_bd *rxbd, *orig_rxbd;
-		int orig_i, orig_cleaned_cnt;
 		struct xdp_buff xdp_buff;
 		struct sk_buff *skb;
+		int orig_i, err;
 		u32 bd_status;
-		int err;
 
 		rxbd = enetc_rxbd(rx_ring, i);
 		bd_status = le32_to_cpu(rxbd->r.lstatus);
@@ -1566,7 +1932,6 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			break;
 
 		orig_rxbd = rxbd;
-		orig_cleaned_cnt = cleaned_cnt;
 		orig_i = i;
 
 		enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i,
@@ -1594,15 +1959,21 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			rx_ring->stats.xdp_drops++;
 			break;
 		case XDP_PASS:
-			rxbd = orig_rxbd;
-			cleaned_cnt = orig_cleaned_cnt;
-			i = orig_i;
-
-			skb = enetc_build_skb(rx_ring, bd_status, &rxbd,
-					      &i, &cleaned_cnt,
-					      ENETC_RXB_DMA_SIZE_XDP);
-			if (unlikely(!skb))
+			skb = xdp_build_skb_from_buff(&xdp_buff);
+			/* Probably under memory pressure, stop NAPI */
+			if (unlikely(!skb)) {
+				enetc_xdp_drop(rx_ring, orig_i, i);
+				rx_ring->stats.xdp_drops++;
 				goto out;
+			}
+
+			enetc_get_offloads(rx_ring, orig_rxbd, skb);
+
+			/* These buffers are about to be owned by the stack.
+			 * Update our buffer cache (the rx_swbd array elements)
+			 * with their other page halves.
+			 */
+			enetc_bulk_flip_buff(rx_ring, orig_i, i);
 
 			napi_gro_receive(napi, skb);
 			break;
@@ -1622,7 +1993,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				tx_ring->stats.xdp_tx_drops++;
 			} else {
-				tx_ring->stats.xdp_tx += xdp_tx_bd_cnt;
+				tx_ring->stats.xdp_tx++;
 				rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt;
 				xdp_tx_frm_cnt++;
 				/* The XDP_TX enqueue was successful, so we
@@ -1644,11 +2015,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				rx_ring->stats.xdp_redirect_failures++;
 			} else {
-				while (orig_i != i) {
-					enetc_flip_rx_buff(rx_ring,
-							   &rx_ring->rx_swbd[orig_i]);
-					enetc_bdr_idx_inc(rx_ring, &orig_i);
-				}
+				enetc_bulk_flip_buff(rx_ring, orig_i, i);
 				xdp_redirect_frm_cnt++;
 				rx_ring->stats.xdp_redirect++;
 			}
@@ -1757,14 +2124,8 @@ void enetc_get_si_caps(struct enetc_si *si)
 		si->num_rss = ENETC_SIRSSCAPR_GET_NUM_RSS(rss);
 	}
 
-	if (val & ENETC_SIPCAPR0_QBV)
-		si->hw_features |= ENETC_SI_F_QBV;
-
-	if (val & ENETC_SIPCAPR0_QBU)
-		si->hw_features |= ENETC_SI_F_QBU;
-
-	if (val & ENETC_SIPCAPR0_PSFP)
-		si->hw_features |= ENETC_SI_F_PSFP;
+	if (val & ENETC_SIPCAPR0_LSO)
+		si->hw_features |= ENETC_SI_F_LSO;
 }
 EXPORT_SYMBOL_GPL(enetc_get_si_caps);
 
@@ -2054,13 +2415,35 @@ static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups)
 	for (i = 0; i < si->num_rss; i++)
 		rss_table[i] = i % num_groups;
 
-	enetc_set_rss_table(si, rss_table, si->num_rss);
+	si->ops->set_rss_table(si, rss_table, si->num_rss);
 
 	kfree(rss_table);
 
 	return 0;
 }
 
+static void enetc_set_lso_flags_mask(struct enetc_hw *hw)
+{
+	enetc_wr(hw, ENETC4_SILSOSFMR0,
+		 SILSOSFMR0_VAL_SET(ENETC4_TCP_NL_SEG_FLAGS_DMASK,
+				    ENETC4_TCP_NL_SEG_FLAGS_DMASK));
+	enetc_wr(hw, ENETC4_SILSOSFMR1, 0);
+}
+
+static void enetc_set_rss(struct net_device *ndev, int en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 reg;
+
+	enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings);
+
+	reg = enetc_rd(hw, ENETC_SIMR);
+	reg &= ~ENETC_SIMR_RSSE;
+	reg |= (en) ? ENETC_SIMR_RSSE : 0;
+	enetc_wr(hw, ENETC_SIMR, reg);
+}
+
 int enetc_configure_si(struct enetc_ndev_priv *priv)
 {
 	struct enetc_si *si = priv->si;
@@ -2074,13 +2457,16 @@ int enetc_configure_si(struct enetc_ndev_priv *priv)
 	/* enable SI */
 	enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN);
 
-	/* TODO: RSS support for i.MX95 will be supported later, and the
-	 * is_enetc_rev1() condition will be removed
-	 */
-	if (si->num_rss && is_enetc_rev1(si)) {
+	if (si->hw_features & ENETC_SI_F_LSO)
+		enetc_set_lso_flags_mask(hw);
+
+	if (si->num_rss) {
 		err = enetc_setup_default_rss_table(si, priv->num_rx_rings);
 		if (err)
 			return err;
+
+		if (priv->ndev->features & NETIF_F_RXHASH)
+			enetc_set_rss(priv->ndev, true);
 	}
 
 	return 0;
@@ -2873,22 +3259,6 @@ struct net_device_stats *enetc_get_stats(struct net_device *ndev)
 }
 EXPORT_SYMBOL_GPL(enetc_get_stats);
 
-static int enetc_set_rss(struct net_device *ndev, int en)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
-	u32 reg;
-
-	enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings);
-
-	reg = enetc_rd(hw, ENETC_SIMR);
-	reg &= ~ENETC_SIMR_RSSE;
-	reg |= (en) ? ENETC_SIMR_RSSE : 0;
-	enetc_wr(hw, ENETC_SIMR, reg);
-
-	return 0;
-}
-
 static void enetc_enable_rxvlan(struct net_device *ndev, bool en)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -2926,16 +3296,17 @@ void enetc_set_features(struct net_device *ndev, netdev_features_t features)
 }
 EXPORT_SYMBOL_GPL(enetc_set_features);
 
-static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
+int enetc_hwtstamp_set(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	int err, new_offloads = priv->active_offloads;
-	struct hwtstamp_config config;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	if (!IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK))
+		return -EOPNOTSUPP;
 
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		new_offloads &= ~ENETC_F_TX_TSTAMP_MASK;
 		break;
@@ -2944,6 +3315,9 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 		new_offloads |= ENETC_F_TX_TSTAMP;
 		break;
 	case HWTSTAMP_TX_ONESTEP_SYNC:
+		if (!enetc_si_is_pf(priv->si))
+			return -EOPNOTSUPP;
+
 		new_offloads &= ~ENETC_F_TX_TSTAMP_MASK;
 		new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP;
 		break;
@@ -2951,13 +3325,13 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		new_offloads &= ~ENETC_F_RX_TSTAMP;
 		break;
 	default:
 		new_offloads |= ENETC_F_RX_TSTAMP;
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
 	if ((new_offloads ^ priv->active_offloads) & ENETC_F_RX_TSTAMP) {
@@ -2970,42 +3344,36 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 
 	priv->active_offloads = new_offloads;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	       -EFAULT : 0;
+	return 0;
 }
+EXPORT_SYMBOL_GPL(enetc_hwtstamp_set);
 
-static int enetc_hwtstamp_get(struct net_device *ndev, struct ifreq *ifr)
+int enetc_hwtstamp_get(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct hwtstamp_config config;
 
-	config.flags = 0;
+	if (!IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK))
+		return -EOPNOTSUPP;
 
 	if (priv->active_offloads & ENETC_F_TX_ONESTEP_SYNC_TSTAMP)
-		config.tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
+		config->tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
 	else if (priv->active_offloads & ENETC_F_TX_TSTAMP)
-		config.tx_type = HWTSTAMP_TX_ON;
+		config->tx_type = HWTSTAMP_TX_ON;
 	else
-		config.tx_type = HWTSTAMP_TX_OFF;
+		config->tx_type = HWTSTAMP_TX_OFF;
 
-	config.rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ?
-			    HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+	config->rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ?
+			     HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	       -EFAULT : 0;
+	return 0;
 }
+EXPORT_SYMBOL_GPL(enetc_hwtstamp_get);
 
 int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 
-	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK)) {
-		if (cmd == SIOCSHWTSTAMP)
-			return enetc_hwtstamp_set(ndev, rq);
-		if (cmd == SIOCGHWTSTAMP)
-			return enetc_hwtstamp_get(ndev, rq);
-	}
-
 	if (!priv->phylink)
 		return -EOPNOTSUPP;
 
@@ -3033,7 +3401,8 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i,
 	bdr->buffer_offset = ENETC_RXB_PAD;
 	priv->rx_ring[i] = bdr;
 
-	err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0);
+	err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
+				 ENETC_RXB_DMA_SIZE_XDP);
 	if (err)
 		goto free_vector;
 
@@ -3275,17 +3644,21 @@ EXPORT_SYMBOL_GPL(enetc_pci_remove);
 static const struct enetc_drvdata enetc_pf_data = {
 	.sysclk_freq = ENETC_CLK_400M,
 	.pmac_offset = ENETC_PMAC_OFFSET,
+	.max_frags = ENETC_MAX_SKB_FRAGS,
 	.eth_ops = &enetc_pf_ethtool_ops,
 };
 
 static const struct enetc_drvdata enetc4_pf_data = {
 	.sysclk_freq = ENETC_CLK_333M,
+	.tx_csum = true,
+	.max_frags = ENETC4_MAX_SKB_FRAGS,
 	.pmac_offset = ENETC4_PMAC_OFFSET,
 	.eth_ops = &enetc4_pf_ethtool_ops,
 };
 
 static const struct enetc_drvdata enetc_vf_data = {
 	.sysclk_freq = ENETC_CLK_400M,
+	.max_frags = ENETC_MAX_SKB_FRAGS,
 	.eth_ops = &enetc_vf_ethtool_ops,
 };
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 72fa03dbc2dd..872d2cbd088b 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -8,6 +8,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/skbuff.h>
 #include <linux/ethtool.h>
+#include <linux/fsl/ntmp.h>
 #include <linux/if_vlan.h>
 #include <linux/phylink.h>
 #include <linux/dim.h>
@@ -22,6 +23,18 @@
 
 #define ENETC_CBD_DATA_MEM_ALIGN 64
 
+#define ENETC_MADDR_HASH_TBL_SZ	64
+
+enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
+
+struct enetc_mac_filter {
+	union {
+		char mac_addr[ETH_ALEN];
+		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
+	};
+	int mac_addr_cnt;
+};
+
 struct enetc_tx_swbd {
 	union {
 		struct sk_buff *skb;
@@ -41,6 +54,18 @@ struct enetc_tx_swbd {
 	u8 qbv_en:1;
 };
 
+struct enetc_lso_t {
+	bool	ipv6;
+	bool	tcp;
+	u8	l3_hdr_len;
+	u8	hdr_len; /* LSO header length */
+	u8	l3_start;
+	u16	lso_seg_size;
+	int	total_len; /* total data length, not include LSO header */
+};
+
+#define ENETC_LSO_MAX_DATA_LEN		SZ_256K
+
 #define ENETC_RX_MAXFRM_SIZE	ENETC_MAC_MAXFRM_SIZE
 #define ENETC_RXB_TRUESIZE	2048 /* PAGE_SIZE >> 1 */
 #define ENETC_RXB_PAD		NET_SKB_PAD /* add extra space if needed */
@@ -59,9 +84,16 @@ struct enetc_rx_swbd {
 
 /* ENETC overhead: optional extension BD + 1 BD gap */
 #define ENETC_TXBDS_NEEDED(val)	((val) + 2)
-/* max # of chained Tx BDs is 15, including head and extension BD */
+/* For LS1028A, max # of chained Tx BDs is 15, including head and
+ * extension BD.
+ */
 #define ENETC_MAX_SKB_FRAGS	13
-#define ENETC_TXBDS_MAX_NEEDED	ENETC_TXBDS_NEEDED(ENETC_MAX_SKB_FRAGS + 1)
+/* For ENETC v4 and later versions, max # of chained Tx BDs is 63,
+ * including head and extension BD, but the range of MAX_SKB_FRAGS
+ * is 17 ~ 45, so set ENETC4_MAX_SKB_FRAGS to MAX_SKB_FRAGS.
+ */
+#define ENETC4_MAX_SKB_FRAGS		MAX_SKB_FRAGS
+#define ENETC_TXBDS_MAX_NEEDED(x)	ENETC_TXBDS_NEEDED((x) + 1)
 
 struct enetc_ring_stats {
 	unsigned int packets;
@@ -231,9 +263,12 @@ enum enetc_errata {
 #define ENETC_SI_F_PSFP BIT(0)
 #define ENETC_SI_F_QBV  BIT(1)
 #define ENETC_SI_F_QBU  BIT(2)
+#define ENETC_SI_F_LSO	BIT(3)
 
 struct enetc_drvdata {
 	u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */
+	u8 tx_csum:1;
+	u8 max_frags;
 	u64 sysclk_freq;
 	const struct ethtool_ops *eth_ops;
 };
@@ -244,6 +279,19 @@ struct enetc_platform_info {
 	const struct enetc_drvdata *data;
 };
 
+struct enetc_si;
+
+/*
+ * This structure defines the some common hooks for ENETC PSI and VSI.
+ * In addition, since VSI only uses the struct enetc_si as its private
+ * driver data, so this structure also define some hooks specifically
+ * for VSI. For VSI-specific hooks, the format is ‘vf_*()’.
+ */
+struct enetc_si_ops {
+	int (*get_rss_table)(struct enetc_si *si, u32 *table, int count);
+	int (*set_rss_table)(struct enetc_si *si, const u32 *table, int count);
+};
+
 /* PCI IEP device data */
 struct enetc_si {
 	struct pci_dev *pdev;
@@ -252,7 +300,10 @@ struct enetc_si {
 
 	struct net_device *ndev; /* back ref. */
 
-	struct enetc_cbdr cbd_ring;
+	union {
+		struct enetc_cbdr cbd_ring; /* Only ENETC 1.0 */
+		struct ntmp_user ntmp_user; /* ENETC 4.1 and later */
+	};
 
 	int num_rx_rings; /* how many rings are available in the SI */
 	int num_tx_rings;
@@ -262,6 +313,11 @@ struct enetc_si {
 	u16 revision;
 	int hw_features;
 	const struct enetc_drvdata *drvdata;
+	const struct enetc_si_ops *ops;
+
+	struct workqueue_struct *workqueue;
+	struct work_struct rx_mode_task;
+	struct dentry *debugfs_root;
 };
 
 #define ENETC_SI_ALIGN	32
@@ -341,6 +397,8 @@ enum enetc_active_offloads {
 	ENETC_F_QBV			= BIT(9),
 	ENETC_F_QCI			= BIT(10),
 	ENETC_F_QBU			= BIT(11),
+	ENETC_F_TXCSUM			= BIT(12),
+	ENETC_F_LSO			= BIT(13),
 };
 
 enum enetc_flags_bit {
@@ -375,6 +433,7 @@ struct enetc_ndev_priv {
 	u16 msg_enable;
 
 	u8 preemptible_tcs;
+	u8 max_frags; /* The maximum number of BDs for fragments */
 
 	enum enetc_active_offloads active_offloads;
 
@@ -441,6 +500,9 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv);
 void enetc_free_si_resources(struct enetc_ndev_priv *priv);
 int enetc_configure_si(struct enetc_ndev_priv *priv);
 int enetc_get_driver_data(struct enetc_si *si);
+void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+				  const unsigned char *addr);
+void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter);
 
 int enetc_open(struct net_device *ndev);
 int enetc_close(struct net_device *ndev);
@@ -456,6 +518,12 @@ int enetc_setup_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 int enetc_xdp_xmit(struct net_device *ndev, int num_frames,
 		   struct xdp_frame **frames, u32 flags);
 
+int enetc_hwtstamp_get(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config);
+int enetc_hwtstamp_set(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack);
+
 /* ethtool */
 extern const struct ethtool_ops enetc_pf_ethtool_ops;
 extern const struct ethtool_ops enetc4_pf_ethtool_ops;
@@ -468,15 +536,19 @@ void enetc_mm_commit_preemptible_tcs(struct enetc_ndev_priv *priv);
 int enetc_setup_cbdr(struct device *dev, struct enetc_hw *hw, int bd_count,
 		     struct enetc_cbdr *cbdr);
 void enetc_teardown_cbdr(struct enetc_cbdr *cbdr);
+int enetc4_setup_cbdr(struct enetc_si *si);
+void enetc4_teardown_cbdr(struct enetc_si *si);
 int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
 			    char *mac_addr, int si_map);
 int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);
 int enetc_set_fs_entry(struct enetc_si *si, struct enetc_cmd_rfse *rfse,
 		       int index);
-void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes);
+void enetc_set_rss_key(struct enetc_si *si, const u8 *bytes);
 int enetc_get_rss_table(struct enetc_si *si, u32 *table, int count);
 int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count);
 int enetc_send_cmd(struct enetc_si *si, struct enetc_cbd *cbd);
+int enetc4_get_rss_table(struct enetc_si *si, u32 *table, int count);
+int enetc4_set_rss_table(struct enetc_si *si, const u32 *table, int count);
 
 static inline void *enetc_cbd_alloc_data_mem(struct enetc_si *si,
 					     struct enetc_cbd *cbd,
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
new file mode 100644
index 000000000000..1b1591dce73d
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright 2025 NXP */
+
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/string_choices.h>
+
+#include "enetc_pf.h"
+#include "enetc4_debugfs.h"
+
+static void enetc_show_si_mac_hash_filter(struct seq_file *s, int i)
+{
+	struct enetc_si *si = s->private;
+	struct enetc_hw *hw = &si->hw;
+	u32 hash_h, hash_l;
+
+	hash_l = enetc_port_rd(hw, ENETC4_PSIUMHFR0(i));
+	hash_h = enetc_port_rd(hw, ENETC4_PSIUMHFR1(i));
+	seq_printf(s, "SI %d unicast MAC hash filter: 0x%08x%08x\n",
+		   i, hash_h, hash_l);
+
+	hash_l = enetc_port_rd(hw, ENETC4_PSIMMHFR0(i));
+	hash_h = enetc_port_rd(hw, ENETC4_PSIMMHFR1(i));
+	seq_printf(s, "SI %d multicast MAC hash filter: 0x%08x%08x\n",
+		   i, hash_h, hash_l);
+}
+
+static int enetc_mac_filter_show(struct seq_file *s, void *data)
+{
+	struct enetc_si *si = s->private;
+	struct enetc_hw *hw = &si->hw;
+	struct maft_entry_data maft;
+	struct enetc_pf *pf;
+	int i, err, num_si;
+	u32 val;
+
+	pf = enetc_si_priv(si);
+	num_si = pf->caps.num_vsi + 1;
+
+	val = enetc_port_rd(hw, ENETC4_PSIPMMR);
+	for (i = 0; i < num_si; i++) {
+		seq_printf(s, "SI %d Unicast Promiscuous mode: %s\n", i,
+			   str_enabled_disabled(PSIPMMR_SI_MAC_UP(i) & val));
+		seq_printf(s, "SI %d Multicast Promiscuous mode: %s\n", i,
+			   str_enabled_disabled(PSIPMMR_SI_MAC_MP(i) & val));
+	}
+
+	/* MAC hash filter table */
+	for (i = 0; i < num_si; i++)
+		enetc_show_si_mac_hash_filter(s, i);
+
+	if (!pf->num_mfe)
+		return 0;
+
+	/* MAC address filter table */
+	seq_puts(s, "MAC address filter table\n");
+	for (i = 0; i < pf->num_mfe; i++) {
+		memset(&maft, 0, sizeof(maft));
+		err = ntmp_maft_query_entry(&si->ntmp_user, i, &maft);
+		if (err)
+			return err;
+
+		seq_printf(s, "Entry %d, MAC: %pM, SI bitmap: 0x%04x\n", i,
+			   maft.keye.mac_addr, le16_to_cpu(maft.cfge.si_bitmap));
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(enetc_mac_filter);
+
+void enetc_create_debugfs(struct enetc_si *si)
+{
+	struct net_device *ndev = si->ndev;
+	struct dentry *root;
+
+	root = debugfs_create_dir(netdev_name(ndev), NULL);
+	if (IS_ERR(root))
+		return;
+
+	si->debugfs_root = root;
+
+	debugfs_create_file("mac_filter", 0444, root, si, &enetc_mac_filter_fops);
+}
+
+void enetc_remove_debugfs(struct enetc_si *si)
+{
+	debugfs_remove(si->debugfs_root);
+	si->debugfs_root = NULL;
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h
new file mode 100644
index 000000000000..96caca35f79d
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2025 NXP */
+
+#ifndef __ENETC4_DEBUGFS_H
+#define __ENETC4_DEBUGFS_H
+
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+void enetc_create_debugfs(struct enetc_si *si);
+void enetc_remove_debugfs(struct enetc_si *si);
+#else
+static inline void enetc_create_debugfs(struct enetc_si *si)
+{
+}
+
+static inline void enetc_remove_debugfs(struct enetc_si *si)
+{
+}
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index 26b220677448..aa25b445d301 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -12,6 +12,29 @@
 #define NXP_ENETC_VENDOR_ID		0x1131
 #define NXP_ENETC_PF_DEV_ID		0xe101
 
+/**********************Station interface registers************************/
+/* Station interface LSO segmentation flag mask register 0/1 */
+#define ENETC4_SILSOSFMR0		0x1300
+#define  SILSOSFMR0_TCP_MID_SEG		GENMASK(27, 16)
+#define  SILSOSFMR0_TCP_1ST_SEG		GENMASK(11, 0)
+#define  SILSOSFMR0_VAL_SET(first, mid)	(FIELD_PREP(SILSOSFMR0_TCP_MID_SEG, mid) | \
+					 FIELD_PREP(SILSOSFMR0_TCP_1ST_SEG, first))
+
+#define ENETC4_SILSOSFMR1		0x1304
+#define  SILSOSFMR1_TCP_LAST_SEG	GENMASK(11, 0)
+#define   ENETC4_TCP_FLAGS_FIN		BIT(0)
+#define   ENETC4_TCP_FLAGS_SYN		BIT(1)
+#define   ENETC4_TCP_FLAGS_RST		BIT(2)
+#define   ENETC4_TCP_FLAGS_PSH		BIT(3)
+#define   ENETC4_TCP_FLAGS_ACK		BIT(4)
+#define   ENETC4_TCP_FLAGS_URG		BIT(5)
+#define   ENETC4_TCP_FLAGS_ECE		BIT(6)
+#define   ENETC4_TCP_FLAGS_CWR		BIT(7)
+#define   ENETC4_TCP_FLAGS_NS		BIT(8)
+/* According to tso_build_hdr(), clear all special flags for not last packet. */
+#define ENETC4_TCP_NL_SEG_FLAGS_DMASK	(ENETC4_TCP_FLAGS_FIN | \
+					 ENETC4_TCP_FLAGS_RST | ENETC4_TCP_FLAGS_PSH)
+
 /***************************ENETC port registers**************************/
 #define ENETC4_ECAPR0			0x0
 #define  ECAPR0_RFS			BIT(2)
@@ -76,6 +99,18 @@
 #define ENETC4_PSICFGR2(a)		((a) * 0x80 + 0x2018)
 #define  PSICFGR2_NUM_MSIX		GENMASK(5, 0)
 
+/* Port station interface a unicast MAC hash filter register 0/1 */
+#define ENETC4_PSIUMHFR0(a)		((a) * 0x80 + 0x2050)
+#define ENETC4_PSIUMHFR1(a)		((a) * 0x80 + 0x2054)
+
+/* Port station interface a multicast MAC hash filter register 0/1 */
+#define ENETC4_PSIMMHFR0(a)		((a) * 0x80 + 0x2058)
+#define ENETC4_PSIMMHFR1(a)		((a) * 0x80 + 0x205c)
+
+/* Port station interface a VLAN hash filter register 0/1 */
+#define ENETC4_PSIVHFR0(a)		((a) * 0x80 + 0x2060)
+#define ENETC4_PSIVHFR1(a)		((a) * 0x80 + 0x2064)
+
 #define ENETC4_PMCAPR			0x4004
 #define  PMCAPR_HD			BIT(8)
 #define  PMCAPR_FP			GENMASK(10, 9)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index fc41078c4f5d..b3dc1afeefd1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -8,9 +8,19 @@
 #include <linux/unaligned.h>
 
 #include "enetc_pf_common.h"
+#include "enetc4_debugfs.h"
 
 #define ENETC_SI_MAX_RING_NUM	8
 
+#define ENETC_MAC_FILTER_TYPE_UC	BIT(0)
+#define ENETC_MAC_FILTER_TYPE_MC	BIT(1)
+#define ENETC_MAC_FILTER_TYPE_ALL	(ENETC_MAC_FILTER_TYPE_UC | \
+					 ENETC_MAC_FILTER_TYPE_MC)
+
+struct enetc_mac_addr {
+	u8 addr[ETH_ALEN];
+};
+
 static void enetc4_get_port_caps(struct enetc_pf *pf)
 {
 	struct enetc_hw *hw = &pf->si->hw;
@@ -26,6 +36,9 @@ static void enetc4_get_port_caps(struct enetc_pf *pf)
 
 	val = enetc_port_rd(hw, ENETC4_PMCAPR);
 	pf->caps.half_duplex = (val & PMCAPR_HD) ? 1 : 0;
+
+	val = enetc_port_rd(hw, ENETC4_PSIMAFCAPR);
+	pf->caps.mac_filter_num = val & PSIMAFCAPR_NUM_MAC_AFTE;
 }
 
 static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si,
@@ -56,6 +69,200 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si,
 	put_unaligned_le16(lower, addr + 4);
 }
 
+static void enetc4_pf_set_si_mac_promisc(struct enetc_hw *hw, int si,
+					 bool uc_promisc, bool mc_promisc)
+{
+	u32 val = enetc_port_rd(hw, ENETC4_PSIPMMR);
+
+	if (uc_promisc)
+		val |= PSIPMMR_SI_MAC_UP(si);
+	else
+		val &= ~PSIPMMR_SI_MAC_UP(si);
+
+	if (mc_promisc)
+		val |= PSIPMMR_SI_MAC_MP(si);
+	else
+		val &= ~PSIPMMR_SI_MAC_MP(si);
+
+	enetc_port_wr(hw, ENETC4_PSIPMMR, val);
+}
+
+static void enetc4_pf_set_si_uc_hash_filter(struct enetc_hw *hw, int si,
+					    u64 hash)
+{
+	enetc_port_wr(hw, ENETC4_PSIUMHFR0(si), lower_32_bits(hash));
+	enetc_port_wr(hw, ENETC4_PSIUMHFR1(si), upper_32_bits(hash));
+}
+
+static void enetc4_pf_set_si_mc_hash_filter(struct enetc_hw *hw, int si,
+					    u64 hash)
+{
+	enetc_port_wr(hw, ENETC4_PSIMMHFR0(si), lower_32_bits(hash));
+	enetc_port_wr(hw, ENETC4_PSIMMHFR1(si), upper_32_bits(hash));
+}
+
+static void enetc4_pf_set_loopback(struct net_device *ndev, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_si *si = priv->si;
+	u32 val;
+
+	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
+	val = u32_replace_bits(val, en ? 1 : 0, PM_CMD_CFG_LOOP_EN);
+	/* Default to select MAC level loopback mode if loopback is enabled. */
+	val = u32_replace_bits(val, en ? LPBCK_MODE_MAC_LEVEL : 0,
+			       PM_CMD_CFG_LPBK_MODE);
+
+	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
+}
+
+static void enetc4_pf_clear_maft_entries(struct enetc_pf *pf)
+{
+	int i;
+
+	for (i = 0; i < pf->num_mfe; i++)
+		ntmp_maft_delete_entry(&pf->si->ntmp_user, i);
+
+	pf->num_mfe = 0;
+}
+
+static int enetc4_pf_add_maft_entries(struct enetc_pf *pf,
+				      struct enetc_mac_addr *mac,
+				      int mac_cnt)
+{
+	struct maft_entry_data maft = {};
+	u16 si_bit = BIT(0);
+	int i, err;
+
+	maft.cfge.si_bitmap = cpu_to_le16(si_bit);
+	for (i = 0; i < mac_cnt; i++) {
+		ether_addr_copy(maft.keye.mac_addr, mac[i].addr);
+		err = ntmp_maft_add_entry(&pf->si->ntmp_user, i, &maft);
+		if (unlikely(err)) {
+			pf->num_mfe = i;
+			goto clear_maft_entries;
+		}
+	}
+
+	pf->num_mfe = mac_cnt;
+
+	return 0;
+
+clear_maft_entries:
+	enetc4_pf_clear_maft_entries(pf);
+
+	return  err;
+}
+
+static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf)
+{
+	int max_num_mfe = pf->caps.mac_filter_num;
+	struct enetc_mac_filter mac_filter = {};
+	struct net_device *ndev = pf->si->ndev;
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_mac_addr *mac_tbl;
+	struct netdev_hw_addr *ha;
+	int i = 0, err;
+	int mac_cnt;
+
+	netif_addr_lock_bh(ndev);
+
+	mac_cnt = netdev_uc_count(ndev);
+	if (!mac_cnt) {
+		netif_addr_unlock_bh(ndev);
+		/* clear both MAC hash and exact filters */
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+		enetc4_pf_clear_maft_entries(pf);
+
+		return 0;
+	}
+
+	if (mac_cnt > max_num_mfe) {
+		err = -ENOSPC;
+		goto unlock_netif_addr;
+	}
+
+	mac_tbl = kcalloc(mac_cnt, sizeof(*mac_tbl), GFP_ATOMIC);
+	if (!mac_tbl) {
+		err = -ENOMEM;
+		goto unlock_netif_addr;
+	}
+
+	netdev_for_each_uc_addr(ha, ndev) {
+		enetc_add_mac_addr_ht_filter(&mac_filter, ha->addr);
+		ether_addr_copy(mac_tbl[i++].addr, ha->addr);
+	}
+
+	netif_addr_unlock_bh(ndev);
+
+	/* Set temporary unicast hash filters in case of Rx loss when
+	 * updating MAC address filter table
+	 */
+	enetc4_pf_set_si_uc_hash_filter(hw, 0, *mac_filter.mac_hash_table);
+	enetc4_pf_clear_maft_entries(pf);
+
+	if (!enetc4_pf_add_maft_entries(pf, mac_tbl, i))
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+
+	kfree(mac_tbl);
+
+	return 0;
+
+unlock_netif_addr:
+	netif_addr_unlock_bh(ndev);
+
+	return err;
+}
+
+static void enetc4_pf_set_mac_hash_filter(struct enetc_pf *pf, int type)
+{
+	struct net_device *ndev = pf->si->ndev;
+	struct enetc_mac_filter *mac_filter;
+	struct enetc_hw *hw = &pf->si->hw;
+	struct netdev_hw_addr *ha;
+
+	netif_addr_lock_bh(ndev);
+	if (type & ENETC_MAC_FILTER_TYPE_UC) {
+		mac_filter = &pf->mac_filter[UC];
+		enetc_reset_mac_addr_filter(mac_filter);
+		netdev_for_each_uc_addr(ha, ndev)
+			enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
+
+		enetc4_pf_set_si_uc_hash_filter(hw, 0,
+						*mac_filter->mac_hash_table);
+	}
+
+	if (type & ENETC_MAC_FILTER_TYPE_MC) {
+		mac_filter = &pf->mac_filter[MC];
+		enetc_reset_mac_addr_filter(mac_filter);
+		netdev_for_each_mc_addr(ha, ndev)
+			enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
+
+		enetc4_pf_set_si_mc_hash_filter(hw, 0,
+						*mac_filter->mac_hash_table);
+	}
+	netif_addr_unlock_bh(ndev);
+}
+
+static void enetc4_pf_set_mac_filter(struct enetc_pf *pf, int type)
+{
+	/* Currently, the MAC address filter table (MAFT) only has 4 entries,
+	 * and multiple multicast addresses for filtering will be configured
+	 * in the default network configuration, so MAFT is only suitable for
+	 * unicast filtering. If the number of unicast addresses exceeds the
+	 * table capacity, the MAC hash filter will be used.
+	 */
+	if (type & ENETC_MAC_FILTER_TYPE_UC && enetc4_pf_set_uc_exact_filter(pf)) {
+		/* Fall back to the MAC hash filter */
+		enetc4_pf_set_mac_hash_filter(pf, ENETC_MAC_FILTER_TYPE_UC);
+		/* Clear the old MAC exact filter */
+		enetc4_pf_clear_maft_entries(pf);
+	}
+
+	if (type & ENETC_MAC_FILTER_TYPE_MC)
+		enetc4_pf_set_mac_hash_filter(pf, ENETC_MAC_FILTER_TYPE_MC);
+}
+
 static const struct enetc_pf_ops enetc4_pf_ops = {
 	.set_si_primary_mac = enetc4_pf_set_si_primary_mac,
 	.get_si_primary_mac = enetc4_pf_get_si_primary_mac,
@@ -226,24 +433,6 @@ static void enetc4_set_trx_frame_size(struct enetc_pf *pf)
 	enetc4_pf_reset_tc_msdu(&si->hw);
 }
 
-static void enetc4_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
-{
-	int i;
-
-	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-		enetc_port_wr(hw, ENETC4_PRSSKR(i), ((u32 *)bytes)[i]);
-}
-
-static void enetc4_set_default_rss_key(struct enetc_pf *pf)
-{
-	u8 hash_key[ENETC_RSSHASH_KEY_SIZE] = {0};
-	struct enetc_hw *hw = &pf->si->hw;
-
-	/* set up hash key */
-	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
-	enetc4_set_rss_key(hw, hash_key);
-}
-
 static void enetc4_enable_trx(struct enetc_pf *pf)
 {
 	struct enetc_hw *hw = &pf->si->hw;
@@ -256,10 +445,25 @@ static void enetc4_configure_port(struct enetc_pf *pf)
 {
 	enetc4_configure_port_si(pf);
 	enetc4_set_trx_frame_size(pf);
-	enetc4_set_default_rss_key(pf);
+	enetc_set_default_rss_key(pf);
 	enetc4_enable_trx(pf);
 }
 
+static int enetc4_init_ntmp_user(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+
+	/* For ENETC 4.1, all table versions are 0 */
+	memset(&user->tbl, 0, sizeof(user->tbl));
+
+	return enetc4_setup_cbdr(si);
+}
+
+static void enetc4_free_ntmp_user(struct enetc_si *si)
+{
+	enetc4_teardown_cbdr(si);
+}
+
 static int enetc4_pf_init(struct enetc_pf *pf)
 {
 	struct device *dev = &pf->si->pdev->dev;
@@ -272,17 +476,99 @@ static int enetc4_pf_init(struct enetc_pf *pf)
 		return err;
 	}
 
+	err = enetc4_init_ntmp_user(pf->si);
+	if (err) {
+		dev_err(dev, "Failed to init CBDR\n");
+		return err;
+	}
+
 	enetc4_configure_port(pf);
 
 	return 0;
 }
 
+static void enetc4_pf_free(struct enetc_pf *pf)
+{
+	enetc4_free_ntmp_user(pf->si);
+}
+
+static void enetc4_psi_do_set_rx_mode(struct work_struct *work)
+{
+	struct enetc_si *si = container_of(work, struct enetc_si, rx_mode_task);
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct net_device *ndev = si->ndev;
+	struct enetc_hw *hw = &si->hw;
+	bool uc_promisc = false;
+	bool mc_promisc = false;
+	int type = 0;
+
+	rtnl_lock();
+
+	if (ndev->flags & IFF_PROMISC) {
+		uc_promisc = true;
+		mc_promisc = true;
+	} else if (ndev->flags & IFF_ALLMULTI) {
+		mc_promisc = true;
+		type = ENETC_MAC_FILTER_TYPE_UC;
+	} else {
+		type = ENETC_MAC_FILTER_TYPE_ALL;
+	}
+
+	enetc4_pf_set_si_mac_promisc(hw, 0, uc_promisc, mc_promisc);
+
+	if (uc_promisc) {
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+		enetc4_pf_clear_maft_entries(pf);
+	}
+
+	if (mc_promisc)
+		enetc4_pf_set_si_mc_hash_filter(hw, 0, 0);
+
+	/* Set new MAC filter */
+	enetc4_pf_set_mac_filter(pf, type);
+
+	rtnl_unlock();
+}
+
+static void enetc4_pf_set_rx_mode(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_si *si = priv->si;
+
+	queue_work(si->workqueue, &si->rx_mode_task);
+}
+
+static int enetc4_pf_set_features(struct net_device *ndev,
+				  netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		bool promisc_en = !(features & NETIF_F_HW_VLAN_CTAG_FILTER);
+
+		enetc4_pf_set_si_vlan_promisc(hw, 0, promisc_en);
+	}
+
+	if (changed & NETIF_F_LOOPBACK)
+		enetc4_pf_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK));
+
+	enetc_set_features(ndev, features);
+
+	return 0;
+}
+
 static const struct net_device_ops enetc4_ndev_ops = {
 	.ndo_open		= enetc_open,
 	.ndo_stop		= enetc_close,
 	.ndo_start_xmit		= enetc_xmit,
 	.ndo_get_stats		= enetc_get_stats,
 	.ndo_set_mac_address	= enetc_pf_set_mac_addr,
+	.ndo_set_rx_mode	= enetc4_pf_set_rx_mode,
+	.ndo_set_features	= enetc4_pf_set_features,
+	.ndo_vlan_rx_add_vid	= enetc_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= enetc_vlan_rx_del_vid,
 };
 
 static struct phylink_pcs *
@@ -617,6 +903,19 @@ static void enetc4_link_deinit(struct enetc_ndev_priv *priv)
 	enetc_mdiobus_destroy(pf);
 }
 
+static int enetc4_psi_wq_task_init(struct enetc_si *si)
+{
+	char wq_name[24];
+
+	INIT_WORK(&si->rx_mode_task, enetc4_psi_do_set_rx_mode);
+	snprintf(wq_name, sizeof(wq_name), "enetc-%s", pci_name(si->pdev));
+	si->workqueue = create_singlethread_workqueue(wq_name);
+	if (!si->workqueue)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int enetc4_pf_netdev_create(struct enetc_si *si)
 {
 	struct device *dev = &si->pdev->dev;
@@ -657,6 +956,12 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 	if (err)
 		goto err_link_init;
 
+	err = enetc4_psi_wq_task_init(si);
+	if (err) {
+		dev_err(dev, "Failed to init workqueue\n");
+		goto err_wq_init;
+	}
+
 	err = register_netdev(ndev);
 	if (err) {
 		dev_err(dev, "Failed to register netdev\n");
@@ -666,13 +971,14 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 	return 0;
 
 err_reg_netdev:
+	destroy_workqueue(si->workqueue);
+err_wq_init:
 	enetc4_link_deinit(priv);
 err_link_init:
 	enetc_free_msix(priv);
 err_alloc_msix:
 err_config_si:
 err_clk_get:
-	mutex_destroy(&priv->mm_lock);
 	free_netdev(ndev);
 
 	return err;
@@ -684,10 +990,18 @@ static void enetc4_pf_netdev_destroy(struct enetc_si *si)
 	struct net_device *ndev = si->ndev;
 
 	unregister_netdev(ndev);
+	cancel_work(&si->rx_mode_task);
+	destroy_workqueue(si->workqueue);
+	enetc4_link_deinit(priv);
 	enetc_free_msix(priv);
 	free_netdev(ndev);
 }
 
+static const struct enetc_si_ops enetc4_psi_ops = {
+	.get_rss_table = enetc4_get_rss_table,
+	.set_rss_table = enetc4_set_rss_table,
+};
+
 static int enetc4_pf_probe(struct pci_dev *pdev,
 			   const struct pci_device_id *ent)
 {
@@ -712,6 +1026,7 @@ static int enetc4_pf_probe(struct pci_dev *pdev,
 				     "Couldn't map PF only space\n");
 
 	si->revision = enetc_get_ip_revision(&si->hw);
+	si->ops = &enetc4_psi_ops;
 	err = enetc_get_driver_data(si);
 	if (err)
 		return dev_err_probe(dev, err,
@@ -728,14 +1043,28 @@ static int enetc4_pf_probe(struct pci_dev *pdev,
 
 	enetc_get_si_caps(si);
 
-	return enetc4_pf_netdev_create(si);
+	err = enetc4_pf_netdev_create(si);
+	if (err)
+		goto err_netdev_create;
+
+	enetc_create_debugfs(si);
+
+	return 0;
+
+err_netdev_create:
+	enetc4_pf_free(pf);
+
+	return err;
 }
 
 static void enetc4_pf_remove(struct pci_dev *pdev)
 {
 	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_pf *pf = enetc_si_priv(si);
 
+	enetc_remove_debugfs(si);
 	enetc4_pf_netdev_destroy(si);
+	enetc4_pf_free(pf);
 }
 
 static const struct pci_device_id enetc4_pf_id_table[] = {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
index 20bfdf7fb4b4..3d5f31879d5c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
@@ -60,6 +60,44 @@ void enetc_teardown_cbdr(struct enetc_cbdr *cbdr)
 }
 EXPORT_SYMBOL_GPL(enetc_teardown_cbdr);
 
+int enetc4_setup_cbdr(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+	struct device *dev = &si->pdev->dev;
+	struct enetc_hw *hw = &si->hw;
+	struct netc_cbdr_regs regs;
+
+	user->cbdr_num = 1;
+	user->dev = dev;
+	user->ring = devm_kcalloc(dev, user->cbdr_num,
+				  sizeof(struct netc_cbdr), GFP_KERNEL);
+	if (!user->ring)
+		return -ENOMEM;
+
+	/* set CBDR cache attributes */
+	enetc_wr(hw, ENETC_SICAR2,
+		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
+
+	regs.pir = hw->reg + ENETC_SICBDRPIR;
+	regs.cir = hw->reg + ENETC_SICBDRCIR;
+	regs.mr = hw->reg + ENETC_SICBDRMR;
+	regs.bar0 = hw->reg + ENETC_SICBDRBAR0;
+	regs.bar1 = hw->reg + ENETC_SICBDRBAR1;
+	regs.lenr = hw->reg + ENETC_SICBDRLENR;
+
+	return ntmp_init_cbdr(user->ring, dev, &regs);
+}
+EXPORT_SYMBOL_GPL(enetc4_setup_cbdr);
+
+void enetc4_teardown_cbdr(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+
+	ntmp_free_cbdr(user->ring);
+	user->dev = NULL;
+}
+EXPORT_SYMBOL_GPL(enetc4_teardown_cbdr);
+
 static void enetc_clean_cbdr(struct enetc_cbdr *ring)
 {
 	struct enetc_cbd *dest_cbd;
@@ -256,3 +294,15 @@ int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count)
 	return enetc_cmd_rss_table(si, (u32 *)table, count, false);
 }
 EXPORT_SYMBOL_GPL(enetc_set_rss_table);
+
+int enetc4_get_rss_table(struct enetc_si *si, u32 *table, int count)
+{
+	return ntmp_rsst_query_entry(&si->ntmp_user, table, count);
+}
+EXPORT_SYMBOL_GPL(enetc4_get_rss_table);
+
+int enetc4_set_rss_table(struct enetc_si *si, const u32 *table, int count)
+{
+	return ntmp_rsst_update_entry(&si->ntmp_user, table, count);
+}
+EXPORT_SYMBOL_GPL(enetc4_set_rss_table);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index bf34b5bb1e35..d38cd36be4a6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -141,7 +141,7 @@ static const struct {
 
 static const struct {
 	int reg;
-	char name[ETH_GSTRING_LEN];
+	char name[ETH_GSTRING_LEN] __nonstring;
 } enetc_port_counters[] = {
 	{ ENETC_PM_REOCT(0),	"MAC rx ethernet octets" },
 	{ ENETC_PM_RALN(0),	"MAC rx alignment errors" },
@@ -264,7 +264,7 @@ static void enetc_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 			break;
 
 		for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++)
-			ethtool_puts(&data, enetc_port_counters[i].name);
+			ethtool_cpy(&data, enetc_port_counters[i].name);
 
 		break;
 	}
@@ -625,6 +625,29 @@ static int enetc_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc,
 	return 0;
 }
 
+/* i.MX95 ENETC does not support RFS table, but we can use ingress port
+ * filter table to implement Wake-on-LAN filter or drop the matched flow,
+ * so the implementation will be different from enetc_get_rxnfc() and
+ * enetc_set_rxnfc(). Therefore, add enetc4_get_rxnfc() for ENETC v4 PF.
+ */
+static int enetc4_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc,
+			    u32 *rule_locs)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	switch (rxnfc->cmd) {
+	case ETHTOOL_GRXRINGS:
+		rxnfc->data = priv->num_rx_rings;
+		break;
+	case ETHTOOL_GRXFH:
+		return enetc_get_rsshash(rxnfc);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int enetc_set_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -677,36 +700,53 @@ static u32 enetc_get_rxfh_indir_size(struct net_device *ndev)
 	return priv->si->num_rss;
 }
 
+static int enetc_get_rss_key_base(struct enetc_si *si)
+{
+	if (is_enetc_rev1(si))
+		return ENETC_PRSSK(0);
+
+	return ENETC4_PRSSKR(0);
+}
+
+static void enetc_get_rss_key(struct enetc_si *si, const u8 *key)
+{
+	int base = enetc_get_rss_key_base(si);
+	struct enetc_hw *hw = &si->hw;
+	int i;
+
+	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
+		((u32 *)key)[i] = enetc_port_rd(hw, base + i * 4);
+}
+
 static int enetc_get_rxfh(struct net_device *ndev,
 			  struct ethtool_rxfh_param *rxfh)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
-	int err = 0, i;
+	struct enetc_si *si = priv->si;
+	int err = 0;
 
 	/* return hash function */
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	/* return hash key */
-	if (rxfh->key && hw->port)
-		for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-			((u32 *)rxfh->key)[i] = enetc_port_rd(hw,
-							      ENETC_PRSSK(i));
+	if (rxfh->key && enetc_si_is_pf(si))
+		enetc_get_rss_key(si, rxfh->key);
 
 	/* return RSS table */
 	if (rxfh->indir)
-		err = enetc_get_rss_table(priv->si, rxfh->indir,
-					  priv->si->num_rss);
+		err = si->ops->get_rss_table(si, rxfh->indir, si->num_rss);
 
 	return err;
 }
 
-void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
+void enetc_set_rss_key(struct enetc_si *si, const u8 *bytes)
 {
+	int base = enetc_get_rss_key_base(si);
+	struct enetc_hw *hw = &si->hw;
 	int i;
 
 	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-		enetc_port_wr(hw, ENETC_PRSSK(i), ((u32 *)bytes)[i]);
+		enetc_port_wr(hw, base + i * 4, ((u32 *)bytes)[i]);
 }
 EXPORT_SYMBOL_GPL(enetc_set_rss_key);
 
@@ -715,17 +755,16 @@ static int enetc_set_rxfh(struct net_device *ndev,
 			  struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
+	struct enetc_si *si = priv->si;
 	int err = 0;
 
 	/* set hash key, if PF */
-	if (rxfh->key && hw->port)
-		enetc_set_rss_key(hw, rxfh->key);
+	if (rxfh->key && enetc_si_is_pf(si))
+		enetc_set_rss_key(si, rxfh->key);
 
 	/* set RSS table */
 	if (rxfh->indir)
-		err = enetc_set_rss_table(priv->si, rxfh->indir,
-					  priv->si->num_rss);
+		err = si->ops->set_rss_table(si, rxfh->indir, si->num_rss);
 
 	return err;
 }
@@ -832,6 +871,7 @@ static int enetc_set_coalesce(struct net_device *ndev,
 static int enetc_get_ts_info(struct net_device *ndev,
 			     struct kernel_ethtool_ts_info *info)
 {
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	int *phc_idx;
 
 	phc_idx = symbol_get(enetc_phc_index);
@@ -852,8 +892,10 @@ static int enetc_get_ts_info(struct net_device *ndev,
 				SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
-			 (1 << HWTSTAMP_TX_ON) |
-			 (1 << HWTSTAMP_TX_ONESTEP_SYNC);
+			 (1 << HWTSTAMP_TX_ON);
+
+	if (enetc_si_is_pf(priv->si))
+		info->tx_types |= (1 << HWTSTAMP_TX_ONESTEP_SYNC);
 
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_ALL);
@@ -1237,6 +1279,11 @@ const struct ethtool_ops enetc4_pf_ethtool_ops = {
 	.set_wol = enetc_set_wol,
 	.get_pauseparam = enetc_get_pauseparam,
 	.set_pauseparam = enetc_set_pauseparam,
+	.get_rxnfc = enetc4_get_rxnfc,
+	.get_rxfh_key_size = enetc_get_rxfh_key_size,
+	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
+	.get_rxfh = enetc_get_rxfh,
+	.set_rxfh = enetc_set_rxfh,
 };
 
 void enetc_set_ethtool_ops(struct net_device *ndev)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 7c3285584f8a..53e8d18c7a34 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -23,11 +23,9 @@
 #define ENETC_SICTR0	0x18
 #define ENETC_SICTR1	0x1c
 #define ENETC_SIPCAPR0	0x20
-#define ENETC_SIPCAPR0_PSFP	BIT(9)
 #define ENETC_SIPCAPR0_RSS	BIT(8)
-#define ENETC_SIPCAPR0_QBV	BIT(4)
-#define ENETC_SIPCAPR0_QBU	BIT(3)
 #define ENETC_SIPCAPR0_RFS	BIT(2)
+#define ENETC_SIPCAPR0_LSO	BIT(1)
 #define ENETC_SIPCAPR1	0x24
 #define ENETC_SITGTGR	0x30
 #define ENETC_SIRBGCR	0x38
@@ -194,6 +192,9 @@ enum enetc_bdr_type {TX, RX};
 #define ENETC_PCAPR0		0x0900
 #define ENETC_PCAPR0_RXBDR(val)	((val) >> 24)
 #define ENETC_PCAPR0_TXBDR(val)	(((val) >> 16) & 0xff)
+#define ENETC_PCAPR0_PSFP	BIT(9)
+#define ENETC_PCAPR0_QBV	BIT(4)
+#define ENETC_PCAPR0_QBU	BIT(3)
 #define ENETC_PCAPR1		0x0904
 #define ENETC_PSICFGR0(n)	(0x0940 + (n) * 0xc)  /* n = SI index */
 #define ENETC_PSICFGR0_SET_TXBDR(val)	((val) & 0xff)
@@ -506,7 +507,7 @@ static inline u64 _enetc_rd_reg64(void __iomem *reg)
 		tmp = ioread32(reg + 4);
 	} while (high != tmp);
 
-	return le64_to_cpu((__le64)high << 32 | low);
+	return (u64)high << 32 | low;
 }
 #endif
 
@@ -554,11 +555,23 @@ static inline u64 _enetc_rd_reg64_wa(void __iomem *reg)
 union enetc_tx_bd {
 	struct {
 		__le64 addr;
-		__le16 buf_len;
+		union {
+			__le16 buf_len;
+			__le16 hdr_len;	/* For LSO, ENETC 4.1 and later */
+		};
 		__le16 frm_len;
 		union {
 			struct {
-				u8 reserved[3];
+				u8 l3_aux0;
+#define ENETC_TX_BD_L3_START	GENMASK(6, 0)
+#define ENETC_TX_BD_IPCS	BIT(7)
+				u8 l3_aux1;
+#define ENETC_TX_BD_L3_HDR_LEN	GENMASK(6, 0)
+#define ENETC_TX_BD_L3T		BIT(7)
+				u8 l4_aux;
+#define ENETC_TX_BD_L4T		GENMASK(7, 5)
+#define ENETC_TXBD_L4T_UDP	1
+#define ENETC_TXBD_L4T_TCP	2
 				u8 flags;
 			}; /* default layout */
 			__le32 txstart;
@@ -569,23 +582,27 @@ union enetc_tx_bd {
 		__le32 tstamp;
 		__le16 tpid;
 		__le16 vid;
-		u8 reserved[6];
+		__le16 lso_sg_size; /* For ENETC 4.1 and later */
+		__le16 frm_len_ext; /* For ENETC 4.1 and later */
+		u8 reserved[2];
 		u8 e_flags;
 		u8 flags;
 	} ext; /* Tx BD extension */
 	struct {
 		__le32 tstamp;
-		u8 reserved[10];
+		u8 reserved[8];
+		__le16 lso_err_count; /* For ENETC 4.1 and later */
 		u8 status;
 		u8 flags;
 	} wb; /* writeback descriptor */
 };
 
 enum enetc_txbd_flags {
-	ENETC_TXBD_FLAGS_RES0 = BIT(0), /* reserved */
+	ENETC_TXBD_FLAGS_L4CS = BIT(0), /* For ENETC 4.1 and later */
 	ENETC_TXBD_FLAGS_TSE = BIT(1),
+	ENETC_TXBD_FLAGS_LSO = BIT(1), /* For ENETC 4.1 and later */
 	ENETC_TXBD_FLAGS_W = BIT(2),
-	ENETC_TXBD_FLAGS_RES3 = BIT(3), /* reserved */
+	ENETC_TXBD_FLAGS_CSUM_LSO = BIT(3), /* For ENETC 4.1 and later */
 	ENETC_TXBD_FLAGS_TXSTART = BIT(4),
 	ENETC_TXBD_FLAGS_EX = BIT(6),
 	ENETC_TXBD_FLAGS_F = BIT(7)
@@ -654,6 +671,8 @@ union enetc_rx_bd {
 #define ENETC_CBD_FLAGS_SF	BIT(7) /* short format */
 #define ENETC_CBD_STATUS_MASK	0xf
 
+#define ENETC_TPID_8021Q	0
+
 struct enetc_cmd_rfse {
 	u8 smac_h[6];
 	u8 smac_m[6];
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index c47b4a743d93..f63a29e2e031 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -72,30 +72,6 @@ static void enetc_set_isol_vlan(struct enetc_hw *hw, int si, u16 vlan, u8 qos)
 	enetc_port_wr(hw, ENETC_PSIVLANR(si), val);
 }
 
-static int enetc_mac_addr_hash_idx(const u8 *addr)
-{
-	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
-	u64 mask = 0;
-	int res = 0;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		mask |= BIT_ULL(i * 6);
-
-	for (i = 0; i < 6; i++)
-		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
-
-	return res;
-}
-
-static void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
-{
-	filter->mac_addr_cnt = 0;
-
-	bitmap_zero(filter->mac_hash_table,
-		    ENETC_MADDR_HASH_TBL_SZ);
-}
-
 static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
 					 const unsigned char *addr)
 {
@@ -104,16 +80,6 @@ static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
 	filter->mac_addr_cnt++;
 }
 
-static void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
-					 const unsigned char *addr)
-{
-	int idx = enetc_mac_addr_hash_idx(addr);
-
-	/* add hash table entry */
-	__set_bit(idx, filter->mac_hash_table);
-	filter->mac_addr_cnt++;
-}
-
 static void enetc_clear_mac_ht_flt(struct enetc_si *si, int si_idx, int type)
 {
 	bool err = si->errata & ENETC_ERR_UCMCSWP;
@@ -250,67 +216,6 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
 	enetc_port_wr(hw, ENETC_PSIPMR, psipmr);
 }
 
-static void enetc_set_vlan_ht_filter(struct enetc_hw *hw, int si_idx,
-				     unsigned long hash)
-{
-	enetc_port_wr(hw, ENETC_PSIVHFR0(si_idx), lower_32_bits(hash));
-	enetc_port_wr(hw, ENETC_PSIVHFR1(si_idx), upper_32_bits(hash));
-}
-
-static int enetc_vid_hash_idx(unsigned int vid)
-{
-	int res = 0;
-	int i;
-
-	for (i = 0; i < 6; i++)
-		res |= (hweight8(vid & (BIT(i) | BIT(i + 6))) & 0x1) << i;
-
-	return res;
-}
-
-static void enetc_sync_vlan_ht_filter(struct enetc_pf *pf, bool rehash)
-{
-	int i;
-
-	if (rehash) {
-		bitmap_zero(pf->vlan_ht_filter, ENETC_VLAN_HT_SIZE);
-
-		for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) {
-			int hidx = enetc_vid_hash_idx(i);
-
-			__set_bit(hidx, pf->vlan_ht_filter);
-		}
-	}
-
-	enetc_set_vlan_ht_filter(&pf->si->hw, 0, *pf->vlan_ht_filter);
-}
-
-static int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_pf *pf = enetc_si_priv(priv->si);
-	int idx;
-
-	__set_bit(vid, pf->active_vlans);
-
-	idx = enetc_vid_hash_idx(vid);
-	if (!__test_and_set_bit(idx, pf->vlan_ht_filter))
-		enetc_sync_vlan_ht_filter(pf, false);
-
-	return 0;
-}
-
-static int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_pf *pf = enetc_si_priv(priv->si);
-
-	__clear_bit(vid, pf->active_vlans);
-	enetc_sync_vlan_ht_filter(pf, true);
-
-	return 0;
-}
-
 static void enetc_set_loopback(struct net_device *ndev, bool en)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -409,6 +314,23 @@ static void enetc_port_assign_rfs_entries(struct enetc_si *si)
 	enetc_port_wr(hw, ENETC_PRFSMR, ENETC_PRFSMR_RFSE);
 }
 
+static void enetc_port_get_caps(struct enetc_si *si)
+{
+	struct enetc_hw *hw = &si->hw;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC_PCAPR0);
+
+	if (val & ENETC_PCAPR0_QBV)
+		si->hw_features |= ENETC_SI_F_QBV;
+
+	if (val & ENETC_PCAPR0_QBU)
+		si->hw_features |= ENETC_SI_F_QBU;
+
+	if (val & ENETC_PCAPR0_PSFP)
+		si->hw_features |= ENETC_SI_F_PSFP;
+}
+
 static void enetc_port_si_configure(struct enetc_si *si)
 {
 	struct enetc_pf *pf = enetc_si_priv(si);
@@ -416,6 +338,8 @@ static void enetc_port_si_configure(struct enetc_si *si)
 	int num_rings, i;
 	u32 val;
 
+	enetc_port_get_caps(si);
+
 	val = enetc_port_rd(hw, ENETC_PCAPR0);
 	num_rings = min(ENETC_PCAPR0_RXBDR(val), ENETC_PCAPR0_TXBDR(val));
 
@@ -530,7 +454,6 @@ static void enetc_mac_enable(struct enetc_si *si, bool en)
 
 static void enetc_configure_port(struct enetc_pf *pf)
 {
-	u8 hash_key[ENETC_RSSHASH_KEY_SIZE];
 	struct enetc_hw *hw = &pf->si->hw;
 
 	enetc_configure_port_mac(pf->si);
@@ -538,8 +461,7 @@ static void enetc_configure_port(struct enetc_pf *pf)
 	enetc_port_si_configure(pf->si);
 
 	/* set up hash key */
-	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
-	enetc_set_rss_key(hw, hash_key);
+	enetc_set_default_rss_key(pf);
 
 	/* split up RFS entries */
 	enetc_port_assign_rfs_entries(pf->si);
@@ -709,6 +631,8 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_setup_tc		= enetc_pf_setup_tc,
 	.ndo_bpf		= enetc_setup_bpf,
 	.ndo_xdp_xmit		= enetc_xdp_xmit,
+	.ndo_hwtstamp_get	= enetc_hwtstamp_get,
+	.ndo_hwtstamp_set	= enetc_hwtstamp_set,
 };
 
 static struct phylink_pcs *
@@ -920,6 +844,11 @@ static int enetc_pf_register_with_ierb(struct pci_dev *pdev)
 	return enetc_ierb_register_pf(ierb_pdev, pdev);
 }
 
+static const struct enetc_si_ops enetc_psi_ops = {
+	.get_rss_table = enetc_get_rss_table,
+	.set_rss_table = enetc_set_rss_table,
+};
+
 static struct enetc_si *enetc_psi_create(struct pci_dev *pdev)
 {
 	struct enetc_si *si;
@@ -939,6 +868,7 @@ static struct enetc_si *enetc_psi_create(struct pci_dev *pdev)
 	}
 
 	si->revision = enetc_get_ip_revision(&si->hw);
+	si->ops = &enetc_psi_ops;
 	err = enetc_get_driver_data(si);
 	if (err) {
 		dev_err(&pdev->dev, "Could not get PF driver data\n");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index a26a12863855..ae407e9e9ee7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -5,19 +5,8 @@
 #include <linux/phylink.h>
 
 #define ENETC_PF_NUM_RINGS	8
-
-enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
 #define ENETC_MAX_NUM_MAC_FLT	((ENETC_MAX_NUM_VFS + 1) * MADDR_TYPE)
 
-#define ENETC_MADDR_HASH_TBL_SZ	64
-struct enetc_mac_filter {
-	union {
-		char mac_addr[ETH_ALEN];
-		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
-	};
-	int mac_addr_cnt;
-};
-
 #define ENETC_VLAN_HT_SIZE	64
 
 enum enetc_vf_flags {
@@ -34,6 +23,7 @@ struct enetc_port_caps {
 	int num_msix;
 	int num_rx_bdr;
 	int num_tx_bdr;
+	int mac_filter_num;
 };
 
 struct enetc_pf;
@@ -71,6 +61,8 @@ struct enetc_pf {
 
 	struct enetc_port_caps caps;
 	const struct enetc_pf_ops *ops;
+
+	int num_mfe;	/* number of mac address filter table entries */
 };
 
 #define phylink_to_enetc_pf(config) \
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 0eecfc833164..edf14a95cab7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -101,6 +101,7 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 
 	priv->msg_enable = (NETIF_MSG_WOL << 1) - 1;
 	priv->sysclk_freq = si->drvdata->sysclk_freq;
+	priv->max_frags = si->drvdata->max_frags;
 	ndev->netdev_ops = ndev_ops;
 	enetc_set_ethtool_ops(ndev);
 	ndev->watchdog_timeo = 5 * HZ;
@@ -109,24 +110,32 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
 			    NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 			    NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK |
-			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			    NETIF_F_GSO_UDP_L4;
 	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM |
 			 NETIF_F_HW_VLAN_CTAG_TX |
 			 NETIF_F_HW_VLAN_CTAG_RX |
-			 NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			 NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			 NETIF_F_GSO_UDP_L4;
 	ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM |
 			      NETIF_F_TSO | NETIF_F_TSO6;
 
 	ndev->priv_flags |= IFF_UNICAST_FLT;
 
-	/* TODO: currently, i.MX95 ENETC driver does not support advanced features */
-	if (!is_enetc_rev1(si)) {
-		ndev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK);
-		goto end;
-	}
+	if (si->drvdata->tx_csum)
+		priv->active_offloads |= ENETC_F_TXCSUM;
 
-	if (si->num_rss)
+	if (si->hw_features & ENETC_SI_F_LSO)
+		priv->active_offloads |= ENETC_F_LSO;
+
+	if (si->num_rss) {
 		ndev->hw_features |= NETIF_F_RXHASH;
+		ndev->features |= NETIF_F_RXHASH;
+	}
+
+	/* TODO: currently, i.MX95 ENETC driver does not support advanced features */
+	if (!is_enetc_rev1(si))
+		goto end;
 
 	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			     NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
@@ -332,5 +341,86 @@ void enetc_phylink_destroy(struct enetc_ndev_priv *priv)
 }
 EXPORT_SYMBOL_GPL(enetc_phylink_destroy);
 
+void enetc_set_default_rss_key(struct enetc_pf *pf)
+{
+	u8 hash_key[ENETC_RSSHASH_KEY_SIZE] = {0};
+
+	/* set up hash key */
+	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
+	enetc_set_rss_key(pf->si, hash_key);
+}
+EXPORT_SYMBOL_GPL(enetc_set_default_rss_key);
+
+static int enetc_vid_hash_idx(unsigned int vid)
+{
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight8(vid & (BIT(i) | BIT(i + 6))) & 0x1) << i;
+
+	return res;
+}
+
+static void enetc_refresh_vlan_ht_filter(struct enetc_pf *pf)
+{
+	int i;
+
+	bitmap_zero(pf->vlan_ht_filter, ENETC_VLAN_HT_SIZE);
+	for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) {
+		int hidx = enetc_vid_hash_idx(i);
+
+		__set_bit(hidx, pf->vlan_ht_filter);
+	}
+}
+
+static void enetc_set_si_vlan_ht_filter(struct enetc_si *si,
+					int si_id, u64 hash)
+{
+	struct enetc_hw *hw = &si->hw;
+	int high_reg_off, low_reg_off;
+
+	if (is_enetc_rev1(si)) {
+		low_reg_off = ENETC_PSIVHFR0(si_id);
+		high_reg_off = ENETC_PSIVHFR1(si_id);
+	} else {
+		low_reg_off = ENETC4_PSIVHFR0(si_id);
+		high_reg_off = ENETC4_PSIVHFR1(si_id);
+	}
+
+	enetc_port_wr(hw, low_reg_off, lower_32_bits(hash));
+	enetc_port_wr(hw, high_reg_off, upper_32_bits(hash));
+}
+
+int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	int idx;
+
+	__set_bit(vid, pf->active_vlans);
+
+	idx = enetc_vid_hash_idx(vid);
+	if (!__test_and_set_bit(idx, pf->vlan_ht_filter))
+		enetc_set_si_vlan_ht_filter(pf->si, 0, *pf->vlan_ht_filter);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(enetc_vlan_rx_add_vid);
+
+int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+
+	if (__test_and_clear_bit(vid, pf->active_vlans)) {
+		enetc_refresh_vlan_ht_filter(pf);
+		enetc_set_si_vlan_ht_filter(pf->si, 0, *pf->vlan_ht_filter);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(enetc_vlan_rx_del_vid);
+
 MODULE_DESCRIPTION("NXP ENETC PF common functionality driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
index 48f55ee743ad..96d4840a3107 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
@@ -12,6 +12,9 @@ void enetc_mdiobus_destroy(struct enetc_pf *pf);
 int enetc_phylink_create(struct enetc_ndev_priv *priv, struct device_node *node,
 			 const struct phylink_mac_ops *ops);
 void enetc_phylink_destroy(struct enetc_ndev_priv *priv);
+void enetc_set_default_rss_key(struct enetc_pf *pf);
+int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid);
+int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid);
 
 static inline u16 enetc_get_ip_revision(struct enetc_hw *hw)
 {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index a5f8ce576b6e..6c4b374bcb0e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -121,6 +121,8 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_set_features	= enetc_vf_set_features,
 	.ndo_eth_ioctl		= enetc_ioctl,
 	.ndo_setup_tc		= enetc_vf_setup_tc,
+	.ndo_hwtstamp_get	= enetc_hwtstamp_get,
+	.ndo_hwtstamp_set	= enetc_hwtstamp_set,
 };
 
 static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
@@ -136,6 +138,7 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 
 	priv->msg_enable = (NETIF_MSG_IFUP << 1) - 1;
 	priv->sysclk_freq = si->drvdata->sysclk_freq;
+	priv->max_frags = si->drvdata->max_frags;
 	ndev->netdev_ops = ndev_ops;
 	enetc_set_ethtool_ops(ndev);
 	ndev->watchdog_timeo = 5 * HZ;
@@ -144,21 +147,30 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
 			    NETIF_F_HW_VLAN_CTAG_TX |
 			    NETIF_F_HW_VLAN_CTAG_RX |
-			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			    NETIF_F_GSO_UDP_L4;
 	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM |
 			 NETIF_F_HW_VLAN_CTAG_TX |
 			 NETIF_F_HW_VLAN_CTAG_RX |
-			 NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			 NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			 NETIF_F_GSO_UDP_L4;
 	ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM |
 			      NETIF_F_TSO | NETIF_F_TSO6;
 
-	if (si->num_rss)
+	if (si->num_rss) {
 		ndev->hw_features |= NETIF_F_RXHASH;
+		ndev->features |= NETIF_F_RXHASH;
+	}
 
 	/* pick up primary MAC address from SI */
 	enetc_load_primary_mac_addr(&si->hw, ndev);
 }
 
+static const struct enetc_si_ops enetc_vsi_ops = {
+	.get_rss_table = enetc_get_rss_table,
+	.set_rss_table = enetc_set_rss_table,
+};
+
 static int enetc_vf_probe(struct pci_dev *pdev,
 			  const struct pci_device_id *ent)
 {
@@ -173,6 +185,7 @@ static int enetc_vf_probe(struct pci_dev *pdev,
 
 	si = pci_get_drvdata(pdev);
 	si->revision = ENETC_REV_1_0;
+	si->ops = &enetc_vsi_ops;
 	err = enetc_get_driver_data(si);
 	if (err) {
 		dev_err_probe(&pdev->dev, err,
diff --git a/drivers/net/ethernet/freescale/enetc/ntmp.c b/drivers/net/ethernet/freescale/enetc/ntmp.c
new file mode 100644
index 000000000000..ba32c1bbd9e1
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/ntmp.c
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/*
+ * NETC NTMP (NETC Table Management Protocol) 2.0 Library
+ * Copyright 2025 NXP
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/fsl/netc_global.h>
+#include <linux/iopoll.h>
+
+#include "ntmp_private.h"
+
+#define NETC_CBDR_TIMEOUT		1000 /* us */
+#define NETC_CBDR_DELAY_US		10
+#define NETC_CBDR_MR_EN			BIT(31)
+
+#define NTMP_BASE_ADDR_ALIGN		128
+#define NTMP_DATA_ADDR_ALIGN		32
+
+/* Define NTMP Table ID */
+#define NTMP_MAFT_ID			1
+#define NTMP_RSST_ID			3
+
+/* Generic Update Actions for most tables */
+#define NTMP_GEN_UA_CFGEU		BIT(0)
+#define NTMP_GEN_UA_STSEU		BIT(1)
+
+#define NTMP_ENTRY_ID_SIZE		4
+#define RSST_ENTRY_NUM			64
+#define RSST_STSE_DATA_SIZE(n)		((n) * 8)
+#define RSST_CFGE_DATA_SIZE(n)		(n)
+
+int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+		   const struct netc_cbdr_regs *regs)
+{
+	int cbd_num = NETC_CBDR_BD_NUM;
+	size_t size;
+
+	size = cbd_num * sizeof(union netc_cbd) + NTMP_BASE_ADDR_ALIGN;
+	cbdr->addr_base = dma_alloc_coherent(dev, size, &cbdr->dma_base,
+					     GFP_KERNEL);
+	if (!cbdr->addr_base)
+		return -ENOMEM;
+
+	cbdr->dma_size = size;
+	cbdr->bd_num = cbd_num;
+	cbdr->regs = *regs;
+	cbdr->dev = dev;
+
+	/* The base address of the Control BD Ring must be 128 bytes aligned */
+	cbdr->dma_base_align =  ALIGN(cbdr->dma_base,  NTMP_BASE_ADDR_ALIGN);
+	cbdr->addr_base_align = PTR_ALIGN(cbdr->addr_base,
+					  NTMP_BASE_ADDR_ALIGN);
+
+	cbdr->next_to_clean = 0;
+	cbdr->next_to_use = 0;
+	spin_lock_init(&cbdr->ring_lock);
+
+	/* Step 1: Configure the base address of the Control BD Ring */
+	netc_write(cbdr->regs.bar0, lower_32_bits(cbdr->dma_base_align));
+	netc_write(cbdr->regs.bar1, upper_32_bits(cbdr->dma_base_align));
+
+	/* Step 2: Configure the producer index register */
+	netc_write(cbdr->regs.pir, cbdr->next_to_clean);
+
+	/* Step 3: Configure the consumer index register */
+	netc_write(cbdr->regs.cir, cbdr->next_to_use);
+
+	/* Step4: Configure the number of BDs of the Control BD Ring */
+	netc_write(cbdr->regs.lenr, cbdr->bd_num);
+
+	/* Step 5: Enable the Control BD Ring */
+	netc_write(cbdr->regs.mr, NETC_CBDR_MR_EN);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ntmp_init_cbdr);
+
+void ntmp_free_cbdr(struct netc_cbdr *cbdr)
+{
+	/* Disable the Control BD Ring */
+	netc_write(cbdr->regs.mr, 0);
+	dma_free_coherent(cbdr->dev, cbdr->dma_size, cbdr->addr_base,
+			  cbdr->dma_base);
+	memset(cbdr, 0, sizeof(*cbdr));
+}
+EXPORT_SYMBOL_GPL(ntmp_free_cbdr);
+
+static int ntmp_get_free_cbd_num(struct netc_cbdr *cbdr)
+{
+	return (cbdr->next_to_clean - cbdr->next_to_use - 1 +
+		cbdr->bd_num) % cbdr->bd_num;
+}
+
+static union netc_cbd *ntmp_get_cbd(struct netc_cbdr *cbdr, int index)
+{
+	return &((union netc_cbd *)(cbdr->addr_base_align))[index];
+}
+
+static void ntmp_clean_cbdr(struct netc_cbdr *cbdr)
+{
+	union netc_cbd *cbd;
+	int i;
+
+	i = cbdr->next_to_clean;
+	while (netc_read(cbdr->regs.cir) != i) {
+		cbd = ntmp_get_cbd(cbdr, i);
+		memset(cbd, 0, sizeof(*cbd));
+		i = (i + 1) % cbdr->bd_num;
+	}
+
+	cbdr->next_to_clean = i;
+}
+
+static int netc_xmit_ntmp_cmd(struct ntmp_user *user, union netc_cbd *cbd)
+{
+	union netc_cbd *cur_cbd;
+	struct netc_cbdr *cbdr;
+	int i, err;
+	u16 status;
+	u32 val;
+
+	/* Currently only i.MX95 ENETC is supported, and it only has one
+	 * command BD ring
+	 */
+	cbdr = &user->ring[0];
+
+	spin_lock_bh(&cbdr->ring_lock);
+
+	if (unlikely(!ntmp_get_free_cbd_num(cbdr)))
+		ntmp_clean_cbdr(cbdr);
+
+	i = cbdr->next_to_use;
+	cur_cbd = ntmp_get_cbd(cbdr, i);
+	*cur_cbd = *cbd;
+	dma_wmb();
+
+	/* Update producer index of both software and hardware */
+	i = (i + 1) % cbdr->bd_num;
+	cbdr->next_to_use = i;
+	netc_write(cbdr->regs.pir, i);
+
+	err = read_poll_timeout_atomic(netc_read, val, val == i,
+				       NETC_CBDR_DELAY_US, NETC_CBDR_TIMEOUT,
+				       true, cbdr->regs.cir);
+	if (unlikely(err))
+		goto cbdr_unlock;
+
+	dma_rmb();
+	/* Get the writeback command BD, because the caller may need
+	 * to check some other fields of the response header.
+	 */
+	*cbd = *cur_cbd;
+
+	/* Check the writeback error status */
+	status = le16_to_cpu(cbd->resp_hdr.error_rr) & NTMP_RESP_ERROR;
+	if (unlikely(status)) {
+		err = -EIO;
+		dev_err(user->dev, "Command BD error: 0x%04x\n", status);
+	}
+
+	ntmp_clean_cbdr(cbdr);
+	dma_wmb();
+
+cbdr_unlock:
+	spin_unlock_bh(&cbdr->ring_lock);
+
+	return err;
+}
+
+static int ntmp_alloc_data_mem(struct ntmp_dma_buf *data, void **buf_align)
+{
+	void *buf;
+
+	buf = dma_alloc_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN,
+				 &data->dma, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	data->buf = buf;
+	*buf_align = PTR_ALIGN(buf, NTMP_DATA_ADDR_ALIGN);
+
+	return 0;
+}
+
+static void ntmp_free_data_mem(struct ntmp_dma_buf *data)
+{
+	dma_free_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN,
+			  data->buf, data->dma);
+}
+
+static void ntmp_fill_request_hdr(union netc_cbd *cbd, dma_addr_t dma,
+				  int len, int table_id, int cmd,
+				  int access_method)
+{
+	dma_addr_t dma_align;
+
+	memset(cbd, 0, sizeof(*cbd));
+	dma_align = ALIGN(dma, NTMP_DATA_ADDR_ALIGN);
+	cbd->req_hdr.addr = cpu_to_le64(dma_align);
+	cbd->req_hdr.len = cpu_to_le32(len);
+	cbd->req_hdr.cmd = cmd;
+	cbd->req_hdr.access_method = FIELD_PREP(NTMP_ACCESS_METHOD,
+						access_method);
+	cbd->req_hdr.table_id = table_id;
+	cbd->req_hdr.ver_cci_rr = FIELD_PREP(NTMP_HDR_VERSION,
+					     NTMP_HDR_VER2);
+	/* For NTMP version 2.0 or later version */
+	cbd->req_hdr.npf = cpu_to_le32(NTMP_NPF);
+}
+
+static void ntmp_fill_crd(struct ntmp_cmn_req_data *crd, u8 tblv,
+			  u8 qa, u16 ua)
+{
+	crd->update_act = cpu_to_le16(ua);
+	crd->tblv_qact = NTMP_TBLV_QACT(tblv, qa);
+}
+
+static void ntmp_fill_crd_eid(struct ntmp_req_by_eid *rbe, u8 tblv,
+			      u8 qa, u16 ua, u32 entry_id)
+{
+	ntmp_fill_crd(&rbe->crd, tblv, qa, ua);
+	rbe->entry_id = cpu_to_le32(entry_id);
+}
+
+static const char *ntmp_table_name(int tbl_id)
+{
+	switch (tbl_id) {
+	case NTMP_MAFT_ID:
+		return "MAC Address Filter Table";
+	case NTMP_RSST_ID:
+		return "RSS Table";
+	default:
+		return "Unknown Table";
+	};
+}
+
+static int ntmp_delete_entry_by_id(struct ntmp_user *user, int tbl_id,
+				   u8 tbl_ver, u32 entry_id, u32 req_len,
+				   u32 resp_len)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = max(req_len, resp_len),
+	};
+	struct ntmp_req_by_eid *req;
+	union netc_cbd cbd;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	ntmp_fill_crd_eid(req, tbl_ver, 0, 0, entry_id);
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(req_len, resp_len),
+			      tbl_id, NTMP_CMD_DELETE, NTMP_AM_ENTRY_ID);
+
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev,
+			"Failed to delete entry 0x%x of %s, err: %pe",
+			entry_id, ntmp_table_name(tbl_id), ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+
+static int ntmp_query_entry_by_id(struct ntmp_user *user, int tbl_id,
+				  u32 len, struct ntmp_req_by_eid *req,
+				  dma_addr_t dma, bool compare_eid)
+{
+	struct ntmp_cmn_resp_query *resp;
+	int cmd = NTMP_CMD_QUERY;
+	union netc_cbd cbd;
+	u32 entry_id;
+	int err;
+
+	entry_id = le32_to_cpu(req->entry_id);
+	if (le16_to_cpu(req->crd.update_act))
+		cmd = NTMP_CMD_QU;
+
+	/* Request header */
+	ntmp_fill_request_hdr(&cbd, dma, len, tbl_id, cmd, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err) {
+		dev_err(user->dev,
+			"Failed to query entry 0x%x of %s, err: %pe\n",
+			entry_id, ntmp_table_name(tbl_id), ERR_PTR(err));
+		return err;
+	}
+
+	/* For a few tables, the first field of their response data is not
+	 * entry_id, so directly return success.
+	 */
+	if (!compare_eid)
+		return 0;
+
+	resp = (struct ntmp_cmn_resp_query *)req;
+	if (unlikely(le32_to_cpu(resp->entry_id) != entry_id)) {
+		dev_err(user->dev,
+			"%s: query EID 0x%x doesn't match response EID 0x%x\n",
+			ntmp_table_name(tbl_id), entry_id, le32_to_cpu(resp->entry_id));
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+			struct maft_entry_data *maft)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = sizeof(struct maft_req_add),
+	};
+	struct maft_req_add *req;
+	union netc_cbd cbd;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set mac address filter table request data buffer */
+	ntmp_fill_crd_eid(&req->rbe, user->tbl.maft_ver, 0, 0, entry_id);
+	req->keye = maft->keye;
+	req->cfge = maft->cfge;
+
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0),
+			      NTMP_MAFT_ID, NTMP_CMD_ADD, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev, "Failed to add MAFT entry 0x%x, err: %pe\n",
+			entry_id, ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_add_entry);
+
+int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+			  struct maft_entry_data *maft)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = sizeof(struct maft_resp_query),
+	};
+	struct maft_resp_query *resp;
+	struct ntmp_req_by_eid *req;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	ntmp_fill_crd_eid(req, user->tbl.maft_ver, 0, 0, entry_id);
+	err = ntmp_query_entry_by_id(user, NTMP_MAFT_ID,
+				     NTMP_LEN(sizeof(*req), data.size),
+				     req, data.dma, true);
+	if (err)
+		goto end;
+
+	resp = (struct maft_resp_query *)req;
+	maft->keye = resp->keye;
+	maft->cfge = resp->cfge;
+
+end:
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_query_entry);
+
+int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id)
+{
+	return ntmp_delete_entry_by_id(user, NTMP_MAFT_ID, user->tbl.maft_ver,
+				       entry_id, NTMP_EID_REQ_LEN, 0);
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_delete_entry);
+
+int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table,
+			   int count)
+{
+	struct ntmp_dma_buf data = {.dev = user->dev};
+	struct rsst_req_update *req;
+	union netc_cbd cbd;
+	int err, i;
+
+	if (count != RSST_ENTRY_NUM)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	data.size = struct_size(req, groups, count);
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set the request data buffer */
+	ntmp_fill_crd_eid(&req->rbe, user->tbl.rsst_ver, 0,
+			  NTMP_GEN_UA_CFGEU | NTMP_GEN_UA_STSEU, 0);
+	for (i = 0; i < count; i++)
+		req->groups[i] = (u8)(table[i]);
+
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0),
+			      NTMP_RSST_ID, NTMP_CMD_UPDATE, NTMP_AM_ENTRY_ID);
+
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev, "Failed to update RSST entry, err: %pe\n",
+			ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_rsst_update_entry);
+
+int ntmp_rsst_query_entry(struct ntmp_user *user, u32 *table, int count)
+{
+	struct ntmp_dma_buf data = {.dev = user->dev};
+	struct ntmp_req_by_eid *req;
+	union netc_cbd cbd;
+	int err, i;
+	u8 *group;
+
+	if (count != RSST_ENTRY_NUM)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	data.size = NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count) +
+		    RSST_CFGE_DATA_SIZE(count);
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set the request data buffer */
+	ntmp_fill_crd_eid(req, user->tbl.rsst_ver, 0, 0, 0);
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(sizeof(*req), data.size),
+			      NTMP_RSST_ID, NTMP_CMD_QUERY, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err) {
+		dev_err(user->dev, "Failed to query RSST entry, err: %pe\n",
+			ERR_PTR(err));
+		goto end;
+	}
+
+	group = (u8 *)req;
+	group += NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count);
+	for (i = 0; i < count; i++)
+		table[i] = group[i];
+
+end:
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_rsst_query_entry);
+
+MODULE_DESCRIPTION("NXP NETC Library");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/ntmp_private.h b/drivers/net/ethernet/freescale/enetc/ntmp_private.h
new file mode 100644
index 000000000000..34394e40fddd
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/ntmp_private.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/*
+ * NTMP table request and response data buffer formats
+ * Copyright 2025 NXP
+ */
+
+#ifndef __NTMP_PRIVATE_H
+#define __NTMP_PRIVATE_H
+
+#include <linux/bitfield.h>
+#include <linux/fsl/ntmp.h>
+
+#define NTMP_EID_REQ_LEN	8
+#define NETC_CBDR_BD_NUM	256
+
+union netc_cbd {
+	struct {
+		__le64 addr;
+		__le32 len;
+#define NTMP_RESP_LEN		GENMASK(19, 0)
+#define NTMP_REQ_LEN		GENMASK(31, 20)
+#define NTMP_LEN(req, resp)	(FIELD_PREP(NTMP_REQ_LEN, (req)) | \
+				((resp) & NTMP_RESP_LEN))
+		u8 cmd;
+#define NTMP_CMD_DELETE		BIT(0)
+#define NTMP_CMD_UPDATE		BIT(1)
+#define NTMP_CMD_QUERY		BIT(2)
+#define NTMP_CMD_ADD		BIT(3)
+#define NTMP_CMD_QU		(NTMP_CMD_QUERY | NTMP_CMD_UPDATE)
+		u8 access_method;
+#define NTMP_ACCESS_METHOD	GENMASK(7, 4)
+#define NTMP_AM_ENTRY_ID	0
+#define NTMP_AM_EXACT_KEY	1
+#define NTMP_AM_SEARCH		2
+#define NTMP_AM_TERNARY_KEY	3
+		u8 table_id;
+		u8 ver_cci_rr;
+#define NTMP_HDR_VERSION	GENMASK(5, 0)
+#define NTMP_HDR_VER2		2
+#define NTMP_CCI		BIT(6)
+#define NTMP_RR			BIT(7)
+		__le32 resv[3];
+		__le32 npf;
+#define NTMP_NPF		BIT(15)
+	} req_hdr;	/* NTMP Request Message Header Format */
+
+	struct {
+		__le32 resv0[3];
+		__le16 num_matched;
+		__le16 error_rr;
+#define NTMP_RESP_ERROR		GENMASK(11, 0)
+#define NTMP_RESP_RR		BIT(15)
+		__le32 resv1[4];
+	} resp_hdr; /* NTMP Response Message Header Format */
+};
+
+struct ntmp_dma_buf {
+	struct device *dev;
+	size_t size;
+	void *buf;
+	dma_addr_t dma;
+};
+
+struct ntmp_cmn_req_data {
+	__le16 update_act;
+	u8 dbg_opt;
+	u8 tblv_qact;
+#define NTMP_QUERY_ACT		GENMASK(3, 0)
+#define NTMP_TBL_VER		GENMASK(7, 4)
+#define NTMP_TBLV_QACT(v, a)	(FIELD_PREP(NTMP_TBL_VER, (v)) | \
+				 ((a) & NTMP_QUERY_ACT))
+};
+
+struct ntmp_cmn_resp_query {
+	__le32 entry_id;
+};
+
+/* Generic structure for request data by entry ID  */
+struct ntmp_req_by_eid {
+	struct ntmp_cmn_req_data crd;
+	__le32 entry_id;
+};
+
+/* MAC Address Filter Table Request Data Buffer Format of Add action */
+struct maft_req_add {
+	struct ntmp_req_by_eid rbe;
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+/* MAC Address Filter Table Response Data Buffer Format of Query action */
+struct maft_resp_query {
+	__le32 entry_id;
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+/* RSS Table Request Data Buffer Format of Update action */
+struct rsst_req_update {
+	struct ntmp_req_by_eid rbe;
+	u8 groups[];
+};
+
+#endif
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 1cca0425d493..c81f2ea588f2 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -671,8 +671,6 @@ struct fec_enet_private {
 	unsigned int tx_time_itr;
 	unsigned int itr_clk_rate;
 
-	/* tx lpi eee mode */
-	struct ethtool_keee eee;
 	unsigned int clk_ref_rate;
 
 	/* ptp clock period in ns*/
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1b55047c0237..17e9bddb9ddd 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -714,7 +714,12 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 	txq->bd.cur = bdp;
 
 	/* Trigger transmission start */
-	writel(0, txq->bd.reg_desc_active);
+	if (!(fep->quirks & FEC_QUIRK_ERR007885) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active))
+		writel(0, txq->bd.reg_desc_active);
 
 	return 0;
 }
@@ -840,6 +845,8 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int hdr_len, total_len, data_left;
 	struct bufdesc *bdp = txq->bd.cur;
+	struct bufdesc *tmp_bdp;
+	struct bufdesc_ex *ebdp;
 	struct tso_t tso;
 	unsigned int index = 0;
 	int ret;
@@ -913,7 +920,34 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	return 0;
 
 err_release:
-	/* TODO: Release all used data descriptors for TSO */
+	/* Release all used data descriptors for TSO */
+	tmp_bdp = txq->bd.cur;
+
+	while (tmp_bdp != bdp) {
+		/* Unmap data buffers */
+		if (tmp_bdp->cbd_bufaddr &&
+		    !IS_TSO_HEADER(txq, fec32_to_cpu(tmp_bdp->cbd_bufaddr)))
+			dma_unmap_single(&fep->pdev->dev,
+					 fec32_to_cpu(tmp_bdp->cbd_bufaddr),
+					 fec16_to_cpu(tmp_bdp->cbd_datlen),
+					 DMA_TO_DEVICE);
+
+		/* Clear standard buffer descriptor fields */
+		tmp_bdp->cbd_sc = 0;
+		tmp_bdp->cbd_datlen = 0;
+		tmp_bdp->cbd_bufaddr = 0;
+
+		/* Handle extended descriptor if enabled */
+		if (fep->bufdesc_ex) {
+			ebdp = (struct bufdesc_ex *)tmp_bdp;
+			ebdp->cbd_esc = 0;
+		}
+
+		tmp_bdp = fec_enet_get_nextdesc(tmp_bdp, &txq->bd);
+	}
+
+	dev_kfree_skb_any(skb);
+
 	return ret;
 }
 
@@ -1064,6 +1098,29 @@ static void fec_enet_enable_ring(struct net_device *ndev)
 	}
 }
 
+/* Whack a reset.  We should wait for this.
+ * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
+ * instead of reset MAC itself.
+ */
+static void fec_ctrl_reset(struct fec_enet_private *fep, bool allow_wol)
+{
+	u32 val;
+
+	if (!allow_wol || !(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
+		if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES ||
+		    ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) {
+			writel(0, fep->hwp + FEC_ECNTRL);
+		} else {
+			writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL);
+			udelay(10);
+		}
+	} else {
+		val = readl(fep->hwp + FEC_ECNTRL);
+		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
+		writel(val, fep->hwp + FEC_ECNTRL);
+	}
+}
+
 /*
  * This function is called to start or restart the FEC during a link
  * change, transmit timeout, or to reconfigure the FEC.  The network
@@ -1080,17 +1137,7 @@ fec_restart(struct net_device *ndev)
 	if (fep->bufdesc_ex)
 		fec_ptp_save_state(fep);
 
-	/* Whack a reset.  We should wait for this.
-	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
-	 * instead of reset MAC itself.
-	 */
-	if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES ||
-	    ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) {
-		writel(0, fep->hwp + FEC_ECNTRL);
-	} else {
-		writel(1, fep->hwp + FEC_ECNTRL);
-		udelay(10);
-	}
+	fec_ctrl_reset(fep, false);
 
 	/*
 	 * enet-mac reset will reset mac address registers too,
@@ -1344,22 +1391,7 @@ fec_stop(struct net_device *ndev)
 	if (fep->bufdesc_ex)
 		fec_ptp_save_state(fep);
 
-	/* Whack a reset.  We should wait for this.
-	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
-	 * instead of reset MAC itself.
-	 */
-	if (!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
-		if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) {
-			writel(0, fep->hwp + FEC_ECNTRL);
-		} else {
-			writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL);
-			udelay(10);
-		}
-	} else {
-		val = readl(fep->hwp + FEC_ECNTRL);
-		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
-		writel(val, fep->hwp + FEC_ECNTRL);
-	}
+	fec_ctrl_reset(fep, true);
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 
@@ -1591,19 +1623,22 @@ static void fec_enet_tx(struct net_device *ndev, int budget)
 		fec_enet_tx_queue(ndev, i, budget);
 }
 
-static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
+static int fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
 				struct bufdesc *bdp, int index)
 {
 	struct page *new_page;
 	dma_addr_t phys_addr;
 
 	new_page = page_pool_dev_alloc_pages(rxq->page_pool);
-	WARN_ON(!new_page);
-	rxq->rx_skb_info[index].page = new_page;
+	if (unlikely(!new_page))
+		return -ENOMEM;
 
+	rxq->rx_skb_info[index].page = new_page;
 	rxq->rx_skb_info[index].offset = FEC_ENET_XDP_HEADROOM;
 	phys_addr = page_pool_get_dma_addr(new_page) + FEC_ENET_XDP_HEADROOM;
 	bdp->cbd_bufaddr = cpu_to_fec32(phys_addr);
+
+	return 0;
 }
 
 static u32
@@ -1698,6 +1733,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	int cpu = smp_processor_id();
 	struct xdp_buff xdp;
 	struct page *page;
+	__fec32 cbd_bufaddr;
 	u32 sub_len = 4;
 
 #if !defined(CONFIG_M5272)
@@ -1766,12 +1802,17 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 
 		index = fec_enet_get_bd_index(bdp, &rxq->bd);
 		page = rxq->rx_skb_info[index].page;
+		cbd_bufaddr = bdp->cbd_bufaddr;
+		if (fec_enet_update_cbd(rxq, bdp, index)) {
+			ndev->stats.rx_dropped++;
+			goto rx_processing_done;
+		}
+
 		dma_sync_single_for_cpu(&fep->pdev->dev,
-					fec32_to_cpu(bdp->cbd_bufaddr),
+					fec32_to_cpu(cbd_bufaddr),
 					pkt_len,
 					DMA_FROM_DEVICE);
 		prefetch(page_address(page));
-		fec_enet_update_cbd(rxq, bdp, index);
 
 		if (xdp_prog) {
 			xdp_buff_clear_frags_flag(&xdp);
@@ -2045,14 +2086,14 @@ static int fec_enet_us_to_tx_cycle(struct net_device *ndev, int us)
 	return us * (fep->clk_ref_rate / 1000) / 1000;
 }
 
-static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable)
+static int fec_enet_eee_mode_set(struct net_device *ndev, u32 lpi_timer,
+				 bool enable)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct ethtool_keee *p = &fep->eee;
 	unsigned int sleep_cycle, wake_cycle;
 
 	if (enable) {
-		sleep_cycle = fec_enet_us_to_tx_cycle(ndev, p->tx_lpi_timer);
+		sleep_cycle = fec_enet_us_to_tx_cycle(ndev, lpi_timer);
 		wake_cycle = sleep_cycle;
 	} else {
 		sleep_cycle = 0;
@@ -2105,7 +2146,9 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 			napi_enable(&fep->napi);
 		}
 		if (fep->quirks & FEC_QUIRK_HAS_EEE)
-			fec_enet_eee_mode_set(ndev, phy_dev->enable_tx_lpi);
+			fec_enet_eee_mode_set(ndev,
+					      phy_dev->eee_cfg.tx_lpi_timer,
+					      phy_dev->enable_tx_lpi);
 	} else {
 		if (fep->link) {
 			netif_stop_queue(ndev);
@@ -3181,7 +3224,6 @@ static int
 fec_enet_get_eee(struct net_device *ndev, struct ethtool_keee *edata)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct ethtool_keee *p = &fep->eee;
 
 	if (!(fep->quirks & FEC_QUIRK_HAS_EEE))
 		return -EOPNOTSUPP;
@@ -3189,8 +3231,6 @@ fec_enet_get_eee(struct net_device *ndev, struct ethtool_keee *edata)
 	if (!netif_running(ndev))
 		return -ENETDOWN;
 
-	edata->tx_lpi_timer = p->tx_lpi_timer;
-
 	return phy_ethtool_get_eee(ndev->phydev, edata);
 }
 
@@ -3198,7 +3238,6 @@ static int
 fec_enet_set_eee(struct net_device *ndev, struct ethtool_keee *edata)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct ethtool_keee *p = &fep->eee;
 
 	if (!(fep->quirks & FEC_QUIRK_HAS_EEE))
 		return -EOPNOTSUPP;
@@ -3206,8 +3245,6 @@ fec_enet_set_eee(struct net_device *ndev, struct ethtool_keee *edata)
 	if (!netif_running(ndev))
 		return -ENETDOWN;
 
-	p->tx_lpi_timer = edata->tx_lpi_timer;
-
 	return phy_ethtool_set_eee(ndev->phydev, edata);
 }
 
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 7f6b57432071..876d90832596 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -30,7 +30,6 @@
 #include <linux/phy.h>
 #include <linux/fec.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_net.h>
 
 #include "fec.h"
@@ -739,8 +738,8 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx)
 
 	INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep);
 
-	hrtimer_init(&fep->perout_timer, CLOCK_REALTIME, HRTIMER_MODE_REL);
-	fep->perout_timer.function = fec_ptp_pps_perout_handler;
+	hrtimer_setup(&fep->perout_timer, fec_ptp_pps_perout_handler, CLOCK_REALTIME,
+		      HRTIMER_MODE_REL);
 
 	irq = platform_get_irq_byname_optional(pdev, "pps");
 	if (irq < 0)
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index fb416d60dcd7..11887458f050 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -2690,13 +2690,12 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 {
 	struct fman *fman;
 	struct device_node *fm_node, *muram_node;
+	void __iomem *base_addr;
 	struct resource *res;
 	u32 val, range[2];
 	int err, irq;
 	struct clk *clk;
 	u32 clk_rate;
-	phys_addr_t phys_base_addr;
-	resource_size_t mem_size;
 
 	fman = kzalloc(sizeof(*fman), GFP_KERNEL);
 	if (!fman)
@@ -2724,18 +2723,6 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 		goto fman_node_put;
 	fman->dts_params.err_irq = err;
 
-	/* Get the FM address */
-	res = platform_get_resource(of_dev, IORESOURCE_MEM, 0);
-	if (!res) {
-		err = -EINVAL;
-		dev_err(&of_dev->dev, "%s: Can't get FMan memory resource\n",
-			__func__);
-		goto fman_node_put;
-	}
-
-	phys_base_addr = res->start;
-	mem_size = resource_size(res);
-
 	clk = of_clk_get(fm_node, 0);
 	if (IS_ERR(clk)) {
 		err = PTR_ERR(clk);
@@ -2803,24 +2790,16 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 		}
 	}
 
-	fman->dts_params.res =
-		devm_request_mem_region(&of_dev->dev, phys_base_addr,
-					mem_size, "fman");
-	if (!fman->dts_params.res) {
-		err = -EBUSY;
-		dev_err(&of_dev->dev, "%s: request_mem_region() failed\n",
-			__func__);
-		goto fman_free;
-	}
-
-	fman->dts_params.base_addr =
-		devm_ioremap(&of_dev->dev, phys_base_addr, mem_size);
-	if (!fman->dts_params.base_addr) {
-		err = -ENOMEM;
+	base_addr = devm_platform_get_and_ioremap_resource(of_dev, 0, &res);
+	if (IS_ERR(base_addr)) {
+		err = PTR_ERR(base_addr);
 		dev_err(&of_dev->dev, "%s: devm_ioremap() failed\n", __func__);
 		goto fman_free;
 	}
 
+	fman->dts_params.base_addr = base_addr;
+	fman->dts_params.res = res;
+
 	fman->dev = &of_dev->dev;
 
 	err = of_platform_populate(fm_node, NULL, NULL, &of_dev->dev);
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 85617bb94959..51402dff72c5 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -755,12 +755,12 @@ static struct fman_mac *pcs_to_dtsec(struct phylink_pcs *pcs)
 	return container_of(pcs, struct fman_mac, pcs);
 }
 
-static void dtsec_pcs_get_state(struct phylink_pcs *pcs,
+static void dtsec_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 				struct phylink_link_state *state)
 {
 	struct fman_mac *dtsec = pcs_to_dtsec(pcs);
 
-	phylink_mii_c22_pcs_get_state(dtsec->tbidev, state);
+	phylink_mii_c22_pcs_get_state(dtsec->tbidev, neg_mode, state);
 }
 
 static int dtsec_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
@@ -1446,7 +1446,6 @@ int dtsec_initialization(struct mac_device *mac_dev,
 		goto _return_fm_mac_free;
 	}
 	dtsec->pcs.ops = &dtsec_pcs_ops;
-	dtsec->pcs.neg_mode = true;
 	dtsec->pcs.poll = true;
 
 	supported = mac_dev->phylink_config.supported_interfaces;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 435138f4699d..bcbcad613512 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1647,20 +1647,11 @@ static void gfar_configure_serdes(struct net_device *dev)
  */
 static int init_phy(struct net_device *dev)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct gfar_private *priv = netdev_priv(dev);
 	phy_interface_t interface = priv->interface;
 	struct phy_device *phydev;
 	struct ethtool_keee edata;
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
-	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, mask);
-
 	priv->oldlink = 0;
 	priv->oldspeed = 0;
 	priv->oldduplex = -1;
@@ -1675,9 +1666,8 @@ static int init_phy(struct net_device *dev)
 	if (interface == PHY_INTERFACE_MODE_SGMII)
 		gfar_configure_serdes(dev);
 
-	/* Remove any features not supported by the controller */
-	linkmode_and(phydev->supported, phydev->supported, mask);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT))
+		phy_set_max_speed(phydev, SPEED_100);
 
 	/* Add support for flow control */
 	phy_support_asym_pause(phydev);
@@ -2071,15 +2061,13 @@ static void gfar_timeout(struct net_device *dev, unsigned int txqueue)
 	schedule_work(&priv->reset_task);
 }
 
-static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
+static int gfar_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
 	struct gfar_private *priv = netdev_priv(netdev);
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		priv->hwts_tx_en = 0;
 		break;
@@ -2092,7 +2080,7 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		if (priv->hwts_rx_en) {
 			priv->hwts_rx_en = 0;
@@ -2106,44 +2094,23 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 			priv->hwts_rx_en = 1;
 			reset_gfar(netdev);
 		}
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	}
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
-static int gfar_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
+static int gfar_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
 	struct gfar_private *priv = netdev_priv(netdev);
 
-	config.flags = 0;
-	config.tx_type = priv->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	config.rx_filter = (priv->hwts_rx_en ?
-			    HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE);
+	config->tx_type = priv->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config->rx_filter = priv->hwts_rx_en ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
-}
-
-static int gfar_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
-	struct phy_device *phydev = dev->phydev;
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	if (cmd == SIOCSHWTSTAMP)
-		return gfar_hwtstamp_set(dev, rq);
-	if (cmd == SIOCGHWTSTAMP)
-		return gfar_hwtstamp_get(dev, rq);
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_mii_ioctl(phydev, rq, cmd);
+	return 0;
 }
 
 /* Interrupt Handler for Transmit complete */
@@ -3184,7 +3151,7 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_set_features = gfar_set_features,
 	.ndo_set_rx_mode = gfar_set_multi,
 	.ndo_tx_timeout = gfar_timeout,
-	.ndo_eth_ioctl = gfar_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
 	.ndo_get_stats64 = gfar_get_stats64,
 	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = gfar_set_mac_addr,
@@ -3192,6 +3159,8 @@ static const struct net_device_ops gfar_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = gfar_netpoll,
 #endif
+	.ndo_hwtstamp_get = gfar_hwtstamp_get,
+	.ndo_hwtstamp_set = gfar_hwtstamp_set,
 };
 
 /* Set up the ethernet device structure, private data,
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 6663c1768089..affd5a6c44e7 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -26,7 +26,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/mii.h>
 #include <linux/phy.h>
-#include <linux/phy_fixed.h>
+#include <linux/phylink.h>
 #include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -34,6 +34,7 @@
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/platform_device.h>
+#include <linux/rtnetlink.h>
 
 #include <linux/uaccess.h>
 #include <asm/irq.h>
@@ -132,7 +133,6 @@ static const struct ucc_geth_info ugeth_primary_info = {
 	.transmitFlowControl = 1,
 	.maxGroupAddrInHash = 4,
 	.maxIndAddrInHash = 4,
-	.prel = 7,
 	.maxFrameLength = 1518+16, /* Add extra bytes for VLANs etc. */
 	.minFrameLength = 64,
 	.maxD1Length = 1520+16, /* Add extra bytes for VLANs etc. */
@@ -1205,34 +1205,6 @@ static int init_mac_station_addr_regs(u8 address_byte_0,
 	return 0;
 }
 
-static int init_check_frame_length_mode(int length_check,
-					u32 __iomem *maccfg2_register)
-{
-	u32 value = 0;
-
-	value = in_be32(maccfg2_register);
-
-	if (length_check)
-		value |= MACCFG2_LC;
-	else
-		value &= ~MACCFG2_LC;
-
-	out_be32(maccfg2_register, value);
-	return 0;
-}
-
-static int init_preamble_length(u8 preamble_length,
-				u32 __iomem *maccfg2_register)
-{
-	if ((preamble_length < 3) || (preamble_length > 7))
-		return -EINVAL;
-
-	clrsetbits_be32(maccfg2_register, MACCFG2_PREL_MASK,
-			preamble_length << MACCFG2_PREL_SHIFT);
-
-	return 0;
-}
-
 static int init_rx_parameters(int reject_broadcast,
 			      int receive_short_frames,
 			      int promiscuous, u32 __iomem *upsmr_register)
@@ -1287,94 +1259,11 @@ static int init_min_frame_len(u16 min_frame_length,
 	return 0;
 }
 
-static int adjust_enet_interface(struct ucc_geth_private *ugeth)
+static bool phy_interface_mode_is_reduced(phy_interface_t interface)
 {
-	struct ucc_geth_info *ug_info;
-	struct ucc_geth __iomem *ug_regs;
-	struct ucc_fast __iomem *uf_regs;
-	int ret_val;
-	u32 upsmr, maccfg2;
-	u16 value;
-
-	ugeth_vdbg("%s: IN", __func__);
-
-	ug_info = ugeth->ug_info;
-	ug_regs = ugeth->ug_regs;
-	uf_regs = ugeth->uccf->uf_regs;
-
-	/*                    Set MACCFG2                    */
-	maccfg2 = in_be32(&ug_regs->maccfg2);
-	maccfg2 &= ~MACCFG2_INTERFACE_MODE_MASK;
-	if ((ugeth->max_speed == SPEED_10) ||
-	    (ugeth->max_speed == SPEED_100))
-		maccfg2 |= MACCFG2_INTERFACE_MODE_NIBBLE;
-	else if (ugeth->max_speed == SPEED_1000)
-		maccfg2 |= MACCFG2_INTERFACE_MODE_BYTE;
-	maccfg2 |= ug_info->padAndCrc;
-	out_be32(&ug_regs->maccfg2, maccfg2);
-
-	/*                    Set UPSMR                      */
-	upsmr = in_be32(&uf_regs->upsmr);
-	upsmr &= ~(UCC_GETH_UPSMR_RPM | UCC_GETH_UPSMR_R10M |
-		   UCC_GETH_UPSMR_TBIM | UCC_GETH_UPSMR_RMM);
-	if ((ugeth->phy_interface == PHY_INTERFACE_MODE_RMII) ||
-	    (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII) ||
-	    (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_ID) ||
-	    (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
-	    (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) ||
-	    (ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) {
-		if (ugeth->phy_interface != PHY_INTERFACE_MODE_RMII)
-			upsmr |= UCC_GETH_UPSMR_RPM;
-		switch (ugeth->max_speed) {
-		case SPEED_10:
-			upsmr |= UCC_GETH_UPSMR_R10M;
-			fallthrough;
-		case SPEED_100:
-			if (ugeth->phy_interface != PHY_INTERFACE_MODE_RTBI)
-				upsmr |= UCC_GETH_UPSMR_RMM;
-		}
-	}
-	if ((ugeth->phy_interface == PHY_INTERFACE_MODE_TBI) ||
-	    (ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) {
-		upsmr |= UCC_GETH_UPSMR_TBIM;
-	}
-	if (ugeth->phy_interface == PHY_INTERFACE_MODE_SGMII)
-		upsmr |= UCC_GETH_UPSMR_SGMM;
-
-	out_be32(&uf_regs->upsmr, upsmr);
-
-	/* Disable autonegotiation in tbi mode, because by default it
-	comes up in autonegotiation mode. */
-	/* Note that this depends on proper setting in utbipar register. */
-	if ((ugeth->phy_interface == PHY_INTERFACE_MODE_TBI) ||
-	    (ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) {
-		struct ucc_geth_info *ug_info = ugeth->ug_info;
-		struct phy_device *tbiphy;
-
-		if (!ug_info->tbi_node)
-			pr_warn("TBI mode requires that the device tree specify a tbi-handle\n");
-
-		tbiphy = of_phy_find_device(ug_info->tbi_node);
-		if (!tbiphy)
-			pr_warn("Could not get TBI device\n");
-
-		value = phy_read(tbiphy, ENET_TBI_MII_CR);
-		value &= ~0x1000;	/* Turn off autonegotiation */
-		phy_write(tbiphy, ENET_TBI_MII_CR, value);
-
-		put_device(&tbiphy->mdio.dev);
-	}
-
-	init_check_frame_length_mode(ug_info->lengthCheckRx, &ug_regs->maccfg2);
-
-	ret_val = init_preamble_length(ug_info->prel, &ug_regs->maccfg2);
-	if (ret_val != 0) {
-		if (netif_msg_probe(ugeth))
-			pr_err("Preamble length must be between 3 and 7 inclusive\n");
-		return ret_val;
-	}
-
-	return 0;
+	return phy_interface_mode_is_rgmii(interface) ||
+	       interface == PHY_INTERFACE_MODE_RMII ||
+	       interface == PHY_INTERFACE_MODE_RTBI;
 }
 
 static int ugeth_graceful_stop_tx(struct ucc_geth_private *ugeth)
@@ -1545,108 +1434,7 @@ static void ugeth_activate(struct ucc_geth_private *ugeth)
 
 	/* allow to xmit again  */
 	netif_tx_wake_all_queues(ugeth->ndev);
-	__netdev_watchdog_up(ugeth->ndev);
-}
-
-/* Called every time the controller might need to be made
- * aware of new link state.  The PHY code conveys this
- * information through variables in the ugeth structure, and this
- * function converts those variables into the appropriate
- * register values, and can bring down the device if needed.
- */
-
-static void adjust_link(struct net_device *dev)
-{
-	struct ucc_geth_private *ugeth = netdev_priv(dev);
-	struct ucc_geth __iomem *ug_regs;
-	struct ucc_fast __iomem *uf_regs;
-	struct phy_device *phydev = ugeth->phydev;
-	int new_state = 0;
-
-	ug_regs = ugeth->ug_regs;
-	uf_regs = ugeth->uccf->uf_regs;
-
-	if (phydev->link) {
-		u32 tempval = in_be32(&ug_regs->maccfg2);
-		u32 upsmr = in_be32(&uf_regs->upsmr);
-		/* Now we make sure that we can be in full duplex mode.
-		 * If not, we operate in half-duplex mode. */
-		if (phydev->duplex != ugeth->oldduplex) {
-			new_state = 1;
-			if (!(phydev->duplex))
-				tempval &= ~(MACCFG2_FDX);
-			else
-				tempval |= MACCFG2_FDX;
-			ugeth->oldduplex = phydev->duplex;
-		}
-
-		if (phydev->speed != ugeth->oldspeed) {
-			new_state = 1;
-			switch (phydev->speed) {
-			case SPEED_1000:
-				tempval = ((tempval &
-					    ~(MACCFG2_INTERFACE_MODE_MASK)) |
-					    MACCFG2_INTERFACE_MODE_BYTE);
-				break;
-			case SPEED_100:
-			case SPEED_10:
-				tempval = ((tempval &
-					    ~(MACCFG2_INTERFACE_MODE_MASK)) |
-					    MACCFG2_INTERFACE_MODE_NIBBLE);
-				/* if reduced mode, re-set UPSMR.R10M */
-				if ((ugeth->phy_interface == PHY_INTERFACE_MODE_RMII) ||
-				    (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII) ||
-				    (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_ID) ||
-				    (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
-				    (ugeth->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) ||
-				    (ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) {
-					if (phydev->speed == SPEED_10)
-						upsmr |= UCC_GETH_UPSMR_R10M;
-					else
-						upsmr &= ~UCC_GETH_UPSMR_R10M;
-				}
-				break;
-			default:
-				if (netif_msg_link(ugeth))
-					pr_warn(
-						"%s: Ack!  Speed (%d) is not 10/100/1000!",
-						dev->name, phydev->speed);
-				break;
-			}
-			ugeth->oldspeed = phydev->speed;
-		}
-
-		if (!ugeth->oldlink) {
-			new_state = 1;
-			ugeth->oldlink = 1;
-		}
-
-		if (new_state) {
-			/*
-			 * To change the MAC configuration we need to disable
-			 * the controller. To do so, we have to either grab
-			 * ugeth->lock, which is a bad idea since 'graceful
-			 * stop' commands might take quite a while, or we can
-			 * quiesce driver's activity.
-			 */
-			ugeth_quiesce(ugeth);
-			ugeth_disable(ugeth, COMM_DIR_RX_AND_TX);
-
-			out_be32(&ug_regs->maccfg2, tempval);
-			out_be32(&uf_regs->upsmr, upsmr);
-
-			ugeth_enable(ugeth, COMM_DIR_RX_AND_TX);
-			ugeth_activate(ugeth);
-		}
-	} else if (ugeth->oldlink) {
-			new_state = 1;
-			ugeth->oldlink = 0;
-			ugeth->oldspeed = 0;
-			ugeth->oldduplex = -1;
-	}
-
-	if (new_state && netif_msg_link(ugeth))
-		phy_print_status(phydev);
+	netdev_watchdog_up(ugeth->ndev);
 }
 
 /* Initialize TBI PHY interface for communicating with the
@@ -1664,8 +1452,7 @@ static void uec_configure_serdes(struct net_device *dev)
 	struct phy_device *tbiphy;
 
 	if (!ug_info->tbi_node) {
-		dev_warn(&dev->dev, "SGMII mode requires that the device "
-			"tree specify a tbi-handle\n");
+		dev_warn(&dev->dev, "SGMII mode requires that the device tree specify a tbi-handle\n");
 		return;
 	}
 
@@ -1696,34 +1483,145 @@ static void uec_configure_serdes(struct net_device *dev)
 	put_device(&tbiphy->mdio.dev);
 }
 
-/* Configure the PHY for dev.
- * returns 0 if success.  -1 if failure
- */
-static int init_phy(struct net_device *dev)
+static void ugeth_mac_link_up(struct phylink_config *config, struct phy_device *phy,
+			      unsigned int mode, phy_interface_t interface,
+			      int speed, int duplex, bool tx_pause, bool rx_pause)
 {
-	struct ucc_geth_private *priv = netdev_priv(dev);
-	struct ucc_geth_info *ug_info = priv->ug_info;
-	struct phy_device *phydev;
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct ucc_geth_private *ugeth = netdev_priv(ndev);
+	struct ucc_geth_info *ug_info = ugeth->ug_info;
+	struct ucc_geth __iomem *ug_regs = ugeth->ug_regs;
+	struct ucc_fast __iomem *uf_regs = ugeth->uccf->uf_regs;
+	u32 old_maccfg2, maccfg2 = in_be32(&ug_regs->maccfg2);
+	u32 old_upsmr, upsmr = in_be32(&uf_regs->upsmr);
 
-	priv->oldlink = 0;
-	priv->oldspeed = 0;
-	priv->oldduplex = -1;
+	old_maccfg2 = maccfg2;
+	old_upsmr = upsmr;
 
-	phydev = of_phy_connect(dev, ug_info->phy_node, &adjust_link, 0,
-				priv->phy_interface);
-	if (!phydev) {
-		dev_err(&dev->dev, "Could not attach to PHY\n");
-		return -ENODEV;
+	/* No length check */
+	maccfg2 &= ~MACCFG2_LC;
+	maccfg2 &= ~MACCFG2_INTERFACE_MODE_MASK;
+	upsmr &= ~(UCC_GETH_UPSMR_RPM | UCC_GETH_UPSMR_R10M |
+		   UCC_GETH_UPSMR_TBIM | UCC_GETH_UPSMR_RMM);
+
+	if (speed == SPEED_10 || speed == SPEED_100)
+		maccfg2 |= MACCFG2_INTERFACE_MODE_NIBBLE;
+	else if (speed == SPEED_1000)
+		maccfg2 |= MACCFG2_INTERFACE_MODE_BYTE;
+
+	maccfg2 |= ug_info->padAndCrc;
+
+	if (phy_interface_mode_is_reduced(interface)) {
+
+		if (interface != PHY_INTERFACE_MODE_RMII)
+			upsmr |= UCC_GETH_UPSMR_RPM;
+
+		switch (speed) {
+		case SPEED_10:
+			upsmr |= UCC_GETH_UPSMR_R10M;
+			fallthrough;
+		case SPEED_100:
+			if (interface != PHY_INTERFACE_MODE_RTBI)
+				upsmr |= UCC_GETH_UPSMR_RMM;
+		}
 	}
 
-	if (priv->phy_interface == PHY_INTERFACE_MODE_SGMII)
-		uec_configure_serdes(dev);
+	if (interface == PHY_INTERFACE_MODE_TBI ||
+	    interface == PHY_INTERFACE_MODE_RTBI)
+		upsmr |= UCC_GETH_UPSMR_TBIM;
 
-	phy_set_max_speed(phydev, priv->max_speed);
+	if (interface == PHY_INTERFACE_MODE_SGMII)
+		upsmr |= UCC_GETH_UPSMR_SGMM;
 
-	priv->phydev = phydev;
+	if (duplex == DUPLEX_HALF)
+		maccfg2 &= ~(MACCFG2_FDX);
+	else
+		maccfg2 |= MACCFG2_FDX;
 
-	return 0;
+	if (maccfg2 != old_maccfg2 || upsmr != old_upsmr) {
+		/*
+		 * To change the MAC configuration we need to disable
+		 * the controller. To do so, we have to either grab
+		 * ugeth->lock, which is a bad idea since 'graceful
+		 * stop' commands might take quite a while, or we can
+		 * quiesce driver's activity.
+		 */
+		ugeth_quiesce(ugeth);
+		ugeth_disable(ugeth, COMM_DIR_RX_AND_TX);
+
+		out_be32(&ug_regs->maccfg2, maccfg2);
+		out_be32(&uf_regs->upsmr, upsmr);
+
+		ugeth_enable(ugeth, COMM_DIR_RX_AND_TX);
+		ugeth_activate(ugeth);
+	}
+
+	if (interface == PHY_INTERFACE_MODE_SGMII)
+		uec_configure_serdes(ndev);
+
+	if (!phylink_autoneg_inband(mode)) {
+		ug_info->aufc = 0;
+		ug_info->receiveFlowControl = rx_pause;
+		ug_info->transmitFlowControl = tx_pause;
+
+		init_flow_control_params(ug_info->aufc,
+					 ug_info->receiveFlowControl,
+					 ug_info->transmitFlowControl,
+					 ug_info->pausePeriod,
+					 ug_info->extensionField,
+					 &ugeth->uccf->uf_regs->upsmr,
+					 &ugeth->ug_regs->uempr,
+					 &ugeth->ug_regs->maccfg1);
+	}
+
+	ugeth_enable(ugeth, COMM_DIR_RX_AND_TX);
+}
+
+static void ugeth_mac_link_down(struct phylink_config *config,
+				unsigned int mode, phy_interface_t interface)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct ucc_geth_private *ugeth = netdev_priv(ndev);
+
+	ugeth_disable(ugeth, COMM_DIR_RX_AND_TX);
+}
+
+static void ugeth_mac_config(struct phylink_config *config, unsigned int mode,
+			     const struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct ucc_geth_private *ugeth = netdev_priv(ndev);
+	struct ucc_geth_info *ug_info = ugeth->ug_info;
+	u16 value;
+
+	if (state->interface == PHY_INTERFACE_MODE_TBI ||
+	    state->interface == PHY_INTERFACE_MODE_RTBI) {
+		struct phy_device *tbiphy;
+
+		if (!ug_info->tbi_node)
+			pr_warn("TBI mode requires that the device tree specify a tbi-handle\n");
+
+		tbiphy = of_phy_find_device(ug_info->tbi_node);
+		if (!tbiphy)
+			pr_warn("Could not get TBI device\n");
+
+		value = phy_read(tbiphy, ENET_TBI_MII_CR);
+		value &= ~0x1000;	/* Turn off autonegotiation */
+		phy_write(tbiphy, ENET_TBI_MII_CR, value);
+
+		put_device(&tbiphy->mdio.dev);
+	}
+
+	if (phylink_autoneg_inband(mode)) {
+		ug_info->aufc = 1;
+
+		init_flow_control_params(ug_info->aufc, 1, 1,
+					 ug_info->pausePeriod,
+					 ug_info->extensionField,
+					 &ugeth->uccf->uf_regs->upsmr,
+					 &ugeth->ug_regs->uempr,
+					 &ugeth->ug_regs->maccfg1);
+	}
 }
 
 static void ugeth_dump_regs(struct ucc_geth_private *ugeth)
@@ -1995,7 +1893,6 @@ static void ucc_geth_set_multi(struct net_device *dev)
 static void ucc_geth_stop(struct ucc_geth_private *ugeth)
 {
 	struct ucc_geth __iomem *ug_regs = ugeth->ug_regs;
-	struct phy_device *phydev = ugeth->phydev;
 
 	ugeth_vdbg("%s: IN", __func__);
 
@@ -2004,7 +1901,7 @@ static void ucc_geth_stop(struct ucc_geth_private *ugeth)
 	 * Must be done before disabling the controller
 	 * or deadlock may happen.
 	 */
-	phy_stop(phydev);
+	phylink_stop(ugeth->phylink);
 
 	/* Disable the controller */
 	ugeth_disable(ugeth, COMM_DIR_RX_AND_TX);
@@ -3246,12 +3143,6 @@ static int ucc_geth_init_mac(struct ucc_geth_private *ugeth)
 		goto err;
 	}
 
-	err = adjust_enet_interface(ugeth);
-	if (err) {
-		netif_err(ugeth, ifup, dev, "Cannot configure net device, aborting\n");
-		goto err;
-	}
-
 	/*       Set MACSTNADDR1, MACSTNADDR2                */
 	/* For more details see the hardware spec.           */
 	init_mac_station_addr_regs(dev->dev_addr[0],
@@ -3263,12 +3154,6 @@ static int ucc_geth_init_mac(struct ucc_geth_private *ugeth)
 				   &ugeth->ug_regs->macstnaddr1,
 				   &ugeth->ug_regs->macstnaddr2);
 
-	err = ugeth_enable(ugeth, COMM_DIR_RX_AND_TX);
-	if (err) {
-		netif_err(ugeth, ifup, dev, "Cannot enable net device, aborting\n");
-		goto err;
-	}
-
 	return 0;
 err:
 	ucc_geth_stop(ugeth);
@@ -3291,10 +3176,10 @@ static int ucc_geth_open(struct net_device *dev)
 		return -EINVAL;
 	}
 
-	err = init_phy(dev);
+	err = phylink_of_phy_connect(ugeth->phylink, ugeth->dev->of_node, 0);
 	if (err) {
-		netif_err(ugeth, ifup, dev, "Cannot initialize PHY, aborting\n");
-		return err;
+		dev_err(&dev->dev, "Could not attach to PHY\n");
+		return -ENODEV;
 	}
 
 	err = ucc_geth_init_mac(ugeth);
@@ -3310,13 +3195,13 @@ static int ucc_geth_open(struct net_device *dev)
 		goto err;
 	}
 
-	phy_start(ugeth->phydev);
+	phylink_start(ugeth->phylink);
 	napi_enable(&ugeth->napi);
 	netdev_reset_queue(dev);
 	netif_start_queue(dev);
 
 	device_set_wakeup_capable(&dev->dev,
-			qe_alive_during_sleep() || ugeth->phydev->irq);
+			qe_alive_during_sleep() || dev->phydev->irq);
 	device_set_wakeup_enable(&dev->dev, ugeth->wol_en);
 
 	return err;
@@ -3337,8 +3222,7 @@ static int ucc_geth_close(struct net_device *dev)
 
 	cancel_work_sync(&ugeth->timeout_work);
 	ucc_geth_stop(ugeth);
-	phy_disconnect(ugeth->phydev);
-	ugeth->phydev = NULL;
+	phylink_disconnect_phy(ugeth->phylink);
 
 	free_irq(ugeth->ug_info->uf_info.irq, ugeth->ndev);
 
@@ -3372,7 +3256,7 @@ static void ucc_geth_timeout_work(struct work_struct *work)
 		ucc_geth_stop(ugeth);
 		ucc_geth_init_mac(ugeth);
 		/* Must start PHY here */
-		phy_start(ugeth->phydev);
+		phylink_start(ugeth->phylink);
 		netif_tx_start_all_queues(dev);
 	}
 
@@ -3397,6 +3281,7 @@ static int ucc_geth_suspend(struct platform_device *ofdev, pm_message_t state)
 {
 	struct net_device *ndev = platform_get_drvdata(ofdev);
 	struct ucc_geth_private *ugeth = netdev_priv(ndev);
+	bool mac_wol = false;
 
 	if (!netif_running(ndev))
 		return 0;
@@ -3410,14 +3295,17 @@ static int ucc_geth_suspend(struct platform_device *ofdev, pm_message_t state)
 	 */
 	ugeth_disable(ugeth, COMM_DIR_RX_AND_TX);
 
-	if (ugeth->wol_en & WAKE_MAGIC) {
+	if (ugeth->wol_en & WAKE_MAGIC && !ugeth->phy_wol_en) {
 		setbits32(ugeth->uccf->p_uccm, UCC_GETH_UCCE_MPD);
 		setbits32(&ugeth->ug_regs->maccfg2, MACCFG2_MPE);
 		ucc_fast_enable(ugeth->uccf, COMM_DIR_RX_AND_TX);
-	} else if (!(ugeth->wol_en & WAKE_PHY)) {
-		phy_stop(ugeth->phydev);
+		mac_wol = true;
 	}
 
+	rtnl_lock();
+	phylink_suspend(ugeth->phylink, mac_wol);
+	rtnl_unlock();
+
 	return 0;
 }
 
@@ -3451,12 +3339,9 @@ static int ucc_geth_resume(struct platform_device *ofdev)
 		}
 	}
 
-	ugeth->oldlink = 0;
-	ugeth->oldspeed = 0;
-	ugeth->oldduplex = -1;
-
-	phy_stop(ugeth->phydev);
-	phy_start(ugeth->phydev);
+	rtnl_lock();
+	phylink_resume(ugeth->phylink);
+	rtnl_unlock();
 
 	napi_enable(&ugeth->napi);
 	netif_device_attach(ndev);
@@ -3469,32 +3354,6 @@ static int ucc_geth_resume(struct platform_device *ofdev)
 #define ucc_geth_resume NULL
 #endif
 
-static phy_interface_t to_phy_interface(const char *phy_connection_type)
-{
-	if (strcasecmp(phy_connection_type, "mii") == 0)
-		return PHY_INTERFACE_MODE_MII;
-	if (strcasecmp(phy_connection_type, "gmii") == 0)
-		return PHY_INTERFACE_MODE_GMII;
-	if (strcasecmp(phy_connection_type, "tbi") == 0)
-		return PHY_INTERFACE_MODE_TBI;
-	if (strcasecmp(phy_connection_type, "rmii") == 0)
-		return PHY_INTERFACE_MODE_RMII;
-	if (strcasecmp(phy_connection_type, "rgmii") == 0)
-		return PHY_INTERFACE_MODE_RGMII;
-	if (strcasecmp(phy_connection_type, "rgmii-id") == 0)
-		return PHY_INTERFACE_MODE_RGMII_ID;
-	if (strcasecmp(phy_connection_type, "rgmii-txid") == 0)
-		return PHY_INTERFACE_MODE_RGMII_TXID;
-	if (strcasecmp(phy_connection_type, "rgmii-rxid") == 0)
-		return PHY_INTERFACE_MODE_RGMII_RXID;
-	if (strcasecmp(phy_connection_type, "rtbi") == 0)
-		return PHY_INTERFACE_MODE_RTBI;
-	if (strcasecmp(phy_connection_type, "sgmii") == 0)
-		return PHY_INTERFACE_MODE_SGMII;
-
-	return PHY_INTERFACE_MODE_MII;
-}
-
 static int ucc_geth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct ucc_geth_private *ugeth = netdev_priv(dev);
@@ -3502,10 +3361,7 @@ static int ucc_geth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (!ugeth->phydev)
-		return -ENODEV;
-
-	return phy_mii_ioctl(ugeth->phydev, rq, cmd);
+	return phylink_mii_ioctl(ugeth->phylink, rq, cmd);
 }
 
 static const struct net_device_ops ucc_geth_netdev_ops = {
@@ -3513,7 +3369,6 @@ static const struct net_device_ops ucc_geth_netdev_ops = {
 	.ndo_stop		= ucc_geth_close,
 	.ndo_start_xmit		= ucc_geth_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_change_carrier     = fixed_phy_change_carrier,
 	.ndo_set_mac_address	= ucc_geth_set_mac_addr,
 	.ndo_set_rx_mode	= ucc_geth_set_multi,
 	.ndo_tx_timeout		= ucc_geth_timeout,
@@ -3553,6 +3408,12 @@ static int ucc_geth_parse_clock(struct device_node *np, const char *which,
 	return 0;
 }
 
+static const struct phylink_mac_ops ugeth_mac_ops = {
+	.mac_link_up = ugeth_mac_link_up,
+	.mac_link_down = ugeth_mac_link_down,
+	.mac_config = ugeth_mac_config,
+};
+
 static int ucc_geth_probe(struct platform_device* ofdev)
 {
 	struct device *device = &ofdev->dev;
@@ -3560,23 +3421,12 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	struct net_device *dev = NULL;
 	struct ucc_geth_private *ugeth = NULL;
 	struct ucc_geth_info *ug_info;
+	struct device_node *phy_node;
+	struct phylink *phylink;
 	struct resource res;
-	int err, ucc_num, max_speed = 0;
+	int err, ucc_num;
 	const unsigned int *prop;
 	phy_interface_t phy_interface;
-	static const int enet_to_speed[] = {
-		SPEED_10, SPEED_10, SPEED_10,
-		SPEED_100, SPEED_100, SPEED_100,
-		SPEED_1000, SPEED_1000, SPEED_1000, SPEED_1000,
-	};
-	static const phy_interface_t enet_to_phy_interface[] = {
-		PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_RMII,
-		PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_MII,
-		PHY_INTERFACE_MODE_RMII, PHY_INTERFACE_MODE_RGMII,
-		PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_RGMII,
-		PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_RTBI,
-		PHY_INTERFACE_MODE_SGMII,
-	};
 
 	ugeth_vdbg("%s: IN", __func__);
 
@@ -3612,57 +3462,35 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	ug_info->uf_info.regs = res.start;
 	ug_info->uf_info.irq = irq_of_parse_and_map(np, 0);
 
-	ug_info->phy_node = of_parse_phandle(np, "phy-handle", 0);
-	if (!ug_info->phy_node && of_phy_is_fixed_link(np)) {
-		/*
-		 * In the case of a fixed PHY, the DT node associated
-		 * to the PHY is the Ethernet MAC DT node.
-		 */
-		err = of_phy_register_fixed_link(np);
-		if (err)
-			return err;
-		ug_info->phy_node = of_node_get(np);
-	}
-
 	/* Find the TBI PHY node.  If it's not there, we don't support SGMII */
 	ug_info->tbi_node = of_parse_phandle(np, "tbi-handle", 0);
 
-	/* get the phy interface type, or default to MII */
-	prop = of_get_property(np, "phy-connection-type", NULL);
-	if (!prop) {
-		/* handle interface property present in old trees */
-		prop = of_get_property(ug_info->phy_node, "interface", NULL);
-		if (prop != NULL) {
-			phy_interface = enet_to_phy_interface[*prop];
-			max_speed = enet_to_speed[*prop];
-		} else
-			phy_interface = PHY_INTERFACE_MODE_MII;
-	} else {
-		phy_interface = to_phy_interface((const char *)prop);
-	}
-
-	/* get speed, or derive from PHY interface */
-	if (max_speed == 0)
-		switch (phy_interface) {
-		case PHY_INTERFACE_MODE_GMII:
-		case PHY_INTERFACE_MODE_RGMII:
-		case PHY_INTERFACE_MODE_RGMII_ID:
-		case PHY_INTERFACE_MODE_RGMII_RXID:
-		case PHY_INTERFACE_MODE_RGMII_TXID:
-		case PHY_INTERFACE_MODE_TBI:
-		case PHY_INTERFACE_MODE_RTBI:
-		case PHY_INTERFACE_MODE_SGMII:
-			max_speed = SPEED_1000;
-			break;
-		default:
-			max_speed = SPEED_100;
-			break;
+	phy_node = of_parse_phandle(np, "phy-handle", 0);
+	if (phy_node) {
+		prop = of_get_property(phy_node, "interface", NULL);
+		if (prop) {
+			dev_err(&ofdev->dev,
+				"Device-tree property 'interface' is no longer supported. Please use 'phy-connection-type' instead.");
+			of_node_put(phy_node);
+			err = -EINVAL;
+			goto err_put_tbi;
 		}
+		of_node_put(phy_node);
+	}
+
+	err = of_get_phy_mode(np, &phy_interface);
+	if (err) {
+		dev_err(&ofdev->dev, "Invalid phy-connection-type");
+		goto err_put_tbi;
+	}
 
-	if (max_speed == SPEED_1000) {
+	if (phy_interface == PHY_INTERFACE_MODE_GMII ||
+	    phy_interface_mode_is_rgmii(phy_interface) ||
+	    phy_interface == PHY_INTERFACE_MODE_TBI ||
+	    phy_interface == PHY_INTERFACE_MODE_RTBI ||
+	    phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		unsigned int snums = qe_get_num_of_snums();
 
-		/* configure muram FIFOs for gigabit operation */
 		ug_info->uf_info.urfs = UCC_GETH_URFS_GIGA_INIT;
 		ug_info->uf_info.urfet = UCC_GETH_URFET_GIGA_INIT;
 		ug_info->uf_info.urfset = UCC_GETH_URFSET_GIGA_INIT;
@@ -3691,7 +3519,7 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	dev = devm_alloc_etherdev(&ofdev->dev, sizeof(*ugeth));
 	if (!dev) {
 		err = -ENOMEM;
-		goto err_deregister_fixed_link;
+		goto err_put_tbi;
 	}
 
 	ugeth = netdev_priv(dev);
@@ -3718,23 +3546,50 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	dev->max_mtu = 1518;
 
 	ugeth->msg_enable = netif_msg_init(debug.msg_enable, UGETH_MSG_DEFAULT);
-	ugeth->phy_interface = phy_interface;
-	ugeth->max_speed = max_speed;
 
-	/* Carrier starts down, phylib will bring it up */
-	netif_carrier_off(dev);
+	ugeth->phylink_config.dev = &dev->dev;
+	ugeth->phylink_config.type = PHYLINK_NETDEV;
+
+	ugeth->phylink_config.mac_capabilities =
+		MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD;
+
+	__set_bit(PHY_INTERFACE_MODE_MII,
+		  ugeth->phylink_config.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_RMII,
+		  ugeth->phylink_config.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_GMII,
+		  ugeth->phylink_config.supported_interfaces);
+	phy_interface_set_rgmii(ugeth->phylink_config.supported_interfaces);
+
+	if (ug_info->tbi_node) {
+		__set_bit(PHY_INTERFACE_MODE_SGMII,
+			  ugeth->phylink_config.supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_TBI,
+			  ugeth->phylink_config.supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_RTBI,
+			  ugeth->phylink_config.supported_interfaces);
+	}
+
+	phylink = phylink_create(&ugeth->phylink_config, dev_fwnode(&dev->dev),
+				 phy_interface, &ugeth_mac_ops);
+	if (IS_ERR(phylink)) {
+		err = PTR_ERR(phylink);
+		goto err_put_tbi;
+	}
+
+	ugeth->phylink = phylink;
 
 	err = devm_register_netdev(&ofdev->dev, dev);
 	if (err) {
 		if (netif_msg_probe(ugeth))
 			pr_err("%s: Cannot register net device, aborting\n",
 			       dev->name);
-		goto err_deregister_fixed_link;
+		goto err_destroy_phylink;
 	}
 
 	err = of_get_ethdev_address(np, dev);
 	if (err == -EPROBE_DEFER)
-		goto err_deregister_fixed_link;
+		goto err_destroy_phylink;
 
 	ugeth->ug_info = ug_info;
 	ugeth->dev = device;
@@ -3743,11 +3598,11 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 
 	return 0;
 
-err_deregister_fixed_link:
-	if (of_phy_is_fixed_link(np))
-		of_phy_deregister_fixed_link(np);
+err_destroy_phylink:
+	phylink_destroy(phylink);
+err_put_tbi:
 	of_node_put(ug_info->tbi_node);
-	of_node_put(ug_info->phy_node);
+
 	return err;
 }
 
@@ -3755,13 +3610,10 @@ static void ucc_geth_remove(struct platform_device* ofdev)
 {
 	struct net_device *dev = platform_get_drvdata(ofdev);
 	struct ucc_geth_private *ugeth = netdev_priv(dev);
-	struct device_node *np = ofdev->dev.of_node;
 
 	ucc_geth_memclean(ugeth);
-	if (of_phy_is_fixed_link(np))
-		of_phy_deregister_fixed_link(np);
+	phylink_destroy(ugeth->phylink);
 	of_node_put(ugeth->ug_info->tbi_node);
-	of_node_put(ugeth->ug_info->phy_node);
 }
 
 static const struct of_device_id ucc_geth_match[] = {
diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h
index 4294ed096ebb..84f92f6384e7 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.h
+++ b/drivers/net/ethernet/freescale/ucc_geth.h
@@ -16,6 +16,7 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/phylink.h>
 #include <linux/if_ether.h>
 
 #include <soc/fsl/qe/immap_qe.h>
@@ -889,8 +890,6 @@ struct ucc_geth_hardware_statistics {
 							   addresses */
 
 #define TX_TIMEOUT                              (1*HZ)
-#define PHY_INIT_TIMEOUT                        100000
-#define PHY_CHANGE_TIME                         2
 
 /* Fast Ethernet (10/100 Mbps) */
 #define UCC_GETH_URFS_INIT                      512	/* Rx virtual FIFO size
@@ -921,7 +920,8 @@ struct ucc_geth_hardware_statistics {
 #define UCC_GETH_UPSMR_INIT                     UCC_GETH_UPSMR_RES1
 
 #define UCC_GETH_MACCFG1_INIT                   0
-#define UCC_GETH_MACCFG2_INIT                   (MACCFG2_RESERVED_1)
+#define UCC_GETH_MACCFG2_INIT                   (MACCFG2_RESERVED_1 | \
+						 (7 << MACCFG2_PREL_SHIFT))
 
 /* Ethernet Address Type. */
 enum enet_addr_type {
@@ -1073,6 +1073,9 @@ struct ucc_geth_tad_params {
 	u16 vid;
 };
 
+struct phylink;
+struct phylink_config;
+
 /* GETH protocol initialization structure */
 struct ucc_geth_info {
 	struct ucc_fast_info uf_info;
@@ -1088,7 +1091,6 @@ struct ucc_geth_info {
 	u8 miminumInterFrameGapEnforcement;
 	u8 backToBackInterFrameGap;
 	int ipAddressAlignment;
-	int lengthCheckRx;
 	u32 mblinterval;
 	u16 nortsrbytetime;
 	u8 fracsiz;
@@ -1114,7 +1116,6 @@ struct ucc_geth_info {
 	int transmitFlowControl;
 	u8 maxGroupAddrInHash;
 	u8 maxIndAddrInHash;
-	u8 prel;
 	u16 maxFrameLength;
 	u16 minFrameLength;
 	u16 maxD1Length;
@@ -1125,7 +1126,6 @@ struct ucc_geth_info {
 	u32 eventRegMask;
 	u16 pausePeriod;
 	u16 extensionField;
-	struct device_node *phy_node;
 	struct device_node *tbi_node;
 	u8 weightfactor[NUM_TX_QUEUES];
 	u8 interruptcoalescingmaxvalue[NUM_RX_QUEUES];
@@ -1210,14 +1210,12 @@ struct ucc_geth_private {
 	u16 skb_dirtytx[NUM_TX_QUEUES];
 
 	struct ugeth_mii_info *mii_info;
-	struct phy_device *phydev;
-	phy_interface_t phy_interface;
-	int max_speed;
 	uint32_t msg_enable;
-	int oldspeed;
-	int oldduplex;
-	int oldlink;
-	int wol_en;
+	u32 wol_en;
+	u32 phy_wol_en;
+
+	struct phylink *phylink;
+	struct phylink_config phylink_config;
 
 	struct device_node *node;
 };
diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 699f346faf5c..1fb49e5a414a 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -104,14 +104,8 @@ static int
 uec_get_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd)
 {
 	struct ucc_geth_private *ugeth = netdev_priv(netdev);
-	struct phy_device *phydev = ugeth->phydev;
 
-	if (!phydev)
-		return -ENODEV;
-
-	phy_ethtool_ksettings_get(phydev, cmd);
-
-	return 0;
+	return phylink_ethtool_ksettings_get(ugeth->phylink, cmd);
 }
 
 static int
@@ -119,12 +113,8 @@ uec_set_ksettings(struct net_device *netdev,
 		  const struct ethtool_link_ksettings *cmd)
 {
 	struct ucc_geth_private *ugeth = netdev_priv(netdev);
-	struct phy_device *phydev = ugeth->phydev;
 
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_ksettings_set(phydev, cmd);
+	return phylink_ethtool_ksettings_set(ugeth->phylink, cmd);
 }
 
 static void
@@ -133,12 +123,7 @@ uec_get_pauseparam(struct net_device *netdev,
 {
 	struct ucc_geth_private *ugeth = netdev_priv(netdev);
 
-	pause->autoneg = ugeth->phydev->autoneg;
-
-	if (ugeth->ug_info->receiveFlowControl)
-		pause->rx_pause = 1;
-	if (ugeth->ug_info->transmitFlowControl)
-		pause->tx_pause = 1;
+	return phylink_ethtool_get_pauseparam(ugeth->phylink, pause);
 }
 
 static int
@@ -146,30 +131,11 @@ uec_set_pauseparam(struct net_device *netdev,
                      struct ethtool_pauseparam *pause)
 {
 	struct ucc_geth_private *ugeth = netdev_priv(netdev);
-	int ret = 0;
 
 	ugeth->ug_info->receiveFlowControl = pause->rx_pause;
 	ugeth->ug_info->transmitFlowControl = pause->tx_pause;
 
-	if (ugeth->phydev->autoneg) {
-		if (netif_running(netdev)) {
-			/* FIXME: automatically restart */
-			netdev_info(netdev, "Please re-open the interface\n");
-		}
-	} else {
-		struct ucc_geth_info *ug_info = ugeth->ug_info;
-
-		ret = init_flow_control_params(ug_info->aufc,
-					ug_info->receiveFlowControl,
-					ug_info->transmitFlowControl,
-					ug_info->pausePeriod,
-					ug_info->extensionField,
-					&ugeth->uccf->uf_regs->upsmr,
-					&ugeth->ug_regs->uempr,
-					&ugeth->ug_regs->maccfg1);
-	}
-
-	return ret;
+	return phylink_ethtool_set_pauseparam(ugeth->phylink, pause);
 }
 
 static uint32_t
@@ -343,28 +309,42 @@ uec_get_drvinfo(struct net_device *netdev,
 static void uec_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct ucc_geth_private *ugeth = netdev_priv(netdev);
-	struct phy_device *phydev = ugeth->phydev;
 
-	if (phydev && phydev->irq)
-		wol->supported |= WAKE_PHY;
+	phylink_ethtool_get_wol(ugeth->phylink, wol);
+
 	if (qe_alive_during_sleep())
 		wol->supported |= WAKE_MAGIC;
 
-	wol->wolopts = ugeth->wol_en;
+	wol->wolopts |= ugeth->wol_en;
 }
 
 static int uec_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct ucc_geth_private *ugeth = netdev_priv(netdev);
-	struct phy_device *phydev = ugeth->phydev;
+	int ret = 0;
 
-	if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC))
-		return -EINVAL;
-	else if (wol->wolopts & WAKE_PHY && (!phydev || !phydev->irq))
+	ret = phylink_ethtool_set_wol(ugeth->phylink, wol);
+	if (ret == -EOPNOTSUPP) {
+		ugeth->phy_wol_en = 0;
+	} else if (ret) {
+		return ret;
+	} else {
+		ugeth->phy_wol_en = wol->wolopts;
+		goto out;
+	}
+
+	/* If the PHY isn't handling the WoL and the MAC is asked to more than
+	 * WAKE_MAGIC, error-out
+	 */
+	if (!ugeth->phy_wol_en &&
+	    wol->wolopts & ~WAKE_MAGIC)
 		return -EINVAL;
-	else if (wol->wolopts & WAKE_MAGIC && !qe_alive_during_sleep())
+
+	if (wol->wolopts & WAKE_MAGIC &&
+	    !qe_alive_during_sleep())
 		return -EINVAL;
 
+out:
 	ugeth->wol_en = wol->wolopts;
 	device_set_wakeup_enable(&netdev->dev, ugeth->wol_en);
 
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index dd92949bb214..2fab38c8ee78 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -59,6 +59,8 @@
 
 #define GVE_MAX_RX_BUFFER_SIZE 4096
 
+#define GVE_XDP_RX_BUFFER_SIZE_DQO 4096
+
 #define GVE_DEFAULT_RX_BUFFER_OFFSET 2048
 
 #define GVE_PAGE_POOL_SIZE_MULTIPLIER 4
@@ -68,6 +70,9 @@
 #define GVE_FLOW_RULE_IDS_CACHE_SIZE \
 	(GVE_ADMINQ_BUFFER_SIZE / sizeof(((struct gve_adminq_queried_flow_rule *)0)->location))
 
+#define GVE_RSS_KEY_SIZE	40
+#define GVE_RSS_INDIR_SIZE	128
+
 #define GVE_XDP_ACTIONS 5
 
 #define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182
@@ -102,7 +107,13 @@ struct gve_rx_desc_queue {
 
 /* The page info for a single slot in the RX data queue */
 struct gve_rx_slot_page_info {
-	struct page *page;
+	/* netmem is used for DQO RDA mode
+	 * page is used in all other modes
+	 */
+	union {
+		struct page *page;
+		netmem_ref netmem;
+	};
 	void *page_address;
 	u32 page_offset; /* offset to write to in page */
 	unsigned int buf_size;
@@ -218,6 +229,11 @@ struct gve_rx_cnts {
 /* Contains datapath state used to represent an RX queue. */
 struct gve_rx_ring {
 	struct gve_priv *gve;
+
+	u16 packet_buffer_size;		/* Size of buffer posted to NIC */
+	u16 packet_buffer_truesize;	/* Total size of RX buffer */
+	u16 rx_headroom;
+
 	union {
 		/* GQI fields */
 		struct {
@@ -226,7 +242,6 @@ struct gve_rx_ring {
 
 			/* threshold for posting new buffs and descs */
 			u32 db_threshold;
-			u16 packet_buffer_size;
 
 			u32 qpl_copy_pool_mask;
 			u32 qpl_copy_pool_head;
@@ -604,8 +619,6 @@ struct gve_tx_ring {
 	dma_addr_t complq_bus_dqo; /* dma address of the dqo.compl_ring */
 	struct u64_stats_sync statss; /* sync stats for 32bit archs */
 	struct xsk_buff_pool *xsk_pool;
-	u32 xdp_xsk_wakeup;
-	u32 xdp_xsk_done;
 	u64 xdp_xsk_sent;
 	u64 xdp_xmit;
 	u64 xdp_xmit_errors;
@@ -624,10 +637,18 @@ struct gve_notify_block {
 	u32 irq;
 };
 
-/* Tracks allowed and current queue settings */
-struct gve_queue_config {
+/* Tracks allowed and current rx queue settings */
+struct gve_rx_queue_config {
 	u16 max_queues;
-	u16 num_queues; /* current */
+	u16 num_queues;
+	u16 packet_buffer_size;
+};
+
+/* Tracks allowed and current tx queue settings */
+struct gve_tx_queue_config {
+	u16 max_queues;
+	u16 num_queues; /* number of TX queues, excluding XDP queues */
+	u16 num_xdp_queues;
 };
 
 /* Tracks the available and used qpl IDs */
@@ -651,11 +672,11 @@ struct gve_ptype_lut {
 
 /* Parameters for allocating resources for tx queues */
 struct gve_tx_alloc_rings_cfg {
-	struct gve_queue_config *qcfg;
+	struct gve_tx_queue_config *qcfg;
+
+	u16 num_xdp_rings;
 
 	u16 ring_size;
-	u16 start_idx;
-	u16 num_rings;
 	bool raw_addressing;
 
 	/* Allocated resources are returned here */
@@ -665,13 +686,15 @@ struct gve_tx_alloc_rings_cfg {
 /* Parameters for allocating resources for rx queues */
 struct gve_rx_alloc_rings_cfg {
 	/* tx config is also needed to determine QPL ids */
-	struct gve_queue_config *qcfg;
-	struct gve_queue_config *qcfg_tx;
+	struct gve_rx_queue_config *qcfg_rx;
+	struct gve_tx_queue_config *qcfg_tx;
 
 	u16 ring_size;
 	u16 packet_buffer_size;
 	bool raw_addressing;
 	bool enable_header_split;
+	bool reset_rss;
+	bool xdp;
 
 	/* Allocated resources are returned here */
 	struct gve_rx_ring *rx;
@@ -722,6 +745,11 @@ struct gve_flow_rules_cache {
 	u32 rule_ids_cache_num;
 };
 
+struct gve_rss_config {
+	u8 *hash_key;
+	u32 *hash_lut;
+};
+
 struct gve_priv {
 	struct net_device *dev;
 	struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */
@@ -751,9 +779,8 @@ struct gve_priv {
 	u32 rx_copybreak; /* copy packets smaller than this */
 	u16 default_num_queues; /* default num queues to set up */
 
-	u16 num_xdp_queues;
-	struct gve_queue_config tx_cfg;
-	struct gve_queue_config rx_cfg;
+	struct gve_tx_queue_config tx_cfg;
+	struct gve_rx_queue_config rx_cfg;
 	u32 num_ntfy_blks; /* spilt between TX and RX so must be even */
 
 	struct gve_registers __iomem *reg_bar0; /* see gve_register.h */
@@ -823,7 +850,6 @@ struct gve_priv {
 	struct gve_ptype_lut *ptype_lut_dqo;
 
 	/* Must be a power of two. */
-	u16 data_buffer_size_dqo;
 	u16 max_rx_buffer_size; /* device limit */
 
 	enum gve_queue_format queue_format;
@@ -842,6 +868,8 @@ struct gve_priv {
 
 	u16 rss_key_size;
 	u16 rss_lut_size;
+	bool cache_rss_config;
+	struct gve_rss_config rss_config;
 };
 
 enum gve_service_task_flags_bit {
@@ -1024,27 +1052,16 @@ static inline bool gve_is_qpl(struct gve_priv *priv)
 }
 
 /* Returns the number of tx queue page lists */
-static inline u32 gve_num_tx_qpls(const struct gve_queue_config *tx_cfg,
-				  int num_xdp_queues,
+static inline u32 gve_num_tx_qpls(const struct gve_tx_queue_config *tx_cfg,
 				  bool is_qpl)
 {
 	if (!is_qpl)
 		return 0;
-	return tx_cfg->num_queues + num_xdp_queues;
-}
-
-/* Returns the number of XDP tx queue page lists
- */
-static inline u32 gve_num_xdp_qpls(struct gve_priv *priv)
-{
-	if (priv->queue_format != GVE_GQI_QPL_FORMAT)
-		return 0;
-
-	return priv->num_xdp_queues;
+	return tx_cfg->num_queues + tx_cfg->num_xdp_queues;
 }
 
 /* Returns the number of rx queue page lists */
-static inline u32 gve_num_rx_qpls(const struct gve_queue_config *rx_cfg,
+static inline u32 gve_num_rx_qpls(const struct gve_rx_queue_config *rx_cfg,
 				  bool is_qpl)
 {
 	if (!is_qpl)
@@ -1062,7 +1079,8 @@ static inline u32 gve_rx_qpl_id(struct gve_priv *priv, int rx_qid)
 	return priv->tx_cfg.max_queues + rx_qid;
 }
 
-static inline u32 gve_get_rx_qpl_id(const struct gve_queue_config *tx_cfg, int rx_qid)
+static inline u32 gve_get_rx_qpl_id(const struct gve_tx_queue_config *tx_cfg,
+				    int rx_qid)
 {
 	return tx_cfg->max_queues + rx_qid;
 }
@@ -1072,7 +1090,7 @@ static inline u32 gve_tx_start_qpl_id(struct gve_priv *priv)
 	return gve_tx_qpl_id(priv, 0);
 }
 
-static inline u32 gve_rx_start_qpl_id(const struct gve_queue_config *tx_cfg)
+static inline u32 gve_rx_start_qpl_id(const struct gve_tx_queue_config *tx_cfg)
 {
 	return gve_get_rx_qpl_id(tx_cfg, 0);
 }
@@ -1103,7 +1121,7 @@ static inline bool gve_is_gqi(struct gve_priv *priv)
 
 static inline u32 gve_num_tx_queues(struct gve_priv *priv)
 {
-	return priv->tx_cfg.num_queues + priv->num_xdp_queues;
+	return priv->tx_cfg.num_queues + priv->tx_cfg.num_xdp_queues;
 }
 
 static inline u32 gve_xdp_tx_queue_id(struct gve_priv *priv, u32 queue_id)
@@ -1116,6 +1134,16 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv)
 	return gve_xdp_tx_queue_id(priv, 0);
 }
 
+static inline bool gve_supports_xdp_xmit(struct gve_priv *priv)
+{
+	switch (priv->queue_format) {
+	case GVE_GQI_QPL_FORMAT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* gqi napi handler defined in gve_main.c */
 int gve_napi_poll(struct napi_struct *napi, int budget);
 
@@ -1140,6 +1168,7 @@ int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx,
 void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid);
 bool gve_tx_poll(struct gve_notify_block *block, int budget);
 bool gve_xdp_poll(struct gve_notify_block *block, int budget);
+int gve_xsk_tx_poll(struct gve_notify_block *block, int budget);
 int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg);
 void gve_tx_free_rings_gqi(struct gve_priv *priv,
@@ -1196,7 +1225,8 @@ void gve_free_buffer(struct gve_rx_ring *rx,
 		     struct gve_rx_buf_state_dqo *buf_state);
 int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc);
 struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
-					  struct gve_rx_ring *rx);
+					  struct gve_rx_ring *rx,
+					  bool xdp);
 
 /* Reset */
 void gve_schedule_reset(struct gve_priv *priv);
@@ -1208,14 +1238,17 @@ int gve_adjust_config(struct gve_priv *priv,
 		      struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
 		      struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
 int gve_adjust_queues(struct gve_priv *priv,
-		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config);
+		      struct gve_rx_queue_config new_rx_config,
+		      struct gve_tx_queue_config new_tx_config,
+		      bool reset_rss);
 /* flow steering rule */
 int gve_get_flow_rule_entry(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_get_flow_rule_ids(struct gve_priv *priv, struct ethtool_rxnfc *cmd, u32 *rule_locs);
 int gve_add_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_del_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_flow_rules_reset(struct gve_priv *priv);
+/* RSS config */
+int gve_init_rss_config(struct gve_priv *priv, u16 num_queues);
 /* report stats handling */
 void gve_handle_report_stats(struct gve_priv *priv);
 /* exported by ethtool.c */
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index 060e0e674938..3e8fc33cc11f 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -731,6 +731,7 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 		.ntfy_id = cpu_to_be32(rx->ntfy_id),
 		.queue_resources_addr = cpu_to_be64(rx->q_resources_bus),
 		.rx_ring_size = cpu_to_be16(priv->rx_desc_cnt),
+		.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size),
 	};
 
 	if (gve_is_gqi(priv)) {
@@ -743,7 +744,6 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 			cpu_to_be64(rx->data.data_bus);
 		cmd->create_rx_queue.index = cpu_to_be32(queue_index);
 		cmd->create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
-		cmd->create_rx_queue.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size);
 	} else {
 		u32 qpl_id = 0;
 
@@ -756,8 +756,6 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 			cpu_to_be64(rx->dqo.complq.bus);
 		cmd->create_rx_queue.rx_data_ring_addr =
 			cpu_to_be64(rx->dqo.bufq.bus);
-		cmd->create_rx_queue.packet_buffer_size =
-			cpu_to_be16(priv->data_buffer_size_dqo);
 		cmd->create_rx_queue.rx_buff_ring_size =
 			cpu_to_be16(priv->rx_desc_cnt);
 		cmd->create_rx_queue.enable_rsc =
@@ -885,6 +883,15 @@ static void gve_set_default_desc_cnt(struct gve_priv *priv,
 	priv->min_rx_desc_cnt = priv->rx_desc_cnt;
 }
 
+static void gve_set_default_rss_sizes(struct gve_priv *priv)
+{
+	if (!gve_is_gqi(priv)) {
+		priv->rss_key_size = GVE_RSS_KEY_SIZE;
+		priv->rss_lut_size = GVE_RSS_INDIR_SIZE;
+		priv->cache_rss_config = true;
+	}
+}
+
 static void gve_enable_supported_features(struct gve_priv *priv,
 					  u32 supported_features_mask,
 					  const struct gve_device_option_jumbo_frames
@@ -968,6 +975,10 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 			be16_to_cpu(dev_op_rss_config->hash_key_size);
 		priv->rss_lut_size =
 			be16_to_cpu(dev_op_rss_config->hash_lut_size);
+		priv->cache_rss_config = false;
+		dev_dbg(&priv->pdev->dev,
+			"RSS device option enabled with key size of %u, lut size of %u.\n",
+			priv->rss_key_size, priv->rss_lut_size);
 	}
 }
 
@@ -1052,6 +1063,8 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	/* set default descriptor counts */
 	gve_set_default_desc_cnt(priv, descriptor);
 
+	gve_set_default_rss_sizes(priv);
+
 	/* DQO supports LRO. */
 	if (!gve_is_gqi(priv))
 		priv->dev->hw_features |= NETIF_F_LRO;
@@ -1128,20 +1141,6 @@ int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id)
 	return gve_adminq_execute_cmd(priv, &cmd);
 }
 
-int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu)
-{
-	union gve_adminq_command cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.opcode = cpu_to_be32(GVE_ADMINQ_SET_DRIVER_PARAMETER);
-	cmd.set_driver_param = (struct gve_adminq_set_driver_parameter) {
-		.parameter_type = cpu_to_be32(GVE_SET_PARAM_MTU),
-		.parameter_value = cpu_to_be64(mtu),
-	};
-
-	return gve_adminq_execute_cmd(priv, &cmd);
-}
-
 int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len,
 			    dma_addr_t stats_report_addr, u64 interval)
 {
@@ -1290,8 +1289,9 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv)
 
 int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh)
 {
+	const u32 *hash_lut_to_config = NULL;
+	const u8 *hash_key_to_config = NULL;
 	dma_addr_t lut_bus = 0, key_bus = 0;
-	u16 key_size = 0, lut_size = 0;
 	union gve_adminq_command cmd;
 	__be32 *lut = NULL;
 	u8 hash_alg = 0;
@@ -1301,7 +1301,7 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 
 	switch (rxfh->hfunc) {
 	case ETH_RSS_HASH_NO_CHANGE:
-		break;
+		fallthrough;
 	case ETH_RSS_HASH_TOP:
 		hash_alg = ETH_RSS_HASH_TOP;
 		break;
@@ -1310,27 +1310,46 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 	}
 
 	if (rxfh->indir) {
-		lut_size = priv->rss_lut_size;
+		if (rxfh->indir_size != priv->rss_lut_size)
+			return -EINVAL;
+
+		hash_lut_to_config = rxfh->indir;
+	} else if (priv->cache_rss_config) {
+		hash_lut_to_config = priv->rss_config.hash_lut;
+	}
+
+	if (hash_lut_to_config) {
 		lut = dma_alloc_coherent(&priv->pdev->dev,
-					 lut_size * sizeof(*lut),
+					 priv->rss_lut_size * sizeof(*lut),
 					 &lut_bus, GFP_KERNEL);
 		if (!lut)
 			return -ENOMEM;
 
 		for (i = 0; i < priv->rss_lut_size; i++)
-			lut[i] = cpu_to_be32(rxfh->indir[i]);
+			lut[i] = cpu_to_be32(hash_lut_to_config[i]);
 	}
 
 	if (rxfh->key) {
-		key_size = priv->rss_key_size;
+		if (rxfh->key_size != priv->rss_key_size) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		hash_key_to_config = rxfh->key;
+	} else if (priv->cache_rss_config) {
+		hash_key_to_config = priv->rss_config.hash_key;
+	}
+
+	if (hash_key_to_config) {
 		key = dma_alloc_coherent(&priv->pdev->dev,
-					 key_size, &key_bus, GFP_KERNEL);
+					 priv->rss_key_size,
+					 &key_bus, GFP_KERNEL);
 		if (!key) {
 			err = -ENOMEM;
 			goto out;
 		}
 
-		memcpy(key, rxfh->key, key_size);
+		memcpy(key, hash_key_to_config, priv->rss_key_size);
 	}
 
 	/* Zero-valued fields in the cmd.configure_rss instruct the device to
@@ -1344,8 +1363,10 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 					  BIT(GVE_RSS_HASH_TCPV6) |
 					  BIT(GVE_RSS_HASH_UDPV6)),
 		.hash_alg = hash_alg,
-		.hash_key_size = cpu_to_be16(key_size),
-		.hash_lut_size = cpu_to_be16(lut_size),
+		.hash_key_size =
+			cpu_to_be16((key_bus) ? priv->rss_key_size : 0),
+		.hash_lut_size =
+			cpu_to_be16((lut_bus) ? priv->rss_lut_size : 0),
 		.hash_key_addr = cpu_to_be64(key_bus),
 		.hash_lut_addr = cpu_to_be64(lut_bus),
 	};
@@ -1355,11 +1376,11 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 out:
 	if (lut)
 		dma_free_coherent(&priv->pdev->dev,
-				  lut_size * sizeof(*lut),
+				  priv->rss_lut_size * sizeof(*lut),
 				  lut, lut_bus);
 	if (key)
 		dma_free_coherent(&priv->pdev->dev,
-				  key_size, key, key_bus);
+				  priv->rss_key_size, key, key_bus);
 	return err;
 }
 
@@ -1463,12 +1484,15 @@ static int gve_adminq_process_rss_query(struct gve_priv *priv,
 	rxfh->hfunc = descriptor->hash_alg;
 
 	rss_info_addr = (void *)(descriptor + 1);
-	if (rxfh->key)
+	if (rxfh->key) {
+		rxfh->key_size = priv->rss_key_size;
 		memcpy(rxfh->key, rss_info_addr, priv->rss_key_size);
+	}
 
 	rss_info_addr += priv->rss_key_size;
 	lut = (__be32 *)rss_info_addr;
 	if (rxfh->indir) {
+		rxfh->indir_size = priv->rss_lut_size;
 		for (i = 0; i < priv->rss_lut_size; i++)
 			rxfh->indir[i] = be32_to_cpu(lut[i]);
 	}
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index 863683de9694..228217458275 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -612,7 +612,6 @@ int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id);
 int gve_adminq_register_page_list(struct gve_priv *priv,
 				  struct gve_queue_page_list *qpl);
 int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id);
-int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu);
 int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len,
 			    dma_addr_t stats_report_addr, u64 interval);
 int gve_adminq_verify_driver_compatibility(struct gve_priv *priv,
diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
index 403f0f335ba6..a71883e1d920 100644
--- a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
@@ -139,7 +139,8 @@ int gve_alloc_qpl_page_dqo(struct gve_rx_ring *rx,
 	buf_state->page_info.page_offset = 0;
 	buf_state->page_info.page_address =
 		page_address(buf_state->page_info.page);
-	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
+	buf_state->page_info.buf_size = rx->packet_buffer_truesize;
+	buf_state->page_info.pad = rx->rx_headroom;
 	buf_state->last_single_ref_offset = 0;
 
 	/* The page already has 1 ref. */
@@ -162,7 +163,7 @@ void gve_free_qpl_page_dqo(struct gve_rx_buf_state_dqo *buf_state)
 void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx,
 			 struct gve_rx_buf_state_dqo *buf_state)
 {
-	const u16 data_buffer_size = priv->data_buffer_size_dqo;
+	const u16 data_buffer_size = rx->packet_buffer_truesize;
 	int pagecount;
 
 	/* Can't reuse if we only fit one buffer per page */
@@ -205,38 +206,40 @@ void gve_free_to_page_pool(struct gve_rx_ring *rx,
 			   struct gve_rx_buf_state_dqo *buf_state,
 			   bool allow_direct)
 {
-	struct page *page = buf_state->page_info.page;
+	netmem_ref netmem = buf_state->page_info.netmem;
 
-	if (!page)
+	if (!netmem)
 		return;
 
-	page_pool_put_full_page(page->pp, page, allow_direct);
-	buf_state->page_info.page = NULL;
+	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, allow_direct);
+	buf_state->page_info.netmem = 0;
 }
 
 static int gve_alloc_from_page_pool(struct gve_rx_ring *rx,
 				    struct gve_rx_buf_state_dqo *buf_state)
 {
-	struct gve_priv *priv = rx->gve;
-	struct page *page;
+	netmem_ref netmem;
 
-	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
-	page = page_pool_alloc(rx->dqo.page_pool,
-			       &buf_state->page_info.page_offset,
-			       &buf_state->page_info.buf_size, GFP_ATOMIC);
+	buf_state->page_info.buf_size = rx->packet_buffer_truesize;
+	netmem = page_pool_alloc_netmem(rx->dqo.page_pool,
+					&buf_state->page_info.page_offset,
+					&buf_state->page_info.buf_size,
+					GFP_ATOMIC);
 
-	if (!page)
+	if (!netmem)
 		return -ENOMEM;
 
-	buf_state->page_info.page = page;
-	buf_state->page_info.page_address = page_address(page);
-	buf_state->addr = page_pool_get_dma_addr(page);
+	buf_state->page_info.netmem = netmem;
+	buf_state->page_info.page_address = netmem_address(netmem);
+	buf_state->addr = page_pool_get_dma_addr_netmem(netmem);
+	buf_state->page_info.pad = rx->dqo.page_pool->p.offset;
 
 	return 0;
 }
 
 struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
-					  struct gve_rx_ring *rx)
+					  struct gve_rx_ring *rx,
+					  bool xdp)
 {
 	u32 ntfy_id = gve_rx_idx_to_ntfy(priv, rx->q_num);
 	struct page_pool_params pp = {
@@ -247,7 +250,8 @@ struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
 		.netdev = priv->dev,
 		.napi = &priv->ntfy_blocks[ntfy_id].napi,
 		.max_len = PAGE_SIZE,
-		.dma_dir = DMA_FROM_DEVICE,
+		.dma_dir = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
+		.offset = xdp ? XDP_PACKET_HEADROOM : 0,
 	};
 
 	return page_pool_create(&pp);
@@ -269,7 +273,7 @@ void gve_reuse_buffer(struct gve_rx_ring *rx,
 		      struct gve_rx_buf_state_dqo *buf_state)
 {
 	if (rx->dqo.page_pool) {
-		buf_state->page_info.page = NULL;
+		buf_state->page_info.netmem = 0;
 		gve_free_buf_state(rx, buf_state);
 	} else {
 		gve_dec_pagecnt_bias(&buf_state->page_info);
@@ -301,7 +305,8 @@ int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc)
 	}
 	desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states);
 	desc->buf_addr = cpu_to_le64(buf_state->addr +
-				     buf_state->page_info.page_offset);
+				     buf_state->page_info.page_offset +
+				     buf_state->page_info.pad);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index bdfc6e77b2af..3c1da0cf3f61 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -63,11 +63,11 @@ static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = {
 static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = {
 	"tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_consumed_desc[%u]", "tx_bytes[%u]",
 	"tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]",
-	"tx_dma_mapping_error[%u]", "tx_xsk_wakeup[%u]",
-	"tx_xsk_done[%u]", "tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
+	"tx_dma_mapping_error[%u]",
+	"tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
 };
 
-static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
+static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] __nonstring_array = {
 	"adminq_prod_cnt", "adminq_cmd_fail", "adminq_timeouts",
 	"adminq_describe_device_cnt", "adminq_cfg_device_resources_cnt",
 	"adminq_register_page_list_cnt", "adminq_unregister_page_list_cnt",
@@ -113,7 +113,7 @@ static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 						i);
 
 		for (i = 0; i < ARRAY_SIZE(gve_gstrings_adminq_stats); i++)
-			ethtool_puts(&s, gve_gstrings_adminq_stats[i]);
+			ethtool_cpy(&s, gve_gstrings_adminq_stats[i]);
 
 		break;
 
@@ -392,7 +392,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 				 */
 				data[i++] = 0;
 				data[i++] = 0;
-				data[i++] = tx->dqo_tx.tail - tx->dqo_tx.head;
+				data[i++] =
+					(tx->dqo_tx.tail - tx->dqo_tx.head) &
+					tx->mask;
 			}
 			do {
 				start =
@@ -417,9 +419,7 @@ gve_get_ethtool_stats(struct net_device *netdev,
 					data[i++] = value;
 				}
 			}
-			/* XDP xsk counters */
-			data[i++] = tx->xdp_xsk_wakeup;
-			data[i++] = tx->xdp_xsk_done;
+			/* XDP counters */
 			do {
 				start = u64_stats_fetch_begin(&priv->tx[ring].statss);
 				data[i] = tx->xdp_xsk_sent;
@@ -477,11 +477,12 @@ static int gve_set_channels(struct net_device *netdev,
 			    struct ethtool_channels *cmd)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
-	struct gve_queue_config new_tx_cfg = priv->tx_cfg;
-	struct gve_queue_config new_rx_cfg = priv->rx_cfg;
+	struct gve_tx_queue_config new_tx_cfg = priv->tx_cfg;
+	struct gve_rx_queue_config new_rx_cfg = priv->rx_cfg;
 	struct ethtool_channels old_settings;
 	int new_tx = cmd->tx_count;
 	int new_rx = cmd->rx_count;
+	bool reset_rss = false;
 
 	gve_get_channels(netdev, &old_settings);
 
@@ -492,22 +493,27 @@ static int gve_set_channels(struct net_device *netdev,
 	if (!new_rx || !new_tx)
 		return -EINVAL;
 
-	if (priv->num_xdp_queues &&
-	    (new_tx != new_rx || (2 * new_tx > priv->tx_cfg.max_queues))) {
-		dev_err(&priv->pdev->dev, "XDP load failed: The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues");
-		return -EINVAL;
-	}
+	if (priv->xdp_prog) {
+		if (new_tx != new_rx ||
+		    (2 * new_tx > priv->tx_cfg.max_queues)) {
+			dev_err(&priv->pdev->dev, "The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues when XDP program is installed");
+			return -EINVAL;
+		}
 
-	if (!netif_running(netdev)) {
-		priv->tx_cfg.num_queues = new_tx;
-		priv->rx_cfg.num_queues = new_rx;
-		return 0;
+		/* One XDP TX queue per RX queue. */
+		new_tx_cfg.num_xdp_queues = new_rx;
+	} else {
+		new_tx_cfg.num_xdp_queues = 0;
 	}
 
+	if (new_rx != priv->rx_cfg.num_queues &&
+	    priv->cache_rss_config && !netif_is_rxfh_configured(netdev))
+		reset_rss = true;
+
 	new_tx_cfg.num_queues = new_tx;
 	new_rx_cfg.num_queues = new_rx;
 
-	return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg);
+	return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg, reset_rss);
 }
 
 static void gve_get_ringparam(struct net_device *netdev,
@@ -643,8 +649,7 @@ static int gve_set_tunable(struct net_device *netdev,
 	switch (etuna->id) {
 	case ETHTOOL_RX_COPYBREAK:
 	{
-		u32 max_copybreak = gve_is_gqi(priv) ?
-			GVE_DEFAULT_RX_BUFFER_SIZE : priv->data_buffer_size_dqo;
+		u32 max_copybreak = priv->rx_cfg.packet_buffer_size;
 
 		len = *(u32 *)value;
 		if (len > max_copybreak)
@@ -700,7 +705,7 @@ static int gve_set_priv_flags(struct net_device *netdev, u32 flags)
 
 		memset(priv->stats_report->stats, 0, (tx_stats_num + rx_stats_num) *
 				   sizeof(struct stats));
-		del_timer_sync(&priv->stats_report_timer);
+		timer_delete_sync(&priv->stats_report_timer);
 	}
 	return 0;
 }
@@ -855,6 +860,25 @@ static u32 gve_get_rxfh_indir_size(struct net_device *netdev)
 	return priv->rss_lut_size;
 }
 
+static void gve_get_rss_config_cache(struct gve_priv *priv,
+				     struct ethtool_rxfh_param *rxfh)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+
+	if (rxfh->key) {
+		rxfh->key_size = priv->rss_key_size;
+		memcpy(rxfh->key, rss_config->hash_key, priv->rss_key_size);
+	}
+
+	if (rxfh->indir) {
+		rxfh->indir_size = priv->rss_lut_size;
+		memcpy(rxfh->indir, rss_config->hash_lut,
+		       priv->rss_lut_size * sizeof(*rxfh->indir));
+	}
+}
+
 static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
@@ -862,18 +886,46 @@ static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rx
 	if (!priv->rss_key_size || !priv->rss_lut_size)
 		return -EOPNOTSUPP;
 
+	if (priv->cache_rss_config) {
+		gve_get_rss_config_cache(priv, rxfh);
+		return 0;
+	}
+
 	return gve_adminq_query_rss_config(priv, rxfh);
 }
 
+static void gve_set_rss_config_cache(struct gve_priv *priv,
+				     struct ethtool_rxfh_param *rxfh)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	if (rxfh->key)
+		memcpy(rss_config->hash_key, rxfh->key, priv->rss_key_size);
+
+	if (rxfh->indir)
+		memcpy(rss_config->hash_lut, rxfh->indir,
+		       priv->rss_lut_size * sizeof(*rxfh->indir));
+}
+
 static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
 			struct netlink_ext_ack *extack)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
+	int err;
 
 	if (!priv->rss_key_size || !priv->rss_lut_size)
 		return -EOPNOTSUPP;
 
-	return gve_adminq_configure_rss(priv, rxfh);
+	err = gve_adminq_configure_rss(priv, rxfh);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Fail to configure RSS config");
+		return err;
+	}
+
+	if (priv->cache_rss_config)
+		gve_set_rss_config_cache(priv, rxfh);
+
+	return 0;
 }
 
 const struct ethtool_ops gve_ethtool_ops = {
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index e171ca248f9a..dc35a23ec47f 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -184,6 +184,43 @@ static void gve_free_flow_rule_caches(struct gve_priv *priv)
 	flow_rules_cache->rules_cache = NULL;
 }
 
+static int gve_alloc_rss_config_cache(struct gve_priv *priv)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	if (!priv->cache_rss_config)
+		return 0;
+
+	rss_config->hash_key = kcalloc(priv->rss_key_size,
+				       sizeof(rss_config->hash_key[0]),
+				       GFP_KERNEL);
+	if (!rss_config->hash_key)
+		return -ENOMEM;
+
+	rss_config->hash_lut = kcalloc(priv->rss_lut_size,
+				       sizeof(rss_config->hash_lut[0]),
+				       GFP_KERNEL);
+	if (!rss_config->hash_lut)
+		goto free_rss_key_cache;
+
+	return 0;
+
+free_rss_key_cache:
+	kfree(rss_config->hash_key);
+	rss_config->hash_key = NULL;
+	return -ENOMEM;
+}
+
+static void gve_free_rss_config_cache(struct gve_priv *priv)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	kfree(rss_config->hash_key);
+	kfree(rss_config->hash_lut);
+
+	memset(rss_config, 0, sizeof(*rss_config));
+}
+
 static int gve_alloc_counter_array(struct gve_priv *priv)
 {
 	priv->counter_array =
@@ -231,7 +268,8 @@ static void gve_stats_report_schedule(struct gve_priv *priv)
 
 static void gve_stats_report_timer(struct timer_list *t)
 {
-	struct gve_priv *priv = from_timer(priv, t, stats_report_timer);
+	struct gve_priv *priv = timer_container_of(priv, t,
+						   stats_report_timer);
 
 	mod_timer(&priv->stats_report_timer,
 		  round_jiffies(jiffies +
@@ -265,7 +303,7 @@ static void gve_free_stats_report(struct gve_priv *priv)
 	if (!priv->stats_report)
 		return;
 
-	del_timer_sync(&priv->stats_report_timer);
+	timer_delete_sync(&priv->stats_report_timer);
 	dma_free_coherent(&priv->pdev->dev, priv->stats_report_len,
 			  priv->stats_report, priv->stats_report_bus);
 	priv->stats_report = NULL;
@@ -333,6 +371,14 @@ int gve_napi_poll(struct napi_struct *napi, int budget)
 
 	if (block->rx) {
 		work_done = gve_rx_poll(block, budget);
+
+		/* Poll XSK TX as part of RX NAPI. Setup re-poll based on max of
+		 * TX and RX work done.
+		 */
+		if (priv->xdp_prog)
+			work_done = max_t(int, work_done,
+					  gve_xsk_tx_poll(block, budget));
+
 		reschedule |= work_done == budget;
 	}
 
@@ -567,9 +613,12 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 	err = gve_alloc_flow_rule_caches(priv);
 	if (err)
 		return err;
-	err = gve_alloc_counter_array(priv);
+	err = gve_alloc_rss_config_cache(priv);
 	if (err)
 		goto abort_with_flow_rule_caches;
+	err = gve_alloc_counter_array(priv);
+	if (err)
+		goto abort_with_rss_config_cache;
 	err = gve_alloc_notify_blocks(priv);
 	if (err)
 		goto abort_with_counter;
@@ -603,6 +652,12 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 		}
 	}
 
+	err = gve_init_rss_config(priv, priv->rx_cfg.num_queues);
+	if (err) {
+		dev_err(&priv->pdev->dev, "Failed to init RSS config");
+		goto abort_with_ptype_lut;
+	}
+
 	err = gve_adminq_report_stats(priv, priv->stats_report_len,
 				      priv->stats_report_bus,
 				      GVE_STATS_REPORT_TIMER_PERIOD);
@@ -621,6 +676,8 @@ abort_with_ntfy_blocks:
 	gve_free_notify_blocks(priv);
 abort_with_counter:
 	gve_free_counter_array(priv);
+abort_with_rss_config_cache:
+	gve_free_rss_config_cache(priv);
 abort_with_flow_rule_caches:
 	gve_free_flow_rule_caches(priv);
 
@@ -661,6 +718,7 @@ static void gve_teardown_device_resources(struct gve_priv *priv)
 	priv->ptype_lut_dqo = NULL;
 
 	gve_free_flow_rule_caches(priv);
+	gve_free_rss_config_cache(priv);
 	gve_free_counter_array(priv);
 	gve_free_notify_blocks(priv);
 	gve_free_stats_report(priv);
@@ -738,30 +796,13 @@ static struct gve_queue_page_list *gve_rx_get_qpl(struct gve_priv *priv, int idx
 		return rx->dqo.qpl;
 }
 
-static int gve_register_xdp_qpls(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-	int i;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) {
-		err = gve_register_qpl(priv, gve_tx_get_qpl(priv, i));
-		/* This failure will trigger a reset - no need to clean up */
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
 static int gve_register_qpls(struct gve_priv *priv)
 {
 	int num_tx_qpls, num_rx_qpls;
 	int err;
 	int i;
 
-	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_num_xdp_qpls(priv),
-				      gve_is_qpl(priv));
+	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_is_qpl(priv));
 	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
 
 	for (i = 0; i < num_tx_qpls; i++) {
@@ -779,30 +820,13 @@ static int gve_register_qpls(struct gve_priv *priv)
 	return 0;
 }
 
-static int gve_unregister_xdp_qpls(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-	int i;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) {
-		err = gve_unregister_qpl(priv, gve_tx_get_qpl(priv, i));
-		/* This failure will trigger a reset - no need to clean */
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
 static int gve_unregister_qpls(struct gve_priv *priv)
 {
 	int num_tx_qpls, num_rx_qpls;
 	int err;
 	int i;
 
-	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_num_xdp_qpls(priv),
-				      gve_is_qpl(priv));
+	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_is_qpl(priv));
 	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
 
 	for (i = 0; i < num_tx_qpls; i++) {
@@ -821,27 +845,6 @@ static int gve_unregister_qpls(struct gve_priv *priv)
 	return 0;
 }
 
-static int gve_create_xdp_rings(struct gve_priv *priv)
-{
-	int err;
-
-	err = gve_adminq_create_tx_queues(priv,
-					  gve_xdp_tx_start_queue_id(priv),
-					  priv->num_xdp_queues);
-	if (err) {
-		netif_err(priv, drv, priv->dev, "failed to create %d XDP tx queues\n",
-			  priv->num_xdp_queues);
-		/* This failure will trigger a reset - no need to clean
-		 * up
-		 */
-		return err;
-	}
-	netif_dbg(priv, drv, priv->dev, "created %d XDP tx queues\n",
-		  priv->num_xdp_queues);
-
-	return 0;
-}
-
 static int gve_create_rings(struct gve_priv *priv)
 {
 	int num_tx_queues = gve_num_tx_queues(priv);
@@ -897,7 +900,7 @@ static void init_xdp_sync_stats(struct gve_priv *priv)
 	int i;
 
 	/* Init stats */
-	for (i = start_id; i < start_id + priv->num_xdp_queues; i++) {
+	for (i = start_id; i < start_id + priv->tx_cfg.num_xdp_queues; i++) {
 		int ntfy_idx = gve_tx_idx_to_ntfy(priv, i);
 
 		u64_stats_init(&priv->tx[i].statss);
@@ -925,19 +928,18 @@ static void gve_tx_get_curr_alloc_cfg(struct gve_priv *priv,
 	cfg->qcfg = &priv->tx_cfg;
 	cfg->raw_addressing = !gve_is_qpl(priv);
 	cfg->ring_size = priv->tx_desc_cnt;
-	cfg->start_idx = 0;
-	cfg->num_rings = gve_num_tx_queues(priv);
+	cfg->num_xdp_rings = cfg->qcfg->num_xdp_queues;
 	cfg->tx = priv->tx;
 }
 
-static void gve_tx_stop_rings(struct gve_priv *priv, int start_id, int num_rings)
+static void gve_tx_stop_rings(struct gve_priv *priv, int num_rings)
 {
 	int i;
 
 	if (!priv->tx)
 		return;
 
-	for (i = start_id; i < start_id + num_rings; i++) {
+	for (i = 0; i < num_rings; i++) {
 		if (gve_is_gqi(priv))
 			gve_tx_stop_ring_gqi(priv, i);
 		else
@@ -945,12 +947,11 @@ static void gve_tx_stop_rings(struct gve_priv *priv, int start_id, int num_rings
 	}
 }
 
-static void gve_tx_start_rings(struct gve_priv *priv, int start_id,
-			       int num_rings)
+static void gve_tx_start_rings(struct gve_priv *priv, int num_rings)
 {
 	int i;
 
-	for (i = start_id; i < start_id + num_rings; i++) {
+	for (i = 0; i < num_rings; i++) {
 		if (gve_is_gqi(priv))
 			gve_tx_start_ring_gqi(priv, i);
 		else
@@ -958,28 +959,6 @@ static void gve_tx_start_rings(struct gve_priv *priv, int start_id,
 	}
 }
 
-static int gve_alloc_xdp_rings(struct gve_priv *priv)
-{
-	struct gve_tx_alloc_rings_cfg cfg = {0};
-	int err = 0;
-
-	if (!priv->num_xdp_queues)
-		return 0;
-
-	gve_tx_get_curr_alloc_cfg(priv, &cfg);
-	cfg.start_idx = gve_xdp_tx_start_queue_id(priv);
-	cfg.num_rings = priv->num_xdp_queues;
-
-	err = gve_tx_alloc_rings_gqi(priv, &cfg);
-	if (err)
-		return err;
-
-	gve_tx_start_rings(priv, cfg.start_idx, cfg.num_rings);
-	init_xdp_sync_stats(priv);
-
-	return 0;
-}
-
 static int gve_queues_mem_alloc(struct gve_priv *priv,
 				struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
 				struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
@@ -1010,26 +989,6 @@ free_tx:
 	return err;
 }
 
-static int gve_destroy_xdp_rings(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	err = gve_adminq_destroy_tx_queues(priv,
-					   start_id,
-					   priv->num_xdp_queues);
-	if (err) {
-		netif_err(priv, drv, priv->dev,
-			  "failed to destroy XDP queues\n");
-		/* This failure will trigger a reset - no need to clean up */
-		return err;
-	}
-	netif_dbg(priv, drv, priv->dev, "destroyed XDP queues\n");
-
-	return 0;
-}
-
 static int gve_destroy_rings(struct gve_priv *priv)
 {
 	int num_tx_queues = gve_num_tx_queues(priv);
@@ -1054,20 +1013,6 @@ static int gve_destroy_rings(struct gve_priv *priv)
 	return 0;
 }
 
-static void gve_free_xdp_rings(struct gve_priv *priv)
-{
-	struct gve_tx_alloc_rings_cfg cfg = {0};
-
-	gve_tx_get_curr_alloc_cfg(priv, &cfg);
-	cfg.start_idx = gve_xdp_tx_start_queue_id(priv);
-	cfg.num_rings = priv->num_xdp_queues;
-
-	if (priv->tx) {
-		gve_tx_stop_rings(priv, cfg.start_idx, cfg.num_rings);
-		gve_tx_free_rings_gqi(priv, &cfg);
-	}
-}
-
 static void gve_queues_mem_free(struct gve_priv *priv,
 				struct gve_tx_alloc_rings_cfg *tx_cfg,
 				struct gve_rx_alloc_rings_cfg *rx_cfg)
@@ -1194,7 +1139,7 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev)
 	int i, j;
 	u32 tx_qid;
 
-	if (!priv->num_xdp_queues)
+	if (!priv->tx_cfg.num_xdp_queues)
 		return 0;
 
 	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
@@ -1205,8 +1150,14 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev)
 				       napi->napi_id);
 		if (err)
 			goto err;
-		err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
-						 MEM_TYPE_PAGE_SHARED, NULL);
+		if (gve_is_qpl(priv))
+			err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+		else
+			err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
+							 MEM_TYPE_PAGE_POOL,
+							 rx->dqo.page_pool);
 		if (err)
 			goto err;
 		rx->xsk_pool = xsk_get_pool_from_qid(dev, i);
@@ -1224,7 +1175,7 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev)
 		}
 	}
 
-	for (i = 0; i < priv->num_xdp_queues; i++) {
+	for (i = 0; i < priv->tx_cfg.num_xdp_queues; i++) {
 		tx_qid = gve_xdp_tx_queue_id(priv, i);
 		priv->tx[tx_qid].xsk_pool = xsk_get_pool_from_qid(dev, i);
 	}
@@ -1245,7 +1196,7 @@ static void gve_unreg_xdp_info(struct gve_priv *priv)
 {
 	int i, tx_qid;
 
-	if (!priv->num_xdp_queues)
+	if (!priv->tx_cfg.num_xdp_queues || !priv->rx || !priv->tx)
 		return;
 
 	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
@@ -1258,7 +1209,7 @@ static void gve_unreg_xdp_info(struct gve_priv *priv)
 		}
 	}
 
-	for (i = 0; i < priv->num_xdp_queues; i++) {
+	for (i = 0; i < priv->tx_cfg.num_xdp_queues; i++) {
 		tx_qid = gve_xdp_tx_queue_id(priv, i);
 		priv->tx[tx_qid].xsk_pool = NULL;
 	}
@@ -1275,15 +1226,14 @@ static void gve_drain_page_cache(struct gve_priv *priv)
 static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv,
 				      struct gve_rx_alloc_rings_cfg *cfg)
 {
-	cfg->qcfg = &priv->rx_cfg;
+	cfg->qcfg_rx = &priv->rx_cfg;
 	cfg->qcfg_tx = &priv->tx_cfg;
 	cfg->raw_addressing = !gve_is_qpl(priv);
 	cfg->enable_header_split = priv->header_split_enabled;
 	cfg->ring_size = priv->rx_desc_cnt;
-	cfg->packet_buffer_size = gve_is_gqi(priv) ?
-				  GVE_DEFAULT_RX_BUFFER_SIZE :
-				  priv->data_buffer_size_dqo;
+	cfg->packet_buffer_size = priv->rx_cfg.packet_buffer_size;
 	cfg->rx = priv->rx;
+	cfg->xdp = !!cfg->qcfg_tx->num_xdp_queues;
 }
 
 void gve_get_curr_alloc_cfgs(struct gve_priv *priv,
@@ -1356,17 +1306,13 @@ static int gve_queues_start(struct gve_priv *priv,
 
 	/* Record new configs into priv */
 	priv->tx_cfg = *tx_alloc_cfg->qcfg;
-	priv->rx_cfg = *rx_alloc_cfg->qcfg;
+	priv->tx_cfg.num_xdp_queues = tx_alloc_cfg->num_xdp_rings;
+	priv->rx_cfg = *rx_alloc_cfg->qcfg_rx;
 	priv->tx_desc_cnt = tx_alloc_cfg->ring_size;
 	priv->rx_desc_cnt = rx_alloc_cfg->ring_size;
 
-	if (priv->xdp_prog)
-		priv->num_xdp_queues = priv->rx_cfg.num_queues;
-	else
-		priv->num_xdp_queues = 0;
-
-	gve_tx_start_rings(priv, 0, tx_alloc_cfg->num_rings);
-	gve_rx_start_rings(priv, rx_alloc_cfg->qcfg->num_queues);
+	gve_tx_start_rings(priv, gve_num_tx_queues(priv));
+	gve_rx_start_rings(priv, rx_alloc_cfg->qcfg_rx->num_queues);
 	gve_init_sync_stats(priv);
 
 	err = netif_set_real_num_tx_queues(dev, priv->tx_cfg.num_queues);
@@ -1380,12 +1326,18 @@ static int gve_queues_start(struct gve_priv *priv,
 	if (err)
 		goto stop_and_free_rings;
 
+	if (rx_alloc_cfg->reset_rss) {
+		err = gve_init_rss_config(priv, priv->rx_cfg.num_queues);
+		if (err)
+			goto reset;
+	}
+
 	err = gve_register_qpls(priv);
 	if (err)
 		goto reset;
 
 	priv->header_split_enabled = rx_alloc_cfg->enable_header_split;
-	priv->data_buffer_size_dqo = rx_alloc_cfg->packet_buffer_size;
+	priv->rx_cfg.packet_buffer_size = rx_alloc_cfg->packet_buffer_size;
 
 	err = gve_create_rings(priv);
 	if (err)
@@ -1412,7 +1364,7 @@ reset:
 	/* return the original error */
 	return err;
 stop_and_free_rings:
-	gve_tx_stop_rings(priv, 0, gve_num_tx_queues(priv));
+	gve_tx_stop_rings(priv, gve_num_tx_queues(priv));
 	gve_rx_stop_rings(priv, priv->rx_cfg.num_queues);
 	gve_queues_mem_remove(priv);
 	return err;
@@ -1457,11 +1409,11 @@ static int gve_queues_stop(struct gve_priv *priv)
 			goto err;
 		gve_clear_device_rings_ok(priv);
 	}
-	del_timer_sync(&priv->stats_report_timer);
+	timer_delete_sync(&priv->stats_report_timer);
 
 	gve_unreg_xdp_info(priv);
 
-	gve_tx_stop_rings(priv, 0, gve_num_tx_queues(priv));
+	gve_tx_stop_rings(priv, gve_num_tx_queues(priv));
 	gve_rx_stop_rings(priv, priv->rx_cfg.num_queues);
 
 	priv->interface_down_cnt++;
@@ -1491,56 +1443,6 @@ static int gve_close(struct net_device *dev)
 	return 0;
 }
 
-static int gve_remove_xdp_queues(struct gve_priv *priv)
-{
-	int err;
-
-	err = gve_destroy_xdp_rings(priv);
-	if (err)
-		return err;
-
-	err = gve_unregister_xdp_qpls(priv);
-	if (err)
-		return err;
-
-	gve_unreg_xdp_info(priv);
-	gve_free_xdp_rings(priv);
-
-	priv->num_xdp_queues = 0;
-	return 0;
-}
-
-static int gve_add_xdp_queues(struct gve_priv *priv)
-{
-	int err;
-
-	priv->num_xdp_queues = priv->rx_cfg.num_queues;
-
-	err = gve_alloc_xdp_rings(priv);
-	if (err)
-		goto err;
-
-	err = gve_reg_xdp_info(priv, priv->dev);
-	if (err)
-		goto free_xdp_rings;
-
-	err = gve_register_xdp_qpls(priv);
-	if (err)
-		goto free_xdp_rings;
-
-	err = gve_create_xdp_rings(priv);
-	if (err)
-		goto free_xdp_rings;
-
-	return 0;
-
-free_xdp_rings:
-	gve_free_xdp_rings(priv);
-err:
-	priv->num_xdp_queues = 0;
-	return err;
-}
-
 static void gve_handle_link_status(struct gve_priv *priv, bool link_status)
 {
 	if (!gve_get_napi_enabled(priv))
@@ -1558,6 +1460,19 @@ static void gve_handle_link_status(struct gve_priv *priv, bool link_status)
 	}
 }
 
+static int gve_configure_rings_xdp(struct gve_priv *priv,
+				   u16 num_xdp_rings)
+{
+	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
+	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
+
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+	tx_alloc_cfg.num_xdp_rings = num_xdp_rings;
+
+	rx_alloc_cfg.xdp = !!num_xdp_rings;
+	return gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+}
+
 static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog,
 		       struct netlink_ext_ack *extack)
 {
@@ -1570,29 +1485,26 @@ static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog,
 		WRITE_ONCE(priv->xdp_prog, prog);
 		if (old_prog)
 			bpf_prog_put(old_prog);
+
+		/* Update priv XDP queue configuration */
+		priv->tx_cfg.num_xdp_queues = priv->xdp_prog ?
+			priv->rx_cfg.num_queues : 0;
 		return 0;
 	}
 
-	gve_turndown(priv);
-	if (!old_prog && prog) {
-		// Allocate XDP TX queues if an XDP program is
-		// being installed
-		err = gve_add_xdp_queues(priv);
-		if (err)
-			goto out;
-	} else if (old_prog && !prog) {
-		// Remove XDP TX queues if an XDP program is
-		// being uninstalled
-		err = gve_remove_xdp_queues(priv);
-		if (err)
-			goto out;
-	}
+	if (!old_prog && prog)
+		err = gve_configure_rings_xdp(priv, priv->rx_cfg.num_queues);
+	else if (old_prog && !prog)
+		err = gve_configure_rings_xdp(priv, 0);
+
+	if (err)
+		goto out;
+
 	WRITE_ONCE(priv->xdp_prog, prog);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
 out:
-	gve_turnup(priv);
 	status = ioread32be(&priv->reg_bar0->device_status);
 	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
 	return err;
@@ -1623,8 +1535,8 @@ static int gve_xsk_pool_enable(struct net_device *dev,
 	if (err)
 		return err;
 
-	/* If XDP prog is not installed, return */
-	if (!priv->xdp_prog)
+	/* If XDP prog is not installed or interface is down, return. */
+	if (!priv->xdp_prog || !netif_running(dev))
 		return 0;
 
 	rx = &priv->rx[qid];
@@ -1669,21 +1581,16 @@ static int gve_xsk_pool_disable(struct net_device *dev,
 	if (qid >= priv->rx_cfg.num_queues)
 		return -EINVAL;
 
-	/* If XDP prog is not installed, unmap DMA and return */
-	if (!priv->xdp_prog)
-		goto done;
-
-	tx_qid = gve_xdp_tx_queue_id(priv, qid);
-	if (!netif_running(dev)) {
-		priv->rx[qid].xsk_pool = NULL;
-		xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq);
-		priv->tx[tx_qid].xsk_pool = NULL;
+	/* If XDP prog is not installed or interface is down, unmap DMA and
+	 * return.
+	 */
+	if (!priv->xdp_prog || !netif_running(dev))
 		goto done;
-	}
 
 	napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi;
 	napi_disable(napi_rx); /* make sure current rx poll is done */
 
+	tx_qid = gve_xdp_tx_queue_id(priv, qid);
 	napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi;
 	napi_disable(napi_tx); /* make sure current tx poll is done */
 
@@ -1709,24 +1616,20 @@ done:
 static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 {
 	struct gve_priv *priv = netdev_priv(dev);
-	int tx_queue_id = gve_xdp_tx_queue_id(priv, queue_id);
+	struct napi_struct *napi;
+
+	if (!gve_get_napi_enabled(priv))
+		return -ENETDOWN;
 
 	if (queue_id >= priv->rx_cfg.num_queues || !priv->xdp_prog)
 		return -EINVAL;
 
-	if (flags & XDP_WAKEUP_TX) {
-		struct gve_tx_ring *tx = &priv->tx[tx_queue_id];
-		struct napi_struct *napi =
-			&priv->ntfy_blocks[tx->ntfy_id].napi;
-
-		if (!napi_if_scheduled_mark_missed(napi)) {
-			/* Call local_bh_enable to trigger SoftIRQ processing */
-			local_bh_disable();
-			napi_schedule(napi);
-			local_bh_enable();
-		}
-
-		tx->xdp_xsk_wakeup++;
+	napi = &priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_id)].napi;
+	if (!napi_if_scheduled_mark_missed(napi)) {
+		/* Call local_bh_enable to trigger SoftIRQ processing */
+		local_bh_disable();
+		napi_schedule(napi);
+		local_bh_enable();
 	}
 
 	return 0;
@@ -1735,6 +1638,7 @@ static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 static int verify_xdp_configuration(struct net_device *dev)
 {
 	struct gve_priv *priv = netdev_priv(dev);
+	u16 max_xdp_mtu;
 
 	if (dev->features & NETIF_F_LRO) {
 		netdev_warn(dev, "XDP is not supported when LRO is on.\n");
@@ -1747,7 +1651,11 @@ static int verify_xdp_configuration(struct net_device *dev)
 		return -EOPNOTSUPP;
 	}
 
-	if (dev->mtu > GVE_DEFAULT_RX_BUFFER_SIZE - sizeof(struct ethhdr) - GVE_RX_PAD) {
+	max_xdp_mtu = priv->rx_cfg.packet_buffer_size - sizeof(struct ethhdr);
+	if (priv->queue_format == GVE_GQI_QPL_FORMAT)
+		max_xdp_mtu -= GVE_RX_PAD;
+
+	if (dev->mtu > max_xdp_mtu) {
 		netdev_warn(dev, "XDP is not supported for mtu %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
@@ -1785,6 +1693,26 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+int gve_init_rss_config(struct gve_priv *priv, u16 num_queues)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+	struct ethtool_rxfh_param rxfh = {0};
+	u16 i;
+
+	if (!priv->cache_rss_config)
+		return 0;
+
+	for (i = 0; i < priv->rss_lut_size; i++)
+		rss_config->hash_lut[i] =
+			ethtool_rxfh_indir_default(i, num_queues);
+
+	netdev_rss_key_fill(rss_config->hash_key, priv->rss_key_size);
+
+	rxfh.hfunc = ETH_RSS_HASH_TOP;
+
+	return gve_adminq_configure_rss(priv, &rxfh);
+}
+
 int gve_flow_rules_reset(struct gve_priv *priv)
 {
 	if (!priv->max_flow_rules)
@@ -1832,8 +1760,9 @@ int gve_adjust_config(struct gve_priv *priv,
 }
 
 int gve_adjust_queues(struct gve_priv *priv,
-		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config)
+		      struct gve_rx_queue_config new_rx_config,
+		      struct gve_tx_queue_config new_tx_config,
+		      bool reset_rss)
 {
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
@@ -1844,14 +1773,19 @@ int gve_adjust_queues(struct gve_priv *priv,
 	/* Relay the new config from ethtool */
 	tx_alloc_cfg.qcfg = &new_tx_config;
 	rx_alloc_cfg.qcfg_tx = &new_tx_config;
-	rx_alloc_cfg.qcfg = &new_rx_config;
-	tx_alloc_cfg.num_rings = new_tx_config.num_queues;
+	rx_alloc_cfg.qcfg_rx = &new_rx_config;
+	rx_alloc_cfg.reset_rss = reset_rss;
 
 	if (netif_running(priv->dev)) {
 		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 		return err;
 	}
 	/* Set the config for the next up. */
+	if (reset_rss) {
+		err = gve_init_rss_config(priv, new_rx_config.num_queues);
+		if (err)
+			return err;
+	}
 	priv->tx_cfg = new_tx_config;
 	priv->rx_cfg = new_rx_config;
 
@@ -1880,7 +1814,7 @@ static void gve_turndown(struct gve_priv *priv)
 			netif_queue_set_napi(priv->dev, idx,
 					     NETDEV_QUEUE_TYPE_TX, NULL);
 
-		napi_disable(&block->napi);
+		napi_disable_locked(&block->napi);
 	}
 	for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) {
 		int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
@@ -1891,14 +1825,19 @@ static void gve_turndown(struct gve_priv *priv)
 
 		netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_RX,
 				     NULL);
-		napi_disable(&block->napi);
+		napi_disable_locked(&block->napi);
 	}
 
 	/* Stop tx queues */
 	netif_tx_disable(priv->dev);
 
+	xdp_features_clear_redirect_target_locked(priv->dev);
+
 	gve_clear_napi_enabled(priv);
 	gve_clear_report_stats(priv);
+
+	/* Make sure that all traffic is finished processing. */
+	synchronize_net();
 }
 
 static void gve_turnup(struct gve_priv *priv)
@@ -1916,7 +1855,7 @@ static void gve_turnup(struct gve_priv *priv)
 		if (!gve_tx_was_added_to_block(priv, idx))
 			continue;
 
-		napi_enable(&block->napi);
+		napi_enable_locked(&block->napi);
 
 		if (idx < priv->tx_cfg.num_queues)
 			netif_queue_set_napi(priv->dev, idx,
@@ -1944,7 +1883,7 @@ static void gve_turnup(struct gve_priv *priv)
 		if (!gve_rx_was_added_to_block(priv, idx))
 			continue;
 
-		napi_enable(&block->napi);
+		napi_enable_locked(&block->napi);
 		netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_RX,
 				     &block->napi);
 
@@ -1963,6 +1902,9 @@ static void gve_turnup(struct gve_priv *priv)
 		napi_schedule(&block->napi);
 	}
 
+	if (priv->tx_cfg.num_xdp_queues && gve_supports_xdp_xmit(priv))
+		xdp_features_set_redirect_target_locked(priv->dev, false);
+
 	gve_set_napi_enabled(priv);
 }
 
@@ -2136,7 +2078,9 @@ static void gve_handle_reset(struct gve_priv *priv)
 
 	if (gve_get_do_reset(priv)) {
 		rtnl_lock();
+		netdev_lock(priv->dev);
 		gve_reset(priv, false);
+		netdev_unlock(priv->dev);
 		rtnl_unlock();
 	}
 }
@@ -2210,7 +2154,7 @@ void gve_handle_report_stats(struct gve_priv *priv)
 			};
 			stats[stats_idx++] = (struct stats) {
 				.stat_name = cpu_to_be32(RX_BUFFERS_POSTED),
-				.value = cpu_to_be64(priv->rx[0].fill_cnt),
+				.value = cpu_to_be64(priv->rx[idx].fill_cnt),
 				.queue_id = cpu_to_be32(idx),
 			};
 		}
@@ -2232,14 +2176,17 @@ static void gve_service_task(struct work_struct *work)
 
 static void gve_set_netdev_xdp_features(struct gve_priv *priv)
 {
+	xdp_features_t xdp_features;
+
 	if (priv->queue_format == GVE_GQI_QPL_FORMAT) {
-		priv->dev->xdp_features = NETDEV_XDP_ACT_BASIC;
-		priv->dev->xdp_features |= NETDEV_XDP_ACT_REDIRECT;
-		priv->dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
-		priv->dev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
+		xdp_features = NETDEV_XDP_ACT_BASIC;
+		xdp_features |= NETDEV_XDP_ACT_REDIRECT;
+		xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
 	} else {
-		priv->dev->xdp_features = 0;
+		xdp_features = 0;
 	}
+
+	xdp_set_features_flag_locked(priv->dev, xdp_features);
 }
 
 static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
@@ -2313,6 +2260,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 		priv->rx_cfg.num_queues = min_t(int, priv->default_num_queues,
 						priv->rx_cfg.num_queues);
 	}
+	priv->tx_cfg.num_xdp_queues = 0;
 
 	dev_info(&priv->pdev->dev, "TX queues %d, RX queues %d\n",
 		 priv->tx_cfg.num_queues, priv->rx_cfg.num_queues);
@@ -2693,7 +2641,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	priv->service_task_flags = 0x0;
 	priv->state_flags = 0x0;
 	priv->ethtool_flags = 0x0;
-	priv->data_buffer_size_dqo = GVE_DEFAULT_RX_BUFFER_SIZE;
+	priv->rx_cfg.packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 	priv->max_rx_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 
 	gve_set_probe_in_progress(priv);
@@ -2712,6 +2660,9 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto abort_with_wq;
 
+	if (!gve_is_gqi(priv) && !gve_is_qpl(priv))
+		dev->netmem_tx = true;
+
 	err = register_netdev(dev);
 	if (err)
 		goto abort_with_gve_init;
@@ -2769,6 +2720,7 @@ static void gve_shutdown(struct pci_dev *pdev)
 	bool was_up = netif_running(priv->dev);
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (was_up && gve_close(priv->dev)) {
 		/* If the dev was up, attempt to close, if close fails, reset */
 		gve_reset_and_teardown(priv, was_up);
@@ -2776,6 +2728,7 @@ static void gve_shutdown(struct pci_dev *pdev)
 		/* If the dev wasn't up or close worked, finish tearing down */
 		gve_teardown_priv_resources(priv);
 	}
+	netdev_unlock(netdev);
 	rtnl_unlock();
 }
 
@@ -2788,6 +2741,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	priv->suspend_cnt++;
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (was_up && gve_close(priv->dev)) {
 		/* If the dev was up, attempt to close, if close fails, reset */
 		gve_reset_and_teardown(priv, was_up);
@@ -2796,6 +2750,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state)
 		gve_teardown_priv_resources(priv);
 	}
 	priv->up_before_suspend = was_up;
+	netdev_unlock(netdev);
 	rtnl_unlock();
 	return 0;
 }
@@ -2808,7 +2763,9 @@ static int gve_resume(struct pci_dev *pdev)
 
 	priv->resume_cnt++;
 	rtnl_lock();
+	netdev_lock(netdev);
 	err = gve_reset_recovery(priv, priv->up_before_suspend);
+	netdev_unlock(netdev);
 	rtnl_unlock();
 	return err;
 }
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index acb73d4d0de6..90e875c1832f 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -141,12 +141,15 @@ void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx,
 	netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx);
 }
 
-static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info,
-			     dma_addr_t addr, struct page *page, __be64 *slot_addr)
+static void gve_setup_rx_buffer(struct gve_rx_ring *rx,
+				struct gve_rx_slot_page_info *page_info,
+				dma_addr_t addr, struct page *page,
+				__be64 *slot_addr)
 {
 	page_info->page = page;
 	page_info->page_offset = 0;
 	page_info->page_address = page_address(page);
+	page_info->buf_size = rx->packet_buffer_size;
 	*slot_addr = cpu_to_be64(addr);
 	/* The page already has 1 ref */
 	page_ref_add(page, INT_MAX - 1);
@@ -171,7 +174,7 @@ static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev,
 		return err;
 	}
 
-	gve_setup_rx_buffer(page_info, dma, page, &data_slot->addr);
+	gve_setup_rx_buffer(rx, page_info, dma, page, &data_slot->addr);
 	return 0;
 }
 
@@ -199,7 +202,8 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 			struct page *page = rx->data.qpl->pages[i];
 			dma_addr_t addr = i * PAGE_SIZE;
 
-			gve_setup_rx_buffer(&rx->data.page_info[i], addr, page,
+			gve_setup_rx_buffer(rx, &rx->data.page_info[i], addr,
+					    page,
 					    &rx->data.data_ring[i].qpl_offset);
 			continue;
 		}
@@ -222,6 +226,7 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 			rx->qpl_copy_pool[j].page = page;
 			rx->qpl_copy_pool[j].page_offset = 0;
 			rx->qpl_copy_pool[j].page_address = page_address(page);
+			rx->qpl_copy_pool[j].buf_size = rx->packet_buffer_size;
 
 			/* The page already has 1 ref. */
 			page_ref_add(page, INT_MAX - 1);
@@ -283,6 +288,7 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 
 	rx->gve = priv;
 	rx->q_num = idx;
+	rx->packet_buffer_size = cfg->packet_buffer_size;
 
 	rx->mask = slots - 1;
 	rx->data.raw_addressing = cfg->raw_addressing;
@@ -351,7 +357,6 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 	rx->db_threshold = slots / 2;
 	gve_rx_init_ring_state_gqi(rx);
 
-	rx->packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 	gve_rx_ctx_clear(&rx->ctx);
 
 	return 0;
@@ -385,12 +390,12 @@ int gve_rx_alloc_rings_gqi(struct gve_priv *priv,
 	int err = 0;
 	int i, j;
 
-	rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring),
+	rx = kvcalloc(cfg->qcfg_rx->max_queues, sizeof(struct gve_rx_ring),
 		      GFP_KERNEL);
 	if (!rx)
 		return -ENOMEM;
 
-	for (i = 0; i < cfg->qcfg->num_queues; i++) {
+	for (i = 0; i < cfg->qcfg_rx->num_queues; i++) {
 		err = gve_rx_alloc_ring_gqi(priv, cfg, &rx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -419,7 +424,7 @@ void gve_rx_free_rings_gqi(struct gve_priv *priv,
 	if (!rx)
 		return;
 
-	for (i = 0; i < cfg->qcfg->num_queues;  i++)
+	for (i = 0; i < cfg->qcfg_rx->num_queues;  i++)
 		gve_rx_free_ring_gqi(priv, &rx[i], cfg);
 
 	kvfree(rx);
@@ -590,7 +595,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx,
 	copy_page_info->pad = page_info->pad;
 
 	skb = gve_rx_add_frags(napi, copy_page_info,
-			       rx->packet_buffer_size, len, ctx);
+			       copy_page_info->buf_size, len, ctx);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -630,7 +635,8 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev,
 	 * device.
 	 */
 	if (page_info->can_flip) {
-		skb = gve_rx_add_frags(napi, page_info, rx->packet_buffer_size, len, ctx);
+		skb = gve_rx_add_frags(napi, page_info, page_info->buf_size,
+				       len, ctx);
 		/* No point in recycling if we didn't get the skb */
 		if (skb) {
 			/* Make sure that the page isn't freed. */
@@ -680,7 +686,7 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx,
 			skb = gve_rx_raw_addressing(&priv->pdev->dev, netdev,
 						    page_info, len, napi,
 						    data_slot,
-						    rx->packet_buffer_size, ctx);
+						    page_info->buf_size, ctx);
 		} else {
 			skb = gve_rx_qpl(&priv->pdev->dev, netdev, rx,
 					 page_info, len, napi, data_slot);
@@ -855,7 +861,7 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat,
 		void *old_data;
 		int xdp_act;
 
-		xdp_init_buff(&xdp, rx->packet_buffer_size, &rx->xdp_rxq);
+		xdp_init_buff(&xdp, page_info->buf_size, &rx->xdp_rxq);
 		xdp_prepare_buff(&xdp, page_info->page_address +
 				 page_info->page_offset, GVE_RX_PAD,
 				 len, false);
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 8ac0047f1ada..dcb0545baa50 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -109,10 +109,13 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx)
 void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx)
 {
 	int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
+	struct gve_rx_ring *rx = &priv->rx[idx];
 
 	if (!gve_rx_was_added_to_block(priv, idx))
 		return;
 
+	if (rx->dqo.page_pool)
+		page_pool_disable_direct_recycling(rx->dqo.page_pool);
 	gve_remove_napi(priv, ntfy_idx);
 	gve_rx_remove_from_block(priv, idx);
 	gve_rx_reset_ring_dqo(priv, idx);
@@ -221,6 +224,15 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 	memset(rx, 0, sizeof(*rx));
 	rx->gve = priv;
 	rx->q_num = idx;
+	rx->packet_buffer_size = cfg->packet_buffer_size;
+
+	if (cfg->xdp) {
+		rx->packet_buffer_truesize = GVE_XDP_RX_BUFFER_SIZE_DQO;
+		rx->rx_headroom = XDP_PACKET_HEADROOM;
+	} else {
+		rx->packet_buffer_truesize = rx->packet_buffer_size;
+		rx->rx_headroom = 0;
+	}
 
 	rx->dqo.num_buf_states = cfg->raw_addressing ? buffer_queue_slots :
 		gve_get_rx_pages_per_qpl_dqo(cfg->ring_size);
@@ -251,7 +263,7 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 		goto err;
 
 	if (cfg->raw_addressing) {
-		pool = gve_rx_create_page_pool(priv, rx);
+		pool = gve_rx_create_page_pool(priv, rx, cfg->xdp);
 		if (IS_ERR(pool))
 			goto err;
 
@@ -297,12 +309,12 @@ int gve_rx_alloc_rings_dqo(struct gve_priv *priv,
 	int err;
 	int i;
 
-	rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring),
+	rx = kvcalloc(cfg->qcfg_rx->max_queues, sizeof(struct gve_rx_ring),
 		      GFP_KERNEL);
 	if (!rx)
 		return -ENOMEM;
 
-	for (i = 0; i < cfg->qcfg->num_queues; i++) {
+	for (i = 0; i < cfg->qcfg_rx->num_queues; i++) {
 		err = gve_rx_alloc_ring_dqo(priv, cfg, &rx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -331,7 +343,7 @@ void gve_rx_free_rings_dqo(struct gve_priv *priv,
 	if (!rx)
 		return;
 
-	for (i = 0; i < cfg->qcfg->num_queues;  i++)
+	for (i = 0; i < cfg->qcfg_rx->num_queues;  i++)
 		gve_rx_free_ring_dqo(priv, &rx[i], cfg);
 
 	kvfree(rx);
@@ -474,6 +486,25 @@ static int gve_rx_copy_ondemand(struct gve_rx_ring *rx,
 	return 0;
 }
 
+static void gve_skb_add_rx_frag(struct gve_rx_ring *rx,
+				struct gve_rx_buf_state_dqo *buf_state,
+				int num_frags, u16 buf_len)
+{
+	if (rx->dqo.page_pool) {
+		skb_add_rx_frag_netmem(rx->ctx.skb_tail, num_frags,
+				       buf_state->page_info.netmem,
+				       buf_state->page_info.page_offset +
+				       buf_state->page_info.pad, buf_len,
+				       buf_state->page_info.buf_size);
+	} else {
+		skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
+				buf_state->page_info.page,
+				buf_state->page_info.page_offset +
+				buf_state->page_info.pad, buf_len,
+				buf_state->page_info.buf_size);
+	}
+}
+
 /* Chains multi skbs for single rx packet.
  * Returns 0 if buffer is appended, -1 otherwise.
  */
@@ -511,14 +542,34 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 	if (gve_rx_should_trigger_copy_ondemand(rx))
 		return gve_rx_copy_ondemand(rx, buf_state, buf_len);
 
-	skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
-			buf_state->page_info.page,
-			buf_state->page_info.page_offset,
-			buf_len, buf_state->page_info.buf_size);
+	gve_skb_add_rx_frag(rx, buf_state, num_frags, buf_len);
 	gve_reuse_buffer(rx, buf_state);
 	return 0;
 }
 
+static void gve_xdp_done_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
+			     struct xdp_buff *xdp, struct bpf_prog *xprog,
+			     int xdp_act,
+			     struct gve_rx_buf_state_dqo *buf_state)
+{
+	u64_stats_update_begin(&rx->statss);
+	switch (xdp_act) {
+	case XDP_ABORTED:
+	case XDP_DROP:
+	default:
+		rx->xdp_actions[xdp_act]++;
+		break;
+	case XDP_TX:
+		rx->xdp_tx_errors++;
+		break;
+	case XDP_REDIRECT:
+		rx->xdp_redirect_errors++;
+		break;
+	}
+	u64_stats_update_end(&rx->statss);
+	gve_free_buffer(rx, buf_state);
+}
+
 /* Returns 0 if descriptor is completed successfully.
  * Returns -EINVAL if descriptor is invalid.
  * Returns -ENOMEM if data cannot be copied to skb.
@@ -533,6 +584,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	const bool hsplit = compl_desc->split_header;
 	struct gve_rx_buf_state_dqo *buf_state;
 	struct gve_priv *priv = rx->gve;
+	struct bpf_prog *xprog;
 	u16 buf_len;
 	u16 hdr_len;
 
@@ -559,7 +611,12 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	/* Page might have not been used for awhile and was likely last written
 	 * by a different thread.
 	 */
-	prefetch(buf_state->page_info.page);
+	if (rx->dqo.page_pool) {
+		if (!netmem_is_net_iov(buf_state->page_info.netmem))
+			prefetch(netmem_to_page(buf_state->page_info.netmem));
+	} else {
+		prefetch(buf_state->page_info.page);
+	}
 
 	/* Copy the header into the skb in the case of header split */
 	if (hsplit) {
@@ -588,7 +645,8 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 
 	/* Sync the portion of dma buffer for CPU to read. */
 	dma_sync_single_range_for_cpu(&priv->pdev->dev, buf_state->addr,
-				      buf_state->page_info.page_offset,
+				      buf_state->page_info.page_offset +
+				      buf_state->page_info.pad,
 				      buf_len, DMA_FROM_DEVICE);
 
 	/* Append to current skb if one exists. */
@@ -600,6 +658,34 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 		return 0;
 	}
 
+	xprog = READ_ONCE(priv->xdp_prog);
+	if (xprog) {
+		struct xdp_buff xdp;
+		void *old_data;
+		int xdp_act;
+
+		xdp_init_buff(&xdp, buf_state->page_info.buf_size,
+			      &rx->xdp_rxq);
+		xdp_prepare_buff(&xdp,
+				 buf_state->page_info.page_address +
+				 buf_state->page_info.page_offset,
+				 buf_state->page_info.pad,
+				 buf_len, false);
+		old_data = xdp.data;
+		xdp_act = bpf_prog_run_xdp(xprog, &xdp);
+		buf_state->page_info.pad += xdp.data - old_data;
+		buf_len = xdp.data_end - xdp.data;
+		if (xdp_act != XDP_PASS) {
+			gve_xdp_done_dqo(priv, rx, &xdp, xprog, xdp_act,
+					 buf_state);
+			return 0;
+		}
+
+		u64_stats_update_begin(&rx->statss);
+		rx->xdp_actions[XDP_PASS]++;
+		u64_stats_update_end(&rx->statss);
+	}
+
 	if (eop && buf_len <= priv->rx_copybreak) {
 		rx->ctx.skb_head = gve_rx_copy(priv->dev, napi,
 					       &buf_state->page_info, buf_len);
@@ -630,9 +716,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	if (rx->dqo.page_pool)
 		skb_mark_for_recycle(rx->ctx.skb_head);
 
-	skb_add_rx_frag(rx->ctx.skb_head, 0, buf_state->page_info.page,
-			buf_state->page_info.page_offset, buf_len,
-			buf_state->page_info.buf_size);
+	gve_skb_add_rx_frag(rx, buf_state, 0, buf_len);
 	gve_reuse_buffer(rx, buf_state);
 	return 0;
 
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index e7fb7d6d283d..1b40bf0c811a 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -206,7 +206,10 @@ void gve_tx_stop_ring_gqi(struct gve_priv *priv, int idx)
 		return;
 
 	gve_remove_napi(priv, ntfy_idx);
-	gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false);
+	if (tx->q_num < priv->tx_cfg.num_queues)
+		gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false);
+	else
+		gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt);
 	netdev_tx_reset_queue(tx->netdev_txq);
 	gve_tx_remove_from_block(priv, idx);
 }
@@ -331,27 +334,23 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg)
 {
 	struct gve_tx_ring *tx = cfg->tx;
+	int total_queues;
 	int err = 0;
 	int i, j;
 
-	if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) {
+	total_queues = cfg->qcfg->num_queues + cfg->num_xdp_rings;
+	if (total_queues > cfg->qcfg->max_queues) {
 		netif_err(priv, drv, priv->dev,
 			  "Cannot alloc more than the max num of Tx rings\n");
 		return -EINVAL;
 	}
 
-	if (cfg->start_idx == 0) {
-		tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
-			      GFP_KERNEL);
-		if (!tx)
-			return -ENOMEM;
-	} else if (!tx) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc tx rings from a nonzero start idx without tx array\n");
-		return -EINVAL;
-	}
+	tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
+		      GFP_KERNEL);
+	if (!tx)
+		return -ENOMEM;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) {
+	for (i = 0; i < total_queues; i++) {
 		err = gve_tx_alloc_ring_gqi(priv, cfg, &tx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -367,8 +366,7 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 cleanup:
 	for (j = 0; j < i; j++)
 		gve_tx_free_ring_gqi(priv, &tx[j], cfg);
-	if (cfg->start_idx == 0)
-		kvfree(tx);
+	kvfree(tx);
 	return err;
 }
 
@@ -381,13 +379,11 @@ void gve_tx_free_rings_gqi(struct gve_priv *priv,
 	if (!tx)
 		return;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++)
+	for (i = 0; i < cfg->qcfg->num_queues + cfg->qcfg->num_xdp_queues; i++)
 		gve_tx_free_ring_gqi(priv, &tx[i], cfg);
 
-	if (cfg->start_idx == 0) {
-		kvfree(tx);
-		cfg->tx = NULL;
-	}
+	kvfree(tx);
+	cfg->tx = NULL;
 }
 
 /* gve_tx_avail - Calculates the number of slots available in the ring
@@ -834,11 +830,14 @@ int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	struct gve_tx_ring *tx;
 	int i, err = 0, qid;
 
-	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK) || !priv->xdp_prog)
 		return -EINVAL;
 
+	if (!gve_get_napi_enabled(priv))
+		return -ENETDOWN;
+
 	qid = gve_xdp_tx_queue_id(priv,
-				  smp_processor_id() % priv->num_xdp_queues);
+				  smp_processor_id() % priv->tx_cfg.num_xdp_queues);
 
 	tx = &priv->tx[qid];
 
@@ -953,13 +952,9 @@ static int gve_xsk_tx(struct gve_priv *priv, struct gve_tx_ring *tx,
 
 	spin_lock(&tx->xdp_lock);
 	while (sent < budget) {
-		if (!gve_can_tx(tx, GVE_TX_START_THRESH))
-			goto out;
-
-		if (!xsk_tx_peek_desc(tx->xsk_pool, &desc)) {
-			tx->xdp_xsk_done = tx->xdp_xsk_wakeup;
+		if (!gve_can_tx(tx, GVE_TX_START_THRESH) ||
+		    !xsk_tx_peek_desc(tx->xsk_pool, &desc))
 			goto out;
-		}
 
 		data = xsk_buff_raw_get_data(tx->xsk_pool, desc.addr);
 		nsegs = gve_tx_fill_xdp(priv, tx, data, desc.len, NULL, true);
@@ -975,33 +970,41 @@ out:
 	return sent;
 }
 
+int gve_xsk_tx_poll(struct gve_notify_block *rx_block, int budget)
+{
+	struct gve_rx_ring *rx = rx_block->rx;
+	struct gve_priv *priv = rx->gve;
+	struct gve_tx_ring *tx;
+	int sent = 0;
+
+	tx = &priv->tx[gve_xdp_tx_queue_id(priv, rx->q_num)];
+	if (tx->xsk_pool) {
+		sent = gve_xsk_tx(priv, tx, budget);
+
+		u64_stats_update_begin(&tx->statss);
+		tx->xdp_xsk_sent += sent;
+		u64_stats_update_end(&tx->statss);
+		if (xsk_uses_need_wakeup(tx->xsk_pool))
+			xsk_set_tx_need_wakeup(tx->xsk_pool);
+	}
+
+	return sent;
+}
+
 bool gve_xdp_poll(struct gve_notify_block *block, int budget)
 {
 	struct gve_priv *priv = block->priv;
 	struct gve_tx_ring *tx = block->tx;
 	u32 nic_done;
-	bool repoll;
 	u32 to_do;
 
 	/* Find out how much work there is to be done */
 	nic_done = gve_tx_load_event_counter(priv, tx);
 	to_do = min_t(u32, (nic_done - tx->done), budget);
 	gve_clean_xdp_done(priv, tx, to_do);
-	repoll = nic_done != tx->done;
-
-	if (tx->xsk_pool) {
-		int sent = gve_xsk_tx(priv, tx, budget);
-
-		u64_stats_update_begin(&tx->statss);
-		tx->xdp_xsk_sent += sent;
-		u64_stats_update_end(&tx->statss);
-		repoll |= (sent == budget);
-		if (xsk_uses_need_wakeup(tx->xsk_pool))
-			xsk_set_tx_need_wakeup(tx->xsk_pool);
-	}
 
 	/* If we still have work we want to repoll */
-	return repoll;
+	return nic_done != tx->done;
 }
 
 bool gve_tx_poll(struct gve_notify_block *block, int budget)
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index f879426cb552..9d705d94b065 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -379,27 +379,23 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg)
 {
 	struct gve_tx_ring *tx = cfg->tx;
+	int total_queues;
 	int err = 0;
 	int i, j;
 
-	if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) {
+	total_queues = cfg->qcfg->num_queues + cfg->num_xdp_rings;
+	if (total_queues > cfg->qcfg->max_queues) {
 		netif_err(priv, drv, priv->dev,
 			  "Cannot alloc more than the max num of Tx rings\n");
 		return -EINVAL;
 	}
 
-	if (cfg->start_idx == 0) {
-		tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
-			      GFP_KERNEL);
-		if (!tx)
-			return -ENOMEM;
-	} else if (!tx) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc tx rings from a nonzero start idx without tx array\n");
-		return -EINVAL;
-	}
+	tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
+		      GFP_KERNEL);
+	if (!tx)
+		return -ENOMEM;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) {
+	for (i = 0; i < total_queues; i++) {
 		err = gve_tx_alloc_ring_dqo(priv, cfg, &tx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -415,8 +411,7 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv,
 err:
 	for (j = 0; j < i; j++)
 		gve_tx_free_ring_dqo(priv, &tx[j], cfg);
-	if (cfg->start_idx == 0)
-		kvfree(tx);
+	kvfree(tx);
 	return err;
 }
 
@@ -429,13 +424,11 @@ void gve_tx_free_rings_dqo(struct gve_priv *priv,
 	if (!tx)
 		return;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++)
+	for (i = 0; i < cfg->qcfg->num_queues + cfg->qcfg->num_xdp_queues; i++)
 		gve_tx_free_ring_dqo(priv, &tx[i], cfg);
 
-	if (cfg->start_idx == 0) {
-		kvfree(tx);
-		cfg->tx = NULL;
-	}
+	kvfree(tx);
+	cfg->tx = NULL;
 }
 
 /* Returns the number of slots available in the ring */
@@ -667,7 +660,8 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 			goto err;
 
 		dma_unmap_len_set(pkt, len[pkt->num_bufs], len);
-		dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr);
+		netmem_dma_unmap_addr_set(skb_frag_netmem(frag), pkt,
+					  dma[pkt->num_bufs], addr);
 		++pkt->num_bufs;
 
 		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb, len, addr,
@@ -770,6 +764,9 @@ static int gve_tx_add_skb_dqo(struct gve_tx_ring *tx,
 	s16 completion_tag;
 
 	pkt = gve_alloc_pending_packet(tx);
+	if (!pkt)
+		return -ENOMEM;
+
 	pkt->skb = skb;
 	completion_tag = pkt - tx->dqo.pending_packets;
 
@@ -1045,8 +1042,9 @@ static void gve_unmap_packet(struct device *dev,
 	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
 			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
 	for (i = 1; i < pkt->num_bufs; i++) {
-		dma_unmap_page(dev, dma_unmap_addr(pkt, dma[i]),
-			       dma_unmap_len(pkt, len[i]), DMA_TO_DEVICE);
+		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
+					    dma_unmap_len(pkt, len[i]),
+					    DMA_TO_DEVICE, 0);
 	}
 	pkt->num_bufs = 0;
 }
@@ -1146,8 +1144,7 @@ static void gve_handle_miss_completion(struct gve_priv *priv,
 	/* jiffies can wraparound but time comparisons can handle overflows. */
 	pending_packet->timeout_jiffies =
 			jiffies +
-			msecs_to_jiffies(GVE_REINJECT_COMPL_TIMEOUT *
-					 MSEC_PER_SEC);
+			secs_to_jiffies(GVE_REINJECT_COMPL_TIMEOUT);
 	add_to_list(tx, &tx->dqo_compl.miss_completions, pending_packet);
 
 	*bytes += pending_packet->skb->len;
@@ -1191,8 +1188,7 @@ static void remove_miss_completions(struct gve_priv *priv,
 		pending_packet->state = GVE_PACKET_STATE_TIMED_OUT_COMPL;
 		pending_packet->timeout_jiffies =
 				jiffies +
-				msecs_to_jiffies(GVE_DEALLOCATE_COMPL_TIMEOUT *
-						 MSEC_PER_SEC);
+				secs_to_jiffies(GVE_DEALLOCATE_COMPL_TIMEOUT);
 		/* Maintain pending packet in another list so the packet can be
 		 * unallocated at a later time.
 		 */
diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c
index 30fef100257e..ace9b8698021 100644
--- a/drivers/net/ethernet/google/gve/gve_utils.c
+++ b/drivers/net/ethernet/google/gve/gve_utils.c
@@ -110,13 +110,13 @@ void gve_add_napi(struct gve_priv *priv, int ntfy_idx,
 {
 	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
-	netif_napi_add(priv->dev, &block->napi, gve_poll);
-	netif_napi_set_irq(&block->napi, block->irq);
+	netif_napi_add_locked(priv->dev, &block->napi, gve_poll);
+	netif_napi_set_irq_locked(&block->napi, block->irq);
 }
 
 void gve_remove_napi(struct gve_priv *priv, int ntfy_idx)
 {
 	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
-	netif_napi_del(&block->napi);
+	netif_napi_del_locked(&block->napi);
 }
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/Makefile b/drivers/net/ethernet/hisilicon/hibmcge/Makefile
index ae58ac38c206..1a9da564b306 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/Makefile
+++ b/drivers/net/ethernet/hisilicon/hibmcge/Makefile
@@ -5,4 +5,5 @@
 
 obj-$(CONFIG_HIBMCGE) += hibmcge.o
 
-hibmcge-objs = hbg_main.o hbg_hw.o hbg_mdio.o hbg_irq.o hbg_txrx.o hbg_ethtool.o
+hibmcge-objs = hbg_main.o hbg_hw.o hbg_mdio.o hbg_irq.o hbg_txrx.o hbg_ethtool.o \
+		hbg_debugfs.o hbg_err.o hbg_diagnose.o
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
index 96daf058d387..7725cb0c5c8a 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
@@ -4,6 +4,7 @@
 #ifndef __HBG_COMMON_H
 #define __HBG_COMMON_H
 
+#include <linux/ethtool.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include "hbg_reg.h"
@@ -33,6 +34,16 @@ enum hbg_tx_state {
 
 enum hbg_nic_state {
 	HBG_NIC_STATE_EVENT_HANDLING = 0,
+	HBG_NIC_STATE_RESETTING,
+	HBG_NIC_STATE_RESET_FAIL,
+	HBG_NIC_STATE_NEED_RESET, /* trigger a reset in scheduled task */
+	HBG_NIC_STATE_NP_LINK_FAIL,
+};
+
+enum hbg_reset_type {
+	HBG_RESET_TYPE_NONE = 0,
+	HBG_RESET_TYPE_FLR,
+	HBG_RESET_TYPE_FUNCTION,
 };
 
 struct hbg_buffer {
@@ -72,6 +83,7 @@ enum hbg_hw_event_type {
 	HBG_HW_EVENT_NONE = 0,
 	HBG_HW_EVENT_INIT, /* driver is loading */
 	HBG_HW_EVENT_RESET,
+	HBG_HW_EVENT_CORE_RESET,
 };
 
 struct hbg_dev_specs {
@@ -84,6 +96,7 @@ struct hbg_dev_specs {
 	u32 vlan_layers;
 	u32 max_mtu;
 	u32 min_mtu;
+	u32 uc_mac_num;
 
 	u32 max_frame_len;
 	u32 rx_buf_size;
@@ -94,14 +107,17 @@ struct hbg_irq_info {
 	u32 mask;
 	bool re_enable;
 	bool need_print;
-	u64 count;
+	bool need_reset;
 
-	void (*irq_handle)(struct hbg_priv *priv, struct hbg_irq_info *info);
+	void (*irq_handle)(struct hbg_priv *priv,
+			   const struct hbg_irq_info *info);
 };
 
 struct hbg_vector {
 	char name[HBG_VECTOR_NUM][32];
-	struct hbg_irq_info *info_array;
+
+	u64 *stats_array;
+	const struct hbg_irq_info *info_array;
 	u32 info_array_len;
 };
 
@@ -114,6 +130,134 @@ struct hbg_mac {
 	u32 duplex;
 	u32 autoneg;
 	u32 link_status;
+	u32 pause_autoneg;
+};
+
+struct hbg_mac_table_entry {
+	u8 addr[ETH_ALEN];
+};
+
+struct hbg_mac_filter {
+	struct hbg_mac_table_entry *mac_table;
+	u32 table_max_len;
+	bool enabled;
+};
+
+/* saved for restore after rest */
+struct hbg_user_def {
+	struct ethtool_pauseparam pause_param;
+};
+
+struct hbg_stats {
+	u64 rx_desc_drop;
+	u64 rx_desc_l2_err_cnt;
+	u64 rx_desc_pkt_len_err_cnt;
+	u64 rx_desc_l3l4_err_cnt;
+	u64 rx_desc_l3_wrong_head_cnt;
+	u64 rx_desc_l3_csum_err_cnt;
+	u64 rx_desc_l3_len_err_cnt;
+	u64 rx_desc_l3_zero_ttl_cnt;
+	u64 rx_desc_l3_other_cnt;
+	u64 rx_desc_l4_err_cnt;
+	u64 rx_desc_l4_wrong_head_cnt;
+	u64 rx_desc_l4_len_err_cnt;
+	u64 rx_desc_l4_csum_err_cnt;
+	u64 rx_desc_l4_zero_port_num_cnt;
+	u64 rx_desc_l4_other_cnt;
+	u64 rx_desc_frag_cnt;
+	u64 rx_desc_ip_ver_err_cnt;
+	u64 rx_desc_ipv4_pkt_cnt;
+	u64 rx_desc_ipv6_pkt_cnt;
+	u64 rx_desc_no_ip_pkt_cnt;
+	u64 rx_desc_ip_pkt_cnt;
+	u64 rx_desc_tcp_pkt_cnt;
+	u64 rx_desc_udp_pkt_cnt;
+	u64 rx_desc_vlan_pkt_cnt;
+	u64 rx_desc_icmp_pkt_cnt;
+	u64 rx_desc_arp_pkt_cnt;
+	u64 rx_desc_rarp_pkt_cnt;
+	u64 rx_desc_multicast_pkt_cnt;
+	u64 rx_desc_broadcast_pkt_cnt;
+	u64 rx_desc_ipsec_pkt_cnt;
+	u64 rx_desc_ip_opt_pkt_cnt;
+	u64 rx_desc_key_not_match_cnt;
+
+	u64 rx_octets_total_ok_cnt;
+	u64 rx_uc_pkt_cnt;
+	u64 rx_mc_pkt_cnt;
+	u64 rx_bc_pkt_cnt;
+	u64 rx_vlan_pkt_cnt;
+	u64 rx_octets_bad_cnt;
+	u64 rx_octets_total_filt_cnt;
+	u64 rx_filt_pkt_cnt;
+	u64 rx_trans_pkt_cnt;
+	u64 rx_framesize_64;
+	u64 rx_framesize_65_127;
+	u64 rx_framesize_128_255;
+	u64 rx_framesize_256_511;
+	u64 rx_framesize_512_1023;
+	u64 rx_framesize_1024_1518;
+	u64 rx_framesize_bt_1518;
+	u64 rx_fcs_error_cnt;
+	u64 rx_data_error_cnt;
+	u64 rx_align_error_cnt;
+	u64 rx_pause_macctl_frame_cnt;
+	u64 rx_unknown_macctl_frame_cnt;
+	/* crc ok, > max_frm_size, < 2max_frm_size */
+	u64 rx_frame_long_err_cnt;
+	/* crc fail, > max_frm_size, < 2max_frm_size */
+	u64 rx_jabber_err_cnt;
+	/* > 2max_frm_size */
+	u64 rx_frame_very_long_err_cnt;
+	/* < 64byte, >= short_runts_thr */
+	u64 rx_frame_runt_err_cnt;
+	/* < short_runts_thr */
+	u64 rx_frame_short_err_cnt;
+	/* PCU: dropped when the RX FIFO is full.*/
+	u64 rx_overflow_cnt;
+	/* GMAC: the count of overflows of the RX FIFO */
+	u64 rx_overrun_cnt;
+	/* PCU: the count of buffer alloc errors in RX */
+	u64 rx_bufrq_err_cnt;
+	/* PCU: the count of write descriptor errors in RX */
+	u64 rx_we_err_cnt;
+	/* GMAC: the count of pkts that contain PAD but length is not 64 */
+	u64 rx_lengthfield_err_cnt;
+	u64 rx_fail_comma_cnt;
+
+	u64 rx_dma_err_cnt;
+	u64 rx_fifo_less_empty_thrsld_cnt;
+
+	u64 tx_octets_total_ok_cnt;
+	u64 tx_uc_pkt_cnt;
+	u64 tx_mc_pkt_cnt;
+	u64 tx_bc_pkt_cnt;
+	u64 tx_vlan_pkt_cnt;
+	u64 tx_octets_bad_cnt;
+	u64 tx_trans_pkt_cnt;
+	u64 tx_pause_frame_cnt;
+	u64 tx_framesize_64;
+	u64 tx_framesize_65_127;
+	u64 tx_framesize_128_255;
+	u64 tx_framesize_256_511;
+	u64 tx_framesize_512_1023;
+	u64 tx_framesize_1024_1518;
+	u64 tx_framesize_bt_1518;
+	/* GMAC: the count of times that frames fail to be transmitted
+	 *       due to internal errors.
+	 */
+	u64 tx_underrun_err_cnt;
+	u64 tx_add_cs_fail_cnt;
+	/* PCU: the count of buffer free errors in TX */
+	u64 tx_bufrl_err_cnt;
+	u64 tx_crc_err_cnt;
+	u64 tx_drop_cnt;
+	u64 tx_excessive_length_drop_cnt;
+
+	u64 tx_timeout_cnt;
+	u64 tx_dma_err_cnt;
+
+	u64 np_link_fail_cnt;
 };
 
 struct hbg_priv {
@@ -126,6 +270,15 @@ struct hbg_priv {
 	struct hbg_vector vectors;
 	struct hbg_ring tx_ring;
 	struct hbg_ring rx_ring;
+	struct hbg_mac_filter filter;
+	enum hbg_reset_type reset_type;
+	struct hbg_user_def user_def;
+	struct hbg_stats stats;
+	unsigned long last_update_stats_time;
+	struct delayed_work service_task;
 };
 
+void hbg_err_reset_task_schedule(struct hbg_priv *priv);
+void hbg_np_link_fail_task_schedule(struct hbg_priv *priv);
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
new file mode 100644
index 000000000000..01ad82d2f5cc
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2024 Hisilicon Limited.
+
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/etherdevice.h>
+#include <linux/seq_file.h>
+#include <linux/string_choices.h>
+#include "hbg_common.h"
+#include "hbg_debugfs.h"
+#include "hbg_hw.h"
+#include "hbg_irq.h"
+#include "hbg_txrx.h"
+
+static struct dentry *hbg_dbgfs_root;
+
+struct hbg_dbg_info {
+	const char *name;
+	int (*read)(struct seq_file *seq, void *data);
+};
+
+#define state_str_true_false(p, s) str_true_false(test_bit(s, &(p)->state))
+
+static void hbg_dbg_ring(struct hbg_priv *priv, struct hbg_ring *ring,
+			 struct seq_file *s)
+{
+	u32 irq_mask = ring->dir == HBG_DIR_TX ? HBG_INT_MSK_TX_B :
+						 HBG_INT_MSK_RX_B;
+
+	seq_printf(s, "ring used num: %u\n",
+		   hbg_get_queue_used_num(ring));
+	seq_printf(s, "ring max num: %u\n", ring->len);
+	seq_printf(s, "ring head: %u, tail: %u\n", ring->head, ring->tail);
+	seq_printf(s, "fifo used num: %u\n",
+		   hbg_hw_get_fifo_used_num(priv, ring->dir));
+	seq_printf(s, "fifo max num: %u\n",
+		   hbg_get_spec_fifo_max_num(priv, ring->dir));
+	seq_printf(s, "irq enabled: %s\n",
+		   str_true_false(hbg_hw_irq_is_enabled(priv, irq_mask)));
+}
+
+static int hbg_dbg_tx_ring(struct seq_file *s, void *unused)
+{
+	struct net_device *netdev = dev_get_drvdata(s->private);
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	hbg_dbg_ring(priv, &priv->tx_ring, s);
+	return 0;
+}
+
+static int hbg_dbg_rx_ring(struct seq_file *s, void *unused)
+{
+	struct net_device *netdev = dev_get_drvdata(s->private);
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	hbg_dbg_ring(priv, &priv->rx_ring, s);
+	return 0;
+}
+
+static int hbg_dbg_irq_info(struct seq_file *s, void *unused)
+{
+	struct net_device *netdev = dev_get_drvdata(s->private);
+	struct hbg_priv *priv = netdev_priv(netdev);
+	const struct hbg_irq_info *info;
+	u32 i;
+
+	for (i = 0; i < priv->vectors.info_array_len; i++) {
+		info = &priv->vectors.info_array[i];
+		seq_printf(s,
+			   "%-20s: enabled: %-5s, reset: %-5s, logged: %-5s, count: %llu\n",
+			   info->name,
+			   str_true_false(hbg_hw_irq_is_enabled(priv,
+								info->mask)),
+			   str_true_false(info->need_reset),
+			   str_true_false(info->need_print),
+			   priv->vectors.stats_array[i]);
+	}
+
+	return 0;
+}
+
+static int hbg_dbg_mac_table(struct seq_file *s, void *unused)
+{
+	struct net_device *netdev = dev_get_drvdata(s->private);
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_mac_filter *filter;
+	u32 i;
+
+	filter = &priv->filter;
+	seq_printf(s, "mac addr max count: %u\n", filter->table_max_len);
+	seq_printf(s, "filter enabled: %s\n", str_true_false(filter->enabled));
+
+	for (i = 0; i < filter->table_max_len; i++) {
+		if (is_zero_ether_addr(filter->mac_table[i].addr))
+			continue;
+
+		seq_printf(s, "[%u] %pM\n", i, filter->mac_table[i].addr);
+	}
+
+	return 0;
+}
+
+static const char * const reset_type_str[] = {"None", "FLR", "Function"};
+
+static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
+{
+	struct net_device *netdev = dev_get_drvdata(s->private);
+	struct hbg_priv *priv = netdev_priv(netdev);
+	bool np_link_fail;
+
+	seq_printf(s, "event handling state: %s\n",
+		   state_str_true_false(priv, HBG_NIC_STATE_EVENT_HANDLING));
+	seq_printf(s, "resetting state: %s\n",
+		   state_str_true_false(priv, HBG_NIC_STATE_RESETTING));
+	seq_printf(s, "reset fail state: %s\n",
+		   state_str_true_false(priv, HBG_NIC_STATE_RESET_FAIL));
+	seq_printf(s, "last reset type: %s\n",
+		   reset_type_str[priv->reset_type]);
+	seq_printf(s, "need reset state: %s\n",
+		   state_str_true_false(priv, HBG_NIC_STATE_NEED_RESET));
+
+	np_link_fail = !hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+					   HBG_REG_AN_NEG_STATE_NP_LINK_OK_B);
+	seq_printf(s, "np_link fail state: %s\n", str_true_false(np_link_fail));
+
+	return 0;
+}
+
+static const struct hbg_dbg_info hbg_dbg_infos[] = {
+	{ "tx_ring", hbg_dbg_tx_ring },
+	{ "rx_ring", hbg_dbg_rx_ring },
+	{ "irq_info", hbg_dbg_irq_info },
+	{ "mac_table", hbg_dbg_mac_table },
+	{ "nic_state", hbg_dbg_nic_state },
+};
+
+static void hbg_debugfs_uninit(void *data)
+{
+	debugfs_remove_recursive((struct dentry *)data);
+}
+
+void hbg_debugfs_init(struct hbg_priv *priv)
+{
+	const char *name = pci_name(priv->pdev);
+	struct device *dev = &priv->pdev->dev;
+	struct dentry *root;
+	u32 i;
+
+	root = debugfs_create_dir(name, hbg_dbgfs_root);
+
+	for (i = 0; i < ARRAY_SIZE(hbg_dbg_infos); i++)
+		debugfs_create_devm_seqfile(dev, hbg_dbg_infos[i].name,
+					    root, hbg_dbg_infos[i].read);
+
+	/* Ignore the failure because debugfs is not a key feature. */
+	devm_add_action_or_reset(dev, hbg_debugfs_uninit, root);
+}
+
+void hbg_debugfs_register(void)
+{
+	hbg_dbgfs_root = debugfs_create_dir("hibmcge", NULL);
+}
+
+void hbg_debugfs_unregister(void)
+{
+	debugfs_remove_recursive(hbg_dbgfs_root);
+	hbg_dbgfs_root = NULL;
+}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.h
new file mode 100644
index 000000000000..80670d66bbeb
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2024 Hisilicon Limited. */
+
+#ifndef __HBG_DEBUGFS_H
+#define __HBG_DEBUGFS_H
+
+void hbg_debugfs_register(void);
+void hbg_debugfs_unregister(void);
+
+void hbg_debugfs_init(struct hbg_priv *priv);
+
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
new file mode 100644
index 000000000000..f23fb5920c3c
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2025 Hisilicon Limited.
+
+#include <linux/iopoll.h>
+#include <linux/phy.h>
+#include "hbg_common.h"
+#include "hbg_ethtool.h"
+#include "hbg_hw.h"
+#include "hbg_diagnose.h"
+
+#define HBG_MSG_DATA_MAX_NUM	64
+
+struct hbg_diagnose_message {
+	u32 opcode;
+	u32 status;
+	u32 data_num;
+	struct hbg_priv *priv;
+
+	u32 data[HBG_MSG_DATA_MAX_NUM];
+};
+
+#define HBG_HW_PUSH_WAIT_TIMEOUT_US	(2 * 1000 * 1000)
+#define HBG_HW_PUSH_WAIT_INTERVAL_US	(1 * 1000)
+
+enum hbg_push_cmd {
+	HBG_PUSH_CMD_IRQ = 0,
+	HBG_PUSH_CMD_STATS,
+	HBG_PUSH_CMD_LINK,
+};
+
+struct hbg_push_stats_info {
+	/* id is used to match the name of the current stats item.
+	 * and is used for pretty print on BMC
+	 */
+	u32 id;
+	u64 offset;
+};
+
+struct hbg_push_irq_info {
+	/* id is used to match the name of the current irq.
+	 * and is used for pretty print on BMC
+	 */
+	u32 id;
+	u32 mask;
+};
+
+#define HBG_PUSH_IRQ_I(name, id) {id, HBG_INT_MSK_##name##_B}
+static const struct hbg_push_irq_info hbg_push_irq_list[] = {
+	HBG_PUSH_IRQ_I(RX, 0),
+	HBG_PUSH_IRQ_I(TX, 1),
+	HBG_PUSH_IRQ_I(TX_PKT_CPL, 2),
+	HBG_PUSH_IRQ_I(MAC_MII_FIFO_ERR, 3),
+	HBG_PUSH_IRQ_I(MAC_PCS_RX_FIFO_ERR, 4),
+	HBG_PUSH_IRQ_I(MAC_PCS_TX_FIFO_ERR, 5),
+	HBG_PUSH_IRQ_I(MAC_APP_RX_FIFO_ERR, 6),
+	HBG_PUSH_IRQ_I(MAC_APP_TX_FIFO_ERR, 7),
+	HBG_PUSH_IRQ_I(SRAM_PARITY_ERR, 8),
+	HBG_PUSH_IRQ_I(TX_AHB_ERR, 9),
+	HBG_PUSH_IRQ_I(RX_BUF_AVL, 10),
+	HBG_PUSH_IRQ_I(REL_BUF_ERR, 11),
+	HBG_PUSH_IRQ_I(TXCFG_AVL, 12),
+	HBG_PUSH_IRQ_I(TX_DROP, 13),
+	HBG_PUSH_IRQ_I(RX_DROP, 14),
+	HBG_PUSH_IRQ_I(RX_AHB_ERR, 15),
+	HBG_PUSH_IRQ_I(MAC_FIFO_ERR, 16),
+	HBG_PUSH_IRQ_I(RBREQ_ERR, 17),
+	HBG_PUSH_IRQ_I(WE_ERR, 18),
+};
+
+#define HBG_PUSH_STATS_I(name, id) {id, HBG_STATS_FIELD_OFF(name)}
+static const struct hbg_push_stats_info hbg_push_stats_list[] = {
+	HBG_PUSH_STATS_I(rx_desc_drop, 0),
+	HBG_PUSH_STATS_I(rx_desc_l2_err_cnt, 1),
+	HBG_PUSH_STATS_I(rx_desc_pkt_len_err_cnt, 2),
+	HBG_PUSH_STATS_I(rx_desc_l3_wrong_head_cnt, 3),
+	HBG_PUSH_STATS_I(rx_desc_l3_csum_err_cnt, 4),
+	HBG_PUSH_STATS_I(rx_desc_l3_len_err_cnt, 5),
+	HBG_PUSH_STATS_I(rx_desc_l3_zero_ttl_cnt, 6),
+	HBG_PUSH_STATS_I(rx_desc_l3_other_cnt, 7),
+	HBG_PUSH_STATS_I(rx_desc_l4_err_cnt, 8),
+	HBG_PUSH_STATS_I(rx_desc_l4_wrong_head_cnt, 9),
+	HBG_PUSH_STATS_I(rx_desc_l4_len_err_cnt, 10),
+	HBG_PUSH_STATS_I(rx_desc_l4_csum_err_cnt, 11),
+	HBG_PUSH_STATS_I(rx_desc_l4_zero_port_num_cnt, 12),
+	HBG_PUSH_STATS_I(rx_desc_l4_other_cnt, 13),
+	HBG_PUSH_STATS_I(rx_desc_frag_cnt, 14),
+	HBG_PUSH_STATS_I(rx_desc_ip_ver_err_cnt, 15),
+	HBG_PUSH_STATS_I(rx_desc_ipv4_pkt_cnt, 16),
+	HBG_PUSH_STATS_I(rx_desc_ipv6_pkt_cnt, 17),
+	HBG_PUSH_STATS_I(rx_desc_no_ip_pkt_cnt, 18),
+	HBG_PUSH_STATS_I(rx_desc_ip_pkt_cnt, 19),
+	HBG_PUSH_STATS_I(rx_desc_tcp_pkt_cnt, 20),
+	HBG_PUSH_STATS_I(rx_desc_udp_pkt_cnt, 21),
+	HBG_PUSH_STATS_I(rx_desc_vlan_pkt_cnt, 22),
+	HBG_PUSH_STATS_I(rx_desc_icmp_pkt_cnt, 23),
+	HBG_PUSH_STATS_I(rx_desc_arp_pkt_cnt, 24),
+	HBG_PUSH_STATS_I(rx_desc_rarp_pkt_cnt, 25),
+	HBG_PUSH_STATS_I(rx_desc_multicast_pkt_cnt, 26),
+	HBG_PUSH_STATS_I(rx_desc_broadcast_pkt_cnt, 27),
+	HBG_PUSH_STATS_I(rx_desc_ipsec_pkt_cnt, 28),
+	HBG_PUSH_STATS_I(rx_desc_ip_opt_pkt_cnt, 29),
+	HBG_PUSH_STATS_I(rx_desc_key_not_match_cnt, 30),
+	HBG_PUSH_STATS_I(rx_octets_total_ok_cnt, 31),
+	HBG_PUSH_STATS_I(rx_uc_pkt_cnt, 32),
+	HBG_PUSH_STATS_I(rx_mc_pkt_cnt, 33),
+	HBG_PUSH_STATS_I(rx_bc_pkt_cnt, 34),
+	HBG_PUSH_STATS_I(rx_vlan_pkt_cnt, 35),
+	HBG_PUSH_STATS_I(rx_octets_bad_cnt, 36),
+	HBG_PUSH_STATS_I(rx_octets_total_filt_cnt, 37),
+	HBG_PUSH_STATS_I(rx_filt_pkt_cnt, 38),
+	HBG_PUSH_STATS_I(rx_trans_pkt_cnt, 39),
+	HBG_PUSH_STATS_I(rx_framesize_64, 40),
+	HBG_PUSH_STATS_I(rx_framesize_65_127, 41),
+	HBG_PUSH_STATS_I(rx_framesize_128_255, 42),
+	HBG_PUSH_STATS_I(rx_framesize_256_511, 43),
+	HBG_PUSH_STATS_I(rx_framesize_512_1023, 44),
+	HBG_PUSH_STATS_I(rx_framesize_1024_1518, 45),
+	HBG_PUSH_STATS_I(rx_framesize_bt_1518, 46),
+	HBG_PUSH_STATS_I(rx_fcs_error_cnt, 47),
+	HBG_PUSH_STATS_I(rx_data_error_cnt, 48),
+	HBG_PUSH_STATS_I(rx_align_error_cnt, 49),
+	HBG_PUSH_STATS_I(rx_frame_long_err_cnt, 50),
+	HBG_PUSH_STATS_I(rx_jabber_err_cnt, 51),
+	HBG_PUSH_STATS_I(rx_pause_macctl_frame_cnt, 52),
+	HBG_PUSH_STATS_I(rx_unknown_macctl_frame_cnt, 53),
+	HBG_PUSH_STATS_I(rx_frame_very_long_err_cnt, 54),
+	HBG_PUSH_STATS_I(rx_frame_runt_err_cnt, 55),
+	HBG_PUSH_STATS_I(rx_frame_short_err_cnt, 56),
+	HBG_PUSH_STATS_I(rx_overflow_cnt, 57),
+	HBG_PUSH_STATS_I(rx_bufrq_err_cnt, 58),
+	HBG_PUSH_STATS_I(rx_we_err_cnt, 59),
+	HBG_PUSH_STATS_I(rx_overrun_cnt, 60),
+	HBG_PUSH_STATS_I(rx_lengthfield_err_cnt, 61),
+	HBG_PUSH_STATS_I(rx_fail_comma_cnt, 62),
+	HBG_PUSH_STATS_I(rx_dma_err_cnt, 63),
+	HBG_PUSH_STATS_I(rx_fifo_less_empty_thrsld_cnt, 64),
+	HBG_PUSH_STATS_I(tx_octets_total_ok_cnt, 65),
+	HBG_PUSH_STATS_I(tx_uc_pkt_cnt, 66),
+	HBG_PUSH_STATS_I(tx_mc_pkt_cnt, 67),
+	HBG_PUSH_STATS_I(tx_bc_pkt_cnt, 68),
+	HBG_PUSH_STATS_I(tx_vlan_pkt_cnt, 69),
+	HBG_PUSH_STATS_I(tx_octets_bad_cnt, 70),
+	HBG_PUSH_STATS_I(tx_trans_pkt_cnt, 71),
+	HBG_PUSH_STATS_I(tx_pause_frame_cnt, 72),
+	HBG_PUSH_STATS_I(tx_framesize_64, 73),
+	HBG_PUSH_STATS_I(tx_framesize_65_127, 74),
+	HBG_PUSH_STATS_I(tx_framesize_128_255, 75),
+	HBG_PUSH_STATS_I(tx_framesize_256_511, 76),
+	HBG_PUSH_STATS_I(tx_framesize_512_1023, 77),
+	HBG_PUSH_STATS_I(tx_framesize_1024_1518, 78),
+	HBG_PUSH_STATS_I(tx_framesize_bt_1518, 79),
+	HBG_PUSH_STATS_I(tx_underrun_err_cnt, 80),
+	HBG_PUSH_STATS_I(tx_add_cs_fail_cnt, 81),
+	HBG_PUSH_STATS_I(tx_bufrl_err_cnt, 82),
+	HBG_PUSH_STATS_I(tx_crc_err_cnt, 83),
+	HBG_PUSH_STATS_I(tx_drop_cnt, 84),
+	HBG_PUSH_STATS_I(tx_excessive_length_drop_cnt, 85),
+	HBG_PUSH_STATS_I(tx_dma_err_cnt, 86),
+};
+
+static int hbg_push_msg_send(struct hbg_priv *priv,
+			     struct hbg_diagnose_message *msg)
+{
+	u32 header = 0;
+	u32 i;
+
+	if (msg->data_num == 0)
+		return 0;
+
+	for (i = 0; i < msg->data_num && i < HBG_MSG_DATA_MAX_NUM; i++)
+		hbg_reg_write(priv,
+			      HBG_REG_MSG_DATA_BASE_ADDR + i * sizeof(u32),
+			      msg->data[i]);
+
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_OPCODE_M, msg->opcode);
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_DATA_NUM_M,  msg->data_num);
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_RESP_CODE_M, ETIMEDOUT);
+
+	/* start status */
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_STATUS_M, 1);
+
+	/* write header msg to start push */
+	hbg_reg_write(priv, HBG_REG_MSG_HEADER_ADDR, header);
+
+	/* wait done */
+	readl_poll_timeout(priv->io_base + HBG_REG_MSG_HEADER_ADDR, header,
+			   !FIELD_GET(HBG_REG_MSG_HEADER_STATUS_M, header),
+			   HBG_HW_PUSH_WAIT_INTERVAL_US,
+			   HBG_HW_PUSH_WAIT_TIMEOUT_US);
+
+	msg->status = FIELD_GET(HBG_REG_MSG_HEADER_STATUS_M, header);
+	return -(int)FIELD_GET(HBG_REG_MSG_HEADER_RESP_CODE_M, header);
+}
+
+static int hbg_push_data(struct hbg_priv *priv,
+			 u32 opcode, u32 *data, u32 data_num)
+{
+	struct hbg_diagnose_message msg = {0};
+	u32 data_left_num;
+	u32 i, j;
+	int ret;
+
+	msg.priv = priv;
+	msg.opcode = opcode;
+	for (i = 0; i < data_num / HBG_MSG_DATA_MAX_NUM + 1; i++) {
+		if (i * HBG_MSG_DATA_MAX_NUM >= data_num)
+			break;
+
+		data_left_num = data_num - i * HBG_MSG_DATA_MAX_NUM;
+		for (j = 0; j < data_left_num && j < HBG_MSG_DATA_MAX_NUM; j++)
+			msg.data[j] = data[i * HBG_MSG_DATA_MAX_NUM + j];
+
+		msg.data_num = j;
+		ret = hbg_push_msg_send(priv, &msg);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hbg_push_data_u64(struct hbg_priv *priv, u32 opcode,
+			     u64 *data, u32 data_num)
+{
+	/* The length of u64 is twice that of u32,
+	 * the data_num must be multiplied by 2.
+	 */
+	return hbg_push_data(priv, opcode, (u32 *)data, data_num * 2);
+}
+
+static u64 hbg_get_irq_stats(struct hbg_vector *vectors, u32 mask)
+{
+	u32 i = 0;
+
+	for (i = 0; i < vectors->info_array_len; i++)
+		if (vectors->info_array[i].mask == mask)
+			return vectors->stats_array[i];
+
+	return 0;
+}
+
+static int hbg_push_irq_cnt(struct hbg_priv *priv)
+{
+	/* An id needs to be added for each data.
+	 * Therefore, the data_num must be multiplied by 2.
+	 */
+	u32 data_num = ARRAY_SIZE(hbg_push_irq_list) * 2;
+	struct hbg_vector *vectors = &priv->vectors;
+	const struct hbg_push_irq_info *info;
+	u32 i, j = 0;
+	u64 *data;
+	int ret;
+
+	data = kcalloc(data_num, sizeof(u64), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* An id needs to be added for each data.
+	 * So i + 2 for each loop.
+	 */
+	for (i = 0; i < data_num; i += 2) {
+		info = &hbg_push_irq_list[j++];
+		data[i] = info->id;
+		data[i + 1] = hbg_get_irq_stats(vectors, info->mask);
+	}
+
+	ret = hbg_push_data_u64(priv, HBG_PUSH_CMD_IRQ, data, data_num);
+	kfree(data);
+	return ret;
+}
+
+static int hbg_push_link_status(struct hbg_priv *priv)
+{
+	u32 link_status[2];
+
+	/* phy link status */
+	link_status[0] = priv->mac.phydev->link;
+	/* mac link status */
+	link_status[1] = hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+					    HBG_REG_AN_NEG_STATE_NP_LINK_OK_B);
+
+	return hbg_push_data(priv, HBG_PUSH_CMD_LINK,
+			     link_status, ARRAY_SIZE(link_status));
+}
+
+static int hbg_push_stats(struct hbg_priv *priv)
+{
+	/* An id needs to be added for each data.
+	 * Therefore, the data_num must be multiplied by 2.
+	 */
+	u64 data_num = ARRAY_SIZE(hbg_push_stats_list) * 2;
+	struct hbg_stats *stats = &priv->stats;
+	const struct hbg_push_stats_info *info;
+	u32 i, j = 0;
+	u64 *data;
+	int ret;
+
+	data = kcalloc(data_num, sizeof(u64), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* An id needs to be added for each data.
+	 * So i + 2 for each loop.
+	 */
+	for (i = 0; i < data_num; i += 2) {
+		info = &hbg_push_stats_list[j++];
+		data[i] = info->id;
+		data[i + 1] = HBG_STATS_R(stats, info->offset);
+	}
+
+	ret = hbg_push_data_u64(priv, HBG_PUSH_CMD_STATS, data, data_num);
+	kfree(data);
+	return ret;
+}
+
+void hbg_diagnose_message_push(struct hbg_priv *priv)
+{
+	int ret;
+
+	if (test_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+		return;
+
+	/* only 1 is the right value */
+	if (hbg_reg_read(priv, HBG_REG_PUSH_REQ_ADDR) != 1)
+		return;
+
+	ret = hbg_push_irq_cnt(priv);
+	if (ret) {
+		dev_err(&priv->pdev->dev,
+			"failed to push irq cnt, ret = %d\n", ret);
+		goto push_done;
+	}
+
+	ret = hbg_push_link_status(priv);
+	if (ret) {
+		dev_err(&priv->pdev->dev,
+			"failed to push link status, ret = %d\n", ret);
+		goto push_done;
+	}
+
+	ret = hbg_push_stats(priv);
+	if (ret)
+		dev_err(&priv->pdev->dev,
+			"failed to push stats, ret = %d\n", ret);
+
+push_done:
+	hbg_reg_write(priv, HBG_REG_PUSH_REQ_ADDR, 0);
+}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h
new file mode 100644
index 000000000000..ba04c6d8c03d
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2025 Hisilicon Limited. */
+
+#ifndef __HBG_DIAGNOSE_H
+#define __HBG_DIAGNOSE_H
+
+#include "hbg_common.h"
+
+void hbg_diagnose_message_push(struct hbg_priv *priv);
+
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
new file mode 100644
index 000000000000..ff3295b60a69
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2024 Hisilicon Limited.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/rtnetlink.h>
+#include "hbg_common.h"
+#include "hbg_err.h"
+#include "hbg_hw.h"
+
+static void hbg_restore_mac_table(struct hbg_priv *priv)
+{
+	struct hbg_mac_filter *filter = &priv->filter;
+	u64 addr;
+	u32 i;
+
+	for (i = 0; i < filter->table_max_len; i++)
+		if (!is_zero_ether_addr(filter->mac_table[i].addr)) {
+			addr = ether_addr_to_u64(filter->mac_table[i].addr);
+			hbg_hw_set_uc_addr(priv, addr, i);
+		}
+
+	hbg_hw_set_mac_filter_enable(priv, priv->filter.enabled);
+}
+
+static void hbg_restore_user_def_settings(struct hbg_priv *priv)
+{
+	/* The index of host mac is always 0. */
+	u64 rx_pause_addr = ether_addr_to_u64(priv->filter.mac_table[0].addr);
+	struct ethtool_pauseparam *pause_param = &priv->user_def.pause_param;
+
+	hbg_restore_mac_table(priv);
+	hbg_hw_set_mtu(priv, priv->netdev->mtu);
+	hbg_hw_set_pause_enable(priv, pause_param->tx_pause,
+				pause_param->rx_pause);
+	hbg_hw_set_rx_pause_mac_addr(priv, rx_pause_addr);
+}
+
+int hbg_rebuild(struct hbg_priv *priv)
+{
+	int ret;
+
+	ret = hbg_hw_init(priv);
+	if (ret)
+		return ret;
+
+	hbg_restore_user_def_settings(priv);
+	return 0;
+}
+
+static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
+{
+	int ret;
+
+	ASSERT_RTNL();
+
+	if (netif_running(priv->netdev)) {
+		dev_warn(&priv->pdev->dev,
+			 "failed to reset because port is up\n");
+		return -EBUSY;
+	}
+
+	netif_device_detach(priv->netdev);
+
+	priv->reset_type = type;
+	set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
+	clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
+	ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET);
+	if (ret) {
+		set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
+		clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
+	}
+
+	return ret;
+}
+
+static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
+{
+	int ret;
+
+	if (!test_bit(HBG_NIC_STATE_RESETTING, &priv->state) ||
+	    type != priv->reset_type)
+		return 0;
+
+	ASSERT_RTNL();
+
+	clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
+	ret = hbg_rebuild(priv);
+	if (ret) {
+		set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
+		dev_err(&priv->pdev->dev, "failed to rebuild after reset\n");
+		return ret;
+	}
+
+	netif_device_attach(priv->netdev);
+
+	dev_info(&priv->pdev->dev, "reset done\n");
+	return ret;
+}
+
+/* must be protected by rtnl lock */
+int hbg_reset(struct hbg_priv *priv)
+{
+	int ret;
+
+	ASSERT_RTNL();
+	ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION);
+	if (ret)
+		return ret;
+
+	return hbg_reset_done(priv, HBG_RESET_TYPE_FUNCTION);
+}
+
+void hbg_err_reset(struct hbg_priv *priv)
+{
+	bool running;
+
+	rtnl_lock();
+	running = netif_running(priv->netdev);
+	if (running)
+		dev_close(priv->netdev);
+
+	if (hbg_reset(priv))
+		goto err_unlock;
+
+	if (running)
+		dev_open(priv->netdev, NULL);
+
+err_unlock:
+	rtnl_unlock();
+}
+
+static pci_ers_result_t hbg_pci_err_detected(struct pci_dev *pdev,
+					     pci_channel_state_t state)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+
+	netif_device_detach(netdev);
+
+	if (state == pci_channel_io_perm_failure)
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	pci_disable_device(pdev);
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t hbg_pci_err_slot_reset(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	if (pci_enable_device(pdev)) {
+		dev_err(&pdev->dev,
+			"failed to re-enable PCI device after reset\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	pci_set_master(pdev);
+	pci_restore_state(pdev);
+	pci_save_state(pdev);
+
+	hbg_err_reset(priv);
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+static void hbg_pci_err_reset_prepare(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	rtnl_lock();
+	hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR);
+}
+
+static void hbg_pci_err_reset_done(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	hbg_reset_done(priv, HBG_RESET_TYPE_FLR);
+	rtnl_unlock();
+}
+
+static const struct pci_error_handlers hbg_pci_err_handler = {
+	.error_detected = hbg_pci_err_detected,
+	.slot_reset = hbg_pci_err_slot_reset,
+	.reset_prepare = hbg_pci_err_reset_prepare,
+	.reset_done = hbg_pci_err_reset_done,
+};
+
+void hbg_set_pci_err_handler(struct pci_driver *pdrv)
+{
+	pdrv->err_handler = &hbg_pci_err_handler;
+}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h
new file mode 100644
index 000000000000..fb9fbe7004e8
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2024 Hisilicon Limited. */
+
+#ifndef __HBG_ERR_H
+#define __HBG_ERR_H
+
+#include <linux/pci.h>
+
+void hbg_set_pci_err_handler(struct pci_driver *pdrv);
+int hbg_reset(struct hbg_priv *priv);
+int hbg_rebuild(struct hbg_priv *priv);
+void hbg_err_reset(struct hbg_priv *priv);
+
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
index c3370114aef3..55520053270a 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
@@ -3,12 +3,494 @@
 
 #include <linux/ethtool.h>
 #include <linux/phy.h>
+#include <linux/rtnetlink.h>
+#include "hbg_common.h"
+#include "hbg_err.h"
 #include "hbg_ethtool.h"
+#include "hbg_hw.h"
+
+struct hbg_ethtool_stats {
+	char name[ETH_GSTRING_LEN];
+	unsigned long offset;
+	u32 reg; /* set to 0 if stats is not updated via dump reg */
+};
+
+#define HBG_STATS_I(stats) { #stats, HBG_STATS_FIELD_OFF(stats), 0}
+#define HBG_STATS_REG_I(stats, reg) { #stats, HBG_STATS_FIELD_OFF(stats), reg}
+
+static const struct hbg_ethtool_stats hbg_ethtool_stats_info[] = {
+	HBG_STATS_I(rx_desc_l2_err_cnt),
+	HBG_STATS_I(rx_desc_pkt_len_err_cnt),
+	HBG_STATS_I(rx_desc_l3_wrong_head_cnt),
+	HBG_STATS_I(rx_desc_l3_csum_err_cnt),
+	HBG_STATS_I(rx_desc_l3_len_err_cnt),
+	HBG_STATS_I(rx_desc_l3_zero_ttl_cnt),
+	HBG_STATS_I(rx_desc_l3_other_cnt),
+	HBG_STATS_I(rx_desc_l4_wrong_head_cnt),
+	HBG_STATS_I(rx_desc_l4_len_err_cnt),
+	HBG_STATS_I(rx_desc_l4_csum_err_cnt),
+	HBG_STATS_I(rx_desc_l4_zero_port_num_cnt),
+	HBG_STATS_I(rx_desc_l4_other_cnt),
+	HBG_STATS_I(rx_desc_ip_ver_err_cnt),
+	HBG_STATS_I(rx_desc_ipv4_pkt_cnt),
+	HBG_STATS_I(rx_desc_ipv6_pkt_cnt),
+	HBG_STATS_I(rx_desc_no_ip_pkt_cnt),
+	HBG_STATS_I(rx_desc_ip_pkt_cnt),
+	HBG_STATS_I(rx_desc_tcp_pkt_cnt),
+	HBG_STATS_I(rx_desc_udp_pkt_cnt),
+	HBG_STATS_I(rx_desc_vlan_pkt_cnt),
+	HBG_STATS_I(rx_desc_icmp_pkt_cnt),
+	HBG_STATS_I(rx_desc_arp_pkt_cnt),
+	HBG_STATS_I(rx_desc_rarp_pkt_cnt),
+	HBG_STATS_I(rx_desc_multicast_pkt_cnt),
+	HBG_STATS_I(rx_desc_broadcast_pkt_cnt),
+	HBG_STATS_I(rx_desc_ipsec_pkt_cnt),
+	HBG_STATS_I(rx_desc_ip_opt_pkt_cnt),
+	HBG_STATS_I(rx_desc_key_not_match_cnt),
+
+	HBG_STATS_REG_I(rx_octets_bad_cnt, HBG_REG_RX_OCTETS_BAD_ADDR),
+	HBG_STATS_REG_I(rx_octets_total_filt_cnt,
+			HBG_REG_RX_OCTETS_TOTAL_FILT_ADDR),
+	HBG_STATS_REG_I(rx_uc_pkt_cnt, HBG_REG_RX_UC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_vlan_pkt_cnt, HBG_REG_RX_TAGGED_ADDR),
+	HBG_STATS_REG_I(rx_filt_pkt_cnt, HBG_REG_RX_FILT_PKT_CNT_ADDR),
+	HBG_STATS_REG_I(rx_data_error_cnt, HBG_REG_RX_DATA_ERR_ADDR),
+	HBG_STATS_REG_I(rx_frame_long_err_cnt, HBG_REG_RX_LONG_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_jabber_err_cnt, HBG_REG_RX_JABBER_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_frame_very_long_err_cnt,
+			HBG_REG_RX_VERY_LONG_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_frame_runt_err_cnt, HBG_REG_RX_RUNT_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_frame_short_err_cnt, HBG_REG_RX_SHORT_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_overflow_cnt, HBG_REG_RX_OVER_FLOW_CNT_ADDR),
+	HBG_STATS_REG_I(rx_bufrq_err_cnt, HBG_REG_RX_BUFRQ_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_we_err_cnt, HBG_REG_RX_WE_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_overrun_cnt, HBG_REG_RX_OVERRUN_CNT_ADDR),
+	HBG_STATS_REG_I(rx_lengthfield_err_cnt,
+			HBG_REG_RX_LENGTHFIELD_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_fail_comma_cnt, HBG_REG_RX_FAIL_COMMA_CNT_ADDR),
+	HBG_STATS_I(rx_dma_err_cnt),
+	HBG_STATS_I(rx_fifo_less_empty_thrsld_cnt),
+
+	HBG_STATS_REG_I(tx_uc_pkt_cnt, HBG_REG_TX_UC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_vlan_pkt_cnt, HBG_REG_TX_TAGGED_ADDR),
+	HBG_STATS_REG_I(tx_octets_bad_cnt, HBG_REG_OCTETS_TRANSMITTED_BAD_ADDR),
+
+	HBG_STATS_REG_I(tx_underrun_err_cnt, HBG_REG_TX_UNDERRUN_ADDR),
+	HBG_STATS_REG_I(tx_add_cs_fail_cnt, HBG_REG_TX_CS_FAIL_CNT_ADDR),
+	HBG_STATS_REG_I(tx_bufrl_err_cnt, HBG_REG_TX_BUFRL_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(tx_crc_err_cnt, HBG_REG_TX_CRC_ERROR_ADDR),
+	HBG_STATS_REG_I(tx_drop_cnt, HBG_REG_TX_DROP_CNT_ADDR),
+	HBG_STATS_REG_I(tx_excessive_length_drop_cnt,
+			HBG_REG_TX_EXCESSIVE_LENGTH_DROP_ADDR),
+	HBG_STATS_I(tx_dma_err_cnt),
+	HBG_STATS_I(tx_timeout_cnt),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_rmon_stats_info[] = {
+	HBG_STATS_I(rx_desc_frag_cnt),
+	HBG_STATS_REG_I(rx_framesize_64, HBG_REG_RX_PKTS_64OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_65_127,
+			HBG_REG_RX_PKTS_65TO127OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_128_255,
+			HBG_REG_RX_PKTS_128TO255OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_256_511,
+			HBG_REG_RX_PKTS_256TO511OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_512_1023,
+			HBG_REG_RX_PKTS_512TO1023OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_1024_1518,
+			HBG_REG_RX_PKTS_1024TO1518OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_bt_1518,
+			HBG_REG_RX_PKTS_1519TOMAXOCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_64, HBG_REG_TX_PKTS_64OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_65_127,
+			HBG_REG_TX_PKTS_65TO127OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_128_255,
+			HBG_REG_TX_PKTS_128TO255OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_256_511,
+			HBG_REG_TX_PKTS_256TO511OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_512_1023,
+			HBG_REG_TX_PKTS_512TO1023OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_1024_1518,
+			HBG_REG_TX_PKTS_1024TO1518OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_bt_1518,
+			HBG_REG_TX_PKTS_1519TOMAXOCTETS_ADDR),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_mac_stats_info[] = {
+	HBG_STATS_REG_I(rx_mc_pkt_cnt, HBG_REG_RX_MC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_bc_pkt_cnt, HBG_REG_RX_BC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_align_error_cnt, HBG_REG_RX_ALIGN_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_octets_total_ok_cnt,
+			HBG_REG_RX_OCTETS_TOTAL_OK_ADDR),
+	HBG_STATS_REG_I(rx_trans_pkt_cnt, HBG_REG_RX_TRANS_PKG_CNT_ADDR),
+	HBG_STATS_REG_I(rx_fcs_error_cnt, HBG_REG_RX_FCS_ERRORS_ADDR),
+	HBG_STATS_REG_I(tx_mc_pkt_cnt, HBG_REG_TX_MC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_bc_pkt_cnt, HBG_REG_TX_BC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_octets_total_ok_cnt,
+			HBG_REG_OCTETS_TRANSMITTED_OK_ADDR),
+	HBG_STATS_REG_I(tx_trans_pkt_cnt, HBG_REG_TX_TRANS_PKG_CNT_ADDR),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_ctrl_stats_info[] = {
+	HBG_STATS_REG_I(rx_pause_macctl_frame_cnt,
+			HBG_REG_RX_PAUSE_MACCTL_FRAMCOUNTER_ADDR),
+	HBG_STATS_REG_I(tx_pause_frame_cnt, HBG_REG_TX_PAUSE_FRAMES_ADDR),
+	HBG_STATS_REG_I(rx_unknown_macctl_frame_cnt,
+			HBG_REG_RX_UNKNOWN_MACCTL_FRAMCOUNTER_ADDR),
+};
+
+enum hbg_reg_dump_type {
+	HBG_DUMP_REG_TYPE_SPEC = 0,
+	HBG_DUMP_REG_TYPE_MDIO,
+	HBG_DUMP_REG_TYPE_GMAC,
+	HBG_DUMP_REG_TYPE_PCU,
+};
+
+struct hbg_reg_info {
+	u32 type;
+	u32 offset;
+	u32 val;
+};
+
+#define HBG_DUMP_SPEC_I(offset) {HBG_DUMP_REG_TYPE_SPEC, offset, 0}
+#define HBG_DUMP_MDIO_I(offset) {HBG_DUMP_REG_TYPE_MDIO, offset, 0}
+#define HBG_DUMP_GMAC_I(offset) {HBG_DUMP_REG_TYPE_GMAC, offset, 0}
+#define HBG_DUMP_PCU_I(offset) {HBG_DUMP_REG_TYPE_PCU, offset, 0}
+
+static const struct hbg_reg_info hbg_dump_reg_infos[] = {
+	/* dev specs */
+	HBG_DUMP_SPEC_I(HBG_REG_SPEC_VALID_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_EVENT_REQ_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_MAC_ID_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_PHY_ID_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_MAC_ADDR_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_MAC_ADDR_HIGH_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_UC_MAC_NUM_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_MDIO_FREQ_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_MAX_MTU_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_MIN_MTU_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_TX_FIFO_NUM_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_RX_FIFO_NUM_ADDR),
+	HBG_DUMP_SPEC_I(HBG_REG_VLAN_LAYERS_ADDR),
+
+	/* mdio */
+	HBG_DUMP_MDIO_I(HBG_REG_MDIO_COMMAND_ADDR),
+	HBG_DUMP_MDIO_I(HBG_REG_MDIO_ADDR_ADDR),
+	HBG_DUMP_MDIO_I(HBG_REG_MDIO_WDATA_ADDR),
+	HBG_DUMP_MDIO_I(HBG_REG_MDIO_RDATA_ADDR),
+	HBG_DUMP_MDIO_I(HBG_REG_MDIO_STA_ADDR),
+
+	/* gmac */
+	HBG_DUMP_GMAC_I(HBG_REG_DUPLEX_TYPE_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_FD_FC_TYPE_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_FC_TX_TIMER_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_FD_FC_ADDR_LOW_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_FD_FC_ADDR_HIGH_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_MAX_FRAME_SIZE_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_PORT_MODE_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_PORT_ENABLE_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_PAUSE_ENABLE_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_AN_NEG_STATE_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_TRANSMIT_CTRL_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_REC_FILT_CTRL_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_LINE_LOOP_BACK_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_CF_CRC_STRIP_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_MODE_CHANGE_EN_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_LOOP_REG_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_RECV_CTRL_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_VLAN_CODE_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_0_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_0_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_1_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_1_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_2_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_2_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_3_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_3_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_4_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_4_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_LOW_5_ADDR),
+	HBG_DUMP_GMAC_I(HBG_REG_STATION_ADDR_HIGH_5_ADDR),
+
+	/* pcu */
+	HBG_DUMP_PCU_I(HBG_REG_TX_FIFO_THRSLD_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_RX_FIFO_THRSLD_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CFG_FIFO_THRSLD_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_INTRPT_MSK_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_INTRPT_STAT_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_INTRPT_CLR_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_TX_BUS_ERR_ADDR_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_RX_BUS_ERR_ADDR_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_MAX_FRAME_LEN_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_DEBUG_ST_MCH_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_FIFO_CURR_STATUS_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_FIFO_HIST_STATUS_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_CFF_DATA_NUM_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_TX_PAUSE_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_RX_CFF_ADDR_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_RX_BUF_SIZE_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_BUS_CTRL_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_RX_CTRL_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_RX_PKT_MODE_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_DBG_ST0_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_DBG_ST1_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_DBG_ST2_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_BUS_RST_EN_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_IND_TXINT_MSK_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_IND_TXINT_STAT_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_IND_TXINT_CLR_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_IND_RXINT_MSK_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_IND_RXINT_STAT_ADDR),
+	HBG_DUMP_PCU_I(HBG_REG_CF_IND_RXINT_CLR_ADDR),
+};
+
+static const u32 hbg_dump_type_base_array[] = {
+	[HBG_DUMP_REG_TYPE_SPEC] = 0,
+	[HBG_DUMP_REG_TYPE_MDIO] = HBG_REG_MDIO_BASE,
+	[HBG_DUMP_REG_TYPE_GMAC] = HBG_REG_SGMII_BASE,
+	[HBG_DUMP_REG_TYPE_PCU] = HBG_REG_SGMII_BASE,
+};
+
+static int hbg_ethtool_get_regs_len(struct net_device *netdev)
+{
+	return ARRAY_SIZE(hbg_dump_reg_infos) * sizeof(struct hbg_reg_info);
+}
+
+static void hbg_ethtool_get_regs(struct net_device *netdev,
+				 struct ethtool_regs *regs, void *data)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_reg_info *info;
+	u32 i, offset = 0;
+
+	regs->version = 0;
+	for (i = 0; i < ARRAY_SIZE(hbg_dump_reg_infos); i++) {
+		info = data + offset;
+
+		*info = hbg_dump_reg_infos[i];
+		info->val = hbg_reg_read(priv, info->offset);
+		info->offset -= hbg_dump_type_base_array[info->type];
+
+		offset += sizeof(*info);
+	}
+}
+
+static void hbg_ethtool_get_pauseparam(struct net_device *net_dev,
+				       struct ethtool_pauseparam *param)
+{
+	struct hbg_priv *priv = netdev_priv(net_dev);
+
+	param->autoneg = priv->mac.pause_autoneg;
+	hbg_hw_get_pause_enable(priv, &param->tx_pause, &param->rx_pause);
+}
+
+static int hbg_ethtool_set_pauseparam(struct net_device *net_dev,
+				      struct ethtool_pauseparam *param)
+{
+	struct hbg_priv *priv = netdev_priv(net_dev);
+
+	priv->mac.pause_autoneg = param->autoneg;
+	phy_set_asym_pause(priv->mac.phydev, param->rx_pause, param->tx_pause);
+
+	if (!param->autoneg)
+		hbg_hw_set_pause_enable(priv, param->tx_pause, param->rx_pause);
+
+	priv->user_def.pause_param = *param;
+	return 0;
+}
+
+static int hbg_ethtool_reset(struct net_device *netdev, u32 *flags)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	if (*flags != ETH_RESET_DEDICATED)
+		return -EOPNOTSUPP;
+
+	*flags = 0;
+	return hbg_reset(priv);
+}
+
+static void hbg_update_stats_by_info(struct hbg_priv *priv,
+				     const struct hbg_ethtool_stats *info,
+				     u32 info_len)
+{
+	const struct hbg_ethtool_stats *stats;
+	u32 i;
+
+	if (test_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+		return;
+
+	for (i = 0; i < info_len; i++) {
+		stats = &info[i];
+		if (!stats->reg)
+			continue;
+
+		HBG_STATS_U(&priv->stats, stats->offset,
+			    hbg_reg_read(priv, stats->reg));
+	}
+}
+
+void hbg_update_stats(struct hbg_priv *priv)
+{
+	hbg_update_stats_by_info(priv, hbg_ethtool_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_rmon_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_rmon_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_mac_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_mac_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_ctrl_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_ctrl_stats_info));
+}
+
+static int hbg_ethtool_get_sset_count(struct net_device *netdev, int stringset)
+{
+	if (stringset != ETH_SS_STATS)
+		return -EOPNOTSUPP;
+
+	return ARRAY_SIZE(hbg_ethtool_stats_info);
+}
+
+static void hbg_ethtool_get_strings(struct net_device *netdev,
+				    u32 stringset, u8 *data)
+{
+	u32 i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(hbg_ethtool_stats_info); i++)
+		ethtool_puts(&data, hbg_ethtool_stats_info[i].name);
+}
+
+static void hbg_ethtool_get_stats(struct net_device *netdev,
+				  struct ethtool_stats *stats, u64 *data)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	u32 i;
+
+	hbg_update_stats(priv);
+	for (i = 0; i < ARRAY_SIZE(hbg_ethtool_stats_info); i++)
+		*data++ = HBG_STATS_R(&priv->stats,
+				      hbg_ethtool_stats_info[i].offset);
+}
+
+static void hbg_ethtool_get_pause_stats(struct net_device *netdev,
+					struct ethtool_pause_stats *epstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	epstats->rx_pause_frames = stats->rx_pause_macctl_frame_cnt;
+	epstats->tx_pause_frames = stats->tx_pause_frame_cnt;
+}
+
+static void hbg_ethtool_get_eth_mac_stats(struct net_device *netdev,
+					  struct ethtool_eth_mac_stats *emstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	emstats->FramesTransmittedOK = stats->tx_trans_pkt_cnt;
+	emstats->FramesReceivedOK = stats->rx_trans_pkt_cnt;
+	emstats->FrameCheckSequenceErrors = stats->rx_fcs_error_cnt;
+	emstats->AlignmentErrors = stats->rx_align_error_cnt;
+	emstats->OctetsTransmittedOK = stats->tx_octets_total_ok_cnt;
+	emstats->OctetsReceivedOK = stats->rx_octets_total_ok_cnt;
+
+	emstats->MulticastFramesXmittedOK = stats->tx_mc_pkt_cnt;
+	emstats->BroadcastFramesXmittedOK = stats->tx_bc_pkt_cnt;
+	emstats->MulticastFramesReceivedOK = stats->rx_mc_pkt_cnt;
+	emstats->BroadcastFramesReceivedOK = stats->rx_bc_pkt_cnt;
+	emstats->InRangeLengthErrors = stats->rx_fcs_error_cnt +
+				       stats->rx_jabber_err_cnt +
+				       stats->rx_unknown_macctl_frame_cnt +
+				       stats->rx_bufrq_err_cnt +
+				       stats->rx_we_err_cnt;
+	emstats->OutOfRangeLengthField = stats->rx_frame_short_err_cnt +
+					 stats->rx_frame_runt_err_cnt +
+					 stats->rx_lengthfield_err_cnt +
+					 stats->rx_frame_long_err_cnt +
+					 stats->rx_frame_very_long_err_cnt;
+	emstats->FrameTooLongErrors = stats->rx_frame_long_err_cnt +
+				      stats->rx_frame_very_long_err_cnt;
+}
+
+static void
+hbg_ethtool_get_eth_ctrl_stats(struct net_device *netdev,
+			       struct ethtool_eth_ctrl_stats *ecstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *s = &priv->stats;
+
+	hbg_update_stats(priv);
+	ecstats->MACControlFramesTransmitted = s->tx_pause_frame_cnt;
+	ecstats->MACControlFramesReceived = s->rx_pause_macctl_frame_cnt;
+	ecstats->UnsupportedOpcodesReceived = s->rx_unknown_macctl_frame_cnt;
+}
+
+static const struct ethtool_rmon_hist_range hbg_rmon_ranges[] = {
+	{    0,    64 },
+	{   65,   127 },
+	{  128,   255 },
+	{  256,   511 },
+	{  512,  1023 },
+	{ 1024,  1518 },
+	{ 1519,  4095 },
+};
+
+static void
+hbg_ethtool_get_rmon_stats(struct net_device *netdev,
+			   struct ethtool_rmon_stats *rmon_stats,
+			   const struct ethtool_rmon_hist_range **ranges)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	rmon_stats->undersize_pkts = stats->rx_frame_short_err_cnt +
+				     stats->rx_frame_runt_err_cnt +
+				     stats->rx_lengthfield_err_cnt;
+	rmon_stats->oversize_pkts = stats->rx_frame_long_err_cnt +
+				    stats->rx_frame_very_long_err_cnt;
+	rmon_stats->fragments = stats->rx_desc_frag_cnt;
+	rmon_stats->hist[0] = stats->rx_framesize_64;
+	rmon_stats->hist[1] = stats->rx_framesize_65_127;
+	rmon_stats->hist[2] = stats->rx_framesize_128_255;
+	rmon_stats->hist[3] = stats->rx_framesize_256_511;
+	rmon_stats->hist[4] = stats->rx_framesize_512_1023;
+	rmon_stats->hist[5] = stats->rx_framesize_1024_1518;
+	rmon_stats->hist[6] = stats->rx_framesize_bt_1518;
+
+	rmon_stats->hist_tx[0] = stats->tx_framesize_64;
+	rmon_stats->hist_tx[1] = stats->tx_framesize_65_127;
+	rmon_stats->hist_tx[2] = stats->tx_framesize_128_255;
+	rmon_stats->hist_tx[3] = stats->tx_framesize_256_511;
+	rmon_stats->hist_tx[4] = stats->tx_framesize_512_1023;
+	rmon_stats->hist_tx[5] = stats->tx_framesize_1024_1518;
+	rmon_stats->hist_tx[6] = stats->tx_framesize_bt_1518;
+
+	*ranges = hbg_rmon_ranges;
+}
 
 static const struct ethtool_ops hbg_ethtool_ops = {
 	.get_link		= ethtool_op_get_link,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
+	.get_regs_len		= hbg_ethtool_get_regs_len,
+	.get_regs		= hbg_ethtool_get_regs,
+	.get_pauseparam         = hbg_ethtool_get_pauseparam,
+	.set_pauseparam         = hbg_ethtool_set_pauseparam,
+	.reset			= hbg_ethtool_reset,
+	.nway_reset		= phy_ethtool_nway_reset,
+	.get_sset_count		= hbg_ethtool_get_sset_count,
+	.get_strings		= hbg_ethtool_get_strings,
+	.get_ethtool_stats	= hbg_ethtool_get_stats,
+	.get_pause_stats	= hbg_ethtool_get_pause_stats,
+	.get_eth_mac_stats	= hbg_ethtool_get_eth_mac_stats,
+	.get_eth_ctrl_stats	= hbg_ethtool_get_eth_ctrl_stats,
+	.get_rmon_stats		= hbg_ethtool_get_rmon_stats,
 };
 
 void hbg_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
index 628707ec2686..e173155b146a 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
@@ -6,6 +6,11 @@
 
 #include <linux/netdevice.h>
 
+#define HBG_STATS_FIELD_OFF(f) (offsetof(struct hbg_stats, f))
+#define HBG_STATS_R(p, offset) (*(u64 *)((u8 *)(p) + (offset)))
+#define HBG_STATS_U(p, offset, val) (HBG_STATS_R(p, offset) += (val))
+
 void hbg_ethtool_set_ops(struct net_device *netdev);
+void hbg_update_stats(struct hbg_priv *priv);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
index 05295c2ad439..9b65eef62b3f 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
@@ -3,6 +3,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <linux/if_vlan.h>
 #include <linux/iopoll.h>
 #include <linux/minmax.h>
 #include "hbg_common.h"
@@ -67,6 +68,8 @@ static int hbg_hw_dev_specs_init(struct hbg_priv *priv)
 	specs->vlan_layers = hbg_reg_read(priv, HBG_REG_VLAN_LAYERS_ADDR);
 	specs->rx_fifo_num = hbg_reg_read(priv, HBG_REG_RX_FIFO_NUM_ADDR);
 	specs->tx_fifo_num = hbg_reg_read(priv, HBG_REG_TX_FIFO_NUM_ADDR);
+	specs->uc_mac_num = hbg_reg_read(priv, HBG_REG_UC_MAC_NUM_ADDR);
+
 	mac_addr = hbg_reg_read64(priv, HBG_REG_MAC_ADDR_ADDR);
 	u64_to_ether_addr(mac_addr, (u8 *)specs->mac_addr.sa_data);
 
@@ -135,9 +138,13 @@ void hbg_hw_irq_enable(struct hbg_priv *priv, u32 mask, bool enable)
 	hbg_reg_write(priv, HBG_REG_CF_INTRPT_MSK_ADDR, value);
 }
 
-void hbg_hw_set_uc_addr(struct hbg_priv *priv, u64 mac_addr)
+void hbg_hw_set_uc_addr(struct hbg_priv *priv, u64 mac_addr, u32 index)
 {
-	hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_2_ADDR, mac_addr);
+	u32 addr;
+
+	/* mac addr is u64, so the addr offset is 0x8 */
+	addr = HBG_REG_STATION_ADDR_LOW_2_ADDR + (index * 0x8);
+	hbg_reg_write64(priv, addr, mac_addr);
 }
 
 static void hbg_hw_set_pcu_max_frame_len(struct hbg_priv *priv,
@@ -161,8 +168,13 @@ static void hbg_hw_set_mac_max_frame_len(struct hbg_priv *priv,
 
 void hbg_hw_set_mtu(struct hbg_priv *priv, u16 mtu)
 {
-	hbg_hw_set_pcu_max_frame_len(priv, mtu);
-	hbg_hw_set_mac_max_frame_len(priv, mtu);
+	u32 frame_len;
+
+	frame_len = mtu + VLAN_HLEN * priv->dev_specs.vlan_layers +
+		    ETH_HLEN + ETH_FCS_LEN;
+
+	hbg_hw_set_pcu_max_frame_len(priv, frame_len);
+	hbg_hw_set_mac_max_frame_len(priv, frame_len);
 }
 
 void hbg_hw_mac_enable(struct hbg_priv *priv, u32 enable)
@@ -201,10 +213,55 @@ void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr)
 
 void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex)
 {
+	hbg_hw_mac_enable(priv, HBG_STATUS_DISABLE);
+
 	hbg_reg_write_field(priv, HBG_REG_PORT_MODE_ADDR,
 			    HBG_REG_PORT_MODE_M, speed);
 	hbg_reg_write_field(priv, HBG_REG_DUPLEX_TYPE_ADDR,
 			    HBG_REG_DUPLEX_B, duplex);
+
+	hbg_hw_event_notify(priv, HBG_HW_EVENT_CORE_RESET);
+
+	hbg_hw_mac_enable(priv, HBG_STATUS_ENABLE);
+
+	if (!hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+				HBG_REG_AN_NEG_STATE_NP_LINK_OK_B))
+		hbg_np_link_fail_task_schedule(priv);
+}
+
+/* only support uc filter */
+void hbg_hw_set_mac_filter_enable(struct hbg_priv *priv, u32 enable)
+{
+	hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR,
+			    HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B, enable);
+
+	/* only uc filter is supported, so set all bits of mc mask reg to 1 */
+	hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_MSK_0, U64_MAX);
+	hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_MSK_1, U64_MAX);
+}
+
+void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en)
+{
+	hbg_reg_write_field(priv, HBG_REG_PAUSE_ENABLE_ADDR,
+			    HBG_REG_PAUSE_ENABLE_TX_B, tx_en);
+	hbg_reg_write_field(priv, HBG_REG_PAUSE_ENABLE_ADDR,
+			    HBG_REG_PAUSE_ENABLE_RX_B, rx_en);
+
+	hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR,
+			    HBG_REG_REC_FILT_CTRL_PAUSE_FRM_PASS_B, rx_en);
+}
+
+void hbg_hw_get_pause_enable(struct hbg_priv *priv, u32 *tx_en, u32 *rx_en)
+{
+	*tx_en = hbg_reg_read_field(priv, HBG_REG_PAUSE_ENABLE_ADDR,
+				    HBG_REG_PAUSE_ENABLE_TX_B);
+	*rx_en = hbg_reg_read_field(priv, HBG_REG_PAUSE_ENABLE_ADDR,
+				    HBG_REG_PAUSE_ENABLE_RX_B);
+}
+
+void hbg_hw_set_rx_pause_mac_addr(struct hbg_priv *priv, u64 mac_addr)
+{
+	hbg_reg_write64(priv, HBG_REG_FD_FC_ADDR_LOW_ADDR, mac_addr);
 }
 
 static void hbg_hw_init_transmit_ctrl(struct hbg_priv *priv)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.h
index 14fb39241c93..a4a049b5121d 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.h
@@ -51,9 +51,13 @@ bool hbg_hw_irq_is_enabled(struct hbg_priv *priv, u32 mask);
 void hbg_hw_irq_enable(struct hbg_priv *priv, u32 mask, bool enable);
 void hbg_hw_set_mtu(struct hbg_priv *priv, u16 mtu);
 void hbg_hw_mac_enable(struct hbg_priv *priv, u32 enable);
-void hbg_hw_set_uc_addr(struct hbg_priv *priv, u64 mac_addr);
+void hbg_hw_set_uc_addr(struct hbg_priv *priv, u64 mac_addr, u32 index);
 u32 hbg_hw_get_fifo_used_num(struct hbg_priv *priv, enum hbg_dir dir);
 void hbg_hw_set_tx_desc(struct hbg_priv *priv, struct hbg_tx_desc *tx_desc);
 void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr);
+void hbg_hw_set_mac_filter_enable(struct hbg_priv *priv, u32 enable);
+void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en);
+void hbg_hw_get_pause_enable(struct hbg_priv *priv, u32 *tx_en, u32 *rx_en);
+void hbg_hw_set_rx_pause_mac_addr(struct hbg_priv *priv, u64 mac_addr);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
index 25dd25f096fe..8af0bc4cca21 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
@@ -6,54 +6,65 @@
 #include "hbg_hw.h"
 
 static void hbg_irq_handle_err(struct hbg_priv *priv,
-			       struct hbg_irq_info *irq_info)
+			       const struct hbg_irq_info *irq_info)
 {
 	if (irq_info->need_print)
 		dev_err(&priv->pdev->dev,
 			"receive error interrupt: %s\n", irq_info->name);
+
+	if (irq_info->need_reset)
+		hbg_err_reset_task_schedule(priv);
 }
 
 static void hbg_irq_handle_tx(struct hbg_priv *priv,
-			      struct hbg_irq_info *irq_info)
+			      const struct hbg_irq_info *irq_info)
 {
 	napi_schedule(&priv->tx_ring.napi);
 }
 
 static void hbg_irq_handle_rx(struct hbg_priv *priv,
-			      struct hbg_irq_info *irq_info)
+			      const struct hbg_irq_info *irq_info)
 {
 	napi_schedule(&priv->rx_ring.napi);
 }
 
-#define HBG_TXRX_IRQ_I(name, handle) \
-	{#name, HBG_INT_MSK_##name##_B, false, false, 0, handle}
-#define HBG_ERR_IRQ_I(name, need_print) \
-	{#name, HBG_INT_MSK_##name##_B, true, need_print, 0, hbg_irq_handle_err}
-
-static struct hbg_irq_info hbg_irqs[] = {
-	HBG_TXRX_IRQ_I(RX, hbg_irq_handle_rx),
-	HBG_TXRX_IRQ_I(TX, hbg_irq_handle_tx),
-	HBG_ERR_IRQ_I(MAC_MII_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_PCS_RX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_PCS_TX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_APP_RX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_APP_TX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(SRAM_PARITY_ERR, true),
-	HBG_ERR_IRQ_I(TX_AHB_ERR, true),
-	HBG_ERR_IRQ_I(RX_BUF_AVL, false),
-	HBG_ERR_IRQ_I(REL_BUF_ERR, true),
-	HBG_ERR_IRQ_I(TXCFG_AVL, false),
-	HBG_ERR_IRQ_I(TX_DROP, false),
-	HBG_ERR_IRQ_I(RX_DROP, false),
-	HBG_ERR_IRQ_I(RX_AHB_ERR, true),
-	HBG_ERR_IRQ_I(MAC_FIFO_ERR, false),
-	HBG_ERR_IRQ_I(RBREQ_ERR, false),
-	HBG_ERR_IRQ_I(WE_ERR, false),
+static void hbg_irq_handle_rx_buf_val(struct hbg_priv *priv,
+				      const struct hbg_irq_info *irq_info)
+{
+	priv->stats.rx_fifo_less_empty_thrsld_cnt++;
+}
+
+#define HBG_IRQ_I(name, handle) \
+	{#name, HBG_INT_MSK_##name##_B, false, false, false, handle}
+#define HBG_ERR_IRQ_I(name, need_print, ndde_reset) \
+	{#name, HBG_INT_MSK_##name##_B, true, need_print, \
+	ndde_reset, hbg_irq_handle_err}
+
+static const struct hbg_irq_info hbg_irqs[] = {
+	HBG_IRQ_I(RX, hbg_irq_handle_rx),
+	HBG_IRQ_I(TX, hbg_irq_handle_tx),
+	HBG_ERR_IRQ_I(TX_PKT_CPL, true, true),
+	HBG_ERR_IRQ_I(MAC_MII_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_PCS_RX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_PCS_TX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_APP_RX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_APP_TX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(SRAM_PARITY_ERR, true, false),
+	HBG_ERR_IRQ_I(TX_AHB_ERR, true, true),
+	HBG_IRQ_I(RX_BUF_AVL, hbg_irq_handle_rx_buf_val),
+	HBG_ERR_IRQ_I(REL_BUF_ERR, true, false),
+	HBG_ERR_IRQ_I(TXCFG_AVL, false, false),
+	HBG_ERR_IRQ_I(TX_DROP, false, false),
+	HBG_ERR_IRQ_I(RX_DROP, false, false),
+	HBG_ERR_IRQ_I(RX_AHB_ERR, true, false),
+	HBG_ERR_IRQ_I(MAC_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(RBREQ_ERR, true, true),
+	HBG_ERR_IRQ_I(WE_ERR, true, true),
 };
 
 static irqreturn_t hbg_irq_handle(int irq_num, void *p)
 {
-	struct hbg_irq_info *info;
+	const struct hbg_irq_info *info;
 	struct hbg_priv *priv = p;
 	u32 status;
 	u32 i;
@@ -68,7 +79,7 @@ static irqreturn_t hbg_irq_handle(int irq_num, void *p)
 			hbg_hw_irq_enable(priv, info->mask, false);
 			hbg_hw_irq_clear(priv, info->mask);
 
-			info->count++;
+			priv->vectors.stats_array[i]++;
 			if (info->irq_handle)
 				info->irq_handle(priv, info);
 
@@ -121,6 +132,12 @@ int hbg_irq_init(struct hbg_priv *priv)
 					     irq_names_map[i]);
 	}
 
+	vectors->stats_array = devm_kcalloc(&priv->pdev->dev,
+					    ARRAY_SIZE(hbg_irqs),
+					    sizeof(u64), GFP_KERNEL);
+	if (!vectors->stats_array)
+		return -ENOMEM;
+
 	vectors->info_array = hbg_irqs;
 	vectors->info_array_len = ARRAY_SIZE(hbg_irqs);
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index 75505fb5cc4a..2e64dc1ab355 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -5,18 +5,23 @@
 #include <linux/if_vlan.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <linux/phy.h>
 #include "hbg_common.h"
+#include "hbg_diagnose.h"
+#include "hbg_err.h"
 #include "hbg_ethtool.h"
 #include "hbg_hw.h"
 #include "hbg_irq.h"
 #include "hbg_mdio.h"
 #include "hbg_txrx.h"
+#include "hbg_debugfs.h"
 
-static void hbg_change_mtu(struct hbg_priv *priv, int new_mtu);
+#define HBG_SUPPORT_FEATURES (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \
+			     NETIF_F_RXCSUM)
 
 static void hbg_all_irq_enable(struct hbg_priv *priv, bool enabled)
 {
-	struct hbg_irq_info *info;
+	const struct hbg_irq_info *info;
 	u32 i;
 
 	for (i = 0; i < priv->vectors.info_array_len; i++) {
@@ -55,11 +60,7 @@ static int hbg_hw_txrx_clear(struct hbg_priv *priv)
 		return ret;
 
 	/* After reset, regs need to be reconfigured */
-	hbg_hw_init(priv);
-	hbg_hw_set_uc_addr(priv, ether_addr_to_u64(priv->netdev->dev_addr));
-	hbg_change_mtu(priv, priv->netdev->mtu);
-
-	return 0;
+	return hbg_rebuild(priv);
 }
 
 static int hbg_net_stop(struct net_device *netdev)
@@ -74,31 +75,127 @@ static int hbg_net_stop(struct net_device *netdev)
 	return hbg_hw_txrx_clear(priv);
 }
 
+static void hbg_update_promisc_mode(struct net_device *netdev, bool overflow)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	/* Only when not table_overflow, and netdev->flags not set IFF_PROMISC,
+	 * The MAC filter will be enabled.
+	 * Otherwise the filter will be disabled.
+	 */
+	priv->filter.enabled = !(overflow || (netdev->flags & IFF_PROMISC));
+	hbg_hw_set_mac_filter_enable(priv, priv->filter.enabled);
+}
+
+static void hbg_set_mac_to_mac_table(struct hbg_priv *priv,
+				     u32 index, const u8 *addr)
+{
+	if (addr) {
+		ether_addr_copy(priv->filter.mac_table[index].addr, addr);
+		hbg_hw_set_uc_addr(priv, ether_addr_to_u64(addr), index);
+	} else {
+		eth_zero_addr(priv->filter.mac_table[index].addr);
+		hbg_hw_set_uc_addr(priv, 0, index);
+	}
+}
+
+static int hbg_get_index_from_mac_table(struct hbg_priv *priv,
+					const u8 *addr, u32 *index)
+{
+	u32 i;
+
+	for (i = 0; i < priv->filter.table_max_len; i++)
+		if (ether_addr_equal(priv->filter.mac_table[i].addr, addr)) {
+			*index = i;
+			return 0;
+		}
+
+	return -EINVAL;
+}
+
+static int hbg_add_mac_to_filter(struct hbg_priv *priv, const u8 *addr)
+{
+	u32 index;
+
+	/* already exists */
+	if (!hbg_get_index_from_mac_table(priv, addr, &index))
+		return 0;
+
+	for (index = 0; index < priv->filter.table_max_len; index++)
+		if (is_zero_ether_addr(priv->filter.mac_table[index].addr)) {
+			hbg_set_mac_to_mac_table(priv, index, addr);
+			return 0;
+		}
+
+	return -ENOSPC;
+}
+
+static void hbg_del_mac_from_filter(struct hbg_priv *priv, const u8 *addr)
+{
+	u32 index;
+
+	/* not exists */
+	if (hbg_get_index_from_mac_table(priv, addr, &index))
+		return;
+
+	hbg_set_mac_to_mac_table(priv, index, NULL);
+}
+
+static int hbg_uc_sync(struct net_device *netdev, const unsigned char *addr)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	return hbg_add_mac_to_filter(priv, addr);
+}
+
+static int hbg_uc_unsync(struct net_device *netdev, const unsigned char *addr)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	if (ether_addr_equal(netdev->dev_addr, (u8 *)addr))
+		return 0;
+
+	hbg_del_mac_from_filter(priv, addr);
+	return 0;
+}
+
+static void hbg_net_set_rx_mode(struct net_device *netdev)
+{
+	int ret;
+
+	ret = __dev_uc_sync(netdev, hbg_uc_sync, hbg_uc_unsync);
+
+	/* If ret != 0, overflow has occurred */
+	hbg_update_promisc_mode(netdev, !!ret);
+}
+
 static int hbg_net_set_mac_address(struct net_device *netdev, void *addr)
 {
 	struct hbg_priv *priv = netdev_priv(netdev);
 	u8 *mac_addr;
+	bool exists;
+	u32 index;
 
 	mac_addr = ((struct sockaddr *)addr)->sa_data;
 
 	if (!is_valid_ether_addr(mac_addr))
 		return -EADDRNOTAVAIL;
 
-	hbg_hw_set_uc_addr(priv, ether_addr_to_u64(mac_addr));
-	dev_addr_set(netdev, mac_addr);
+	/* The index of host mac is always 0.
+	 * If new mac address already exists,
+	 * delete the existing mac address and
+	 * add it to the position with index 0.
+	 */
+	exists = !hbg_get_index_from_mac_table(priv, mac_addr, &index);
+	hbg_set_mac_to_mac_table(priv, 0, mac_addr);
+	if (exists)
+		hbg_set_mac_to_mac_table(priv, index, NULL);
 
+	hbg_hw_set_rx_pause_mac_addr(priv, ether_addr_to_u64(mac_addr));
+	dev_addr_set(netdev, mac_addr);
 	return 0;
 }
 
-static void hbg_change_mtu(struct hbg_priv *priv, int new_mtu)
-{
-	u32 frame_len;
-
-	frame_len = new_mtu + VLAN_HLEN * priv->dev_specs.vlan_layers +
-		    ETH_HLEN + ETH_FCS_LEN;
-	hbg_hw_set_mtu(priv, frame_len);
-}
-
 static int hbg_net_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct hbg_priv *priv = netdev_priv(netdev);
@@ -106,12 +203,12 @@ static int hbg_net_change_mtu(struct net_device *netdev, int new_mtu)
 	if (netif_running(netdev))
 		return -EBUSY;
 
-	hbg_change_mtu(priv, new_mtu);
-	WRITE_ONCE(netdev->mtu, new_mtu);
-
 	dev_dbg(&priv->pdev->dev,
 		"change mtu from %u to %u\n", netdev->mtu, new_mtu);
 
+	hbg_hw_set_mtu(priv, new_mtu);
+	WRITE_ONCE(netdev->mtu, new_mtu);
+
 	return 0;
 }
 
@@ -122,6 +219,10 @@ static void hbg_net_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	char *buf = ring->tout_log_buf;
 	u32 pos = 0;
 
+	priv->stats.tx_timeout_cnt++;
+
+	pos += scnprintf(buf + pos, HBG_TX_TIMEOUT_BUF_LEN - pos,
+			 "tx_timeout cnt: %llu\n", priv->stats.tx_timeout_cnt);
 	pos += scnprintf(buf + pos, HBG_TX_TIMEOUT_BUF_LEN - pos,
 			 "ring used num: %u, fifo used num: %u\n",
 			 hbg_get_queue_used_num(ring),
@@ -134,6 +235,39 @@ static void hbg_net_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	netdev_info(netdev, "%s", buf);
 }
 
+static void hbg_net_get_stats(struct net_device *netdev,
+			      struct rtnl_link_stats64 *stats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *h_stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	dev_get_tstats64(netdev, stats);
+
+	/* fifo empty */
+	stats->tx_fifo_errors += h_stats->tx_drop_cnt;
+
+	stats->tx_dropped += h_stats->tx_excessive_length_drop_cnt +
+			     h_stats->tx_drop_cnt;
+	stats->tx_errors += h_stats->tx_add_cs_fail_cnt +
+			    h_stats->tx_bufrl_err_cnt +
+			    h_stats->tx_underrun_err_cnt +
+			    h_stats->tx_crc_err_cnt;
+	stats->rx_errors += h_stats->rx_data_error_cnt;
+	stats->multicast += h_stats->rx_mc_pkt_cnt;
+	stats->rx_dropped += h_stats->rx_desc_drop;
+	stats->rx_length_errors += h_stats->rx_frame_very_long_err_cnt +
+				   h_stats->rx_frame_long_err_cnt +
+				   h_stats->rx_frame_runt_err_cnt +
+				   h_stats->rx_frame_short_err_cnt +
+				   h_stats->rx_lengthfield_err_cnt;
+	stats->rx_frame_errors += h_stats->rx_desc_l2_err_cnt +
+				  h_stats->rx_desc_l3l4_err_cnt;
+	stats->rx_fifo_errors += h_stats->rx_overflow_cnt +
+				 h_stats->rx_overrun_cnt;
+	stats->rx_crc_errors += h_stats->rx_fcs_error_cnt;
+}
+
 static const struct net_device_ops hbg_netdev_ops = {
 	.ndo_open		= hbg_net_open,
 	.ndo_stop		= hbg_net_stop,
@@ -142,8 +276,93 @@ static const struct net_device_ops hbg_netdev_ops = {
 	.ndo_set_mac_address	= hbg_net_set_mac_address,
 	.ndo_change_mtu		= hbg_net_change_mtu,
 	.ndo_tx_timeout		= hbg_net_tx_timeout,
+	.ndo_set_rx_mode	= hbg_net_set_rx_mode,
+	.ndo_get_stats64	= hbg_net_get_stats,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 };
 
+static void hbg_service_task(struct work_struct *work)
+{
+	struct hbg_priv *priv = container_of(work, struct hbg_priv,
+					     service_task.work);
+
+	if (test_and_clear_bit(HBG_NIC_STATE_NEED_RESET, &priv->state))
+		hbg_err_reset(priv);
+
+	if (test_and_clear_bit(HBG_NIC_STATE_NP_LINK_FAIL, &priv->state))
+		hbg_fix_np_link_fail(priv);
+
+	hbg_diagnose_message_push(priv);
+
+	/* The type of statistics register is u32,
+	 * To prevent the statistics register from overflowing,
+	 * the driver dumps the statistics every 30 seconds.
+	 */
+	if (time_after(jiffies, priv->last_update_stats_time + 30 * HZ)) {
+		hbg_update_stats(priv);
+		priv->last_update_stats_time = jiffies;
+	}
+
+	schedule_delayed_work(&priv->service_task,
+			      msecs_to_jiffies(MSEC_PER_SEC));
+}
+
+void hbg_err_reset_task_schedule(struct hbg_priv *priv)
+{
+	set_bit(HBG_NIC_STATE_NEED_RESET, &priv->state);
+	schedule_delayed_work(&priv->service_task, 0);
+}
+
+void hbg_np_link_fail_task_schedule(struct hbg_priv *priv)
+{
+	set_bit(HBG_NIC_STATE_NP_LINK_FAIL, &priv->state);
+	schedule_delayed_work(&priv->service_task, 0);
+}
+
+static void hbg_cancel_delayed_work_sync(void *data)
+{
+	cancel_delayed_work_sync(data);
+}
+
+static int hbg_delaywork_init(struct hbg_priv *priv)
+{
+	INIT_DELAYED_WORK(&priv->service_task, hbg_service_task);
+	schedule_delayed_work(&priv->service_task, 0);
+	return devm_add_action_or_reset(&priv->pdev->dev,
+					hbg_cancel_delayed_work_sync,
+					&priv->service_task);
+}
+
+static int hbg_mac_filter_init(struct hbg_priv *priv)
+{
+	struct hbg_dev_specs *dev_specs = &priv->dev_specs;
+	struct hbg_mac_filter *filter = &priv->filter;
+	struct hbg_mac_table_entry *tmp_table;
+
+	tmp_table = devm_kcalloc(&priv->pdev->dev, dev_specs->uc_mac_num,
+				 sizeof(*tmp_table), GFP_KERNEL);
+	if (!tmp_table)
+		return -ENOMEM;
+
+	filter->mac_table = tmp_table;
+	filter->table_max_len = dev_specs->uc_mac_num;
+	filter->enabled = true;
+
+	hbg_hw_set_mac_filter_enable(priv, filter->enabled);
+	return 0;
+}
+
+static void hbg_init_user_def(struct hbg_priv *priv)
+{
+	struct ethtool_pauseparam *pause_param = &priv->user_def.pause_param;
+
+	priv->mac.pause_autoneg = HBG_STATUS_ENABLE;
+
+	pause_param->autoneg = priv->mac.pause_autoneg;
+	hbg_hw_get_pause_enable(priv, &pause_param->tx_pause,
+				&pause_param->rx_pause);
+}
+
 static int hbg_init(struct hbg_priv *priv)
 {
 	int ret;
@@ -160,7 +379,21 @@ static int hbg_init(struct hbg_priv *priv)
 	if (ret)
 		return ret;
 
-	return hbg_mdio_init(priv);
+	ret = hbg_mdio_init(priv);
+	if (ret)
+		return ret;
+
+	ret = hbg_mac_filter_init(priv);
+	if (ret)
+		return ret;
+
+	ret = hbg_delaywork_init(priv);
+	if (ret)
+		return ret;
+
+	hbg_debugfs_init(priv);
+	hbg_init_user_def(priv);
+	return 0;
 }
 
 static int hbg_pci_init(struct pci_dev *pdev)
@@ -216,13 +449,18 @@ static int hbg_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		return ret;
 
+	/* set default features */
+	netdev->features |= HBG_SUPPORT_FEATURES;
+	netdev->hw_features |= HBG_SUPPORT_FEATURES;
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
 	netdev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	netdev->max_mtu = priv->dev_specs.max_mtu;
 	netdev->min_mtu = priv->dev_specs.min_mtu;
 	netdev->netdev_ops = &hbg_netdev_ops;
 	netdev->watchdog_timeo = 5 * HZ;
 
-	hbg_change_mtu(priv, ETH_DATA_LEN);
+	hbg_hw_set_mtu(priv, ETH_DATA_LEN);
 	hbg_net_set_mac_address(priv->netdev, &priv->dev_specs.mac_addr);
 	hbg_ethtool_set_ops(netdev);
 
@@ -245,7 +483,27 @@ static struct pci_driver hbg_driver = {
 	.id_table	= hbg_pci_tbl,
 	.probe		= hbg_probe,
 };
-module_pci_driver(hbg_driver);
+
+static int __init hbg_module_init(void)
+{
+	int ret;
+
+	hbg_debugfs_register();
+	hbg_set_pci_err_handler(&hbg_driver);
+	ret = pci_register_driver(&hbg_driver);
+	if (ret)
+		hbg_debugfs_unregister();
+
+	return ret;
+}
+module_init(hbg_module_init);
+
+static void __exit hbg_module_exit(void)
+{
+	pci_unregister_driver(&hbg_driver);
+	hbg_debugfs_unregister();
+}
+module_exit(hbg_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Huawei Tech. Co., Ltd.");
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
index a3479fba8501..42b0083c9193 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2024 Hisilicon Limited.
 
 #include <linux/phy.h>
+#include <linux/rtnetlink.h>
 #include "hbg_common.h"
 #include "hbg_hw.h"
 #include "hbg_mdio.h"
@@ -17,6 +18,8 @@
 #define HBG_MDIO_OP_TIMEOUT_US		(1 * 1000 * 1000)
 #define HBG_MDIO_OP_INTERVAL_US		(5 * 1000)
 
+#define HBG_NP_LINK_FAIL_RETRY_TIMES	5
+
 static void hbg_mdio_set_command(struct hbg_mac *mac, u32 cmd)
 {
 	hbg_reg_write(HBG_MAC_GET_PRIV(mac), HBG_REG_MDIO_COMMAND_ADDR, cmd);
@@ -114,6 +117,47 @@ static void hbg_mdio_init_hw(struct hbg_priv *priv)
 	hbg_mdio_set_command(mac, cmd);
 }
 
+static void hbg_flowctrl_cfg(struct hbg_priv *priv)
+{
+	struct phy_device *phydev = priv->mac.phydev;
+	bool rx_pause;
+	bool tx_pause;
+
+	if (!priv->mac.pause_autoneg)
+		return;
+
+	phy_get_pause(phydev, &tx_pause, &rx_pause);
+	hbg_hw_set_pause_enable(priv, tx_pause, rx_pause);
+}
+
+void hbg_fix_np_link_fail(struct hbg_priv *priv)
+{
+	struct device *dev = &priv->pdev->dev;
+
+	rtnl_lock();
+
+	if (priv->stats.np_link_fail_cnt >= HBG_NP_LINK_FAIL_RETRY_TIMES) {
+		dev_err(dev, "failed to fix the MAC link status\n");
+		priv->stats.np_link_fail_cnt = 0;
+		goto unlock;
+	}
+
+	if (!priv->mac.phydev->link)
+		goto unlock;
+
+	priv->stats.np_link_fail_cnt++;
+	dev_err(dev, "failed to link between MAC and PHY, try to fix...\n");
+
+	/* Replace phy_reset() with phy_stop() and phy_start(),
+	 * as suggested by Andrew.
+	 */
+	hbg_phy_stop(priv);
+	hbg_phy_start(priv);
+
+unlock:
+	rtnl_unlock();
+}
+
 static void hbg_phy_adjust_link(struct net_device *netdev)
 {
 	struct hbg_priv *priv = netdev_priv(netdev);
@@ -140,6 +184,7 @@ static void hbg_phy_adjust_link(struct net_device *netdev)
 			priv->mac.duplex = phydev->duplex;
 			priv->mac.autoneg = phydev->autoneg;
 			hbg_hw_adjust_link(priv, speed, phydev->duplex);
+			hbg_flowctrl_cfg(priv);
 		}
 
 		priv->mac.link_status = phydev->link;
@@ -168,6 +213,7 @@ static int hbg_phy_connect(struct hbg_priv *priv)
 		return ret;
 
 	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+	phy_support_asym_pause(phydev);
 	phy_attached_info(phydev);
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
index febd02a309c7..f3771c1bbd34 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
@@ -9,4 +9,6 @@
 int hbg_mdio_init(struct hbg_priv *priv);
 void hbg_phy_start(struct hbg_priv *priv);
 void hbg_phy_stop(struct hbg_priv *priv);
+void hbg_fix_np_link_fail(struct hbg_priv *priv);
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
index 57d81c6d7633..a6e7f5e62b48 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
@@ -10,12 +10,21 @@
 #define HBG_REG_MAC_ID_ADDR			0x0008
 #define HBG_REG_PHY_ID_ADDR			0x000C
 #define HBG_REG_MAC_ADDR_ADDR			0x0010
+#define HBG_REG_MAC_ADDR_HIGH_ADDR		0x0014
+#define HBG_REG_UC_MAC_NUM_ADDR			0x0018
 #define HBG_REG_MDIO_FREQ_ADDR			0x0024
 #define HBG_REG_MAX_MTU_ADDR			0x0028
 #define HBG_REG_MIN_MTU_ADDR			0x002C
 #define HBG_REG_TX_FIFO_NUM_ADDR		0x0030
 #define HBG_REG_RX_FIFO_NUM_ADDR		0x0034
 #define HBG_REG_VLAN_LAYERS_ADDR		0x0038
+#define HBG_REG_PUSH_REQ_ADDR			0x00F0
+#define HBG_REG_MSG_HEADER_ADDR			0x00F4
+#define HBG_REG_MSG_HEADER_OPCODE_M		GENMASK(7, 0)
+#define HBG_REG_MSG_HEADER_STATUS_M		GENMASK(11, 8)
+#define HBG_REG_MSG_HEADER_DATA_NUM_M		GENMASK(19, 12)
+#define HBG_REG_MSG_HEADER_RESP_CODE_M		GENMASK(27, 20)
+#define HBG_REG_MSG_DATA_BASE_ADDR		0x0100
 
 /* MDIO */
 #define HBG_REG_MDIO_BASE			0x8000
@@ -28,6 +37,7 @@
 #define HBG_REG_MDIO_COMMAND_OP_M		GENMASK(11, 10)
 #define HBG_REG_MDIO_COMMAND_PRTAD_M		GENMASK(9, 5)
 #define HBG_REG_MDIO_COMMAND_DEVAD_M		GENMASK(4, 0)
+#define HBG_REG_MDIO_ADDR_ADDR			(HBG_REG_MDIO_BASE + 0x0004)
 #define HBG_REG_MDIO_WDATA_ADDR			(HBG_REG_MDIO_BASE + 0x0008)
 #define HBG_REG_MDIO_WDATA_M			GENMASK(15, 0)
 #define HBG_REG_MDIO_RDATA_ADDR			(HBG_REG_MDIO_BASE + 0x000C)
@@ -36,6 +46,10 @@
 /* GMAC */
 #define HBG_REG_SGMII_BASE			0x10000
 #define HBG_REG_DUPLEX_TYPE_ADDR		(HBG_REG_SGMII_BASE + 0x0008)
+#define HBG_REG_FD_FC_TYPE_ADDR			(HBG_REG_SGMII_BASE + 0x000C)
+#define HBG_REG_FC_TX_TIMER_ADDR		(HBG_REG_SGMII_BASE + 0x001C)
+#define HBG_REG_FD_FC_ADDR_LOW_ADDR		(HBG_REG_SGMII_BASE + 0x0020)
+#define HBG_REG_FD_FC_ADDR_HIGH_ADDR		(HBG_REG_SGMII_BASE + 0x0024)
 #define HBG_REG_DUPLEX_B			BIT(0)
 #define HBG_REG_MAX_FRAME_SIZE_ADDR		(HBG_REG_SGMII_BASE + 0x003C)
 #define HBG_REG_PORT_MODE_ADDR			(HBG_REG_SGMII_BASE + 0x0040)
@@ -43,20 +57,91 @@
 #define HBG_REG_PORT_ENABLE_ADDR		(HBG_REG_SGMII_BASE + 0x0044)
 #define HBG_REG_PORT_ENABLE_RX_B		BIT(1)
 #define HBG_REG_PORT_ENABLE_TX_B		BIT(2)
+#define HBG_REG_PAUSE_ENABLE_ADDR		(HBG_REG_SGMII_BASE + 0x0048)
+#define HBG_REG_PAUSE_ENABLE_RX_B		BIT(0)
+#define HBG_REG_PAUSE_ENABLE_TX_B		BIT(1)
+#define HBG_REG_AN_NEG_STATE_ADDR		(HBG_REG_SGMII_BASE + 0x0058)
+#define HBG_REG_AN_NEG_STATE_NP_LINK_OK_B	BIT(15)
 #define HBG_REG_TRANSMIT_CTRL_ADDR		(HBG_REG_SGMII_BASE + 0x0060)
 #define HBG_REG_TRANSMIT_CTRL_PAD_EN_B		BIT(7)
 #define HBG_REG_TRANSMIT_CTRL_CRC_ADD_B		BIT(6)
 #define HBG_REG_TRANSMIT_CTRL_AN_EN_B		BIT(5)
+#define HBG_REG_REC_FILT_CTRL_ADDR		(HBG_REG_SGMII_BASE + 0x0064)
+#define HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B	BIT(0)
+#define HBG_REG_REC_FILT_CTRL_PAUSE_FRM_PASS_B	BIT(4)
+#define HBG_REG_RX_OCTETS_TOTAL_OK_ADDR		(HBG_REG_SGMII_BASE + 0x0080)
+#define HBG_REG_RX_OCTETS_BAD_ADDR		(HBG_REG_SGMII_BASE + 0x0084)
+#define HBG_REG_RX_UC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0088)
+#define HBG_REG_RX_MC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x008C)
+#define HBG_REG_RX_BC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0090)
+#define HBG_REG_RX_PKTS_64OCTETS_ADDR		(HBG_REG_SGMII_BASE + 0x0094)
+#define HBG_REG_RX_PKTS_65TO127OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0098)
+#define HBG_REG_RX_PKTS_128TO255OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x009C)
+#define HBG_REG_RX_PKTS_256TO511OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A0)
+#define HBG_REG_RX_PKTS_512TO1023OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A4)
+#define HBG_REG_RX_PKTS_1024TO1518OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A8)
+#define HBG_REG_RX_PKTS_1519TOMAXOCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00AC)
+#define HBG_REG_RX_FCS_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00B0)
+#define HBG_REG_RX_TAGGED_ADDR			(HBG_REG_SGMII_BASE + 0x00B4)
+#define HBG_REG_RX_DATA_ERR_ADDR		(HBG_REG_SGMII_BASE + 0x00B8)
+#define HBG_REG_RX_ALIGN_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00BC)
+#define HBG_REG_RX_LONG_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00C0)
+#define HBG_REG_RX_JABBER_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00C4)
+#define HBG_REG_RX_PAUSE_MACCTL_FRAMCOUNTER_ADDR   (HBG_REG_SGMII_BASE + 0x00C8)
+#define HBG_REG_RX_UNKNOWN_MACCTL_FRAMCOUNTER_ADDR (HBG_REG_SGMII_BASE + 0x00CC)
+#define HBG_REG_RX_VERY_LONG_ERR_CNT_ADDR	(HBG_REG_SGMII_BASE + 0x00D0)
+#define HBG_REG_RX_RUNT_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00D4)
+#define HBG_REG_RX_SHORT_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00D8)
+#define HBG_REG_RX_FILT_PKT_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00E8)
+#define HBG_REG_RX_OCTETS_TOTAL_FILT_ADDR	(HBG_REG_SGMII_BASE + 0x00EC)
+#define HBG_REG_OCTETS_TRANSMITTED_OK_ADDR	(HBG_REG_SGMII_BASE + 0x0100)
+#define HBG_REG_OCTETS_TRANSMITTED_BAD_ADDR	(HBG_REG_SGMII_BASE + 0x0104)
+#define HBG_REG_TX_UC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0108)
+#define HBG_REG_TX_MC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x010C)
+#define HBG_REG_TX_BC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0110)
+#define HBG_REG_TX_PKTS_64OCTETS_ADDR		(HBG_REG_SGMII_BASE + 0x0114)
+#define HBG_REG_TX_PKTS_65TO127OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0118)
+#define HBG_REG_TX_PKTS_128TO255OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x011C)
+#define HBG_REG_TX_PKTS_256TO511OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0120)
+#define HBG_REG_TX_PKTS_512TO1023OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0124)
+#define HBG_REG_TX_PKTS_1024TO1518OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0128)
+#define HBG_REG_TX_PKTS_1519TOMAXOCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x012C)
+#define HBG_REG_TX_EXCESSIVE_LENGTH_DROP_ADDR	(HBG_REG_SGMII_BASE + 0x014C)
+#define HBG_REG_TX_UNDERRUN_ADDR		(HBG_REG_SGMII_BASE + 0x0150)
+#define HBG_REG_TX_TAGGED_ADDR			(HBG_REG_SGMII_BASE + 0x0154)
+#define HBG_REG_TX_CRC_ERROR_ADDR		(HBG_REG_SGMII_BASE + 0x0158)
+#define HBG_REG_TX_PAUSE_FRAMES_ADDR		(HBG_REG_SGMII_BASE + 0x015C)
+#define HBG_REG_LINE_LOOP_BACK_ADDR		(HBG_REG_SGMII_BASE + 0x01A8)
 #define HBG_REG_CF_CRC_STRIP_ADDR		(HBG_REG_SGMII_BASE + 0x01B0)
 #define HBG_REG_CF_CRC_STRIP_B			BIT(0)
 #define HBG_REG_MODE_CHANGE_EN_ADDR		(HBG_REG_SGMII_BASE + 0x01B4)
 #define HBG_REG_MODE_CHANGE_EN_B		BIT(0)
+#define HBG_REG_LOOP_REG_ADDR			(HBG_REG_SGMII_BASE + 0x01DC)
 #define HBG_REG_RECV_CTRL_ADDR			(HBG_REG_SGMII_BASE + 0x01E0)
 #define HBG_REG_RECV_CTRL_STRIP_PAD_EN_B	BIT(3)
+#define HBG_REG_VLAN_CODE_ADDR			(HBG_REG_SGMII_BASE + 0x01E8)
+#define HBG_REG_RX_OVERRUN_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x01EC)
+#define HBG_REG_RX_LENGTHFIELD_ERR_CNT_ADDR	(HBG_REG_SGMII_BASE + 0x01F4)
+#define HBG_REG_RX_FAIL_COMMA_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x01F8)
+#define HBG_REG_STATION_ADDR_LOW_0_ADDR		(HBG_REG_SGMII_BASE + 0x0200)
+#define HBG_REG_STATION_ADDR_HIGH_0_ADDR	(HBG_REG_SGMII_BASE + 0x0204)
+#define HBG_REG_STATION_ADDR_LOW_1_ADDR		(HBG_REG_SGMII_BASE + 0x0208)
+#define HBG_REG_STATION_ADDR_HIGH_1_ADDR	(HBG_REG_SGMII_BASE + 0x020C)
 #define HBG_REG_STATION_ADDR_LOW_2_ADDR		(HBG_REG_SGMII_BASE + 0x0210)
 #define HBG_REG_STATION_ADDR_HIGH_2_ADDR	(HBG_REG_SGMII_BASE + 0x0214)
+#define HBG_REG_STATION_ADDR_LOW_3_ADDR		(HBG_REG_SGMII_BASE + 0x0218)
+#define HBG_REG_STATION_ADDR_HIGH_3_ADDR	(HBG_REG_SGMII_BASE + 0x021C)
+#define HBG_REG_STATION_ADDR_LOW_4_ADDR		(HBG_REG_SGMII_BASE + 0x0220)
+#define HBG_REG_STATION_ADDR_HIGH_4_ADDR	(HBG_REG_SGMII_BASE + 0x0224)
+#define HBG_REG_STATION_ADDR_LOW_5_ADDR		(HBG_REG_SGMII_BASE + 0x0228)
+#define HBG_REG_STATION_ADDR_HIGH_5_ADDR	(HBG_REG_SGMII_BASE + 0x022C)
+#define HBG_REG_STATION_ADDR_LOW_MSK_0		(HBG_REG_SGMII_BASE + 0x0230)
+#define HBG_REG_STATION_ADDR_LOW_MSK_1		(HBG_REG_SGMII_BASE + 0x0238)
 
 /* PCU */
+#define HBG_REG_TX_FIFO_THRSLD_ADDR		(HBG_REG_SGMII_BASE + 0x0420)
+#define HBG_REG_RX_FIFO_THRSLD_ADDR		(HBG_REG_SGMII_BASE + 0x0424)
+#define HBG_REG_CFG_FIFO_THRSLD_ADDR		(HBG_REG_SGMII_BASE + 0x0428)
 #define HBG_REG_CF_INTRPT_MSK_ADDR		(HBG_REG_SGMII_BASE + 0x042C)
 #define HBG_INT_MSK_WE_ERR_B			BIT(31)
 #define HBG_INT_MSK_RBREQ_ERR_B			BIT(30)
@@ -74,15 +159,27 @@
 #define HBG_INT_MSK_MAC_PCS_TX_FIFO_ERR_B	BIT(17)
 #define HBG_INT_MSK_MAC_PCS_RX_FIFO_ERR_B	BIT(16)
 #define HBG_INT_MSK_MAC_MII_FIFO_ERR_B		BIT(15)
+#define HBG_INT_MSK_TX_PKT_CPL_B		BIT(14)
 #define HBG_INT_MSK_TX_B			BIT(1) /* just used in driver */
 #define HBG_INT_MSK_RX_B			BIT(0) /* just used in driver */
 #define HBG_REG_CF_INTRPT_STAT_ADDR		(HBG_REG_SGMII_BASE + 0x0434)
 #define HBG_REG_CF_INTRPT_CLR_ADDR		(HBG_REG_SGMII_BASE + 0x0438)
+#define HBG_REG_TX_BUS_ERR_ADDR_ADDR		(HBG_REG_SGMII_BASE + 0x043C)
+#define HBG_REG_RX_BUS_ERR_ADDR_ADDR		(HBG_REG_SGMII_BASE + 0x0440)
 #define HBG_REG_MAX_FRAME_LEN_ADDR		(HBG_REG_SGMII_BASE + 0x0444)
 #define HBG_REG_MAX_FRAME_LEN_M			GENMASK(15, 0)
+#define HBG_REG_TX_DROP_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0448)
+#define HBG_REG_RX_OVER_FLOW_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x044C)
+#define HBG_REG_DEBUG_ST_MCH_ADDR		(HBG_REG_SGMII_BASE + 0x0450)
+#define HBG_REG_FIFO_CURR_STATUS_ADDR		(HBG_REG_SGMII_BASE + 0x0454)
+#define HBG_REG_FIFO_HIST_STATUS_ADDR		(HBG_REG_SGMII_BASE + 0x0458)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR		(HBG_REG_SGMII_BASE + 0x045C)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR_TX_M	GENMASK(8, 0)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR_RX_M	GENMASK(24, 16)
+#define HBG_REG_TX_CS_FAIL_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0460)
+#define HBG_REG_RX_TRANS_PKG_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0464)
+#define HBG_REG_TX_TRANS_PKG_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0468)
+#define HBG_REG_CF_TX_PAUSE_ADDR		(HBG_REG_SGMII_BASE + 0x0470)
 #define HBG_REG_TX_CFF_ADDR_0_ADDR		(HBG_REG_SGMII_BASE + 0x0488)
 #define HBG_REG_TX_CFF_ADDR_1_ADDR		(HBG_REG_SGMII_BASE + 0x048C)
 #define HBG_REG_TX_CFF_ADDR_2_ADDR		(HBG_REG_SGMII_BASE + 0x0490)
@@ -101,6 +198,13 @@
 #define HBG_REG_RX_CTRL_RXBUF_1ST_SKIP_SIZE2_M	GENMASK(3, 0)
 #define HBG_REG_RX_PKT_MODE_ADDR		(HBG_REG_SGMII_BASE + 0x04F4)
 #define HBG_REG_RX_PKT_MODE_PARSE_MODE_M	GENMASK(22, 21)
+#define HBG_REG_RX_BUFRQ_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x058C)
+#define HBG_REG_TX_BUFRL_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0590)
+#define HBG_REG_RX_WE_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0594)
+#define HBG_REG_DBG_ST0_ADDR			(HBG_REG_SGMII_BASE + 0x05E4)
+#define HBG_REG_DBG_ST1_ADDR			(HBG_REG_SGMII_BASE + 0x05E8)
+#define HBG_REG_DBG_ST2_ADDR			(HBG_REG_SGMII_BASE + 0x05EC)
+#define HBG_REG_BUS_RST_EN_ADDR			(HBG_REG_SGMII_BASE + 0x0688)
 #define HBG_REG_CF_IND_TXINT_MSK_ADDR		(HBG_REG_SGMII_BASE + 0x0694)
 #define HBG_REG_IND_INTR_MASK_B			BIT(0)
 #define HBG_REG_CF_IND_TXINT_STAT_ADDR		(HBG_REG_SGMII_BASE + 0x0698)
@@ -139,5 +243,48 @@ struct hbg_rx_desc {
 };
 
 #define HBG_RX_DESC_W2_PKT_LEN_M	GENMASK(31, 16)
+#define HBG_RX_DESC_W2_PORT_NUM_M	GENMASK(15, 12)
+#define HBG_RX_DESC_W4_IP_TCP_UDP_M	GENMASK(31, 30)
+#define HBG_RX_DESC_W4_IPSEC_B		BIT(29)
+#define HBG_RX_DESC_W4_IP_VERSION_B	BIT(28)
+#define HBG_RX_DESC_W4_L4_ERR_CODE_M	GENMASK(26, 23)
+#define HBG_RX_DESC_W4_FRAG_B		BIT(22)
+#define HBG_RX_DESC_W4_OPT_B		BIT(21)
+#define HBG_RX_DESC_W4_IP_VERSION_ERR_B	BIT(20)
+#define HBG_RX_DESC_W4_BRD_CST_B	BIT(19)
+#define HBG_RX_DESC_W4_MUL_CST_B	BIT(18)
+#define HBG_RX_DESC_W4_ARP_B		BIT(17)
+#define HBG_RX_DESC_W4_RARP_B		BIT(16)
+#define HBG_RX_DESC_W4_ICMP_B		BIT(15)
+#define HBG_RX_DESC_W4_VLAN_FLAG_B	BIT(14)
+#define HBG_RX_DESC_W4_DROP_B		BIT(13)
+#define HBG_RX_DESC_W4_L3_ERR_CODE_M	GENMASK(12, 9)
+#define HBG_RX_DESC_W4_L2_ERR_B		BIT(8)
+#define HBG_RX_DESC_W4_IDX_MATCH_B	BIT(7)
+
+enum hbg_l3_err_code {
+	HBG_L3_OK = 0,
+	HBG_L3_WRONG_HEAD,
+	HBG_L3_CSUM_ERR,
+	HBG_L3_LEN_ERR,
+	HBG_L3_ZERO_TTL,
+	HBG_L3_RSVD,
+};
+
+enum hbg_l4_err_code {
+	HBG_L4_OK = 0,
+	HBG_L4_WRONG_HEAD,
+	HBG_L4_LEN_ERR,
+	HBG_L4_CSUM_ERR,
+	HBG_L4_ZERO_PORT_NUM,
+	HBG_L4_RSVD,
+};
+
+enum hbg_pkt_type_code {
+	HBG_NO_IP_PKT = 0,
+	HBG_IP_PKT,
+	HBG_TCP_PKT,
+	HBG_UDP_PKT,
+};
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
index f4f256a0dfea..8d814c8f19ea 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
@@ -38,8 +38,14 @@ static int hbg_dma_map(struct hbg_buffer *buffer)
 	buffer->skb_dma = dma_map_single(&priv->pdev->dev,
 					 buffer->skb->data, buffer->skb_len,
 					 buffer_to_dma_dir(buffer));
-	if (unlikely(dma_mapping_error(&priv->pdev->dev, buffer->skb_dma)))
+	if (unlikely(dma_mapping_error(&priv->pdev->dev, buffer->skb_dma))) {
+		if (buffer->dir == HBG_DIR_RX)
+			priv->stats.rx_dma_err_cnt++;
+		else
+			priv->stats.tx_dma_err_cnt++;
+
 		return -ENOMEM;
+	}
 
 	return 0;
 }
@@ -195,6 +201,173 @@ static int hbg_napi_tx_recycle(struct napi_struct *napi, int budget)
 	return packet_done;
 }
 
+static bool hbg_rx_check_l3l4_error(struct hbg_priv *priv,
+				    struct hbg_rx_desc *desc,
+				    struct sk_buff *skb)
+{
+	bool rx_checksum_offload = !!(priv->netdev->features & NETIF_F_RXCSUM);
+
+	skb->ip_summed = rx_checksum_offload ?
+			 CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
+
+	if (likely(!FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, desc->word4) &&
+		   !FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, desc->word4)))
+		return true;
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, desc->word4)) {
+	case HBG_L3_OK:
+		break;
+	case HBG_L3_WRONG_HEAD:
+		priv->stats.rx_desc_l3_wrong_head_cnt++;
+		return false;
+	case HBG_L3_CSUM_ERR:
+		skb->ip_summed = CHECKSUM_NONE;
+		priv->stats.rx_desc_l3_csum_err_cnt++;
+
+		/* Don't drop packets on csum validation failure,
+		 * suggest by Jakub
+		 */
+		break;
+	case HBG_L3_LEN_ERR:
+		priv->stats.rx_desc_l3_len_err_cnt++;
+		return false;
+	case HBG_L3_ZERO_TTL:
+		priv->stats.rx_desc_l3_zero_ttl_cnt++;
+		return false;
+	default:
+		priv->stats.rx_desc_l3_other_cnt++;
+		return false;
+	}
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, desc->word4)) {
+	case HBG_L4_OK:
+		break;
+	case HBG_L4_WRONG_HEAD:
+		priv->stats.rx_desc_l4_wrong_head_cnt++;
+		return false;
+	case HBG_L4_LEN_ERR:
+		priv->stats.rx_desc_l4_len_err_cnt++;
+		return false;
+	case HBG_L4_CSUM_ERR:
+		skb->ip_summed = CHECKSUM_NONE;
+		priv->stats.rx_desc_l4_csum_err_cnt++;
+
+		/* Don't drop packets on csum validation failure,
+		 * suggest by Jakub
+		 */
+		break;
+	case HBG_L4_ZERO_PORT_NUM:
+		priv->stats.rx_desc_l4_zero_port_num_cnt++;
+		return false;
+	default:
+		priv->stats.rx_desc_l4_other_cnt++;
+		return false;
+	}
+
+	return true;
+}
+
+static void hbg_update_rx_ip_protocol_stats(struct hbg_priv *priv,
+					    struct hbg_rx_desc *desc)
+{
+	if (unlikely(!FIELD_GET(HBG_RX_DESC_W4_IP_TCP_UDP_M, desc->word4))) {
+		priv->stats.rx_desc_no_ip_pkt_cnt++;
+		return;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W4_IP_VERSION_ERR_B, desc->word4))) {
+		priv->stats.rx_desc_ip_ver_err_cnt++;
+		return;
+	}
+
+	/* 0:ipv4, 1:ipv6 */
+	if (FIELD_GET(HBG_RX_DESC_W4_IP_VERSION_B, desc->word4))
+		priv->stats.rx_desc_ipv6_pkt_cnt++;
+	else
+		priv->stats.rx_desc_ipv4_pkt_cnt++;
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_IP_TCP_UDP_M, desc->word4)) {
+	case HBG_IP_PKT:
+		priv->stats.rx_desc_ip_pkt_cnt++;
+		if (FIELD_GET(HBG_RX_DESC_W4_OPT_B, desc->word4))
+			priv->stats.rx_desc_ip_opt_pkt_cnt++;
+		if (FIELD_GET(HBG_RX_DESC_W4_FRAG_B, desc->word4))
+			priv->stats.rx_desc_frag_cnt++;
+
+		if (FIELD_GET(HBG_RX_DESC_W4_ICMP_B, desc->word4))
+			priv->stats.rx_desc_icmp_pkt_cnt++;
+		else if (FIELD_GET(HBG_RX_DESC_W4_IPSEC_B, desc->word4))
+			priv->stats.rx_desc_ipsec_pkt_cnt++;
+		break;
+	case HBG_TCP_PKT:
+		priv->stats.rx_desc_tcp_pkt_cnt++;
+		break;
+	case HBG_UDP_PKT:
+		priv->stats.rx_desc_udp_pkt_cnt++;
+		break;
+	default:
+		priv->stats.rx_desc_no_ip_pkt_cnt++;
+		break;
+	}
+}
+
+static void hbg_update_rx_protocol_stats(struct hbg_priv *priv,
+					 struct hbg_rx_desc *desc)
+{
+	if (unlikely(!FIELD_GET(HBG_RX_DESC_W4_IDX_MATCH_B, desc->word4))) {
+		priv->stats.rx_desc_key_not_match_cnt++;
+		return;
+	}
+
+	if (FIELD_GET(HBG_RX_DESC_W4_BRD_CST_B, desc->word4))
+		priv->stats.rx_desc_broadcast_pkt_cnt++;
+	else if (FIELD_GET(HBG_RX_DESC_W4_MUL_CST_B, desc->word4))
+		priv->stats.rx_desc_multicast_pkt_cnt++;
+
+	if (FIELD_GET(HBG_RX_DESC_W4_VLAN_FLAG_B, desc->word4))
+		priv->stats.rx_desc_vlan_pkt_cnt++;
+
+	if (FIELD_GET(HBG_RX_DESC_W4_ARP_B, desc->word4)) {
+		priv->stats.rx_desc_arp_pkt_cnt++;
+		return;
+	} else if (FIELD_GET(HBG_RX_DESC_W4_RARP_B, desc->word4)) {
+		priv->stats.rx_desc_rarp_pkt_cnt++;
+		return;
+	}
+
+	hbg_update_rx_ip_protocol_stats(priv, desc);
+}
+
+static bool hbg_rx_pkt_check(struct hbg_priv *priv, struct hbg_rx_desc *desc,
+			     struct sk_buff *skb)
+{
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, desc->word2) >
+		     priv->dev_specs.max_frame_len)) {
+		priv->stats.rx_desc_pkt_len_err_cnt++;
+		return false;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W2_PORT_NUM_M, desc->word2) !=
+		     priv->dev_specs.mac_id ||
+		     FIELD_GET(HBG_RX_DESC_W4_DROP_B, desc->word4))) {
+		priv->stats.rx_desc_drop++;
+		return false;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W4_L2_ERR_B, desc->word4))) {
+		priv->stats.rx_desc_l2_err_cnt++;
+		return false;
+	}
+
+	if (unlikely(!hbg_rx_check_l3l4_error(priv, desc, skb))) {
+		priv->stats.rx_desc_l3l4_err_cnt++;
+		return false;
+	}
+
+	hbg_update_rx_protocol_stats(priv, desc);
+	return true;
+}
+
 static int hbg_rx_fill_one_buffer(struct hbg_priv *priv)
 {
 	struct hbg_ring *ring = &priv->rx_ring;
@@ -257,8 +430,12 @@ static int hbg_napi_rx_poll(struct napi_struct *napi, int budget)
 		rx_desc = (struct hbg_rx_desc *)buffer->skb->data;
 		pkt_len = FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2);
 
-		hbg_dma_unmap(buffer);
+		if (unlikely(!hbg_rx_pkt_check(priv, rx_desc, buffer->skb))) {
+			hbg_buffer_free(buffer);
+			goto next_buffer;
+		}
 
+		hbg_dma_unmap(buffer);
 		skb_reserve(buffer->skb, HBG_PACKET_HEAD_SIZE + NET_IP_ALIGN);
 		skb_put(buffer->skb, pkt_len);
 		buffer->skb->protocol = eth_type_trans(buffer->skb,
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index a376d4bdf281..18376bcc718a 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -934,8 +934,6 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	priv->chan = arg.args[1] * RX_DESC_NUM;
 	priv->group = arg.args[2];
 
-	hrtimer_init(&priv->tx_coalesce_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-
 	/* BQL will try to keep the TX queue as short as possible, but it can't
 	 * be faster than tx_coalesce_usecs, so we need a fast timeout here,
 	 * but also long enough to gather up enough frames to ensure we don't
@@ -944,7 +942,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	 */
 	priv->tx_coalesce_frames = TX_DESC_NUM * 3 / 4;
 	priv->tx_coalesce_usecs = 200;
-	priv->tx_coalesce_timer.function = tx_done;
+	hrtimer_setup(&priv->tx_coalesce_timer, tx_done, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	priv->map = syscon_node_to_regmap(arg.np);
 	of_node_put(arg.np);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 851490346261..6b6ced37e490 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -3019,115 +3019,6 @@ static struct platform_driver g_dsaf_driver = {
 
 module_platform_driver(g_dsaf_driver);
 
-/**
- * hns_dsaf_roce_reset - reset dsaf and roce
- * @dsaf_fwnode: Pointer to framework node for the dasf
- * @dereset: false - request reset , true - drop reset
- * return 0 - success , negative -fail
- */
-int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
-{
-	struct dsaf_device *dsaf_dev;
-	struct platform_device *pdev;
-	u32 mp;
-	u32 sl;
-	u32 credit;
-	int i;
-	static const u32 port_map[DSAF_ROCE_CREDIT_CHN][DSAF_ROCE_CHAN_MODE_NUM] = {
-		{DSAF_ROCE_PORT_0, DSAF_ROCE_PORT_0, DSAF_ROCE_PORT_0},
-		{DSAF_ROCE_PORT_1, DSAF_ROCE_PORT_0, DSAF_ROCE_PORT_0},
-		{DSAF_ROCE_PORT_2, DSAF_ROCE_PORT_1, DSAF_ROCE_PORT_0},
-		{DSAF_ROCE_PORT_3, DSAF_ROCE_PORT_1, DSAF_ROCE_PORT_0},
-		{DSAF_ROCE_PORT_4, DSAF_ROCE_PORT_2, DSAF_ROCE_PORT_1},
-		{DSAF_ROCE_PORT_4, DSAF_ROCE_PORT_2, DSAF_ROCE_PORT_1},
-		{DSAF_ROCE_PORT_5, DSAF_ROCE_PORT_3, DSAF_ROCE_PORT_1},
-		{DSAF_ROCE_PORT_5, DSAF_ROCE_PORT_3, DSAF_ROCE_PORT_1},
-	};
-	static const u32 sl_map[DSAF_ROCE_CREDIT_CHN][DSAF_ROCE_CHAN_MODE_NUM] = {
-		{DSAF_ROCE_SL_0, DSAF_ROCE_SL_0, DSAF_ROCE_SL_0},
-		{DSAF_ROCE_SL_0, DSAF_ROCE_SL_1, DSAF_ROCE_SL_1},
-		{DSAF_ROCE_SL_0, DSAF_ROCE_SL_0, DSAF_ROCE_SL_2},
-		{DSAF_ROCE_SL_0, DSAF_ROCE_SL_1, DSAF_ROCE_SL_3},
-		{DSAF_ROCE_SL_0, DSAF_ROCE_SL_0, DSAF_ROCE_SL_0},
-		{DSAF_ROCE_SL_1, DSAF_ROCE_SL_1, DSAF_ROCE_SL_1},
-		{DSAF_ROCE_SL_0, DSAF_ROCE_SL_0, DSAF_ROCE_SL_2},
-		{DSAF_ROCE_SL_1, DSAF_ROCE_SL_1, DSAF_ROCE_SL_3},
-	};
-
-	/* find the platform device corresponding to fwnode */
-	if (is_of_node(dsaf_fwnode)) {
-		pdev = of_find_device_by_node(to_of_node(dsaf_fwnode));
-	} else if (is_acpi_device_node(dsaf_fwnode)) {
-		pdev = hns_dsaf_find_platform_device(dsaf_fwnode);
-	} else {
-		pr_err("fwnode is neither OF or ACPI type\n");
-		return -EINVAL;
-	}
-
-	/* check if we were a success in fetching pdev */
-	if (!pdev) {
-		pr_err("couldn't find platform device for node\n");
-		return -ENODEV;
-	}
-
-	/* retrieve the dsaf_device from the driver data */
-	dsaf_dev = dev_get_drvdata(&pdev->dev);
-	if (!dsaf_dev) {
-		dev_err(&pdev->dev, "dsaf_dev is NULL\n");
-		put_device(&pdev->dev);
-		return -ENODEV;
-	}
-
-	/* now, make sure we are running on compatible SoC */
-	if (AE_IS_VER1(dsaf_dev->dsaf_ver)) {
-		dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n",
-			dsaf_dev->ae_dev.name);
-		put_device(&pdev->dev);
-		return -ENODEV;
-	}
-
-	/* do reset or de-reset according to the flag */
-	if (!dereset) {
-		/* reset rocee-channels in dsaf and rocee */
-		dsaf_dev->misc_op->hns_dsaf_srst_chns(dsaf_dev, DSAF_CHNS_MASK,
-						      false);
-		dsaf_dev->misc_op->hns_dsaf_roce_srst(dsaf_dev, false);
-	} else {
-		/* configure dsaf tx roce correspond to port map and sl map */
-		mp = dsaf_read_dev(dsaf_dev, DSAF_ROCE_PORT_MAP_REG);
-		for (i = 0; i < DSAF_ROCE_CREDIT_CHN; i++)
-			dsaf_set_field(mp, 7 << i * 3, i * 3,
-				       port_map[i][DSAF_ROCE_6PORT_MODE]);
-		dsaf_set_field(mp, 3 << i * 3, i * 3, 0);
-		dsaf_write_dev(dsaf_dev, DSAF_ROCE_PORT_MAP_REG, mp);
-
-		sl = dsaf_read_dev(dsaf_dev, DSAF_ROCE_SL_MAP_REG);
-		for (i = 0; i < DSAF_ROCE_CREDIT_CHN; i++)
-			dsaf_set_field(sl, 3 << i * 2, i * 2,
-				       sl_map[i][DSAF_ROCE_6PORT_MODE]);
-		dsaf_write_dev(dsaf_dev, DSAF_ROCE_SL_MAP_REG, sl);
-
-		/* de-reset rocee-channels in dsaf and rocee */
-		dsaf_dev->misc_op->hns_dsaf_srst_chns(dsaf_dev, DSAF_CHNS_MASK,
-						      true);
-		msleep(SRST_TIME_INTERVAL);
-		dsaf_dev->misc_op->hns_dsaf_roce_srst(dsaf_dev, true);
-
-		/* enable dsaf channel rocee credit */
-		credit = dsaf_read_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG);
-		dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 0);
-		dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit);
-
-		dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 1);
-		dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit);
-	}
-
-	put_device(&pdev->dev);
-
-	return 0;
-}
-EXPORT_SYMBOL(hns_dsaf_roce_reset);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Huawei Tech. Co., Ltd.");
 MODULE_DESCRIPTION("HNS DSAF driver");
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 0eb03dff1a8b..653dfbb25d1b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -42,29 +42,6 @@ struct hns_mac_cb;
 
 #define HNS_MAX_WAIT_CNT 10000
 
-enum dsaf_roce_port_mode {
-	DSAF_ROCE_6PORT_MODE,
-	DSAF_ROCE_4PORT_MODE,
-	DSAF_ROCE_2PORT_MODE,
-	DSAF_ROCE_CHAN_MODE_NUM,
-};
-
-enum dsaf_roce_port_num {
-	DSAF_ROCE_PORT_0,
-	DSAF_ROCE_PORT_1,
-	DSAF_ROCE_PORT_2,
-	DSAF_ROCE_PORT_3,
-	DSAF_ROCE_PORT_4,
-	DSAF_ROCE_PORT_5,
-};
-
-enum dsaf_roce_qos_sl {
-	DSAF_ROCE_SL_0,
-	DSAF_ROCE_SL_1,
-	DSAF_ROCE_SL_2,
-	DSAF_ROCE_SL_3,
-};
-
 #define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
 #define HNS_DSAF_IS_DEBUG(dev) ((dev)->dsaf_mode == DSAF_MODE_DISABLE_SP)
 
@@ -307,9 +284,6 @@ struct dsaf_misc_op {
 	void (*ge_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset);
 	void (*ppe_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset);
 	void (*ppe_comm_srst)(struct dsaf_device *dsaf_dev, bool dereset);
-	void (*hns_dsaf_srst_chns)(struct dsaf_device *dsaf_dev, u32 msk,
-				   bool dereset);
-	void (*hns_dsaf_roce_srst)(struct dsaf_device *dsaf_dev, bool dereset);
 
 	phy_interface_t (*get_phy_if)(struct hns_mac_cb *mac_cb);
 	int (*get_sfp_prsnt)(struct hns_mac_cb *mac_cb, int *sfp_prsnt);
@@ -463,6 +437,4 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     u8 mac_id, u8 port_num);
 int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port);
 
-int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset);
-
 #endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 5df19c604d09..91391a49fcea 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -326,69 +326,6 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
 				   HNS_XGE_RESET_FUNC, port, dereset);
 }
 
-/**
- * hns_dsaf_srst_chns - reset dsaf channels
- * @dsaf_dev: dsaf device struct pointer
- * @msk: xbar channels mask value:
- * @dereset: false - request reset , true - drop reset
- *
- * bit0-5 for xge0-5
- * bit6-11 for ppe0-5
- * bit12-17 for roce0-5
- * bit18-19 for com/dfx
- */
-static void
-hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
-{
-	u32 reg_addr;
-
-	if (!dereset)
-		reg_addr = DSAF_SUB_SC_DSAF_RESET_REQ_REG;
-	else
-		reg_addr = DSAF_SUB_SC_DSAF_RESET_DREQ_REG;
-
-	dsaf_write_sub(dsaf_dev, reg_addr, msk);
-}
-
-/**
- * hns_dsaf_srst_chns_acpi - reset dsaf channels
- * @dsaf_dev: dsaf device struct pointer
- * @msk: xbar channels mask value:
- * @dereset: false - request reset , true - drop reset
- *
- * bit0-5 for xge0-5
- * bit6-11 for ppe0-5
- * bit12-17 for roce0-5
- * bit18-19 for com/dfx
- */
-static void
-hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
-{
-	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
-				   HNS_DSAF_CHN_RESET_FUNC,
-				   msk, dereset);
-}
-
-static void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset)
-{
-	if (!dereset) {
-		dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_ROCEE_RESET_REQ_REG, 1);
-	} else {
-		dsaf_write_sub(dsaf_dev,
-			       DSAF_SUB_SC_ROCEE_CLK_DIS_REG, 1);
-		dsaf_write_sub(dsaf_dev,
-			       DSAF_SUB_SC_ROCEE_RESET_DREQ_REG, 1);
-		msleep(20);
-		dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_ROCEE_CLK_EN_REG, 1);
-	}
-}
-
-static void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset)
-{
-	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
-				   HNS_ROCE_RESET_FUNC, 0, dereset);
-}
-
 static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
 				     bool dereset)
 {
@@ -729,8 +666,6 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev)
 		misc_op->ge_srst = hns_dsaf_ge_srst_by_port;
 		misc_op->ppe_srst = hns_ppe_srst_by_port;
 		misc_op->ppe_comm_srst = hns_ppe_com_srst;
-		misc_op->hns_dsaf_srst_chns = hns_dsaf_srst_chns;
-		misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst;
 
 		misc_op->get_phy_if = hns_mac_get_phy_if;
 		misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt;
@@ -746,8 +681,6 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev)
 		misc_op->ge_srst = hns_dsaf_ge_srst_by_port_acpi;
 		misc_op->ppe_srst = hns_ppe_srst_by_port_acpi;
 		misc_op->ppe_comm_srst = hns_ppe_com_srst;
-		misc_op->hns_dsaf_srst_chns = hns_dsaf_srst_chns_acpi;
-		misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst_acpi;
 
 		misc_op->get_phy_if = hns_mac_get_phy_if_acpi;
 		misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt_acpi;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 46af467aa596..635b3a95dd82 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -195,11 +195,6 @@ void hns_rcb_ring_enable_hw(struct hnae_queue *q, u32 val)
 	dsaf_write_dev(q, RCB_RING_PREFETCH_EN_REG, !!val);
 }
 
-void hns_rcb_start(struct hnae_queue *q, u32 val)
-{
-	hns_rcb_ring_enable_hw(q, val);
-}
-
 /**
  *hns_rcb_common_init_commit_hw - make rcb common init completed
  *@rcb_common: rcb common device
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
index 0f4cc184ef39..68f81547dfb4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
@@ -116,7 +116,6 @@ int hns_rcb_buf_size2type(u32 buf_size);
 int hns_rcb_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index);
 void hns_rcb_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index);
 int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common);
-void hns_rcb_start(struct hnae_queue *q, u32 val);
 int hns_rcb_get_cfg(struct rcb_common_cb *rcb_common);
 void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode,
 			    u16 *max_vfn, u16 *max_q_per_vf);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 42bb341fd80b..e905f10b894e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1402,7 +1402,7 @@ static void hns_nic_net_down(struct net_device *ndev)
 	if (test_and_set_bit(NIC_STATE_DOWN, &priv->state))
 		return;
 
-	(void)del_timer_sync(&priv->service_timer);
+	(void) timer_delete_sync(&priv->service_timer);
 	netif_tx_stop_all_queues(ndev);
 	netif_carrier_off(ndev);
 	netif_tx_disable(ndev);
@@ -2075,7 +2075,7 @@ static void hns_nic_task_schedule(struct hns_nic_priv *priv)
 
 static void hns_nic_service_timer(struct timer_list *t)
 {
-	struct hns_nic_priv *priv = from_timer(priv, t, service_timer);
+	struct hns_nic_priv *priv = timer_container_of(priv, t, service_timer);
 
 	(void)mod_timer(&priv->service_timer, jiffies + SERVICE_TIMER_HZ);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 6c458f037262..60a586a951a0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -266,9 +266,9 @@ static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en)
 		if (err)
 			goto out;
 
-		err = phy_loopback(phy_dev, true);
+		err = phy_loopback(phy_dev, true, 0);
 	} else {
-		err = phy_loopback(phy_dev, false);
+		err = phy_loopback(phy_dev, false, 0);
 		if (err)
 			goto out;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 9a63fbc69408..b25fb400f476 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -40,6 +40,21 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare);
  */
 static DEFINE_MUTEX(hnae3_common_lock);
 
+/* ensure the drivers being unloaded one by one */
+static DEFINE_MUTEX(hnae3_unload_lock);
+
+void hnae3_acquire_unload_lock(void)
+{
+	mutex_lock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_acquire_unload_lock);
+
+void hnae3_release_unload_lock(void)
+{
+	mutex_unlock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_release_unload_lock);
+
 static bool hnae3_client_match(enum hnae3_client_type client_type)
 {
 	if (client_type == HNAE3_CLIENT_KNIC ||
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 710a8f9f2248..4e44f28288f9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -916,9 +916,6 @@ struct hnae3_handle {
 
 	u8 netdev_flags;
 	struct dentry *hnae3_dbgfs;
-	/* protects concurrent contention between debugfs commands */
-	struct mutex dbgfs_lock;
-	char **dbgfs_buf;
 
 	/* Network interface message level enabled bits */
 	u32 msg_enable;
@@ -966,4 +963,6 @@ int hnae3_register_client(struct hnae3_client *client);
 void hnae3_set_client_init_flag(struct hnae3_client *client,
 				struct hnae3_ae_dev *ae_dev,
 				unsigned int inited);
+void hnae3_acquire_unload_lock(void);
+void hnae3_release_unload_lock(void);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 807eb3bbb11c..4e5d8bc39a1b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -3,6 +3,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/device.h>
+#include <linux/string_choices.h>
 
 #include "hnae3.h"
 #include "hns3_debugfs.h"
@@ -60,7 +61,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
 		.name = "tm_qset",
 		.cmd = HNAE3_DBG_CMD_TM_QSET,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
+		.buf_len = HNS3_DBG_READ_LEN_1MB,
 		.init = hns3_dbg_common_file_init,
 	},
 	{
@@ -661,12 +662,14 @@ static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring,
 		HNS3_RING_RX_RING_PKTNUM_RECORD_REG));
 	sprintf(result[j++], "%u", ring->rx_copybreak);
 
-	sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_EN_REG) ? "on" : "off");
+	sprintf(result[j++], "%s",
+		str_on_off(readl_relaxed(ring->tqp->io_base +
+					 HNS3_RING_EN_REG)));
 
 	if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev))
-		sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-			HNS3_RING_RX_EN_REG) ? "on" : "off");
+		sprintf(result[j++], "%s",
+			str_on_off(readl_relaxed(ring->tqp->io_base +
+						 HNS3_RING_RX_EN_REG)));
 	else
 		sprintf(result[j++], "%s", "NA");
 
@@ -764,12 +767,14 @@ static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring,
 	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
 		HNS3_RING_TX_RING_PKTNUM_RECORD_REG));
 
-	sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_EN_REG) ? "on" : "off");
+	sprintf(result[j++], "%s",
+		str_on_off(readl_relaxed(ring->tqp->io_base +
+					 HNS3_RING_EN_REG)));
 
 	if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev))
-		sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-			HNS3_RING_TX_EN_REG) ? "on" : "off");
+		sprintf(result[j++], "%s",
+			str_on_off(readl_relaxed(ring->tqp->io_base +
+						 HNS3_RING_TX_EN_REG)));
 	else
 		sprintf(result[j++], "%s", "NA");
 
@@ -1030,7 +1035,6 @@ static void
 hns3_dbg_dev_caps(struct hnae3_handle *h, char *buf, int len, int *pos)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	const char * const str[] = {"no", "yes"};
 	unsigned long *caps = ae_dev->caps;
 	u32 i, state;
 
@@ -1039,7 +1043,7 @@ hns3_dbg_dev_caps(struct hnae3_handle *h, char *buf, int len, int *pos)
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cap); i++) {
 		state = test_bit(hns3_dbg_cap[i].cap_bit, caps);
 		*pos += scnprintf(buf + *pos, len - *pos, "%s: %s\n",
-				  hns3_dbg_cap[i].name, str[state]);
+				  hns3_dbg_cap[i].name, str_yes_no(state));
 	}
 
 	*pos += scnprintf(buf + *pos, len - *pos, "\n");
@@ -1260,69 +1264,55 @@ static int hns3_dbg_read_cmd(struct hns3_dbg_data *dbg_data,
 static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 			     size_t count, loff_t *ppos)
 {
-	struct hns3_dbg_data *dbg_data = filp->private_data;
+	char *buf = filp->private_data;
+
+	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+}
+
+static int hns3_dbg_open(struct inode *inode, struct file *filp)
+{
+	struct hns3_dbg_data *dbg_data = inode->i_private;
 	struct hnae3_handle *handle = dbg_data->handle;
 	struct hns3_nic_priv *priv = handle->priv;
-	ssize_t size = 0;
-	char **save_buf;
-	char *read_buf;
 	u32 index;
+	char *buf;
 	int ret;
 
+	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+		return -EBUSY;
+
 	ret = hns3_dbg_get_cmd_index(dbg_data, &index);
 	if (ret)
 		return ret;
 
-	mutex_lock(&handle->dbgfs_lock);
-	save_buf = &handle->dbgfs_buf[index];
-
-	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
-	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	if (*save_buf) {
-		read_buf = *save_buf;
-	} else {
-		read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL);
-		if (!read_buf) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		/* save the buffer addr until the last read operation */
-		*save_buf = read_buf;
-
-		/* get data ready for the first time to read */
-		ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
-					read_buf, hns3_dbg_cmd[index].buf_len);
-		if (ret)
-			goto out;
-	}
+	buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
-	size = simple_read_from_buffer(buffer, count, ppos, read_buf,
-				       strlen(read_buf));
-	if (size > 0) {
-		mutex_unlock(&handle->dbgfs_lock);
-		return size;
+	ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
+				buf, hns3_dbg_cmd[index].buf_len);
+	if (ret) {
+		kvfree(buf);
+		return ret;
 	}
 
-out:
-	/* free the buffer for the last read operation */
-	if (*save_buf) {
-		kvfree(*save_buf);
-		*save_buf = NULL;
-	}
+	filp->private_data = buf;
+	return 0;
+}
 
-	mutex_unlock(&handle->dbgfs_lock);
-	return ret;
+static int hns3_dbg_release(struct inode *inode, struct file *filp)
+{
+	kvfree(filp->private_data);
+	filp->private_data = NULL;
+	return 0;
 }
 
 static const struct file_operations hns3_dbg_fops = {
 	.owner = THIS_MODULE,
-	.open  = simple_open,
+	.open  = hns3_dbg_open,
 	.read  = hns3_dbg_read,
+	.release = hns3_dbg_release,
 };
 
 static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd)
@@ -1379,13 +1369,6 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 	int ret;
 	u32 i;
 
-	handle->dbgfs_buf = devm_kcalloc(&handle->pdev->dev,
-					 ARRAY_SIZE(hns3_dbg_cmd),
-					 sizeof(*handle->dbgfs_buf),
-					 GFP_KERNEL);
-	if (!handle->dbgfs_buf)
-		return -ENOMEM;
-
 	hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry =
 				debugfs_create_dir(name, hns3_dbgfs_root);
 	handle->hnae3_dbgfs = hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry;
@@ -1395,8 +1378,6 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 			debugfs_create_dir(hns3_dbg_dentry[i].name,
 					   handle->hnae3_dbgfs);
 
-	mutex_init(&handle->dbgfs_lock);
-
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) {
 		if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES &&
 		     ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) ||
@@ -1425,24 +1406,13 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 out:
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
-	mutex_destroy(&handle->dbgfs_lock);
 	return ret;
 }
 
 void hns3_dbg_uninit(struct hnae3_handle *handle)
 {
-	u32 i;
-
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
-
-	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++)
-		if (handle->dbgfs_buf[i]) {
-			kvfree(handle->dbgfs_buf[i]);
-			handle->dbgfs_buf[i] = NULL;
-		}
-
-	mutex_destroy(&handle->dbgfs_lock);
 }
 
 void hns3_dbg_register_debugfs(const char *debugfs_dir_name)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 43377a7b2426..b03b8758c777 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -473,20 +473,14 @@ static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector,
 	writel(mask_en, tqp_vector->mask_addr);
 }
 
-static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_enable(struct hns3_enet_tqp_vector *tqp_vector)
 {
 	napi_enable(&tqp_vector->napi);
 	enable_irq(tqp_vector->vector_irq);
-
-	/* enable vector */
-	hns3_mask_vector_irq(tqp_vector, 1);
 }
 
-static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_disable(struct hns3_enet_tqp_vector *tqp_vector)
 {
-	/* disable vector */
-	hns3_mask_vector_irq(tqp_vector, 0);
-
 	disable_irq(tqp_vector->vector_irq);
 	napi_disable(&tqp_vector->napi);
 	cancel_work_sync(&tqp_vector->rx_group.dim.work);
@@ -707,11 +701,42 @@ static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
 	return 0;
 }
 
+static void hns3_enable_irqs_and_tqps(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	u16 i;
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_irq_enable(&priv->tqp_vector[i]);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_mask_vector_irq(&priv->tqp_vector[i], 1);
+
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_enable(h->kinfo.tqp[i]);
+}
+
+static void hns3_disable_irqs_and_tqps(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	u16 i;
+
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_disable(h->kinfo.tqp[i]);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_mask_vector_irq(&priv->tqp_vector[i], 0);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_irq_disable(&priv->tqp_vector[i]);
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int i, j;
 	int ret;
 
 	ret = hns3_nic_reset_all_ring(h);
@@ -720,23 +745,13 @@ static int hns3_nic_net_up(struct net_device *netdev)
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
-	/* enable the vectors */
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_enable(&priv->tqp_vector[i]);
-
-	/* enable rcb */
-	for (j = 0; j < h->kinfo.num_tqps; j++)
-		hns3_tqp_enable(h->kinfo.tqp[j]);
+	hns3_enable_irqs_and_tqps(netdev);
 
 	/* start the ae_dev */
 	ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
 	if (ret) {
 		set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
-		while (j--)
-			hns3_tqp_disable(h->kinfo.tqp[j]);
-
-		for (j = i - 1; j >= 0; j--)
-			hns3_vector_disable(&priv->tqp_vector[j]);
+		hns3_disable_irqs_and_tqps(netdev);
 	}
 
 	return ret;
@@ -823,17 +838,9 @@ static void hns3_reset_tx_queue(struct hnae3_handle *h)
 static void hns3_nic_net_down(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops;
-	int i;
 
-	/* disable vectors */
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_disable(&priv->tqp_vector[i]);
-
-	/* disable rcb */
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_disable(h->kinfo.tqp[i]);
+	hns3_disable_irqs_and_tqps(netdev);
 
 	/* stop ae_dev */
 	ops = priv->ae_handle->ae_algo->ops;
@@ -2452,7 +2459,6 @@ static int hns3_nic_set_features(struct net_device *netdev,
 			return ret;
 	}
 
-	netdev->features = features;
 	return 0;
 }
 
@@ -5865,8 +5871,6 @@ int hns3_set_channels(struct net_device *netdev,
 void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
-	struct hnae3_handle *h = priv->ae_handle;
-	int i;
 
 	if (!if_running)
 		return;
@@ -5877,11 +5881,7 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
 	netif_carrier_off(ndev);
 	netif_tx_disable(ndev);
 
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_disable(&priv->tqp_vector[i]);
-
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_disable(h->kinfo.tqp[i]);
+	hns3_disable_irqs_and_tqps(ndev);
 
 	/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
 	 * during reset process, because driver may not be able
@@ -5897,7 +5897,6 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int i;
 
 	if (!if_running)
 		return;
@@ -5913,11 +5912,7 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_enable(&priv->tqp_vector[i]);
-
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_enable(h->kinfo.tqp[i]);
+	hns3_enable_irqs_and_tqps(ndev);
 
 	netif_tx_wake_all_queues(ndev);
 
@@ -6003,9 +5998,11 @@ module_init(hns3_init_module);
  */
 static void __exit hns3_exit_module(void)
 {
+	hnae3_acquire_unload_lock();
 	pci_unregister_driver(&hns3_driver);
 	hnae3_unregister_client(&client);
 	hns3_dbg_unregister_debugfs();
+	hnae3_release_unload_lock();
 }
 module_exit(hns3_exit_module);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index b771a2daba43..6715222aeb66 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -3,6 +3,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/phy.h>
 #include <linux/sfp.h>
 
@@ -1198,7 +1199,7 @@ static int hns3_set_tx_push(struct net_device *netdev, u32 tx_push)
 		return 0;
 
 	netdev_dbg(netdev, "Changing tx push from %s to %s\n",
-		   old_state ? "on" : "off", tx_push ? "on" : "off");
+		   str_on_off(old_state), str_on_off(tx_push));
 
 	if (tx_push)
 		set_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index debf143e9940..c46490693594 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -3,6 +3,7 @@
 
 #include <linux/device.h>
 #include <linux/sched/clock.h>
+#include <linux/string_choices.h>
 
 #include "hclge_debugfs.h"
 #include "hclge_err.h"
@@ -11,7 +12,6 @@
 #include "hclge_tm.h"
 #include "hnae3.h"
 
-static const char * const state_str[] = { "off", "on" };
 static const char * const hclge_mac_state_str[] = {
 	"TO_ADD", "TO_DEL", "ACTIVE"
 };
@@ -2573,7 +2573,7 @@ static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
 	loopback_en = hnae3_get_bit(le32_to_cpu(req_app->txrx_pad_fcs_loop_en),
 				    HCLGE_MAC_APP_LP_B);
 	pos += scnprintf(buf + pos, len - pos, "app loopback: %s\n",
-			 state_str[loopback_en]);
+			 str_on_off(loopback_en));
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_COMMON_LOOPBACK, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2586,22 +2586,22 @@ static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
 
 	loopback_en = req_common->enable & HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
 	pos += scnprintf(buf + pos, len - pos, "serdes serial loopback: %s\n",
-			 state_str[loopback_en]);
+			 str_on_off(loopback_en));
 
 	loopback_en = req_common->enable &
 			HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B ? 1 : 0;
 	pos += scnprintf(buf + pos, len - pos, "serdes parallel loopback: %s\n",
-			 state_str[loopback_en]);
+			 str_on_off(loopback_en));
 
 	if (phydev) {
 		loopback_en = phydev->loopback_enabled;
 		pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n",
-				 state_str[loopback_en]);
+				 str_on_off(loopback_en));
 	} else if (hnae3_dev_phy_imp_supported(hdev)) {
 		loopback_en = req_common->enable &
 			      HCLGE_CMD_GE_PHY_INNER_LOOP_B;
 		pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n",
-				 state_str[loopback_en]);
+				 str_on_off(loopback_en));
 	}
 
 	return 0;
@@ -2894,9 +2894,9 @@ static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf,
 	egress = vlan_fe & HCLGE_FILTER_FE_NIC_EGRESS_B ? 1 : 0;
 
 	*pos += scnprintf(buf, len, "I_PORT_VLAN_FILTER: %s\n",
-			  state_str[ingress]);
+			  str_on_off(ingress));
 	*pos += scnprintf(buf + *pos, len - *pos, "E_PORT_VLAN_FILTER: %s\n",
-			  state_str[egress]);
+			  str_on_off(egress));
 
 	hclge_dbg_fill_content(content, sizeof(content), vlan_filter_items,
 			       NULL, ARRAY_SIZE(vlan_filter_items));
@@ -2915,11 +2915,11 @@ static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf,
 			return ret;
 		j = 0;
 		result[j++] = hclge_dbg_get_func_id_str(str_id, i);
-		result[j++] = state_str[ingress];
-		result[j++] = state_str[egress];
-		result[j++] =
-			test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
-				 hdev->ae_dev->caps) ? state_str[bypass] : "NA";
+		result[j++] = str_on_off(ingress);
+		result[j++] = str_on_off(egress);
+		result[j++] = test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
+				       hdev->ae_dev->caps) ?
+			      str_on_off(bypass) : "NA";
 		hclge_dbg_fill_content(content, sizeof(content),
 				       vlan_filter_items, result,
 				       ARRAY_SIZE(vlan_filter_items));
@@ -2958,19 +2958,19 @@ static int hclge_dbg_dump_vlan_offload_config(struct hclge_dev *hdev, char *buf,
 		j = 0;
 		result[j++] = hclge_dbg_get_func_id_str(str_id, i);
 		result[j++] = str_pvid;
-		result[j++] = state_str[vlan_cfg.accept_tag1];
-		result[j++] = state_str[vlan_cfg.accept_tag2];
-		result[j++] = state_str[vlan_cfg.accept_untag1];
-		result[j++] = state_str[vlan_cfg.accept_untag2];
-		result[j++] = state_str[vlan_cfg.insert_tag1];
-		result[j++] = state_str[vlan_cfg.insert_tag2];
-		result[j++] = state_str[vlan_cfg.shift_tag];
-		result[j++] = state_str[vlan_cfg.strip_tag1];
-		result[j++] = state_str[vlan_cfg.strip_tag2];
-		result[j++] = state_str[vlan_cfg.drop_tag1];
-		result[j++] = state_str[vlan_cfg.drop_tag2];
-		result[j++] = state_str[vlan_cfg.pri_only1];
-		result[j++] = state_str[vlan_cfg.pri_only2];
+		result[j++] = str_on_off(vlan_cfg.accept_tag1);
+		result[j++] = str_on_off(vlan_cfg.accept_tag2);
+		result[j++] = str_on_off(vlan_cfg.accept_untag1);
+		result[j++] = str_on_off(vlan_cfg.accept_untag2);
+		result[j++] = str_on_off(vlan_cfg.insert_tag1);
+		result[j++] = str_on_off(vlan_cfg.insert_tag2);
+		result[j++] = str_on_off(vlan_cfg.shift_tag);
+		result[j++] = str_on_off(vlan_cfg.strip_tag1);
+		result[j++] = str_on_off(vlan_cfg.strip_tag2);
+		result[j++] = str_on_off(vlan_cfg.drop_tag1);
+		result[j++] = str_on_off(vlan_cfg.drop_tag2);
+		result[j++] = str_on_off(vlan_cfg.pri_only1);
+		result[j++] = str_on_off(vlan_cfg.pri_only2);
 
 		hclge_dbg_fill_content(content, sizeof(content),
 				       vlan_offload_items, result,
@@ -3007,14 +3007,13 @@ static int hclge_dbg_dump_ptp_info(struct hclge_dev *hdev, char *buf, int len)
 	pos += scnprintf(buf + pos, len - pos, "phc %s's debug info:\n",
 			 ptp->info.name);
 	pos += scnprintf(buf + pos, len - pos, "ptp enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags) ?
-			 "yes" : "no");
+			 str_yes_no(test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags)));
 	pos += scnprintf(buf + pos, len - pos, "ptp tx enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ?
-			 "yes" : "no");
+			 str_yes_no(test_bit(HCLGE_PTP_FLAG_TX_EN,
+					     &ptp->flags)));
 	pos += scnprintf(buf + pos, len - pos, "ptp rx enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_RX_EN, &ptp->flags) ?
-			 "yes" : "no");
+			 str_yes_no(test_bit(HCLGE_PTP_FLAG_RX_EN,
+					     &ptp->flags)));
 
 	last_rx = jiffies_to_msecs(ptp->last_rx);
 	pos += scnprintf(buf + pos, len - pos, "last rx time: %lu.%lu\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 05942fa78b11..a7de67699a01 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6,6 +6,7 @@
 #include <linux/etherdevice.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
@@ -3574,6 +3575,17 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf,
 	return ret;
 }
 
+static void hclge_set_reset_pending(struct hclge_dev *hdev,
+				    enum hnae3_reset_type reset_type)
+{
+	/* When an incorrect reset type is executed, the get_reset_level
+	 * function generates the HNAE3_NONE_RESET flag. As a result, this
+	 * type do not need to pending.
+	 */
+	if (reset_type != HNAE3_NONE_RESET)
+		set_bit(reset_type, &hdev->reset_pending);
+}
+
 static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 {
 	u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg;
@@ -3594,7 +3606,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	 */
 	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & msix_src_reg) {
 		dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
-		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_IMP_RESET);
 		set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
 		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
 		hdev->rst_stats.imp_rst_cnt++;
@@ -3604,7 +3616,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & msix_src_reg) {
 		dev_info(&hdev->pdev->dev, "global reset interrupt\n");
 		set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
-		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_GLOBAL_RESET);
 		*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
 		hdev->rst_stats.global_rst_cnt++;
 		return HCLGE_VECTOR0_EVENT_RST;
@@ -3759,7 +3771,7 @@ static int hclge_misc_irq_init(struct hclge_dev *hdev)
 	snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s",
 		 HCLGE_NAME, pci_name(hdev->pdev));
 	ret = request_irq(hdev->misc_vector.vector_irq, hclge_misc_irq_handle,
-			  0, hdev->misc_vector.name, hdev);
+			  IRQF_NO_AUTOEN, hdev->misc_vector.name, hdev);
 	if (ret) {
 		hclge_free_vector(hdev, 0);
 		dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n",
@@ -4052,7 +4064,7 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 	case HNAE3_FUNC_RESET:
 		dev_info(&pdev->dev, "PF reset requested\n");
 		/* schedule again to check later */
-		set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_FUNC_RESET);
 		hclge_reset_task_schedule(hdev);
 		break;
 	default:
@@ -4086,6 +4098,8 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 		clear_bit(HNAE3_FLR_RESET, addr);
 	}
 
+	clear_bit(HNAE3_NONE_RESET, addr);
+
 	if (hdev->reset_type != HNAE3_NONE_RESET &&
 	    rst_level < hdev->reset_type)
 		return HNAE3_NONE_RESET;
@@ -4227,7 +4241,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev)
 		return false;
 	} else if (hdev->rst_stats.reset_fail_cnt < MAX_RESET_FAIL_CNT) {
 		hdev->rst_stats.reset_fail_cnt++;
-		set_bit(hdev->reset_type, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, hdev->reset_type);
 		dev_info(&hdev->pdev->dev,
 			 "re-schedule reset task(%u)\n",
 			 hdev->rst_stats.reset_fail_cnt);
@@ -4470,14 +4484,26 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
 					enum hnae3_reset_type rst_type)
 {
+#define HCLGE_SUPPORT_RESET_TYPE \
+	(BIT(HNAE3_FLR_RESET) | BIT(HNAE3_FUNC_RESET) | \
+	BIT(HNAE3_GLOBAL_RESET) | BIT(HNAE3_IMP_RESET))
+
 	struct hclge_dev *hdev = ae_dev->priv;
 
+	if (!(BIT(rst_type) & HCLGE_SUPPORT_RESET_TYPE)) {
+		/* To prevent reset triggered by hclge_reset_event */
+		set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request);
+		dev_warn(&hdev->pdev->dev, "unsupported reset type %d\n",
+			 rst_type);
+		return;
+	}
+
 	set_bit(rst_type, &hdev->default_reset_request);
 }
 
 static void hclge_reset_timer(struct timer_list *t)
 {
-	struct hclge_dev *hdev = from_timer(hdev, t, reset_timer);
+	struct hclge_dev *hdev = timer_container_of(hdev, t, reset_timer);
 
 	/* if default_reset_request has no value, it means that this reset
 	 * request has already be handled, so just return here
@@ -7849,7 +7875,7 @@ static int hclge_enable_phy_loopback(struct hclge_dev *hdev,
 	if (ret)
 		return ret;
 
-	return phy_loopback(phydev, true);
+	return phy_loopback(phydev, true, 0);
 }
 
 static int hclge_disable_phy_loopback(struct hclge_dev *hdev,
@@ -7857,7 +7883,7 @@ static int hclge_disable_phy_loopback(struct hclge_dev *hdev,
 {
 	int ret;
 
-	ret = phy_loopback(phydev, false);
+	ret = phy_loopback(phydev, false, 0);
 	if (ret)
 		return ret;
 
@@ -7974,7 +8000,7 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 	ret = hclge_tqp_enable(handle, en);
 	if (ret)
 		dev_err(&hdev->pdev->dev, "failed to %s tqp in loopback, ret = %d\n",
-			en ? "enable" : "disable", ret);
+			str_enable_disable(en), ret);
 
 	return ret;
 }
@@ -11174,9 +11200,9 @@ static void hclge_info_show(struct hclge_dev *hdev)
 	dev_info(dev, "This is %s PF\n",
 		 hdev->flag & HCLGE_FLAG_MAIN ? "main" : "not main");
 	dev_info(dev, "DCB %s\n",
-		 handle->kinfo.tc_info.dcb_ets_active ? "enable" : "disable");
+		 str_enable_disable(handle->kinfo.tc_info.dcb_ets_active));
 	dev_info(dev, "MQPRIO %s\n",
-		 handle->kinfo.tc_info.mqprio_active ? "enable" : "disable");
+		 str_enable_disable(handle->kinfo.tc_info.mqprio_active));
 	dev_info(dev, "Default tx spare buffer size: %u\n",
 		 hdev->tx_spare_buf_size);
 
@@ -11466,7 +11492,7 @@ static void hclge_state_uninit(struct hclge_dev *hdev)
 	set_bit(HCLGE_STATE_REMOVING, &hdev->state);
 
 	if (hdev->reset_timer.function)
-		del_timer_sync(&hdev->reset_timer);
+		timer_delete_sync(&hdev->reset_timer);
 	if (hdev->service_task.work.func)
 		cancel_delayed_work_sync(&hdev->service_task);
 }
@@ -11881,9 +11907,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	hclge_init_rxd_adv_layout(hdev);
 
-	/* Enable MISC vector(vector0) */
-	hclge_enable_vector(&hdev->misc_vector, true);
-
 	ret = hclge_init_wol(hdev);
 	if (ret)
 		dev_warn(&pdev->dev,
@@ -11896,6 +11919,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_state_init(hdev);
 	hdev->last_reset_time = jiffies;
 
+	/* Enable MISC vector(vector0) */
+	enable_irq(hdev->misc_vector.vector_irq);
+	hclge_enable_vector(&hdev->misc_vector, true);
+
 	dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n",
 		 HCLGE_DRIVER_NAME);
 
@@ -11949,7 +11976,7 @@ static int hclge_set_vf_spoofchk_hw(struct hclge_dev *hdev, int vf, bool enable)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Set vf %d mac spoof check %s failed, ret=%d\n",
-			vf, enable ? "on" : "off", ret);
+			vf, str_on_off(enable), ret);
 		return ret;
 	}
 
@@ -11957,7 +11984,7 @@ static int hclge_set_vf_spoofchk_hw(struct hclge_dev *hdev, int vf, bool enable)
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Set vf %d vlan spoof check %s failed, ret=%d\n",
-			vf, enable ? "on" : "off", ret);
+			vf, str_on_off(enable), ret);
 
 	return ret;
 }
@@ -12301,7 +12328,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	/* Disable MISC vector(vector0) */
 	hclge_enable_vector(&hdev->misc_vector, false);
-	synchronize_irq(hdev->misc_vector.vector_irq);
+	disable_irq(hdev->misc_vector.vector_irq);
 
 	/* Disable all hw interrupts */
 	hclge_config_mac_tnl_int(hdev, false);
@@ -12892,9 +12919,11 @@ static int __init hclge_init(void)
 
 static void __exit hclge_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo_prepare(&ae_algo);
 	hnae3_unregister_ae_algo(&ae_algo);
 	destroy_workqueue(hclge_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclge_init);
 module_exit(hclge_exit);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 80079657afeb..9a456ebf9b7c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -258,7 +258,7 @@ void hclge_mac_start_phy(struct hclge_dev *hdev)
 	if (!phydev)
 		return;
 
-	phy_loopback(phydev, false);
+	phy_loopback(phydev, false, 0);
 
 	phy_start(phydev);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 5505caea88e9..ec581d4b696f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2021 Hisilicon Limited.
 
 #include <linux/skbuff.h>
+#include <linux/string_choices.h>
 #include "hclge_main.h"
 #include "hnae3.h"
 
@@ -58,6 +59,9 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb)
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_ptp *ptp = hdev->ptp;
 
+	if (!ptp)
+		return false;
+
 	if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ||
 	    test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) {
 		ptp->tx_skipped++;
@@ -223,7 +227,7 @@ static int hclge_ptp_int_en(struct hclge_dev *hdev, bool en)
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"failed to %s ptp interrupt, ret = %d\n",
-			en ? "enable" : "disable", ret);
+			str_enable_disable(en), ret);
 
 	return ret;
 }
@@ -436,6 +440,13 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
 	ptp->info.settime64 = hclge_ptp_settime;
 
 	ptp->info.n_alarm = 0;
+
+	spin_lock_init(&ptp->lock);
+	ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
+	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
+	hdev->ptp = ptp;
+
 	ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev);
 	if (IS_ERR(ptp->clock)) {
 		dev_err(&hdev->pdev->dev,
@@ -447,12 +458,6 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
 		return -ENODEV;
 	}
 
-	spin_lock_init(&ptp->lock);
-	ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
-	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
-	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
-	hdev->ptp = ptp;
-
 	return 0;
 }
 
@@ -480,7 +485,7 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 
 		ret = hclge_ptp_get_cycle(hdev);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = hclge_ptp_int_en(hdev, true);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
index 43c1c18fa81f..8c057192aae6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c
@@ -510,9 +510,9 @@ out:
 static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
 			      struct hnae3_knic_private_info *kinfo)
 {
-#define HCLGE_RING_REG_OFFSET		0x200
 #define HCLGE_RING_INT_REG_OFFSET	0x4
 
+	struct hnae3_queue *tqp;
 	int i, j, reg_num;
 	int data_num_sum;
 	u32 *reg = data;
@@ -533,10 +533,11 @@ static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
 	reg_num = ARRAY_SIZE(ring_reg_addr_list);
 	for (j = 0; j < kinfo->num_tqps; j++) {
 		reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg);
+		tqp = kinfo->tqp[j];
 		for (i = 0; i < reg_num; i++)
-			*reg++ = hclge_read_dev(&hdev->hw,
-						ring_reg_addr_list[i] +
-						HCLGE_RING_REG_OFFSET * j);
+			*reg++ = readl_relaxed(tqp->io_base -
+					       HCLGE_TQP_REG_OFFSET +
+					       ring_reg_addr_list[i]);
 	}
 	data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 2f6ffb88e700..c4f35e8e2177 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1292,9 +1292,8 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
 	rtnl_unlock();
 }
 
-static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+static int hclgevf_en_hw_strip_rxvtag_cmd(struct hclgevf_dev *hdev, bool enable)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hclge_vf_to_pf_msg send_msg;
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
@@ -1303,6 +1302,19 @@ static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
 }
 
+static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int ret;
+
+	ret = hclgevf_en_hw_strip_rxvtag_cmd(hdev, enable);
+	if (ret)
+		return ret;
+
+	hdev->rxvtag_strip_en = enable;
+	return 0;
+}
+
 static int hclgevf_reset_tqp(struct hnae3_handle *handle)
 {
 #define HCLGEVF_RESET_ALL_QUEUE_DONE	1U
@@ -1393,6 +1405,17 @@ static int hclgevf_notify_roce_client(struct hclgevf_dev *hdev,
 	return ret;
 }
 
+static void hclgevf_set_reset_pending(struct hclgevf_dev *hdev,
+				      enum hnae3_reset_type reset_type)
+{
+	/* When an incorrect reset type is executed, the get_reset_level
+	 * function generates the HNAE3_NONE_RESET flag. As a result, this
+	 * type do not need to pending.
+	 */
+	if (reset_type != HNAE3_NONE_RESET)
+		set_bit(reset_type, &hdev->reset_pending);
+}
+
 static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 {
 #define HCLGEVF_RESET_WAIT_US	20000
@@ -1542,7 +1565,7 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev)
 		hdev->rst_stats.rst_fail_cnt);
 
 	if (hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT)
-		set_bit(hdev->reset_type, &hdev->reset_pending);
+		hclgevf_set_reset_pending(hdev, hdev->reset_type);
 
 	if (hclgevf_is_reset_pending(hdev)) {
 		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
@@ -1662,6 +1685,8 @@ static enum hnae3_reset_type hclgevf_get_reset_level(unsigned long *addr)
 		clear_bit(HNAE3_FLR_RESET, addr);
 	}
 
+	clear_bit(HNAE3_NONE_RESET, addr);
+
 	return rst_level;
 }
 
@@ -1671,14 +1696,15 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
 	struct hclgevf_dev *hdev = ae_dev->priv;
 
-	dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
-
 	if (hdev->default_reset_request)
 		hdev->reset_level =
 			hclgevf_get_reset_level(&hdev->default_reset_request);
 	else
 		hdev->reset_level = HNAE3_VF_FUNC_RESET;
 
+	dev_info(&hdev->pdev->dev, "received reset request from VF enet, reset level is %d\n",
+		 hdev->reset_level);
+
 	/* reset of this VF requested */
 	set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
 	hclgevf_reset_task_schedule(hdev);
@@ -1689,8 +1715,20 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
 static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
 					  enum hnae3_reset_type rst_type)
 {
+#define HCLGEVF_SUPPORT_RESET_TYPE \
+	(BIT(HNAE3_VF_RESET) | BIT(HNAE3_VF_FUNC_RESET) | \
+	BIT(HNAE3_VF_PF_FUNC_RESET) | BIT(HNAE3_VF_FULL_RESET) | \
+	BIT(HNAE3_FLR_RESET) | BIT(HNAE3_VF_EXP_RESET))
+
 	struct hclgevf_dev *hdev = ae_dev->priv;
 
+	if (!(BIT(rst_type) & HCLGEVF_SUPPORT_RESET_TYPE)) {
+		/* To prevent reset triggered by hclge_reset_event */
+		set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request);
+		dev_info(&hdev->pdev->dev, "unsupported reset type %d\n",
+			 rst_type);
+		return;
+	}
 	set_bit(rst_type, &hdev->default_reset_request);
 }
 
@@ -1847,14 +1885,14 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev)
 		 */
 		if (hdev->reset_attempts > HCLGEVF_MAX_RESET_ATTEMPTS_CNT) {
 			/* prepare for full reset of stack + pcie interface */
-			set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending);
+			hclgevf_set_reset_pending(hdev, HNAE3_VF_FULL_RESET);
 
 			/* "defer" schedule the reset task again */
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		} else {
 			hdev->reset_attempts++;
 
-			set_bit(hdev->reset_level, &hdev->reset_pending);
+			hclgevf_set_reset_pending(hdev, hdev->reset_level);
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		}
 		hclgevf_reset_task_schedule(hdev);
@@ -1977,7 +2015,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 		rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
 		dev_info(&hdev->pdev->dev,
 			 "receive reset interrupt 0x%x!\n", rst_ing_reg);
-		set_bit(HNAE3_VF_RESET, &hdev->reset_pending);
+		hclgevf_set_reset_pending(hdev, HNAE3_VF_RESET);
 		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
 		*clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B);
@@ -2019,7 +2057,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 
 static void hclgevf_reset_timer(struct timer_list *t)
 {
-	struct hclgevf_dev *hdev = from_timer(hdev, t, reset_timer);
+	struct hclgevf_dev *hdev = timer_container_of(hdev, t, reset_timer);
 
 	hclgevf_clear_event_cause(hdev, HCLGEVF_VECTOR0_EVENT_RST);
 	hclgevf_reset_task_schedule(hdev);
@@ -2178,12 +2216,13 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 					  tc_valid, tc_size);
 }
 
-static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
+static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev,
+				    bool rxvtag_strip_en)
 {
 	struct hnae3_handle *nic = &hdev->nic;
 	int ret;
 
-	ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+	ret = hclgevf_en_hw_strip_rxvtag(nic, rxvtag_strip_en);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to enable rx vlan offload, ret = %d\n", ret);
@@ -2287,6 +2326,8 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev)
 	clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state);
 
 	INIT_DELAYED_WORK(&hdev->service_task, hclgevf_service_task);
+	/* timer needs to be initialized before misc irq */
+	timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0);
 
 	mutex_init(&hdev->mbx_resp.mbx_mutex);
 	sema_init(&hdev->reset_sem, 1);
@@ -2851,7 +2892,7 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclgevf_init_vlan_config(hdev);
+	ret = hclgevf_init_vlan_config(hdev, hdev->rxvtag_strip_en);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to initialize VLAN config\n", ret);
@@ -2966,7 +3007,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
-	ret = hclgevf_init_vlan_config(hdev);
+	ret = hclgevf_init_vlan_config(hdev, true);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to initialize VLAN config\n", ret);
@@ -2986,7 +3027,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		 HCLGEVF_DRIVER_NAME);
 
 	hclgevf_task_schedule(hdev, round_jiffies_relative(HZ));
-	timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0);
 
 	return 0;
 
@@ -3383,8 +3423,10 @@ static int __init hclgevf_init(void)
 
 static void __exit hclgevf_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo(&ae_algovf);
 	destroy_workqueue(hclgevf_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclgevf_init);
 module_exit(hclgevf_exit);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index cccef3228461..0208425ab594 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -253,6 +253,7 @@ struct hclgevf_dev {
 	int *vector_irq;
 
 	bool gro_en;
+	bool rxvtag_strip_en;
 
 	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
index 6db415d8b917..7d9d9dbc7560 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
@@ -123,10 +123,10 @@ int hclgevf_get_regs_len(struct hnae3_handle *handle)
 void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
 		      void *data)
 {
-#define HCLGEVF_RING_REG_OFFSET		0x200
 #define HCLGEVF_RING_INT_REG_OFFSET	0x4
 
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	struct hnae3_queue *tqp;
 	int i, j, reg_um;
 	u32 *reg = data;
 
@@ -147,10 +147,11 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
 	reg_um = ARRAY_SIZE(ring_reg_addr_list);
 	for (j = 0; j < hdev->num_tqps; j++) {
 		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg);
+		tqp = &hdev->htqp[j].q;
 		for (i = 0; i < reg_um; i++)
-			*reg++ = hclgevf_read_dev(&hdev->hw,
-						  ring_reg_addr_list[i] +
-						  HCLGEVF_RING_REG_OFFSET * j);
+			*reg++ = readl_relaxed(tqp->io_base -
+					       HCLGEVF_TQP_REG_OFFSET +
+					       ring_reg_addr_list[i]);
 	}
 
 	reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list);
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index a1aa6c1f966e..6812be8dc64f 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -640,7 +640,7 @@ static struct platform_driver hns_mdio_driver = {
 	.driver = {
 		   .name = MDIO_DRV_NAME,
 		   .of_match_table = hns_mdio_match,
-		   .acpi_match_table = ACPI_PTR(hns_mdio_acpi_match),
+		   .acpi_match_table = hns_mdio_acpi_match,
 		   },
 };
 
diff --git a/drivers/net/ethernet/huawei/Kconfig b/drivers/net/ethernet/huawei/Kconfig
index c05fce15eb51..7d0feb1da158 100644
--- a/drivers/net/ethernet/huawei/Kconfig
+++ b/drivers/net/ethernet/huawei/Kconfig
@@ -16,5 +16,6 @@ config NET_VENDOR_HUAWEI
 if NET_VENDOR_HUAWEI
 
 source "drivers/net/ethernet/huawei/hinic/Kconfig"
+source "drivers/net/ethernet/huawei/hinic3/Kconfig"
 
 endif # NET_VENDOR_HUAWEI
diff --git a/drivers/net/ethernet/huawei/Makefile b/drivers/net/ethernet/huawei/Makefile
index 2549ad5afe6d..59865b882879 100644
--- a/drivers/net/ethernet/huawei/Makefile
+++ b/drivers/net/ethernet/huawei/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_HINIC) += hinic/
+obj-$(CONFIG_HINIC3) += hinic3/
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 890f213da8d1..ae1f523d6841 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -172,6 +172,7 @@ err_init_txq:
 	hinic_sq_dbgfs_uninit(nic_dev);
 
 	devm_kfree(&netdev->dev, nic_dev->txqs);
+	nic_dev->txqs = NULL;
 	return err;
 }
 
@@ -268,6 +269,7 @@ err_init_rxq:
 	hinic_rq_dbgfs_uninit(nic_dev);
 
 	devm_kfree(&netdev->dev, nic_dev->rxqs);
+	nic_dev->rxqs = NULL;
 	return err;
 }
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index f81a43d2cdfc..486fb0e20bef 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -469,7 +469,7 @@ int hinic_set_vlan_fliter(struct hinic_dev *nic_dev, u32 en)
 		err = HINIC_MGMT_CMD_UNSUPPORTED;
 	} else if (err || !out_size || vlan_filter.status) {
 		dev_err(&pdev->dev,
-			"Failed to set vlan fliter, err: %d, status: 0x%x, out size: 0x%x\n",
+			"Failed to set vlan filter, err: %d, status: 0x%x, out size: 0x%x\n",
 			err, vlan_filter.status, out_size);
 		err = -EINVAL;
 	}
diff --git a/drivers/net/ethernet/huawei/hinic3/Kconfig b/drivers/net/ethernet/huawei/hinic3/Kconfig
new file mode 100644
index 000000000000..ce4331d1387b
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/Kconfig
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Huawei driver configuration
+#
+
+config HINIC3
+	tristate "Huawei 3rd generation network adapters (HINIC3) support"
+	# Fields of HW and management structures are little endian and are
+	# currently not converted
+	depends on !CPU_BIG_ENDIAN
+	depends on X86 || ARM64 || COMPILE_TEST
+	depends on PCI_MSI && 64BIT
+	select AUXILIARY_BUS
+	select PAGE_POOL
+	help
+	  This driver supports HiNIC 3rd gen Network Adapter (HINIC3).
+	  The driver is supported on X86_64 and ARM64 little endian.
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called hinic3.
diff --git a/drivers/net/ethernet/huawei/hinic3/Makefile b/drivers/net/ethernet/huawei/hinic3/Makefile
new file mode 100644
index 000000000000..509dfbfb0e96
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/Makefile
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+obj-$(CONFIG_HINIC3) += hinic3.o
+
+hinic3-objs := hinic3_common.o \
+	       hinic3_hw_cfg.o \
+	       hinic3_hw_comm.o \
+	       hinic3_hwdev.o \
+	       hinic3_hwif.o \
+	       hinic3_irq.o \
+	       hinic3_lld.o \
+	       hinic3_main.o \
+	       hinic3_mbox.o \
+	       hinic3_netdev_ops.o \
+	       hinic3_nic_cfg.o \
+	       hinic3_nic_io.o \
+	       hinic3_queue_common.o \
+	       hinic3_rx.o \
+	       hinic3_tx.o \
+	       hinic3_wq.o
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_common.c b/drivers/net/ethernet/huawei/hinic3/hinic3_common.c
new file mode 100644
index 000000000000..0aa42068728c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_common.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+
+#include "hinic3_common.h"
+
+int hinic3_dma_zalloc_coherent_align(struct device *dev, u32 size, u32 align,
+				     gfp_t flag,
+				     struct hinic3_dma_addr_align *mem_align)
+{
+	dma_addr_t paddr, align_paddr;
+	void *vaddr, *align_vaddr;
+	u32 real_size = size;
+
+	vaddr = dma_alloc_coherent(dev, real_size, &paddr, flag);
+	if (!vaddr)
+		return -ENOMEM;
+
+	align_paddr = ALIGN(paddr, align);
+	if (align_paddr == paddr) {
+		align_vaddr = vaddr;
+		goto out;
+	}
+
+	dma_free_coherent(dev, real_size, vaddr, paddr);
+
+	/* realloc memory for align */
+	real_size = size + align;
+	vaddr = dma_alloc_coherent(dev, real_size, &paddr, flag);
+	if (!vaddr)
+		return -ENOMEM;
+
+	align_paddr = ALIGN(paddr, align);
+	align_vaddr = vaddr + (align_paddr - paddr);
+
+out:
+	mem_align->real_size = real_size;
+	mem_align->ori_vaddr = vaddr;
+	mem_align->ori_paddr = paddr;
+	mem_align->align_vaddr = align_vaddr;
+	mem_align->align_paddr = align_paddr;
+
+	return 0;
+}
+
+void hinic3_dma_free_coherent_align(struct device *dev,
+				    struct hinic3_dma_addr_align *mem_align)
+{
+	dma_free_coherent(dev, mem_align->real_size,
+			  mem_align->ori_vaddr, mem_align->ori_paddr);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_common.h b/drivers/net/ethernet/huawei/hinic3/hinic3_common.h
new file mode 100644
index 000000000000..bb795dace04c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_common.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_COMMON_H_
+#define _HINIC3_COMMON_H_
+
+#include <linux/device.h>
+
+#define HINIC3_MIN_PAGE_SIZE  0x1000
+
+struct hinic3_dma_addr_align {
+	u32        real_size;
+
+	void       *ori_vaddr;
+	dma_addr_t ori_paddr;
+
+	void       *align_vaddr;
+	dma_addr_t align_paddr;
+};
+
+int hinic3_dma_zalloc_coherent_align(struct device *dev, u32 size, u32 align,
+				     gfp_t flag,
+				     struct hinic3_dma_addr_align *mem_align);
+void hinic3_dma_free_coherent_align(struct device *dev,
+				    struct hinic3_dma_addr_align *mem_align);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
new file mode 100644
index 000000000000..87d9450c30ca
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/device.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+bool hinic3_support_nic(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.supp_svcs_bitmap &
+	       BIT(HINIC3_SERVICE_T_NIC);
+}
+
+u16 hinic3_func_max_qnum(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.nic_svc_cap.max_sqs;
+}
+
+u8 hinic3_physical_port_id(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.port_id;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
new file mode 100644
index 000000000000..e017b1ae9f05
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_CFG_H_
+#define _HINIC3_HW_CFG_H_
+
+#include <linux/mutex.h>
+#include <linux/pci.h>
+
+struct hinic3_hwdev;
+
+struct hinic3_irq {
+	u32  irq_id;
+	u16  msix_entry_idx;
+	bool allocated;
+};
+
+struct hinic3_irq_info {
+	struct hinic3_irq *irq;
+	u16               num_irq;
+	/* device max irq number */
+	u16               num_irq_hw;
+	/* protect irq alloc and free */
+	struct mutex      irq_mutex;
+};
+
+struct hinic3_nic_service_cap {
+	u16 max_sqs;
+};
+
+/* Device capabilities */
+struct hinic3_dev_cap {
+	/* Bitmasks of services supported by device */
+	u16                           supp_svcs_bitmap;
+	/* Physical port */
+	u8                            port_id;
+	struct hinic3_nic_service_cap nic_svc_cap;
+};
+
+struct hinic3_cfg_mgmt_info {
+	struct hinic3_irq_info irq_info;
+	struct hinic3_dev_cap  cap;
+};
+
+int hinic3_alloc_irqs(struct hinic3_hwdev *hwdev, u16 num,
+		      struct msix_entry *alloc_arr, u16 *act_num);
+void hinic3_free_irq(struct hinic3_hwdev *hwdev, u32 irq_id);
+
+bool hinic3_support_nic(struct hinic3_hwdev *hwdev);
+u16 hinic3_func_max_qnum(struct hinic3_hwdev *hwdev);
+u8 hinic3_physical_port_id(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
new file mode 100644
index 000000000000..434696ce7dc2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+int hinic3_func_reset(struct hinic3_hwdev *hwdev, u16 func_id, u64 reset_flag)
+{
+	struct comm_cmd_func_reset func_reset = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	func_reset.func_id = func_id;
+	func_reset.reset_flag = reset_flag;
+
+	mgmt_msg_params_init_default(&msg_params, &func_reset,
+				     sizeof(func_reset));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_FUNC_RESET, &msg_params);
+	if (err || func_reset.head.status) {
+		dev_err(hwdev->dev, "Failed to reset func resources, reset_flag 0x%llx, err: %d, status: 0x%x\n",
+			reset_flag, err, func_reset.head.status);
+		return -EIO;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
new file mode 100644
index 000000000000..c33a1c77da9c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_COMM_H_
+#define _HINIC3_HW_COMM_H_
+
+#include "hinic3_hw_intf.h"
+
+struct hinic3_hwdev;
+
+int hinic3_func_reset(struct hinic3_hwdev *hwdev, u16 func_id, u64 reset_flag);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
new file mode 100644
index 000000000000..22c84093efa2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_INTF_H_
+#define _HINIC3_HW_INTF_H_
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+#define MGMT_MSG_CMD_OP_SET   1
+#define MGMT_MSG_CMD_OP_GET   0
+
+#define MGMT_STATUS_PF_SET_VF_ALREADY  0x4
+#define MGMT_STATUS_EXIST              0x6
+#define MGMT_STATUS_CMD_UNSUPPORTED    0xFF
+
+#define MGMT_MSG_POLLING_TIMEOUT 0
+
+struct mgmt_msg_head {
+	u8 status;
+	u8 version;
+	u8 rsvd0[6];
+};
+
+struct mgmt_msg_params {
+	const void  *buf_in;
+	u32         in_size;
+	void        *buf_out;
+	u32         expected_out_size;
+	u32         timeout_ms;
+};
+
+/* CMDQ MODULE_TYPE */
+enum mgmt_mod_type {
+	/* HW communication module */
+	MGMT_MOD_COMM   = 0,
+	/* L2NIC module */
+	MGMT_MOD_L2NIC  = 1,
+	/* Configuration module */
+	MGMT_MOD_CFGM   = 7,
+	MGMT_MOD_HILINK = 14,
+};
+
+static inline void mgmt_msg_params_init_default(struct mgmt_msg_params *msg_params,
+						void *inout_buf, u32 buf_size)
+{
+	msg_params->buf_in = inout_buf;
+	msg_params->buf_out = inout_buf;
+	msg_params->in_size = buf_size;
+	msg_params->expected_out_size = buf_size;
+	msg_params->timeout_ms = 0;
+}
+
+/* COMM Commands between Driver to fw */
+enum comm_cmd {
+	/* Commands for clearing FLR and resources */
+	COMM_CMD_FUNC_RESET              = 0,
+	COMM_CMD_FEATURE_NEGO            = 1,
+	COMM_CMD_FLUSH_DOORBELL          = 2,
+	COMM_CMD_START_FLUSH             = 3,
+	COMM_CMD_GET_GLOBAL_ATTR         = 5,
+	COMM_CMD_SET_FUNC_SVC_USED_STATE = 7,
+
+	/* Driver Configuration Commands */
+	COMM_CMD_SET_CMDQ_CTXT           = 20,
+	COMM_CMD_SET_VAT                 = 21,
+	COMM_CMD_CFG_PAGESIZE            = 22,
+	COMM_CMD_CFG_MSIX_CTRL_REG       = 23,
+	COMM_CMD_SET_CEQ_CTRL_REG        = 24,
+	COMM_CMD_SET_DMA_ATTR            = 25,
+};
+
+enum comm_func_reset_bits {
+	COMM_FUNC_RESET_BIT_FLUSH        = BIT(0),
+	COMM_FUNC_RESET_BIT_MQM          = BIT(1),
+	COMM_FUNC_RESET_BIT_SMF          = BIT(2),
+	COMM_FUNC_RESET_BIT_PF_BW_CFG    = BIT(3),
+
+	COMM_FUNC_RESET_BIT_COMM         = BIT(10),
+	/* clear mbox and aeq, The COMM_FUNC_RESET_BIT_COMM bit must be set */
+	COMM_FUNC_RESET_BIT_COMM_MGMT_CH = BIT(11),
+	/* clear cmdq and ceq, The COMM_FUNC_RESET_BIT_COMM bit must be set */
+	COMM_FUNC_RESET_BIT_COMM_CMD_CH  = BIT(12),
+	COMM_FUNC_RESET_BIT_NIC          = BIT(13),
+};
+
+struct comm_cmd_func_reset {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u16                  rsvd1[3];
+	u64                  reset_flag;
+};
+
+#define COMM_MAX_FEATURE_QWORD  4
+struct comm_cmd_feature_nego {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd;
+	u64                  s_feature[COMM_MAX_FEATURE_QWORD];
+};
+
+/* Services supported by HW. HW uses these values when delivering events.
+ * HW supports multiple services that are not yet supported by driver
+ * (e.g. RoCE).
+ */
+enum hinic3_service_type {
+	HINIC3_SERVICE_T_NIC = 0,
+	/* MAX is only used by SW for array sizes. */
+	HINIC3_SERVICE_T_MAX = 1,
+};
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
new file mode 100644
index 000000000000..6e8788a64925
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_mgmt.h"
+
+int hinic3_init_hwdev(struct pci_dev *pdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_hwdev(struct hinic3_hwdev *hwdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+void hinic3_set_api_stop(struct hinic3_hwdev *hwdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
new file mode 100644
index 000000000000..62e2745e9316
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HWDEV_H_
+#define _HINIC3_HWDEV_H_
+
+#include <linux/auxiliary_bus.h>
+#include <linux/pci.h>
+
+#include "hinic3_hw_intf.h"
+
+struct hinic3_cmdqs;
+struct hinic3_hwif;
+
+enum hinic3_event_service_type {
+	HINIC3_EVENT_SRV_COMM = 0,
+	HINIC3_EVENT_SRV_NIC  = 1
+};
+
+#define HINIC3_SRV_EVENT_TYPE(svc, type)    (((svc) << 16) | (type))
+
+/* driver-specific data of pci_dev */
+struct hinic3_pcidev {
+	struct pci_dev       *pdev;
+	struct hinic3_hwdev  *hwdev;
+	/* Auxiliary devices */
+	struct hinic3_adev   *hadev[HINIC3_SERVICE_T_MAX];
+
+	void __iomem         *cfg_reg_base;
+	void __iomem         *intr_reg_base;
+	void __iomem         *db_base;
+	u64                  db_dwqe_len;
+	u64                  db_base_phy;
+
+	/* lock for attach/detach uld */
+	struct mutex         pdev_mutex;
+	unsigned long        state;
+};
+
+struct hinic3_hwdev {
+	struct hinic3_pcidev        *adapter;
+	struct pci_dev              *pdev;
+	struct device               *dev;
+	int                         dev_id;
+	struct hinic3_hwif          *hwif;
+	struct hinic3_cfg_mgmt_info *cfg_mgmt;
+	struct hinic3_aeqs          *aeqs;
+	struct hinic3_ceqs          *ceqs;
+	struct hinic3_mbox          *mbox;
+	struct hinic3_cmdqs         *cmdqs;
+	struct workqueue_struct     *workq;
+	/* protect channel init and uninit */
+	spinlock_t                  channel_lock;
+	u64                         features[COMM_MAX_FEATURE_QWORD];
+	u32                         wq_page_size;
+	u8                          max_cmdq;
+	ulong                       func_state;
+};
+
+struct hinic3_event_info {
+	/* enum hinic3_event_service_type */
+	u16 service;
+	u16 type;
+	u8  event_data[104];
+};
+
+struct hinic3_adev {
+	struct auxiliary_device  adev;
+	struct hinic3_hwdev      *hwdev;
+	enum hinic3_service_type svc_type;
+
+	void (*event)(struct auxiliary_device *adev,
+		      struct hinic3_event_info *event);
+};
+
+int hinic3_init_hwdev(struct pci_dev *pdev);
+void hinic3_free_hwdev(struct hinic3_hwdev *hwdev);
+
+void hinic3_set_api_stop(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
new file mode 100644
index 000000000000..0865453bf0e7
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/io.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+
+void hinic3_set_msix_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+			   enum hinic3_msix_state flag)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+u16 hinic3_global_func_id(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->hwif->attr.func_global_idx;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
new file mode 100644
index 000000000000..513c9680e6b6
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HWIF_H_
+#define _HINIC3_HWIF_H_
+
+#include <linux/build_bug.h>
+#include <linux/spinlock_types.h>
+
+struct hinic3_hwdev;
+
+enum hinic3_func_type {
+	HINIC3_FUNC_TYPE_VF = 1,
+};
+
+struct hinic3_db_area {
+	unsigned long *db_bitmap_array;
+	u32           db_max_areas;
+	/* protect doorbell area alloc and free */
+	spinlock_t    idx_lock;
+};
+
+struct hinic3_func_attr {
+	enum hinic3_func_type func_type;
+	u16                   func_global_idx;
+	u16                   global_vf_id_of_pf;
+	u16                   num_irqs;
+	u16                   num_sq;
+	u8                    port_to_port_idx;
+	u8                    pci_intf_idx;
+	u8                    ppf_idx;
+	u8                    num_aeqs;
+	u8                    num_ceqs;
+	u8                    msix_flex_en;
+};
+
+static_assert(sizeof(struct hinic3_func_attr) == 20);
+
+struct hinic3_hwif {
+	u8 __iomem              *cfg_regs_base;
+	u64                     db_base_phy;
+	u64                     db_dwqe_len;
+	u8 __iomem              *db_base;
+	struct hinic3_db_area   db_area;
+	struct hinic3_func_attr attr;
+};
+
+enum hinic3_msix_state {
+	HINIC3_MSIX_ENABLE,
+	HINIC3_MSIX_DISABLE,
+};
+
+void hinic3_set_msix_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+			   enum hinic3_msix_state flag);
+
+u16 hinic3_global_func_id(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
new file mode 100644
index 000000000000..8b92eed25edf
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/netdevice.h>
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+static int hinic3_poll(struct napi_struct *napi, int budget)
+{
+	struct hinic3_irq_cfg *irq_cfg =
+		container_of(napi, struct hinic3_irq_cfg, napi);
+	struct hinic3_nic_dev *nic_dev;
+	bool busy = false;
+	int work_done;
+
+	nic_dev = netdev_priv(irq_cfg->netdev);
+
+	busy |= hinic3_tx_poll(irq_cfg->txq, budget);
+
+	if (unlikely(!budget))
+		return 0;
+
+	work_done = hinic3_rx_poll(irq_cfg->rxq, budget);
+	busy |= work_done >= budget;
+
+	if (busy)
+		return budget;
+
+	if (likely(napi_complete_done(napi, work_done)))
+		hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx,
+				      HINIC3_MSIX_ENABLE);
+
+	return work_done;
+}
+
+void qp_add_napi(struct hinic3_irq_cfg *irq_cfg)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(irq_cfg->netdev);
+
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi);
+	netif_napi_add(nic_dev->netdev, &irq_cfg->napi, hinic3_poll);
+	napi_enable(&irq_cfg->napi);
+}
+
+void qp_del_napi(struct hinic3_irq_cfg *irq_cfg)
+{
+	napi_disable(&irq_cfg->napi);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_RX, NULL);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_TX, NULL);
+	netif_stop_subqueue(irq_cfg->netdev, irq_cfg->irq_id);
+	netif_napi_del(&irq_cfg->napi);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
new file mode 100644
index 000000000000..4827326e6a59
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
@@ -0,0 +1,414 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+#include <linux/iopoll.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_lld.h"
+#include "hinic3_mgmt.h"
+
+#define HINIC3_VF_PCI_CFG_REG_BAR  0
+#define HINIC3_PCI_INTR_REG_BAR    2
+#define HINIC3_PCI_DB_BAR          4
+
+#define HINIC3_EVENT_POLL_SLEEP_US   1000
+#define HINIC3_EVENT_POLL_TIMEOUT_US 10000000
+
+static struct hinic3_adev_device {
+	const char *name;
+} hinic3_adev_devices[HINIC3_SERVICE_T_MAX] = {
+	[HINIC3_SERVICE_T_NIC] = {
+		.name = "nic",
+	},
+};
+
+static bool hinic3_adev_svc_supported(struct hinic3_hwdev *hwdev,
+				      enum hinic3_service_type svc_type)
+{
+	switch (svc_type) {
+	case HINIC3_SERVICE_T_NIC:
+		return hinic3_support_nic(hwdev);
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static void hinic3_comm_adev_release(struct device *dev)
+{
+	struct hinic3_adev *hadev = container_of(dev, struct hinic3_adev,
+						 adev.dev);
+
+	kfree(hadev);
+}
+
+static struct hinic3_adev *hinic3_add_one_adev(struct hinic3_hwdev *hwdev,
+					       enum hinic3_service_type svc_type)
+{
+	struct hinic3_adev *hadev;
+	const char *svc_name;
+	int ret;
+
+	hadev = kzalloc(sizeof(*hadev), GFP_KERNEL);
+	if (!hadev)
+		return NULL;
+
+	svc_name = hinic3_adev_devices[svc_type].name;
+	hadev->adev.name = svc_name;
+	hadev->adev.id = hwdev->dev_id;
+	hadev->adev.dev.parent = hwdev->dev;
+	hadev->adev.dev.release = hinic3_comm_adev_release;
+	hadev->svc_type = svc_type;
+	hadev->hwdev = hwdev;
+
+	ret = auxiliary_device_init(&hadev->adev);
+	if (ret) {
+		dev_err(hwdev->dev, "failed init adev %s %u\n",
+			svc_name, hwdev->dev_id);
+		kfree(hadev);
+		return NULL;
+	}
+
+	ret = auxiliary_device_add(&hadev->adev);
+	if (ret) {
+		dev_err(hwdev->dev, "failed to add adev %s %u\n",
+			svc_name, hwdev->dev_id);
+		auxiliary_device_uninit(&hadev->adev);
+		return NULL;
+	}
+
+	return hadev;
+}
+
+static void hinic3_del_one_adev(struct hinic3_hwdev *hwdev,
+				enum hinic3_service_type svc_type)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	struct hinic3_adev *hadev;
+	int timeout;
+	bool state;
+
+	timeout = read_poll_timeout(test_and_set_bit, state, !state,
+				    HINIC3_EVENT_POLL_SLEEP_US,
+				    HINIC3_EVENT_POLL_TIMEOUT_US,
+				    false, svc_type, &pci_adapter->state);
+
+	hadev = pci_adapter->hadev[svc_type];
+	auxiliary_device_delete(&hadev->adev);
+	auxiliary_device_uninit(&hadev->adev);
+	pci_adapter->hadev[svc_type] = NULL;
+	if (!timeout)
+		clear_bit(svc_type, &pci_adapter->state);
+}
+
+static int hinic3_attach_aux_devices(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	enum hinic3_service_type svc_type;
+
+	mutex_lock(&pci_adapter->pdev_mutex);
+
+	for (svc_type = 0; svc_type < HINIC3_SERVICE_T_MAX; svc_type++) {
+		if (!hinic3_adev_svc_supported(hwdev, svc_type))
+			continue;
+
+		pci_adapter->hadev[svc_type] = hinic3_add_one_adev(hwdev,
+								   svc_type);
+		if (!pci_adapter->hadev[svc_type])
+			goto err_del_adevs;
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+	return 0;
+
+err_del_adevs:
+	while (svc_type > 0) {
+		svc_type--;
+		if (pci_adapter->hadev[svc_type]) {
+			hinic3_del_one_adev(hwdev, svc_type);
+			pci_adapter->hadev[svc_type] = NULL;
+		}
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+	return -ENOMEM;
+}
+
+static void hinic3_detach_aux_devices(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	int i;
+
+	mutex_lock(&pci_adapter->pdev_mutex);
+	for (i = 0; i < ARRAY_SIZE(hinic3_adev_devices); i++) {
+		if (pci_adapter->hadev[i])
+			hinic3_del_one_adev(hwdev, i);
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+}
+
+struct hinic3_hwdev *hinic3_adev_get_hwdev(struct auxiliary_device *adev)
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	return hadev->hwdev;
+}
+
+void hinic3_adev_event_register(struct auxiliary_device *adev,
+				void (*event_handler)(struct auxiliary_device *adev,
+						      struct hinic3_event_info *event))
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	hadev->event = event_handler;
+}
+
+void hinic3_adev_event_unregister(struct auxiliary_device *adev)
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	hadev->event = NULL;
+}
+
+static int hinic3_mapping_bar(struct pci_dev *pdev,
+			      struct hinic3_pcidev *pci_adapter)
+{
+	pci_adapter->cfg_reg_base = pci_ioremap_bar(pdev,
+						    HINIC3_VF_PCI_CFG_REG_BAR);
+	if (!pci_adapter->cfg_reg_base) {
+		dev_err(&pdev->dev, "Failed to map configuration regs\n");
+		return -ENOMEM;
+	}
+
+	pci_adapter->intr_reg_base = pci_ioremap_bar(pdev,
+						     HINIC3_PCI_INTR_REG_BAR);
+	if (!pci_adapter->intr_reg_base) {
+		dev_err(&pdev->dev, "Failed to map interrupt regs\n");
+		goto err_unmap_cfg_reg_base;
+	}
+
+	pci_adapter->db_base_phy = pci_resource_start(pdev, HINIC3_PCI_DB_BAR);
+	pci_adapter->db_dwqe_len = pci_resource_len(pdev, HINIC3_PCI_DB_BAR);
+	pci_adapter->db_base = pci_ioremap_bar(pdev, HINIC3_PCI_DB_BAR);
+	if (!pci_adapter->db_base) {
+		dev_err(&pdev->dev, "Failed to map doorbell regs\n");
+		goto err_unmap_intr_reg_base;
+	}
+
+	return 0;
+
+err_unmap_intr_reg_base:
+	iounmap(pci_adapter->intr_reg_base);
+
+err_unmap_cfg_reg_base:
+	iounmap(pci_adapter->cfg_reg_base);
+
+	return -ENOMEM;
+}
+
+static void hinic3_unmapping_bar(struct hinic3_pcidev *pci_adapter)
+{
+	iounmap(pci_adapter->db_base);
+	iounmap(pci_adapter->intr_reg_base);
+	iounmap(pci_adapter->cfg_reg_base);
+}
+
+static int hinic3_pci_init(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter;
+	int err;
+
+	pci_adapter = kzalloc(sizeof(*pci_adapter), GFP_KERNEL);
+	if (!pci_adapter)
+		return -ENOMEM;
+
+	pci_adapter->pdev = pdev;
+	mutex_init(&pci_adapter->pdev_mutex);
+
+	pci_set_drvdata(pdev, pci_adapter);
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to enable PCI device\n");
+		goto err_free_pci_adapter;
+	}
+
+	err = pci_request_regions(pdev, HINIC3_NIC_DRV_NAME);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to request regions\n");
+		goto err_disable_device;
+	}
+
+	pci_set_master(pdev);
+
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_err(&pdev->dev, "Failed to set DMA mask\n");
+		goto err_release_regions;
+	}
+
+	return 0;
+
+err_release_regions:
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+
+err_disable_device:
+	pci_disable_device(pdev);
+
+err_free_pci_adapter:
+	pci_set_drvdata(pdev, NULL);
+	mutex_destroy(&pci_adapter->pdev_mutex);
+	kfree(pci_adapter);
+
+	return err;
+}
+
+static void hinic3_pci_uninit(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+	mutex_destroy(&pci_adapter->pdev_mutex);
+	kfree(pci_adapter);
+}
+
+static int hinic3_func_init(struct pci_dev *pdev,
+			    struct hinic3_pcidev *pci_adapter)
+{
+	int err;
+
+	err = hinic3_init_hwdev(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to initialize hardware device\n");
+		return err;
+	}
+
+	err = hinic3_attach_aux_devices(pci_adapter->hwdev);
+	if (err)
+		goto err_free_hwdev;
+
+	return 0;
+
+err_free_hwdev:
+	hinic3_free_hwdev(pci_adapter->hwdev);
+
+	return err;
+}
+
+static void hinic3_func_uninit(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	hinic3_detach_aux_devices(pci_adapter->hwdev);
+	hinic3_free_hwdev(pci_adapter->hwdev);
+}
+
+static int hinic3_probe_func(struct hinic3_pcidev *pci_adapter)
+{
+	struct pci_dev *pdev = pci_adapter->pdev;
+	int err;
+
+	err = hinic3_mapping_bar(pdev, pci_adapter);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to map bar\n");
+		goto err_out;
+	}
+
+	err = hinic3_func_init(pdev, pci_adapter);
+	if (err)
+		goto err_unmap_bar;
+
+	return 0;
+
+err_unmap_bar:
+	hinic3_unmapping_bar(pci_adapter);
+
+err_out:
+	dev_err(&pdev->dev, "PCIe device probe function failed\n");
+	return err;
+}
+
+static void hinic3_remove_func(struct hinic3_pcidev *pci_adapter)
+{
+	struct pci_dev *pdev = pci_adapter->pdev;
+
+	hinic3_func_uninit(pdev);
+	hinic3_unmapping_bar(pci_adapter);
+}
+
+static int hinic3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct hinic3_pcidev *pci_adapter;
+	int err;
+
+	err = hinic3_pci_init(pdev);
+	if (err)
+		goto err_out;
+
+	pci_adapter = pci_get_drvdata(pdev);
+	err = hinic3_probe_func(pci_adapter);
+	if (err)
+		goto err_uninit_pci;
+
+	return 0;
+
+err_uninit_pci:
+	hinic3_pci_uninit(pdev);
+
+err_out:
+	dev_err(&pdev->dev, "PCIe device probe failed\n");
+	return err;
+}
+
+static void hinic3_remove(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	hinic3_remove_func(pci_adapter);
+	hinic3_pci_uninit(pdev);
+}
+
+static const struct pci_device_id hinic3_pci_table[] = {
+	/* Completed by later submission due to LoC limit. */
+	{0, 0}
+
+};
+
+MODULE_DEVICE_TABLE(pci, hinic3_pci_table);
+
+static void hinic3_shutdown(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	pci_disable_device(pdev);
+
+	if (pci_adapter)
+		hinic3_set_api_stop(pci_adapter->hwdev);
+}
+
+static struct pci_driver hinic3_driver = {
+	.name            = HINIC3_NIC_DRV_NAME,
+	.id_table        = hinic3_pci_table,
+	.probe           = hinic3_probe,
+	.remove          = hinic3_remove,
+	.shutdown        = hinic3_shutdown,
+	.sriov_configure = pci_sriov_configure_simple
+};
+
+int hinic3_lld_init(void)
+{
+	return pci_register_driver(&hinic3_driver);
+}
+
+void hinic3_lld_exit(void)
+{
+	pci_unregister_driver(&hinic3_driver);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
new file mode 100644
index 000000000000..322b44803476
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_LLD_H_
+#define _HINIC3_LLD_H_
+
+#include <linux/auxiliary_bus.h>
+
+struct hinic3_event_info;
+
+#define HINIC3_NIC_DRV_NAME "hinic3"
+
+int hinic3_lld_init(void);
+void hinic3_lld_exit(void);
+void hinic3_adev_event_register(struct auxiliary_device *adev,
+				void (*event_handler)(struct auxiliary_device *adev,
+						      struct hinic3_event_info *event));
+void hinic3_adev_event_unregister(struct auxiliary_device *adev);
+struct hinic3_hwdev *hinic3_adev_get_hwdev(struct auxiliary_device *adev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_main.c b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
new file mode 100644
index 000000000000..497f2a36f35d
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_lld.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+#define HINIC3_NIC_DRV_DESC  "Intelligent Network Interface Card Driver"
+
+#define HINIC3_RX_BUF_LEN            2048
+#define HINIC3_LRO_REPLENISH_THLD    256
+#define HINIC3_NIC_DEV_WQ_NAME       "hinic3_nic_dev_wq"
+
+#define HINIC3_SQ_DEPTH              1024
+#define HINIC3_RQ_DEPTH              1024
+
+static int hinic3_alloc_txrxqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	err = hinic3_alloc_txqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc txqs\n");
+		return err;
+	}
+
+	err = hinic3_alloc_rxqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc rxqs\n");
+		goto err_free_txqs;
+	}
+
+	return 0;
+
+err_free_txqs:
+	hinic3_free_txqs(netdev);
+
+	return err;
+}
+
+static void hinic3_free_txrxqs(struct net_device *netdev)
+{
+	hinic3_free_rxqs(netdev);
+	hinic3_free_txqs(netdev);
+}
+
+static int hinic3_init_nic_dev(struct net_device *netdev,
+			       struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = hwdev->pdev;
+
+	nic_dev->netdev = netdev;
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+	nic_dev->hwdev = hwdev;
+	nic_dev->pdev = pdev;
+
+	nic_dev->rx_buf_len = HINIC3_RX_BUF_LEN;
+	nic_dev->lro_replenish_thld = HINIC3_LRO_REPLENISH_THLD;
+	nic_dev->nic_svc_cap = hwdev->cfg_mgmt->cap.nic_svc_cap;
+
+	return 0;
+}
+
+static int hinic3_sw_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	nic_dev->q_params.sq_depth = HINIC3_SQ_DEPTH;
+	nic_dev->q_params.rq_depth = HINIC3_RQ_DEPTH;
+
+	/* VF driver always uses random MAC address. During VM migration to a
+	 * new device, the new device should learn the VMs old MAC rather than
+	 * provide its own MAC. The product design assumes that every VF is
+	 * suspectable to migration so the device avoids offering MAC address
+	 * to VFs.
+	 */
+	eth_hw_addr_random(netdev);
+	err = hinic3_set_mac(hwdev, netdev->dev_addr, 0,
+			     hinic3_global_func_id(hwdev));
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set default MAC\n");
+		return err;
+	}
+
+	err = hinic3_alloc_txrxqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc qps\n");
+		goto err_del_mac;
+	}
+
+	return 0;
+
+err_del_mac:
+	hinic3_del_mac(hwdev, netdev->dev_addr, 0,
+		       hinic3_global_func_id(hwdev));
+
+	return err;
+}
+
+static void hinic3_sw_uninit(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	hinic3_free_txrxqs(netdev);
+	hinic3_del_mac(nic_dev->hwdev, netdev->dev_addr, 0,
+		       hinic3_global_func_id(nic_dev->hwdev));
+}
+
+static void hinic3_assign_netdev_ops(struct net_device *netdev)
+{
+	hinic3_set_netdev_ops(netdev);
+}
+
+static void netdev_feature_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	netdev_features_t cso_fts = 0;
+	netdev_features_t tso_fts = 0;
+	netdev_features_t dft_fts;
+
+	dft_fts = NETIF_F_SG | NETIF_F_HIGHDMA;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_CSUM))
+		cso_fts |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_SCTP_CRC))
+		cso_fts |= NETIF_F_SCTP_CRC;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_TSO))
+		tso_fts |= NETIF_F_TSO | NETIF_F_TSO6;
+
+	netdev->features |= dft_fts | cso_fts | tso_fts;
+}
+
+static int hinic3_set_default_hw_feature(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	err = hinic3_set_nic_feature_to_hw(nic_dev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set nic features\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static void hinic3_link_status_change(struct net_device *netdev,
+				      bool link_status_up)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	if (link_status_up) {
+		if (netif_carrier_ok(netdev))
+			return;
+
+		nic_dev->link_status_up = true;
+		netif_carrier_on(netdev);
+		netdev_dbg(netdev, "Link is up\n");
+	} else {
+		if (!netif_carrier_ok(netdev))
+			return;
+
+		nic_dev->link_status_up = false;
+		netif_carrier_off(netdev);
+		netdev_dbg(netdev, "Link is down\n");
+	}
+}
+
+static void hinic3_nic_event(struct auxiliary_device *adev,
+			     struct hinic3_event_info *event)
+{
+	struct hinic3_nic_dev *nic_dev = dev_get_drvdata(&adev->dev);
+	struct net_device *netdev;
+
+	netdev = nic_dev->netdev;
+
+	switch (HINIC3_SRV_EVENT_TYPE(event->service, event->type)) {
+	case HINIC3_SRV_EVENT_TYPE(HINIC3_EVENT_SRV_NIC,
+				   HINIC3_NIC_EVENT_LINK_UP):
+		hinic3_link_status_change(netdev, true);
+		break;
+	case HINIC3_SRV_EVENT_TYPE(HINIC3_EVENT_SRV_NIC,
+				   HINIC3_NIC_EVENT_LINK_DOWN):
+		hinic3_link_status_change(netdev, false);
+		break;
+	default:
+		break;
+	}
+}
+
+static int hinic3_nic_probe(struct auxiliary_device *adev,
+			    const struct auxiliary_device_id *id)
+{
+	struct hinic3_hwdev *hwdev = hinic3_adev_get_hwdev(adev);
+	struct pci_dev *pdev = hwdev->pdev;
+	struct hinic3_nic_dev *nic_dev;
+	struct net_device *netdev;
+	u16 max_qps, glb_func_id;
+	int err;
+
+	if (!hinic3_support_nic(hwdev)) {
+		dev_dbg(&adev->dev, "HW doesn't support nic\n");
+		return 0;
+	}
+
+	hinic3_adev_event_register(adev, hinic3_nic_event);
+
+	glb_func_id = hinic3_global_func_id(hwdev);
+	err = hinic3_func_reset(hwdev, glb_func_id, COMM_FUNC_RESET_BIT_NIC);
+	if (err) {
+		dev_err(&adev->dev, "Failed to reset function\n");
+		goto err_unregister_adev_event;
+	}
+
+	max_qps = hinic3_func_max_qnum(hwdev);
+	netdev = alloc_etherdev_mq(sizeof(*nic_dev), max_qps);
+	if (!netdev) {
+		dev_err(&adev->dev, "Failed to allocate netdev\n");
+		err = -ENOMEM;
+		goto err_unregister_adev_event;
+	}
+
+	nic_dev = netdev_priv(netdev);
+	dev_set_drvdata(&adev->dev, nic_dev);
+	err = hinic3_init_nic_dev(netdev, hwdev);
+	if (err)
+		goto err_free_netdev;
+
+	err = hinic3_init_nic_io(nic_dev);
+	if (err)
+		goto err_free_netdev;
+
+	err = hinic3_sw_init(netdev);
+	if (err)
+		goto err_free_nic_io;
+
+	hinic3_assign_netdev_ops(netdev);
+
+	netdev_feature_init(netdev);
+	err = hinic3_set_default_hw_feature(netdev);
+	if (err)
+		goto err_uninit_sw;
+
+	netif_carrier_off(netdev);
+
+	err = register_netdev(netdev);
+	if (err)
+		goto err_uninit_nic_feature;
+
+	return 0;
+
+err_uninit_nic_feature:
+	hinic3_update_nic_feature(nic_dev, 0);
+	hinic3_set_nic_feature_to_hw(nic_dev);
+
+err_uninit_sw:
+	hinic3_sw_uninit(netdev);
+
+err_free_nic_io:
+	hinic3_free_nic_io(nic_dev);
+
+err_free_netdev:
+	free_netdev(netdev);
+
+err_unregister_adev_event:
+	hinic3_adev_event_unregister(adev);
+	dev_err(&pdev->dev, "NIC service probe failed\n");
+
+	return err;
+}
+
+static void hinic3_nic_remove(struct auxiliary_device *adev)
+{
+	struct hinic3_nic_dev *nic_dev = dev_get_drvdata(&adev->dev);
+	struct net_device *netdev;
+
+	if (!hinic3_support_nic(nic_dev->hwdev))
+		return;
+
+	netdev = nic_dev->netdev;
+	unregister_netdev(netdev);
+
+	hinic3_update_nic_feature(nic_dev, 0);
+	hinic3_set_nic_feature_to_hw(nic_dev);
+	hinic3_sw_uninit(netdev);
+
+	hinic3_free_nic_io(nic_dev);
+
+	free_netdev(netdev);
+}
+
+static const struct auxiliary_device_id hinic3_nic_id_table[] = {
+	{
+		.name = HINIC3_NIC_DRV_NAME ".nic",
+	},
+	{}
+};
+
+static struct auxiliary_driver hinic3_nic_driver = {
+	.probe    = hinic3_nic_probe,
+	.remove   = hinic3_nic_remove,
+	.suspend  = NULL,
+	.resume   = NULL,
+	.name     = "nic",
+	.id_table = hinic3_nic_id_table,
+};
+
+static __init int hinic3_nic_lld_init(void)
+{
+	int err;
+
+	err = hinic3_lld_init();
+	if (err)
+		return err;
+
+	err = auxiliary_driver_register(&hinic3_nic_driver);
+	if (err) {
+		hinic3_lld_exit();
+		return err;
+	}
+
+	return 0;
+}
+
+static __exit void hinic3_nic_lld_exit(void)
+{
+	auxiliary_driver_unregister(&hinic3_nic_driver);
+
+	hinic3_lld_exit();
+}
+
+module_init(hinic3_nic_lld_init);
+module_exit(hinic3_nic_lld_exit);
+
+MODULE_AUTHOR("Huawei Technologies CO., Ltd");
+MODULE_DESCRIPTION(HINIC3_NIC_DRV_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
new file mode 100644
index 000000000000..e74d1eb09730
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/dma-mapping.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+int hinic3_send_mbox_to_mgmt(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+			     const struct mgmt_msg_params *msg_params)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
new file mode 100644
index 000000000000..d7a6c37b7eff
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MBOX_H_
+#define _HINIC3_MBOX_H_
+
+#include <linux/bitfield.h>
+#include <linux/mutex.h>
+
+struct hinic3_hwdev;
+
+int hinic3_send_mbox_to_mgmt(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+			     const struct mgmt_msg_params *msg_params);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
new file mode 100644
index 000000000000..4edabeb32112
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MGMT_H_
+#define _HINIC3_MGMT_H_
+
+#include <linux/types.h>
+
+struct hinic3_hwdev;
+
+void hinic3_flush_mgmt_workq(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
new file mode 100644
index 000000000000..c4434efdc7f7
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MGMT_INTERFACE_H_
+#define _HINIC3_MGMT_INTERFACE_H_
+
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/if_ether.h>
+
+#include "hinic3_hw_intf.h"
+
+struct l2nic_cmd_feature_nego {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd;
+	u64                  s_feature[4];
+};
+
+enum l2nic_func_tbl_cfg_bitmap {
+	L2NIC_FUNC_TBL_CFG_INIT        = 0,
+	L2NIC_FUNC_TBL_CFG_RX_BUF_SIZE = 1,
+	L2NIC_FUNC_TBL_CFG_MTU         = 2,
+};
+
+struct l2nic_func_tbl_cfg {
+	u16 rx_wqe_buf_size;
+	u16 mtu;
+	u32 rsvd[9];
+};
+
+struct l2nic_cmd_set_func_tbl {
+	struct mgmt_msg_head      msg_head;
+	u16                       func_id;
+	u16                       rsvd;
+	u32                       cfg_bitmap;
+	struct l2nic_func_tbl_cfg tbl_cfg;
+};
+
+struct l2nic_cmd_set_mac {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  vlan_id;
+	u16                  rsvd1;
+	u8                   mac[ETH_ALEN];
+};
+
+struct l2nic_cmd_update_mac {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  vlan_id;
+	u16                  rsvd1;
+	u8                   old_mac[ETH_ALEN];
+	u16                  rsvd2;
+	u8                   new_mac[ETH_ALEN];
+};
+
+struct l2nic_cmd_force_pkt_drop {
+	struct mgmt_msg_head msg_head;
+	u8                   port;
+	u8                   rsvd1[3];
+};
+
+/* Commands between NIC to fw */
+enum l2nic_cmd {
+	/* FUNC CFG */
+	L2NIC_CMD_SET_FUNC_TBL        = 5,
+	L2NIC_CMD_SET_VPORT_ENABLE    = 6,
+	L2NIC_CMD_SET_SQ_CI_ATTR      = 8,
+	L2NIC_CMD_CLEAR_QP_RESOURCE   = 11,
+	L2NIC_CMD_FEATURE_NEGO        = 15,
+	L2NIC_CMD_SET_MAC             = 21,
+	L2NIC_CMD_DEL_MAC             = 22,
+	L2NIC_CMD_UPDATE_MAC          = 23,
+	L2NIC_CMD_CFG_RSS             = 60,
+	L2NIC_CMD_CFG_RSS_HASH_KEY    = 63,
+	L2NIC_CMD_CFG_RSS_HASH_ENGINE = 64,
+	L2NIC_CMD_SET_RSS_CTX_TBL     = 65,
+	L2NIC_CMD_QOS_DCB_STATE       = 110,
+	L2NIC_CMD_FORCE_PKT_DROP      = 113,
+	L2NIC_CMD_MAX                 = 256,
+};
+
+enum hinic3_nic_feature_cap {
+	HINIC3_NIC_F_CSUM           = BIT(0),
+	HINIC3_NIC_F_SCTP_CRC       = BIT(1),
+	HINIC3_NIC_F_TSO            = BIT(2),
+	HINIC3_NIC_F_LRO            = BIT(3),
+	HINIC3_NIC_F_UFO            = BIT(4),
+	HINIC3_NIC_F_RSS            = BIT(5),
+	HINIC3_NIC_F_RX_VLAN_FILTER = BIT(6),
+	HINIC3_NIC_F_RX_VLAN_STRIP  = BIT(7),
+	HINIC3_NIC_F_TX_VLAN_INSERT = BIT(8),
+	HINIC3_NIC_F_VXLAN_OFFLOAD  = BIT(9),
+	HINIC3_NIC_F_FDIR           = BIT(11),
+	HINIC3_NIC_F_PROMISC        = BIT(12),
+	HINIC3_NIC_F_ALLMULTI       = BIT(13),
+	HINIC3_NIC_F_RATE_LIMIT     = BIT(16),
+};
+
+#define HINIC3_NIC_F_ALL_MASK           0x33bff
+#define HINIC3_NIC_DRV_DEFAULT_FEATURE  0x3f03f
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
new file mode 100644
index 000000000000..71104a6b8bef
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic3_hwif.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+static int hinic3_open(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+static int hinic3_close(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+static int hinic3_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	int err;
+
+	err = hinic3_set_port_mtu(netdev, new_mtu);
+	if (err) {
+		netdev_err(netdev, "Failed to change port mtu to %d\n",
+			   new_mtu);
+		return err;
+	}
+
+	netdev_dbg(netdev, "Change mtu from %u to %d\n", netdev->mtu, new_mtu);
+	WRITE_ONCE(netdev->mtu, new_mtu);
+
+	return 0;
+}
+
+static int hinic3_set_mac_addr(struct net_device *netdev, void *addr)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct sockaddr *saddr = addr;
+	int err;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	if (ether_addr_equal(netdev->dev_addr, saddr->sa_data))
+		return 0;
+
+	err = hinic3_update_mac(nic_dev->hwdev, netdev->dev_addr,
+				saddr->sa_data, 0,
+				hinic3_global_func_id(nic_dev->hwdev));
+
+	if (err)
+		return err;
+
+	eth_hw_addr_set(netdev, saddr->sa_data);
+
+	return 0;
+}
+
+static const struct net_device_ops hinic3_netdev_ops = {
+	.ndo_open             = hinic3_open,
+	.ndo_stop             = hinic3_close,
+	.ndo_change_mtu       = hinic3_change_mtu,
+	.ndo_set_mac_address  = hinic3_set_mac_addr,
+	.ndo_start_xmit       = hinic3_xmit_frame,
+};
+
+void hinic3_set_netdev_ops(struct net_device *netdev)
+{
+	netdev->netdev_ops = &hinic3_netdev_ops;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
new file mode 100644
index 000000000000..5b1a91a18c67
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/if_vlan.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+
+static int hinic3_feature_nego(struct hinic3_hwdev *hwdev, u8 opcode,
+			       u64 *s_feature, u16 size)
+{
+	struct l2nic_cmd_feature_nego feature_nego = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	feature_nego.func_id = hinic3_global_func_id(hwdev);
+	feature_nego.opcode = opcode;
+	if (opcode == MGMT_MSG_CMD_OP_SET)
+		memcpy(feature_nego.s_feature, s_feature, size * sizeof(u64));
+
+	mgmt_msg_params_init_default(&msg_params, &feature_nego,
+				     sizeof(feature_nego));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_FEATURE_NEGO, &msg_params);
+	if (err || feature_nego.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to negotiate nic feature, err:%d, status: 0x%x\n",
+			err, feature_nego.msg_head.status);
+		return -EIO;
+	}
+
+	if (opcode == MGMT_MSG_CMD_OP_GET)
+		memcpy(s_feature, feature_nego.s_feature, size * sizeof(u64));
+
+	return 0;
+}
+
+int hinic3_set_nic_feature_to_hw(struct hinic3_nic_dev *nic_dev)
+{
+	return hinic3_feature_nego(nic_dev->hwdev, MGMT_MSG_CMD_OP_SET,
+				   &nic_dev->nic_io->feature_cap, 1);
+}
+
+bool hinic3_test_support(struct hinic3_nic_dev *nic_dev,
+			 enum hinic3_nic_feature_cap feature_bits)
+{
+	return (nic_dev->nic_io->feature_cap & feature_bits) == feature_bits;
+}
+
+void hinic3_update_nic_feature(struct hinic3_nic_dev *nic_dev, u64 feature_cap)
+{
+	nic_dev->nic_io->feature_cap = feature_cap;
+}
+
+static int hinic3_set_function_table(struct hinic3_hwdev *hwdev, u32 cfg_bitmap,
+				     const struct l2nic_func_tbl_cfg *cfg)
+{
+	struct l2nic_cmd_set_func_tbl cmd_func_tbl = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	cmd_func_tbl.func_id = hinic3_global_func_id(hwdev);
+	cmd_func_tbl.cfg_bitmap = cfg_bitmap;
+	cmd_func_tbl.tbl_cfg = *cfg;
+
+	mgmt_msg_params_init_default(&msg_params, &cmd_func_tbl,
+				     sizeof(cmd_func_tbl));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_FUNC_TBL, &msg_params);
+	if (err || cmd_func_tbl.msg_head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set func table, bitmap: 0x%x, err: %d, status: 0x%x\n",
+			cfg_bitmap, err, cmd_func_tbl.msg_head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic3_set_port_mtu(struct net_device *netdev, u16 new_mtu)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct l2nic_func_tbl_cfg func_tbl_cfg = {};
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+
+	func_tbl_cfg.mtu = new_mtu;
+	return hinic3_set_function_table(hwdev, BIT(L2NIC_FUNC_TBL_CFG_MTU),
+					 &func_tbl_cfg);
+}
+
+static int hinic3_check_mac_info(struct hinic3_hwdev *hwdev, u8 status,
+				 u16 vlan_id)
+{
+	if ((status && status != MGMT_STATUS_EXIST) ||
+	    ((vlan_id & BIT(15)) && status == MGMT_STATUS_EXIST)) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic3_set_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id)
+{
+	struct l2nic_cmd_set_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.mac, mac_addr);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_MAC, &msg_params);
+	if (err || hinic3_check_mac_info(hwdev, mac_info.msg_head.status,
+					 mac_info.vlan_id)) {
+		dev_err(hwdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+
+	if (mac_info.msg_head.status == MGMT_STATUS_PF_SET_VF_ALREADY) {
+		dev_warn(hwdev->dev, "PF has already set VF mac, Ignore set operation\n");
+		return 0;
+	}
+
+	if (mac_info.msg_head.status == MGMT_STATUS_EXIST) {
+		dev_warn(hwdev->dev, "MAC is repeated. Ignore update operation\n");
+		return 0;
+	}
+
+	return 0;
+}
+
+int hinic3_del_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id)
+{
+	struct l2nic_cmd_set_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.mac, mac_addr);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_DEL_MAC, &msg_params);
+	if (err) {
+		dev_err(hwdev->dev,
+			"Failed to delete MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return err;
+	}
+
+	return 0;
+}
+
+int hinic3_update_mac(struct hinic3_hwdev *hwdev, const u8 *old_mac,
+		      u8 *new_mac, u16 vlan_id, u16 func_id)
+{
+	struct l2nic_cmd_update_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.old_mac, old_mac);
+	ether_addr_copy(mac_info.new_mac, new_mac);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_UPDATE_MAC, &msg_params);
+	if (err || hinic3_check_mac_info(hwdev, mac_info.msg_head.status,
+					 mac_info.vlan_id)) {
+		dev_err(hwdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+	return 0;
+}
+
+int hinic3_force_drop_tx_pkt(struct hinic3_hwdev *hwdev)
+{
+	struct l2nic_cmd_force_pkt_drop pkt_drop = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	pkt_drop.port = hinic3_physical_port_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &pkt_drop, sizeof(pkt_drop));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_FORCE_PKT_DROP, &msg_params);
+	if ((pkt_drop.msg_head.status != MGMT_STATUS_CMD_UNSUPPORTED &&
+	     pkt_drop.msg_head.status) || err) {
+		dev_err(hwdev->dev,
+			"Failed to set force tx packets drop, err: %d, status: 0x%x\n",
+			err, pkt_drop.msg_head.status);
+		return -EFAULT;
+	}
+
+	return pkt_drop.msg_head.status;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
new file mode 100644
index 000000000000..bf9ce51dc401
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_CFG_H_
+#define _HINIC3_NIC_CFG_H_
+
+#include <linux/types.h>
+
+#include "hinic3_hw_intf.h"
+#include "hinic3_mgmt_interface.h"
+
+struct hinic3_hwdev;
+struct hinic3_nic_dev;
+
+#define HINIC3_MIN_MTU_SIZE          256
+#define HINIC3_MAX_JUMBO_FRAME_SIZE  9600
+
+#define HINIC3_VLAN_ID_MASK          0x7FFF
+
+enum hinic3_nic_event_type {
+	HINIC3_NIC_EVENT_LINK_DOWN = 0,
+	HINIC3_NIC_EVENT_LINK_UP   = 1,
+};
+
+int hinic3_set_nic_feature_to_hw(struct hinic3_nic_dev *nic_dev);
+bool hinic3_test_support(struct hinic3_nic_dev *nic_dev,
+			 enum hinic3_nic_feature_cap feature_bits);
+void hinic3_update_nic_feature(struct hinic3_nic_dev *nic_dev, u64 feature_cap);
+
+int hinic3_set_port_mtu(struct net_device *netdev, u16 new_mtu);
+
+int hinic3_set_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id);
+int hinic3_del_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id);
+int hinic3_update_mac(struct hinic3_hwdev *hwdev, const u8 *old_mac,
+		      u8 *new_mac, u16 vlan_id, u16 func_id);
+
+int hinic3_force_drop_tx_pkt(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
new file mode 100644
index 000000000000..c994fc9b6ee0
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_DEV_H_
+#define _HINIC3_NIC_DEV_H_
+
+#include <linux/netdevice.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_mgmt_interface.h"
+
+enum hinic3_flags {
+	HINIC3_RSS_ENABLE,
+};
+
+enum hinic3_rss_hash_type {
+	HINIC3_RSS_HASH_ENGINE_TYPE_XOR  = 0,
+	HINIC3_RSS_HASH_ENGINE_TYPE_TOEP = 1,
+};
+
+struct hinic3_rss_type {
+	u8 tcp_ipv6_ext;
+	u8 ipv6_ext;
+	u8 tcp_ipv6;
+	u8 ipv6;
+	u8 tcp_ipv4;
+	u8 ipv4;
+	u8 udp_ipv6;
+	u8 udp_ipv4;
+};
+
+struct hinic3_irq_cfg {
+	struct net_device  *netdev;
+	u16                msix_entry_idx;
+	/* provided by OS */
+	u32                irq_id;
+	char               irq_name[IFNAMSIZ + 16];
+	struct napi_struct napi;
+	cpumask_t          affinity_mask;
+	struct hinic3_txq  *txq;
+	struct hinic3_rxq  *rxq;
+};
+
+struct hinic3_dyna_txrxq_params {
+	u16                        num_qps;
+	u32                        sq_depth;
+	u32                        rq_depth;
+
+	struct hinic3_dyna_txq_res *txqs_res;
+	struct hinic3_dyna_rxq_res *rxqs_res;
+	struct hinic3_irq_cfg      *irq_cfg;
+};
+
+struct hinic3_nic_dev {
+	struct pci_dev                  *pdev;
+	struct net_device               *netdev;
+	struct hinic3_hwdev             *hwdev;
+	struct hinic3_nic_io            *nic_io;
+
+	u16                             max_qps;
+	u16                             rx_buf_len;
+	u32                             lro_replenish_thld;
+	unsigned long                   flags;
+	struct hinic3_nic_service_cap   nic_svc_cap;
+
+	struct hinic3_dyna_txrxq_params q_params;
+	struct hinic3_txq               *txqs;
+	struct hinic3_rxq               *rxqs;
+
+	u16                             num_qp_irq;
+	struct msix_entry               *qps_msix_entries;
+
+	bool                            link_status_up;
+};
+
+void hinic3_set_netdev_ops(struct net_device *netdev);
+
+/* Temporary prototypes. Functions become static in later submission. */
+void qp_add_napi(struct hinic3_irq_cfg *irq_cfg);
+void qp_del_napi(struct hinic3_irq_cfg *irq_cfg);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
new file mode 100644
index 000000000000..34a1f5bd5ac1
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hw_intf.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+
+int hinic3_init_nic_io(struct hinic3_nic_dev *nic_dev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_nic_io(struct hinic3_nic_dev *nic_dev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
new file mode 100644
index 000000000000..865ba6878c48
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_IO_H_
+#define _HINIC3_NIC_IO_H_
+
+#include <linux/bitfield.h>
+
+#include "hinic3_wq.h"
+
+struct hinic3_nic_dev;
+
+#define HINIC3_SQ_WQEBB_SHIFT      4
+#define HINIC3_RQ_WQEBB_SHIFT      3
+#define HINIC3_SQ_WQEBB_SIZE       BIT(HINIC3_SQ_WQEBB_SHIFT)
+
+/* ******************** RQ_CTRL ******************** */
+enum hinic3_rq_wqe_type {
+	HINIC3_NORMAL_RQ_WQE = 1,
+};
+
+/* ******************** SQ_CTRL ******************** */
+#define HINIC3_TX_MSS_DEFAULT  0x3E00
+#define HINIC3_TX_MSS_MIN      0x50
+#define HINIC3_MAX_SQ_SGE      18
+
+struct hinic3_io_queue {
+	struct hinic3_wq  wq;
+	u8                owner;
+	u16               q_id;
+	u16               msix_entry_idx;
+	u8 __iomem        *db_addr;
+	u16               *cons_idx_addr;
+} ____cacheline_aligned;
+
+static inline u16 hinic3_get_sq_local_ci(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return wq->cons_idx & wq->idx_mask;
+}
+
+static inline u16 hinic3_get_sq_local_pi(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return wq->prod_idx & wq->idx_mask;
+}
+
+static inline u16 hinic3_get_sq_hw_ci(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return READ_ONCE(*sq->cons_idx_addr) & wq->idx_mask;
+}
+
+/* ******************** DB INFO ******************** */
+#define DB_INFO_QID_MASK    GENMASK(12, 0)
+#define DB_INFO_CFLAG_MASK  BIT(23)
+#define DB_INFO_COS_MASK    GENMASK(26, 24)
+#define DB_INFO_TYPE_MASK   GENMASK(31, 27)
+#define DB_INFO_SET(val, member)  \
+	FIELD_PREP(DB_INFO_##member##_MASK, val)
+
+#define DB_PI_LOW_MASK   0xFFU
+#define DB_PI_HIGH_MASK  0xFFU
+#define DB_PI_HI_SHIFT   8
+#define DB_PI_LOW(pi)    ((pi) & DB_PI_LOW_MASK)
+#define DB_PI_HIGH(pi)   (((pi) >> DB_PI_HI_SHIFT) & DB_PI_HIGH_MASK)
+#define DB_ADDR(q, pi)   ((u64 __iomem *)((q)->db_addr) + DB_PI_LOW(pi))
+#define DB_SRC_TYPE      1
+
+/* CFLAG_DATA_PATH */
+#define DB_CFLAG_DP_SQ   0
+#define DB_CFLAG_DP_RQ   1
+
+struct hinic3_nic_db {
+	u32 db_info;
+	u32 pi_hi;
+};
+
+static inline void hinic3_write_db(struct hinic3_io_queue *queue, int cos,
+				   u8 cflag, u16 pi)
+{
+	struct hinic3_nic_db db;
+
+	db.db_info = DB_INFO_SET(DB_SRC_TYPE, TYPE) |
+		     DB_INFO_SET(cflag, CFLAG) |
+		     DB_INFO_SET(cos, COS) |
+		     DB_INFO_SET(queue->q_id, QID);
+	db.pi_hi = DB_PI_HIGH(pi);
+
+	writeq(*((u64 *)&db), DB_ADDR(queue, pi));
+}
+
+struct hinic3_nic_io {
+	struct hinic3_io_queue *sq;
+	struct hinic3_io_queue *rq;
+
+	u16                    num_qps;
+	u16                    max_qps;
+
+	/* Base address for consumer index of all tx queues. Each queue is
+	 * given a full cache line to hold its consumer index. HW updates
+	 * current consumer index as it consumes tx WQEs.
+	 */
+	void                   *ci_vaddr_base;
+	dma_addr_t             ci_dma_base;
+
+	u8 __iomem             *sqs_db_addr;
+	u8 __iomem             *rqs_db_addr;
+
+	u16                    rx_buf_len;
+	u64                    feature_cap;
+};
+
+int hinic3_init_nic_io(struct hinic3_nic_dev *nic_dev);
+void hinic3_free_nic_io(struct hinic3_nic_dev *nic_dev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
new file mode 100644
index 000000000000..fab9011de9ad
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/device.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_queue_common.h"
+
+void hinic3_queue_pages_init(struct hinic3_queue_pages *qpages, u32 q_depth,
+			     u32 page_size, u32 elem_size)
+{
+	u32 elem_per_page;
+
+	elem_per_page = min(page_size / elem_size, q_depth);
+
+	qpages->pages = NULL;
+	qpages->page_size = page_size;
+	qpages->num_pages = max(q_depth / elem_per_page, 1);
+	qpages->elem_size_shift = ilog2(elem_size);
+	qpages->elem_per_pg_shift = ilog2(elem_per_page);
+}
+
+static void __queue_pages_free(struct hinic3_hwdev *hwdev,
+			       struct hinic3_queue_pages *qpages, u32 pg_cnt)
+{
+	while (pg_cnt > 0) {
+		pg_cnt--;
+		hinic3_dma_free_coherent_align(hwdev->dev,
+					       qpages->pages + pg_cnt);
+	}
+	kfree(qpages->pages);
+	qpages->pages = NULL;
+}
+
+void hinic3_queue_pages_free(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages)
+{
+	__queue_pages_free(hwdev, qpages, qpages->num_pages);
+}
+
+int hinic3_queue_pages_alloc(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages, u32 align)
+{
+	u32 pg_idx;
+	int err;
+
+	qpages->pages = kcalloc(qpages->num_pages, sizeof(qpages->pages[0]),
+				GFP_KERNEL);
+	if (!qpages->pages)
+		return -ENOMEM;
+
+	if (align == 0)
+		align = qpages->page_size;
+
+	for (pg_idx = 0; pg_idx < qpages->num_pages; pg_idx++) {
+		err = hinic3_dma_zalloc_coherent_align(hwdev->dev,
+						       qpages->page_size,
+						       align,
+						       GFP_KERNEL,
+						       qpages->pages + pg_idx);
+		if (err) {
+			__queue_pages_free(hwdev, qpages, pg_idx);
+			return err;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
new file mode 100644
index 000000000000..ec4cae0a0929
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_QUEUE_COMMON_H_
+#define _HINIC3_QUEUE_COMMON_H_
+
+#include <linux/types.h>
+
+#include "hinic3_common.h"
+
+struct hinic3_hwdev;
+
+struct hinic3_queue_pages {
+	/* Array of DMA-able pages that actually holds the queue entries. */
+	struct hinic3_dma_addr_align  *pages;
+	/* Page size in bytes. */
+	u32                           page_size;
+	/* Number of pages, must be power of 2. */
+	u16                           num_pages;
+	u8                            elem_size_shift;
+	u8                            elem_per_pg_shift;
+};
+
+void hinic3_queue_pages_init(struct hinic3_queue_pages *qpages, u32 q_depth,
+			     u32 page_size, u32 elem_size);
+int hinic3_queue_pages_alloc(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages, u32 align);
+void hinic3_queue_pages_free(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages);
+
+/* Get pointer to queue entry at the specified index. Index does not have to be
+ * masked to queue depth, only least significant bits will be used. Also
+ * provides remaining elements in same page (including the first one) in case
+ * caller needs multiple entries.
+ */
+static inline void *get_q_element(const struct hinic3_queue_pages *qpages,
+				  u32 idx, u32 *remaining_in_page)
+{
+	const struct hinic3_dma_addr_align *page;
+	u32 page_idx, elem_idx, elem_per_pg, ofs;
+	u8 shift;
+
+	shift = qpages->elem_per_pg_shift;
+	page_idx = (idx >> shift) & (qpages->num_pages - 1);
+	elem_per_pg = 1 << shift;
+	elem_idx = idx & (elem_per_pg - 1);
+	if (remaining_in_page)
+		*remaining_in_page = elem_per_pg - elem_idx;
+	ofs = elem_idx << qpages->elem_size_shift;
+	page = qpages->pages + page_idx;
+	return (char *)page->align_vaddr + ofs;
+}
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
new file mode 100644
index 000000000000..860163e9d66c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
+#include <net/gro.h>
+#include <net/page_pool/helpers.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+
+#define HINIC3_RX_HDR_SIZE              256
+#define HINIC3_RX_BUFFER_WRITE          16
+
+#define HINIC3_RX_TCP_PKT               0x3
+#define HINIC3_RX_UDP_PKT               0x4
+#define HINIC3_RX_SCTP_PKT              0x7
+
+#define HINIC3_RX_IPV4_PKT              0
+#define HINIC3_RX_IPV6_PKT              1
+#define HINIC3_RX_INVALID_IP_TYPE       2
+
+#define HINIC3_RX_PKT_FORMAT_NON_TUNNEL 0
+#define HINIC3_RX_PKT_FORMAT_VXLAN      1
+
+#define HINIC3_LRO_PKT_HDR_LEN_IPV4     66
+#define HINIC3_LRO_PKT_HDR_LEN_IPV6     86
+#define HINIC3_LRO_PKT_HDR_LEN(cqe) \
+	(RQ_CQE_OFFOLAD_TYPE_GET((cqe)->offload_type, IP_TYPE) == \
+	 HINIC3_RX_IPV6_PKT ? HINIC3_LRO_PKT_HDR_LEN_IPV6 : \
+	 HINIC3_LRO_PKT_HDR_LEN_IPV4)
+
+int hinic3_alloc_rxqs(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_rxqs(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+static int rx_alloc_mapped_page(struct page_pool *page_pool,
+				struct hinic3_rx_info *rx_info, u16 buf_len)
+{
+	struct page *page;
+	u32 page_offset;
+
+	page = page_pool_dev_alloc_frag(page_pool, &page_offset, buf_len);
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	rx_info->page = page;
+	rx_info->page_offset = page_offset;
+
+	return 0;
+}
+
+static void rq_wqe_buf_set(struct hinic3_io_queue *rq, uint32_t wqe_idx,
+			   dma_addr_t dma_addr, u16 len)
+{
+	struct hinic3_rq_wqe *rq_wqe;
+
+	rq_wqe = get_q_element(&rq->wq.qpages, wqe_idx, NULL);
+	rq_wqe->buf_hi_addr = upper_32_bits(dma_addr);
+	rq_wqe->buf_lo_addr = lower_32_bits(dma_addr);
+}
+
+static u32 hinic3_rx_fill_buffers(struct hinic3_rxq *rxq)
+{
+	u32 i, free_wqebbs = rxq->delta - 1;
+	struct hinic3_rx_info *rx_info;
+	dma_addr_t dma_addr;
+	int err;
+
+	for (i = 0; i < free_wqebbs; i++) {
+		rx_info = &rxq->rx_info[rxq->next_to_update];
+
+		err = rx_alloc_mapped_page(rxq->page_pool, rx_info,
+					   rxq->buf_len);
+		if (unlikely(err))
+			break;
+
+		dma_addr = page_pool_get_dma_addr(rx_info->page) +
+			rx_info->page_offset;
+		rq_wqe_buf_set(rxq->rq, rxq->next_to_update, dma_addr,
+			       rxq->buf_len);
+		rxq->next_to_update = (rxq->next_to_update + 1) & rxq->q_mask;
+	}
+
+	if (likely(i)) {
+		hinic3_write_db(rxq->rq, rxq->q_id & 3, DB_CFLAG_DP_RQ,
+				rxq->next_to_update << HINIC3_NORMAL_RQ_WQE);
+		rxq->delta -= i;
+		rxq->next_to_alloc = rxq->next_to_update;
+	}
+
+	return i;
+}
+
+static void hinic3_add_rx_frag(struct hinic3_rxq *rxq,
+			       struct hinic3_rx_info *rx_info,
+			       struct sk_buff *skb, u32 size)
+{
+	struct page *page;
+	u8 *va;
+
+	page = rx_info->page;
+	va = (u8 *)page_address(page) + rx_info->page_offset;
+	net_prefetch(va);
+
+	page_pool_dma_sync_for_cpu(rxq->page_pool, page, rx_info->page_offset,
+				   rxq->buf_len);
+
+	if (size <= HINIC3_RX_HDR_SIZE && !skb_is_nonlinear(skb)) {
+		memcpy(__skb_put(skb, size), va,
+		       ALIGN(size, sizeof(long)));
+		page_pool_put_full_page(rxq->page_pool, page, false);
+
+		return;
+	}
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+			rx_info->page_offset, size, rxq->buf_len);
+	skb_mark_for_recycle(skb);
+}
+
+static void packaging_skb(struct hinic3_rxq *rxq, struct sk_buff *skb,
+			  u32 sge_num, u32 pkt_len)
+{
+	struct hinic3_rx_info *rx_info;
+	u32 temp_pkt_len = pkt_len;
+	u32 temp_sge_num = sge_num;
+	u32 sw_ci;
+	u32 size;
+
+	sw_ci = rxq->cons_idx & rxq->q_mask;
+	while (temp_sge_num) {
+		rx_info = &rxq->rx_info[sw_ci];
+		sw_ci = (sw_ci + 1) & rxq->q_mask;
+		if (unlikely(temp_pkt_len > rxq->buf_len)) {
+			size = rxq->buf_len;
+			temp_pkt_len -= rxq->buf_len;
+		} else {
+			size = temp_pkt_len;
+		}
+
+		hinic3_add_rx_frag(rxq, rx_info, skb, size);
+
+		/* clear contents of buffer_info */
+		rx_info->page = NULL;
+		temp_sge_num--;
+	}
+}
+
+static u32 hinic3_get_sge_num(struct hinic3_rxq *rxq, u32 pkt_len)
+{
+	u32 sge_num;
+
+	sge_num = pkt_len >> rxq->buf_len_shift;
+	sge_num += (pkt_len & (rxq->buf_len - 1)) ? 1 : 0;
+
+	return sge_num;
+}
+
+static struct sk_buff *hinic3_fetch_rx_buffer(struct hinic3_rxq *rxq,
+					      u32 pkt_len)
+{
+	struct sk_buff *skb;
+	u32 sge_num;
+
+	skb = napi_alloc_skb(&rxq->irq_cfg->napi, HINIC3_RX_HDR_SIZE);
+	if (unlikely(!skb))
+		return NULL;
+
+	sge_num = hinic3_get_sge_num(rxq, pkt_len);
+
+	net_prefetchw(skb->data);
+	packaging_skb(rxq, skb, sge_num, pkt_len);
+
+	rxq->cons_idx += sge_num;
+	rxq->delta += sge_num;
+
+	return skb;
+}
+
+static void hinic3_pull_tail(struct sk_buff *skb)
+{
+	skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
+	unsigned int pull_len;
+	unsigned char *va;
+
+	va = skb_frag_address(frag);
+
+	/* we need the header to contain the greater of either ETH_HLEN or
+	 * 60 bytes if the skb->len is less than 60 for skb_pad.
+	 */
+	pull_len = eth_get_headlen(skb->dev, va, HINIC3_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	skb_frag_size_sub(frag, pull_len);
+	skb_frag_off_add(frag, pull_len);
+
+	skb->data_len -= pull_len;
+	skb->tail += pull_len;
+}
+
+static void hinic3_rx_csum(struct hinic3_rxq *rxq, u32 offload_type,
+			   u32 status, struct sk_buff *skb)
+{
+	u32 pkt_fmt = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, TUNNEL_PKT_FORMAT);
+	u32 pkt_type = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, PKT_TYPE);
+	u32 ip_type = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, IP_TYPE);
+	u32 csum_err = RQ_CQE_STATUS_GET(status, CSUM_ERR);
+	struct net_device *netdev = rxq->netdev;
+
+	if (!(netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (unlikely(csum_err)) {
+		/* pkt type is recognized by HW, and csum is wrong */
+		skb->ip_summed = CHECKSUM_NONE;
+		return;
+	}
+
+	if (ip_type == HINIC3_RX_INVALID_IP_TYPE ||
+	    !(pkt_fmt == HINIC3_RX_PKT_FORMAT_NON_TUNNEL ||
+	      pkt_fmt == HINIC3_RX_PKT_FORMAT_VXLAN)) {
+		skb->ip_summed = CHECKSUM_NONE;
+		return;
+	}
+
+	switch (pkt_type) {
+	case HINIC3_RX_TCP_PKT:
+	case HINIC3_RX_UDP_PKT:
+	case HINIC3_RX_SCTP_PKT:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		break;
+	default:
+		skb->ip_summed = CHECKSUM_NONE;
+		break;
+	}
+}
+
+static void hinic3_lro_set_gso_params(struct sk_buff *skb, u16 num_lro)
+{
+	struct ethhdr *eth = (struct ethhdr *)(skb->data);
+	__be16 proto;
+
+	proto = __vlan_get_protocol(skb, eth->h_proto, NULL);
+
+	skb_shinfo(skb)->gso_size = DIV_ROUND_UP(skb->len - skb_headlen(skb),
+						 num_lro);
+	skb_shinfo(skb)->gso_type = proto == htons(ETH_P_IP) ?
+				    SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+	skb_shinfo(skb)->gso_segs = num_lro;
+}
+
+static int recv_one_pkt(struct hinic3_rxq *rxq, struct hinic3_rq_cqe *rx_cqe,
+			u32 pkt_len, u32 vlan_len, u32 status)
+{
+	struct net_device *netdev = rxq->netdev;
+	struct sk_buff *skb;
+	u32 offload_type;
+	u16 num_lro;
+
+	skb = hinic3_fetch_rx_buffer(rxq, pkt_len);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	/* place header in linear portion of buffer */
+	if (skb_is_nonlinear(skb))
+		hinic3_pull_tail(skb);
+
+	offload_type = rx_cqe->offload_type;
+	hinic3_rx_csum(rxq, offload_type, status, skb);
+
+	num_lro = RQ_CQE_STATUS_GET(status, NUM_LRO);
+	if (num_lro)
+		hinic3_lro_set_gso_params(skb, num_lro);
+
+	skb_record_rx_queue(skb, rxq->q_id);
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	if (skb_has_frag_list(skb)) {
+		napi_gro_flush(&rxq->irq_cfg->napi, false);
+		netif_receive_skb(skb);
+	} else {
+		napi_gro_receive(&rxq->irq_cfg->napi, skb);
+	}
+
+	return 0;
+}
+
+int hinic3_rx_poll(struct hinic3_rxq *rxq, int budget)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(rxq->netdev);
+	u32 sw_ci, status, pkt_len, vlan_len;
+	struct hinic3_rq_cqe *rx_cqe;
+	u32 num_wqe = 0;
+	int nr_pkts = 0;
+	u16 num_lro;
+
+	while (likely(nr_pkts < budget)) {
+		sw_ci = rxq->cons_idx & rxq->q_mask;
+		rx_cqe = rxq->cqe_arr + sw_ci;
+		status = rx_cqe->status;
+		if (!RQ_CQE_STATUS_GET(status, RXDONE))
+			break;
+
+		/* make sure we read rx_done before packet length */
+		rmb();
+
+		vlan_len = rx_cqe->vlan_len;
+		pkt_len = RQ_CQE_SGE_GET(vlan_len, LEN);
+		if (recv_one_pkt(rxq, rx_cqe, pkt_len, vlan_len, status))
+			break;
+
+		nr_pkts++;
+		num_lro = RQ_CQE_STATUS_GET(status, NUM_LRO);
+		if (num_lro)
+			num_wqe += hinic3_get_sge_num(rxq, pkt_len);
+
+		rx_cqe->status = 0;
+
+		if (num_wqe >= nic_dev->lro_replenish_thld)
+			break;
+	}
+
+	if (rxq->delta >= HINIC3_RX_BUFFER_WRITE)
+		hinic3_rx_fill_buffers(rxq);
+
+	return nr_pkts;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
new file mode 100644
index 000000000000..1cca21858d40
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_RX_H_
+#define _HINIC3_RX_H_
+
+#include <linux/bitfield.h>
+#include <linux/netdevice.h>
+
+#define RQ_CQE_OFFOLAD_TYPE_PKT_TYPE_MASK           GENMASK(4, 0)
+#define RQ_CQE_OFFOLAD_TYPE_IP_TYPE_MASK            GENMASK(6, 5)
+#define RQ_CQE_OFFOLAD_TYPE_TUNNEL_PKT_FORMAT_MASK  GENMASK(11, 8)
+#define RQ_CQE_OFFOLAD_TYPE_VLAN_EN_MASK            BIT(21)
+#define RQ_CQE_OFFOLAD_TYPE_GET(val, member) \
+	FIELD_GET(RQ_CQE_OFFOLAD_TYPE_##member##_MASK, val)
+
+#define RQ_CQE_SGE_VLAN_MASK  GENMASK(15, 0)
+#define RQ_CQE_SGE_LEN_MASK   GENMASK(31, 16)
+#define RQ_CQE_SGE_GET(val, member) \
+	FIELD_GET(RQ_CQE_SGE_##member##_MASK, val)
+
+#define RQ_CQE_STATUS_CSUM_ERR_MASK  GENMASK(15, 0)
+#define RQ_CQE_STATUS_NUM_LRO_MASK   GENMASK(23, 16)
+#define RQ_CQE_STATUS_RXDONE_MASK    BIT(31)
+#define RQ_CQE_STATUS_GET(val, member) \
+	FIELD_GET(RQ_CQE_STATUS_##member##_MASK, val)
+
+/* RX Completion information that is provided by HW for a specific RX WQE */
+struct hinic3_rq_cqe {
+	u32 status;
+	u32 vlan_len;
+	u32 offload_type;
+	u32 rsvd3;
+	u32 rsvd4;
+	u32 rsvd5;
+	u32 rsvd6;
+	u32 pkt_info;
+};
+
+struct hinic3_rq_wqe {
+	u32 buf_hi_addr;
+	u32 buf_lo_addr;
+	u32 cqe_hi_addr;
+	u32 cqe_lo_addr;
+};
+
+struct hinic3_rx_info {
+	struct page      *page;
+	u32              page_offset;
+};
+
+struct hinic3_rxq {
+	struct net_device       *netdev;
+
+	u16                     q_id;
+	u32                     q_depth;
+	u32                     q_mask;
+
+	u16                     buf_len;
+	u32                     buf_len_shift;
+
+	u32                     cons_idx;
+	u32                     delta;
+
+	u32                     irq_id;
+	u16                     msix_entry_idx;
+
+	/* cqe_arr and rx_info are arrays of rq_depth elements. Each element is
+	 * statically associated (by index) to a specific rq_wqe.
+	 */
+	struct hinic3_rq_cqe   *cqe_arr;
+	struct hinic3_rx_info  *rx_info;
+	struct page_pool       *page_pool;
+
+	struct hinic3_io_queue *rq;
+
+	struct hinic3_irq_cfg  *irq_cfg;
+	u16                    next_to_alloc;
+	u16                    next_to_update;
+	struct device          *dev; /* device for DMA mapping */
+
+	dma_addr_t             cqe_start_paddr;
+} ____cacheline_aligned;
+
+int hinic3_alloc_rxqs(struct net_device *netdev);
+void hinic3_free_rxqs(struct net_device *netdev);
+
+int hinic3_rx_poll(struct hinic3_rxq *rxq, int budget);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
new file mode 100644
index 000000000000..ae08257dd1d2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
@@ -0,0 +1,670 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/if_vlan.h>
+#include <linux/iopoll.h>
+#include <net/ip6_checksum.h>
+#include <net/ipv6.h>
+#include <net/netdev_queues.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_tx.h"
+#include "hinic3_wq.h"
+
+#define MIN_SKB_LEN                32
+
+int hinic3_alloc_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	u16 q_id, num_txqs = nic_dev->max_qps;
+	struct pci_dev *pdev = nic_dev->pdev;
+	struct hinic3_txq *txq;
+
+	if (!num_txqs) {
+		dev_err(hwdev->dev, "Cannot allocate zero size txqs\n");
+		return -EINVAL;
+	}
+
+	nic_dev->txqs = kcalloc(num_txqs, sizeof(*nic_dev->txqs),  GFP_KERNEL);
+	if (!nic_dev->txqs)
+		return -ENOMEM;
+
+	for (q_id = 0; q_id < num_txqs; q_id++) {
+		txq = &nic_dev->txqs[q_id];
+		txq->netdev = netdev;
+		txq->q_id = q_id;
+		txq->q_depth = nic_dev->q_params.sq_depth;
+		txq->q_mask = nic_dev->q_params.sq_depth - 1;
+		txq->dev = &pdev->dev;
+	}
+
+	return 0;
+}
+
+void hinic3_free_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	kfree(nic_dev->txqs);
+}
+
+static void hinic3_set_buf_desc(struct hinic3_sq_bufdesc *buf_descs,
+				dma_addr_t addr, u32 len)
+{
+	buf_descs->hi_addr = upper_32_bits(addr);
+	buf_descs->lo_addr = lower_32_bits(addr);
+	buf_descs->len  = len;
+}
+
+static int hinic3_tx_map_skb(struct net_device *netdev, struct sk_buff *skb,
+			     struct hinic3_txq *txq,
+			     struct hinic3_tx_info *tx_info,
+			     struct hinic3_sq_wqe_combo *wqe_combo)
+{
+	struct hinic3_sq_wqe_desc *wqe_desc = wqe_combo->ctrl_bd0;
+	struct hinic3_sq_bufdesc *buf_desc = wqe_combo->bds_head;
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dma_info *dma_info = tx_info->dma_info;
+	struct pci_dev *pdev = nic_dev->pdev;
+	skb_frag_t *frag;
+	u32 i, idx;
+	int err;
+
+	dma_info[0].dma = dma_map_single(&pdev->dev, skb->data,
+					 skb_headlen(skb), DMA_TO_DEVICE);
+	if (dma_mapping_error(&pdev->dev, dma_info[0].dma))
+		return -EFAULT;
+
+	dma_info[0].len = skb_headlen(skb);
+
+	wqe_desc->hi_addr = upper_32_bits(dma_info[0].dma);
+	wqe_desc->lo_addr = lower_32_bits(dma_info[0].dma);
+
+	wqe_desc->ctrl_len = dma_info[0].len;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		frag = &(skb_shinfo(skb)->frags[i]);
+		if (unlikely(i == wqe_combo->first_bds_num))
+			buf_desc = wqe_combo->bds_sec2;
+
+		idx = i + 1;
+		dma_info[idx].dma = skb_frag_dma_map(&pdev->dev, frag, 0,
+						     skb_frag_size(frag),
+						     DMA_TO_DEVICE);
+		if (dma_mapping_error(&pdev->dev, dma_info[idx].dma)) {
+			err = -EFAULT;
+			goto err_unmap_page;
+		}
+		dma_info[idx].len = skb_frag_size(frag);
+
+		hinic3_set_buf_desc(buf_desc, dma_info[idx].dma,
+				    dma_info[idx].len);
+		buf_desc++;
+	}
+
+	return 0;
+
+err_unmap_page:
+	while (idx > 1) {
+		idx--;
+		dma_unmap_page(&pdev->dev, dma_info[idx].dma,
+			       dma_info[idx].len, DMA_TO_DEVICE);
+	}
+	dma_unmap_single(&pdev->dev, dma_info[0].dma, dma_info[0].len,
+			 DMA_TO_DEVICE);
+	return err;
+}
+
+static void hinic3_tx_unmap_skb(struct net_device *netdev,
+				struct sk_buff *skb,
+				struct hinic3_dma_info *dma_info)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = nic_dev->pdev;
+	int i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags;) {
+		i++;
+		dma_unmap_page(&pdev->dev,
+			       dma_info[i].dma,
+			       dma_info[i].len, DMA_TO_DEVICE);
+	}
+
+	dma_unmap_single(&pdev->dev, dma_info[0].dma,
+			 dma_info[0].len, DMA_TO_DEVICE);
+}
+
+union hinic3_ip {
+	struct iphdr   *v4;
+	struct ipv6hdr *v6;
+	unsigned char  *hdr;
+};
+
+union hinic3_l4 {
+	struct tcphdr *tcp;
+	struct udphdr *udp;
+	unsigned char *hdr;
+};
+
+enum hinic3_l3_type {
+	HINIC3_L3_UNKNOWN         = 0,
+	HINIC3_L3_IP6_PKT         = 1,
+	HINIC3_L3_IP4_PKT_NO_CSUM = 2,
+	HINIC3_L3_IP4_PKT_CSUM    = 3,
+};
+
+enum hinic3_l4_offload_type {
+	HINIC3_L4_OFFLOAD_DISABLE = 0,
+	HINIC3_L4_OFFLOAD_TCP     = 1,
+	HINIC3_L4_OFFLOAD_STCP    = 2,
+	HINIC3_L4_OFFLOAD_UDP     = 3,
+};
+
+/* initialize l4 offset and offload */
+static void get_inner_l4_info(struct sk_buff *skb, union hinic3_l4 *l4,
+			      u8 l4_proto, u32 *offset,
+			      enum hinic3_l4_offload_type *l4_offload)
+{
+	switch (l4_proto) {
+	case IPPROTO_TCP:
+		*l4_offload = HINIC3_L4_OFFLOAD_TCP;
+		/* To be same with TSO, payload offset begins from payload */
+		*offset = (l4->tcp->doff << TCP_HDR_DATA_OFF_UNIT_SHIFT) +
+			   TRANSPORT_OFFSET(l4->hdr, skb);
+		break;
+
+	case IPPROTO_UDP:
+		*l4_offload = HINIC3_L4_OFFLOAD_UDP;
+		*offset = TRANSPORT_OFFSET(l4->hdr, skb);
+		break;
+	default:
+		*l4_offload = HINIC3_L4_OFFLOAD_DISABLE;
+		*offset = 0;
+	}
+}
+
+static int hinic3_tx_csum(struct hinic3_txq *txq, struct hinic3_sq_task *task,
+			  struct sk_buff *skb)
+{
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (skb->encapsulation) {
+		union hinic3_ip ip;
+		u8 l4_proto;
+
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, TUNNEL_FLAG);
+
+		ip.hdr = skb_network_header(skb);
+		if (ip.v4->version == 4) {
+			l4_proto = ip.v4->protocol;
+		} else if (ip.v4->version == 6) {
+			union hinic3_l4 l4;
+			unsigned char *exthdr;
+			__be16 frag_off;
+
+			exthdr = ip.hdr + sizeof(*ip.v6);
+			l4_proto = ip.v6->nexthdr;
+			l4.hdr = skb_transport_header(skb);
+			if (l4.hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data,
+						 &l4_proto, &frag_off);
+		} else {
+			l4_proto = IPPROTO_RAW;
+		}
+
+		if (l4_proto != IPPROTO_UDP ||
+		    ((struct udphdr *)skb_transport_header(skb))->dest !=
+		    VXLAN_OFFLOAD_PORT_LE) {
+			/* Unsupported tunnel packet, disable csum offload */
+			skb_checksum_help(skb);
+			return 0;
+		}
+	}
+
+	task->pkt_info0 |= SQ_TASK_INFO0_SET(1, INNER_L4_EN);
+
+	return 1;
+}
+
+static void get_inner_l3_l4_type(struct sk_buff *skb, union hinic3_ip *ip,
+				 union hinic3_l4 *l4,
+				 enum hinic3_l3_type *l3_type, u8 *l4_proto)
+{
+	unsigned char *exthdr;
+	__be16 frag_off;
+
+	if (ip->v4->version == 4) {
+		*l3_type = HINIC3_L3_IP4_PKT_CSUM;
+		*l4_proto = ip->v4->protocol;
+	} else if (ip->v4->version == 6) {
+		*l3_type = HINIC3_L3_IP6_PKT;
+		exthdr = ip->hdr + sizeof(*ip->v6);
+		*l4_proto = ip->v6->nexthdr;
+		if (exthdr != l4->hdr) {
+			ipv6_skip_exthdr(skb, exthdr - skb->data,
+					 l4_proto, &frag_off);
+		}
+	} else {
+		*l3_type = HINIC3_L3_UNKNOWN;
+		*l4_proto = 0;
+	}
+}
+
+static void hinic3_set_tso_info(struct hinic3_sq_task *task, u32 *queue_info,
+				enum hinic3_l4_offload_type l4_offload,
+				u32 offset, u32 mss)
+{
+	if (l4_offload == HINIC3_L4_OFFLOAD_TCP) {
+		*queue_info |= SQ_CTRL_QUEUE_INFO_SET(1, TSO);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, INNER_L4_EN);
+	} else if (l4_offload == HINIC3_L4_OFFLOAD_UDP) {
+		*queue_info |= SQ_CTRL_QUEUE_INFO_SET(1, UFO);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, INNER_L4_EN);
+	}
+
+	/* enable L3 calculation */
+	task->pkt_info0 |= SQ_TASK_INFO0_SET(1, INNER_L3_EN);
+
+	*queue_info |= SQ_CTRL_QUEUE_INFO_SET(offset >> 1, PLDOFF);
+
+	/* set MSS value */
+	*queue_info &= ~SQ_CTRL_QUEUE_INFO_MSS_MASK;
+	*queue_info |= SQ_CTRL_QUEUE_INFO_SET(mss, MSS);
+}
+
+static __sum16 csum_magic(union hinic3_ip *ip, unsigned short proto)
+{
+	return (ip->v4->version == 4) ?
+		csum_tcpudp_magic(ip->v4->saddr, ip->v4->daddr, 0, proto, 0) :
+		csum_ipv6_magic(&ip->v6->saddr, &ip->v6->daddr, 0, proto, 0);
+}
+
+static int hinic3_tso(struct hinic3_sq_task *task, u32 *queue_info,
+		      struct sk_buff *skb)
+{
+	enum hinic3_l4_offload_type l4_offload;
+	enum hinic3_l3_type l3_type;
+	union hinic3_ip ip;
+	union hinic3_l4 l4;
+	u8 l4_proto;
+	u32 offset;
+	int err;
+
+	if (!skb_is_gso(skb))
+		return 0;
+
+	err = skb_cow_head(skb, 0);
+	if (err < 0)
+		return err;
+
+	if (skb->encapsulation) {
+		u32 gso_type = skb_shinfo(skb)->gso_type;
+		/* L3 checksum is always enabled */
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, OUT_L3_EN);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, TUNNEL_FLAG);
+
+		l4.hdr = skb_transport_header(skb);
+		ip.hdr = skb_network_header(skb);
+
+		if (gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			l4.udp->check = ~csum_magic(&ip, IPPROTO_UDP);
+			task->pkt_info0 |= SQ_TASK_INFO0_SET(1, OUT_L4_EN);
+		}
+
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
+	} else {
+		ip.hdr = skb_network_header(skb);
+		l4.hdr = skb_transport_header(skb);
+	}
+
+	get_inner_l3_l4_type(skb, &ip, &l4, &l3_type, &l4_proto);
+
+	if (l4_proto == IPPROTO_TCP)
+		l4.tcp->check = ~csum_magic(&ip, IPPROTO_TCP);
+
+	get_inner_l4_info(skb, &l4, l4_proto, &offset, &l4_offload);
+
+	hinic3_set_tso_info(task, queue_info, l4_offload, offset,
+			    skb_shinfo(skb)->gso_size);
+
+	return 1;
+}
+
+static void hinic3_set_vlan_tx_offload(struct hinic3_sq_task *task,
+				       u16 vlan_tag, u8 vlan_tpid)
+{
+	/* vlan_tpid: 0=select TPID0 in IPSU, 1=select TPID1 in IPSU
+	 * 2=select TPID2 in IPSU, 3=select TPID3 in IPSU,
+	 * 4=select TPID4 in IPSU
+	 */
+	task->vlan_offload = SQ_TASK_INFO3_SET(vlan_tag, VLAN_TAG) |
+			     SQ_TASK_INFO3_SET(vlan_tpid, VLAN_TPID) |
+			     SQ_TASK_INFO3_SET(1, VLAN_TAG_VALID);
+}
+
+static u32 hinic3_tx_offload(struct sk_buff *skb, struct hinic3_sq_task *task,
+			     u32 *queue_info, struct hinic3_txq *txq)
+{
+	u32 offload = 0;
+	int tso_cs_en;
+
+	task->pkt_info0 = 0;
+	task->ip_identify = 0;
+	task->rsvd = 0;
+	task->vlan_offload = 0;
+
+	tso_cs_en = hinic3_tso(task, queue_info, skb);
+	if (tso_cs_en < 0) {
+		offload = HINIC3_TX_OFFLOAD_INVALID;
+		return offload;
+	} else if (tso_cs_en) {
+		offload |= HINIC3_TX_OFFLOAD_TSO;
+	} else {
+		tso_cs_en = hinic3_tx_csum(txq, task, skb);
+		if (tso_cs_en)
+			offload |= HINIC3_TX_OFFLOAD_CSUM;
+	}
+
+#define VLAN_INSERT_MODE_MAX 5
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		/* select vlan insert mode by qid, default 802.1Q Tag type */
+		hinic3_set_vlan_tx_offload(task, skb_vlan_tag_get(skb),
+					   txq->q_id % VLAN_INSERT_MODE_MAX);
+		offload |= HINIC3_TX_OFFLOAD_VLAN;
+	}
+
+	if (unlikely(SQ_CTRL_QUEUE_INFO_GET(*queue_info, PLDOFF) >
+		     SQ_CTRL_MAX_PLDOFF)) {
+		offload = HINIC3_TX_OFFLOAD_INVALID;
+		return offload;
+	}
+
+	return offload;
+}
+
+static u16 hinic3_get_and_update_sq_owner(struct hinic3_io_queue *sq,
+					  u16 curr_pi, u16 wqebb_cnt)
+{
+	u16 owner = sq->owner;
+
+	if (unlikely(curr_pi + wqebb_cnt >= sq->wq.q_depth))
+		sq->owner = !sq->owner;
+
+	return owner;
+}
+
+static u16 hinic3_set_wqe_combo(struct hinic3_txq *txq,
+				struct hinic3_sq_wqe_combo *wqe_combo,
+				u32 offload, u16 num_sge, u16 *curr_pi)
+{
+	struct hinic3_sq_bufdesc *first_part_wqebbs, *second_part_wqebbs;
+	u16 first_part_wqebbs_num, tmp_pi;
+
+	wqe_combo->ctrl_bd0 = hinic3_wq_get_one_wqebb(&txq->sq->wq, curr_pi);
+	if (!offload && num_sge == 1) {
+		wqe_combo->wqe_type = SQ_WQE_COMPACT_TYPE;
+		return hinic3_get_and_update_sq_owner(txq->sq, *curr_pi, 1);
+	}
+
+	wqe_combo->wqe_type = SQ_WQE_EXTENDED_TYPE;
+
+	if (offload) {
+		wqe_combo->task = hinic3_wq_get_one_wqebb(&txq->sq->wq,
+							  &tmp_pi);
+		wqe_combo->task_type = SQ_WQE_TASKSECT_16BYTES;
+	} else {
+		wqe_combo->task_type = SQ_WQE_TASKSECT_46BITS;
+	}
+
+	if (num_sge > 1) {
+		/* first wqebb contain bd0, and bd size is equal to sq wqebb
+		 * size, so we use (num_sge - 1) as wanted weqbb_cnt
+		 */
+		hinic3_wq_get_multi_wqebbs(&txq->sq->wq, num_sge - 1, &tmp_pi,
+					   &first_part_wqebbs,
+					   &second_part_wqebbs,
+					   &first_part_wqebbs_num);
+		wqe_combo->bds_head = first_part_wqebbs;
+		wqe_combo->bds_sec2 = second_part_wqebbs;
+		wqe_combo->first_bds_num = first_part_wqebbs_num;
+	}
+
+	return hinic3_get_and_update_sq_owner(txq->sq, *curr_pi,
+					      num_sge + !!offload);
+}
+
+static void hinic3_prepare_sq_ctrl(struct hinic3_sq_wqe_combo *wqe_combo,
+				   u32 queue_info, int nr_descs, u16 owner)
+{
+	struct hinic3_sq_wqe_desc *wqe_desc = wqe_combo->ctrl_bd0;
+
+	if (wqe_combo->wqe_type == SQ_WQE_COMPACT_TYPE) {
+		wqe_desc->ctrl_len |=
+		    SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) |
+		    SQ_CTRL_SET(wqe_combo->wqe_type, EXTENDED) |
+		    SQ_CTRL_SET(owner, OWNER);
+
+		/* compact wqe queue_info will transfer to chip */
+		wqe_desc->queue_info = 0;
+		return;
+	}
+
+	wqe_desc->ctrl_len |= SQ_CTRL_SET(nr_descs, BUFDESC_NUM) |
+			      SQ_CTRL_SET(wqe_combo->task_type, TASKSECT_LEN) |
+			      SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) |
+			      SQ_CTRL_SET(wqe_combo->wqe_type, EXTENDED) |
+			      SQ_CTRL_SET(owner, OWNER);
+
+	wqe_desc->queue_info = queue_info;
+	wqe_desc->queue_info |= SQ_CTRL_QUEUE_INFO_SET(1, UC);
+
+	if (!SQ_CTRL_QUEUE_INFO_GET(wqe_desc->queue_info, MSS)) {
+		wqe_desc->queue_info |=
+		    SQ_CTRL_QUEUE_INFO_SET(HINIC3_TX_MSS_DEFAULT, MSS);
+	} else if (SQ_CTRL_QUEUE_INFO_GET(wqe_desc->queue_info, MSS) <
+		   HINIC3_TX_MSS_MIN) {
+		/* mss should not be less than 80 */
+		wqe_desc->queue_info &= ~SQ_CTRL_QUEUE_INFO_MSS_MASK;
+		wqe_desc->queue_info |=
+		    SQ_CTRL_QUEUE_INFO_SET(HINIC3_TX_MSS_MIN, MSS);
+	}
+}
+
+static netdev_tx_t hinic3_send_one_skb(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       struct hinic3_txq *txq)
+{
+	struct hinic3_sq_wqe_combo wqe_combo = {};
+	struct hinic3_tx_info *tx_info;
+	struct hinic3_txq *tx_q = txq;
+	u32 offload, queue_info = 0;
+	struct hinic3_sq_task task;
+	u16 wqebb_cnt, num_sge;
+	u16 saved_wq_prod_idx;
+	u16 owner, pi = 0;
+	u8 saved_sq_owner;
+	int err;
+
+	if (unlikely(skb->len < MIN_SKB_LEN)) {
+		if (skb_pad(skb, MIN_SKB_LEN - skb->len))
+			goto err_out;
+
+		skb->len = MIN_SKB_LEN;
+	}
+
+	num_sge = skb_shinfo(skb)->nr_frags + 1;
+	/* assume normal wqe format + 1 wqebb for task info */
+	wqebb_cnt = num_sge + 1;
+
+	if (unlikely(hinic3_wq_free_wqebbs(&txq->sq->wq) < wqebb_cnt)) {
+		if (likely(wqebb_cnt > txq->tx_stop_thrs))
+			txq->tx_stop_thrs = min(wqebb_cnt, txq->tx_start_thrs);
+
+		netif_subqueue_try_stop(netdev, tx_q->sq->q_id,
+					hinic3_wq_free_wqebbs(&tx_q->sq->wq),
+					tx_q->tx_start_thrs);
+
+		return NETDEV_TX_BUSY;
+	}
+
+	offload = hinic3_tx_offload(skb, &task, &queue_info, txq);
+	if (unlikely(offload == HINIC3_TX_OFFLOAD_INVALID)) {
+		goto err_drop_pkt;
+	} else if (!offload) {
+		wqebb_cnt -= 1;
+		if (unlikely(num_sge == 1 &&
+			     skb->len > HINIC3_COMPACT_WQEE_SKB_MAX_LEN))
+			goto err_drop_pkt;
+	}
+
+	saved_wq_prod_idx = txq->sq->wq.prod_idx;
+	saved_sq_owner = txq->sq->owner;
+
+	owner = hinic3_set_wqe_combo(txq, &wqe_combo, offload, num_sge, &pi);
+	if (offload)
+		*wqe_combo.task = task;
+
+	tx_info = &txq->tx_info[pi];
+	tx_info->skb = skb;
+	tx_info->wqebb_cnt = wqebb_cnt;
+
+	err = hinic3_tx_map_skb(netdev, skb, txq, tx_info, &wqe_combo);
+	if (err) {
+		/* Rollback work queue to reclaim the wqebb we did not use */
+		txq->sq->wq.prod_idx = saved_wq_prod_idx;
+		txq->sq->owner = saved_sq_owner;
+		goto err_drop_pkt;
+	}
+
+	netdev_tx_sent_queue(netdev_get_tx_queue(netdev, txq->sq->q_id),
+			     skb->len);
+	netif_subqueue_maybe_stop(netdev, tx_q->sq->q_id,
+				  hinic3_wq_free_wqebbs(&tx_q->sq->wq),
+				  tx_q->tx_stop_thrs,
+				  tx_q->tx_start_thrs);
+
+	hinic3_prepare_sq_ctrl(&wqe_combo, queue_info, num_sge, owner);
+	hinic3_write_db(txq->sq, 0, DB_CFLAG_DP_SQ,
+			hinic3_get_sq_local_pi(txq->sq));
+
+	return NETDEV_TX_OK;
+
+err_drop_pkt:
+	dev_kfree_skb_any(skb);
+
+err_out:
+	return NETDEV_TX_OK;
+}
+
+netdev_tx_t hinic3_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 q_id = skb_get_queue_mapping(skb);
+
+	if (unlikely(!netif_carrier_ok(netdev)))
+		goto err_drop_pkt;
+
+	if (unlikely(q_id >= nic_dev->q_params.num_qps))
+		goto err_drop_pkt;
+
+	return hinic3_send_one_skb(skb, netdev, &nic_dev->txqs[q_id]);
+
+err_drop_pkt:
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+static bool is_hw_complete_sq_process(struct hinic3_io_queue *sq)
+{
+	u16 sw_pi, hw_ci;
+
+	sw_pi = hinic3_get_sq_local_pi(sq);
+	hw_ci = hinic3_get_sq_hw_ci(sq);
+
+	return sw_pi == hw_ci;
+}
+
+#define HINIC3_FLUSH_QUEUE_POLL_SLEEP_US   10000
+#define HINIC3_FLUSH_QUEUE_POLL_TIMEOUT_US 10000000
+static int hinic3_stop_sq(struct hinic3_txq *txq)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(txq->netdev);
+	int err, rc;
+
+	err = read_poll_timeout(hinic3_force_drop_tx_pkt, rc,
+				is_hw_complete_sq_process(txq->sq) || rc,
+				HINIC3_FLUSH_QUEUE_POLL_SLEEP_US,
+				HINIC3_FLUSH_QUEUE_POLL_TIMEOUT_US,
+				true, nic_dev->hwdev);
+	if (rc)
+		return rc;
+	else
+		return err;
+}
+
+/* packet transmission should be stopped before calling this function */
+void hinic3_flush_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 qid;
+	int err;
+
+	for (qid = 0; qid < nic_dev->q_params.num_qps; qid++) {
+		err = hinic3_stop_sq(&nic_dev->txqs[qid]);
+		netdev_tx_reset_subqueue(netdev, qid);
+		if (err)
+			netdev_err(netdev, "Failed to stop sq%u\n", qid);
+	}
+}
+
+#define HINIC3_BDS_PER_SQ_WQEBB \
+	(HINIC3_SQ_WQEBB_SIZE / sizeof(struct hinic3_sq_bufdesc))
+
+bool hinic3_tx_poll(struct hinic3_txq *txq, int budget)
+{
+	struct net_device *netdev = txq->netdev;
+	u16 hw_ci, sw_ci, q_id = txq->sq->q_id;
+	struct hinic3_tx_info *tx_info;
+	struct hinic3_txq *tx_q = txq;
+	unsigned int bytes_compl = 0;
+	unsigned int pkts = 0;
+	u16 wqebb_cnt = 0;
+
+	hw_ci = hinic3_get_sq_hw_ci(txq->sq);
+	dma_rmb();
+	sw_ci = hinic3_get_sq_local_ci(txq->sq);
+
+	do {
+		tx_info = &txq->tx_info[sw_ci];
+
+		/* Did all wqebb of this wqe complete? */
+		if (hw_ci == sw_ci ||
+		    ((hw_ci - sw_ci) & txq->q_mask) < tx_info->wqebb_cnt)
+			break;
+
+		sw_ci = (sw_ci + tx_info->wqebb_cnt) & txq->q_mask;
+		net_prefetch(&txq->tx_info[sw_ci]);
+
+		wqebb_cnt += tx_info->wqebb_cnt;
+		bytes_compl += tx_info->skb->len;
+		pkts++;
+
+		hinic3_tx_unmap_skb(netdev, tx_info->skb, tx_info->dma_info);
+		napi_consume_skb(tx_info->skb, budget);
+		tx_info->skb = NULL;
+	} while (likely(pkts < HINIC3_TX_POLL_WEIGHT));
+
+	hinic3_wq_put_wqebbs(&txq->sq->wq, wqebb_cnt);
+
+	netif_subqueue_completed_wake(netdev, q_id, pkts, bytes_compl,
+				      hinic3_wq_free_wqebbs(&tx_q->sq->wq),
+				      tx_q->tx_start_thrs);
+
+	return pkts == HINIC3_TX_POLL_WEIGHT;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
new file mode 100644
index 000000000000..9e505cc19dd5
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_TX_H_
+#define _HINIC3_TX_H_
+
+#include <linux/bitops.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/netdevice.h>
+#include <net/checksum.h>
+
+#define VXLAN_OFFLOAD_PORT_LE            cpu_to_be16(4789)
+#define TCP_HDR_DATA_OFF_UNIT_SHIFT      2
+#define TRANSPORT_OFFSET(l4_hdr, skb)    ((l4_hdr) - (skb)->data)
+
+#define HINIC3_COMPACT_WQEE_SKB_MAX_LEN  16383
+#define HINIC3_TX_POLL_WEIGHT		 64
+#define HINIC3_DEFAULT_STOP_THRS	 6
+#define HINIC3_DEFAULT_START_THRS	 24
+
+enum sq_wqe_data_format {
+	SQ_NORMAL_WQE = 0,
+};
+
+enum sq_wqe_ec_type {
+	SQ_WQE_COMPACT_TYPE  = 0,
+	SQ_WQE_EXTENDED_TYPE = 1,
+};
+
+enum sq_wqe_tasksect_len_type {
+	SQ_WQE_TASKSECT_46BITS  = 0,
+	SQ_WQE_TASKSECT_16BYTES = 1,
+};
+
+enum hinic3_tx_offload_type {
+	HINIC3_TX_OFFLOAD_TSO     = BIT(0),
+	HINIC3_TX_OFFLOAD_CSUM    = BIT(1),
+	HINIC3_TX_OFFLOAD_VLAN    = BIT(2),
+	HINIC3_TX_OFFLOAD_INVALID = BIT(3),
+	HINIC3_TX_OFFLOAD_ESP     = BIT(4),
+};
+
+#define SQ_CTRL_BUFDESC_NUM_MASK   GENMASK(26, 19)
+#define SQ_CTRL_TASKSECT_LEN_MASK  BIT(27)
+#define SQ_CTRL_DATA_FORMAT_MASK   BIT(28)
+#define SQ_CTRL_EXTENDED_MASK      BIT(30)
+#define SQ_CTRL_OWNER_MASK         BIT(31)
+#define SQ_CTRL_SET(val, member) \
+	FIELD_PREP(SQ_CTRL_##member##_MASK, val)
+
+#define SQ_CTRL_QUEUE_INFO_PLDOFF_MASK  GENMASK(9, 2)
+#define SQ_CTRL_QUEUE_INFO_UFO_MASK     BIT(10)
+#define SQ_CTRL_QUEUE_INFO_TSO_MASK     BIT(11)
+#define SQ_CTRL_QUEUE_INFO_MSS_MASK     GENMASK(26, 13)
+#define SQ_CTRL_QUEUE_INFO_UC_MASK      BIT(28)
+
+#define SQ_CTRL_QUEUE_INFO_SET(val, member) \
+	FIELD_PREP(SQ_CTRL_QUEUE_INFO_##member##_MASK, val)
+#define SQ_CTRL_QUEUE_INFO_GET(val, member) \
+	FIELD_GET(SQ_CTRL_QUEUE_INFO_##member##_MASK, val)
+
+#define SQ_CTRL_MAX_PLDOFF  221
+
+#define SQ_TASK_INFO0_TUNNEL_FLAG_MASK  BIT(19)
+#define SQ_TASK_INFO0_INNER_L4_EN_MASK  BIT(24)
+#define SQ_TASK_INFO0_INNER_L3_EN_MASK  BIT(25)
+#define SQ_TASK_INFO0_OUT_L4_EN_MASK    BIT(27)
+#define SQ_TASK_INFO0_OUT_L3_EN_MASK    BIT(28)
+#define SQ_TASK_INFO0_SET(val, member) \
+	FIELD_PREP(SQ_TASK_INFO0_##member##_MASK, val)
+
+#define SQ_TASK_INFO3_VLAN_TAG_MASK        GENMASK(15, 0)
+#define SQ_TASK_INFO3_VLAN_TPID_MASK       GENMASK(18, 16)
+#define SQ_TASK_INFO3_VLAN_TAG_VALID_MASK  BIT(19)
+#define SQ_TASK_INFO3_SET(val, member) \
+	FIELD_PREP(SQ_TASK_INFO3_##member##_MASK, val)
+
+struct hinic3_sq_wqe_desc {
+	u32 ctrl_len;
+	u32 queue_info;
+	u32 hi_addr;
+	u32 lo_addr;
+};
+
+struct hinic3_sq_task {
+	u32 pkt_info0;
+	u32 ip_identify;
+	u32 rsvd;
+	u32 vlan_offload;
+};
+
+struct hinic3_sq_wqe_combo {
+	struct hinic3_sq_wqe_desc *ctrl_bd0;
+	struct hinic3_sq_task     *task;
+	struct hinic3_sq_bufdesc  *bds_head;
+	struct hinic3_sq_bufdesc  *bds_sec2;
+	u16                       first_bds_num;
+	u32                       wqe_type;
+	u32                       task_type;
+};
+
+struct hinic3_dma_info {
+	dma_addr_t dma;
+	u32        len;
+};
+
+struct hinic3_tx_info {
+	struct sk_buff         *skb;
+	u16                    wqebb_cnt;
+	struct hinic3_dma_info *dma_info;
+};
+
+struct hinic3_txq {
+	struct net_device       *netdev;
+	struct device           *dev;
+
+	u16                     q_id;
+	u16                     tx_stop_thrs;
+	u16                     tx_start_thrs;
+	u32                     q_mask;
+	u32                     q_depth;
+
+	struct hinic3_tx_info   *tx_info;
+	struct hinic3_io_queue  *sq;
+} ____cacheline_aligned;
+
+int hinic3_alloc_txqs(struct net_device *netdev);
+void hinic3_free_txqs(struct net_device *netdev);
+
+netdev_tx_t hinic3_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+bool hinic3_tx_poll(struct hinic3_txq *txq, int budget);
+void hinic3_flush_txqs(struct net_device *netdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
new file mode 100644
index 000000000000..2ac7efcd1365
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/dma-mapping.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_wq.h"
+
+void hinic3_wq_get_multi_wqebbs(struct hinic3_wq *wq,
+				u16 num_wqebbs, u16 *prod_idx,
+				struct hinic3_sq_bufdesc **first_part_wqebbs,
+				struct hinic3_sq_bufdesc **second_part_wqebbs,
+				u16 *first_part_wqebbs_num)
+{
+	u32 idx, remaining;
+
+	idx = wq->prod_idx & wq->idx_mask;
+	wq->prod_idx += num_wqebbs;
+	*prod_idx = idx;
+	*first_part_wqebbs = get_q_element(&wq->qpages, idx, &remaining);
+	if (likely(remaining >= num_wqebbs)) {
+		*first_part_wqebbs_num = num_wqebbs;
+		*second_part_wqebbs = NULL;
+	} else {
+		*first_part_wqebbs_num = remaining;
+		idx += remaining;
+		*second_part_wqebbs = get_q_element(&wq->qpages, idx, NULL);
+	}
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h
new file mode 100644
index 000000000000..ab37893efd7e
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_WQ_H_
+#define _HINIC3_WQ_H_
+
+#include <linux/io.h>
+
+#include "hinic3_queue_common.h"
+
+struct hinic3_sq_bufdesc {
+	/* 31-bits Length, L2NIC only uses length[17:0] */
+	u32 len;
+	u32 rsvd;
+	u32 hi_addr;
+	u32 lo_addr;
+};
+
+/* Work queue is used to submit elements (tx, rx, cmd) to hw.
+ * Driver is the producer that advances prod_idx. cons_idx is advanced when
+ * HW reports completions of previously submitted elements.
+ */
+struct hinic3_wq {
+	struct hinic3_queue_pages qpages;
+	/* Unmasked producer/consumer indices that are advanced to natural
+	 * integer overflow regardless of queue depth.
+	 */
+	u16                       cons_idx;
+	u16                       prod_idx;
+
+	u32                       q_depth;
+	u16                       idx_mask;
+
+	/* Work Queue (logical WQEBB array) is mapped to hw via Chip Logical
+	 * Address (CLA) using 1 of 2 levels:
+	 *     level 0 - direct mapping of single wq page
+	 *     level 1 - indirect mapping of multiple pages via additional page
+	 *               table.
+	 * When wq uses level 1, wq_block will hold the allocated indirection
+	 * table.
+	 */
+	dma_addr_t                wq_block_paddr;
+	__be64                    *wq_block_vaddr;
+} ____cacheline_aligned;
+
+/* Get number of elements in work queue that are in-use. */
+static inline u16 hinic3_wq_get_used(const struct hinic3_wq *wq)
+{
+	return READ_ONCE(wq->prod_idx) - READ_ONCE(wq->cons_idx);
+}
+
+static inline u16 hinic3_wq_free_wqebbs(struct hinic3_wq *wq)
+{
+	/* Don't allow queue to become completely full, report (free - 1). */
+	return wq->q_depth - hinic3_wq_get_used(wq) - 1;
+}
+
+static inline void *hinic3_wq_get_one_wqebb(struct hinic3_wq *wq, u16 *pi)
+{
+	*pi = wq->prod_idx & wq->idx_mask;
+	wq->prod_idx++;
+	return get_q_element(&wq->qpages, *pi, NULL);
+}
+
+static inline void hinic3_wq_put_wqebbs(struct hinic3_wq *wq, u16 num_wqebbs)
+{
+	wq->cons_idx += num_wqebbs;
+}
+
+void hinic3_wq_get_multi_wqebbs(struct hinic3_wq *wq,
+				u16 num_wqebbs, u16 *prod_idx,
+				struct hinic3_sq_bufdesc **first_part_wqebbs,
+				struct hinic3_sq_bufdesc **second_part_wqebbs,
+				u16 *first_part_wqebbs_num);
+
+#endif
diff --git a/drivers/net/ethernet/ibm/Kconfig b/drivers/net/ethernet/ibm/Kconfig
index c0c112d95b89..4f4b23465c47 100644
--- a/drivers/net/ethernet/ibm/Kconfig
+++ b/drivers/net/ethernet/ibm/Kconfig
@@ -27,6 +27,19 @@ config IBMVETH
 	  To compile this driver as a module, choose M here. The module will
 	  be called ibmveth.
 
+config IBMVETH_KUNIT_TEST
+	bool "KUnit test for IBM LAN Virtual Ethernet support" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	depends on KUNIT=y && IBMVETH=y
+	default KUNIT_ALL_TESTS
+	help
+	  This builds unit tests for the IBM LAN Virtual Ethernet driver.
+
+	  For more information on KUnit and unit tests in general, please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 source "drivers/net/ethernet/ibm/emac/Kconfig"
 
 config EHEA
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 25b8a3556004..417dfa18daae 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2554,17 +2554,12 @@ static int emac_dt_mdio_probe(struct emac_instance *dev)
 	struct mii_bus *bus;
 	int res;
 
-	mii_np = of_get_child_by_name(dev->ofdev->dev.of_node, "mdio");
+	mii_np = of_get_available_child_by_name(dev->ofdev->dev.of_node, "mdio");
 	if (!mii_np) {
 		dev_err(&dev->ofdev->dev, "no mdio definition found.");
 		return -ENODEV;
 	}
 
-	if (!of_device_is_available(mii_np)) {
-		res = -ENODEV;
-		goto put_node;
-	}
-
 	bus = devm_mdiobus_alloc(&dev->ofdev->dev);
 	if (!bus) {
 		res = -ENOMEM;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index b619a3ec245b..24046fe16634 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -39,8 +39,6 @@
 #include "ibmveth.h"
 
 static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance);
-static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
-				       bool reuse);
 static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev);
 
 static struct kobj_type ktype_veth_pool;
@@ -231,7 +229,10 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
 		index = pool->free_map[free_index];
 		skb = NULL;
 
-		BUG_ON(index == IBM_VETH_INVALID_MAP);
+		if (WARN_ON(index == IBM_VETH_INVALID_MAP)) {
+			schedule_work(&adapter->work);
+			goto bad_index_failure;
+		}
 
 		/* are we allocating a new buffer or recycling an old one */
 		if (pool->skbuff[index])
@@ -300,6 +301,7 @@ failure:
 		                 DMA_FROM_DEVICE);
 	dev_kfree_skb_any(pool->skbuff[index]);
 	pool->skbuff[index] = NULL;
+bad_index_failure:
 	adapter->replenish_add_buff_failure++;
 
 	mb();
@@ -370,20 +372,36 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter,
 	}
 }
 
-/* remove a buffer from a pool */
-static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
-					    u64 correlator, bool reuse)
+/**
+ * ibmveth_remove_buffer_from_pool - remove a buffer from a pool
+ * @adapter: adapter instance
+ * @correlator: identifies pool and index
+ * @reuse: whether to reuse buffer
+ *
+ * Return:
+ * * %0       - success
+ * * %-EINVAL - correlator maps to pool or index out of range
+ * * %-EFAULT - pool and index map to null skb
+ */
+static int ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
+					   u64 correlator, bool reuse)
 {
 	unsigned int pool  = correlator >> 32;
 	unsigned int index = correlator & 0xffffffffUL;
 	unsigned int free_index;
 	struct sk_buff *skb;
 
-	BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS);
-	BUG_ON(index >= adapter->rx_buff_pool[pool].size);
+	if (WARN_ON(pool >= IBMVETH_NUM_BUFF_POOLS) ||
+	    WARN_ON(index >= adapter->rx_buff_pool[pool].size)) {
+		schedule_work(&adapter->work);
+		return -EINVAL;
+	}
 
 	skb = adapter->rx_buff_pool[pool].skbuff[index];
-	BUG_ON(skb == NULL);
+	if (WARN_ON(!skb)) {
+		schedule_work(&adapter->work);
+		return -EFAULT;
+	}
 
 	/* if we are going to reuse the buffer then keep the pointers around
 	 * but mark index as available. replenish will see the skb pointer and
@@ -411,6 +429,8 @@ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
 	mb();
 
 	atomic_dec(&(adapter->rx_buff_pool[pool].available));
+
+	return 0;
 }
 
 /* get the current buffer on the rx queue */
@@ -420,24 +440,44 @@ static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *ada
 	unsigned int pool = correlator >> 32;
 	unsigned int index = correlator & 0xffffffffUL;
 
-	BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS);
-	BUG_ON(index >= adapter->rx_buff_pool[pool].size);
+	if (WARN_ON(pool >= IBMVETH_NUM_BUFF_POOLS) ||
+	    WARN_ON(index >= adapter->rx_buff_pool[pool].size)) {
+		schedule_work(&adapter->work);
+		return NULL;
+	}
 
 	return adapter->rx_buff_pool[pool].skbuff[index];
 }
 
-static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
-				       bool reuse)
+/**
+ * ibmveth_rxq_harvest_buffer - Harvest buffer from pool
+ *
+ * @adapter: pointer to adapter
+ * @reuse:   whether to reuse buffer
+ *
+ * Context: called from ibmveth_poll
+ *
+ * Return:
+ * * %0    - success
+ * * other - non-zero return from ibmveth_remove_buffer_from_pool
+ */
+static int ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
+				      bool reuse)
 {
 	u64 cor;
+	int rc;
 
 	cor = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
-	ibmveth_remove_buffer_from_pool(adapter, cor, reuse);
+	rc = ibmveth_remove_buffer_from_pool(adapter, cor, reuse);
+	if (unlikely(rc))
+		return rc;
 
 	if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
 		adapter->rx_queue.index = 0;
 		adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
 	}
+
+	return 0;
 }
 
 static void ibmveth_free_tx_ltb(struct ibmveth_adapter *adapter, int idx)
@@ -709,6 +749,35 @@ static int ibmveth_close(struct net_device *netdev)
 	return 0;
 }
 
+/**
+ * ibmveth_reset - Handle scheduled reset work
+ *
+ * @w: pointer to work_struct embedded in adapter structure
+ *
+ * Context: This routine acquires rtnl_mutex and disables its NAPI through
+ *          ibmveth_close. It can't be called directly in a context that has
+ *          already acquired rtnl_mutex or disabled its NAPI, or directly from
+ *          a poll routine.
+ *
+ * Return: void
+ */
+static void ibmveth_reset(struct work_struct *w)
+{
+	struct ibmveth_adapter *adapter = container_of(w, struct ibmveth_adapter, work);
+	struct net_device *netdev = adapter->netdev;
+
+	netdev_dbg(netdev, "reset starting\n");
+
+	rtnl_lock();
+
+	dev_close(adapter->netdev);
+	dev_open(adapter->netdev, NULL);
+
+	rtnl_unlock();
+
+	netdev_dbg(netdev, "reset complete\n");
+}
+
 static int ibmveth_set_link_ksettings(struct net_device *dev,
 				      const struct ethtool_link_ksettings *cmd)
 {
@@ -1324,7 +1393,8 @@ restart_poll:
 			wmb(); /* suggested by larson1 */
 			adapter->rx_invalid_buffer++;
 			netdev_dbg(netdev, "recycling invalid buffer\n");
-			ibmveth_rxq_harvest_buffer(adapter, true);
+			if (unlikely(ibmveth_rxq_harvest_buffer(adapter, true)))
+				break;
 		} else {
 			struct sk_buff *skb, *new_skb;
 			int length = ibmveth_rxq_frame_length(adapter);
@@ -1334,6 +1404,8 @@ restart_poll:
 			__sum16 iph_check = 0;
 
 			skb = ibmveth_rxq_get_buffer(adapter);
+			if (unlikely(!skb))
+				break;
 
 			/* if the large packet bit is set in the rx queue
 			 * descriptor, the mss will be written by PHYP eight
@@ -1357,10 +1429,12 @@ restart_poll:
 				if (rx_flush)
 					ibmveth_flush_buffer(skb->data,
 						length + offset);
-				ibmveth_rxq_harvest_buffer(adapter, true);
+				if (unlikely(ibmveth_rxq_harvest_buffer(adapter, true)))
+					break;
 				skb = new_skb;
 			} else {
-				ibmveth_rxq_harvest_buffer(adapter, false);
+				if (unlikely(ibmveth_rxq_harvest_buffer(adapter, false)))
+					break;
 				skb_reserve(skb, offset);
 			}
 
@@ -1407,7 +1481,10 @@ restart_poll:
 	 * then check once more to make sure we are done.
 	 */
 	lpar_rc = h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_ENABLE);
-	BUG_ON(lpar_rc != H_SUCCESS);
+	if (WARN_ON(lpar_rc != H_SUCCESS)) {
+		schedule_work(&adapter->work);
+		goto out;
+	}
 
 	if (ibmveth_rxq_pending_buffer(adapter) && napi_schedule(napi)) {
 		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
@@ -1428,7 +1505,7 @@ static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
 	if (napi_schedule_prep(&adapter->napi)) {
 		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
 				       VIO_IRQ_DISABLE);
-		BUG_ON(lpar_rc != H_SUCCESS);
+		WARN_ON(lpar_rc != H_SUCCESS);
 		__napi_schedule(&adapter->napi);
 	}
 	return IRQ_HANDLED;
@@ -1670,6 +1747,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	adapter->vdev = dev;
 	adapter->netdev = netdev;
+	INIT_WORK(&adapter->work, ibmveth_reset);
 	adapter->mcastFilterSize = be32_to_cpu(*mcastFilterSize_p);
 	ibmveth_init_link_settings(netdev);
 
@@ -1762,6 +1840,8 @@ static void ibmveth_remove(struct vio_dev *dev)
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
 	int i;
 
+	cancel_work_sync(&adapter->work);
+
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
 		kobject_put(&adapter->rx_buff_pool[i].kobj);
 
@@ -1791,6 +1871,26 @@ static ssize_t veth_pool_show(struct kobject *kobj,
 	return 0;
 }
 
+/**
+ * veth_pool_store - sysfs store handler for pool attributes
+ * @kobj: kobject embedded in pool
+ * @attr: attribute being changed
+ * @buf: value being stored
+ * @count: length of @buf in bytes
+ *
+ * Stores new value in pool attribute. Verifies the range of the new value for
+ * size and buff_size. Verifies that at least one pool remains available to
+ * receive MTU-sized packets.
+ *
+ * Context: Process context.
+ *          Takes and releases rtnl_mutex to ensure correct ordering of close
+ *	    and open calls.
+ * Return:
+ * * %-EPERM  - Not allowed to disabled all MTU-sized buffer pools
+ * * %-EINVAL - New pool size or buffer size is out of range
+ * * count    - Return count for success
+ * * other    - Return value from a failed ibmveth_open call
+ */
 static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 			       const char *buf, size_t count)
 {
@@ -1800,24 +1900,30 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 	struct net_device *netdev = dev_get_drvdata(kobj_to_dev(kobj->parent));
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
 	long value = simple_strtol(buf, NULL, 10);
+	bool change = false;
+	u32 newbuff_size;
+	u32 oldbuff_size;
+	int newactive;
+	int oldactive;
+	u32 newsize;
+	u32 oldsize;
 	long rc;
 
+	rtnl_lock();
+
+	oldbuff_size = pool->buff_size;
+	oldactive = pool->active;
+	oldsize = pool->size;
+
+	newbuff_size = oldbuff_size;
+	newactive = oldactive;
+	newsize = oldsize;
+
 	if (attr == &veth_active_attr) {
-		if (value && !pool->active) {
-			if (netif_running(netdev)) {
-				if (ibmveth_alloc_buffer_pool(pool)) {
-					netdev_err(netdev,
-						   "unable to alloc pool\n");
-					return -ENOMEM;
-				}
-				pool->active = 1;
-				ibmveth_close(netdev);
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
-			} else {
-				pool->active = 1;
-			}
-		} else if (!value && pool->active) {
+		if (value && !oldactive) {
+			newactive = 1;
+			change = true;
+		} else if (!value && oldactive) {
 			int mtu = netdev->mtu + IBMVETH_BUFF_OH;
 			int i;
 			/* Make sure there is a buffer pool with buffers that
@@ -1833,48 +1939,60 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 
 			if (i == IBMVETH_NUM_BUFF_POOLS) {
 				netdev_err(netdev, "no active pool >= MTU\n");
-				return -EPERM;
+				rc = -EPERM;
+				goto unlock_err;
 			}
 
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->active = 0;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
-			}
-			pool->active = 0;
+			newactive = 0;
+			change = true;
 		}
 	} else if (attr == &veth_num_attr) {
 		if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) {
-			return -EINVAL;
-		} else {
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->size = value;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
-			} else {
-				pool->size = value;
-			}
+			rc = -EINVAL;
+			goto unlock_err;
+		}
+		if (value != oldsize) {
+			newsize = value;
+			change = true;
 		}
 	} else if (attr == &veth_size_attr) {
 		if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) {
-			return -EINVAL;
-		} else {
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->buff_size = value;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
-			} else {
-				pool->buff_size = value;
+			rc = -EINVAL;
+			goto unlock_err;
+		}
+		if (value != oldbuff_size) {
+			newbuff_size = value;
+			change = true;
+		}
+	}
+
+	if (change) {
+		if (netif_running(netdev))
+			ibmveth_close(netdev);
+
+		pool->active = newactive;
+		pool->buff_size = newbuff_size;
+		pool->size = newsize;
+
+		if (netif_running(netdev)) {
+			rc = ibmveth_open(netdev);
+			if (rc) {
+				pool->active = oldactive;
+				pool->buff_size = oldbuff_size;
+				pool->size = oldsize;
+				goto unlock_err;
 			}
 		}
 	}
+	rtnl_unlock();
 
 	/* kick the interrupt handler to allocate/deallocate pools */
 	ibmveth_interrupt(netdev->irq, netdev);
 	return count;
+
+unlock_err:
+	rtnl_unlock();
+	return rc;
 }
 
 
@@ -1947,3 +2065,132 @@ static void __exit ibmveth_module_exit(void)
 
 module_init(ibmveth_module_init);
 module_exit(ibmveth_module_exit);
+
+#ifdef CONFIG_IBMVETH_KUNIT_TEST
+#include <kunit/test.h>
+
+/**
+ * ibmveth_reset_kunit - reset routine for running in KUnit environment
+ *
+ * @w: pointer to work_struct embedded in adapter structure
+ *
+ * Context: Called in the KUnit environment. Does nothing.
+ *
+ * Return: void
+ */
+static void ibmveth_reset_kunit(struct work_struct *w)
+{
+	netdev_dbg(NULL, "reset_kunit starting\n");
+	netdev_dbg(NULL, "reset_kunit complete\n");
+}
+
+/**
+ * ibmveth_remove_buffer_from_pool_test - unit test for some of
+ *                                        ibmveth_remove_buffer_from_pool
+ * @test: pointer to kunit structure
+ *
+ * Tests the error returns from ibmveth_remove_buffer_from_pool.
+ * ibmveth_remove_buffer_from_pool also calls WARN_ON, so dmesg should be
+ * checked to see that these warnings happened.
+ *
+ * Return: void
+ */
+static void ibmveth_remove_buffer_from_pool_test(struct kunit *test)
+{
+	struct ibmveth_adapter *adapter = kunit_kzalloc(test, sizeof(*adapter), GFP_KERNEL);
+	struct ibmveth_buff_pool *pool;
+	u64 correlator;
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter);
+
+	INIT_WORK(&adapter->work, ibmveth_reset_kunit);
+
+	/* Set sane values for buffer pools */
+	for (int i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
+		ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+					 pool_count[i], pool_size[i],
+					 pool_active[i]);
+
+	pool = &adapter->rx_buff_pool[0];
+	pool->skbuff = kunit_kcalloc(test, pool->size, sizeof(void *), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pool->skbuff);
+
+	correlator = ((u64)IBMVETH_NUM_BUFF_POOLS << 32) | 0;
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	correlator = ((u64)0 << 32) | adapter->rx_buff_pool[0].size;
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	correlator = (u64)0 | 0;
+	pool->skbuff[0] = NULL;
+	KUNIT_EXPECT_EQ(test, -EFAULT, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EFAULT, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	flush_work(&adapter->work);
+}
+
+/**
+ * ibmveth_rxq_get_buffer_test - unit test for ibmveth_rxq_get_buffer
+ * @test: pointer to kunit structure
+ *
+ * Tests ibmveth_rxq_get_buffer. ibmveth_rxq_get_buffer also calls WARN_ON for
+ * the NULL returns, so dmesg should be checked to see that these warnings
+ * happened.
+ *
+ * Return: void
+ */
+static void ibmveth_rxq_get_buffer_test(struct kunit *test)
+{
+	struct ibmveth_adapter *adapter = kunit_kzalloc(test, sizeof(*adapter), GFP_KERNEL);
+	struct sk_buff *skb = kunit_kzalloc(test, sizeof(*skb), GFP_KERNEL);
+	struct ibmveth_buff_pool *pool;
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	INIT_WORK(&adapter->work, ibmveth_reset_kunit);
+
+	adapter->rx_queue.queue_len = 1;
+	adapter->rx_queue.index = 0;
+	adapter->rx_queue.queue_addr = kunit_kzalloc(test, sizeof(struct ibmveth_rx_q_entry),
+						     GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter->rx_queue.queue_addr);
+
+	/* Set sane values for buffer pools */
+	for (int i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
+		ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+					 pool_count[i], pool_size[i],
+					 pool_active[i]);
+
+	pool = &adapter->rx_buff_pool[0];
+	pool->skbuff = kunit_kcalloc(test, pool->size, sizeof(void *), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pool->skbuff);
+
+	adapter->rx_queue.queue_addr[0].correlator = (u64)IBMVETH_NUM_BUFF_POOLS << 32 | 0;
+	KUNIT_EXPECT_PTR_EQ(test, NULL, ibmveth_rxq_get_buffer(adapter));
+
+	adapter->rx_queue.queue_addr[0].correlator = (u64)0 << 32 | adapter->rx_buff_pool[0].size;
+	KUNIT_EXPECT_PTR_EQ(test, NULL, ibmveth_rxq_get_buffer(adapter));
+
+	pool->skbuff[0] = skb;
+	adapter->rx_queue.queue_addr[0].correlator = (u64)0 << 32 | 0;
+	KUNIT_EXPECT_PTR_EQ(test, skb, ibmveth_rxq_get_buffer(adapter));
+
+	flush_work(&adapter->work);
+}
+
+static struct kunit_case ibmveth_test_cases[] = {
+	KUNIT_CASE(ibmveth_remove_buffer_from_pool_test),
+	KUNIT_CASE(ibmveth_rxq_get_buffer_test),
+	{}
+};
+
+static struct kunit_suite ibmveth_test_suite = {
+	.name = "ibmveth-kunit-test",
+	.test_cases = ibmveth_test_cases,
+};
+
+kunit_test_suite(ibmveth_test_suite);
+#endif
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 8468e2c59d7a..b0a2460ec9f9 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -134,38 +134,39 @@ struct ibmveth_rx_q {
 };
 
 struct ibmveth_adapter {
-    struct vio_dev *vdev;
-    struct net_device *netdev;
-    struct napi_struct napi;
-    unsigned int mcastFilterSize;
-    void * buffer_list_addr;
-    void * filter_list_addr;
-    void *tx_ltb_ptr[IBMVETH_MAX_QUEUES];
-    unsigned int tx_ltb_size;
-    dma_addr_t tx_ltb_dma[IBMVETH_MAX_QUEUES];
-    dma_addr_t buffer_list_dma;
-    dma_addr_t filter_list_dma;
-    struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS];
-    struct ibmveth_rx_q rx_queue;
-    int rx_csum;
-    int large_send;
-    bool is_active_trunk;
-
-    u64 fw_ipv6_csum_support;
-    u64 fw_ipv4_csum_support;
-    u64 fw_large_send_support;
-    /* adapter specific stats */
-    u64 replenish_task_cycles;
-    u64 replenish_no_mem;
-    u64 replenish_add_buff_failure;
-    u64 replenish_add_buff_success;
-    u64 rx_invalid_buffer;
-    u64 rx_no_buffer;
-    u64 tx_map_failed;
-    u64 tx_send_failed;
-    u64 tx_large_packets;
-    u64 rx_large_packets;
-    /* Ethtool settings */
+	struct vio_dev *vdev;
+	struct net_device *netdev;
+	struct napi_struct napi;
+	struct work_struct work;
+	unsigned int mcastFilterSize;
+	void *buffer_list_addr;
+	void *filter_list_addr;
+	void *tx_ltb_ptr[IBMVETH_MAX_QUEUES];
+	unsigned int tx_ltb_size;
+	dma_addr_t tx_ltb_dma[IBMVETH_MAX_QUEUES];
+	dma_addr_t buffer_list_dma;
+	dma_addr_t filter_list_dma;
+	struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS];
+	struct ibmveth_rx_q rx_queue;
+	int rx_csum;
+	int large_send;
+	bool is_active_trunk;
+
+	u64 fw_ipv6_csum_support;
+	u64 fw_ipv4_csum_support;
+	u64 fw_large_send_support;
+	/* adapter specific stats */
+	u64 replenish_task_cycles;
+	u64 replenish_no_mem;
+	u64 replenish_add_buff_failure;
+	u64 replenish_add_buff_success;
+	u64 rx_invalid_buffer;
+	u64 rx_no_buffer;
+	u64 tx_map_failed;
+	u64 tx_send_failed;
+	u64 tx_large_packets;
+	u64 rx_large_packets;
+	/* Ethtool settings */
 	u8 duplex;
 	u32 speed;
 };
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index e95ae0d39948..92647e137cf8 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -234,11 +234,17 @@ static int ibmvnic_set_queue_affinity(struct ibmvnic_sub_crq_queue *queue,
 		(*stragglers)--;
 	}
 	/* atomic write is safer than writing bit by bit directly */
-	for (i = 0; i < stride; i++) {
-		cpumask_set_cpu(*cpu, mask);
-		*cpu = cpumask_next_wrap(*cpu, cpu_online_mask,
-					 nr_cpu_ids, false);
+	for_each_online_cpu_wrap(i, *cpu) {
+		if (!stride--) {
+			/* For the next queue we start from the first
+			 * unused CPU in this queue
+			 */
+			*cpu = i;
+			break;
+		}
+		cpumask_set_cpu(i, mask);
 	}
+
 	/* set queue affinity mask */
 	cpumask_copy(queue->affinity_mask, mask);
 	rc = irq_set_affinity_and_hint(queue->irq, queue->affinity_mask);
@@ -256,7 +262,7 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter)
 	int num_rxqs = adapter->num_active_rx_scrqs, i_rxqs = 0;
 	int num_txqs = adapter->num_active_tx_scrqs, i_txqs = 0;
 	int total_queues, stride, stragglers, i;
-	unsigned int num_cpu, cpu;
+	unsigned int num_cpu, cpu = 0;
 	bool is_rx_queue;
 	int rc = 0;
 
@@ -274,8 +280,6 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter)
 	stride = max_t(int, num_cpu / total_queues, 1);
 	/* number of leftover cpu's */
 	stragglers = num_cpu >= total_queues ? num_cpu % total_queues : 0;
-	/* next available cpu to assign irq to */
-	cpu = cpumask_next(-1, cpu_online_mask);
 
 	for (i = 0; i < total_queues; i++) {
 		is_rx_queue = false;
@@ -2408,6 +2412,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	dma_addr_t data_dma_addr;
 	struct netdev_queue *txq;
 	unsigned long lpar_rc;
+	unsigned int skblen;
 	union sub_crq tx_crq;
 	unsigned int offset;
 	bool use_scrq_send_direct = false;
@@ -2522,6 +2527,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_buff->skb = skb;
 	tx_buff->index = bufidx;
 	tx_buff->pool_index = queue_num;
+	skblen = skb->len;
 
 	memset(&tx_crq, 0, sizeof(tx_crq));
 	tx_crq.v1.first = IBMVNIC_CRQ_CMD;
@@ -2614,7 +2620,7 @@ early_exit:
 		netif_stop_subqueue(netdev, queue_num);
 	}
 
-	tx_bytes += skb->len;
+	tx_bytes += skblen;
 	txq_trans_cond_update(txq);
 	ret = NETDEV_TX_OK;
 	goto out;
@@ -4827,6 +4833,18 @@ static void vnic_add_client_data(struct ibmvnic_adapter *adapter,
 	strscpy(vlcd->name, adapter->netdev->name, len);
 }
 
+static void ibmvnic_print_hex_dump(struct net_device *dev, void *buf,
+				   size_t len)
+{
+	unsigned char hex_str[16 * 3];
+
+	for (size_t i = 0; i < len; i += 16) {
+		hex_dump_to_buffer((unsigned char *)buf + i, len - i, 16, 8,
+				   hex_str, sizeof(hex_str), false);
+		netdev_dbg(dev, "%s\n", hex_str);
+	}
+}
+
 static int send_login(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_login_rsp_buffer *login_rsp_buffer;
@@ -4937,10 +4955,8 @@ static int send_login(struct ibmvnic_adapter *adapter)
 	vnic_add_client_data(adapter, vlcd);
 
 	netdev_dbg(adapter->netdev, "Login Buffer:\n");
-	for (i = 0; i < (adapter->login_buf_sz - 1) / 8 + 1; i++) {
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(adapter->login_buf))[i]);
-	}
+	ibmvnic_print_hex_dump(adapter->netdev, adapter->login_buf,
+			       adapter->login_buf_sz);
 
 	memset(&crq, 0, sizeof(crq));
 	crq.login.first = IBMVNIC_CRQ_CMD;
@@ -5317,15 +5333,13 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
-	int i;
 
 	dma_unmap_single(dev, adapter->ip_offload_tok,
 			 sizeof(adapter->ip_offload_buf), DMA_FROM_DEVICE);
 
 	netdev_dbg(adapter->netdev, "Query IP Offload Buffer:\n");
-	for (i = 0; i < (sizeof(adapter->ip_offload_buf) - 1) / 8 + 1; i++)
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(buf))[i]);
+	ibmvnic_print_hex_dump(adapter->netdev, buf,
+			       sizeof(adapter->ip_offload_buf));
 
 	netdev_dbg(adapter->netdev, "ipv4_chksum = %d\n", buf->ipv4_chksum);
 	netdev_dbg(adapter->netdev, "ipv6_chksum = %d\n", buf->ipv6_chksum);
@@ -5556,10 +5570,8 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	netdev_dbg(adapter->netdev, "Login Response Buffer:\n");
-	for (i = 0; i < (adapter->login_rsp_buf_sz - 1) / 8 + 1; i++) {
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(adapter->login_rsp_buf))[i]);
-	}
+	ibmvnic_print_hex_dump(netdev, adapter->login_rsp_buf,
+			       adapter->login_rsp_buf_sz);
 
 	/* Sanity checks */
 	if (login->num_txcomp_subcrqs != login_rsp->num_txsubm_subcrqs ||
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 20bc40eec487..5a331c1c76cb 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -147,6 +147,8 @@ config IXGBE
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select MDIO
+	select NET_DEVLINK
+	select PLDMFW
 	select PHYLIB
 	help
 	  This driver supports Intel(R) 10GbE PCI Express family of
@@ -264,6 +266,7 @@ config I40EVF
 	tristate "Intel(R) Ethernet Adaptive Virtual Function support"
 	select IAVF
 	depends on PCI_MSI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This driver supports virtual functions for Intel XL710,
 	  X710, X722, XXV710, and all devices advertising support for
@@ -292,6 +295,7 @@ config ICE
 	select DIMLIB
 	select LIBIE
 	select NET_DEVLINK
+	select PACKING
 	select PLDMFW
 	select DPLL
 	help
@@ -335,7 +339,7 @@ config ICE_SWITCHDEV
 config ICE_HWTS
 	bool "Support HW cross-timestamp on platforms with PTM support"
 	default y
-	depends on ICE && X86
+	depends on ICE && X86 && PCIE_PTM
 	help
 	  Say Y to enable hardware supported cross-timestamping on platforms
 	  with PCIe PTM support. The cross-timestamp is available through
@@ -365,6 +369,7 @@ config IGC
 	default n
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	depends on ETHTOOL_NETLINK
 	help
 	  This driver supports Intel(R) Ethernet Controller I225-LM/I225-V
 	  family of adapters.
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 3a5bbda235cb..5c56c1edd492 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1682,7 +1682,7 @@ static void e100_adjust_adaptive_ifs(struct nic *nic, int speed, int duplex)
 
 static void e100_watchdog(struct timer_list *t)
 {
-	struct nic *nic = from_timer(nic, t, watchdog);
+	struct nic *nic = timer_container_of(nic, t, watchdog);
 	struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
 	u32 speed;
 
@@ -2293,7 +2293,7 @@ static int e100_up(struct nic *nic)
 	return 0;
 
 err_no_irq:
-	del_timer_sync(&nic->watchdog);
+	timer_delete_sync(&nic->watchdog);
 err_clean_cbs:
 	e100_clean_cbs(nic);
 err_rx_clean_list:
@@ -2308,7 +2308,7 @@ static void e100_down(struct nic *nic)
 	netif_stop_queue(nic->netdev);
 	e100_hw_reset(nic);
 	free_irq(nic->pdev->irq, nic->netdev);
-	del_timer_sync(&nic->watchdog);
+	timer_delete_sync(&nic->watchdog);
 	netif_carrier_off(nic->netdev);
 	e100_clean_cbs(nic);
 	e100_rx_clean_list(nic);
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 3f089c3d47b2..d8595e84326d 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -477,10 +477,6 @@ static void e1000_down_and_stop(struct e1000_adapter *adapter)
 
 	cancel_delayed_work_sync(&adapter->phy_info_task);
 	cancel_delayed_work_sync(&adapter->fifo_stall_task);
-
-	/* Only kill reset task if adapter is not resetting */
-	if (!test_bit(__E1000_RESETTING, &adapter->flags))
-		cancel_work_sync(&adapter->reset_task);
 }
 
 void e1000_down(struct e1000_adapter *adapter)
@@ -1266,6 +1262,10 @@ static void e1000_remove(struct pci_dev *pdev)
 
 	unregister_netdev(netdev);
 
+	/* Only kill reset task if adapter is not resetting */
+	if (!test_bit(__E1000_RESETTING, &adapter->flags))
+		cancel_work_sync(&adapter->reset_task);
+
 	e1000_phy_hw_reset(hw);
 
 	kfree(adapter->tx_ring);
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 5e2cfa73f889..8294a7c4f122 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -803,4 +803,7 @@
 /* SerDes Control */
 #define E1000_GEN_POLL_TIMEOUT          640
 
+#define E1000_FEXTNVM12_PHYPD_CTRL_MASK	0x00C00000
+#define E1000_FEXTNVM12_PHYPD_CTRL_P1	0x00800000
+
 #endif /* _E1000_DEFINES_H_ */
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index ba9c19e6994c..952898151565 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -319,7 +319,7 @@ struct e1000_adapter {
 	u16 tx_ring_count;
 	u16 rx_ring_count;
 
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	struct delayed_work systim_overflow_work;
 	struct sk_buff *tx_hwtstamp_skb;
 	unsigned long tx_hwtstamp_start;
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 2f9655cf5dd9..364378133526 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -286,6 +286,45 @@ static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw)
 }
 
 /**
+ * e1000_reconfigure_k1_exit_timeout - reconfigure K1 exit timeout to
+ * align to MTP and later platform requirements.
+ * @hw: pointer to the HW structure
+ *
+ * Context: PHY semaphore must be held by caller.
+ * Return: 0 on success, negative on failure
+ */
+static s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw)
+{
+	u16 phy_timeout;
+	u32 fextnvm12;
+	s32 ret_val;
+
+	if (hw->mac.type < e1000_pch_mtp)
+		return 0;
+
+	/* Change Kumeran K1 power down state from P0s to P1 */
+	fextnvm12 = er32(FEXTNVM12);
+	fextnvm12 &= ~E1000_FEXTNVM12_PHYPD_CTRL_MASK;
+	fextnvm12 |= E1000_FEXTNVM12_PHYPD_CTRL_P1;
+	ew32(FEXTNVM12, fextnvm12);
+
+	/* Wait for the interface the settle */
+	usleep_range(1000, 1100);
+
+	/* Change K1 exit timeout */
+	ret_val = e1e_rphy_locked(hw, I217_PHY_TIMEOUTS_REG,
+				  &phy_timeout);
+	if (ret_val)
+		return ret_val;
+
+	phy_timeout &= ~I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK;
+	phy_timeout |= 0xF00;
+
+	return e1e_wphy_locked(hw, I217_PHY_TIMEOUTS_REG,
+				  phy_timeout);
+}
+
+/**
  *  e1000_init_phy_workarounds_pchlan - PHY initialization workarounds
  *  @hw: pointer to the HW structure
  *
@@ -327,15 +366,22 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 	 * LANPHYPC Value bit to force the interconnect to PCIe mode.
 	 */
 	switch (hw->mac.type) {
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+	case e1000_pch_nvp:
+		/* At this point the PHY might be inaccessible so don't
+		 * propagate the failure
+		 */
+		if (e1000_reconfigure_k1_exit_timeout(hw))
+			e_dbg("Failed to reconfigure K1 exit timeout\n");
+
+		fallthrough;
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
-	case e1000_pch_nvp:
 		if (e1000_phy_is_accessible_pchlan(hw))
 			break;
 
@@ -419,8 +465,20 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 		 *  the PHY is in.
 		 */
 		ret_val = hw->phy.ops.check_reset_block(hw);
-		if (ret_val)
+		if (ret_val) {
 			e_err("ME blocked access to PHY after reset\n");
+			goto out;
+		}
+
+		if (hw->mac.type >= e1000_pch_mtp) {
+			ret_val = hw->phy.ops.acquire(hw);
+			if (ret_val) {
+				e_err("Failed to reconfigure K1 exit timeout\n");
+				goto out;
+			}
+			ret_val = e1000_reconfigure_k1_exit_timeout(hw);
+			hw->phy.ops.release(hw);
+		}
 	}
 
 out:
@@ -4888,6 +4946,18 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw)
 	u16 i;
 
 	e1000_initialize_hw_bits_ich8lan(hw);
+	if (hw->mac.type >= e1000_pch_mtp) {
+		ret_val = hw->phy.ops.acquire(hw);
+		if (ret_val)
+			return ret_val;
+
+		ret_val = e1000_reconfigure_k1_exit_timeout(hw);
+		hw->phy.ops.release(hw);
+		if (ret_val) {
+			e_dbg("Error failed to reconfigure K1 exit timeout\n");
+			return ret_val;
+		}
+	}
 
 	/* Initialize identification LED */
 	ret_val = mac->ops.id_led_init(hw);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index 2504b11c3169..5feb589a9b5f 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -219,6 +219,10 @@
 #define I217_PLL_CLOCK_GATE_REG	PHY_REG(772, 28)
 #define I217_PLL_CLOCK_GATE_MASK	0x07FF
 
+/* PHY Timeouts */
+#define I217_PHY_TIMEOUTS_REG                   PHY_REG(770, 21)
+#define I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK       0x0FC0
+
 #define SW_FLAG_TIMEOUT		1000	/* SW Semaphore flag timeout in ms */
 
 /* Inband Control */
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index d7df2a0ed629..44249dd91bd6 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -331,8 +331,21 @@ void e1000e_update_mc_addr_list_generic(struct e1000_hw *hw,
 	}
 
 	/* replace the entire MTA table */
-	for (i = hw->mac.mta_reg_count - 1; i >= 0; i--)
+	for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) {
 		E1000_WRITE_REG_ARRAY(hw, E1000_MTA, i, hw->mac.mta_shadow[i]);
+
+		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			/*
+			 * Do not queue up too many posted writes to prevent
+			 * increased latency for other devices on the
+			 * interconnect. Flush after each 8th posted write,
+			 * to keep additional execution time low while still
+			 * preventing increased latency.
+			 */
+			if (!(i % 8) && i)
+				e1e_flush();
+		}
+	}
 	e1e_flush();
 }
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 286155efcedf..7719e15813ee 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3534,9 +3534,6 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
@@ -3552,6 +3549,17 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 			adapter->cc.shift = shift;
 		}
 		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		/* System firmware can misreport this value, so set it to a
+		 * stable 38400KHz frequency.
+		 */
+		incperiod = INCPERIOD_38400KHZ;
+		incvalue = INCVALUE_38400KHZ;
+		shift = INCVALUE_SHIFT_38400KHZ;
+		adapter->cc.shift = shift;
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		/* Stable 25MHz frequency */
@@ -3574,6 +3582,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
  * e1000e_config_hwtstamp - configure the hwtstamp registers and enable/disable
  * @adapter: board private structure
  * @config: timestamp configuration
+ * @extack: netlink extended ACK for error report
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -3587,7 +3596,8 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
  * exception of "all V2 events regardless of level 2 or 4".
  **/
 static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
-				  struct hwtstamp_config *config)
+				  struct kernel_hwtstamp_config *config,
+				  struct netlink_ext_ack *extack)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
@@ -3598,8 +3608,10 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	bool is_l2 = false;
 	u32 regval;
 
-	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP))
+	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP)) {
+		NL_SET_ERR_MSG(extack, "No HW timestamp support");
 		return -EINVAL;
+	}
 
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
@@ -3608,6 +3620,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	case HWTSTAMP_TX_ON:
 		break;
 	default:
+		NL_SET_ERR_MSG(extack, "Unsupported TX HW timestamp type");
 		return -ERANGE;
 	}
 
@@ -3681,6 +3694,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
+		NL_SET_ERR_MSG(extack, "Unsupported RX HW timestamp filter");
 		return -ERANGE;
 	}
 
@@ -3693,7 +3707,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	ew32(TSYNCTXCTL, regval);
 	if ((er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) !=
 	    (regval & E1000_TSYNCTXCTL_ENABLED)) {
-		e_err("Timesync Tx Control register not set as expected\n");
+		NL_SET_ERR_MSG(extack,
+			       "Timesync Tx Control register not set as expected");
 		return -EAGAIN;
 	}
 
@@ -3706,7 +3721,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 				 E1000_TSYNCRXCTL_TYPE_MASK)) !=
 	    (regval & (E1000_TSYNCRXCTL_ENABLED |
 		       E1000_TSYNCRXCTL_TYPE_MASK))) {
-		e_err("Timesync Rx Control register not set as expected\n");
+		NL_SET_ERR_MSG(extack,
+			       "Timesync Rx Control register not set as expected");
 		return -EAGAIN;
 	}
 
@@ -3901,6 +3917,7 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter)
 {
 	struct ptp_clock_info *info = &adapter->ptp_clock_info;
 	struct e1000_hw *hw = &adapter->hw;
+	struct netlink_ext_ack extack = {};
 	unsigned long flags;
 	u32 timinca;
 	s32 ret_val;
@@ -3932,7 +3949,12 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->systim_lock, flags);
 
 	/* restore the previous hwtstamp configuration settings */
-	e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config);
+	ret_val = e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config,
+					 &extack);
+	if (ret_val) {
+		if (extack._msg)
+			e_err("%s\n", extack._msg);
+	}
 }
 
 /**
@@ -4287,8 +4309,8 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset)
 
 	napi_synchronize(&adapter->napi);
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	spin_lock(&adapter->stats64_lock);
 	e1000e_update_stats(adapter);
@@ -4839,7 +4861,8 @@ static void e1000e_update_phy_task(struct work_struct *work)
  **/
 static void e1000_update_phy_info(struct timer_list *t)
 {
-	struct e1000_adapter *adapter = from_timer(adapter, t, phy_info_timer);
+	struct e1000_adapter *adapter = timer_container_of(adapter, t,
+							   phy_info_timer);
 
 	if (test_bit(__E1000_DOWN, &adapter->state))
 		return;
@@ -5175,7 +5198,8 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
  **/
 static void e1000_watchdog(struct timer_list *t)
 {
-	struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct e1000_adapter *adapter = timer_container_of(adapter, t,
+							   watchdog_timer);
 
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
@@ -6079,8 +6103,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
-static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
-			   int cmd)
+static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct mii_ioctl_data *data = if_mii(ifr);
@@ -6140,7 +6163,8 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
 /**
  * e1000e_hwtstamp_set - control hardware time stamping
  * @netdev: network interface device structure
- * @ifr: interface request
+ * @config: timestamp configuration
+ * @extack: netlink extended ACK report
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -6153,20 +6177,18 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
  * specified. Matching the kind of event packet is not supported, with the
  * exception of "all V2 events regardless of level 2 or 4".
  **/
-static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
+static int e1000e_hwtstamp_set(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config config;
 	int ret_val;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	ret_val = e1000e_config_hwtstamp(adapter, &config);
+	ret_val = e1000e_config_hwtstamp(adapter, config, extack);
 	if (ret_val)
 		return ret_val;
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -6178,38 +6200,23 @@ static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 		 * by hardware so notify the caller the requested packets plus
 		 * some others are time stamped.
 		 */
-		config.rx_filter = HWTSTAMP_FILTER_SOME;
+		config->rx_filter = HWTSTAMP_FILTER_SOME;
 		break;
 	default:
 		break;
 	}
 
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
-static int e1000e_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
+static int e1000e_hwtstamp_get(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *kernel_config)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
-	return copy_to_user(ifr->ifr_data, &adapter->hwtstamp_config,
-			    sizeof(adapter->hwtstamp_config)) ? -EFAULT : 0;
-}
+	*kernel_config = adapter->hwtstamp_config;
 
-static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	case SIOCGMIIPHY:
-	case SIOCGMIIREG:
-	case SIOCSMIIREG:
-		return e1000_mii_ioctl(netdev, ifr, cmd);
-	case SIOCSHWTSTAMP:
-		return e1000e_hwtstamp_set(netdev, ifr);
-	case SIOCGHWTSTAMP:
-		return e1000e_hwtstamp_get(netdev, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	return 0;
 }
 
 static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc)
@@ -7346,9 +7353,11 @@ static const struct net_device_ops e1000e_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= e1000_netpoll,
 #endif
-	.ndo_set_features = e1000_set_features,
-	.ndo_fix_features = e1000_fix_features,
+	.ndo_set_features	= e1000_set_features,
+	.ndo_fix_features	= e1000_fix_features,
 	.ndo_features_check	= passthru_features_check,
+	.ndo_hwtstamp_get	= e1000e_hwtstamp_get,
+	.ndo_hwtstamp_set	= e1000e_hwtstamp_set,
 };
 
 /**
@@ -7741,8 +7750,8 @@ static void e1000_remove(struct pci_dev *pdev)
 	 * from being rescheduled.
 	 */
 	set_bit(__E1000_DOWN, &adapter->state);
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 89d57dd911dc..ea3c3eb2ef20 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -295,15 +295,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
 			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
 		else
 			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
 		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 92de609b7218..ae5fe34659cf 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -199,8 +199,8 @@ static void fm10k_start_service_event(struct fm10k_intfc *interface)
  **/
 static void fm10k_service_timer(struct timer_list *t)
 {
-	struct fm10k_intfc *interface = from_timer(interface, t,
-						   service_timer);
+	struct fm10k_intfc *interface = timer_container_of(interface, t,
+							   service_timer);
 
 	/* Reset the timer */
 	mod_timer(&interface->service_timer, (HZ * 2) + jiffies);
@@ -2245,7 +2245,7 @@ static void fm10k_remove(struct pci_dev *pdev)
 	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
 	struct net_device *netdev = interface->netdev;
 
-	del_timer_sync(&interface->service_timer);
+	timer_delete_sync(&interface->service_timer);
 
 	fm10k_stop_service_event(interface);
 	fm10k_stop_macvlan_task(interface);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index 98861cc6df7c..b9dd7b719832 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1180,126 +1180,6 @@ s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid)
 }
 
 /**
- *  fm10k_iov_msg_mac_vlan_pf - Message handler for MAC/VLAN request from VF
- *  @hw: Pointer to hardware structure
- *  @results: Pointer array to message, results[0] is pointer to message
- *  @mbx: Pointer to mailbox information structure
- *
- *  This function is a default handler for MAC/VLAN requests from the VF.
- *  The assumption is that in this case it is acceptable to just directly
- *  hand off the message from the VF to the underlying shared code.
- **/
-s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results,
-			      struct fm10k_mbx_info *mbx)
-{
-	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
-	u8 mac[ETH_ALEN];
-	u32 *result;
-	int err = 0;
-	bool set;
-	u16 vlan;
-	u32 vid;
-
-	/* we shouldn't be updating rules on a disabled interface */
-	if (!FM10K_VF_FLAG_ENABLED(vf_info))
-		err = FM10K_ERR_PARAM;
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) {
-		result = results[FM10K_MAC_VLAN_MSG_VLAN];
-
-		/* record VLAN id requested */
-		err = fm10k_tlv_attr_get_u32(result, &vid);
-		if (err)
-			return err;
-
-		set = !(vid & FM10K_VLAN_CLEAR);
-		vid &= ~FM10K_VLAN_CLEAR;
-
-		/* if the length field has been set, this is a multi-bit
-		 * update request. For multi-bit requests, simply disallow
-		 * them when the pf_vid has been set. In this case, the PF
-		 * should have already cleared the VLAN_TABLE, and if we
-		 * allowed them, it could allow a rogue VF to receive traffic
-		 * on a VLAN it was not assigned. In the single-bit case, we
-		 * need to modify requests for VLAN 0 to use the default PF or
-		 * SW vid when assigned.
-		 */
-
-		if (vid >> 16) {
-			/* prevent multi-bit requests when PF has
-			 * administratively set the VLAN for this VF
-			 */
-			if (vf_info->pf_vid)
-				return FM10K_ERR_PARAM;
-		} else {
-			err = fm10k_iov_select_vid(vf_info, (u16)vid);
-			if (err < 0)
-				return err;
-
-			vid = err;
-		}
-
-		/* update VSI info for VF in regards to VLAN table */
-		err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set);
-	}
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) {
-		result = results[FM10K_MAC_VLAN_MSG_MAC];
-
-		/* record unicast MAC address requested */
-		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
-		if (err)
-			return err;
-
-		/* block attempts to set MAC for a locked device */
-		if (is_valid_ether_addr(vf_info->mac) &&
-		    !ether_addr_equal(mac, vf_info->mac))
-			return FM10K_ERR_PARAM;
-
-		set = !(vlan & FM10K_VLAN_CLEAR);
-		vlan &= ~FM10K_VLAN_CLEAR;
-
-		err = fm10k_iov_select_vid(vf_info, vlan);
-		if (err < 0)
-			return err;
-
-		vlan = (u16)err;
-
-		/* notify switch of request for new unicast address */
-		err = hw->mac.ops.update_uc_addr(hw, vf_info->glort,
-						 mac, vlan, set, 0);
-	}
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) {
-		result = results[FM10K_MAC_VLAN_MSG_MULTICAST];
-
-		/* record multicast MAC address requested */
-		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
-		if (err)
-			return err;
-
-		/* verify that the VF is allowed to request multicast */
-		if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED))
-			return FM10K_ERR_PARAM;
-
-		set = !(vlan & FM10K_VLAN_CLEAR);
-		vlan &= ~FM10K_VLAN_CLEAR;
-
-		err = fm10k_iov_select_vid(vf_info, vlan);
-		if (err < 0)
-			return err;
-
-		vlan = (u16)err;
-
-		/* notify switch of request for new multicast address */
-		err = hw->mac.ops.update_mc_addr(hw, vf_info->glort,
-						 mac, vlan, set);
-	}
-
-	return err;
-}
-
-/**
  *  fm10k_iov_supported_xcast_mode_pf - Determine best match for xcast mode
  *  @vf_info: VF info structure containing capability flags
  *  @mode: Requested xcast mode
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
index 8e814df709d2..ad3696893cb1 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
@@ -99,8 +99,6 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[];
 
 s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid);
 s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
-s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **,
-			      struct fm10k_mbx_info *);
 s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *, u32 **,
 				 struct fm10k_mbx_info *);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d4255c2706fa..c67963bfe14e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -88,6 +88,7 @@ enum i40e_state {
 	__I40E_SERVICE_SCHED,
 	__I40E_ADMINQ_EVENT_PENDING,
 	__I40E_MDD_EVENT_PENDING,
+	__I40E_MDD_VF_PRINT_PENDING,
 	__I40E_VFLR_EVENT_PENDING,
 	__I40E_RESET_RECOVERY_PENDING,
 	__I40E_TIMEOUT_RECOVERY_PENDING,
@@ -191,6 +192,7 @@ enum i40e_pf_flags {
 	 */
 	I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA,
 	I40E_FLAG_VF_VLAN_PRUNING_ENA,
+	I40E_FLAG_MDD_AUTO_RESET_VF,
 	I40E_PF_FLAGS_NBITS,		/* must be last */
 };
 
@@ -572,7 +574,7 @@ struct i40e_pf {
 	int num_alloc_vfs;	/* actual number of VFs allocated */
 	u32 vf_aq_requests;
 	u32 arq_overflows;	/* Not fatal, possibly indicative of problems */
-
+	struct ratelimit_state mdd_message_rate_limit;
 	/* DCBx/DCBNL capability for PF that indicates
 	 * whether DCBx is managed by firmware or host
 	 * based agent (LLDPAD). Also, indicates what
@@ -1189,7 +1191,6 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 		      struct i40e_fdir_filter *input, bool add);
 void i40e_fdir_check_and_reenable(struct i40e_pf *pf);
 u32 i40e_get_current_fd_count(struct i40e_pf *pf);
-u32 i40e_get_cur_guaranteed_fd_count(struct i40e_pf *pf);
 u32 i40e_get_current_atr_cnt(struct i40e_pf *pf);
 u32 i40e_get_global_fd_count(struct i40e_pf *pf);
 bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features);
@@ -1197,7 +1198,6 @@ void i40e_set_ethtool_ops(struct net_device *netdev);
 struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
 					const u8 *macaddr, s16 vlan);
 void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f);
-void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan);
 int i40e_sync_vsi_filters(struct i40e_vsi *vsi);
 struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 				u16 uplink, u32 param1);
@@ -1313,7 +1313,6 @@ int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset);
 int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
 int i40e_get_partition_bw_setting(struct i40e_pf *pf);
 int i40e_set_partition_bw_setting(struct i40e_pf *pf);
-int i40e_commit_partition_bw_setting(struct i40e_pf *pf);
 void i40e_print_link_message(struct i40e_vsi *vsi, bool isup);
 
 void i40e_set_fec_in_flags(u8 fec_cfg, unsigned long *flags);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index f73f5930fc58..175c1320c143 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -1016,16 +1016,6 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw,
 	return status;
 }
 
-int
-i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc,
-			 void *buff, /* can be NULL */ u16  buff_size,
-			 struct i40e_asq_cmd_details *cmd_details,
-			 enum i40e_admin_queue_err *aq_status)
-{
-	return i40e_asq_send_command_atomic_v2(hw, desc, buff, buff_size,
-					       cmd_details, true, aq_status);
-}
-
 /**
  *  i40e_fill_default_direct_cmd_desc - AQ descriptor helper function
  *  @desc:     pointer to the temp descriptor (non DMA mem)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index e8031f1a9b4f..b11c35e307ca 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -817,10 +817,11 @@ int i40e_pf_reset(struct i40e_hw *hw)
 void i40e_clear_hw(struct i40e_hw *hw)
 {
 	u32 num_queues, base_queue;
-	u32 num_pf_int;
-	u32 num_vf_int;
+	s32 num_pf_int;
+	s32 num_vf_int;
 	u32 num_vfs;
-	u32 i, j;
+	s32 i;
+	u32 j;
 	u32 val;
 	u32 eol = 0x7ff;
 
@@ -1805,37 +1806,6 @@ int i40e_aq_set_vsi_broadcast(struct i40e_hw *hw,
 }
 
 /**
- * i40e_aq_set_vsi_vlan_promisc - control the VLAN promiscuous setting
- * @hw: pointer to the hw struct
- * @seid: vsi number
- * @enable: set MAC L2 layer unicast promiscuous enable/disable for a given VLAN
- * @cmd_details: pointer to command details structure or NULL
- **/
-int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw,
-				 u16 seid, bool enable,
-				 struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
-	u16 flags = 0;
-	int status;
-
-	i40e_fill_default_direct_cmd_desc(&desc,
-					i40e_aqc_opc_set_vsi_promiscuous_modes);
-	if (enable)
-		flags |= I40E_AQC_SET_VSI_PROMISC_VLAN;
-
-	cmd->promiscuous_flags = cpu_to_le16(flags);
-	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_VLAN);
-	cmd->seid = cpu_to_le16(seid);
-
-	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
-	return status;
-}
-
-/**
  * i40e_aq_get_vsi_params - get VSI configuration info
  * @hw: pointer to the hw struct
  * @vsi_ctx: pointer to a vsi context struct
@@ -2436,136 +2406,6 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 }
 
 /**
- * i40e_mirrorrule_op - Internal helper function to add/delete mirror rule
- * @hw: pointer to the hw struct
- * @opcode: AQ opcode for add or delete mirror rule
- * @sw_seid: Switch SEID (to which rule refers)
- * @rule_type: Rule Type (ingress/egress/VLAN)
- * @id: Destination VSI SEID or Rule ID
- * @count: length of the list
- * @mr_list: list of mirrored VSI SEIDs or VLAN IDs
- * @cmd_details: pointer to command details structure or NULL
- * @rule_id: Rule ID returned from FW
- * @rules_used: Number of rules used in internal switch
- * @rules_free: Number of rules free in internal switch
- *
- * Add/Delete a mirror rule to a specific switch. Mirror rules are supported for
- * VEBs/VEPA elements only
- **/
-static int i40e_mirrorrule_op(struct i40e_hw *hw,
-			      u16 opcode, u16 sw_seid, u16 rule_type, u16 id,
-			      u16 count, __le16 *mr_list,
-			      struct i40e_asq_cmd_details *cmd_details,
-			      u16 *rule_id, u16 *rules_used, u16 *rules_free)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_delete_mirror_rule *cmd =
-		(struct i40e_aqc_add_delete_mirror_rule *)&desc.params.raw;
-	struct i40e_aqc_add_delete_mirror_rule_completion *resp =
-	(struct i40e_aqc_add_delete_mirror_rule_completion *)&desc.params.raw;
-	u16 buf_size;
-	int status;
-
-	buf_size = count * sizeof(*mr_list);
-
-	/* prep the rest of the request */
-	i40e_fill_default_direct_cmd_desc(&desc, opcode);
-	cmd->seid = cpu_to_le16(sw_seid);
-	cmd->rule_type = cpu_to_le16(rule_type &
-				     I40E_AQC_MIRROR_RULE_TYPE_MASK);
-	cmd->num_entries = cpu_to_le16(count);
-	/* Dest VSI for add, rule_id for delete */
-	cmd->destination = cpu_to_le16(id);
-	if (mr_list) {
-		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
-						I40E_AQ_FLAG_RD));
-		if (buf_size > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
-	}
-
-	status = i40e_asq_send_command(hw, &desc, mr_list, buf_size,
-				       cmd_details);
-	if (!status ||
-	    hw->aq.asq_last_status == I40E_AQ_RC_ENOSPC) {
-		if (rule_id)
-			*rule_id = le16_to_cpu(resp->rule_id);
-		if (rules_used)
-			*rules_used = le16_to_cpu(resp->mirror_rules_used);
-		if (rules_free)
-			*rules_free = le16_to_cpu(resp->mirror_rules_free);
-	}
-	return status;
-}
-
-/**
- * i40e_aq_add_mirrorrule - add a mirror rule
- * @hw: pointer to the hw struct
- * @sw_seid: Switch SEID (to which rule refers)
- * @rule_type: Rule Type (ingress/egress/VLAN)
- * @dest_vsi: SEID of VSI to which packets will be mirrored
- * @count: length of the list
- * @mr_list: list of mirrored VSI SEIDs or VLAN IDs
- * @cmd_details: pointer to command details structure or NULL
- * @rule_id: Rule ID returned from FW
- * @rules_used: Number of rules used in internal switch
- * @rules_free: Number of rules free in internal switch
- *
- * Add mirror rule. Mirror rules are supported for VEBs or VEPA elements only
- **/
-int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
-			   u16 rule_type, u16 dest_vsi, u16 count,
-			   __le16 *mr_list,
-			   struct i40e_asq_cmd_details *cmd_details,
-			   u16 *rule_id, u16 *rules_used, u16 *rules_free)
-{
-	if (!(rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS ||
-	    rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS)) {
-		if (count == 0 || !mr_list)
-			return -EINVAL;
-	}
-
-	return i40e_mirrorrule_op(hw, i40e_aqc_opc_add_mirror_rule, sw_seid,
-				  rule_type, dest_vsi, count, mr_list,
-				  cmd_details, rule_id, rules_used, rules_free);
-}
-
-/**
- * i40e_aq_delete_mirrorrule - delete a mirror rule
- * @hw: pointer to the hw struct
- * @sw_seid: Switch SEID (to which rule refers)
- * @rule_type: Rule Type (ingress/egress/VLAN)
- * @count: length of the list
- * @rule_id: Rule ID that is returned in the receive desc as part of
- *		add_mirrorrule.
- * @mr_list: list of mirrored VLAN IDs to be removed
- * @cmd_details: pointer to command details structure or NULL
- * @rules_used: Number of rules used in internal switch
- * @rules_free: Number of rules free in internal switch
- *
- * Delete a mirror rule. Mirror rules are supported for VEBs/VEPA elements only
- **/
-int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
-			      u16 rule_type, u16 rule_id, u16 count,
-			      __le16 *mr_list,
-			      struct i40e_asq_cmd_details *cmd_details,
-			      u16 *rules_used, u16 *rules_free)
-{
-	/* Rule ID has to be valid except rule_type: INGRESS VLAN mirroring */
-	if (rule_type == I40E_AQC_MIRROR_RULE_TYPE_VLAN) {
-		/* count and mr_list shall be valid for rule_type INGRESS VLAN
-		 * mirroring. For other rule_type, count and rule_type should
-		 * not matter.
-		 */
-		if (count == 0 || !mr_list)
-			return -EINVAL;
-	}
-
-	return i40e_mirrorrule_op(hw, i40e_aqc_opc_delete_mirror_rule, sw_seid,
-				  rule_type, rule_id, count, mr_list,
-				  cmd_details, NULL, rules_used, rules_free);
-}
-
-/**
  * i40e_aq_send_msg_to_vf
  * @hw: pointer to the hardware structure
  * @vfid: VF id to send msg
@@ -3180,41 +3020,6 @@ i40e_aq_update_nvm_exit:
 }
 
 /**
- * i40e_aq_rearrange_nvm
- * @hw: pointer to the hw struct
- * @rearrange_nvm: defines direction of rearrangement
- * @cmd_details: pointer to command details structure or NULL
- *
- * Rearrange NVM structure, available only for transition FW
- **/
-int i40e_aq_rearrange_nvm(struct i40e_hw *hw,
-			  u8 rearrange_nvm,
-			  struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aqc_nvm_update *cmd;
-	struct i40e_aq_desc desc;
-	int status;
-
-	cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw;
-
-	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_update);
-
-	rearrange_nvm &= (I40E_AQ_NVM_REARRANGE_TO_FLAT |
-			 I40E_AQ_NVM_REARRANGE_TO_STRUCT);
-
-	if (!rearrange_nvm) {
-		status = -EINVAL;
-		goto i40e_aq_rearrange_nvm_exit;
-	}
-
-	cmd->command_flags |= rearrange_nvm;
-	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
-i40e_aq_rearrange_nvm_exit:
-	return status;
-}
-
-/**
  * i40e_aq_get_lldp_mib
  * @hw: pointer to the hw struct
  * @bridge_type: type of bridge requested
@@ -3335,44 +3140,6 @@ int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
 }
 
 /**
- * i40e_aq_restore_lldp
- * @hw: pointer to the hw struct
- * @setting: pointer to factory setting variable or NULL
- * @restore: True if factory settings should be restored
- * @cmd_details: pointer to command details structure or NULL
- *
- * Restore LLDP Agent factory settings if @restore set to True. In other case
- * only returns factory setting in AQ response.
- **/
-int
-i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
-		     struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_restore *cmd =
-		(struct i40e_aqc_lldp_restore *)&desc.params.raw;
-	int status;
-
-	if (!test_bit(I40E_HW_CAP_FW_LLDP_PERSISTENT, hw->caps)) {
-		i40e_debug(hw, I40E_DEBUG_ALL,
-			   "Restore LLDP not supported by current FW version.\n");
-		return -ENODEV;
-	}
-
-	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_restore);
-
-	if (restore)
-		cmd->command |= I40E_AQ_LLDP_AGENT_RESTORE;
-
-	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
-	if (setting)
-		*setting = cmd->command & 1;
-
-	return status;
-}
-
-/**
  * i40e_aq_stop_lldp
  * @hw: pointer to the hw struct
  * @shutdown_agent: True if LLDP Agent needs to be Shutdown
@@ -4570,84 +4337,6 @@ phy_write_end:
 }
 
 /**
- * i40e_write_phy_register
- * @hw: pointer to the HW structure
- * @page: registers page number
- * @reg: register address in the page
- * @phy_addr: PHY address on MDIO interface
- * @value: PHY register value
- *
- * Writes value to specified PHY register
- **/
-int i40e_write_phy_register(struct i40e_hw *hw,
-			    u8 page, u16 reg, u8 phy_addr, u16 value)
-{
-	int status;
-
-	switch (hw->device_id) {
-	case I40E_DEV_ID_1G_BASE_T_X722:
-		status = i40e_write_phy_register_clause22(hw, reg, phy_addr,
-							  value);
-		break;
-	case I40E_DEV_ID_1G_BASE_T_BC:
-	case I40E_DEV_ID_5G_BASE_T_BC:
-	case I40E_DEV_ID_10G_BASE_T:
-	case I40E_DEV_ID_10G_BASE_T4:
-	case I40E_DEV_ID_10G_BASE_T_BC:
-	case I40E_DEV_ID_10G_BASE_T_X722:
-	case I40E_DEV_ID_25G_B:
-	case I40E_DEV_ID_25G_SFP28:
-		status = i40e_write_phy_register_clause45(hw, page, reg,
-							  phy_addr, value);
-		break;
-	default:
-		status = -EIO;
-		break;
-	}
-
-	return status;
-}
-
-/**
- * i40e_read_phy_register
- * @hw: pointer to the HW structure
- * @page: registers page number
- * @reg: register address in the page
- * @phy_addr: PHY address on MDIO interface
- * @value: PHY register value
- *
- * Reads specified PHY register value
- **/
-int i40e_read_phy_register(struct i40e_hw *hw,
-			   u8 page, u16 reg, u8 phy_addr, u16 *value)
-{
-	int status;
-
-	switch (hw->device_id) {
-	case I40E_DEV_ID_1G_BASE_T_X722:
-		status = i40e_read_phy_register_clause22(hw, reg, phy_addr,
-							 value);
-		break;
-	case I40E_DEV_ID_1G_BASE_T_BC:
-	case I40E_DEV_ID_5G_BASE_T_BC:
-	case I40E_DEV_ID_10G_BASE_T:
-	case I40E_DEV_ID_10G_BASE_T4:
-	case I40E_DEV_ID_10G_BASE_T_BC:
-	case I40E_DEV_ID_10G_BASE_T_X722:
-	case I40E_DEV_ID_25G_B:
-	case I40E_DEV_ID_25G_SFP28:
-		status = i40e_read_phy_register_clause45(hw, page, reg,
-							 phy_addr, value);
-		break;
-	default:
-		status = -EIO;
-		break;
-	}
-
-	return status;
-}
-
-/**
  * i40e_get_phy_address
  * @hw: pointer to the HW structure
  * @dev_num: PHY port num that address we want
@@ -4663,80 +4352,6 @@ u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num)
 }
 
 /**
- * i40e_blink_phy_link_led
- * @hw: pointer to the HW structure
- * @time: time how long led will blinks in secs
- * @interval: gap between LED on and off in msecs
- *
- * Blinks PHY link LED
- **/
-int i40e_blink_phy_link_led(struct i40e_hw *hw,
-			    u32 time, u32 interval)
-{
-	u16 led_addr = I40E_PHY_LED_PROV_REG_1;
-	u16 gpio_led_port;
-	u8 phy_addr = 0;
-	int status = 0;
-	u16 led_ctl;
-	u8 port_num;
-	u16 led_reg;
-	u32 i;
-
-	i = rd32(hw, I40E_PFGEN_PORTNUM);
-	port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
-	phy_addr = i40e_get_phy_address(hw, port_num);
-
-	for (gpio_led_port = 0; gpio_led_port < 3; gpio_led_port++,
-	     led_addr++) {
-		status = i40e_read_phy_register_clause45(hw,
-							 I40E_PHY_COM_REG_PAGE,
-							 led_addr, phy_addr,
-							 &led_reg);
-		if (status)
-			goto phy_blinking_end;
-		led_ctl = led_reg;
-		if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) {
-			led_reg = 0;
-			status = i40e_write_phy_register_clause45(hw,
-							 I40E_PHY_COM_REG_PAGE,
-							 led_addr, phy_addr,
-							 led_reg);
-			if (status)
-				goto phy_blinking_end;
-			break;
-		}
-	}
-
-	if (time > 0 && interval > 0) {
-		for (i = 0; i < time * 1000; i += interval) {
-			status = i40e_read_phy_register_clause45(hw,
-						I40E_PHY_COM_REG_PAGE,
-						led_addr, phy_addr, &led_reg);
-			if (status)
-				goto restore_config;
-			if (led_reg & I40E_PHY_LED_MANUAL_ON)
-				led_reg = 0;
-			else
-				led_reg = I40E_PHY_LED_MANUAL_ON;
-			status = i40e_write_phy_register_clause45(hw,
-						I40E_PHY_COM_REG_PAGE,
-						led_addr, phy_addr, led_reg);
-			if (status)
-				goto restore_config;
-			msleep(interval);
-		}
-	}
-
-restore_config:
-	status = i40e_write_phy_register_clause45(hw,
-						  I40E_PHY_COM_REG_PAGE,
-						  led_addr, phy_addr, led_ctl);
-
-phy_blinking_end:
-	return status;
-}
-
-/**
  * i40e_led_get_reg - read LED register
  * @hw: pointer to the HW structure
  * @led_addr: LED register address
@@ -5269,39 +4884,6 @@ i40e_find_segment_in_package(u32 segment_type,
 	(struct i40e_profile_section_header *)((u8 *)(profile) + (offset))
 
 /**
- * i40e_find_section_in_profile
- * @section_type: the section type to search for (i.e., SECTION_TYPE_NOTE)
- * @profile: pointer to the i40e segment header to be searched
- *
- * This function searches i40e segment for a particular section type. On
- * success it returns a pointer to the section header, otherwise it will
- * return NULL.
- **/
-struct i40e_profile_section_header *
-i40e_find_section_in_profile(u32 section_type,
-			     struct i40e_profile_segment *profile)
-{
-	struct i40e_profile_section_header *sec;
-	struct i40e_section_table *sec_tbl;
-	u32 sec_off;
-	u32 i;
-
-	if (profile->header.type != SEGMENT_TYPE_I40E)
-		return NULL;
-
-	I40E_SECTION_TABLE(profile, sec_tbl);
-
-	for (i = 0; i < sec_tbl->section_count; i++) {
-		sec_off = sec_tbl->section_offset[i];
-		sec = I40E_SECTION_HEADER(profile, sec_off);
-		if (sec->section.type == section_type)
-			return sec;
-	}
-
-	return NULL;
-}
-
-/**
  * i40e_ddp_exec_aq_section - Execute generic AQ for DDP
  * @hw: pointer to the hw struct
  * @aq: command buffer containing all data to execute AQ
@@ -5524,45 +5106,6 @@ i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
 }
 
 /**
- * i40e_add_pinfo_to_list
- * @hw: pointer to the hardware structure
- * @profile: pointer to the profile segment of the package
- * @profile_info_sec: buffer for information section
- * @track_id: package tracking id
- *
- * Register a profile to the list of loaded profiles.
- */
-int
-i40e_add_pinfo_to_list(struct i40e_hw *hw,
-		       struct i40e_profile_segment *profile,
-		       u8 *profile_info_sec, u32 track_id)
-{
-	struct i40e_profile_section_header *sec = NULL;
-	struct i40e_profile_info *pinfo;
-	u32 offset = 0, info = 0;
-	int status = 0;
-
-	sec = (struct i40e_profile_section_header *)profile_info_sec;
-	sec->tbl_size = 1;
-	sec->data_end = sizeof(struct i40e_profile_section_header) +
-			sizeof(struct i40e_profile_info);
-	sec->section.type = SECTION_TYPE_INFO;
-	sec->section.offset = sizeof(struct i40e_profile_section_header);
-	sec->section.size = sizeof(struct i40e_profile_info);
-	pinfo = (struct i40e_profile_info *)(profile_info_sec +
-					     sec->section.offset);
-	pinfo->track_id = track_id;
-	pinfo->version = profile->version;
-	pinfo->op = I40E_DDP_ADD_TRACKID;
-	memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
-
-	status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end,
-				   track_id, &offset, &info, NULL);
-
-	return status;
-}
-
-/**
  * i40e_aq_add_cloud_filters
  * @hw: pointer to the hardware structure
  * @seid: VSI seid to add cloud filters from
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 8db1eb0c1768..352e957443fd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -1491,19 +1491,6 @@ void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc)
 }
 
 /**
- * i40e_dcb_hw_get_num_tc
- * @hw: pointer to the hw struct
- *
- * Returns number of traffic classes configured in HW
- **/
-u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw)
-{
-	u32 reg = rd32(hw, I40E_PRTDCB_GENC);
-
-	return FIELD_GET(I40E_PRTDCB_GENC_NUMTC_MASK, reg);
-}
-
-/**
  * i40e_dcb_hw_rx_ets_bw_config
  * @hw: pointer to the hw struct
  * @bw_share: Bandwidth share indexed per traffic class
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index d76497566e40..d5662c639c41 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -253,7 +253,6 @@ void i40e_dcb_hw_rx_cmd_monitor_config(struct i40e_hw *hw,
 void i40e_dcb_hw_pfc_config(struct i40e_hw *hw,
 			    u8 pfc_en, u8 *prio_tc);
 void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc);
-u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw);
 void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share,
 				  u8 *mode, u8 *prio_type);
 void i40e_dcb_hw_rx_up2tc_config(struct i40e_hw *hw, u8 *prio_tc);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 208c2f0857b6..6cd9da662ae1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -722,7 +722,7 @@ static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id)
 		dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n",
 			 vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs);
 		dev_info(&pf->pdev->dev, "       num MDD=%lld\n",
-			 vf->num_mdd_events);
+			 vf->mdd_tx_events.count + vf->mdd_rx_events.count);
 	} else {
 		dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id);
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index bce5b76f1e7a..8a7a83f83ee5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -459,6 +459,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
 	I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0),
 	I40E_PRIV_FLAG("vf-vlan-pruning",
 		       I40E_FLAG_VF_VLAN_PRUNING_ENA, 0),
+	I40E_PRIV_FLAG("mdd-auto-reset-vf",
+		       I40E_FLAG_MDD_AUTO_RESET_VF, 0),
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ab5febf83ec3..f1c9e575703e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -99,7 +99,7 @@ module_param(debug, uint, 0);
 MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX)");
 
 MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver");
-MODULE_IMPORT_NS(LIBIE);
+MODULE_IMPORT_NS("LIBIE");
 MODULE_LICENSE("GPL v2");
 
 static struct workqueue_struct *i40e_wq;
@@ -1666,9 +1666,8 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
  * @vsi: VSI to remove from
  * @f: the filter to remove from the list
  *
- * This function should be called instead of i40e_del_filter only if you know
- * the exact filter you will remove already, such as via i40e_find_filter or
- * i40e_find_mac.
+ * This function requires you've found * the exact filter you will remove
+ * already, such as via i40e_find_filter or i40e_find_mac.
  *
  * NOTE: This function is expected to be called with mac_filter_hash_lock
  * being held.
@@ -1698,29 +1697,6 @@ void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f)
 }
 
 /**
- * i40e_del_filter - Remove a MAC/VLAN filter from the VSI
- * @vsi: the VSI to be searched
- * @macaddr: the MAC address
- * @vlan: the VLAN
- *
- * NOTE: This function is expected to be called with mac_filter_hash_lock
- * being held.
- * ANOTHER NOTE: This function MUST be called from within the context of
- * the "safe" variants of any list iterators, e.g. list_for_each_entry_safe()
- * instead of list_for_each_entry().
- **/
-void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan)
-{
-	struct i40e_mac_filter *f;
-
-	if (!vsi || !macaddr)
-		return;
-
-	f = i40e_find_filter(vsi, macaddr, vlan);
-	__i40e_del_filter(vsi, f);
-}
-
-/**
  * i40e_add_mac_filter - Add a MAC filter for all active VLANs
  * @vsi: the VSI to be searched
  * @macaddr: the mac address to be filtered
@@ -9629,19 +9605,6 @@ static void i40e_handle_lan_overflow_event(struct i40e_pf *pf,
 }
 
 /**
- * i40e_get_cur_guaranteed_fd_count - Get the consumed guaranteed FD filters
- * @pf: board private structure
- **/
-u32 i40e_get_cur_guaranteed_fd_count(struct i40e_pf *pf)
-{
-	u32 val, fcnt_prog;
-
-	val = rd32(&pf->hw, I40E_PFQF_FDSTAT);
-	fcnt_prog = (val & I40E_PFQF_FDSTAT_GUARANT_CNT_MASK);
-	return fcnt_prog;
-}
-
-/**
  * i40e_get_current_fd_count - Get total FD filters programmed for this PF
  * @pf: board private structure
  **/
@@ -11217,6 +11180,67 @@ static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired)
 }
 
 /**
+ * i40e_print_vf_mdd_event - print VF Tx/Rx malicious driver detect event
+ * @pf: board private structure
+ * @vf: pointer to the VF structure
+ * @is_tx: true - for Tx event, false - for  Rx
+ */
+static void i40e_print_vf_mdd_event(struct i40e_pf *pf, struct i40e_vf *vf,
+				    bool is_tx)
+{
+	dev_err(&pf->pdev->dev, is_tx ?
+		"%lld Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n" :
+		"%lld Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n",
+		is_tx ? vf->mdd_tx_events.count : vf->mdd_rx_events.count,
+		pf->hw.pf_id,
+		vf->vf_id,
+		vf->default_lan_addr.addr,
+		str_on_off(test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)));
+}
+
+/**
+ * i40e_print_vfs_mdd_events - print VFs malicious driver detect event
+ * @pf: pointer to the PF structure
+ *
+ * Called from i40e_handle_mdd_event to rate limit and print VFs MDD events.
+ */
+static void i40e_print_vfs_mdd_events(struct i40e_pf *pf)
+{
+	unsigned int i;
+
+	/* check that there are pending MDD events to print */
+	if (!test_and_clear_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state))
+		return;
+
+	if (!__ratelimit(&pf->mdd_message_rate_limit))
+		return;
+
+	for (i = 0; i < pf->num_alloc_vfs; i++) {
+		struct i40e_vf *vf = &pf->vf[i];
+		bool is_printed = false;
+
+		/* only print Rx MDD event message if there are new events */
+		if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) {
+			vf->mdd_rx_events.last_printed = vf->mdd_rx_events.count;
+			i40e_print_vf_mdd_event(pf, vf, false);
+			is_printed = true;
+		}
+
+		/* only print Tx MDD event message if there are new events */
+		if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) {
+			vf->mdd_tx_events.last_printed = vf->mdd_tx_events.count;
+			i40e_print_vf_mdd_event(pf, vf, true);
+			is_printed = true;
+		}
+
+		if (is_printed && !test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags))
+			dev_info(&pf->pdev->dev,
+				 "Use PF Control I/F to re-enable the VF #%d\n",
+				 i);
+	}
+}
+
+/**
  * i40e_handle_mdd_event
  * @pf: pointer to the PF structure
  *
@@ -11230,8 +11254,13 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	u32 reg;
 	int i;
 
-	if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state))
+	if (!test_and_clear_bit(__I40E_MDD_EVENT_PENDING, pf->state)) {
+		/* Since the VF MDD event logging is rate limited, check if
+		 * there are pending MDD events.
+		 */
+		i40e_print_vfs_mdd_events(pf);
 		return;
+	}
 
 	/* find what triggered the MDD event */
 	reg = rd32(hw, I40E_GL_MDET_TX);
@@ -11275,36 +11304,48 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 
 	/* see if one of the VFs needs its hand slapped */
 	for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) {
+		bool is_mdd_on_tx = false;
+		bool is_mdd_on_rx = false;
+
 		vf = &(pf->vf[i]);
 		reg = rd32(hw, I40E_VP_MDET_TX(i));
 		if (reg & I40E_VP_MDET_TX_VALID_MASK) {
+			set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state);
 			wr32(hw, I40E_VP_MDET_TX(i), 0xFFFF);
-			vf->num_mdd_events++;
-			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
-				 i);
-			dev_info(&pf->pdev->dev,
-				 "Use PF Control I/F to re-enable the VF\n");
+			vf->mdd_tx_events.count++;
 			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
+			is_mdd_on_tx = true;
 		}
 
 		reg = rd32(hw, I40E_VP_MDET_RX(i));
 		if (reg & I40E_VP_MDET_RX_VALID_MASK) {
+			set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state);
 			wr32(hw, I40E_VP_MDET_RX(i), 0xFFFF);
-			vf->num_mdd_events++;
-			dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
-				 i);
-			dev_info(&pf->pdev->dev,
-				 "Use PF Control I/F to re-enable the VF\n");
+			vf->mdd_rx_events.count++;
 			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
+			is_mdd_on_rx = true;
+		}
+
+		if ((is_mdd_on_tx || is_mdd_on_rx) &&
+		    test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) {
+			/* VF MDD event counters will be cleared by
+			 * reset, so print the event prior to reset.
+			 */
+			if (is_mdd_on_rx)
+				i40e_print_vf_mdd_event(pf, vf, false);
+			if (is_mdd_on_tx)
+				i40e_print_vf_mdd_event(pf, vf, true);
+
+			i40e_vc_reset_vf(vf, true);
 		}
 	}
 
-	/* re-enable mdd interrupt cause */
-	clear_bit(__I40E_MDD_EVENT_PENDING, pf->state);
 	reg = rd32(hw, I40E_PFINT_ICR0_ENA);
 	reg |=  I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
 	wr32(hw, I40E_PFINT_ICR0_ENA, reg);
 	i40e_flush(hw);
+
+	i40e_print_vfs_mdd_events(pf);
 }
 
 /**
@@ -11371,7 +11412,7 @@ static void i40e_service_task(struct work_struct *work)
  **/
 static void i40e_service_timer(struct timer_list *t)
 {
-	struct i40e_pf *pf = from_timer(pf, t, service_timer);
+	struct i40e_pf *pf = timer_container_of(pf, t, service_timer);
 
 	mod_timer(&pf->service_timer,
 		  round_jiffies(jiffies + pf->service_timer_period));
@@ -12614,89 +12655,6 @@ int i40e_set_partition_bw_setting(struct i40e_pf *pf)
 }
 
 /**
- * i40e_commit_partition_bw_setting - Commit BW settings for this PF partition
- * @pf: board private structure
- **/
-int i40e_commit_partition_bw_setting(struct i40e_pf *pf)
-{
-	/* Commit temporary BW setting to permanent NVM image */
-	enum i40e_admin_queue_err last_aq_status;
-	u16 nvm_word;
-	int ret;
-
-	if (pf->hw.partition_id != 1) {
-		dev_info(&pf->pdev->dev,
-			 "Commit BW only works on partition 1! This is partition %d",
-			 pf->hw.partition_id);
-		ret = -EOPNOTSUPP;
-		goto bw_commit_out;
-	}
-
-	/* Acquire NVM for read access */
-	ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_READ);
-	last_aq_status = pf->hw.aq.asq_last_status;
-	if (ret) {
-		dev_info(&pf->pdev->dev,
-			 "Cannot acquire NVM for read access, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, last_aq_status));
-		goto bw_commit_out;
-	}
-
-	/* Read word 0x10 of NVM - SW compatibility word 1 */
-	ret = i40e_aq_read_nvm(&pf->hw,
-			       I40E_SR_NVM_CONTROL_WORD,
-			       0x10, sizeof(nvm_word), &nvm_word,
-			       false, NULL);
-	/* Save off last admin queue command status before releasing
-	 * the NVM
-	 */
-	last_aq_status = pf->hw.aq.asq_last_status;
-	i40e_release_nvm(&pf->hw);
-	if (ret) {
-		dev_info(&pf->pdev->dev, "NVM read error, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, last_aq_status));
-		goto bw_commit_out;
-	}
-
-	/* Wait a bit for NVM release to complete */
-	msleep(50);
-
-	/* Acquire NVM for write access */
-	ret = i40e_acquire_nvm(&pf->hw, I40E_RESOURCE_WRITE);
-	last_aq_status = pf->hw.aq.asq_last_status;
-	if (ret) {
-		dev_info(&pf->pdev->dev,
-			 "Cannot acquire NVM for write access, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, last_aq_status));
-		goto bw_commit_out;
-	}
-	/* Write it back out unchanged to initiate update NVM,
-	 * which will force a write of the shadow (alt) RAM to
-	 * the NVM - thus storing the bandwidth values permanently.
-	 */
-	ret = i40e_aq_update_nvm(&pf->hw,
-				 I40E_SR_NVM_CONTROL_WORD,
-				 0x10, sizeof(nvm_word),
-				 &nvm_word, true, 0, NULL);
-	/* Save off last admin queue command status before releasing
-	 * the NVM
-	 */
-	last_aq_status = pf->hw.aq.asq_last_status;
-	i40e_release_nvm(&pf->hw);
-	if (ret)
-		dev_info(&pf->pdev->dev,
-			 "BW settings NOT SAVED, err %pe aq_err %s\n",
-			 ERR_PTR(ret),
-			 i40e_aq_str(&pf->hw, last_aq_status));
-bw_commit_out:
-
-	return ret;
-}
-
-/**
  * i40e_is_total_port_shutdown_enabled - read NVM and return value
  * if total port shutdown feature is enabled for this PF
  * @pf: board private structure
@@ -15998,6 +15956,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			 ERR_PTR(err),
 			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 
+	/* VF MDD event logs are rate limited to one second intervals */
+	ratelimit_state_init(&pf->mdd_message_rate_limit, 1 * HZ, 1);
+
 	/* Reconfigure hardware for allowing smaller MSS in the case
 	 * of TSO, so that we avoid the MDD being fired and causing
 	 * a reset in the case of small MSS+TSO.
@@ -16421,7 +16382,7 @@ static int i40e_io_suspend(struct i40e_pf *pf)
 	set_bit(__I40E_DOWN, pf->state);
 
 	/* Ensure service task will not be running */
-	del_timer_sync(&pf->service_timer);
+	timer_delete_sync(&pf->service_timer);
 	cancel_work_sync(&pf->service_task);
 
 	/* Client close must be called explicitly here because the timer
@@ -16620,7 +16581,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	set_bit(__I40E_SUSPENDED, pf->state);
 	set_bit(__I40E_DOWN, pf->state);
 
-	del_timer_sync(&pf->service_timer);
+	timer_delete_sync(&pf->service_timer);
 	cancel_work_sync(&pf->service_task);
 	i40e_cloud_filter_exit(pf);
 	i40e_fdir_teardown(pf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 5a0699ca7ce5..099bb8ab7d70 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -27,13 +27,6 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc,
 		      void *buff, /* can be NULL */ u16  buff_size,
 		      struct i40e_asq_cmd_details *cmd_details);
 int
-i40e_asq_send_command_v2(struct i40e_hw *hw,
-			 struct i40e_aq_desc *desc,
-			 void *buff, /* can be NULL */
-			 u16  buff_size,
-			 struct i40e_asq_cmd_details *cmd_details,
-			 enum i40e_admin_queue_err *aq_status);
-int
 i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc,
 			     void *buff, /* can be NULL */ u16  buff_size,
 			     struct i40e_asq_cmd_details *cmd_details,
@@ -72,8 +65,6 @@ int i40e_led_set_phy(struct i40e_hw *hw, bool on,
 		     u16 led_addr, u32 mode);
 int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr,
 		     u16 *val);
-int i40e_blink_phy_link_led(struct i40e_hw *hw,
-			    u32 time, u32 interval);
 
 /* admin send queue commands */
 
@@ -141,9 +132,6 @@ int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw,
 int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw,
 				       u16 seid, bool enable, u16 vid,
 				       struct i40e_asq_cmd_details *cmd_details);
-int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw,
-				 u16 seid, bool enable,
-				 struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_get_vsi_params(struct i40e_hw *hw,
 			   struct i40e_vsi_context *vsi_ctx,
 			   struct i40e_asq_cmd_details *cmd_details);
@@ -176,14 +164,6 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_remove_macvlan_element_data *mv_list,
 			  u16 count, struct i40e_asq_cmd_details *cmd_details,
 			  enum i40e_admin_queue_err *aq_status);
-int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
-			   u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list,
-			   struct i40e_asq_cmd_details *cmd_details,
-			   u16 *rule_id, u16 *rules_used, u16 *rules_free);
-int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
-			      u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list,
-			      struct i40e_asq_cmd_details *cmd_details,
-			      u16 *rules_used, u16 *rules_free);
 
 int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid,
 			   u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen,
@@ -220,9 +200,6 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 		       u32 offset, u16 length, void *data,
 		       bool last_command, u8 preservation_flags,
 		       struct i40e_asq_cmd_details *cmd_details);
-int i40e_aq_rearrange_nvm(struct i40e_hw *hw,
-			  u8 rearrange_nvm,
-			  struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 			 u8 mib_type, void *buff, u16 buff_size,
 			 u16 *local_len, u16 *remote_len,
@@ -234,9 +211,6 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw,
 int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
 				      bool enable_update,
 				      struct i40e_asq_cmd_details *cmd_details);
-int
-i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
-		     struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 		      bool persist,
 		      struct i40e_asq_cmd_details *cmd_details);
@@ -458,13 +432,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw,
 				    u8 page, u16 reg, u8 phy_addr, u16 *value);
 int i40e_write_phy_register_clause45(struct i40e_hw *hw,
 				     u8 page, u16 reg, u8 phy_addr, u16 value);
-int i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
-			   u8 phy_addr, u16 *value);
-int i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
-			    u8 phy_addr, u16 value);
 u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num);
-int i40e_blink_phy_link_led(struct i40e_hw *hw,
-			    u32 time, u32 interval);
 int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff,
 		      u16 buff_size, u32 track_id,
 		      u32 *error_offset, u32 *error_info,
@@ -477,20 +445,12 @@ int i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff,
 struct i40e_generic_seg_header *
 i40e_find_segment_in_package(u32 segment_type,
 			     struct i40e_package_header *pkg_header);
-struct i40e_profile_section_header *
-i40e_find_section_in_profile(u32 section_type,
-			     struct i40e_profile_segment *profile);
 int
 i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
 		   u32 track_id);
 int
 i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
 		      u32 track_id);
-int
-i40e_add_pinfo_to_list(struct i40e_hw *hw,
-		       struct i40e_profile_segment *profile,
-		       u8 *profile_info_sec, u32 track_id);
-
 /* i40e_ddp */
 int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index dfa785e39458..88e6bef69342 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -216,7 +216,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
  * @notify_vf: notify vf about reset or not
  * Reset VF handler.
  **/
-static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf)
+void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf)
 {
 	struct i40e_pf *pf = vf->pf;
 	int i;
@@ -1546,8 +1546,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
  * @vf: pointer to the VF structure
  * @flr: VFLR was issued or not
  *
- * Returns true if the VF is in reset, resets successfully, or resets
- * are disabled and false otherwise.
+ * Return: True if reset was performed successfully or if resets are disabled.
+ * False if reset is already in progress.
  **/
 bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 {
@@ -1566,7 +1566,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 
 	/* If VF is being reset already we don't need to continue. */
 	if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
-		return true;
+		return false;
 
 	i40e_trigger_vf_reset(vf, flr);
 
@@ -4328,7 +4328,10 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
 		reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx));
 		if (reg & BIT(bit_idx))
 			/* i40e_reset_vf will clear the bit in GLGEN_VFLRSTAT */
-			i40e_reset_vf(vf, true);
+			if (!i40e_reset_vf(vf, true)) {
+				/* At least one VF did not finish resetting, retry next time */
+				set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
+			}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 66f95e2f3146..5cf74f16f433 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -64,6 +64,12 @@ struct i40evf_channel {
 	u64 max_tx_rate; /* bandwidth rate allocation for VSIs */
 };
 
+struct i40e_mdd_vf_events {
+	u64 count;      /* total count of Rx|Tx events */
+	/* count number of the last printed event */
+	u64 last_printed;
+};
+
 /* VF information structure */
 struct i40e_vf {
 	struct i40e_pf *pf;
@@ -92,7 +98,9 @@ struct i40e_vf {
 
 	u8 num_queue_pairs;	/* num of qps assigned to VF vsis */
 	u8 num_req_queues;	/* num of requested qps */
-	u64 num_mdd_events;	/* num of mdd events detected */
+	/* num of mdd tx and rx events detected */
+	struct i40e_mdd_vf_events mdd_rx_events;
+	struct i40e_mdd_vf_events mdd_tx_events;
 
 	unsigned long vf_caps;	/* vf's adv. capabilities */
 	unsigned long vf_states;	/* vf's runtime states */
@@ -120,6 +128,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs);
 int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 			   u32 v_retval, u8 *msg, u16 msglen);
 int i40e_vc_process_vflr_event(struct i40e_pf *pf);
+void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf);
 bool i40e_reset_vf(struct i40e_vf *vf, bool flr);
 bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr);
 void i40e_vc_notify_vf_reset(struct i40e_vf *vf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 4e885df789ef..9f47388eaba5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
 #include <net/xdp_sock_drv.h>
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
@@ -395,32 +396,6 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 	WARN_ON_ONCE(1);
 }
 
-static int
-i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first,
-		  struct xdp_buff *xdp, const unsigned int size)
-{
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first);
-
-	if (!xdp_buff_has_frags(first)) {
-		sinfo->nr_frags = 0;
-		sinfo->xdp_frags_size = 0;
-		xdp_buff_set_frags_flag(first);
-	}
-
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		xsk_buff_free(first);
-		return -ENOMEM;
-	}
-
-	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start),
-				   XDP_PACKET_HEADROOM, size);
-	sinfo->xdp_frags_size += size;
-	xsk_buff_add_frag(xdp);
-
-	return 0;
-}
-
 /**
  * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
  * @rx_ring: Rx ring
@@ -486,8 +461,10 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 
 		if (!first)
 			first = bi;
-		else if (i40e_add_xsk_frag(rx_ring, first, bi, size))
+		else if (!xsk_buff_add_frag(first, bi)) {
+			xsk_buff_free(first);
 			break;
+		}
 
 		if (++next_to_process == count)
 			next_to_process = 0;
@@ -553,7 +530,8 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des
 	dma_addr_t dma;
 	u32 i;
 
-	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+	unrolled_count(PKTS_PER_BATCH)
+	for (i = 0; i < PKTS_PER_BATCH; i++) {
 		u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]);
 
 		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index ef156fad52f2..dd16351a7af8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -6,7 +6,7 @@
 
 #include <linux/types.h>
 
-/* This value should match the pragma in the loop_unrolled_for
+/* This value should match the pragma in the unrolled_count()
  * macro. Why 4? It is strictly empirical. It seems to be a good
  * compromise between the advantage of having simultaneous outstanding
  * reads to the DMA array that can hide each others latency and the
@@ -14,14 +14,6 @@
  */
 #define PKTS_PER_BATCH 4
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 4") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct i40e_ring;
 struct i40e_vsi;
 struct net_device;
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile
index 356ac9faa5bf..e13720a728ff 100644
--- a/drivers/net/ethernet/intel/iavf/Makefile
+++ b/drivers/net/ethernet/intel/iavf/Makefile
@@ -13,3 +13,5 @@ obj-$(CONFIG_IAVF) += iavf.o
 
 iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \
 	  iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o
+
+iavf-$(CONFIG_PTP_1588_CLOCK) += iavf_ptp.o
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 532a0a595fe8..f7a98ff43a57 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -41,6 +41,7 @@
 #include "iavf_txrx.h"
 #include "iavf_fdir.h"
 #include "iavf_adv_rss.h"
+#include "iavf_types.h"
 #include <linux/bitmap.h>
 
 #define DEFAULT_DEBUG_LEVEL_SHIFT 3
@@ -82,7 +83,7 @@ struct iavf_vsi {
 
 #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
 
-#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i]))
+#define IAVF_RX_DESC(R, i) (&(((struct iavf_rx_desc *)((R)->desc))[i]))
 #define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i]))
 #define IAVF_TX_CTXTDESC(R, i) \
 	(&(((struct iavf_tx_context_desc *)((R)->desc))[i]))
@@ -267,10 +268,10 @@ struct iavf_adapter {
 	struct list_head vlan_filter_list;
 	int num_vlan_filters;
 	struct list_head mac_filter_list;
-	struct mutex crit_lock;
 	/* Lock to protect accesses to MAC and VLAN lists */
 	spinlock_t mac_vlan_list_lock;
 	char misc_vector_name[IFNAMSIZ + 9];
+	u8 rxdid;
 	int num_active_queues;
 	int num_req_queues;
 
@@ -343,6 +344,17 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW		BIT_ULL(39)
 #define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE		BIT_ULL(40)
 #define IAVF_FLAG_AQ_GET_QOS_CAPS			BIT_ULL(41)
+#define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS		BIT_ULL(42)
+#define IAVF_FLAG_AQ_GET_PTP_CAPS			BIT_ULL(43)
+#define IAVF_FLAG_AQ_SEND_PTP_CMD			BIT_ULL(44)
+
+	/* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in
+	 * order to negotiated extended capabilities.
+	 */
+#define IAVF_FLAG_AQ_EXTENDED_CAPS			\
+	(IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS |	\
+	 IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS |		\
+	 IAVF_FLAG_AQ_GET_PTP_CAPS)
 
 	/* flags for processing extended capability messages during
 	 * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires
@@ -354,10 +366,18 @@ struct iavf_adapter {
 	u64 extended_caps;
 #define IAVF_EXTENDED_CAP_SEND_VLAN_V2			BIT_ULL(0)
 #define IAVF_EXTENDED_CAP_RECV_VLAN_V2			BIT_ULL(1)
+#define IAVF_EXTENDED_CAP_SEND_RXDID			BIT_ULL(2)
+#define IAVF_EXTENDED_CAP_RECV_RXDID			BIT_ULL(3)
+#define IAVF_EXTENDED_CAP_SEND_PTP			BIT_ULL(4)
+#define IAVF_EXTENDED_CAP_RECV_PTP			BIT_ULL(5)
 
 #define IAVF_EXTENDED_CAPS				\
 	(IAVF_EXTENDED_CAP_SEND_VLAN_V2 |		\
-	 IAVF_EXTENDED_CAP_RECV_VLAN_V2)
+	 IAVF_EXTENDED_CAP_RECV_VLAN_V2 |		\
+	 IAVF_EXTENDED_CAP_SEND_RXDID |			\
+	 IAVF_EXTENDED_CAP_RECV_RXDID |			\
+	 IAVF_EXTENDED_CAP_SEND_PTP |			\
+	 IAVF_EXTENDED_CAP_RECV_PTP)
 
 	/* Lock to prevent possible clobbering of
 	 * current_netdev_promisc_flags
@@ -417,12 +437,18 @@ struct iavf_adapter {
 			     VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF)
 #define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
 			 VIRTCHNL_VF_OFFLOAD_QOS)
+#define IAVF_RXDID_ALLOWED(a)						\
+	((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
+#define IAVF_PTP_ALLOWED(a)						\
+	((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP)
 	struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
 	struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
 	struct virtchnl_version_info pf_version;
 #define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \
 		       ((_a)->pf_version.minor == 1))
 	struct virtchnl_vlan_caps vlan_v2_caps;
+	u64 supp_rxdids;
+	struct iavf_ptp ptp;
 	u16 msg_enable;
 	struct iavf_eth_stats current_stats;
 	struct virtchnl_qos_cap_list *qos_caps;
@@ -555,6 +581,10 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter);
 int iavf_get_vf_config(struct iavf_adapter *adapter);
 int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter);
 int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter);
+int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter);
+int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter);
 void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter);
 u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter);
 void iavf_irq_enable(struct iavf_adapter *adapter, bool flush);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 74a1e9fe1821..2b2b315205b5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -4,6 +4,8 @@
 #include <linux/bitfield.h>
 #include <linux/uaccess.h>
 
+#include <net/netdev_lock.h>
+
 /* ethtool support for iavf */
 #include "iavf.h"
 
@@ -1256,9 +1258,10 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 {
 	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
 	struct iavf_fdir_fltr *fltr;
-	int count = 50;
 	int err;
 
+	netdev_assert_locked(adapter->netdev);
+
 	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
@@ -1277,14 +1280,6 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (!fltr)
 		return -ENOMEM;
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(fltr);
-			return -EINVAL;
-		}
-		udelay(1);
-	}
-
 	err = iavf_add_fdir_fltr_info(adapter, fsp, fltr);
 	if (!err)
 		err = iavf_fdir_add_fltr(adapter, fltr);
@@ -1292,7 +1287,6 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (err)
 		kfree(fltr);
 
-	mutex_unlock(&adapter->crit_lock);
 	return err;
 }
 
@@ -1435,11 +1429,13 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 {
 	struct iavf_adv_rss *rss_old, *rss_new;
 	bool rss_new_add = false;
-	int count = 50, err = 0;
 	bool symm = false;
 	u64 hash_flds;
+	int err = 0;
 	u32 hdrs;
 
+	netdev_assert_locked(adapter->netdev);
+
 	if (!ADV_RSS_SUPPORT(adapter))
 		return -EOPNOTSUPP;
 
@@ -1463,15 +1459,6 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 		return -EINVAL;
 	}
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(rss_new);
-			return -EINVAL;
-		}
-
-		udelay(1);
-	}
-
 	spin_lock_bh(&adapter->adv_rss_lock);
 	rss_old = iavf_find_adv_rss_cfg_by_hdrs(adapter, hdrs);
 	if (rss_old) {
@@ -1500,8 +1487,6 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	if (!err)
 		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_ADV_RSS_CFG);
 
-	mutex_unlock(&adapter->crit_lock);
-
 	if (!rss_new_add)
 		kfree(rss_new);
 
@@ -1808,7 +1793,7 @@ static int iavf_set_rxfh(struct net_device *netdev,
 static const struct ethtool_ops iavf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
-	.cap_rss_sym_xor_supported = true,
+	.supported_input_xfrm	= RXH_XFRM_SYM_XOR,
 	.get_drvinfo		= iavf_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= iavf_get_ringparam,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 12ef160425aa..81d7249d1149 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2,8 +2,10 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/net/intel/libie/rx.h>
+#include <net/netdev_lock.h>
 
 #include "iavf.h"
+#include "iavf_ptp.h"
 #include "iavf_prototype.h"
 /* All iavf tracepoints are defined by the include below, which must
  * be included exactly once across the whole kernel with
@@ -46,8 +48,8 @@ MODULE_DEVICE_TABLE(pci, iavf_pci_tbl);
 
 MODULE_ALIAS("i40evf");
 MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver");
-MODULE_IMPORT_NS(LIBETH);
-MODULE_IMPORT_NS(LIBIE);
+MODULE_IMPORT_NS("LIBETH");
+MODULE_IMPORT_NS("LIBIE");
 MODULE_LICENSE("GPL v2");
 
 static const struct net_device_ops iavf_netdev_ops;
@@ -710,6 +712,47 @@ static void iavf_configure_tx(struct iavf_adapter *adapter)
 }
 
 /**
+ * iavf_select_rx_desc_format - Select Rx descriptor format
+ * @adapter: adapter private structure
+ *
+ * Select what Rx descriptor format based on availability and enabled
+ * features.
+ *
+ * Return: the desired RXDID to select for a given Rx queue, as defined by
+ *         enum virtchnl_rxdid_format.
+ */
+static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter)
+{
+	u64 rxdids = adapter->supp_rxdids;
+
+	/* If we did not negotiate VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, we must
+	 * stick with the default value of the legacy 32 byte format.
+	 */
+	if (!IAVF_RXDID_ALLOWED(adapter))
+		return VIRTCHNL_RXDID_1_32B_BASE;
+
+	/* Rx timestamping requires the use of flexible NIC descriptors */
+	if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) {
+		if (rxdids & BIT(VIRTCHNL_RXDID_2_FLEX_SQ_NIC))
+			return VIRTCHNL_RXDID_2_FLEX_SQ_NIC;
+
+		pci_warn(adapter->pdev,
+			 "Unable to negotiate flexible descriptor format\n");
+	}
+
+	/* Warn if the PF does not list support for the default legacy
+	 * descriptor format. This shouldn't happen, as this is the format
+	 * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is
+	 * likely caused by a bug in the PF implementation failing to indicate
+	 * support for the format.
+	 */
+	if (!(rxdids & VIRTCHNL_RXDID_1_32B_BASE_M))
+		netdev_warn(adapter->netdev, "PF does not list support for default Rx descriptor format\n");
+
+	return VIRTCHNL_RXDID_1_32B_BASE;
+}
+
+/**
  * iavf_configure_rx - Configure Receive Unit after Reset
  * @adapter: board private structure
  *
@@ -719,8 +762,12 @@ static void iavf_configure_rx(struct iavf_adapter *adapter)
 {
 	struct iavf_hw *hw = &adapter->hw;
 
-	for (u32 i = 0; i < adapter->num_active_queues; i++)
+	adapter->rxdid = iavf_select_rx_desc_format(adapter);
+
+	for (u32 i = 0; i < adapter->num_active_queues; i++) {
 		adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i);
+		adapter->rx_rings[i].rxdid = adapter->rxdid;
+	}
 }
 
 /**
@@ -773,6 +820,11 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter,
 		f->state = IAVF_VLAN_ADD;
 		adapter->num_vlan_filters++;
 		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER);
+	} else if (f->state == IAVF_VLAN_REMOVE) {
+		/* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed.
+		 * We can safely only change the state here.
+		 */
+		f->state = IAVF_VLAN_ACTIVE;
 	}
 
 clearout:
@@ -793,8 +845,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan)
 
 	f = iavf_find_vlan(adapter, vlan);
 	if (f) {
-		f->state = IAVF_VLAN_REMOVE;
-		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER);
+		/* IAVF_ADD_VLAN means that VLAN wasn't even added yet.
+		 * Remove it from the list.
+		 */
+		if (f->state == IAVF_VLAN_ADD) {
+			list_del(&f->list);
+			kfree(f);
+			adapter->num_vlan_filters--;
+		} else {
+			f->state = IAVF_VLAN_REMOVE;
+			iavf_schedule_aq_request(adapter,
+						 IAVF_FLAG_AQ_DEL_VLAN_FILTER);
+		}
 	}
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
@@ -1180,7 +1242,7 @@ static void iavf_napi_enable_all(struct iavf_adapter *adapter)
 
 		q_vector = &adapter->q_vectors[q_idx];
 		napi = &q_vector->napi;
-		napi_enable(napi);
+		napi_enable_locked(napi);
 	}
 }
 
@@ -1196,7 +1258,7 @@ static void iavf_napi_disable_all(struct iavf_adapter *adapter)
 
 	for (q_idx = 0; q_idx < q_vectors; q_idx++) {
 		q_vector = &adapter->q_vectors[q_idx];
-		napi_disable(&q_vector->napi);
+		napi_disable_locked(&q_vector->napi);
 	}
 }
 
@@ -1225,11 +1287,11 @@ static void iavf_configure(struct iavf_adapter *adapter)
 /**
  * iavf_up_complete - Finish the last steps of bringing up a connection
  * @adapter: board private structure
- *
- * Expects to be called while holding crit_lock.
- **/
+ */
 static void iavf_up_complete(struct iavf_adapter *adapter)
 {
+	netdev_assert_locked(adapter->netdev);
+
 	iavf_change_state(adapter, __IAVF_RUNNING);
 	clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
 
@@ -1348,13 +1410,13 @@ static void iavf_clear_adv_rss_conf(struct iavf_adapter *adapter)
 /**
  * iavf_down - Shutdown the connection processing
  * @adapter: board private structure
- *
- * Expects to be called while holding crit_lock.
- **/
+ */
 void iavf_down(struct iavf_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 
+	netdev_assert_locked(netdev);
+
 	if (adapter->state <= __IAVF_DOWN_PENDING)
 		return;
 
@@ -1800,8 +1862,8 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter)
 		q_vector->v_idx = q_idx;
 		q_vector->reg_idx = q_idx;
 		cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask);
-		netif_napi_add(adapter->netdev, &q_vector->napi,
-			       iavf_napi_poll);
+		netif_napi_add_locked(adapter->netdev, &q_vector->napi,
+				      iavf_napi_poll);
 	}
 
 	return 0;
@@ -1827,7 +1889,7 @@ static void iavf_free_q_vectors(struct iavf_adapter *adapter)
 	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
 		struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx];
 
-		netif_napi_del(&q_vector->napi);
+		netif_napi_del_locked(&q_vector->napi);
 	}
 	kfree(adapter->q_vectors);
 	adapter->q_vectors = NULL;
@@ -1963,21 +2025,21 @@ err:
  * iavf_finish_config - do all netdev work that needs RTNL
  * @work: our work_struct
  *
- * Do work that needs both RTNL and crit_lock.
- **/
+ * Do work that needs RTNL.
+ */
 static void iavf_finish_config(struct work_struct *work)
 {
 	struct iavf_adapter *adapter;
+	bool netdev_released = false;
 	int pairs, err;
 
 	adapter = container_of(work, struct iavf_adapter, finish_config);
 
 	/* Always take RTNL first to prevent circular lock dependency;
-	 * The dev->lock is needed to update the queue number
+	 * the dev->lock (== netdev lock) is needed to update the queue number.
 	 */
 	rtnl_lock();
-	mutex_lock(&adapter->netdev->lock);
-	mutex_lock(&adapter->crit_lock);
+	netdev_lock(adapter->netdev);
 
 	if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) &&
 	    adapter->netdev->reg_state == NETREG_REGISTERED &&
@@ -1988,26 +2050,33 @@ static void iavf_finish_config(struct work_struct *work)
 
 	switch (adapter->state) {
 	case __IAVF_DOWN:
+		/* Set the real number of queues when reset occurs while
+		 * state == __IAVF_DOWN
+		 */
+		pairs = adapter->num_active_queues;
+		netif_set_real_num_rx_queues(adapter->netdev, pairs);
+		netif_set_real_num_tx_queues(adapter->netdev, pairs);
+
 		if (adapter->netdev->reg_state != NETREG_REGISTERED) {
+			netdev_unlock(adapter->netdev);
+			netdev_released = true;
 			err = register_netdevice(adapter->netdev);
 			if (err) {
 				dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n",
 					err);
 
 				/* go back and try again.*/
+				netdev_lock(adapter->netdev);
 				iavf_free_rss(adapter);
 				iavf_free_misc_irq(adapter);
 				iavf_reset_interrupt_capability(adapter);
 				iavf_change_state(adapter,
 						  __IAVF_INIT_CONFIG_ADAPTER);
+				netdev_unlock(adapter->netdev);
 				goto out;
 			}
 		}
-
-		/* Set the real number of queues when reset occurs while
-		 * state == __IAVF_DOWN
-		 */
-		fallthrough;
+		break;
 	case __IAVF_RUNNING:
 		pairs = adapter->num_active_queues;
 		netif_set_real_num_rx_queues(adapter->netdev, pairs);
@@ -2019,8 +2088,8 @@ static void iavf_finish_config(struct work_struct *work)
 	}
 
 out:
-	mutex_unlock(&adapter->crit_lock);
-	mutex_unlock(&adapter->netdev->lock);
+	if (!netdev_released)
+		netdev_unlock(adapter->netdev);
 	rtnl_unlock();
 }
 
@@ -2049,6 +2118,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		return iavf_send_vf_config_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS)
 		return iavf_send_vf_offload_vlan_v2_msg(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS)
+		return iavf_send_vf_supported_rxdids_msg(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_PTP_CAPS)
+		return iavf_send_vf_ptp_caps_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) {
 		iavf_disable_queues(adapter);
 		return 0;
@@ -2213,7 +2286,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021AD);
 		return 0;
 	}
-
+	if (adapter->aq_required & IAVF_FLAG_AQ_SEND_PTP_CMD) {
+		iavf_virtchnl_send_ptp_cmd(adapter);
+		return IAVF_SUCCESS;
+	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) {
 		iavf_request_stats(adapter);
 		return 0;
@@ -2578,6 +2654,112 @@ err:
 }
 
 /**
+ * iavf_init_send_supported_rxdids - part of querying for supported RXDID
+ * formats
+ * @adapter: board private structure
+ *
+ * Function processes send of the request for supported RXDIDs to the PF.
+ * Must clear IAVF_EXTENDED_CAP_RECV_RXDID if the message is not sent, e.g.
+ * due to the PF not negotiating VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC.
+ */
+static void iavf_init_send_supported_rxdids(struct iavf_adapter *adapter)
+{
+	int ret;
+
+	ret = iavf_send_vf_supported_rxdids_msg(adapter);
+	if (ret == -EOPNOTSUPP) {
+		/* PF does not support VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. In this
+		 * case, we did not send the capability exchange message and
+		 * do not expect a response.
+		 */
+		adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID;
+	}
+
+	/* We sent the message, so move on to the next step */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_RXDID;
+}
+
+/**
+ * iavf_init_recv_supported_rxdids - part of querying for supported RXDID
+ * formats
+ * @adapter: board private structure
+ *
+ * Function processes receipt of the supported RXDIDs message from the PF.
+ **/
+static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter)
+{
+	int ret;
+
+	memset(&adapter->supp_rxdids, 0, sizeof(adapter->supp_rxdids));
+
+	ret = iavf_get_vf_supported_rxdids(adapter);
+	if (ret)
+		goto err;
+
+	/* We've processed the PF response to the
+	 * VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message we sent previously.
+	 */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID;
+	return;
+
+err:
+	/* We didn't receive a reply. Make sure we try sending again when
+	 * __IAVF_INIT_FAILED attempts to recover.
+	 */
+	adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_RXDID;
+	iavf_change_state(adapter, __IAVF_INIT_FAILED);
+}
+
+/**
+ * iavf_init_send_ptp_caps - part of querying for extended PTP capabilities
+ * @adapter: board private structure
+ *
+ * Function processes send of the request for 1588 PTP capabilities to the PF.
+ * Must clear IAVF_EXTENDED_CAP_SEND_PTP if the message is not sent, e.g.
+ * due to the PF not negotiating VIRTCHNL_VF_PTP_CAP
+ */
+static void iavf_init_send_ptp_caps(struct iavf_adapter *adapter)
+{
+	if (iavf_send_vf_ptp_caps_msg(adapter) == -EOPNOTSUPP) {
+		/* PF does not support VIRTCHNL_VF_PTP_CAP. In this case, we
+		 * did not send the capability exchange message and do not
+		 * expect a response.
+		 */
+		adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP;
+	}
+
+	/* We sent the message, so move on to the next step */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_PTP;
+}
+
+/**
+ * iavf_init_recv_ptp_caps - part of querying for supported PTP capabilities
+ * @adapter: board private structure
+ *
+ * Function processes receipt of the PTP capabilities supported on this VF.
+ **/
+static void iavf_init_recv_ptp_caps(struct iavf_adapter *adapter)
+{
+	memset(&adapter->ptp.hw_caps, 0, sizeof(adapter->ptp.hw_caps));
+
+	if (iavf_get_vf_ptp_caps(adapter))
+		goto err;
+
+	/* We've processed the PF response to the VIRTCHNL_OP_1588_PTP_GET_CAPS
+	 * message we sent previously.
+	 */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP;
+	return;
+
+err:
+	/* We didn't receive a reply. Make sure we try sending again when
+	 * __IAVF_INIT_FAILED attempts to recover.
+	 */
+	adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_PTP;
+	iavf_change_state(adapter, __IAVF_INIT_FAILED);
+}
+
+/**
  * iavf_init_process_extended_caps - Part of driver startup
  * @adapter: board private structure
  *
@@ -2601,6 +2783,24 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter)
 		return;
 	}
 
+	/* Process capability exchange for RXDID formats */
+	if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_RXDID) {
+		iavf_init_send_supported_rxdids(adapter);
+		return;
+	} else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_RXDID) {
+		iavf_init_recv_supported_rxdids(adapter);
+		return;
+	}
+
+	/* Process capability exchange for PTP features */
+	if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_PTP) {
+		iavf_init_send_ptp_caps(adapter);
+		return;
+	} else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_PTP) {
+		iavf_init_recv_ptp_caps(adapter);
+		return;
+	}
+
 	/* When we reach here, no further extended capabilities exchanges are
 	 * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER
 	 */
@@ -2692,6 +2892,9 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 	if (QOS_ALLOWED(adapter))
 		adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS;
 
+	/* Setup initial PTP configuration */
+	iavf_ptp_init(adapter);
+
 	iavf_schedule_finish_config(adapter);
 	return;
 
@@ -2704,24 +2907,15 @@ err:
 	iavf_change_state(adapter, __IAVF_INIT_FAILED);
 }
 
-/**
- * iavf_watchdog_task - Periodic call-back task
- * @work: pointer to work_struct
- **/
-static void iavf_watchdog_task(struct work_struct *work)
+static const int IAVF_NO_RESCHED = -1;
+
+/* return: msec delay for requeueing itself */
+static int iavf_watchdog_step(struct iavf_adapter *adapter)
 {
-	struct iavf_adapter *adapter = container_of(work,
-						    struct iavf_adapter,
-						    watchdog_task.work);
 	struct iavf_hw *hw = &adapter->hw;
 	u32 reg_val;
 
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state == __IAVF_REMOVE)
-			return;
-
-		goto restart_watchdog;
-	}
+	netdev_assert_locked(adapter->netdev);
 
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
 		iavf_change_state(adapter, __IAVF_COMM_FAILED);
@@ -2729,34 +2923,19 @@ static void iavf_watchdog_task(struct work_struct *work)
 	switch (adapter->state) {
 	case __IAVF_STARTUP:
 		iavf_startup(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(30));
-		return;
+		return 30;
 	case __IAVF_INIT_VERSION_CHECK:
 		iavf_init_version_check(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(30));
-		return;
+		return 30;
 	case __IAVF_INIT_GET_RESOURCES:
 		iavf_init_get_resources(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_EXTENDED_CAPS:
 		iavf_init_process_extended_caps(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_CONFIG_ADAPTER:
 		iavf_init_config_adapter(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_FAILED:
 		if (test_bit(__IAVF_IN_REMOVE_TASK,
 			     &adapter->crit_section)) {
@@ -2764,24 +2943,18 @@ static void iavf_watchdog_task(struct work_struct *work)
 			 * watchdog task, iavf_remove should handle this state
 			 * as it can loop forever
 			 */
-			mutex_unlock(&adapter->crit_lock);
-			return;
+			return IAVF_NO_RESCHED;
 		}
 		if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) {
 			dev_err(&adapter->pdev->dev,
 				"Failed to communicate with PF; waiting before retry\n");
 			adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 			iavf_shutdown_adminq(hw);
-			mutex_unlock(&adapter->crit_lock);
-			queue_delayed_work(adapter->wq,
-					   &adapter->watchdog_task, (5 * HZ));
-			return;
+			return 5000;
 		}
 		/* Try again from failed step*/
 		iavf_change_state(adapter, adapter->last_state);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ);
-		return;
+		return 1000;
 	case __IAVF_COMM_FAILED:
 		if (test_bit(__IAVF_IN_REMOVE_TASK,
 			     &adapter->crit_section)) {
@@ -2791,8 +2964,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 			 */
 			iavf_change_state(adapter, __IAVF_INIT_FAILED);
 			adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
-			mutex_unlock(&adapter->crit_lock);
-			return;
+			return IAVF_NO_RESCHED;
 		}
 		reg_val = rd32(hw, IAVF_VFGEN_RSTAT) &
 			  IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
@@ -2810,16 +2982,9 @@ static void iavf_watchdog_task(struct work_struct *work)
 		}
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq,
-				   &adapter->watchdog_task,
-				   msecs_to_jiffies(10));
-		return;
+		return 10;
 	case __IAVF_RESETTING:
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   HZ * 2);
-		return;
+		return 2000;
 	case __IAVF_DOWN:
 	case __IAVF_DOWN_PENDING:
 	case __IAVF_TESTING:
@@ -2846,8 +3011,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 		break;
 	case __IAVF_REMOVE:
 	default:
-		mutex_unlock(&adapter->crit_lock);
-		return;
+		return IAVF_NO_RESCHED;
 	}
 
 	/* check for hw reset */
@@ -2857,22 +3021,29 @@ static void iavf_watchdog_task(struct work_struct *work)
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
 		dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
 		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING);
-		mutex_unlock(&adapter->crit_lock);
-		queue_delayed_work(adapter->wq,
-				   &adapter->watchdog_task, HZ * 2);
-		return;
 	}
 
-	mutex_unlock(&adapter->crit_lock);
-restart_watchdog:
+	return adapter->aq_required ? 20 : 2000;
+}
+
+static void iavf_watchdog_task(struct work_struct *work)
+{
+	struct iavf_adapter *adapter = container_of(work,
+						    struct iavf_adapter,
+						    watchdog_task.work);
+	struct net_device *netdev = adapter->netdev;
+	int msec_delay;
+
+	netdev_lock(netdev);
+	msec_delay = iavf_watchdog_step(adapter);
+	/* note that we schedule a different task */
 	if (adapter->state >= __IAVF_DOWN)
 		queue_work(adapter->wq, &adapter->adminq_task);
-	if (adapter->aq_required)
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(20));
-	else
+
+	if (msec_delay != IAVF_NO_RESCHED)
 		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   HZ * 2);
+				   msecs_to_jiffies(msec_delay));
+	netdev_unlock(netdev);
 }
 
 /**
@@ -2880,14 +3051,15 @@ restart_watchdog:
  * @adapter: board private structure
  *
  * Set communication failed flag and free all resources.
- * NOTE: This function is expected to be called with crit_lock being held.
- **/
+ */
 static void iavf_disable_vf(struct iavf_adapter *adapter)
 {
 	struct iavf_mac_filter *f, *ftmp;
 	struct iavf_vlan_filter *fv, *fvtmp;
 	struct iavf_cloud_filter *cf, *cftmp;
 
+	netdev_assert_locked(adapter->netdev);
+
 	adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 
 	/* We don't use netif_running() because it may be true prior to
@@ -2987,17 +3159,7 @@ static void iavf_reset_task(struct work_struct *work)
 	int i = 0, err;
 	bool running;
 
-	/* When device is being removed it doesn't make sense to run the reset
-	 * task, just return in such a case.
-	 */
-	mutex_lock(&netdev->lock);
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state != __IAVF_REMOVE)
-			queue_work(adapter->wq, &adapter->reset_task);
-
-		mutex_unlock(&netdev->lock);
-		return;
-	}
+	netdev_lock(netdev);
 
 	iavf_misc_irq_disable(adapter);
 	if (adapter->flags & IAVF_FLAG_RESET_NEEDED) {
@@ -3042,12 +3204,22 @@ static void iavf_reset_task(struct work_struct *work)
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			reg_val);
 		iavf_disable_vf(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		mutex_unlock(&netdev->lock);
+		netdev_unlock(netdev);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
 continue_reset:
+	/* If we are still early in the state machine, just restart. */
+	if (adapter->state <= __IAVF_INIT_FAILED) {
+		iavf_shutdown_adminq(hw);
+		iavf_change_state(adapter, __IAVF_STARTUP);
+		iavf_startup(adapter);
+		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+				   msecs_to_jiffies(30));
+		netdev_unlock(netdev);
+		return;
+	}
+
 	/* We don't use netif_running() because it may be true prior to
 	 * ndo_open() returning, so we can't assume it means all our open
 	 * tasks have finished, since we're not holding the rtnl_lock here.
@@ -3099,15 +3271,18 @@ continue_reset:
 	}
 
 	adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG;
-	/* always set since VIRTCHNL_OP_GET_VF_RESOURCES has not been
-	 * sent/received yet, so VLAN_V2_ALLOWED() cannot is not reliable here,
-	 * however the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS won't be sent until
-	 * VIRTCHNL_OP_GET_VF_RESOURCES and VIRTCHNL_VF_OFFLOAD_VLAN_V2 have
-	 * been successfully sent and negotiated
-	 */
-	adapter->aq_required |= IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS;
 	adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS;
 
+	/* Certain capabilities require an extended negotiation process using
+	 * extra messages that must be processed after getting the VF
+	 * configuration. The related checks such as VLAN_V2_ALLOWED() are not
+	 * reliable here, since the configuration has not yet been negotiated.
+	 *
+	 * Always set these flags, since them related VIRTCHNL messages won't
+	 * be sent until after VIRTCHNL_OP_GET_VF_RESOURCES.
+	 */
+	adapter->aq_required |= IAVF_FLAG_AQ_EXTENDED_CAPS;
+
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
 
 	/* Delete filter for the current MAC address, it could have
@@ -3183,8 +3358,7 @@ continue_reset:
 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 
 	wake_up(&adapter->reset_waitqueue);
-	mutex_unlock(&adapter->crit_lock);
-	mutex_unlock(&netdev->lock);
+	netdev_unlock(netdev);
 
 	return;
 reset_err:
@@ -3194,8 +3368,7 @@ reset_err:
 	}
 	iavf_disable_vf(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
-	mutex_unlock(&netdev->lock);
+	netdev_unlock(netdev);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 }
 
@@ -3207,6 +3380,7 @@ static void iavf_adminq_task(struct work_struct *work)
 {
 	struct iavf_adapter *adapter =
 		container_of(work, struct iavf_adapter, adminq_task);
+	struct net_device *netdev = adapter->netdev;
 	struct iavf_hw *hw = &adapter->hw;
 	struct iavf_arq_event_info event;
 	enum virtchnl_ops v_op;
@@ -3214,13 +3388,7 @@ static void iavf_adminq_task(struct work_struct *work)
 	u32 val, oldval;
 	u16 pending;
 
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state == __IAVF_REMOVE)
-			return;
-
-		queue_work(adapter->wq, &adapter->adminq_task);
-		goto out;
-	}
+	netdev_lock(netdev);
 
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
 		goto unlock;
@@ -3287,8 +3455,7 @@ static void iavf_adminq_task(struct work_struct *work)
 freedom:
 	kfree(event.msg_buf);
 unlock:
-	mutex_unlock(&adapter->crit_lock);
-out:
+	netdev_unlock(netdev);
 	/* re-enable Admin queue interrupt cause */
 	iavf_misc_irq_enable(adapter);
 }
@@ -3667,10 +3834,8 @@ exit:
 	if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
 		return 0;
 
-	mutex_lock(&netdev->lock);
 	netif_set_real_num_rx_queues(netdev, total_qps);
 	netif_set_real_num_tx_queues(netdev, total_qps);
-	mutex_unlock(&netdev->lock);
 
 	return ret;
 }
@@ -3983,8 +4148,8 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 				    struct flow_cls_offload *cls_flower)
 {
 	int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid);
-	struct iavf_cloud_filter *filter = NULL;
-	int err = -EINVAL, count = 50;
+	struct iavf_cloud_filter *filter;
+	int err;
 
 	if (tc < 0) {
 		dev_err(&adapter->pdev->dev, "Invalid traffic class\n");
@@ -3994,17 +4159,10 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
 	if (!filter)
 		return -ENOMEM;
-
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(filter);
-			return err;
-		}
-		udelay(1);
-	}
-
 	filter->cookie = cls_flower->cookie;
 
+	netdev_lock(adapter->netdev);
+
 	/* bail out here if filter already exists */
 	spin_lock_bh(&adapter->cloud_filter_list_lock);
 	if (iavf_find_cf(adapter, &cls_flower->cookie)) {
@@ -4038,7 +4196,7 @@ err:
 	if (err)
 		kfree(filter);
 
-	mutex_unlock(&adapter->crit_lock);
+	netdev_unlock(adapter->netdev);
 	return err;
 }
 
@@ -4335,33 +4493,20 @@ static int iavf_open(struct net_device *netdev)
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	int err;
 
+	netdev_assert_locked(netdev);
+
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) {
 		dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n");
 		return -EIO;
 	}
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		/* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock
-		 * is already taken and iavf_open is called from an upper
-		 * device's notifier reacting on NETDEV_REGISTER event.
-		 * We have to leave here to avoid dead lock.
-		 */
-		if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER)
-			return -EBUSY;
-
-		usleep_range(500, 1000);
-	}
-
-	if (adapter->state != __IAVF_DOWN) {
-		err = -EBUSY;
-		goto err_unlock;
-	}
+	if (adapter->state != __IAVF_DOWN)
+		return -EBUSY;
 
 	if (adapter->state == __IAVF_RUNNING &&
 	    !test_bit(__IAVF_VSI_DOWN, adapter->vsi.state)) {
 		dev_dbg(&adapter->pdev->dev, "VF is already open.\n");
-		err = 0;
-		goto err_unlock;
+		return 0;
 	}
 
 	/* allocate transmit descriptors */
@@ -4380,9 +4525,7 @@ static int iavf_open(struct net_device *netdev)
 		goto err_req_irq;
 
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
-
 	iavf_add_filter(adapter, adapter->hw.mac.addr);
-
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
 	/* Restore filters that were removed with IFF_DOWN */
@@ -4395,8 +4538,6 @@ static int iavf_open(struct net_device *netdev)
 
 	iavf_irq_enable(adapter, true);
 
-	mutex_unlock(&adapter->crit_lock);
-
 	return 0;
 
 err_req_irq:
@@ -4406,8 +4547,6 @@ err_setup_rx:
 	iavf_free_all_rx_resources(adapter);
 err_setup_tx:
 	iavf_free_all_tx_resources(adapter);
-err_unlock:
-	mutex_unlock(&adapter->crit_lock);
 
 	return err;
 }
@@ -4429,12 +4568,10 @@ static int iavf_close(struct net_device *netdev)
 	u64 aq_to_restore;
 	int status;
 
-	mutex_lock(&adapter->crit_lock);
+	netdev_assert_locked(netdev);
 
-	if (adapter->state <= __IAVF_DOWN_PENDING) {
-		mutex_unlock(&adapter->crit_lock);
+	if (adapter->state <= __IAVF_DOWN_PENDING)
 		return 0;
-	}
 
 	set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
 	/* We cannot send IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS before
@@ -4465,7 +4602,7 @@ static int iavf_close(struct net_device *netdev)
 	iavf_change_state(adapter, __IAVF_DOWN_PENDING);
 	iavf_free_traffic_irqs(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
+	netdev_unlock(netdev);
 
 	/* We explicitly don't free resources here because the hardware is
 	 * still active and can DMA into memory. Resources are cleared in
@@ -4483,10 +4620,10 @@ static int iavf_close(struct net_device *netdev)
 				    msecs_to_jiffies(500));
 	if (!status)
 		netdev_warn(netdev, "Device resources not yet released\n");
+	netdev_lock(netdev);
 
-	mutex_lock(&adapter->crit_lock);
 	adapter->aq_required |= aq_to_restore;
-	mutex_unlock(&adapter->crit_lock);
+
 	return 0;
 }
 
@@ -4948,6 +5085,25 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 	return iavf_fix_strip_features(adapter, features);
 }
 
+static int iavf_hwstamp_get(struct net_device *netdev,
+			    struct kernel_hwtstamp_config *config)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
+	*config = adapter->ptp.hwtstamp_config;
+
+	return 0;
+}
+
+static int iavf_hwstamp_set(struct net_device *netdev,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
+	return iavf_ptp_set_ts_config(adapter, config, extack);
+}
+
 static int
 iavf_verify_shaper(struct net_shaper_binding *binding,
 		   const struct net_shaper *shaper,
@@ -4976,15 +5132,16 @@ iavf_shaper_set(struct net_shaper_binding *binding,
 	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
 	const struct net_shaper_handle *handle = &shaper->handle;
 	struct iavf_ring *tx_ring;
-	int ret = 0;
+	int ret;
+
+	netdev_assert_locked(adapter->netdev);
 
-	mutex_lock(&adapter->crit_lock);
 	if (handle->id >= adapter->num_active_queues)
-		goto unlock;
+		return 0;
 
 	ret = iavf_verify_shaper(binding, shaper, extack);
 	if (ret)
-		goto unlock;
+		return ret;
 
 	tx_ring = &adapter->tx_rings[handle->id];
 
@@ -4994,9 +5151,7 @@ iavf_shaper_set(struct net_shaper_binding *binding,
 
 	adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
 
-unlock:
-	mutex_unlock(&adapter->crit_lock);
-	return ret;
+	return 0;
 }
 
 static int iavf_shaper_del(struct net_shaper_binding *binding,
@@ -5006,9 +5161,10 @@ static int iavf_shaper_del(struct net_shaper_binding *binding,
 	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
 	struct iavf_ring *tx_ring;
 
-	mutex_lock(&adapter->crit_lock);
+	netdev_assert_locked(adapter->netdev);
+
 	if (handle->id >= adapter->num_active_queues)
-		goto unlock;
+		return 0;
 
 	tx_ring = &adapter->tx_rings[handle->id];
 	tx_ring->q_shaper.bw_min = 0;
@@ -5017,8 +5173,6 @@ static int iavf_shaper_del(struct net_shaper_binding *binding,
 
 	adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
 
-unlock:
-	mutex_unlock(&adapter->crit_lock);
 	return 0;
 }
 
@@ -5056,6 +5210,8 @@ static const struct net_device_ops iavf_netdev_ops = {
 	.ndo_set_features	= iavf_set_features,
 	.ndo_setup_tc		= iavf_setup_tc,
 	.net_shaper_ops		= &iavf_shaper_ops,
+	.ndo_hwtstamp_get	= iavf_hwstamp_get,
+	.ndo_hwtstamp_set	= iavf_hwstamp_set,
 };
 
 /**
@@ -5277,10 +5433,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_alloc_qos_cap;
 	}
 
-	/* set up the locks for the AQ, do this only once in probe
-	 * and destroy them only once in remove
-	 */
-	mutex_init(&adapter->crit_lock);
 	mutex_init(&hw->aq.asq_mutex);
 	mutex_init(&hw->aq.arq_mutex);
 
@@ -5310,6 +5462,10 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup the wait queue for indicating virtchannel events */
 	init_waitqueue_head(&adapter->vc_waitqueue);
 
+	INIT_LIST_HEAD(&adapter->ptp.aq_cmds);
+	init_waitqueue_head(&adapter->ptp.phc_time_waitqueue);
+	mutex_init(&adapter->ptp.aq_cmd_lock);
+
 	queue_delayed_work(adapter->wq, &adapter->watchdog_task,
 			   msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
 	/* Initialization goes on in the work. Do not add more of it below. */
@@ -5339,20 +5495,24 @@ static int iavf_suspend(struct device *dev_d)
 {
 	struct net_device *netdev = dev_get_drvdata(dev_d);
 	struct iavf_adapter *adapter = netdev_priv(netdev);
+	bool running;
 
 	netif_device_detach(netdev);
 
-	mutex_lock(&adapter->crit_lock);
-
-	if (netif_running(netdev)) {
+	running = netif_running(netdev);
+	if (running)
 		rtnl_lock();
+	netdev_lock(netdev);
+
+	if (running)
 		iavf_down(adapter);
-		rtnl_unlock();
-	}
+
 	iavf_free_misc_irq(adapter);
 	iavf_reset_interrupt_capability(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
+	netdev_unlock(netdev);
+	if (running)
+		rtnl_unlock();
 
 	return 0;
 }
@@ -5429,20 +5589,20 @@ static void iavf_remove(struct pci_dev *pdev)
 	 * There are flows where register/unregister netdev may race.
 	 */
 	while (1) {
-		mutex_lock(&adapter->crit_lock);
+		netdev_lock(netdev);
 		if (adapter->state == __IAVF_RUNNING ||
 		    adapter->state == __IAVF_DOWN ||
 		    adapter->state == __IAVF_INIT_FAILED) {
-			mutex_unlock(&adapter->crit_lock);
+			netdev_unlock(netdev);
 			break;
 		}
 		/* Simply return if we already went through iavf_shutdown */
 		if (adapter->state == __IAVF_REMOVE) {
-			mutex_unlock(&adapter->crit_lock);
+			netdev_unlock(netdev);
 			return;
 		}
 
-		mutex_unlock(&adapter->crit_lock);
+		netdev_unlock(netdev);
 		usleep_range(500, 1000);
 	}
 	cancel_delayed_work_sync(&adapter->watchdog_task);
@@ -5451,7 +5611,7 @@ static void iavf_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
-	mutex_lock(&adapter->crit_lock);
+	netdev_lock(netdev);
 	dev_info(&adapter->pdev->dev, "Removing device\n");
 	iavf_change_state(adapter, __IAVF_REMOVE);
 
@@ -5463,11 +5623,15 @@ static void iavf_remove(struct pci_dev *pdev)
 		msleep(50);
 	}
 
+	iavf_ptp_release(adapter);
+
 	iavf_misc_irq_disable(adapter);
 	/* Shut down all the garbage mashers on the detention level */
+	netdev_unlock(netdev);
 	cancel_work_sync(&adapter->reset_task);
 	cancel_delayed_work_sync(&adapter->watchdog_task);
 	cancel_work_sync(&adapter->adminq_task);
+	netdev_lock(netdev);
 
 	adapter->aq_required = 0;
 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
@@ -5485,8 +5649,7 @@ static void iavf_remove(struct pci_dev *pdev)
 	/* destroy the locks only once, here */
 	mutex_destroy(&hw->aq.arq_mutex);
 	mutex_destroy(&hw->aq.asq_mutex);
-	mutex_unlock(&adapter->crit_lock);
-	mutex_destroy(&adapter->crit_lock);
+	netdev_unlock(netdev);
 
 	iounmap(hw->hw_addr);
 	pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
new file mode 100644
index 000000000000..b4d5eda2e84f
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
@@ -0,0 +1,485 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024 Intel Corporation. */
+
+#include "iavf.h"
+#include "iavf_ptp.h"
+
+#define iavf_clock_to_adapter(info)				\
+	container_of_const(info, struct iavf_adapter, ptp.info)
+
+/**
+ * iavf_ptp_disable_rx_tstamp - Disable timestamping in Rx rings
+ * @adapter: private adapter structure
+ *
+ * Disable timestamp reporting for all Rx rings.
+ */
+static void iavf_ptp_disable_rx_tstamp(struct iavf_adapter *adapter)
+{
+	for (u32 i = 0; i < adapter->num_active_queues; i++)
+		adapter->rx_rings[i].flags &= ~IAVF_TXRX_FLAGS_HW_TSTAMP;
+}
+
+/**
+ * iavf_ptp_enable_rx_tstamp - Enable timestamping in Rx rings
+ * @adapter: private adapter structure
+ *
+ * Enable timestamp reporting for all Rx rings.
+ */
+static void iavf_ptp_enable_rx_tstamp(struct iavf_adapter *adapter)
+{
+	for (u32 i = 0; i < adapter->num_active_queues; i++)
+		adapter->rx_rings[i].flags |= IAVF_TXRX_FLAGS_HW_TSTAMP;
+}
+
+/**
+ * iavf_ptp_set_timestamp_mode - Set device timestamping mode
+ * @adapter: private adapter structure
+ * @config: pointer to kernel_hwtstamp_config
+ *
+ * Set the timestamping mode requested from the userspace.
+ *
+ * Note: this function always translates Rx timestamp requests for any packet
+ * category into HWTSTAMP_FILTER_ALL.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int iavf_ptp_set_timestamp_mode(struct iavf_adapter *adapter,
+				       struct kernel_hwtstamp_config *config)
+{
+	/* Reserved for future extensions. */
+	if (config->flags)
+		return -EINVAL;
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+	case HWTSTAMP_TX_ON:
+		return -EOPNOTSUPP;
+	default:
+		return -ERANGE;
+	}
+
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
+		iavf_ptp_disable_rx_tstamp(adapter);
+		return 0;
+	} else if (config->rx_filter > HWTSTAMP_FILTER_NTP_ALL) {
+		return -ERANGE;
+	} else if (!(iavf_ptp_cap_supported(adapter,
+					    VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))) {
+		return -EOPNOTSUPP;
+	}
+
+	config->rx_filter = HWTSTAMP_FILTER_ALL;
+	iavf_ptp_enable_rx_tstamp(adapter);
+
+	return 0;
+}
+
+/**
+ * iavf_ptp_set_ts_config - Set timestamping configuration
+ * @adapter: private adapter structure
+ * @config: pointer to kernel_hwtstamp_config structure
+ * @extack: pointer to netlink_ext_ack structure
+ *
+ * Program the requested timestamping configuration to the device.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
+{
+	int err;
+
+	err = iavf_ptp_set_timestamp_mode(adapter, config);
+	if (err)
+		return err;
+
+	/* Save successful settings for future reference */
+	adapter->ptp.hwtstamp_config = *config;
+
+	return 0;
+}
+
+/**
+ * iavf_ptp_cap_supported - Check if a PTP capability is supported
+ * @adapter: private adapter structure
+ * @cap: the capability bitmask to check
+ *
+ * Return: true if every capability set in cap is also set in the enabled
+ *         capabilities reported by the PF, false otherwise.
+ */
+bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap)
+{
+	if (!IAVF_PTP_ALLOWED(adapter))
+		return false;
+
+	/* Only return true if every bit in cap is set in hw_caps.caps */
+	return (adapter->ptp.hw_caps.caps & cap) == cap;
+}
+
+/**
+ * iavf_allocate_ptp_cmd - Allocate a PTP command message structure
+ * @v_opcode: the virtchnl opcode
+ * @msglen: length in bytes of the associated virtchnl structure
+ *
+ * Allocates a PTP command message and pre-fills it with the provided message
+ * length and opcode.
+ *
+ * Return: allocated PTP command.
+ */
+static struct iavf_ptp_aq_cmd *iavf_allocate_ptp_cmd(enum virtchnl_ops v_opcode,
+						     u16 msglen)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+
+	cmd = kzalloc(struct_size(cmd, msg, msglen), GFP_KERNEL);
+	if (!cmd)
+		return NULL;
+
+	cmd->v_opcode = v_opcode;
+	cmd->msglen = msglen;
+
+	return cmd;
+}
+
+/**
+ * iavf_queue_ptp_cmd - Queue PTP command for sending over virtchnl
+ * @adapter: private adapter structure
+ * @cmd: the command structure to send
+ *
+ * Queue the given command structure into the PTP virtchnl command queue tos
+ * end to the PF.
+ */
+static void iavf_queue_ptp_cmd(struct iavf_adapter *adapter,
+			       struct iavf_ptp_aq_cmd *cmd)
+{
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	list_add_tail(&cmd->list, &adapter->ptp.aq_cmds);
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+
+	adapter->aq_required |= IAVF_FLAG_AQ_SEND_PTP_CMD;
+	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+}
+
+/**
+ * iavf_send_phc_read - Send request to read PHC time
+ * @adapter: private adapter structure
+ *
+ * Send a request to obtain the PTP hardware clock time. This allocates the
+ * VIRTCHNL_OP_1588_PTP_GET_TIME message and queues it up to send to
+ * indirectly read the PHC time.
+ *
+ * This function does not wait for the reply from the PF.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+static int iavf_send_phc_read(struct iavf_adapter *adapter)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+
+	if (!adapter->ptp.clock)
+		return -EOPNOTSUPP;
+
+	cmd = iavf_allocate_ptp_cmd(VIRTCHNL_OP_1588_PTP_GET_TIME,
+				    sizeof(struct virtchnl_phc_time));
+	if (!cmd)
+		return -ENOMEM;
+
+	iavf_queue_ptp_cmd(adapter, cmd);
+
+	return 0;
+}
+
+/**
+ * iavf_read_phc_indirect - Indirectly read the PHC time via virtchnl
+ * @adapter: private adapter structure
+ * @ts: storage for the timestamp value
+ * @sts: system timestamp values before and after the read
+ *
+ * Used when the device does not have direct register access to the PHC time.
+ * Indirectly reads the time via the VIRTCHNL_OP_1588_PTP_GET_TIME, and waits
+ * for the reply from the PF.
+ *
+ * Based on some simple measurements using ftrace and phc2sys, this clock
+ * access method has about a ~110 usec latency even when the system is not
+ * under load. In order to achieve acceptable results when using phc2sys with
+ * the indirect clock access method, it is recommended to use more
+ * conservative proportional and integration constants with the P/I servo.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+static int iavf_read_phc_indirect(struct iavf_adapter *adapter,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	long ret;
+	int err;
+
+	adapter->ptp.phc_time_ready = false;
+
+	ptp_read_system_prets(sts);
+
+	err = iavf_send_phc_read(adapter);
+	if (err)
+		return err;
+
+	ret = wait_event_interruptible_timeout(adapter->ptp.phc_time_waitqueue,
+					       adapter->ptp.phc_time_ready,
+					       HZ);
+
+	ptp_read_system_postts(sts);
+
+	if (ret < 0)
+		return ret;
+	else if (!ret)
+		return -EBUSY;
+
+	*ts = ns_to_timespec64(adapter->ptp.cached_phc_time);
+
+	return 0;
+}
+
+static int iavf_ptp_gettimex64(struct ptp_clock_info *info,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct iavf_adapter *adapter = iavf_clock_to_adapter(info);
+
+	if (!adapter->ptp.clock)
+		return -EOPNOTSUPP;
+
+	return iavf_read_phc_indirect(adapter, ts, sts);
+}
+
+/**
+ * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension
+ * @adapter: private adapter structure
+ *
+ * Periodically cache the PHC time in order to allow for timestamp extension.
+ * This is required because the Tx and Rx timestamps only contain 32bits of
+ * nanoseconds. Timestamp extension allows calculating the corrected 64bit
+ * timestamp. This algorithm relies on the cached time being within ~1 second
+ * of the timestamp.
+ */
+static void iavf_ptp_cache_phc_time(struct iavf_adapter *adapter)
+{
+	if (!time_is_before_jiffies(adapter->ptp.cached_phc_updated + HZ))
+		return;
+
+	/* The response from virtchnl will store the time into
+	 * cached_phc_time.
+	 */
+	iavf_send_phc_read(adapter);
+}
+
+/**
+ * iavf_ptp_do_aux_work - Perform periodic work required for PTP support
+ * @info: PTP clock info structure
+ *
+ * Handler to take care of periodic work required for PTP operation. This
+ * includes the following tasks:
+ *
+ *   1) updating cached_phc_time
+ *
+ *      cached_phc_time is used by the Tx and Rx timestamp flows in order to
+ *      perform timestamp extension, by carefully comparing the timestamp
+ *      32bit nanosecond timestamps and determining the corrected 64bit
+ *      timestamp value to report to userspace. This algorithm only works if
+ *      the cached_phc_time is within ~1 second of the Tx or Rx timestamp
+ *      event. This task periodically reads the PHC time and stores it, to
+ *      ensure that timestamp extension operates correctly.
+ *
+ * Returns: time in jiffies until the periodic task should be re-scheduled.
+ */
+static long iavf_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+	struct iavf_adapter *adapter = iavf_clock_to_adapter(info);
+
+	iavf_ptp_cache_phc_time(adapter);
+
+	/* Check work about twice a second */
+	return msecs_to_jiffies(500);
+}
+
+/**
+ * iavf_ptp_register_clock - Register a new PTP for userspace
+ * @adapter: private adapter structure
+ *
+ * Allocate and register a new PTP clock device if necessary.
+ *
+ * Return: 0 if success, error otherwise.
+ */
+static int iavf_ptp_register_clock(struct iavf_adapter *adapter)
+{
+	struct ptp_clock_info *ptp_info = &adapter->ptp.info;
+	struct device *dev = &adapter->pdev->dev;
+	struct ptp_clock *clock;
+
+	snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk",
+		 KBUILD_MODNAME, dev_name(dev));
+	ptp_info->owner = THIS_MODULE;
+	ptp_info->gettimex64 = iavf_ptp_gettimex64;
+	ptp_info->do_aux_work = iavf_ptp_do_aux_work;
+
+	clock = ptp_clock_register(ptp_info, dev);
+	if (IS_ERR(clock))
+		return PTR_ERR(clock);
+
+	adapter->ptp.clock = clock;
+
+	dev_dbg(&adapter->pdev->dev, "PTP clock %s registered\n",
+		adapter->ptp.info.name);
+
+	return 0;
+}
+
+/**
+ * iavf_ptp_init - Initialize PTP support if capability was negotiated
+ * @adapter: private adapter structure
+ *
+ * Initialize PTP functionality, based on the capabilities that the PF has
+ * enabled for this VF.
+ */
+void iavf_ptp_init(struct iavf_adapter *adapter)
+{
+	int err;
+
+	if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC)) {
+		pci_notice(adapter->pdev,
+			   "Device does not have PTP clock support\n");
+		return;
+	}
+
+	err = iavf_ptp_register_clock(adapter);
+	if (err) {
+		pci_err(adapter->pdev,
+			"Failed to register PTP clock device (%p)\n",
+			ERR_PTR(err));
+		return;
+	}
+
+	for (int i = 0; i < adapter->num_active_queues; i++) {
+		struct iavf_ring *rx_ring = &adapter->rx_rings[i];
+
+		rx_ring->ptp = &adapter->ptp;
+	}
+
+	ptp_schedule_worker(adapter->ptp.clock, 0);
+}
+
+/**
+ * iavf_ptp_release - Disable PTP support
+ * @adapter: private adapter structure
+ *
+ * Release all PTP resources that were previously initialized.
+ */
+void iavf_ptp_release(struct iavf_adapter *adapter)
+{
+	struct iavf_ptp_aq_cmd *cmd, *tmp;
+
+	if (!adapter->ptp.clock)
+		return;
+
+	pci_dbg(adapter->pdev, "removing PTP clock %s\n",
+		adapter->ptp.info.name);
+	ptp_clock_unregister(adapter->ptp.clock);
+	adapter->ptp.clock = NULL;
+
+	/* Cancel any remaining uncompleted PTP clock commands */
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	list_for_each_entry_safe(cmd, tmp, &adapter->ptp.aq_cmds, list) {
+		list_del(&cmd->list);
+		kfree(cmd);
+	}
+	adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+
+	adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	iavf_ptp_disable_rx_tstamp(adapter);
+}
+
+/**
+ * iavf_ptp_process_caps - Handle change in PTP capabilities
+ * @adapter: private adapter structure
+ *
+ * Handle any state changes necessary due to change in PTP capabilities, such
+ * as after a device reset or change in configuration from the PF.
+ */
+void iavf_ptp_process_caps(struct iavf_adapter *adapter)
+{
+	bool phc = iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC);
+
+	/* Check if the device gained or lost necessary access to support the
+	 * PTP hardware clock. If so, driver must respond appropriately by
+	 * creating or destroying the PTP clock device.
+	 */
+	if (adapter->ptp.clock && !phc)
+		iavf_ptp_release(adapter);
+	else if (!adapter->ptp.clock && phc)
+		iavf_ptp_init(adapter);
+
+	/* Check if the device lost access to Rx timestamp incoming packets */
+	if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) {
+		adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+		iavf_ptp_disable_rx_tstamp(adapter);
+	}
+}
+
+/**
+ * iavf_ptp_extend_32b_timestamp - Convert a 32b nanoseconds timestamp to 64b
+ * nanoseconds
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ *
+ * Extend the 32bit nanosecond timestamp using the following algorithm and
+ * assumptions:
+ *
+ * 1) have a recently cached copy of the PHC time
+ * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1
+ *    seconds) before or after the PHC time was captured.
+ * 3) calculate the delta between the cached time and the timestamp
+ * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was
+ *    captured after the PHC time. In this case, the full timestamp is just
+ *    the cached PHC time plus the delta.
+ * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the
+ *    timestamp was captured *before* the PHC time, i.e. because the PHC
+ *    cache was updated after the timestamp was captured by hardware. In this
+ *    case, the full timestamp is the cached time minus the inverse delta.
+ *
+ * This algorithm works even if the PHC time was updated after a Tx timestamp
+ * was requested, but before the Tx timestamp event was reported from
+ * hardware.
+ *
+ * This calculation primarily relies on keeping the cached PHC time up to
+ * date. If the timestamp was captured more than 2^31 nanoseconds after the
+ * PHC time, it is possible that the lower 32bits of PHC time have
+ * overflowed more than once, and we might generate an incorrect timestamp.
+ *
+ * This is prevented by (a) periodically updating the cached PHC time once
+ * a second, and (b) discarding any Tx timestamp packet if it has waited for
+ * a timestamp for more than one second.
+ *
+ * Return: extended timestamp (to 64b).
+ */
+u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp)
+{
+	u32 low = lower_32_bits(cached_phc_time);
+	u32 delta = in_tstamp - low;
+	u64 ns;
+
+	/* Do not assume that the in_tstamp is always more recent than the
+	 * cached PHC time. If the delta is large, it indicates that the
+	 * in_tstamp was taken in the past, and should be converted
+	 * forward.
+	 */
+	if (delta > S32_MAX)
+		ns = cached_phc_time - (low - in_tstamp);
+	else
+		ns = cached_phc_time + delta;
+
+	return ns;
+}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
new file mode 100644
index 000000000000..783b8f287cd9
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IAVF_PTP_H_
+#define _IAVF_PTP_H_
+
+#include "iavf_types.h"
+
+/* bit indicating whether a 40bit timestamp is valid */
+#define IAVF_PTP_40B_TSTAMP_VALID	BIT(24)
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+void iavf_ptp_init(struct iavf_adapter *adapter);
+void iavf_ptp_release(struct iavf_adapter *adapter);
+void iavf_ptp_process_caps(struct iavf_adapter *adapter);
+bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap);
+void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter);
+int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack);
+u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp);
+#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+static inline void iavf_ptp_init(struct iavf_adapter *adapter) { }
+static inline void iavf_ptp_release(struct iavf_adapter *adapter) { }
+static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { }
+static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter,
+					  u32 cap)
+{
+	return false;
+}
+
+static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { }
+static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+					 struct kernel_hwtstamp_config *config,
+					 struct netlink_ext_ack *extack)
+{
+	return -1;
+}
+
+static inline u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time,
+						u32 in_tstamp)
+{
+	return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+#endif /* _IAVF_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h
index 62212011c807..c5e4d1823886 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_trace.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h
@@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS(
 	iavf_rx_template,
 
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb),
@@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS(
 DEFINE_EVENT(
 	iavf_rx_template, iavf_clean_rx_irq,
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb));
@@ -148,7 +148,7 @@ DEFINE_EVENT(
 DEFINE_EVENT(
 	iavf_rx_template, iavf_clean_rx_irq_rx,
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb));
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 26b424fd6718..422312b8b54a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -8,6 +8,26 @@
 #include "iavf.h"
 #include "iavf_trace.h"
 #include "iavf_prototype.h"
+#include "iavf_ptp.h"
+
+/**
+ * iavf_is_descriptor_done - tests DD bit in Rx descriptor
+ * @qw1: quad word 1 from descriptor to get Descriptor Done field from
+ * @flex: is the descriptor flex or legacy
+ *
+ * This function tests the descriptor done bit in specified descriptor. Because
+ * there are two types of descriptors (legacy and flex) the parameter rx_ring
+ * is used to distinguish.
+ *
+ * Return: true or false based on the state of DD bit in Rx descriptor.
+ */
+static bool iavf_is_descriptor_done(u64 qw1, bool flex)
+{
+	if (flex)
+		return FIELD_GET(IAVF_RXD_FLEX_DD_M, qw1);
+	else
+		return FIELD_GET(IAVF_RXD_LEGACY_DD_M, qw1);
+}
 
 static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
 			 u32 td_tag)
@@ -766,7 +786,7 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
 	u64_stats_init(&rx_ring->syncp);
 
 	/* Round up to nearest 4K */
-	rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc);
+	rx_ring->size = rx_ring->count * sizeof(struct iavf_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
 	rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size,
 					   &rx_ring->dma, GFP_KERNEL);
@@ -845,7 +865,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		.count		= rx_ring->count,
 	};
 	u16 ntu = rx_ring->next_to_use;
-	union iavf_rx_desc *rx_desc;
+	struct iavf_rx_desc *rx_desc;
 
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
@@ -863,7 +883,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(addr);
+		rx_desc->qw0 = cpu_to_le64(addr);
 
 		rx_desc++;
 		ntu++;
@@ -873,7 +893,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		}
 
 		/* clear the status bits for the next_to_use descriptor */
-		rx_desc->wb.qword1.status_error_len = 0;
+		rx_desc->qw1 = 0;
 
 		cleaned_count--;
 	} while (cleaned_count);
@@ -896,60 +916,43 @@ no_buffers:
 }
 
 /**
- * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum
+ * iavf_rx_csum - Indicate in skb if hw indicated a good checksum
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
- * @rx_desc: the receive descriptor
+ * @decoded_pt: decoded ptype information
+ * @csum_bits: decoded Rx descriptor information
  **/
-static void iavf_rx_checksum(struct iavf_vsi *vsi,
-			     struct sk_buff *skb,
-			     union iavf_rx_desc *rx_desc)
+static void iavf_rx_csum(const struct iavf_vsi *vsi, struct sk_buff *skb,
+			 struct libeth_rx_pt decoded_pt,
+			 struct libeth_rx_csum csum_bits)
 {
-	struct libeth_rx_pt decoded;
-	u32 rx_error, rx_status;
 	bool ipv4, ipv6;
-	u8 ptype;
-	u64 qword;
 
 	skb->ip_summed = CHECKSUM_NONE;
 
-	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-
-	decoded = libie_rx_pt_parse(ptype);
-	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded))
-		return;
-
-	rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
-	rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword);
-
 	/* did the hardware decode the packet and checksum? */
-	if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT)))
+	if (unlikely(!csum_bits.l3l4p))
 		return;
 
-	ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
-	ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
+	ipv4 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV4;
+	ipv6 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV6;
 
-	if (ipv4 &&
-	    (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) |
-			 BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT))))
+	if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe)))
 		goto checksum_fail;
 
 	/* likely incorrect csum if alternate IP extension headers found */
-	if (ipv6 &&
-	    rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT))
-		/* don't increment checksum err here, non-fatal err */
+	if (unlikely(ipv6 && csum_bits.ipv6exadd))
 		return;
 
 	/* there was some L4 error, count error and punt packet to the stack */
-	if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT))
+	if (unlikely(csum_bits.l4e))
 		goto checksum_fail;
 
 	/* handle packets that were not able to be checksummed due
 	 * to arrival speed, in this case the stack can compute
 	 * the csum.
 	 */
-	if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT))
+	if (unlikely(csum_bits.pprs))
 		return;
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -960,52 +963,196 @@ checksum_fail:
 }
 
 /**
- * iavf_rx_hash - set the hash value in the skb
+ * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good checksum
+ * @vsi: the VSI we care about
+ * @qw1: quad word 1
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ *
+ * Return: decoded checksum bits.
+ **/
+static struct libeth_rx_csum
+iavf_legacy_rx_csum(const struct iavf_vsi *vsi, u64 qw1,
+		    const struct libeth_rx_pt decoded_pt)
+{
+	struct libeth_rx_csum csum_bits = {};
+
+	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt))
+		return csum_bits;
+
+	csum_bits.ipe = FIELD_GET(IAVF_RXD_LEGACY_IPE_M, qw1);
+	csum_bits.eipe = FIELD_GET(IAVF_RXD_LEGACY_EIPE_M, qw1);
+	csum_bits.l4e = FIELD_GET(IAVF_RXD_LEGACY_L4E_M, qw1);
+	csum_bits.pprs = FIELD_GET(IAVF_RXD_LEGACY_PPRS_M, qw1);
+	csum_bits.l3l4p = FIELD_GET(IAVF_RXD_LEGACY_L3L4P_M, qw1);
+	csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_LEGACY_IPV6EXADD_M, qw1);
+
+	return csum_bits;
+}
+
+/**
+ * iavf_flex_rx_csum - Indicate in skb if hw indicated a good checksum
+ * @vsi: the VSI we care about
+ * @qw1: quad word 1
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ *
+ * Return: decoded checksum bits.
+ **/
+static struct libeth_rx_csum
+iavf_flex_rx_csum(const struct iavf_vsi *vsi, u64 qw1,
+		  const struct libeth_rx_pt decoded_pt)
+{
+	struct libeth_rx_csum csum_bits = {};
+
+	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt))
+		return csum_bits;
+
+	csum_bits.ipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_IPE_M, qw1);
+	csum_bits.eipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EIPE_M, qw1);
+	csum_bits.l4e = FIELD_GET(IAVF_RXD_FLEX_XSUM_L4E_M, qw1);
+	csum_bits.eudpe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EUDPE_M, qw1);
+	csum_bits.l3l4p = FIELD_GET(IAVF_RXD_FLEX_L3L4P_M, qw1);
+	csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_FLEX_IPV6EXADD_M, qw1);
+	csum_bits.nat = FIELD_GET(IAVF_RXD_FLEX_NAT_M, qw1);
+
+	return csum_bits;
+}
+
+/**
+ * iavf_legacy_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @qw0: quad word 0
+ * @qw1: quad word 1
+ * @skb: skb currently being received and modified
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ **/
+static void iavf_legacy_rx_hash(const struct iavf_ring *ring, __le64 qw0,
+				__le64 qw1, struct sk_buff *skb,
+				const struct libeth_rx_pt decoded_pt)
+{
+	const __le64 rss_mask = cpu_to_le64(IAVF_RXD_LEGACY_FLTSTAT_M);
+	u32 hash;
+
+	if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt))
+		return;
+
+	if ((qw1 & rss_mask) == rss_mask) {
+		hash = le64_get_bits(qw0, IAVF_RXD_LEGACY_RSS_M);
+		libeth_rx_pt_set_hash(skb, hash, decoded_pt);
+	}
+}
+
+/**
+ * iavf_flex_rx_hash - set the hash value in the skb
  * @ring: descriptor ring
- * @rx_desc: specific descriptor
+ * @qw1: quad word 1
  * @skb: skb currently being received and modified
- * @rx_ptype: Rx packet type
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
  **/
-static void iavf_rx_hash(struct iavf_ring *ring,
-			 union iavf_rx_desc *rx_desc,
-			 struct sk_buff *skb,
-			 u8 rx_ptype)
+static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1,
+			      struct sk_buff *skb,
+			      const struct libeth_rx_pt decoded_pt)
 {
-	struct libeth_rx_pt decoded;
+	bool rss_valid;
 	u32 hash;
-	const __le64 rss_mask =
-		cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH <<
-			    IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT);
 
-	decoded = libie_rx_pt_parse(rx_ptype);
-	if (!libeth_rx_pt_has_hash(ring->netdev, decoded))
+	if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt))
 		return;
 
-	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
-		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
-		libeth_rx_pt_set_hash(skb, hash, decoded);
+	rss_valid = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_VALID_M);
+	if (rss_valid) {
+		hash = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_HASH_M);
+		libeth_rx_pt_set_hash(skb, hash, decoded_pt);
 	}
 }
 
 /**
+ * iavf_flex_rx_tstamp - Capture Rx timestamp from the descriptor
+ * @rx_ring: descriptor ring
+ * @qw2: quad word 2 of descriptor
+ * @qw3: quad word 3 of descriptor
+ * @skb: skb currently being received
+ *
+ * Read the Rx timestamp value from the descriptor and pass it to the stack.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ */
+static void iavf_flex_rx_tstamp(const struct iavf_ring *rx_ring, __le64 qw2,
+				__le64 qw3, struct sk_buff *skb)
+{
+	u32 tstamp;
+	u64 ns;
+
+	/* Skip processing if timestamps aren't enabled */
+	if (!(rx_ring->flags & IAVF_TXRX_FLAGS_HW_TSTAMP))
+		return;
+
+	/* Check if this Rx descriptor has a valid timestamp */
+	if (!le64_get_bits(qw2, IAVF_PTP_40B_TSTAMP_VALID))
+		return;
+
+	/* the ts_low field only contains the valid bit and sub-nanosecond
+	 * precision, so we don't need to extract it.
+	 */
+	tstamp = le64_get_bits(qw3, IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M);
+
+	ns = iavf_ptp_extend_32b_timestamp(rx_ring->ptp->cached_phc_time,
+					   tstamp);
+
+	*skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) {
+		.hwtstamp = ns_to_ktime(ns),
+	};
+}
+
+/**
  * iavf_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
- * @rx_ptype: the packet type decoded by hardware
+ * @ptype: the packet type decoded by hardware
+ * @flex: is the descriptor flex or legacy
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and
  * other fields within the skb.
  **/
-static void
-iavf_process_skb_fields(struct iavf_ring *rx_ring,
-			union iavf_rx_desc *rx_desc, struct sk_buff *skb,
-			u8 rx_ptype)
+static void iavf_process_skb_fields(const struct iavf_ring *rx_ring,
+				    const struct iavf_rx_desc *rx_desc,
+				    struct sk_buff *skb, u32 ptype,
+				    bool flex)
 {
-	iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
-
-	iavf_rx_checksum(rx_ring->vsi, skb, rx_desc);
+	struct libeth_rx_csum csum_bits;
+	struct libeth_rx_pt decoded_pt;
+	__le64 qw0 = rx_desc->qw0;
+	__le64 qw1 = rx_desc->qw1;
+	__le64 qw2 = rx_desc->qw2;
+	__le64 qw3 = rx_desc->qw3;
+
+	decoded_pt = libie_rx_pt_parse(ptype);
+
+	if (flex) {
+		iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt);
+		iavf_flex_rx_tstamp(rx_ring, qw2, qw3, skb);
+		csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+					      decoded_pt);
+	} else {
+		iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt);
+		csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+						decoded_pt);
+	}
+	iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits);
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
 
@@ -1092,8 +1239,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
 /**
  * iavf_is_non_eop - process handling of non-EOP buffers
  * @rx_ring: Rx ring being processed
- * @rx_desc: Rx descriptor for current buffer
- * @skb: Current socket buffer containing buffer in progress
+ * @fields: Rx descriptor extracted fields
  *
  * This function updates next to clean.  If the buffer is an EOP buffer
  * this function exits returning false, otherwise it will place the
@@ -1101,8 +1247,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
  * that this is in fact a non-EOP buffer.
  **/
 static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
-			    union iavf_rx_desc *rx_desc,
-			    struct sk_buff *skb)
+			    struct libeth_rqe_info fields)
 {
 	u32 ntc = rx_ring->next_to_clean + 1;
 
@@ -1113,8 +1258,7 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
 	prefetch(IAVF_RX_DESC(rx_ring, ntc));
 
 	/* if we are the last buffer then there is nothing else to do */
-#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT)
-	if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF)))
+	if (likely(fields.eop))
 		return false;
 
 	rx_ring->rx_stats.non_eop_descs++;
@@ -1123,6 +1267,109 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
 }
 
 /**
+ * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ *
+ * Return: fields extracted from the Rx descriptor.
+ */
+static struct libeth_rqe_info
+iavf_extract_legacy_rx_fields(const struct iavf_ring *rx_ring,
+			      const struct iavf_rx_desc *rx_desc)
+{
+	u64 qw0 = le64_to_cpu(rx_desc->qw0);
+	u64 qw1 = le64_to_cpu(rx_desc->qw1);
+	u64 qw2 = le64_to_cpu(rx_desc->qw2);
+	struct libeth_rqe_info fields;
+	bool l2tag1p, l2tag2p;
+
+	fields.eop = FIELD_GET(IAVF_RXD_LEGACY_EOP_M, qw1);
+	fields.len = FIELD_GET(IAVF_RXD_LEGACY_LENGTH_M, qw1);
+
+	if (!fields.eop)
+		return fields;
+
+	fields.rxe = FIELD_GET(IAVF_RXD_LEGACY_RXE_M, qw1);
+	fields.ptype = FIELD_GET(IAVF_RXD_LEGACY_PTYPE_M, qw1);
+	fields.vlan = 0;
+
+	if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) {
+		l2tag1p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1P_M, qw1);
+		if (l2tag1p)
+			fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1_M, qw0);
+	} else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+		l2tag2p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2P_M, qw2);
+		if (l2tag2p)
+			fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2_M, qw2);
+	}
+
+	return fields;
+}
+
+/**
+ * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ *
+ * Return: fields extracted from the Rx descriptor.
+ */
+static struct libeth_rqe_info
+iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring,
+			    const struct iavf_rx_desc *rx_desc)
+{
+	struct libeth_rqe_info fields = {};
+	u64 qw0 = le64_to_cpu(rx_desc->qw0);
+	u64 qw1 = le64_to_cpu(rx_desc->qw1);
+	u64 qw2 = le64_to_cpu(rx_desc->qw2);
+	bool l2tag1p, l2tag2p;
+
+	fields.eop = FIELD_GET(IAVF_RXD_FLEX_EOP_M, qw1);
+	fields.len = FIELD_GET(IAVF_RXD_FLEX_PKT_LEN_M, qw0);
+
+	if (!fields.eop)
+		return fields;
+
+	fields.rxe = FIELD_GET(IAVF_RXD_FLEX_RXE_M, qw1);
+	fields.ptype = FIELD_GET(IAVF_RXD_FLEX_PTYPE_M, qw0);
+	fields.vlan = 0;
+
+	if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) {
+		l2tag1p = FIELD_GET(IAVF_RXD_FLEX_L2TAG1P_M, qw1);
+		if (l2tag1p)
+			fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG1_M, qw1);
+	} else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+		l2tag2p = FIELD_GET(IAVF_RXD_FLEX_L2TAG2P_M, qw2);
+		if (l2tag2p)
+			fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG2_2_M, qw2);
+	}
+
+	return fields;
+}
+
+static struct libeth_rqe_info
+iavf_extract_rx_fields(const struct iavf_ring *rx_ring,
+		       const struct iavf_rx_desc *rx_desc,
+		       bool flex)
+{
+	if (flex)
+		return iavf_extract_flex_rx_fields(rx_ring, rx_desc);
+	else
+		return iavf_extract_legacy_rx_fields(rx_ring, rx_desc);
+}
+
+/**
  * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
@@ -1136,18 +1383,17 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
  **/
 static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 {
+	bool flex = rx_ring->rxdid == VIRTCHNL_RXDID_2_FLEX_SQ_NIC;
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring);
 	bool failure = false;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
+		struct libeth_rqe_info fields;
 		struct libeth_fqe *rx_buffer;
-		union iavf_rx_desc *rx_desc;
-		unsigned int size;
-		u16 vlan_tag = 0;
-		u8 rx_ptype;
-		u64 qword;
+		struct iavf_rx_desc *rx_desc;
+		u64 qw1;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IAVF_RX_BUFFER_WRITE) {
@@ -1158,35 +1404,32 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 
 		rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
-		/* status_error_len will always be zero for unused descriptors
-		 * because it's cleared in cleanup, and overlaps with hdr_addr
-		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then the length will be non-zero
-		 */
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-
 		/* This memory barrier is needed to keep us from reading
 		 * any other fields out of the rx_desc until we have
 		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
-#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT)
-		if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
+
+		qw1 = le64_to_cpu(rx_desc->qw1);
+		/* If DD field (descriptor done) is unset then other fields are
+		 * not valid
+		 */
+		if (!iavf_is_descriptor_done(qw1, flex))
 			break;
 
-		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
+		fields = iavf_extract_rx_fields(rx_ring, rx_desc, flex);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
 
 		rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean];
-		if (!libeth_rx_sync_for_cpu(rx_buffer, size))
+		if (!libeth_rx_sync_for_cpu(rx_buffer, fields.len))
 			goto skip_data;
 
 		/* retrieve a buffer from the ring */
 		if (skb)
-			iavf_add_rx_frag(skb, rx_buffer, size);
+			iavf_add_rx_frag(skb, rx_buffer, fields.len);
 		else
-			skb = iavf_build_skb(rx_buffer, size);
+			skb = iavf_build_skb(rx_buffer, fields.len);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -1197,15 +1440,14 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 skip_data:
 		cleaned_count++;
 
-		if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!skb))
+		if (iavf_is_non_eop(rx_ring, fields) || unlikely(!skb))
 			continue;
 
-		/* ERR_MASK will only have valid bits if EOP set, and
-		 * what we are doing here is actually checking
-		 * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
-		 * the error field
+		/* RXE field in descriptor is an indication of the MAC errors
+		 * (like CRC, alignment, oversize etc). If it is set then iavf
+		 * should finish.
 		 */
-		if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) {
+		if (unlikely(fields.rxe)) {
 			dev_kfree_skb_any(skb);
 			skb = NULL;
 			continue;
@@ -1219,22 +1461,11 @@ skip_data:
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-		rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-
 		/* populate checksum, VLAN, and protocol */
-		iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
-
-		if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) &&
-		    rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1)
-			vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1);
-		if (rx_desc->wb.qword2.ext_status &
-		    cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) &&
-		    rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2)
-			vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2);
+		iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype, flex);
 
 		iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
-		iavf_receive_skb(rx_ring, skb, vlan_tag);
+		iavf_receive_skb(rx_ring, skb, fields.vlan);
 		skb = NULL;
 
 		/* update budget accounting */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index f97c702c0802..79ad554f2d53 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -80,25 +80,6 @@ enum iavf_dyn_idx_t {
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
-#define iavf_rx_desc iavf_32byte_rx_desc
-
-/**
- * iavf_test_staterr - tests bits in Rx descriptor status and error fields
- * @rx_desc: pointer to receive descriptor (in le64 format)
- * @stat_err_bits: value to mask
- *
- * This function does some fast chicanery in order to return the
- * value of the mask which is really only used for boolean tests.
- * The status_error_len doesn't need to be shifted because it begins
- * at offset zero.
- */
-static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc,
-				     const u64 stat_err_bits)
-{
-	return !!(rx_desc->wb.qword1.status_error_len &
-		  cpu_to_le64(stat_err_bits));
-}
-
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define IAVF_RX_INCREMENT(r, i) \
 	do {					\
@@ -262,6 +243,8 @@ struct iavf_ring {
 	u16 next_to_use;
 	u16 next_to_clean;
 
+	u16 rxdid;		/* Rx descriptor format */
+
 	u16 flags;
 #define IAVF_TXR_FLAGS_WB_ON_ITR		BIT(0)
 #define IAVF_TXR_FLAGS_ARM_WB			BIT(1)
@@ -269,6 +252,7 @@ struct iavf_ring {
 #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1	BIT(3)
 #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2	BIT(4)
 #define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2	BIT(5)
+#define IAVF_TXRX_FLAGS_HW_TSTAMP		BIT(6)
 
 	/* stats structs */
 	struct iavf_queue_stats	stats;
@@ -295,6 +279,8 @@ struct iavf_ring {
 					 * for this ring.
 					 */
 
+	struct iavf_ptp *ptp;
+
 	u32 rx_buf_len;
 	struct net_shaper q_shaper;
 	bool q_shaper_update;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index f6b09e57abce..f9e1319620f4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -178,110 +178,116 @@ struct iavf_hw {
 	char err_str[16];
 };
 
-/* RX Descriptors */
-union iavf_16byte_rx_desc {
-	struct {
-		__le64 pkt_addr; /* Packet buffer address */
-		__le64 hdr_addr; /* Header buffer address */
-	} read;
-	struct {
-		struct {
-			struct {
-				union {
-					__le16 mirroring_status;
-					__le16 fcoe_ctx_id;
-				} mirr_fcoe;
-				__le16 l2tag1;
-			} lo_dword;
-			union {
-				__le32 rss; /* RSS Hash */
-				__le32 fd_id; /* Flow director filter id */
-				__le32 fcoe_param; /* FCoE DDP Context id */
-			} hi_dword;
-		} qword0;
-		struct {
-			/* ext status/error/pktype/length */
-			__le64 status_error_len;
-		} qword1;
-	} wb;  /* writeback */
-};
-
-union iavf_32byte_rx_desc {
-	struct {
-		__le64  pkt_addr; /* Packet buffer address */
-		__le64  hdr_addr; /* Header buffer address */
-			/* bit 0 of hdr_buffer_addr is DD bit */
-		__le64  rsvd1;
-		__le64  rsvd2;
-	} read;
-	struct {
-		struct {
-			struct {
-				union {
-					__le16 mirroring_status;
-					__le16 fcoe_ctx_id;
-				} mirr_fcoe;
-				__le16 l2tag1;
-			} lo_dword;
-			union {
-				__le32 rss; /* RSS Hash */
-				__le32 fcoe_param; /* FCoE DDP Context id */
-				/* Flow director filter id in case of
-				 * Programming status desc WB
-				 */
-				__le32 fd_id;
-			} hi_dword;
-		} qword0;
-		struct {
-			/* status/error/pktype/length */
-			__le64 status_error_len;
-		} qword1;
-		struct {
-			__le16 ext_status; /* extended status */
-			__le16 rsvd;
-			__le16 l2tag2_1;
-			__le16 l2tag2_2;
-		} qword2;
-		struct {
-			union {
-				__le32 flex_bytes_lo;
-				__le32 pe_status;
-			} lo_dword;
-			union {
-				__le32 flex_bytes_hi;
-				__le32 fd_id;
-			} hi_dword;
-		} qword3;
-	} wb;  /* writeback */
-};
-
-enum iavf_rx_desc_status_bits {
-	/* Note: These are predefined bit offsets */
-	IAVF_RX_DESC_STATUS_DD_SHIFT		= 0,
-	IAVF_RX_DESC_STATUS_EOF_SHIFT		= 1,
-	IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT	= 2,
-	IAVF_RX_DESC_STATUS_L3L4P_SHIFT		= 3,
-	IAVF_RX_DESC_STATUS_CRCP_SHIFT		= 4,
-	IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT	= 5, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT	= 7,
-	/* Note: Bit 8 is reserved in X710 and XL710 */
-	IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT	= 8,
-	IAVF_RX_DESC_STATUS_UMBCAST_SHIFT	= 9, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_FLM_SHIFT		= 11,
-	IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT	= 12, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_LPBK_SHIFT		= 14,
-	IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT	= 15,
-	IAVF_RX_DESC_STATUS_RESERVED_SHIFT	= 16, /* 2 BITS */
-	/* Note: For non-tunnel packets INT_UDP_0 is the right status for
-	 * UDP header
-	 */
-	IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT	= 18,
-	IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */
-};
-
-#define IAVF_RXD_QW1_STATUS_SHIFT	0
-#define IAVF_RXD_QW1_STATUS_MASK	((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \
-					 << IAVF_RXD_QW1_STATUS_SHIFT)
+/**
+ * struct iavf_rx_desc - Receive descriptor (both legacy and flexible)
+ * @qw0: quad word 0 fields:
+ *	 Legacy: Descriptor Type; Mirror ID; L2TAG1P (S-TAG); Filter Status
+ *	 Flex: Descriptor Type; Mirror ID; UMBCAST; Packet Type; Flexible Flags
+ *	       Section 0; Packet Length; Header Length; Split Header Flag;
+ *	       Flexible Flags section 1 / Extended Status
+ * @qw1: quad word 1 fields:
+ *	 Legacy: Status Field; Error Field; Packet Type; Packet Length (packet,
+ *		 header, Split Header Flag)
+ *	 Flex: Status / Error 0 Field; L2TAG1P (S-TAG); Flexible Metadata
+ *	       Container #0; Flexible Metadata Container #1
+ * @qw2: quad word 2 fields:
+ *	 Legacy: Extended Status; 1st L2TAG2P (C-TAG); 2nd L2TAG2P (C-TAG)
+ *	 Flex: Status / Error 1 Field; Flexible Flags section 2; Timestamp Low;
+ *	       1st L2TAG2 (C-TAG); 2nd L2TAG2 (C-TAG)
+ * @qw3: quad word 3 fields:
+ *	 Legacy: FD Filter ID / Flexible Bytes
+ *	 Flex: Flexible Metadata Container #2; Flexible Metadata Container #3;
+ *	       Flexible Metadata Container #4 / Timestamp High 0; Flexible
+ *	       Metadata Container #5 / Timestamp High 1;
+ */
+struct iavf_rx_desc {
+	aligned_le64 qw0;
+/* The hash signature (RSS) */
+#define IAVF_RXD_LEGACY_RSS_M			GENMASK_ULL(63, 32)
+/* Stripped C-TAG VLAN from the receive packet */
+#define IAVF_RXD_LEGACY_L2TAG1_M		GENMASK_ULL(33, 16)
+/* Packet type */
+#define IAVF_RXD_FLEX_PTYPE_M			GENMASK_ULL(25, 16)
+/* Packet length */
+#define IAVF_RXD_FLEX_PKT_LEN_M			GENMASK_ULL(45, 32)
+
+	aligned_le64 qw1;
+/* Descriptor done indication flag. */
+#define IAVF_RXD_LEGACY_DD_M			BIT(0)
+/* End of packet. Set to 1 if this descriptor is the last one of the packet */
+#define IAVF_RXD_LEGACY_EOP_M			BIT(1)
+/* L2 TAG 1 presence indication */
+#define IAVF_RXD_LEGACY_L2TAG1P_M		BIT(2)
+/* Detectable L3 and L4 integrity check is processed by the HW */
+#define IAVF_RXD_LEGACY_L3L4P_M			BIT(3)
+/* Set when an IPv6 packet contains a Destination Options Header or a Routing
+ * Header.
+ */
+#define IAVF_RXD_LEGACY_IPV6EXADD_M		BIT(15)
+/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */
+#define IAVF_RXD_LEGACY_RXE_M			BIT(19)
+/* Checksum reports:
+ * - IPE: IP checksum error
+ * - L4E: L4 integrity error
+ * - EIPE: External IP header (tunneled packets)
+ */
+#define IAVF_RXD_LEGACY_IPE_M			BIT(22)
+#define IAVF_RXD_LEGACY_L4E_M			BIT(23)
+#define IAVF_RXD_LEGACY_EIPE_M			BIT(24)
+/* Set for packets that skip checksum calculation in pre-parser */
+#define IAVF_RXD_LEGACY_PPRS_M			BIT(26)
+/* Indicates the content in the Filter Status field */
+#define IAVF_RXD_LEGACY_FLTSTAT_M		GENMASK_ULL(13, 12)
+/* Packet type */
+#define IAVF_RXD_LEGACY_PTYPE_M			GENMASK_ULL(37, 30)
+/* Packet length */
+#define IAVF_RXD_LEGACY_LENGTH_M		GENMASK_ULL(51, 38)
+/* Descriptor done indication flag */
+#define IAVF_RXD_FLEX_DD_M			BIT(0)
+/* End of packet. Set to 1 if this descriptor is the last one of the packet */
+#define IAVF_RXD_FLEX_EOP_M			BIT(1)
+/* Detectable L3 and L4 integrity check is processed by the HW */
+#define IAVF_RXD_FLEX_L3L4P_M			BIT(3)
+/* Checksum reports:
+ * - IPE: IP checksum error
+ * - L4E: L4 integrity error
+ * - EIPE: External IP header (tunneled packets)
+ * - EUDPE: External UDP checksum error (tunneled packets)
+ */
+#define IAVF_RXD_FLEX_XSUM_IPE_M		BIT(4)
+#define IAVF_RXD_FLEX_XSUM_L4E_M		BIT(5)
+#define IAVF_RXD_FLEX_XSUM_EIPE_M		BIT(6)
+#define IAVF_RXD_FLEX_XSUM_EUDPE_M		BIT(7)
+/* Set when an IPv6 packet contains a Destination Options Header or a Routing
+ * Header.
+ */
+#define IAVF_RXD_FLEX_IPV6EXADD_M		BIT(9)
+/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */
+#define IAVF_RXD_FLEX_RXE_M			BIT(10)
+/* Indicates that the RSS/HASH result is valid */
+#define IAVF_RXD_FLEX_RSS_VALID_M		BIT(12)
+/* L2 TAG 1 presence indication */
+#define IAVF_RXD_FLEX_L2TAG1P_M			BIT(13)
+/* Stripped L2 Tag from the receive packet */
+#define IAVF_RXD_FLEX_L2TAG1_M			GENMASK_ULL(31, 16)
+/* The hash signature (RSS) */
+#define IAVF_RXD_FLEX_RSS_HASH_M		GENMASK_ULL(63, 32)
+
+	aligned_le64 qw2;
+/* L2 Tag 2 Presence */
+#define IAVF_RXD_LEGACY_L2TAG2P_M		BIT(0)
+/* Stripped S-TAG VLAN from the receive packet */
+#define IAVF_RXD_LEGACY_L2TAG2_M		GENMASK_ULL(63, 32)
+/* Stripped S-TAG VLAN from the receive packet */
+#define IAVF_RXD_FLEX_L2TAG2_2_M		GENMASK_ULL(63, 48)
+/* The packet is a UDP tunneled packet */
+#define IAVF_RXD_FLEX_NAT_M			BIT(4)
+/* L2 Tag 2 Presence */
+#define IAVF_RXD_FLEX_L2TAG2P_M			BIT(11)
+	aligned_le64 qw3;
+#define IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M		GENMASK_ULL(63, 32)
+} __aligned(4 * sizeof(__le64));
+static_assert(sizeof(struct iavf_rx_desc) == 32);
 
 #define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT
 #define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK  (0x3UL << \
@@ -298,22 +304,6 @@ enum iavf_rx_desc_fltstat_values {
 	IAVF_RX_DESC_FLTSTAT_RSS_HASH	= 3,
 };
 
-#define IAVF_RXD_QW1_ERROR_SHIFT	19
-#define IAVF_RXD_QW1_ERROR_MASK		(0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT)
-
-enum iavf_rx_desc_error_bits {
-	/* Note: These are predefined bit offsets */
-	IAVF_RX_DESC_ERROR_RXE_SHIFT		= 0,
-	IAVF_RX_DESC_ERROR_RECIPE_SHIFT		= 1,
-	IAVF_RX_DESC_ERROR_HBO_SHIFT		= 2,
-	IAVF_RX_DESC_ERROR_L3L4E_SHIFT		= 3, /* 3 BITS */
-	IAVF_RX_DESC_ERROR_IPE_SHIFT		= 3,
-	IAVF_RX_DESC_ERROR_L4E_SHIFT		= 4,
-	IAVF_RX_DESC_ERROR_EIPE_SHIFT		= 5,
-	IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT	= 6,
-	IAVF_RX_DESC_ERROR_PPRS_SHIFT		= 7
-};
-
 enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 	IAVF_RX_DESC_ERROR_L3L4E_NONE		= 0,
 	IAVF_RX_DESC_ERROR_L3L4E_PROT		= 1,
@@ -322,13 +312,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 	IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN	= 4
 };
 
-#define IAVF_RXD_QW1_PTYPE_SHIFT	30
-#define IAVF_RXD_QW1_PTYPE_MASK		(0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT)
-
-#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT	38
-#define IAVF_RXD_QW1_LENGTH_PBUF_MASK	(0x3FFFULL << \
-					 IAVF_RXD_QW1_LENGTH_PBUF_SHIFT)
-
 #define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT	52
 #define IAVF_RXD_QW1_LENGTH_HBUF_MASK	(0x7FFULL << \
 					 IAVF_RXD_QW1_LENGTH_HBUF_SHIFT)
@@ -347,6 +330,8 @@ enum iavf_rx_desc_ext_status_bits {
 	IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT	= 11,
 };
 
+#define IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M	BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)
+
 enum iavf_rx_desc_pe_status_bits {
 	/* Note: These are predefined bit offsets */
 	IAVF_RX_DESC_PE_STATUS_QPID_SHIFT	= 0, /* 18 BITS */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_types.h b/drivers/net/ethernet/intel/iavf/iavf_types.h
new file mode 100644
index 000000000000..a095855122bf
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_types.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IAVF_TYPES_H_
+#define _IAVF_TYPES_H_
+
+#include "iavf_types.h"
+
+#include <linux/avf/virtchnl.h>
+#include <linux/ptp_clock_kernel.h>
+
+/* structure used to queue PTP commands for processing */
+struct iavf_ptp_aq_cmd {
+	struct list_head list;
+	enum virtchnl_ops v_opcode:16;
+	u16 msglen;
+	u8 msg[] __counted_by(msglen);
+};
+
+struct iavf_ptp {
+	wait_queue_head_t phc_time_waitqueue;
+	struct virtchnl_ptp_caps hw_caps;
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct list_head aq_cmds;
+	u64 cached_phc_time;
+	unsigned long cached_phc_updated;
+	/* Lock protecting access to the AQ command list */
+	struct mutex aq_cmd_lock;
+	struct kernel_hwtstamp_config hwtstamp_config;
+	bool phc_time_ready:1;
+};
+
+#endif /* _IAVF_TYPES_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 15d388b431c5..07f0d0a0f1e2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -4,6 +4,7 @@
 #include <linux/net/intel/libie/rx.h>
 
 #include "iavf.h"
+#include "iavf_ptp.h"
 #include "iavf_prototype.h"
 
 /**
@@ -78,6 +79,23 @@ iavf_poll_virtchnl_msg(struct iavf_hw *hw, struct iavf_arq_event_info *event,
 			return iavf_status_to_errno(status);
 		received_op =
 		    (enum virtchnl_ops)le32_to_cpu(event->desc.cookie_high);
+
+		if (received_op == VIRTCHNL_OP_EVENT) {
+			struct iavf_adapter *adapter = hw->back;
+			struct virtchnl_pf_event *vpe =
+				(struct virtchnl_pf_event *)event->msg_buf;
+
+			if (vpe->event != VIRTCHNL_EVENT_RESET_IMPENDING)
+				continue;
+
+			dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n");
+			if (!(adapter->flags & IAVF_FLAG_RESET_PENDING))
+				iavf_schedule_reset(adapter,
+						    IAVF_FLAG_RESET_PENDING);
+
+			return -EIO;
+		}
+
 		if (op_to_poll == received_op)
 			break;
 	}
@@ -144,9 +162,11 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
 	       VIRTCHNL_VF_OFFLOAD_ENCAP |
 	       VIRTCHNL_VF_OFFLOAD_TC_U32 |
 	       VIRTCHNL_VF_OFFLOAD_VLAN_V2 |
+	       VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC |
 	       VIRTCHNL_VF_OFFLOAD_CRC |
 	       VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM |
 	       VIRTCHNL_VF_OFFLOAD_REQ_QUEUES |
+	       VIRTCHNL_VF_CAP_PTP |
 	       VIRTCHNL_VF_OFFLOAD_ADQ |
 	       VIRTCHNL_VF_OFFLOAD_USO |
 	       VIRTCHNL_VF_OFFLOAD_FDIR_PF |
@@ -177,6 +197,54 @@ int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter)
 				NULL, 0);
 }
 
+int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter)
+{
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS;
+
+	if (!IAVF_RXDID_ALLOWED(adapter))
+		return -EOPNOTSUPP;
+
+	adapter->current_op = VIRTCHNL_OP_GET_SUPPORTED_RXDIDS;
+
+	return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS,
+				NULL, 0);
+}
+
+/**
+ * iavf_send_vf_ptp_caps_msg - Send request for PTP capabilities
+ * @adapter: private adapter structure
+ *
+ * Send the VIRTCHNL_OP_1588_PTP_GET_CAPS command to the PF to request the PTP
+ * capabilities available to this device. This includes the following
+ * potential access:
+ *
+ * * READ_PHC - access to read the PTP hardware clock time
+ * * RX_TSTAMP - access to request Rx timestamps on all received packets
+ *
+ * The PF will reply with the same opcode a filled out copy of the
+ * virtchnl_ptp_caps structure which defines the specifics of which features
+ * are accessible to this device.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter)
+{
+	struct virtchnl_ptp_caps hw_caps = {
+		.caps = VIRTCHNL_1588_PTP_CAP_READ_PHC |
+			VIRTCHNL_1588_PTP_CAP_RX_TSTAMP
+	};
+
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_PTP_CAPS;
+
+	if (!IAVF_PTP_ALLOWED(adapter))
+		return -EOPNOTSUPP;
+
+	adapter->current_op = VIRTCHNL_OP_1588_PTP_GET_CAPS;
+
+	return iavf_send_pf_msg(adapter, VIRTCHNL_OP_1588_PTP_GET_CAPS,
+				(u8 *)&hw_caps, sizeof(hw_caps));
+}
+
 /**
  * iavf_validate_num_queues
  * @adapter: adapter structure
@@ -263,6 +331,40 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter)
 	return err;
 }
 
+int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter)
+{
+	struct iavf_arq_event_info event;
+	u64 rxdids;
+	int err;
+
+	event.msg_buf = (u8 *)&rxdids;
+	event.buf_len = sizeof(rxdids);
+
+	err = iavf_poll_virtchnl_msg(&adapter->hw, &event,
+				     VIRTCHNL_OP_GET_SUPPORTED_RXDIDS);
+	if (!err)
+		adapter->supp_rxdids = rxdids;
+
+	return err;
+}
+
+int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter)
+{
+	struct virtchnl_ptp_caps caps = {};
+	struct iavf_arq_event_info event;
+	int err;
+
+	event.msg_buf = (u8 *)&caps;
+	event.buf_len = sizeof(caps);
+
+	err = iavf_poll_virtchnl_msg(&adapter->hw, &event,
+				     VIRTCHNL_OP_1588_PTP_GET_CAPS);
+	if (!err)
+		adapter->ptp.hw_caps = caps;
+
+	return err;
+}
+
 /**
  * iavf_configure_queues
  * @adapter: adapter structure
@@ -275,6 +377,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 	int pairs = adapter->num_active_queues;
 	struct virtchnl_queue_pair_info *vqpi;
 	u32 i, max_frame;
+	u8 rx_flags = 0;
 	size_t len;
 
 	max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset);
@@ -292,6 +395,9 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 	if (!vqci)
 		return;
 
+	if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))
+		rx_flags |= VIRTCHNL_PTP_RX_TSTAMP;
+
 	vqci->vsi_id = adapter->vsi_res->vsi_id;
 	vqci->num_queue_pairs = pairs;
 	vqpi = vqci->qpair;
@@ -309,9 +415,12 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 		vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
 		vqpi->rxq.max_pkt_size = max_frame;
 		vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
+		if (IAVF_RXDID_ALLOWED(adapter))
+			vqpi->rxq.rxdid = adapter->rxdid;
 		if (CRC_OFFLOAD_ALLOWED(adapter))
 			vqpi->rxq.crc_disable = !!(adapter->netdev->features &
 						   NETIF_F_RXFCS);
+		vqpi->rxq.flags = rx_flags;
 		vqpi++;
 	}
 
@@ -1402,6 +1511,67 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid)
 				  VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2);
 }
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+/**
+ * iavf_virtchnl_send_ptp_cmd - Send one queued PTP command
+ * @adapter: adapter private structure
+ *
+ * De-queue one PTP command request and send the command message to the PF.
+ * Clear IAVF_FLAG_AQ_SEND_PTP_CMD if no more messages are left to send.
+ */
+void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+	int err;
+
+	if (!adapter->ptp.clock) {
+		/* This shouldn't be possible to hit, since no messages should
+		 * be queued if PTP is not initialized.
+		 */
+		pci_err(adapter->pdev, "PTP is not initialized\n");
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+		return;
+	}
+
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	cmd = list_first_entry_or_null(&adapter->ptp.aq_cmds,
+				       struct iavf_ptp_aq_cmd, list);
+	if (!cmd) {
+		/* no further PTP messages to send */
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+		goto out_unlock;
+	}
+
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		pci_err(adapter->pdev,
+			"Cannot send PTP command %d, command %d pending\n",
+			cmd->v_opcode, adapter->current_op);
+		goto out_unlock;
+	}
+
+	err = iavf_send_pf_msg(adapter, cmd->v_opcode, cmd->msg, cmd->msglen);
+	if (!err) {
+		/* Command was sent without errors, so we can remove it from
+		 * the list and discard it.
+		 */
+		list_del(&cmd->list);
+		kfree(cmd);
+	} else {
+		/* We failed to send the command, try again next cycle */
+		pci_err(adapter->pdev, "Failed to send PTP command %d\n",
+			cmd->v_opcode);
+	}
+
+	if (list_empty(&adapter->ptp.aq_cmds))
+		/* no further PTP messages to send */
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+
+out_unlock:
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+}
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+
 /**
  * iavf_print_link_message - print link up or down
  * @adapter: adapter structure
@@ -2098,6 +2268,37 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
 }
 
 /**
+ * iavf_virtchnl_ptp_get_time - Respond to VIRTCHNL_OP_1588_PTP_GET_TIME
+ * @adapter: private adapter structure
+ * @data: the message from the PF
+ * @len: length of the message from the PF
+ *
+ * Handle the VIRTCHNL_OP_1588_PTP_GET_TIME message from the PF. This message
+ * is sent by the PF in response to the same op as a request from the VF.
+ * Extract the 64bit nanoseconds time from the message and store it in
+ * cached_phc_time. Then, notify any thread that is waiting for the update via
+ * the wait queue.
+ */
+static void iavf_virtchnl_ptp_get_time(struct iavf_adapter *adapter,
+				       void *data, u16 len)
+{
+	struct virtchnl_phc_time *msg = data;
+
+	if (len != sizeof(*msg)) {
+		dev_err_once(&adapter->pdev->dev,
+			     "Invalid VIRTCHNL_OP_1588_PTP_GET_TIME from PF. Got size %u, expected %zu\n",
+			     len, sizeof(*msg));
+		return;
+	}
+
+	adapter->ptp.cached_phc_time = msg->time;
+	adapter->ptp.cached_phc_updated = jiffies;
+	adapter->ptp.phc_time_ready = true;
+
+	wake_up(&adapter->ptp.phc_time_waitqueue);
+}
+
+/**
  * iavf_virtchnl_completion
  * @adapter: adapter structure
  * @v_opcode: opcode sent by PF
@@ -2509,6 +2710,25 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			aq_required;
 		}
 		break;
+	case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS:
+		if (msglen != sizeof(u64))
+			return;
+
+		adapter->supp_rxdids = *(u64 *)msg;
+
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		if (msglen != sizeof(adapter->ptp.hw_caps))
+			return;
+
+		adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg;
+
+		/* process any state change needed due to new capabilities */
+		iavf_ptp_process_caps(adapter);
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		iavf_virtchnl_ptp_get_time(adapter, msg, msglen);
+		break;
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */
 		iavf_irq_enable(adapter, true);
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 3307d551f431..9e0d9f710441 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -32,7 +32,8 @@ ice-y := ice_main.o	\
 	 ice_parser_rt.o \
 	 ice_idc.o	\
 	 devlink/devlink.o	\
-	 devlink/devlink_port.o \
+	 devlink/health.o \
+	 devlink/port.o \
 	 ice_sf_eth.o	\
 	 ice_sf_vsi_vlan_ops.o \
 	 ice_ddp.o	\
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 415445cefdb2..4af60e2f37df 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -6,7 +6,7 @@
 #include "ice.h"
 #include "ice_lib.h"
 #include "devlink.h"
-#include "devlink_port.h"
+#include "port.h"
 #include "ice_eswitch.h"
 #include "ice_fw_update.h"
 #include "ice_dcb_lib.h"
@@ -368,14 +368,18 @@ static int ice_devlink_info_get(struct devlink *devlink,
 			}
 			break;
 		case ICE_VERSION_RUNNING:
-			err = devlink_info_version_running_put(req, key, ctx->buf);
+			err = devlink_info_version_running_put_ext(req, key,
+								   ctx->buf,
+								   DEVLINK_INFO_VERSION_TYPE_COMPONENT);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Unable to set running version");
 				goto out_free_ctx;
 			}
 			break;
 		case ICE_VERSION_STORED:
-			err = devlink_info_version_stored_put(req, key, ctx->buf);
+			err = devlink_info_version_stored_put_ext(req, key,
+								  ctx->buf,
+								  DEVLINK_INFO_VERSION_TYPE_COMPONENT);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Unable to set stored version");
 				goto out_free_ctx;
@@ -977,6 +981,9 @@ static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv
 
 	/* preallocate memory for ice_sched_node */
 	node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
 	*priv = node;
 
 	return 0;
@@ -1198,6 +1205,25 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate,
 	return status;
 }
 
+static void ice_set_min_max_msix(struct ice_pf *pf)
+{
+	struct devlink *devlink = priv_to_devlink(pf);
+	union devlink_param_value val;
+	int err;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+					      &val);
+	if (!err)
+		pf->msix.min = val.vu32;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+					      &val);
+	if (!err)
+		pf->msix.max = val.vu32;
+}
+
 /**
  * ice_devlink_reinit_up - do reinit of the given PF
  * @pf: pointer to the PF struct
@@ -1207,9 +1233,18 @@ static int ice_devlink_reinit_up(struct ice_pf *pf)
 	struct ice_vsi *vsi = ice_get_main_vsi(pf);
 	int err;
 
+	err = ice_init_hw(&pf->hw);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err);
+		return err;
+	}
+
+	/* load MSI-X values */
+	ice_set_min_max_msix(pf);
+
 	err = ice_init_dev(pf);
 	if (err)
-		return err;
+		goto unroll_hw_init;
 
 	vsi->flags = ICE_VSI_FLAG_INIT;
 
@@ -1232,6 +1267,8 @@ err_load:
 	rtnl_unlock();
 err_vsi_cfg:
 	ice_deinit_dev(pf);
+unroll_hw_init:
+	ice_deinit_hw(&pf->hw);
 	return err;
 }
 
@@ -1302,8 +1339,13 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id,
 			    struct devlink_param_gset_ctx *ctx)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
+
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
 
-	ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? true : false;
+	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2);
 
 	return 0;
 }
@@ -1313,19 +1355,24 @@ static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id,
 				       struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 	bool roce_ena = ctx->val.vbool;
 	int ret;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	if (!roce_ena) {
 		ice_unplug_aux_dev(pf);
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
 		return 0;
 	}
 
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2;
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
 
 	return ret;
 }
@@ -1336,11 +1383,16 @@ ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id,
 				 struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
+
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
 
 	if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
-	if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP) {
+	if (cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP) {
 		NL_SET_ERR_MSG_MOD(extack, "iWARP is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously");
 		return -EOPNOTSUPP;
 	}
@@ -1353,8 +1405,13 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id,
 			  struct devlink_param_gset_ctx *ctx)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 
-	ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP;
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
+	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP);
 
 	return 0;
 }
@@ -1364,19 +1421,24 @@ static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id,
 				     struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 	bool iw_ena = ctx->val.vbool;
 	int ret;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	if (!iw_ena) {
 		ice_unplug_aux_dev(pf);
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP;
 		return 0;
 	}
 
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_IWARP;
+	cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_IWARP;
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP;
 
 	return ret;
 }
@@ -1391,7 +1453,7 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id,
 	if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
-	if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2) {
+	if (pf->cdev_info->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2) {
 		NL_SET_ERR_MSG_MOD(extack, "RoCEv2 is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously");
 		return -EOPNOTSUPP;
 	}
@@ -1518,6 +1580,43 @@ static int ice_devlink_local_fwd_validate(struct devlink *devlink, u32 id,
 	return 0;
 }
 
+static int
+ice_devlink_msix_max_pf_validate(struct devlink *devlink, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+
+	if (val.vu32 > pf->hw.func_caps.common_cap.num_msix_vectors)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	if (val.vu32 < ICE_MIN_MSIX)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ice_devlink_enable_rdma_validate(struct devlink *devlink, u32 id,
+					    union devlink_param_value val,
+					    struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+	bool new_state = val.vbool;
+
+	if (new_state && !test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 enum ice_param_id {
 	ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
@@ -1533,6 +1632,17 @@ static const struct devlink_param ice_dvl_rdma_params[] = {
 			      ice_devlink_enable_iw_get,
 			      ice_devlink_enable_iw_set,
 			      ice_devlink_enable_iw_validate),
+	DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_enable_rdma_validate),
+};
+
+static const struct devlink_param ice_dvl_msix_params[] = {
+	DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_msix_max_pf_validate),
+	DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_msix_min_pf_validate),
 };
 
 static const struct devlink_param ice_dvl_sched_params[] = {
@@ -1636,6 +1746,7 @@ void ice_devlink_unregister(struct ice_pf *pf)
 int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
+	union devlink_param_value value;
 	struct ice_hw *hw = &pf->hw;
 	int status;
 
@@ -1644,10 +1755,39 @@ int ice_devlink_register_params(struct ice_pf *pf)
 	if (status)
 		return status;
 
+	status = devl_params_register(devlink, ice_dvl_msix_params,
+				      ARRAY_SIZE(ice_dvl_msix_params));
+	if (status)
+		goto unregister_rdma_params;
+
 	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
 		status = devl_params_register(devlink, ice_dvl_sched_params,
 					      ARRAY_SIZE(ice_dvl_sched_params));
+	if (status)
+		goto unregister_msix_params;
+
+	value.vu32 = pf->msix.max;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+					value);
+	value.vu32 = pf->msix.min;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+					value);
+
+	value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+					value);
 
+	return 0;
+
+unregister_msix_params:
+	devl_params_unregister(devlink, ice_dvl_msix_params,
+			       ARRAY_SIZE(ice_dvl_msix_params));
+unregister_rdma_params:
+	devl_params_unregister(devlink, ice_dvl_rdma_params,
+			       ARRAY_SIZE(ice_dvl_rdma_params));
 	return status;
 }
 
@@ -1658,6 +1798,8 @@ void ice_devlink_unregister_params(struct ice_pf *pf)
 
 	devl_params_unregister(devlink, ice_dvl_rdma_params,
 			       ARRAY_SIZE(ice_dvl_rdma_params));
+	devl_params_unregister(devlink, ice_dvl_msix_params,
+			       ARRAY_SIZE(ice_dvl_msix_params));
 
 	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
 		devl_params_unregister(devlink, ice_dvl_sched_params,
diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c
new file mode 100644
index 000000000000..19c3d37aa768
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/devlink/health.c
@@ -0,0 +1,550 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_adminq_cmd.h" /* for enum ice_aqc_health_status_elem */
+#include "health.h"
+
+#define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \
+	devlink_fmsg_put(fmsg, #name, (obj)->name)
+
+#define ICE_HEALTH_STATUS_DATA_SIZE 2
+
+struct ice_health_status {
+	enum ice_aqc_health_status code;
+	const char *description;
+	const char *solution;
+	const char *data_label[ICE_HEALTH_STATUS_DATA_SIZE];
+};
+
+/*
+ * In addition to the health status codes provided below, the firmware might
+ * generate Health Status Codes that are not pertinent to the end-user.
+ * For instance, Health Code 0x1002 is triggered when the command fails.
+ * Such codes should be disregarded by the end-user.
+ * The below lookup requires to be sorted by code.
+ */
+
+static const char ice_common_port_solutions[] =
+	"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.";
+static const char ice_port_number_label[] = "Port Number";
+static const char ice_update_nvm_solution[] = "Update to the latest NVM image.";
+
+static const struct ice_health_status ice_health_status_lookup[] = {
+	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE, "Module type is not supported.",
+		"Change or replace the module or cable.", {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL, "Module is not qualified.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM,
+		"Device cannot communicate with the module.",
+		"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT, "Unresolved module conflict.",
+		"Manually set speed/duplex or change the port option. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT, "Module is not present.",
+		"Check that the module is inserted correctly. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED, "Underutilized module.",
+		"Change or replace the module or cable. Change the port option.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT, "An unsupported module was detected.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG, "Invalid link configuration.",
+		NULL, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS, "Port hardware access error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE, "A port is unreachable.",
+		"Change the port option. Update to the latest NVM image."},
+	{ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED, "Port speed is limited due to module.",
+		"Change the module or configure the port option to match the current module speed. Change the port option.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT,
+		"All configured link modes were attempted but failed to establish link. The device will restart the process to establish link.",
+		"Check link partner connection and configuration.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED,
+		"Port speed is limited by PHY capabilities.",
+		"Change the module to align to port option.", {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO, "LOM topology netlist is corrupted.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NETLIST, "Unrecoverable netlist error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT, "Port topology conflict.",
+		"Change the port option. Update to the latest NVM image."},
+	{ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS, "Unrecoverable hardware access error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME, "Unrecoverable runtime error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT, "Link management engine failed to initialize.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD,
+		"Failed to load the firmware image in the external PHY.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_RECOVERY, "The device is in firmware recovery mode.",
+		ice_update_nvm_solution, {"Extended Error"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS, "The flash chip cannot be accessed.",
+		"If issue persists, call customer support.", {"Access Type"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH, "NVM authentication failed.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH, "Option ROM authentication failed.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH, "DDP package authentication failed.",
+		"Update to latest base driver and DDP package."},
+	{ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT, "NVM image is incompatible.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT, "Option ROM is incompatible.",
+		ice_update_nvm_solution, {"Expected PCI Device ID", "Expected Module ID"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB,
+		"Supplied MIB file is invalid. DCB reverted to default configuration.",
+		"Disable FW-LLDP and check DCBx system configuration.",
+		{ice_port_number_label, "MIB ID"}},
+};
+
+static int ice_health_status_lookup_compare(const void *a, const void *b)
+{
+	return ((struct ice_health_status *)a)->code - ((struct ice_health_status *)b)->code;
+}
+
+static const struct ice_health_status *ice_get_health_status(u16 code)
+{
+	struct ice_health_status key = { .code = code };
+
+	return bsearch(&key, ice_health_status_lookup, ARRAY_SIZE(ice_health_status_lookup),
+		       sizeof(struct ice_health_status), ice_health_status_lookup_compare);
+}
+
+static void ice_describe_status_code(struct devlink_fmsg *fmsg,
+				     struct ice_aqc_health_status_elem *hse)
+{
+	static const char *const aux_label[] = { "Aux Data 1", "Aux Data 2" };
+	const struct ice_health_status *health_code;
+	u32 internal_data[2];
+	u16 status_code;
+
+	status_code = le16_to_cpu(hse->health_status_code);
+
+	devlink_fmsg_put(fmsg, "Syndrome", status_code);
+	if (status_code) {
+		internal_data[0] = le32_to_cpu(hse->internal_data1);
+		internal_data[1] = le32_to_cpu(hse->internal_data2);
+
+		health_code = ice_get_health_status(status_code);
+		if (!health_code)
+			return;
+
+		devlink_fmsg_string_pair_put(fmsg, "Description", health_code->description);
+		if (health_code->solution)
+			devlink_fmsg_string_pair_put(fmsg, "Possible Solution",
+						     health_code->solution);
+
+		for (size_t i = 0; i < ICE_HEALTH_STATUS_DATA_SIZE; i++) {
+			if (internal_data[i] != ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA)
+				devlink_fmsg_u32_pair_put(fmsg,
+							  health_code->data_label[i] ?
+							  health_code->data_label[i] :
+							  aux_label[i],
+							  internal_data[i]);
+		}
+	}
+}
+
+static int
+ice_port_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+			   struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.port_status);
+	return 0;
+}
+
+static int
+ice_port_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+		       void *priv_ctx, struct netlink_ext_ack __always_unused *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.port_status);
+	return 0;
+}
+
+static int
+ice_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+			 struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.fw_status);
+	return 0;
+}
+
+static int
+ice_fw_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+		     void *priv_ctx, struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.fw_status);
+	return 0;
+}
+
+static void ice_config_health_events(struct ice_pf *pf, bool enable)
+{
+	u8 enable_bits = 0;
+	int ret;
+
+	if (enable)
+		enable_bits = ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK |
+			      ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK;
+
+	ret = ice_aq_set_health_status_cfg(&pf->hw, enable_bits);
+	if (ret)
+		dev_err(ice_pf_to_dev(pf), "Failed to %s firmware health events, err %d aq_err %s\n",
+			str_enable_disable(enable), ret,
+			ice_aq_str(pf->hw.adminq.sq_last_status));
+}
+
+/**
+ * ice_process_health_status_event - Process the health status event from FW
+ * @pf: pointer to the PF structure
+ * @event: event structure containing the Health Status Event opcode
+ *
+ * Decode the Health Status Events and print the associated messages
+ */
+void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+	const struct ice_aqc_health_status_elem *health_info;
+	u16 count;
+
+	health_info = (struct ice_aqc_health_status_elem *)event->msg_buf;
+	count = le16_to_cpu(event->desc.params.get_health_status.health_status_count);
+
+	if (count > (event->buf_len / sizeof(*health_info))) {
+		dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n");
+		return;
+	}
+
+	for (size_t i = 0; i < count; i++) {
+		const struct ice_health_status *health_code;
+		u16 status_code;
+
+		status_code = le16_to_cpu(health_info->health_status_code);
+		health_code = ice_get_health_status(status_code);
+
+		if (health_code) {
+			switch (le16_to_cpu(health_info->event_source)) {
+			case ICE_AQC_HEALTH_STATUS_GLOBAL:
+				pf->health_reporters.fw_status = *health_info;
+				devlink_health_report(pf->health_reporters.fw,
+						      "FW syndrome reported", NULL);
+				break;
+			case ICE_AQC_HEALTH_STATUS_PF:
+			case ICE_AQC_HEALTH_STATUS_PORT:
+				pf->health_reporters.port_status = *health_info;
+				devlink_health_report(pf->health_reporters.port,
+						      "Port syndrome reported", NULL);
+				break;
+			default:
+				dev_err(ice_pf_to_dev(pf), "Health code with unknown source\n");
+			}
+		} else {
+			u32 data1, data2;
+			u16 source;
+
+			source = le16_to_cpu(health_info->event_source);
+			data1 = le32_to_cpu(health_info->internal_data1);
+			data2 = le32_to_cpu(health_info->internal_data2);
+			dev_dbg(ice_pf_to_dev(pf),
+				"Received internal health status code 0x%08x, source: 0x%08x, data1: 0x%08x, data2: 0x%08x",
+				status_code, source, data1, data2);
+		}
+		health_info++;
+	}
+}
+
+/**
+ * ice_devlink_health_report - boilerplate to call given @reporter
+ *
+ * @reporter: devlink health reporter to call, do nothing on NULL
+ * @msg: message to pass up, "event name" is fine
+ * @priv_ctx: typically some event struct
+ */
+static void ice_devlink_health_report(struct devlink_health_reporter *reporter,
+				      const char *msg, void *priv_ctx)
+{
+	if (!reporter)
+		return;
+
+	/* We do not do auto recovering, so return value of the below function
+	 * will always be 0, thus we do ignore it.
+	 */
+	devlink_health_report(reporter, msg, priv_ctx);
+}
+
+struct ice_mdd_event {
+	enum ice_mdd_src src;
+	u16 vf_num;
+	u16 queue;
+	u8 pf_num;
+	u8 event;
+};
+
+static const char *ice_mdd_src_to_str(enum ice_mdd_src src)
+{
+	switch (src) {
+	case ICE_MDD_SRC_TX_PQM:
+		return "tx_pqm";
+	case ICE_MDD_SRC_TX_TCLAN:
+		return "tx_tclan";
+	case ICE_MDD_SRC_TX_TDPU:
+		return "tx_tdpu";
+	case ICE_MDD_SRC_RX:
+		return "rx";
+	default:
+		return "invalid";
+	}
+}
+
+static int
+ice_mdd_reporter_dump(struct devlink_health_reporter *reporter,
+		      struct devlink_fmsg *fmsg, void *priv_ctx,
+		      struct netlink_ext_ack *extack)
+{
+	struct ice_mdd_event *mdd_event = priv_ctx;
+	const char *src;
+
+	if (!mdd_event)
+		return 0;
+
+	src = ice_mdd_src_to_str(mdd_event->src);
+
+	devlink_fmsg_obj_nest_start(fmsg);
+	devlink_fmsg_put(fmsg, "src", src);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, pf_num);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, vf_num);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, event);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, queue);
+	devlink_fmsg_obj_nest_end(fmsg);
+
+	return 0;
+}
+
+/**
+ * ice_report_mdd_event - Report an MDD event through devlink health
+ * @pf: the PF device structure
+ * @src: the HW block that was the source of this MDD event
+ * @pf_num: the pf_num on which the MDD event occurred
+ * @vf_num: the vf_num on which the MDD event occurred
+ * @event: the event type of the MDD event
+ * @queue: the queue on which the MDD event occurred
+ *
+ * Report an MDD event that has occurred on this PF.
+ */
+void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num,
+			  u16 vf_num, u8 event, u16 queue)
+{
+	struct ice_mdd_event ev = {
+		.src = src,
+		.pf_num = pf_num,
+		.vf_num = vf_num,
+		.event = event,
+		.queue = queue,
+	};
+
+	ice_devlink_health_report(pf->health_reporters.mdd, "MDD event", &ev);
+}
+
+/**
+ * ice_fmsg_put_ptr - put hex value of pointer into fmsg
+ *
+ * @fmsg: devlink fmsg under construction
+ * @name: name to pass
+ * @ptr: 64 bit value to print as hex and put into fmsg
+ */
+static void ice_fmsg_put_ptr(struct devlink_fmsg *fmsg, const char *name,
+			     void *ptr)
+{
+	char buf[sizeof(ptr) * 3];
+
+	sprintf(buf, "%p", ptr);
+	devlink_fmsg_put(fmsg, name, buf);
+}
+
+struct ice_tx_hang_event {
+	u32 head;
+	u32 intr;
+	u16 vsi_num;
+	u16 queue;
+	u16 next_to_clean;
+	u16 next_to_use;
+	struct ice_tx_ring *tx_ring;
+};
+
+static int ice_tx_hang_reporter_dump(struct devlink_health_reporter *reporter,
+				     struct devlink_fmsg *fmsg, void *priv_ctx,
+				     struct netlink_ext_ack *extack)
+{
+	struct ice_tx_hang_event *event = priv_ctx;
+	struct sk_buff *skb;
+
+	if (!event)
+		return 0;
+
+	skb = event->tx_ring->tx_buf->skb;
+	devlink_fmsg_obj_nest_start(fmsg);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, head);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, intr);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, vsi_num);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, queue);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_clean);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_use);
+	devlink_fmsg_put(fmsg, "irq-mapping", event->tx_ring->q_vector->name);
+	ice_fmsg_put_ptr(fmsg, "desc-ptr", event->tx_ring->desc);
+	ice_fmsg_put_ptr(fmsg, "dma-ptr", (void *)(long)event->tx_ring->dma);
+	ice_fmsg_put_ptr(fmsg, "skb-ptr", skb);
+	devlink_fmsg_binary_pair_put(fmsg, "desc", event->tx_ring->desc,
+				     event->tx_ring->count * sizeof(struct ice_tx_desc));
+	devlink_fmsg_dump_skb(fmsg, skb);
+	devlink_fmsg_obj_nest_end(fmsg);
+
+	return 0;
+}
+
+void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring,
+			     u16 vsi_num, u32 head, u32 intr)
+{
+	struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf;
+
+	buf->tx_ring = tx_ring;
+	buf->vsi_num = vsi_num;
+	buf->head = head;
+	buf->intr = intr;
+}
+
+void ice_report_tx_hang(struct ice_pf *pf)
+{
+	struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf;
+	struct ice_tx_ring *tx_ring = buf->tx_ring;
+
+	struct ice_tx_hang_event ev = {
+		.head = buf->head,
+		.intr = buf->intr,
+		.vsi_num = buf->vsi_num,
+		.queue = tx_ring->q_index,
+		.next_to_clean = tx_ring->next_to_clean,
+		.next_to_use = tx_ring->next_to_use,
+		.tx_ring = tx_ring,
+	};
+
+	ice_devlink_health_report(pf->health_reporters.tx_hang, "Tx hang", &ev);
+}
+
+static struct devlink_health_reporter *
+ice_init_devlink_rep(struct ice_pf *pf,
+		     const struct devlink_health_reporter_ops *ops)
+{
+	struct devlink *devlink = priv_to_devlink(pf);
+	struct devlink_health_reporter *rep;
+	const u64 graceful_period = 0;
+
+	rep = devl_health_reporter_create(devlink, ops, graceful_period, pf);
+	if (IS_ERR(rep)) {
+		struct device *dev = ice_pf_to_dev(pf);
+
+		dev_err(dev, "failed to create devlink %s health report er",
+			ops->name);
+		return NULL;
+	}
+	return rep;
+}
+
+#define ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field) \
+	._field = ice_##_name##_reporter_##_field,
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS_1(_name, _field1) \
+	static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \
+	.name = #_name, \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \
+	}
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS_2(_name, _field1, _field2) \
+	static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \
+	.name = #_name, \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field2) \
+	}
+
+ICE_DEFINE_HEALTH_REPORTER_OPS_1(mdd, dump);
+ICE_DEFINE_HEALTH_REPORTER_OPS_1(tx_hang, dump);
+ICE_DEFINE_HEALTH_REPORTER_OPS_2(fw, dump, diagnose);
+ICE_DEFINE_HEALTH_REPORTER_OPS_2(port, dump, diagnose);
+
+/**
+ * ice_health_init - allocate and init all ice devlink health reporters and
+ * accompanied data
+ *
+ * @pf: PF struct
+ */
+void ice_health_init(struct ice_pf *pf)
+{
+	struct ice_health *reps = &pf->health_reporters;
+
+	reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops);
+	reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops);
+
+	if (ice_is_fw_health_report_supported(&pf->hw)) {
+		reps->fw = ice_init_devlink_rep(pf, &ice_fw_reporter_ops);
+		reps->port = ice_init_devlink_rep(pf, &ice_port_reporter_ops);
+		ice_config_health_events(pf, true);
+	}
+}
+
+/**
+ * ice_deinit_devl_reporter - destroy given devlink health reporter
+ * @reporter: reporter to destroy
+ */
+static void ice_deinit_devl_reporter(struct devlink_health_reporter *reporter)
+{
+	if (reporter)
+		devl_health_reporter_destroy(reporter);
+}
+
+/**
+ * ice_health_deinit - deallocate all ice devlink health reporters and
+ * accompanied data
+ *
+ * @pf: PF struct
+ */
+void ice_health_deinit(struct ice_pf *pf)
+{
+	ice_deinit_devl_reporter(pf->health_reporters.mdd);
+	ice_deinit_devl_reporter(pf->health_reporters.tx_hang);
+	if (ice_is_fw_health_report_supported(&pf->hw)) {
+		ice_deinit_devl_reporter(pf->health_reporters.fw);
+		ice_deinit_devl_reporter(pf->health_reporters.port);
+		ice_config_health_events(pf, false);
+	}
+}
+
+static
+void ice_health_assign_healthy_state(struct devlink_health_reporter *reporter)
+{
+	if (reporter)
+		devlink_health_reporter_state_update(reporter,
+						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+}
+
+/**
+ * ice_health_clear - clear devlink health issues after a reset
+ * @pf: the PF device structure
+ *
+ * Mark the PF in healthy state again after a reset has completed.
+ */
+void ice_health_clear(struct ice_pf *pf)
+{
+	ice_health_assign_healthy_state(pf->health_reporters.mdd);
+	ice_health_assign_healthy_state(pf->health_reporters.tx_hang);
+}
diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h
new file mode 100644
index 000000000000..5edfc4d2adce
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/devlink/health.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2024, Intel Corporation. */
+
+#ifndef _HEALTH_H_
+#define _HEALTH_H_
+
+#include <linux/types.h>
+
+/**
+ * DOC: health.h
+ *
+ * This header file stores everything that is needed for broadly understood
+ * devlink health mechanism for ice driver.
+ */
+
+struct ice_aqc_health_status_elem;
+struct ice_pf;
+struct ice_tx_ring;
+struct ice_rq_event_info;
+
+enum ice_mdd_src {
+	ICE_MDD_SRC_TX_PQM,
+	ICE_MDD_SRC_TX_TCLAN,
+	ICE_MDD_SRC_TX_TDPU,
+	ICE_MDD_SRC_RX,
+};
+
+/**
+ * struct ice_health - stores ice devlink health reporters and accompanied data
+ * @fw: devlink health reporter for FW Health Status events
+ * @mdd: devlink health reporter for MDD detection event
+ * @port: devlink health reporter for Port Health Status events
+ * @tx_hang: devlink health reporter for tx_hang event
+ * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from
+ *               non-sleeping context
+ * @tx_ring: ring that the hang occurred on
+ * @head: descriptor head
+ * @intr: interrupt register value
+ * @vsi_num: VSI owning the queue that the hang occurred on
+ * @fw_status: buffer for last received FW Status event
+ * @port_status: buffer for last received Port Status event
+ */
+struct ice_health {
+	struct devlink_health_reporter *fw;
+	struct devlink_health_reporter *mdd;
+	struct devlink_health_reporter *port;
+	struct devlink_health_reporter *tx_hang;
+	struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf,
+		struct ice_tx_ring *tx_ring;
+		u32 head;
+		u32 intr;
+		u16 vsi_num;
+	);
+	struct ice_aqc_health_status_elem fw_status;
+	struct ice_aqc_health_status_elem port_status;
+};
+
+void ice_process_health_status_event(struct ice_pf *pf,
+				     struct ice_rq_event_info *event);
+
+void ice_health_init(struct ice_pf *pf);
+void ice_health_deinit(struct ice_pf *pf);
+void ice_health_clear(struct ice_pf *pf);
+
+void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring,
+			     u16 vsi_num, u32 head, u32 intr);
+void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num,
+			  u16 vf_num, u8 event, u16 queue);
+void ice_report_tx_hang(struct ice_pf *pf);
+
+#endif /* _HEALTH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/port.c
index c6779d9dffff..767419a67fef 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/port.c
@@ -5,7 +5,7 @@
 
 #include "ice.h"
 #include "devlink.h"
-#include "devlink_port.h"
+#include "port.h"
 #include "ice_lib.h"
 #include "ice_fltr.h"
 
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/port.h
index d60efc340945..d60efc340945 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
+++ b/drivers/net/ethernet/intel/ice/devlink/port.h
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 2f5d6f974185..ddd0ad68185b 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -78,6 +78,7 @@
 #include "ice_irq.h"
 #include "ice_dpll.h"
 #include "ice_adapter.h"
+#include "devlink/health.h"
 
 #define ICE_BAR0		0
 #define ICE_REQ_DESC_MULTIPLE	32
@@ -96,9 +97,6 @@
 #define ICE_MIN_LAN_OICR_MSIX	1
 #define ICE_MIN_MSIX		(ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX)
 #define ICE_FDIR_MSIX		2
-#define ICE_RDMA_NUM_AEQ_MSIX	4
-#define ICE_MIN_RDMA_MSIX	2
-#define ICE_ESWITCH_MSIX	1
 #define ICE_NO_VSI		0xffff
 #define ICE_VSI_MAP_CONTIG	0
 #define ICE_VSI_MAP_SCATTER	1
@@ -195,14 +193,13 @@
 
 #define ice_pf_to_dev(pf) (&((pf)->pdev->dev))
 
-#define ice_pf_src_tmr_owned(pf) ((pf)->hw.func_caps.ts_func_info.src_tmr_owned)
-
 enum ice_feature {
 	ICE_F_DSCP,
 	ICE_F_PHY_RCLK,
 	ICE_F_SMA_CTRL,
 	ICE_F_CGU,
 	ICE_F_GNSS,
+	ICE_F_GCS,
 	ICE_F_ROCE_LAG,
 	ICE_F_SRIOV_LAG,
 	ICE_F_MBX_LIMIT,
@@ -402,7 +399,6 @@ struct ice_vsi {
 	u16 req_rxq;			 /* User requested Rx queues */
 	u16 num_rx_desc;
 	u16 num_tx_desc;
-	u16 qset_handle[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_tc_cfg tc_cfg;
 	struct bpf_prog *xdp_prog;
 	struct ice_tx_ring **xdp_rings;	 /* XDP ring array */
@@ -477,9 +473,6 @@ struct ice_q_vector {
 	struct ice_ring_container rx;
 	struct ice_ring_container tx;
 
-	cpumask_t affinity_mask;
-	struct irq_affinity_notify affinity_notify;
-
 	struct ice_channel *ch;
 
 	char name[ICE_INT_NAME_STR_LEN];
@@ -519,6 +512,7 @@ enum ice_pf_flags {
 	ICE_FLAG_MTU_CHANGED,
 	ICE_FLAG_GNSS,			/* GNSS successfully initialized */
 	ICE_FLAG_DPLL,			/* SyncE/PTP dplls initialized */
+	ICE_FLAG_LLDP_AQ_FLTR,
 	ICE_PF_FLAGS_NBITS		/* must be last */
 };
 
@@ -541,6 +535,14 @@ struct ice_agg_node {
 	u8 valid;
 };
 
+struct ice_pf_msix {
+	u32 cur;
+	u32 min;
+	u32 max;
+	u32 total;
+	u32 rest;
+};
+
 struct ice_pf {
 	struct pci_dev *pdev;
 	struct ice_adapter *adapter;
@@ -553,15 +555,8 @@ struct ice_pf {
 	struct devlink_port devlink_port;
 
 	/* OS reserved IRQ details */
-	struct msix_entry *msix_entries;
 	struct ice_irq_tracker irq_tracker;
-	/* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
-	 * number of MSIX vectors needed for all SR-IOV VFs from the number of
-	 * MSIX vectors allowed on this PF.
-	 */
-	u16 sriov_base_vector;
-	unsigned long *sriov_irq_bm;	/* bitmap to track irq usage */
-	u16 sriov_irq_size;		/* size of the irq_bm bitmap */
+	struct ice_virt_irq_tracker virt_irq_tracker;
 
 	u16 ctrl_vsi_idx;		/* control VSI index in pf->vsi array */
 
@@ -594,7 +589,6 @@ struct ice_pf {
 	struct gnss_serial *gnss_serial;
 	struct gnss_device *gnss_dev;
 	u16 num_rdma_msix;		/* Total MSIX vectors for RDMA driver */
-	u16 rdma_base_vector;
 
 	/* spinlock to protect the AdminQ wait list */
 	spinlock_t aq_wait_lock;
@@ -611,7 +605,7 @@ struct ice_pf {
 	struct msi_map ll_ts_irq;	/* LL_TS interrupt MSIX vector */
 	u16 max_pf_txqs;	/* Total Tx queues PF wide */
 	u16 max_pf_rxqs;	/* Total Rx queues PF wide */
-	u16 num_lan_msix;	/* Total MSIX vectors for base driver */
+	struct ice_pf_msix msix;
 	u16 num_lan_tx;		/* num LAN Tx queues setup */
 	u16 num_lan_rx;		/* num LAN Rx queues setup */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
@@ -627,14 +621,12 @@ struct ice_pf {
 	struct ice_hw_port_stats stats_prev;
 	struct ice_hw hw;
 	u8 stat_prev_loaded:1; /* has previous stats been loaded */
-	u8 rdma_mode;
 	u16 dcbx_cap;
 	u32 tx_timeout_count;
 	unsigned long tx_timeout_last_recovery;
 	u32 tx_timeout_recovery_level;
 	char int_name[ICE_INT_NAME_STR_LEN];
 	char int_name_ll_ts[ICE_INT_NAME_STR_LEN];
-	struct auxiliary_device *adev;
 	int aux_idx;
 	u32 sw_int_count;
 	/* count of tc_flower filters specific to channel (aka where filter
@@ -665,6 +657,8 @@ struct ice_pf {
 	struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES];
 	struct ice_dplls dplls;
 	struct device *hwmon_dev;
+	struct ice_health health_reporters;
+	struct iidc_rdma_core_dev_info *cdev_info;
 
 	u8 num_quanta_prof_used;
 };
@@ -1045,10 +1039,63 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
 	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
 }
 
-static inline enum ice_phy_model ice_get_phy_model(const struct ice_hw *hw)
+extern const struct xdp_metadata_ops ice_xdp_md_ops;
+
+/**
+ * ice_is_dual - Check if given config is multi-NAC
+ * @hw: pointer to HW structure
+ *
+ * Return: true if the device is running in mutli-NAC (Network
+ * Acceleration Complex) configuration variant, false otherwise
+ * (always false for non-E825 devices).
+ */
+static inline bool ice_is_dual(struct ice_hw *hw)
 {
-	return hw->ptp.phy_model;
+	return hw->mac_type == ICE_MAC_GENERIC_3K_E825 &&
+	       (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M);
 }
 
-extern const struct xdp_metadata_ops ice_xdp_md_ops;
+/**
+ * ice_is_primary - Check if given device belongs to the primary complex
+ * @hw: pointer to HW structure
+ *
+ * Check if given PF/HW is running on primary complex in multi-NAC
+ * configuration.
+ *
+ * Return: true if the device is dual, false otherwise (always true
+ * for non-E825 devices).
+ */
+static inline bool ice_is_primary(struct ice_hw *hw)
+{
+	return hw->mac_type != ICE_MAC_GENERIC_3K_E825 ||
+	       !ice_is_dual(hw) ||
+	       (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M);
+}
+
+/**
+ * ice_pf_src_tmr_owned - Check if a primary timer is owned by PF
+ * @pf: pointer to PF structure
+ *
+ * Return: true if PF owns primary timer, false otherwise.
+ */
+static inline bool ice_pf_src_tmr_owned(struct ice_pf *pf)
+{
+	return pf->hw.func_caps.ts_func_info.src_tmr_owned &&
+	       ice_is_primary(&pf->hw);
+}
+
+/**
+ * ice_get_primary_hw - Get pointer to primary ice_hw structure
+ * @pf: pointer to PF structure
+ *
+ * Return: A pointer to ice_hw structure with access to timesync
+ * register space.
+ */
+static inline struct ice_hw *ice_get_primary_hw(struct ice_pf *pf)
+{
+	if (!pf->adapter->ctrl_pf)
+		return &pf->hw;
+	else
+		return &pf->adapter->ctrl_pf->hw;
+}
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
index 01a08cfd0090..66e070095d1b 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.c
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 // SPDX-FileCopyrightText: Copyright Red Hat
 
-#include <linux/bitfield.h>
 #include <linux/cleanup.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
@@ -14,32 +13,16 @@
 static DEFINE_XARRAY(ice_adapters);
 static DEFINE_MUTEX(ice_adapters_mutex);
 
-/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */
-#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13)
-#define INDEX_FIELD_DEV    GENMASK(31, 16)
-#define INDEX_FIELD_BUS    GENMASK(12, 5)
-#define INDEX_FIELD_SLOT   GENMASK(4, 0)
-
-static unsigned long ice_adapter_index(const struct pci_dev *pdev)
+static unsigned long ice_adapter_index(u64 dsn)
 {
-	unsigned int domain = pci_domain_nr(pdev->bus);
-
-	WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN));
-
-	switch (pdev->device) {
-	case ICE_DEV_ID_E825C_BACKPLANE:
-	case ICE_DEV_ID_E825C_QSFP:
-	case ICE_DEV_ID_E825C_SFP:
-	case ICE_DEV_ID_E825C_SGMII:
-		return FIELD_PREP(INDEX_FIELD_DEV, pdev->device);
-	default:
-		return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) |
-		       FIELD_PREP(INDEX_FIELD_BUS,    pdev->bus->number) |
-		       FIELD_PREP(INDEX_FIELD_SLOT,   PCI_SLOT(pdev->devfn));
-	}
+#if BITS_PER_LONG == 64
+	return dsn;
+#else
+	return (u32)dsn ^ (u32)(dsn >> 32);
+#endif
 }
 
-static struct ice_adapter *ice_adapter_new(void)
+static struct ice_adapter *ice_adapter_new(u64 dsn)
 {
 	struct ice_adapter *adapter;
 
@@ -47,6 +30,7 @@ static struct ice_adapter *ice_adapter_new(void)
 	if (!adapter)
 		return NULL;
 
+	adapter->device_serial_number = dsn;
 	spin_lock_init(&adapter->ptp_gltsyn_time_lock);
 	refcount_set(&adapter->refcount, 1);
 
@@ -77,23 +61,26 @@ static void ice_adapter_free(struct ice_adapter *adapter)
  * Return:  Pointer to ice_adapter on success.
  *          ERR_PTR() on error. -ENOMEM is the only possible error.
  */
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
 {
-	unsigned long index = ice_adapter_index(pdev);
+	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
+	unsigned long index;
 	int err;
 
+	index = ice_adapter_index(dsn);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL);
 		if (err == -EBUSY) {
 			adapter = xa_load(&ice_adapters, index);
 			refcount_inc(&adapter->refcount);
+			WARN_ON_ONCE(adapter->device_serial_number != dsn);
 			return adapter;
 		}
 		if (err)
 			return ERR_PTR(err);
 
-		adapter = ice_adapter_new();
+		adapter = ice_adapter_new(dsn);
 		if (!adapter)
 			return ERR_PTR(-ENOMEM);
 		xa_store(&ice_adapters, index, adapter, GFP_KERNEL);
@@ -110,11 +97,13 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
  *
  * Context: Process, may sleep.
  */
-void ice_adapter_put(const struct pci_dev *pdev)
+void ice_adapter_put(struct pci_dev *pdev)
 {
-	unsigned long index = ice_adapter_index(pdev);
+	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
+	unsigned long index;
 
+	index = ice_adapter_index(dsn);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		adapter = xa_load(&ice_adapters, index);
 		if (WARN_ON(!adapter))
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
index e233225848b3..ac15c0d2bc1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.h
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -32,6 +32,7 @@ struct ice_port_list {
  * @refcount: Reference count. struct ice_pf objects hold the references.
  * @ctrl_pf: Control PF of the adapter
  * @ports: Ports list
+ * @device_serial_number: DSN cached for collision detection on 32bit systems
  */
 struct ice_adapter {
 	refcount_t refcount;
@@ -40,9 +41,10 @@ struct ice_adapter {
 
 	struct ice_pf *ctrl_pf;
 	struct ice_port_list ports;
+	u64 device_serial_number;
 };
 
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev);
-void ice_adapter_put(const struct pci_dev *pdev);
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev);
+void ice_adapter_put(struct pci_dev *pdev);
 
 #endif /* _ICE_ADAPTER_H */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 1489a8ceec51..bdee499f991a 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -12,6 +12,13 @@
 #define ICE_AQC_TOPO_MAX_LEVEL_NUM	0x9
 #define ICE_AQ_SET_MAC_FRAME_SIZE_MAX	9728
 
+#define ICE_RXQ_CTX_SIZE_DWORDS		8
+#define ICE_RXQ_CTX_SZ			(ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
+#define ICE_TXQ_CTX_SZ			22
+
+typedef struct __packed { u8 buf[ICE_RXQ_CTX_SZ]; } ice_rxq_ctx_buf_t;
+typedef struct __packed { u8 buf[ICE_TXQ_CTX_SZ]; } ice_txq_ctx_buf_t;
+
 struct ice_aqc_generic {
 	__le32 param0;
 	__le32 param1;
@@ -1491,7 +1498,6 @@ struct ice_aqc_dnl_equa_param {
 #define ICE_AQC_RX_EQU_POST1 (0x12 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_BFLF (0x13 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_BFHF (0x14 << ICE_AQC_RX_EQU_SHIFT)
-#define ICE_AQC_RX_EQU_DRATE (0x15 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINHF (0x20 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINLF (0x21 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINDC (0x22 << ICE_AQC_RX_EQU_SHIFT)
@@ -1665,6 +1671,7 @@ struct ice_aqc_get_port_options_elem {
 #define ICE_AQC_PORT_OPT_MAX_LANE_25G	5
 #define ICE_AQC_PORT_OPT_MAX_LANE_50G	6
 #define ICE_AQC_PORT_OPT_MAX_LANE_100G	7
+#define ICE_AQC_PORT_OPT_MAX_LANE_200G	8
 
 	u8 global_scid[2];
 	u8 phy_scid[2];
@@ -1807,6 +1814,7 @@ struct ice_aqc_nvm_pass_comp_tbl {
 #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED		0x0
 #define ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE	0x1
 #define ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED		0x2
+#define ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK		0x3
 	u8 component_response_code; /* Response only */
 #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED_CODE	0x0
 #define ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE	0x1
@@ -2084,10 +2092,10 @@ struct ice_aqc_add_txqs_perq {
 	__le16 txq_id;
 	u8 rsvd[2];
 	__le32 q_teid;
-	u8 txq_ctx[22];
+	ice_txq_ctx_buf_t txq_ctx;
 	u8 rsvd2[2];
 	struct ice_aqc_txsched_elem info;
-};
+} __packed;
 
 /* The format of the command buffer for Add Tx LAN Queues (0x0C30)
  * is an array of the following structs. Please note that the length of
@@ -2264,6 +2272,8 @@ struct ice_aqc_get_pkg_info_resp {
 	struct ice_aqc_get_pkg_info pkg_info[];
 };
 
+#define ICE_AQC_GET_CGU_MAX_PHASE_ADJ	GENMASK(30, 0)
+
 /* Get CGU abilities command response data structure (indirect 0x0C61) */
 struct ice_aqc_get_cgu_abilities {
 	u8 num_inputs;
@@ -2508,6 +2518,87 @@ enum ice_aqc_fw_logging_mod {
 	ICE_AQC_FW_LOG_ID_MAX,
 };
 
+enum ice_aqc_health_status_mask {
+	ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK = BIT(0),
+	ICE_AQC_HEALTH_STATUS_SET_ALL_PF_MASK      = BIT(1),
+	ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK      = BIT(2),
+};
+
+/* Set Health Status (direct 0xFF20) */
+struct ice_aqc_set_health_status_cfg {
+	u8 event_source;
+	u8 reserved[15];
+};
+
+enum ice_aqc_health_status {
+	ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT		= 0x101,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE			= 0x102,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL			= 0x103,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM			= 0x104,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT			= 0x105,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT		= 0x106,
+	ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED		= 0x107,
+	ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT		= 0x108,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_DIAGNOSTIC_FEATURE	= 0x109,
+	ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG		= 0x10B,
+	ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS			= 0x10C,
+	ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE		= 0x10D,
+	ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED	= 0x10F,
+	ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT		= 0x110,
+	ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED	= 0x111,
+	ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO			= 0x112,
+	ICE_AQC_HEALTH_STATUS_ERR_NETLIST			= 0x113,
+	ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT			= 0x114,
+	ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS		= 0x115,
+	ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME			= 0x116,
+	ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT			= 0x117,
+	ICE_AQC_HEALTH_STATUS_ERR_PHY_NVM_PROG			= 0x120,
+	ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD			= 0x121,
+	ICE_AQC_HEALTH_STATUS_INFO_RECOVERY			= 0x500,
+	ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS			= 0x501,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH			= 0x502,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH			= 0x503,
+	ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH			= 0x504,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT			= 0x505,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT			= 0x506,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_SEC_VIOLATION		= 0x507,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_SEC_VIOLATION		= 0x508,
+	ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB			= 0x509,
+	ICE_AQC_HEALTH_STATUS_ERR_MNG_TIMEOUT			= 0x50A,
+	ICE_AQC_HEALTH_STATUS_ERR_BMC_RESET			= 0x50B,
+	ICE_AQC_HEALTH_STATUS_ERR_LAST_MNG_FAIL			= 0x50C,
+	ICE_AQC_HEALTH_STATUS_ERR_RESOURCE_ALLOC_FAIL		= 0x50D,
+	ICE_AQC_HEALTH_STATUS_ERR_FW_LOOP			= 0x1000,
+	ICE_AQC_HEALTH_STATUS_ERR_FW_PFR_FAIL			= 0x1001,
+	ICE_AQC_HEALTH_STATUS_ERR_LAST_FAIL_AQ			= 0x1002,
+};
+
+/* Get Health Status (indirect 0xFF22) */
+struct ice_aqc_get_health_status {
+	__le16 health_status_count;
+	u8 reserved[6];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+enum ice_aqc_health_status_scope {
+	ICE_AQC_HEALTH_STATUS_PF	= 0x1,
+	ICE_AQC_HEALTH_STATUS_PORT	= 0x2,
+	ICE_AQC_HEALTH_STATUS_GLOBAL	= 0x3,
+};
+
+#define ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA	0xDEADBEEF
+
+/* Get Health Status event buffer entry (0xFF22),
+ * repeated per reported health status.
+ */
+struct ice_aqc_health_status_elem {
+	__le16 health_status_code;
+	__le16 event_source;
+	__le32 internal_data1;
+	__le32 internal_data2;
+};
+
 /* Set FW Logging configuration (indirect 0xFF30)
  * Register for FW Logging (indirect 0xFF31)
  * Query FW Logging (indirect 0xFF32)
@@ -2648,6 +2739,8 @@ struct ice_aq_desc {
 		struct ice_aqc_get_link_status get_link_status;
 		struct ice_aqc_event_lan_overflow lan_overflow;
 		struct ice_aqc_get_link_topo get_link_topo;
+		struct ice_aqc_set_health_status_cfg set_health_status_cfg;
+		struct ice_aqc_get_health_status get_health_status;
 		struct ice_aqc_dnl_call_command dnl_call;
 		struct ice_aqc_i2c read_write_i2c;
 		struct ice_aqc_read_i2c_resp read_i2c_resp;
@@ -2850,6 +2943,10 @@ enum ice_adminq_opc {
 	/* Standalone Commands/Events */
 	ice_aqc_opc_event_lan_overflow			= 0x1001,
 
+	/* System Diagnostic commands */
+	ice_aqc_opc_set_health_status_cfg		= 0xFF20,
+	ice_aqc_opc_get_health_status			= 0xFF22,
+
 	/* FW Logging Commands */
 	ice_aqc_opc_fw_logs_config			= 0xFF30,
 	ice_aqc_opc_fw_logs_register			= 0xFF31,
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 7cee365cc7d1..1f7834c03550 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -378,6 +378,50 @@ ice_arfs_is_perfect_flow_set(struct ice_hw *hw, __be16 l3_proto, u8 l4_proto)
 }
 
 /**
+ * ice_arfs_cmp - Check if aRFS filter matches this flow.
+ * @fltr_info: filter info of the saved ARFS entry.
+ * @fk: flow dissector keys.
+ * @n_proto:  One of htons(ETH_P_IP) or htons(ETH_P_IPV6).
+ * @ip_proto: One of IPPROTO_TCP or IPPROTO_UDP.
+ *
+ * Since this function assumes limited values for n_proto and ip_proto, it
+ * is meant to be called only from ice_rx_flow_steer().
+ *
+ * Return:
+ * * true	- fltr_info refers to the same flow as fk.
+ * * false	- fltr_info and fk refer to different flows.
+ */
+static bool
+ice_arfs_cmp(const struct ice_fdir_fltr *fltr_info, const struct flow_keys *fk,
+	     __be16 n_proto, u8 ip_proto)
+{
+	/* Determine if the filter is for IPv4 or IPv6 based on flow_type,
+	 * which is one of ICE_FLTR_PTYPE_NONF_IPV{4,6}_{TCP,UDP}.
+	 */
+	bool is_v4 = fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+		     fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+
+	/* Following checks are arranged in the quickest and most discriminative
+	 * fields first for early failure.
+	 */
+	if (is_v4)
+		return n_proto == htons(ETH_P_IP) &&
+			fltr_info->ip.v4.src_port == fk->ports.src &&
+			fltr_info->ip.v4.dst_port == fk->ports.dst &&
+			fltr_info->ip.v4.src_ip == fk->addrs.v4addrs.src &&
+			fltr_info->ip.v4.dst_ip == fk->addrs.v4addrs.dst &&
+			fltr_info->ip.v4.proto == ip_proto;
+
+	return fltr_info->ip.v6.src_port == fk->ports.src &&
+		fltr_info->ip.v6.dst_port == fk->ports.dst &&
+		fltr_info->ip.v6.proto == ip_proto &&
+		!memcmp(&fltr_info->ip.v6.src_ip, &fk->addrs.v6addrs.src,
+			sizeof(struct in6_addr)) &&
+		!memcmp(&fltr_info->ip.v6.dst_ip, &fk->addrs.v6addrs.dst,
+			sizeof(struct in6_addr));
+}
+
+/**
  * ice_rx_flow_steer - steer the Rx flow to where application is being run
  * @netdev: ptr to the netdev being adjusted
  * @skb: buffer with required header information
@@ -448,6 +492,10 @@ ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
 			continue;
 
 		fltr_info = &arfs_entry->fltr_info;
+
+		if (!ice_arfs_cmp(fltr_info, &fk, n_proto, ip_proto))
+			continue;
+
 		ret = fltr_info->fltr_id;
 
 		if (fltr_info->q_index == rxq_idx ||
@@ -511,7 +559,7 @@ void ice_init_arfs(struct ice_vsi *vsi)
 	struct hlist_head *arfs_fltr_list;
 	unsigned int i;
 
-	if (!vsi || vsi->type != ICE_VSI_PF)
+	if (!vsi || vsi->type != ICE_VSI_PF || ice_is_arfs_active(vsi))
 		return;
 
 	arfs_fltr_list = kcalloc(ICE_MAX_ARFS_LIST, sizeof(*arfs_fltr_list),
@@ -571,25 +619,6 @@ void ice_clear_arfs(struct ice_vsi *vsi)
 }
 
 /**
- * ice_free_cpu_rx_rmap - free setup CPU reverse map
- * @vsi: the VSI to be forwarded to
- */
-void ice_free_cpu_rx_rmap(struct ice_vsi *vsi)
-{
-	struct net_device *netdev;
-
-	if (!vsi || vsi->type != ICE_VSI_PF)
-		return;
-
-	netdev = vsi->netdev;
-	if (!netdev || !netdev->rx_cpu_rmap)
-		return;
-
-	free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-	netdev->rx_cpu_rmap = NULL;
-}
-
-/**
  * ice_set_cpu_rx_rmap - setup CPU reverse map for each queue
  * @vsi: the VSI to be forwarded to
  */
@@ -597,7 +626,6 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 {
 	struct net_device *netdev;
 	struct ice_pf *pf;
-	int i;
 
 	if (!vsi || vsi->type != ICE_VSI_PF)
 		return 0;
@@ -610,18 +638,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 	netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n",
 		   vsi->type, netdev->name, vsi->num_q_vectors);
 
-	netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors);
-	if (unlikely(!netdev->rx_cpu_rmap))
-		return -EINVAL;
-
-	ice_for_each_q_vector(vsi, i)
-		if (irq_cpu_rmap_add(netdev->rx_cpu_rmap,
-				     vsi->q_vectors[i]->irq.virq)) {
-			ice_free_cpu_rx_rmap(vsi);
-			return -EINVAL;
-		}
-
-	return 0;
+	return netif_enable_cpu_rmap(netdev, vsi->num_q_vectors);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h
index 9669ad9bf7b5..9706293128c3 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.h
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.h
@@ -45,7 +45,6 @@ int
 ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
 		  u16 rxq_idx, u32 flow_id);
 void ice_clear_arfs(struct ice_vsi *vsi);
-void ice_free_cpu_rx_rmap(struct ice_vsi *vsi);
 void ice_init_arfs(struct ice_vsi *vsi);
 void ice_sync_arfs_fltrs(struct ice_pf *pf);
 int ice_set_cpu_rx_rmap(struct ice_vsi *vsi);
@@ -56,7 +55,6 @@ ice_is_arfs_using_perfect_flow(struct ice_hw *hw,
 			       enum ice_fltr_ptype flow_type);
 #else
 static inline void ice_clear_arfs(struct ice_vsi *vsi) { }
-static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { }
 static inline void ice_init_arfs(struct ice_vsi *vsi) { }
 static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { }
 static inline void ice_remove_arfs(struct ice_pf *pf) { }
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 82a9cd4ec7ae..6db4ad8fc70b 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -147,10 +147,6 @@ skip_alloc:
 	q_vector->reg_idx = q_vector->irq.index;
 	q_vector->vf_reg_idx = q_vector->irq.index;
 
-	/* only set affinity_mask if the CPU is online */
-	if (cpu_online(v_idx))
-		cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
-
 	/* This will not be called in the driver load path because the netdev
 	 * will not be created yet. All other cases with register the NAPI
 	 * handler here (i.e. resume, reset/rebuild, etc.)
@@ -276,7 +272,8 @@ static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring)
 	if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state))
 		return;
 
-	netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask,
+	netif_set_xps_queue(ring->netdev,
+			    &ring->q_vector->napi.config->affinity_mask,
 			    ring->q_index);
 }
 
@@ -454,6 +451,9 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	/* Rx queue threshold in units of 64 */
 	rlan_ctx.lrxqthresh = 1;
 
+	/* Enable descriptor prefetch */
+	rlan_ctx.prefena = 1;
+
 	/* PF acts as uplink for switchdev; set flex descriptor with src_vsi
 	 * metadata and flags to allow redirecting to PR netdev
 	 */
@@ -470,9 +470,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	 */
 	if (vsi->type != ICE_VSI_VF)
 		ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true);
-	else
-		ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3,
-					false);
 
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
@@ -798,13 +795,11 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
 	return 0;
 
 err_out:
-	while (v_idx--)
-		ice_free_q_vector(vsi, v_idx);
 
-	dev_err(dev, "Failed to allocate %d q_vector for VSI %d, ret=%d\n",
-		vsi->num_q_vectors, vsi->vsi_num, err);
-	vsi->num_q_vectors = 0;
-	return err;
+	dev_info(dev, "Failed to allocate %d q_vectors for VSI %d, new value %d",
+		 vsi->num_q_vectors, vsi->vsi_num, v_idx);
+	vsi->num_q_vectors = v_idx;
+	return v_idx ? 0 : err;
 }
 
 /**
@@ -910,8 +905,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring,
 	ice_setup_tx_ctx(ring, &tlan_ctx, pf_q);
 	/* copy context contents into the qg_buf */
 	qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
-	ice_set_ctx(hw, (u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
-		    ice_tlan_ctx_info);
+	ice_pack_txq_ctx(&tlan_ctx, &qg_buf->txqs[0].txq_ctx);
 
 	/* init queue specific tail reg. It is referred as
 	 * transmit comm scheduler queue doorbell.
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index b22e71dc59d4..4fedf0181c4e 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -6,6 +6,7 @@
 #include "ice_adminq_cmd.h"
 #include "ice_flow.h"
 #include "ice_ptp_hw.h"
+#include <linux/packing.h>
 
 #define ICE_PF_RESET_WAIT_COUNT	300
 #define ICE_MAX_NETLIST_SIZE	10
@@ -185,7 +186,7 @@ static int ice_set_mac_type(struct ice_hw *hw)
  * ice_is_generic_mac - check if device's mac_type is generic
  * @hw: pointer to the hardware structure
  *
- * Return: true if mac_type is generic (with SBQ support), false if not
+ * Return: true if mac_type is ICE_MAC_GENERIC*, false otherwise.
  */
 bool ice_is_generic_mac(struct ice_hw *hw)
 {
@@ -194,117 +195,39 @@ bool ice_is_generic_mac(struct ice_hw *hw)
 }
 
 /**
- * ice_is_e810
- * @hw: pointer to the hardware structure
- *
- * returns true if the device is E810 based, false if not.
- */
-bool ice_is_e810(struct ice_hw *hw)
-{
-	return hw->mac_type == ICE_MAC_E810;
-}
-
-/**
- * ice_is_e810t
- * @hw: pointer to the hardware structure
+ * ice_is_pf_c827 - check if pf contains c827 phy
+ * @hw: pointer to the hw struct
  *
- * returns true if the device is E810T based, false if not.
+ * Return: true if the device has c827 phy.
  */
-bool ice_is_e810t(struct ice_hw *hw)
+static bool ice_is_pf_c827(struct ice_hw *hw)
 {
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E810C_SFP:
-		switch (hw->subsystem_device_id) {
-		case ICE_SUBDEV_ID_E810T:
-		case ICE_SUBDEV_ID_E810T2:
-		case ICE_SUBDEV_ID_E810T3:
-		case ICE_SUBDEV_ID_E810T4:
-		case ICE_SUBDEV_ID_E810T6:
-		case ICE_SUBDEV_ID_E810T7:
-			return true;
-		}
-		break;
-	case ICE_DEV_ID_E810C_QSFP:
-		switch (hw->subsystem_device_id) {
-		case ICE_SUBDEV_ID_E810T2:
-		case ICE_SUBDEV_ID_E810T3:
-		case ICE_SUBDEV_ID_E810T5:
-			return true;
-		}
-		break;
-	default:
-		break;
-	}
-
-	return false;
-}
+	struct ice_aqc_get_link_topo cmd = {};
+	u8 node_part_number;
+	u16 node_handle;
+	int status;
 
-/**
- * ice_is_e822 - Check if a device is E822 family device
- * @hw: pointer to the hardware structure
- *
- * Return: true if the device is E822 based, false if not.
- */
-bool ice_is_e822(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E822C_BACKPLANE:
-	case ICE_DEV_ID_E822C_QSFP:
-	case ICE_DEV_ID_E822C_SFP:
-	case ICE_DEV_ID_E822C_10G_BASE_T:
-	case ICE_DEV_ID_E822C_SGMII:
-	case ICE_DEV_ID_E822L_BACKPLANE:
-	case ICE_DEV_ID_E822L_SFP:
-	case ICE_DEV_ID_E822L_10G_BASE_T:
-	case ICE_DEV_ID_E822L_SGMII:
-		return true;
-	default:
+	if (hw->mac_type != ICE_MAC_E810)
 		return false;
-	}
-}
 
-/**
- * ice_is_e823
- * @hw: pointer to the hardware structure
- *
- * returns true if the device is E823-L or E823-C based, false if not.
- */
-bool ice_is_e823(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E823L_BACKPLANE:
-	case ICE_DEV_ID_E823L_SFP:
-	case ICE_DEV_ID_E823L_10G_BASE_T:
-	case ICE_DEV_ID_E823L_1GBE:
-	case ICE_DEV_ID_E823L_QSFP:
-	case ICE_DEV_ID_E823C_BACKPLANE:
-	case ICE_DEV_ID_E823C_QSFP:
-	case ICE_DEV_ID_E823C_SFP:
-	case ICE_DEV_ID_E823C_10G_BASE_T:
-	case ICE_DEV_ID_E823C_SGMII:
+	if (hw->device_id != ICE_DEV_ID_E810C_QSFP)
 		return true;
-	default:
+
+	cmd.addr.topo_params.node_type_ctx =
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) |
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT);
+	cmd.addr.topo_params.index = 0;
+
+	status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number,
+					 &node_handle);
+
+	if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827)
 		return false;
-	}
-}
 
-/**
- * ice_is_e825c - Check if a device is E825C family device
- * @hw: pointer to the hardware structure
- *
- * Return: true if the device is E825-C based, false if not.
- */
-bool ice_is_e825c(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E825C_BACKPLANE:
-	case ICE_DEV_ID_E825C_QSFP:
-	case ICE_DEV_ID_E825C_SFP:
-	case ICE_DEV_ID_E825C_SGMII:
+	if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE)
 		return true;
-	default:
-		return false;
-	}
+
+	return false;
 }
 
 /**
@@ -542,7 +465,8 @@ ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd,
 /**
  * ice_find_netlist_node
  * @hw: pointer to the hw struct
- * @node_type_ctx: type of netlist node to look for
+ * @node_type: type of netlist node to look for
+ * @ctx: context of the search
  * @node_part_number: node part number to look for
  * @node_handle: output parameter if node found - optional
  *
@@ -552,10 +476,12 @@ ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd,
  * valid if the function returns zero, and should be ignored on any non-zero
  * return value.
  *
- * Returns: 0 if the node is found, -ENOENT if no handle was found, and
- * a negative error code on failure to access the AQ.
+ * Return:
+ * * 0 if the node is found,
+ * * -ENOENT if no handle was found,
+ * * negative error code on failure to access the AQ.
  */
-static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type_ctx,
+static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type, u8 ctx,
 				 u8 node_part_number, u16 *node_handle)
 {
 	u8 idx;
@@ -566,8 +492,8 @@ static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type_ctx,
 		int status;
 
 		cmd.addr.topo_params.node_type_ctx =
-			FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M,
-				   node_type_ctx);
+			FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, node_type) |
+			FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ctx);
 		cmd.addr.topo_params.index = idx;
 
 		status = ice_aq_get_netlist_node(hw, &cmd,
@@ -1022,6 +948,33 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw)
 }
 
 /**
+ * ice_wait_for_fw - wait for full FW readiness
+ * @hw: pointer to the hardware structure
+ * @timeout: milliseconds that can elapse before timing out
+ *
+ * Return: 0 on success, -ETIMEDOUT on timeout.
+ */
+static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
+{
+	int fw_loading;
+	u32 elapsed = 0;
+
+	while (elapsed <= timeout) {
+		fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
+
+		/* firmware was not yet loaded, we have to wait more */
+		if (fw_loading) {
+			elapsed += 100;
+			msleep(100);
+			continue;
+		}
+		return 0;
+	}
+
+	return -ETIMEDOUT;
+}
+
+/**
  * ice_init_hw - main hardware initialization routine
  * @hw: pointer to the hardware structure
  */
@@ -1170,8 +1123,21 @@ int ice_init_hw(struct ice_hw *hw)
 	mutex_init(&hw->tnl_lock);
 	ice_init_chk_recipe_reuse_support(hw);
 
-	return 0;
+	/* Some cards require longer initialization times
+	 * due to necessity of loading FW from an external source.
+	 * This can take even half a minute.
+	 */
+	if (ice_is_pf_c827(hw)) {
+		status = ice_wait_for_fw(hw, 30000);
+		if (status) {
+			dev_err(ice_hw_to_dev(hw), "ice_wait_for_fw timed out");
+			goto err_unroll_fltr_mgmt_struct;
+		}
+	}
+
+	hw->lane_num = ice_get_phy_lane_number(hw);
 
+	return 0;
 err_unroll_fltr_mgmt_struct:
 	ice_cleanup_fltr_mgmt_struct(hw);
 err_unroll_sched:
@@ -1357,39 +1323,31 @@ int ice_reset(struct ice_hw *hw, enum ice_reset_req req)
 }
 
 /**
- * ice_copy_rxq_ctx_to_hw
+ * ice_copy_rxq_ctx_to_hw - Copy packed Rx queue context to HW registers
  * @hw: pointer to the hardware structure
- * @ice_rxq_ctx: pointer to the rxq context
+ * @rxq_ctx: pointer to the packed Rx queue context
  * @rxq_index: the index of the Rx queue
- *
- * Copies rxq context from dense structure to HW register space
  */
-static int
-ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index)
+static void ice_copy_rxq_ctx_to_hw(struct ice_hw *hw,
+				   const ice_rxq_ctx_buf_t *rxq_ctx,
+				   u32 rxq_index)
 {
-	u8 i;
-
-	if (!ice_rxq_ctx)
-		return -EINVAL;
-
-	if (rxq_index > QRX_CTRL_MAX_INDEX)
-		return -EINVAL;
-
 	/* Copy each dword separately to HW */
-	for (i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) {
-		wr32(hw, QRX_CONTEXT(i, rxq_index),
-		     *((u32 *)(ice_rxq_ctx + (i * sizeof(u32)))));
+	for (int i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) {
+		u32 ctx = ((const u32 *)rxq_ctx)[i];
 
-		ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i,
-			  *((u32 *)(ice_rxq_ctx + (i * sizeof(u32)))));
-	}
+		wr32(hw, QRX_CONTEXT(i, rxq_index), ctx);
 
-	return 0;
+		ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i, ctx);
+	}
 }
 
+#define ICE_CTX_STORE(struct_name, struct_field, width, lsb) \
+	PACKED_FIELD((lsb) + (width) - 1, (lsb), struct struct_name, struct_field)
+
 /* LAN Rx Queue Context */
-static const struct ice_ctx_ele ice_rlan_ctx_info[] = {
-	/* Field		Width	LSB */
+static const struct packed_field_u8 ice_rlan_ctx_fields[] = {
+				 /* Field		Width	LSB */
 	ICE_CTX_STORE(ice_rlan_ctx, head,		13,	0),
 	ICE_CTX_STORE(ice_rlan_ctx, cpuid,		8,	13),
 	ICE_CTX_STORE(ice_rlan_ctx, base,		57,	32),
@@ -1410,35 +1368,50 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = {
 	ICE_CTX_STORE(ice_rlan_ctx, tphhead_ena,	1,	196),
 	ICE_CTX_STORE(ice_rlan_ctx, lrxqthresh,		3,	198),
 	ICE_CTX_STORE(ice_rlan_ctx, prefena,		1,	201),
-	{ 0 }
 };
 
 /**
- * ice_write_rxq_ctx
+ * ice_pack_rxq_ctx - Pack Rx queue context into a HW buffer
+ * @ctx: the Rx queue context to pack
+ * @buf: the HW buffer to pack into
+ *
+ * Pack the Rx queue context from the CPU-friendly unpacked buffer into its
+ * bit-packed HW layout.
+ */
+static void ice_pack_rxq_ctx(const struct ice_rlan_ctx *ctx,
+			     ice_rxq_ctx_buf_t *buf)
+{
+	pack_fields(buf, sizeof(*buf), ctx, ice_rlan_ctx_fields,
+		    QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST);
+}
+
+/**
+ * ice_write_rxq_ctx - Write Rx Queue context to hardware
  * @hw: pointer to the hardware structure
- * @rlan_ctx: pointer to the rxq context
+ * @rlan_ctx: pointer to the unpacked Rx queue context
  * @rxq_index: the index of the Rx queue
  *
- * Converts rxq context from sparse to dense structure and then writes
- * it to HW register space and enables the hardware to prefetch descriptors
- * instead of only fetching them on demand
+ * Pack the sparse Rx Queue context into dense hardware format and write it
+ * into the HW register space.
+ *
+ * Return: 0 on success, or -EINVAL if the Rx queue index is invalid.
  */
 int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
 		      u32 rxq_index)
 {
-	u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 };
+	ice_rxq_ctx_buf_t buf = {};
 
-	if (!rlan_ctx)
+	if (rxq_index > QRX_CTRL_MAX_INDEX)
 		return -EINVAL;
 
-	rlan_ctx->prefena = 1;
+	ice_pack_rxq_ctx(rlan_ctx, &buf);
+	ice_copy_rxq_ctx_to_hw(hw, &buf, rxq_index);
 
-	ice_set_ctx(hw, (u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info);
-	return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index);
+	return 0;
 }
 
 /* LAN Tx Queue Context */
-const struct ice_ctx_ele ice_tlan_ctx_info[] = {
+static const struct packed_field_u8 ice_tlan_ctx_fields[] = {
 				    /* Field			Width	LSB */
 	ICE_CTX_STORE(ice_tlan_ctx, base,			57,	0),
 	ICE_CTX_STORE(ice_tlan_ctx, port_num,			3,	57),
@@ -1467,10 +1440,22 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = {
 	ICE_CTX_STORE(ice_tlan_ctx, drop_ena,			1,	165),
 	ICE_CTX_STORE(ice_tlan_ctx, cache_prof_idx,		2,	166),
 	ICE_CTX_STORE(ice_tlan_ctx, pkt_shaper_prof_idx,	3,	168),
-	ICE_CTX_STORE(ice_tlan_ctx, int_q_state,		122,	171),
-	{ 0 }
 };
 
+/**
+ * ice_pack_txq_ctx - Pack Tx queue context into a HW buffer
+ * @ctx: the Tx queue context to pack
+ * @buf: the HW buffer to pack into
+ *
+ * Pack the Tx queue context from the CPU-friendly unpacked buffer into its
+ * bit-packed HW layout.
+ */
+void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf)
+{
+	pack_fields(buf, sizeof(*buf), ctx, ice_tlan_ctx_fields,
+		    QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST);
+}
+
 /* Sideband Queue command wrappers */
 
 /**
@@ -2174,7 +2159,8 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 			  caps->nvm_unified_update);
 		break;
 	case ICE_AQC_CAPS_RDMA:
-		caps->rdma = (number == 1);
+		if (IS_ENABLED(CONFIG_INFINIBAND_IRDMA))
+			caps->rdma = (number == 1);
 		ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma);
 		break;
 	case ICE_AQC_CAPS_MAX_MTU:
@@ -2311,7 +2297,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 	info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0);
 	info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0);
 
-	if (!ice_is_e825c(hw)) {
+	if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) {
 		info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number);
 		info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0);
 	} else {
@@ -2544,6 +2530,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 
 	info->ts_ll_read = ((number & ICE_TS_LL_TX_TS_READ_M) != 0);
 	info->ts_ll_int_read = ((number & ICE_TS_LL_TX_TS_INT_READ_M) != 0);
+	info->ll_phy_tmr_update = ((number & ICE_TS_LL_PHY_TMR_UPDATE_M) != 0);
 
 	info->ena_ports = logical_id;
 	info->tmr_own_map = phys_id;
@@ -2566,6 +2553,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		  info->ts_ll_read);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_int_read = %u\n",
 		  info->ts_ll_int_read);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: ll_phy_tmr_update = %u\n",
+		  info->ll_phy_tmr_update);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n",
 		  info->ena_ports);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n",
@@ -2706,40 +2695,6 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 }
 
 /**
- * ice_is_pf_c827 - check if pf contains c827 phy
- * @hw: pointer to the hw struct
- */
-bool ice_is_pf_c827(struct ice_hw *hw)
-{
-	struct ice_aqc_get_link_topo cmd = {};
-	u8 node_part_number;
-	u16 node_handle;
-	int status;
-
-	if (hw->mac_type != ICE_MAC_E810)
-		return false;
-
-	if (hw->device_id != ICE_DEV_ID_E810C_QSFP)
-		return true;
-
-	cmd.addr.topo_params.node_type_ctx =
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) |
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT);
-	cmd.addr.topo_params.index = 0;
-
-	status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number,
-					 &node_handle);
-
-	if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827)
-		return false;
-
-	if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE)
-		return true;
-
-	return false;
-}
-
-/**
  * ice_is_phy_rclk_in_netlist
  * @hw: pointer to the hw struct
  *
@@ -2747,9 +2702,11 @@ bool ice_is_pf_c827(struct ice_hw *hw)
  */
 bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw)
 {
-	if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL,
+	if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY,
+				  ICE_AQC_LINK_TOPO_NODE_CTX_PORT,
 				  ICE_AQC_GET_LINK_TOPO_NODE_NR_C827, NULL) &&
-	    ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL,
+	    ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY,
+				  ICE_AQC_LINK_TOPO_NODE_CTX_PORT,
 				  ICE_AQC_GET_LINK_TOPO_NODE_NR_E822_PHY, NULL))
 		return false;
 
@@ -2765,6 +2722,7 @@ bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw)
 bool ice_is_clock_mux_in_netlist(struct ice_hw *hw)
 {
 	if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_MUX,
+				  ICE_AQC_LINK_TOPO_NODE_CTX_GLOBAL,
 				  ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX,
 				  NULL))
 		return false;
@@ -2785,12 +2743,14 @@ bool ice_is_clock_mux_in_netlist(struct ice_hw *hw)
 bool ice_is_cgu_in_netlist(struct ice_hw *hw)
 {
 	if (!ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL,
+				   ICE_AQC_LINK_TOPO_NODE_CTX_GLOBAL,
 				   ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032,
 				   NULL)) {
 		hw->cgu_part_number = ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032;
 		return true;
 	} else if (!ice_find_netlist_node(hw,
 					  ICE_AQC_LINK_TOPO_NODE_TYPE_CLK_CTRL,
+					  ICE_AQC_LINK_TOPO_NODE_CTX_GLOBAL,
 					  ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384,
 					  NULL)) {
 		hw->cgu_part_number = ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384;
@@ -2809,6 +2769,7 @@ bool ice_is_cgu_in_netlist(struct ice_hw *hw)
 bool ice_is_gps_in_netlist(struct ice_hw *hw)
 {
 	if (ice_find_netlist_node(hw, ICE_AQC_LINK_TOPO_NODE_TYPE_GPS,
+				  ICE_AQC_LINK_TOPO_NODE_CTX_GLOBAL,
 				  ICE_AQC_GET_LINK_TOPO_NODE_NR_GEN_GPS, NULL))
 		return false;
 
@@ -3475,7 +3436,7 @@ int ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port,
 	msg.msg_addr_low = lower_16_bits(reg_offset);
 	msg.msg_addr_high = receiver_id;
 	msg.opcode = ice_sbq_msg_rd;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 
 	err = ice_sbq_rw_reg(hw, &msg, flag);
 	if (err)
@@ -4087,6 +4048,59 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 }
 
 /**
+ * ice_get_phy_lane_number - Get PHY lane number for current adapter
+ * @hw: pointer to the hw struct
+ *
+ * Return: PHY lane number on success, negative error code otherwise.
+ */
+int ice_get_phy_lane_number(struct ice_hw *hw)
+{
+	struct ice_aqc_get_port_options_elem *options;
+	unsigned int lport = 0;
+	unsigned int lane;
+	int err;
+
+	options = kcalloc(ICE_AQC_PORT_OPT_MAX, sizeof(*options), GFP_KERNEL);
+	if (!options)
+		return -ENOMEM;
+
+	for (lane = 0; lane < ICE_MAX_PORT_PER_PCI_DEV; lane++) {
+		u8 options_count = ICE_AQC_PORT_OPT_MAX;
+		u8 speed, active_idx, pending_idx;
+		bool active_valid, pending_valid;
+
+		err = ice_aq_get_port_options(hw, options, &options_count, lane,
+					      true, &active_idx, &active_valid,
+					      &pending_idx, &pending_valid);
+		if (err)
+			goto err;
+
+		if (!active_valid)
+			continue;
+
+		speed = options[active_idx].max_lane_speed;
+		/* If we don't get speed for this lane, it's unoccupied */
+		if (speed > ICE_AQC_PORT_OPT_MAX_LANE_200G)
+			continue;
+
+		if (hw->pf_id == lport) {
+			if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 &&
+			    ice_is_dual(hw) && !ice_is_primary(hw))
+				lane += ICE_PORTS_PER_QUAD;
+			kfree(options);
+			return lane;
+		}
+		lport++;
+	}
+
+	/* PHY lane not found */
+	err = -ENXIO;
+err:
+	kfree(options);
+	return err;
+}
+
+/**
  * ice_aq_sff_eeprom
  * @hw: pointer to the HW struct
  * @lport: bits [7:0] = logical port, bit [8] = logical port valid
@@ -4549,205 +4563,6 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps,
 /* End of FW Admin Queue command wrappers */
 
 /**
- * ice_pack_ctx_byte - write a byte to a packed context structure
- * @src_ctx: unpacked source context structure
- * @dest_ctx: packed destination context data
- * @ce_info: context element description
- */
-static void ice_pack_ctx_byte(u8 *src_ctx, u8 *dest_ctx,
-			      const struct ice_ctx_ele *ce_info)
-{
-	u8 src_byte, dest_byte, mask;
-	u8 *from, *dest;
-	u16 shift_width;
-
-	/* copy from the next struct field */
-	from = src_ctx + ce_info->offset;
-
-	/* prepare the bits and mask */
-	shift_width = ce_info->lsb % 8;
-	mask = GENMASK(ce_info->width - 1 + shift_width, shift_width);
-
-	src_byte = *from;
-	src_byte <<= shift_width;
-	src_byte &= mask;
-
-	/* get the current bits from the target bit string */
-	dest = dest_ctx + (ce_info->lsb / 8);
-
-	memcpy(&dest_byte, dest, sizeof(dest_byte));
-
-	dest_byte &= ~mask;	/* get the bits not changing */
-	dest_byte |= src_byte;	/* add in the new bits */
-
-	/* put it all back */
-	memcpy(dest, &dest_byte, sizeof(dest_byte));
-}
-
-/**
- * ice_pack_ctx_word - write a word to a packed context structure
- * @src_ctx: unpacked source context structure
- * @dest_ctx: packed destination context data
- * @ce_info: context element description
- */
-static void ice_pack_ctx_word(u8 *src_ctx, u8 *dest_ctx,
-			      const struct ice_ctx_ele *ce_info)
-{
-	u16 src_word, mask;
-	__le16 dest_word;
-	u8 *from, *dest;
-	u16 shift_width;
-
-	/* copy from the next struct field */
-	from = src_ctx + ce_info->offset;
-
-	/* prepare the bits and mask */
-	shift_width = ce_info->lsb % 8;
-	mask = GENMASK(ce_info->width - 1 + shift_width, shift_width);
-
-	/* don't swizzle the bits until after the mask because the mask bits
-	 * will be in a different bit position on big endian machines
-	 */
-	src_word = *(u16 *)from;
-	src_word <<= shift_width;
-	src_word &= mask;
-
-	/* get the current bits from the target bit string */
-	dest = dest_ctx + (ce_info->lsb / 8);
-
-	memcpy(&dest_word, dest, sizeof(dest_word));
-
-	dest_word &= ~(cpu_to_le16(mask));	/* get the bits not changing */
-	dest_word |= cpu_to_le16(src_word);	/* add in the new bits */
-
-	/* put it all back */
-	memcpy(dest, &dest_word, sizeof(dest_word));
-}
-
-/**
- * ice_pack_ctx_dword - write a dword to a packed context structure
- * @src_ctx: unpacked source context structure
- * @dest_ctx: packed destination context data
- * @ce_info: context element description
- */
-static void ice_pack_ctx_dword(u8 *src_ctx, u8 *dest_ctx,
-			       const struct ice_ctx_ele *ce_info)
-{
-	u32 src_dword, mask;
-	__le32 dest_dword;
-	u8 *from, *dest;
-	u16 shift_width;
-
-	/* copy from the next struct field */
-	from = src_ctx + ce_info->offset;
-
-	/* prepare the bits and mask */
-	shift_width = ce_info->lsb % 8;
-	mask = GENMASK(ce_info->width - 1 + shift_width, shift_width);
-
-	/* don't swizzle the bits until after the mask because the mask bits
-	 * will be in a different bit position on big endian machines
-	 */
-	src_dword = *(u32 *)from;
-	src_dword <<= shift_width;
-	src_dword &= mask;
-
-	/* get the current bits from the target bit string */
-	dest = dest_ctx + (ce_info->lsb / 8);
-
-	memcpy(&dest_dword, dest, sizeof(dest_dword));
-
-	dest_dword &= ~(cpu_to_le32(mask));	/* get the bits not changing */
-	dest_dword |= cpu_to_le32(src_dword);	/* add in the new bits */
-
-	/* put it all back */
-	memcpy(dest, &dest_dword, sizeof(dest_dword));
-}
-
-/**
- * ice_pack_ctx_qword - write a qword to a packed context structure
- * @src_ctx: unpacked source context structure
- * @dest_ctx: packed destination context data
- * @ce_info: context element description
- */
-static void ice_pack_ctx_qword(u8 *src_ctx, u8 *dest_ctx,
-			       const struct ice_ctx_ele *ce_info)
-{
-	u64 src_qword, mask;
-	__le64 dest_qword;
-	u8 *from, *dest;
-	u16 shift_width;
-
-	/* copy from the next struct field */
-	from = src_ctx + ce_info->offset;
-
-	/* prepare the bits and mask */
-	shift_width = ce_info->lsb % 8;
-	mask = GENMASK_ULL(ce_info->width - 1 + shift_width, shift_width);
-
-	/* don't swizzle the bits until after the mask because the mask bits
-	 * will be in a different bit position on big endian machines
-	 */
-	src_qword = *(u64 *)from;
-	src_qword <<= shift_width;
-	src_qword &= mask;
-
-	/* get the current bits from the target bit string */
-	dest = dest_ctx + (ce_info->lsb / 8);
-
-	memcpy(&dest_qword, dest, sizeof(dest_qword));
-
-	dest_qword &= ~(cpu_to_le64(mask));	/* get the bits not changing */
-	dest_qword |= cpu_to_le64(src_qword);	/* add in the new bits */
-
-	/* put it all back */
-	memcpy(dest, &dest_qword, sizeof(dest_qword));
-}
-
-/**
- * ice_set_ctx - set context bits in packed structure
- * @hw: pointer to the hardware structure
- * @src_ctx:  pointer to a generic non-packed context structure
- * @dest_ctx: pointer to memory for the packed structure
- * @ce_info: List of Rx context elements
- */
-int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx,
-		const struct ice_ctx_ele *ce_info)
-{
-	int f;
-
-	for (f = 0; ce_info[f].width; f++) {
-		/* We have to deal with each element of the FW response
-		 * using the correct size so that we are correct regardless
-		 * of the endianness of the machine.
-		 */
-		if (ce_info[f].width > (ce_info[f].size_of * BITS_PER_BYTE)) {
-			ice_debug(hw, ICE_DBG_QCTX, "Field %d width of %d bits larger than size of %d byte(s) ... skipping write\n",
-				  f, ce_info[f].width, ce_info[f].size_of);
-			continue;
-		}
-		switch (ce_info[f].size_of) {
-		case sizeof(u8):
-			ice_pack_ctx_byte(src_ctx, dest_ctx, &ce_info[f]);
-			break;
-		case sizeof(u16):
-			ice_pack_ctx_word(src_ctx, dest_ctx, &ce_info[f]);
-			break;
-		case sizeof(u32):
-			ice_pack_ctx_dword(src_ctx, dest_ctx, &ce_info[f]);
-			break;
-		case sizeof(u64):
-			ice_pack_ctx_qword(src_ctx, dest_ctx, &ce_info[f]);
-			break;
-		default:
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
-/**
  * ice_get_lan_q_ctx - get the LAN queue context for the given VSI and TC
  * @hw: pointer to the HW struct
  * @vsi_handle: software VSI handle
@@ -5841,6 +5656,96 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 }
 
 /**
+ * ice_get_pca9575_handle - find and return the PCA9575 controller
+ * @hw: pointer to the hw struct
+ * @pca9575_handle: GPIO controller's handle
+ *
+ * Find and return the GPIO controller's handle in the netlist.
+ * When found - the value will be cached in the hw structure and following calls
+ * will return cached value.
+ *
+ * Return: 0 on success, -ENXIO when there's no PCA9575 present.
+ */
+int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
+{
+	struct ice_aqc_get_link_topo *cmd;
+	struct ice_aq_desc desc;
+	int err;
+	u8 idx;
+
+	/* If handle was read previously return cached value */
+	if (hw->io_expander_handle) {
+		*pca9575_handle = hw->io_expander_handle;
+		return 0;
+	}
+
+#define SW_PCA9575_SFP_TOPO_IDX		2
+#define SW_PCA9575_QSFP_TOPO_IDX	1
+
+	/* Check if the SW IO expander controlling SMA exists in the netlist. */
+	if (hw->device_id == ICE_DEV_ID_E810C_SFP)
+		idx = SW_PCA9575_SFP_TOPO_IDX;
+	else if (hw->device_id == ICE_DEV_ID_E810C_QSFP)
+		idx = SW_PCA9575_QSFP_TOPO_IDX;
+	else
+		return -ENXIO;
+
+	/* If handle was not detected read it from the netlist */
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
+	cmd = &desc.params.get_link_topo;
+	cmd->addr.topo_params.node_type_ctx =
+		ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL;
+	cmd->addr.topo_params.index = idx;
+
+	err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+	if (err)
+		return -ENXIO;
+
+	/* Verify if we found the right IO expander type */
+	if (desc.params.get_link_topo.node_part_num !=
+	    ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
+		return -ENXIO;
+
+	/* If present save the handle and return it */
+	hw->io_expander_handle =
+		le16_to_cpu(desc.params.get_link_topo.addr.handle);
+	*pca9575_handle = hw->io_expander_handle;
+
+	return 0;
+}
+
+/**
+ * ice_read_pca9575_reg - read the register from the PCA9575 controller
+ * @hw: pointer to the hw struct
+ * @offset: GPIO controller register offset
+ * @data: pointer to data to be read from the GPIO controller
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data)
+{
+	struct ice_aqc_link_topo_addr link_topo;
+	__le16 addr;
+	u16 handle;
+	int err;
+
+	memset(&link_topo, 0, sizeof(link_topo));
+
+	err = ice_get_pca9575_handle(hw, &handle);
+	if (err)
+		return err;
+
+	link_topo.handle = cpu_to_le16(handle);
+	link_topo.topo_params.node_type_ctx =
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M,
+			   ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED);
+
+	addr = cpu_to_le16((u16)offset);
+
+	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
+}
+
+/**
  * ice_aq_set_gpio
  * @hw: pointer to the hw struct
  * @gpio_ctrl_handle: GPIO controller node handle
@@ -6023,6 +5928,44 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps)
 }
 
 /**
+ * ice_is_fw_health_report_supported - checks if firmware supports health events
+ * @hw: pointer to the hardware structure
+ *
+ * Return: true if firmware supports health status reports,
+ * false otherwise
+ */
+bool ice_is_fw_health_report_supported(struct ice_hw *hw)
+{
+	return ice_is_fw_api_min_ver(hw, ICE_FW_API_HEALTH_REPORT_MAJ,
+				     ICE_FW_API_HEALTH_REPORT_MIN,
+				     ICE_FW_API_HEALTH_REPORT_PATCH);
+}
+
+/**
+ * ice_aq_set_health_status_cfg - Configure FW health events
+ * @hw: pointer to the HW struct
+ * @event_source: type of diagnostic events to enable
+ *
+ * Configure the health status event types that the firmware will send to this
+ * PF. The supported event types are: PF-specific, all PFs, and global.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source)
+{
+	struct ice_aqc_set_health_status_cfg *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.set_health_status_cfg;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_health_status_cfg);
+
+	cmd->event_source = event_source;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+}
+
+/**
  * ice_aq_set_lldp_mib - Set the LLDP MIB
  * @hw: pointer to the HW struct
  * @mib_type: Local, Remote or both Local and Remote MIBs
@@ -6072,15 +6015,21 @@ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw)
 /**
  * ice_lldp_fltr_add_remove - add or remove a LLDP Rx switch filter
  * @hw: pointer to HW struct
- * @vsi_num: absolute HW index for VSI
+ * @vsi: VSI to add the filter to
  * @add: boolean for if adding or removing a filter
+ *
+ * Return: 0 on success, -EOPNOTSUPP if the operation cannot be performed
+ *	   with this HW or VSI, otherwise an error corresponding to
+ *	   the AQ transaction result.
  */
-int
-ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add)
+int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add)
 {
 	struct ice_aqc_lldp_filter_ctrl *cmd;
 	struct ice_aq_desc desc;
 
+	if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw))
+		return -EOPNOTSUPP;
+
 	cmd = &desc.params.lldp_filter_ctrl;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_filter_ctrl);
@@ -6090,7 +6039,7 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add)
 	else
 		cmd->cmd_flags = ICE_AQC_LLDP_FILTER_ACTION_DELETE;
 
-	cmd->vsi_num = cpu_to_le16(vsi_num);
+	cmd->vsi_num = cpu_to_le16(vsi->vsi_num);
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 27208a60cece..64c530b39191 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -92,9 +92,8 @@ ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle,
 bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq);
 int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading);
 void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode);
-extern const struct ice_ctx_ele ice_tlan_ctx_info[];
-int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx,
-		const struct ice_ctx_ele *ce_info);
+
+void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf);
 
 extern struct mutex ice_global_cfg_lock_sw;
 
@@ -113,7 +112,6 @@ int
 ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 		    struct ice_aqc_get_phy_caps_data *caps,
 		    struct ice_sq_cd *cd);
-bool ice_is_pf_c827(struct ice_hw *hw);
 bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw);
 bool ice_is_clock_mux_in_netlist(struct ice_hw *hw);
 bool ice_is_cgu_in_netlist(struct ice_hw *hw);
@@ -133,7 +131,6 @@ int
 ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd);
 bool ice_is_generic_mac(struct ice_hw *hw);
-bool ice_is_e810(struct ice_hw *hw);
 int ice_clear_pf_cfg(struct ice_hw *hw);
 int
 ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
@@ -143,6 +140,8 @@ int
 ice_get_link_default_override(struct ice_link_default_override_tlv *ldo,
 			      struct ice_port_info *pi);
 bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps);
+bool ice_is_fw_health_report_supported(struct ice_hw *hw);
+int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source);
 int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code,
 				u8 serdes_num, int *output);
 int
@@ -193,6 +192,7 @@ ice_aq_get_port_options(struct ice_hw *hw,
 int
 ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 		       u8 new_option);
+int ice_get_phy_lane_number(struct ice_hw *hw);
 int
 ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		  u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length,
@@ -275,10 +275,6 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 void
 ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 		  u64 *prev_stat, u64 *cur_stat);
-bool ice_is_e810t(struct ice_hw *hw);
-bool ice_is_e822(struct ice_hw *hw);
-bool ice_is_e823(struct ice_hw *hw);
-bool ice_is_e825c(struct ice_hw *hw);
 int
 ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
 		     struct ice_aqc_txsched_elem_data *buf);
@@ -294,8 +290,7 @@ int
 ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
 		    struct ice_sq_cd *cd);
 bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw);
-int
-ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add);
+int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add);
 int ice_lldp_execute_pending_mib(struct ice_hw *hw);
 int
 ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
@@ -305,5 +300,7 @@ int
 ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		 u16 bus_addr, __le16 addr, u8 params, const u8 *data,
 		 struct ice_sq_cd *cd);
+int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle);
+int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data);
 bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw);
 #endif /* _ICE_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index 74418c445cc4..64737fc62306 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -1288,7 +1288,7 @@ ice_add_dscp_up_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 	tlv->ouisubtype = htonl(ouisubtype);
 
 	/* bytes 0 - 63 - IPv4 DSCP2UP LUT */
-	for (i = 0; i < ICE_DSCP_NUM_VAL; i++) {
+	for (i = 0; i < DSCP_MAX; i++) {
 		/* IPv4 mapping */
 		buf[i] = dcbcfg->dscp_map[i];
 		/* IPv6 mapping */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index a7c510832824..533eb8930aa8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -352,8 +352,8 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 	struct ice_aqc_port_ets_elem buf = { 0 };
 	struct ice_dcbx_cfg *old_cfg, *curr_cfg;
 	struct device *dev = ice_pf_to_dev(pf);
+	struct iidc_rdma_event *event;
 	int ret = ICE_DCB_NO_HW_CHG;
-	struct iidc_event *event;
 	struct ice_vsi *pf_vsi;
 
 	curr_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
@@ -405,7 +405,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 		goto free_cfg;
 	}
 
-	set_bit(IIDC_EVENT_BEFORE_TC_CHANGE, event->type);
+	set_bit(IIDC_RDMA_EVENT_BEFORE_TC_CHANGE, event->type);
 	ice_send_event_to_aux(pf, event);
 	kfree(event);
 
@@ -740,7 +740,9 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf)
 void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked)
 {
 	struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
-	struct iidc_event *event;
+	struct iidc_rdma_priv_dev_info *privd;
+	struct iidc_rdma_core_dev_info *cdev;
+	struct iidc_rdma_event *event;
 	u8 tc_map = 0;
 	int v, ret;
 
@@ -783,13 +785,17 @@ void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked)
 		if (vsi->type == ICE_VSI_PF)
 			ice_dcbnl_set_all(vsi);
 	}
-	if (!locked) {
+
+	cdev = pf->cdev_info;
+	if (cdev && !locked) {
+		privd = cdev->iidc_priv;
+		ice_setup_dcb_qos_info(pf, &privd->qos_info);
 		/* Notify the AUX drivers that TC change is finished */
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (!event)
 			return;
 
-		set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type);
+		set_bit(IIDC_RDMA_EVENT_AFTER_TC_CHANGE, event->type);
 		ice_send_event_to_aux(pf, event);
 		kfree(event);
 	}
@@ -846,7 +852,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 			goto dcb_init_err;
 		}
 
-		ice_cfg_sw_lldp(pf_vsi, false, true);
+		ice_cfg_sw_rx_lldp(pf, true);
 
 		pf->dcbx_cap = ice_dcb_get_mode(port_info, true);
 		return 0;
@@ -945,6 +951,37 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring,
 }
 
 /**
+ * ice_setup_dcb_qos_info - Setup DCB QoS information
+ * @pf: ptr to ice_pf
+ * @qos_info: QoS param instance
+ */
+void ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info)
+{
+	struct ice_dcbx_cfg *dcbx_cfg;
+	unsigned int i;
+	u32 up2tc;
+
+	if (!pf || !qos_info)
+		return;
+
+	dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
+	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
+
+	qos_info->num_tc = ice_dcb_get_num_tc(dcbx_cfg);
+
+	for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++)
+		qos_info->up2tc[i] = (up2tc >> (i * 3)) & 0x7;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		qos_info->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i];
+
+	qos_info->pfc_mode = dcbx_cfg->pfc_mode;
+	if (qos_info->pfc_mode == IIDC_DSCP_PFC_MODE)
+		for (i = 0; i < DSCP_MAX; i++)
+			qos_info->dscp_map[i] = dcbx_cfg->dscp_map[i];
+}
+
+/**
  * ice_dcb_is_mib_change_pending - Check if MIB change is pending
  * @state: MIB change state
  */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
index 800879a88c5e..da9ba814b4e8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
@@ -31,6 +31,9 @@ void
 ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring,
 			      struct ice_tx_buf *first);
 void
+ice_setup_dcb_qos_info(struct ice_pf *pf,
+		       struct iidc_rdma_qos_params *qos_info);
+void
 ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 				    struct ice_rq_event_info *event);
 /**
@@ -134,5 +137,11 @@ static inline void ice_update_dcb_stats(struct ice_pf *pf) { }
 static inline void
 ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { }
 static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { }
+static inline void
+ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info)
+{
+	qos_info->num_tc = 1;
+	qos_info->tc_info[0].rel_bw = 100;
+}
 #endif /* CONFIG_DCB */
 #endif /* _ICE_DCB_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index 6d50b90a7359..a10c1c8d8697 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -754,7 +754,7 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app)
 	if (!ice_is_feature_supported(pf, ICE_F_DSCP))
 		return -EOPNOTSUPP;
 
-	if (app->protocol >= ICE_DSCP_NUM_VAL) {
+	if (app->protocol >= DSCP_MAX) {
 		netdev_err(netdev, "DSCP value 0x%04X out of range\n",
 			   app->protocol);
 		return -EINVAL;
@@ -931,7 +931,7 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app)
 	/* if the last DSCP mapping just got deleted, need to switch
 	 * to L2 VLAN QoS mode
 	 */
-	if (bitmap_empty(new_cfg->dscp_mapped, ICE_DSCP_NUM_VAL) &&
+	if (bitmap_empty(new_cfg->dscp_mapped, DSCP_MAX) &&
 	    new_cfg->pfc_mode == ICE_QOS_MODE_DSCP) {
 		ret = ice_aq_set_pfc_mode(&pf->hw,
 					  ICE_AQC_PFC_VLAN_BASED_PFC,
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 03988be03729..59323c019544 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -2345,15 +2345,15 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
 			cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
 					  ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
 
-		if (ice_is_e825c(hw))
-			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 	} else {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
 		cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
-	}
 
-	if (!ice_is_e825c(hw))
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		if (hw->mac_type == ICE_MAC_E810 ||
+		    hw->mac_type == ICE_MAC_GENERIC)
+			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	}
 
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
 	if (status)
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index d5ad6d84007c..bce3ad6ca2a6 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -95,7 +95,7 @@ ice_dpll_pin_freq_set(struct ice_pf *pf, struct ice_dpll_pin *pin,
 	}
 	if (ret) {
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin freq:%u on pin:%u\n",
+				   "err:%d %s failed to set pin freq:%u on pin:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   freq, pin->idx);
@@ -322,7 +322,7 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin,
 	}
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to enable %s pin:%u\n",
+				   "err:%d %s failed to enable %s pin:%u",
 				   ret, ice_aq_str(hw->adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
 
@@ -367,7 +367,7 @@ ice_dpll_pin_disable(struct ice_hw *hw, struct ice_dpll_pin *pin,
 	}
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to disable %s pin:%u\n",
+				   "err:%d %s failed to disable %s pin:%u",
 				   ret, ice_aq_str(hw->adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
 
@@ -479,7 +479,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 err:
 	if (extack)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to update %s pin:%u\n",
+				   "err:%d %s failed to update %s pin:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
@@ -518,7 +518,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll,
 				      (u8)prio);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin prio:%u on pin:%u\n",
+				   "err:%d %s failed to set pin prio:%u on pin:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   prio, pin->idx);
@@ -1004,7 +1004,7 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv,
 	mutex_unlock(&pf->dplls.lock);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u\n",
+				   "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   phase_adjust, p->idx, d->dpll_idx);
@@ -1362,7 +1362,7 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv,
 					 &p->freq);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin state:%u for pin:%u on parent:%u\n",
+				   "err:%d %s failed to set pin state:%u for pin:%u on parent:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   state, p->idx, parent->idx);
@@ -2053,7 +2053,7 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
 	struct kthread_worker *kworker;
 
 	kthread_init_delayed_work(&d->work, ice_dpll_periodic_work);
-	kworker = kthread_create_worker(0, "ice-dplls-%s",
+	kworker = kthread_run_worker(0, "ice-dplls-%s",
 					dev_name(ice_pf_to_dev(pf)));
 	if (IS_ERR(kworker))
 		return PTR_ERR(kworker);
@@ -2065,6 +2065,18 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
 }
 
 /**
+ * ice_dpll_phase_range_set - initialize phase adjust range helper
+ * @range: pointer to phase adjust range struct to be initialized
+ * @phase_adj: a value to be used as min(-)/max(+) boundary
+ */
+static void ice_dpll_phase_range_set(struct dpll_pin_phase_adjust_range *range,
+				     u32 phase_adj)
+{
+	range->min = -phase_adj;
+	range->max = phase_adj;
+}
+
+/**
  * ice_dpll_init_info_pins_generic - initializes generic pins info
  * @pf: board private structure
  * @input: if input pins initialized
@@ -2105,8 +2117,8 @@ static int ice_dpll_init_info_pins_generic(struct ice_pf *pf, bool input)
 	for (i = 0; i < pin_num; i++) {
 		pins[i].idx = i;
 		pins[i].prop.board_label = labels[i];
-		pins[i].prop.phase_range.min = phase_adj_max;
-		pins[i].prop.phase_range.max = -phase_adj_max;
+		ice_dpll_phase_range_set(&pins[i].prop.phase_range,
+					 phase_adj_max);
 		pins[i].prop.capabilities = cap;
 		pins[i].pf = pf;
 		ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL);
@@ -2152,6 +2164,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 	struct ice_hw *hw = &pf->hw;
 	struct ice_dpll_pin *pins;
 	unsigned long caps;
+	u32 phase_adj_max;
 	u8 freq_supp_num;
 	bool input;
 
@@ -2159,11 +2172,13 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 	case ICE_DPLL_PIN_TYPE_INPUT:
 		pins = pf->dplls.inputs;
 		num_pins = pf->dplls.num_inputs;
+		phase_adj_max = pf->dplls.input_phase_adj_max;
 		input = true;
 		break;
 	case ICE_DPLL_PIN_TYPE_OUTPUT:
 		pins = pf->dplls.outputs;
 		num_pins = pf->dplls.num_outputs;
+		phase_adj_max = pf->dplls.output_phase_adj_max;
 		input = false;
 		break;
 	default:
@@ -2188,19 +2203,13 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 				return ret;
 			caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE |
 				 DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE);
-			pins[i].prop.phase_range.min =
-				pf->dplls.input_phase_adj_max;
-			pins[i].prop.phase_range.max =
-				-pf->dplls.input_phase_adj_max;
 		} else {
-			pins[i].prop.phase_range.min =
-				pf->dplls.output_phase_adj_max;
-			pins[i].prop.phase_range.max =
-				-pf->dplls.output_phase_adj_max;
 			ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps);
 			if (ret)
 				return ret;
 		}
+		ice_dpll_phase_range_set(&pins[i].prop.phase_range,
+					 phase_adj_max);
 		pins[i].prop.capabilities = caps;
 		ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL);
 		if (ret)
@@ -2308,8 +2317,10 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu)
 	dp->dpll_idx = abilities.pps_dpll_idx;
 	d->num_inputs = abilities.num_inputs;
 	d->num_outputs = abilities.num_outputs;
-	d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj);
-	d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj);
+	d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj) &
+		ICE_AQC_GET_CGU_MAX_PHASE_ADJ;
+	d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj) &
+		ICE_AQC_GET_CGU_MAX_PHASE_ADJ;
 
 	alloc_size = sizeof(*d->inputs) * d->num_inputs;
 	d->inputs = kzalloc(alloc_size, GFP_KERNEL);
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index fb527434b58b..2e4f0969035f 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -29,6 +29,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 			return -ENODEV;
 
 	ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx);
+	ice_vsi_cfg_sw_lldp(uplink_vsi, true, false);
 
 	netif_addr_lock_bh(netdev);
 	__dev_uc_unsync(netdev, NULL);
@@ -38,8 +39,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (ice_vsi_add_vlan_zero(uplink_vsi))
 		goto err_vlan_zero;
 
-	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
-			     ICE_FLTR_RX))
+	if (ice_set_dflt_vsi(uplink_vsi))
 		goto err_def_rx;
 
 	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
@@ -50,9 +50,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (vlan_ops->dis_rx_filtering(uplink_vsi))
 		goto err_vlan_filtering;
 
-	if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override))
-		goto err_override_uplink;
-
 	if (ice_vsi_update_local_lb(uplink_vsi, true))
 		goto err_override_local_lb;
 
@@ -64,8 +61,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 err_up:
 	ice_vsi_update_local_lb(uplink_vsi, false);
 err_override_local_lb:
-	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
-err_override_uplink:
 	vlan_ops->ena_rx_filtering(uplink_vsi);
 err_vlan_filtering:
 	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
@@ -251,6 +246,10 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb,
 	u64 cd_cmd, dst_vsi;
 
 	if (!dst) {
+		struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb);
+
+		if (unlikely(eth->h_proto == htons(ETH_P_LLDP)))
+			return;
 		cd_cmd = ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S;
 		off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX);
 	} else {
@@ -276,7 +275,6 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
 
 	ice_vsi_update_local_lb(uplink_vsi, false);
-	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 	vlan_ops->ena_rx_filtering(uplink_vsi);
 	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
 			 ICE_FLTR_TX);
@@ -285,6 +283,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 	ice_fltr_add_mac_and_broadcast(uplink_vsi,
 				       uplink_vsi->port_info->mac.perm_addr,
 				       ICE_FWD_TO_VSI);
+	ice_vsi_cfg_sw_lldp(uplink_vsi, true, true);
 }
 
 /**
@@ -509,10 +508,14 @@ err_create_repr:
  */
 int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 {
-	struct ice_repr *repr = ice_repr_create_vf(vf);
 	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_repr *repr;
 	int err;
 
+	if (!ice_is_eswitch_mode_switchdev(pf))
+		return 0;
+
+	repr = ice_repr_create_vf(vf);
 	if (IS_ERR(repr))
 		return PTR_ERR(repr);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h
index ac7db100e2cd..5c7dcf21b222 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h
@@ -5,7 +5,7 @@
 #define _ICE_ESWITCH_H_
 
 #include <net/devlink.h>
-#include "devlink/devlink_port.h"
+#include "devlink/port.h"
 
 #ifdef CONFIG_ICE_SWITCHDEV
 void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf);
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 3072634bf049..bbf9e6fd315b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -710,7 +710,6 @@ static int ice_get_tx_rx_equa(struct ice_hw *hw, u8 serdes_num,
 		{ ICE_AQC_RX_EQU_POST1, rx, &ptr->rx_equ_post1 },
 		{ ICE_AQC_RX_EQU_BFLF, rx, &ptr->rx_equ_bflf },
 		{ ICE_AQC_RX_EQU_BFHF, rx, &ptr->rx_equ_bfhf },
-		{ ICE_AQC_RX_EQU_DRATE, rx, &ptr->rx_equ_drate },
 		{ ICE_AQC_RX_EQU_CTLE_GAINHF, rx, &ptr->rx_equ_ctle_gainhf },
 		{ ICE_AQC_RX_EQU_CTLE_GAINLF, rx, &ptr->rx_equ_ctle_gainlf },
 		{ ICE_AQC_RX_EQU_CTLE_GAINDC, rx, &ptr->rx_equ_ctle_gaindc },
@@ -1819,7 +1818,7 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
 			/* Remove rule to direct LLDP packets to default VSI.
 			 * The FW LLDP engine will now be consuming them.
 			 */
-			ice_cfg_sw_lldp(vsi, false, false);
+			ice_cfg_sw_rx_lldp(vsi->back, false);
 
 			/* AQ command to start FW LLDP agent will return an
 			 * error if the agent is already started
@@ -3789,8 +3788,7 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info)
  */
 static int ice_get_max_txq(struct ice_pf *pf)
 {
-	return min3(pf->num_lan_msix, (u16)num_online_cpus(),
-		    (u16)pf->hw.func_caps.common_cap.num_txq);
+	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq);
 }
 
 /**
@@ -3799,8 +3797,7 @@ static int ice_get_max_txq(struct ice_pf *pf)
  */
 static int ice_get_max_rxq(struct ice_pf *pf)
 {
-	return min3(pf->num_lan_msix, (u16)num_online_cpus(),
-		    (u16)pf->hw.func_caps.common_cap.num_rxq);
+	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq);
 }
 
 /**
@@ -3818,8 +3815,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi)
 	ice_for_each_q_vector(vsi, q_idx) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
 
-		if (q_vector->rx.rx_ring && q_vector->tx.tx_ring)
-			combined++;
+		combined += min(q_vector->num_ring_tx, q_vector->num_ring_rx);
 	}
 
 	return combined;
@@ -3968,11 +3964,11 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 		return -EINVAL;
 	}
 
-	if (pf->adev) {
+	if (pf->cdev_info && pf->cdev_info->adev) {
 		mutex_lock(&pf->adev_mutex);
-		device_lock(&pf->adev->dev);
+		device_lock(&pf->cdev_info->adev->dev);
 		locked = true;
-		if (pf->adev->dev.driver) {
+		if (pf->cdev_info->adev->dev.driver) {
 			netdev_err(dev, "Cannot change channels when RDMA is active\n");
 			ret = -EBUSY;
 			goto adev_unlock;
@@ -3991,7 +3987,7 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 
 adev_unlock:
 	if (locked) {
-		device_unlock(&pf->adev->dev);
+		device_unlock(&pf->cdev_info->adev->dev);
 		mutex_unlock(&pf->adev_mutex);
 	}
 	return ret;
@@ -4774,7 +4770,7 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_RX_USECS_HIGH,
-	.cap_rss_sym_xor_supported = true,
+	.supported_input_xfrm	= RXH_XFRM_SYM_XOR,
 	.rxfh_per_ctx_key	= true,
 	.get_link_ksettings	= ice_get_link_ksettings,
 	.set_link_ksettings	= ice_set_link_ksettings,
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h
index 8f2ad1c172c0..23b2cfbc9684 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.h
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h
@@ -15,7 +15,6 @@ struct ice_serdes_equalization_to_ethtool {
 	int rx_equ_post1;
 	int rx_equ_bflf;
 	int rx_equ_bfhf;
-	int rx_equ_drate;
 	int rx_equ_ctle_gainhf;
 	int rx_equ_ctle_gainlf;
 	int rx_equ_ctle_gaindc;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index ee9862ddfe15..aceec184e89b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1605,22 +1605,19 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf)
  */
 int ice_fdir_create_dflt_rules(struct ice_pf *pf)
 {
+	static const enum ice_fltr_ptype dflt_rules[] = {
+		ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_UDP,
+		ICE_FLTR_PTYPE_NONF_IPV6_TCP, ICE_FLTR_PTYPE_NONF_IPV6_UDP,
+	};
 	int err;
 
 	/* Create perfect TCP and UDP rules in hardware. */
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_TCP);
-	if (err)
-		return err;
-
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP);
-	if (err)
-		return err;
+	for (int i = 0; i < ARRAY_SIZE(dflt_rules); i++) {
+		err = ice_create_init_fdir_rule(pf, dflt_rules[i]);
 
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_TCP);
-	if (err)
-		return err;
-
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_UDP);
+		if (err)
+			break;
+	}
 
 	return err;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 2702a0da5c3e..70c201f569ce 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -6,6 +6,7 @@
 #include <linux/crc32.h>
 #include <linux/pldmfw.h>
 #include "ice.h"
+#include "ice_lib.h"
 #include "ice_fw_update.h"
 
 struct ice_fwu_priv {
@@ -125,6 +126,10 @@ ice_check_component_response(struct ice_pf *pf, u16 id, u8 response, u8 code,
 	case ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED:
 		dev_info(dev, "firmware has rejected updating %s\n", component);
 		break;
+	case ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK:
+		if (ice_is_recovery_mode(&pf->hw))
+			return 0;
+		break;
 	}
 
 	switch (code) {
@@ -1004,13 +1009,20 @@ int ice_devlink_flash_update(struct devlink *devlink,
 		return -EOPNOTSUPP;
 	}
 
-	if (!hw->dev_caps.common_cap.nvm_unified_update) {
+	if (!hw->dev_caps.common_cap.nvm_unified_update && !ice_is_recovery_mode(hw)) {
 		NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update");
 		return -EOPNOTSUPP;
 	}
 
 	memset(&priv, 0, sizeof(priv));
 
+	if (params->component && strcmp(params->component, "fw.mgmt") == 0) {
+		priv.context.mode = PLDMFW_UPDATE_MODE_SINGLE_COMPONENT;
+		priv.context.component_identifier = NVM_COMP_ID_NVM;
+	} else if (params->component) {
+		return -EOPNOTSUPP;
+	}
+
 	/* the E822 device needs a slightly different ops */
 	if (hw->mac_type == ICE_MAC_GENERIC)
 		priv.context.ops = &ice_fwu_ops_e822;
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c
index f02e8ca55375..6b26290452d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.c
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.c
@@ -182,7 +182,7 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf)
 	pf->gnss_serial = gnss;
 
 	kthread_init_delayed_work(&gnss->read_work, ice_gnss_read);
-	kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev));
+	kworker = kthread_run_worker(0, "ice-gnss-%s", dev_name(dev));
 	if (IS_ERR(kworker)) {
 		kfree(gnss);
 		return NULL;
@@ -381,32 +381,23 @@ void ice_gnss_exit(struct ice_pf *pf)
 }
 
 /**
- * ice_gnss_is_gps_present - Check if GPS HW is present
+ * ice_gnss_is_module_present - Check if GNSS HW is present
  * @hw: pointer to HW struct
+ *
+ * Return: true when GNSS is present, false otherwise.
  */
-bool ice_gnss_is_gps_present(struct ice_hw *hw)
+bool ice_gnss_is_module_present(struct ice_hw *hw)
 {
-	if (!hw->func_caps.ts_func_info.src_tmr_owned)
-		return false;
+	int err;
+	u8 data;
 
-	if (!ice_is_gps_in_netlist(hw))
+	if (!hw->func_caps.ts_func_info.src_tmr_owned ||
+	    !ice_is_gps_in_netlist(hw))
 		return false;
 
-#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-	if (ice_is_e810t(hw)) {
-		int err;
-		u8 data;
-
-		err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data);
-		if (err || !!(data & ICE_P0_GNSS_PRSNT_N))
-			return false;
-	} else {
-		return false;
-	}
-#else
-	if (!ice_is_e810t(hw))
+	err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data);
+	if (err || !!(data & ICE_P0_GNSS_PRSNT_N))
 		return false;
-#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 
 	return true;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h
index 75e567ad7059..15daf603ed7b 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.h
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.h
@@ -37,11 +37,11 @@ struct gnss_serial {
 #if IS_ENABLED(CONFIG_GNSS)
 void ice_gnss_init(struct ice_pf *pf);
 void ice_gnss_exit(struct ice_pf *pf);
-bool ice_gnss_is_gps_present(struct ice_hw *hw);
+bool ice_gnss_is_module_present(struct ice_hw *hw);
 #else
 static inline void ice_gnss_init(struct ice_pf *pf) { }
 static inline void ice_gnss_exit(struct ice_pf *pf) { }
-static inline bool ice_gnss_is_gps_present(struct ice_hw *hw)
+static inline bool ice_gnss_is_module_present(struct ice_hw *hw)
 {
 	return false;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index dc88aea9f473..aa4bfbcf85d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -541,10 +541,22 @@
 #define PFPM_WUS_MAG_M				BIT(1)
 #define PFPM_WUS_MNG_M				BIT(3)
 #define PFPM_WUS_FW_RST_WK_M			BIT(31)
+#define E830_PRTMAC_TS_TX_MEM_VALID_H		0x001E2020
+#define E830_PRTMAC_TS_TX_MEM_VALID_L		0x001E2000
 #define E830_PRTMAC_CL01_PS_QNT			0x001E32A0
 #define E830_PRTMAC_CL01_PS_QNT_CL0_M		GENMASK(15, 0)
 #define E830_PRTMAC_CL01_QNT_THR		0x001E3320
 #define E830_PRTMAC_CL01_QNT_THR_CL0_M		GENMASK(15, 0)
+#define E830_PRTTSYN_TXTIME_H(_i)		(0x001E5800 + ((_i) * 32))
+#define E830_PRTTSYN_TXTIME_L(_i)		(0x001E5000 + ((_i) * 32))
+#define E830_GLPTM_ART_CTL			0x00088B50
+#define E830_GLPTM_ART_CTL_ACTIVE_M		BIT(0)
+#define E830_GLPTM_ART_TIME_H			0x00088B54
+#define E830_GLPTM_ART_TIME_L			0x00088B58
+#define E830_GLTSYN_PTMTIME_H(_i)		(0x00088B48 + ((_i) * 4))
+#define E830_GLTSYN_PTMTIME_L(_i)		(0x00088B40 + ((_i) * 4))
+#define E830_PFPTM_SEM				0x00088B00
+#define E830_PFPTM_SEM_BUSY_M			BIT(0)
 #define VFINT_DYN_CTLN(_i)			(0x00003800 + ((_i) * 4))
 #define VFINT_DYN_CTLN_CLEARPBA_M		BIT(1)
 #define E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH	0x00234000
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 145b27f2a4ce..6ab53e430f91 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -9,22 +9,25 @@
 static DEFINE_XARRAY_ALLOC1(ice_aux_id);
 
 /**
- * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct
- * @pf: pointer to PF struct
+ * ice_get_auxiliary_drv - retrieve iidc_rdma_core_auxiliary_drv struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  *
  * This function has to be called with a device_lock on the
- * pf->adev.dev to avoid race conditions.
+ * cdev->adev.dev to avoid race conditions.
+ *
+ * Return: pointer to the matched auxiliary driver struct
  */
-static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf)
+static struct iidc_rdma_core_auxiliary_drv *
+ice_get_auxiliary_drv(struct iidc_rdma_core_dev_info *cdev)
 {
 	struct auxiliary_device *adev;
 
-	adev = pf->adev;
+	adev = cdev->adev;
 	if (!adev || !adev->dev.driver)
 		return NULL;
 
-	return container_of(adev->dev.driver, struct iidc_auxiliary_drv,
-			    adrv.driver);
+	return container_of(adev->dev.driver,
+			    struct iidc_rdma_core_auxiliary_drv, adrv.driver);
 }
 
 /**
@@ -32,44 +35,54 @@ static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf)
  * @pf: pointer to PF struct
  * @event: event struct
  */
-void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event)
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event)
 {
-	struct iidc_auxiliary_drv *iadrv;
+	struct iidc_rdma_core_auxiliary_drv *iadrv;
+	struct iidc_rdma_core_dev_info *cdev;
 
 	if (WARN_ON_ONCE(!in_task()))
 		return;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return;
+
 	mutex_lock(&pf->adev_mutex);
-	if (!pf->adev)
+	if (!cdev->adev)
 		goto finish;
 
-	device_lock(&pf->adev->dev);
-	iadrv = ice_get_auxiliary_drv(pf);
+	device_lock(&cdev->adev->dev);
+	iadrv = ice_get_auxiliary_drv(cdev);
 	if (iadrv && iadrv->event_handler)
-		iadrv->event_handler(pf, event);
-	device_unlock(&pf->adev->dev);
+		iadrv->event_handler(cdev, event);
+	device_unlock(&cdev->adev->dev);
 finish:
 	mutex_unlock(&pf->adev_mutex);
 }
 
 /**
  * ice_add_rdma_qset - Add Leaf Node for RDMA Qset
- * @pf: PF struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @qset: Resource to be allocated
+ *
+ * Return: Zero on success or error code encountered
  */
-int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+int ice_add_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset)
 {
 	u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_vsi *vsi;
 	struct device *dev;
+	struct ice_pf *pf;
 	u32 qset_teid;
 	u16 qs_handle;
 	int status;
 	int i;
 
-	if (WARN_ON(!pf || !qset))
+	if (WARN_ON(!cdev || !qset))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	dev = ice_pf_to_dev(pf);
 
 	if (!ice_is_rdma_ena(pf))
@@ -100,7 +113,6 @@ int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
 		dev_err(dev, "Failed VSI RDMA Qset enable\n");
 		return status;
 	}
-	vsi->qset_handle[qset->tc] = qset->qs_handle;
 	qset->teid = qset_teid;
 
 	return 0;
@@ -109,18 +121,23 @@ EXPORT_SYMBOL_GPL(ice_add_rdma_qset);
 
 /**
  * ice_del_rdma_qset - Delete leaf node for RDMA Qset
- * @pf: PF struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @qset: Resource to be freed
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+int ice_del_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset)
 {
 	struct ice_vsi *vsi;
+	struct ice_pf *pf;
 	u32 teid;
 	u16 q_id;
 
-	if (WARN_ON(!pf || !qset))
+	if (WARN_ON(!cdev || !qset))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	vsi = ice_find_vsi(pf, qset->vport_id);
 	if (!vsi) {
 		dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n");
@@ -130,36 +147,36 @@ int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
 	q_id = qset->qs_handle;
 	teid = qset->teid;
 
-	vsi->qset_handle[qset->tc] = 0;
-
 	return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id);
 }
 EXPORT_SYMBOL_GPL(ice_del_rdma_qset);
 
 /**
  * ice_rdma_request_reset - accept request from RDMA to perform a reset
- * @pf: struct for PF
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @reset_type: type of reset
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type)
+int ice_rdma_request_reset(struct iidc_rdma_core_dev_info *cdev,
+			   enum iidc_rdma_reset_type reset_type)
 {
 	enum ice_reset_req reset;
+	struct ice_pf *pf;
 
-	if (WARN_ON(!pf))
+	if (WARN_ON(!cdev))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
+
 	switch (reset_type) {
-	case IIDC_PFR:
+	case IIDC_FUNC_RESET:
 		reset = ICE_RESET_PFR;
 		break;
-	case IIDC_CORER:
+	case IIDC_DEV_RESET:
 		reset = ICE_RESET_CORER;
 		break;
-	case IIDC_GLOBR:
-		reset = ICE_RESET_GLOBR;
-		break;
 	default:
-		dev_err(ice_pf_to_dev(pf), "incorrect reset request\n");
 		return -EINVAL;
 	}
 
@@ -169,18 +186,23 @@ EXPORT_SYMBOL_GPL(ice_rdma_request_reset);
 
 /**
  * ice_rdma_update_vsi_filter - update main VSI filters for RDMA
- * @pf: pointer to struct for PF
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @vsi_id: VSI HW idx to update filter on
  * @enable: bool whether to enable or disable filters
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable)
+int ice_rdma_update_vsi_filter(struct iidc_rdma_core_dev_info *cdev,
+			       u16 vsi_id, bool enable)
 {
 	struct ice_vsi *vsi;
+	struct ice_pf *pf;
 	int status;
 
-	if (WARN_ON(!pf))
+	if (WARN_ON(!cdev))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	vsi = ice_find_vsi(pf, vsi_id);
 	if (!vsi)
 		return -EINVAL;
@@ -201,88 +223,54 @@ int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable)
 EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter);
 
 /**
- * ice_get_qos_params - parse QoS params for RDMA consumption
- * @pf: pointer to PF struct
- * @qos: set of QoS values
- */
-void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos)
-{
-	struct ice_dcbx_cfg *dcbx_cfg;
-	unsigned int i;
-	u32 up2tc;
-
-	dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
-	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
-
-	qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg);
-	for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++)
-		qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7;
-
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
-		qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i];
-
-	qos->pfc_mode = dcbx_cfg->pfc_mode;
-	if (qos->pfc_mode == IIDC_DSCP_PFC_MODE)
-		for (i = 0; i < IIDC_MAX_DSCP_MAPPING; i++)
-			qos->dscp_map[i] = dcbx_cfg->dscp_map[i];
-}
-EXPORT_SYMBOL_GPL(ice_get_qos_params);
-
-/**
- * ice_alloc_rdma_qvectors - Allocate vector resources for RDMA driver
- * @pf: board private structure to initialize
+ * ice_alloc_rdma_qvector - alloc vector resources reserved for RDMA driver
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
+ * @entry: MSI-X entry to be removed
+ *
+ * Return: Zero on success, error code on failure
  */
-static int ice_alloc_rdma_qvectors(struct ice_pf *pf)
+int ice_alloc_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry)
 {
-	if (ice_is_rdma_ena(pf)) {
-		int i;
-
-		pf->msix_entries = kcalloc(pf->num_rdma_msix,
-					   sizeof(*pf->msix_entries),
-						  GFP_KERNEL);
-		if (!pf->msix_entries)
-			return -ENOMEM;
+	struct msi_map map;
+	struct ice_pf *pf;
 
-		/* RDMA is the only user of pf->msix_entries array */
-		pf->rdma_base_vector = 0;
+	if (WARN_ON(!cdev))
+		return -EINVAL;
 
-		for (i = 0; i < pf->num_rdma_msix; i++) {
-			struct msix_entry *entry = &pf->msix_entries[i];
-			struct msi_map map;
+	pf = pci_get_drvdata(cdev->pdev);
+	map = ice_alloc_irq(pf, true);
+	if (map.index < 0)
+		return -ENOMEM;
 
-			map = ice_alloc_irq(pf, false);
-			if (map.index < 0)
-				break;
+	entry->entry = map.index;
+	entry->vector = map.virq;
 
-			entry->entry = map.index;
-			entry->vector = map.virq;
-		}
-	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ice_alloc_rdma_qvector);
 
 /**
  * ice_free_rdma_qvector - free vector resources reserved for RDMA driver
- * @pf: board private structure to initialize
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
+ * @entry: MSI-X entry to be removed
  */
-static void ice_free_rdma_qvector(struct ice_pf *pf)
+void ice_free_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry)
 {
-	int i;
+	struct msi_map map;
+	struct ice_pf *pf;
 
-	if (!pf->msix_entries)
+	if (WARN_ON(!cdev || !entry))
 		return;
 
-	for (i = 0; i < pf->num_rdma_msix; i++) {
-		struct msi_map map;
-
-		map.index = pf->msix_entries[i].entry;
-		map.virq = pf->msix_entries[i].vector;
-		ice_free_irq(pf, map);
-	}
+	pf = pci_get_drvdata(cdev->pdev);
 
-	kfree(pf->msix_entries);
-	pf->msix_entries = NULL;
+	map.index = entry->entry;
+	map.virq = entry->vector;
+	ice_free_irq(pf, map);
 }
+EXPORT_SYMBOL_GPL(ice_free_rdma_qvector);
 
 /**
  * ice_adev_release - function to be mapped to AUX dev's release op
@@ -290,19 +278,23 @@ static void ice_free_rdma_qvector(struct ice_pf *pf)
  */
 static void ice_adev_release(struct device *dev)
 {
-	struct iidc_auxiliary_dev *iadev;
+	struct iidc_rdma_core_auxiliary_dev *iadev;
 
-	iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev);
+	iadev = container_of(dev, struct iidc_rdma_core_auxiliary_dev,
+			     adev.dev);
 	kfree(iadev);
 }
 
 /**
  * ice_plug_aux_dev - allocate and register AUX device
  * @pf: pointer to pf struct
+ *
+ * Return: Zero on success, error code on failure
  */
 int ice_plug_aux_dev(struct ice_pf *pf)
 {
-	struct iidc_auxiliary_dev *iadev;
+	struct iidc_rdma_core_auxiliary_dev *iadev;
+	struct iidc_rdma_core_dev_info *cdev;
 	struct auxiliary_device *adev;
 	int ret;
 
@@ -312,17 +304,22 @@ int ice_plug_aux_dev(struct ice_pf *pf)
 	if (!ice_is_rdma_ena(pf))
 		return 0;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
 	if (!iadev)
 		return -ENOMEM;
 
 	adev = &iadev->adev;
-	iadev->pf = pf;
+	iadev->cdev_info = cdev;
 
 	adev->id = pf->aux_idx;
 	adev->dev.release = ice_adev_release;
 	adev->dev.parent = &pf->pdev->dev;
-	adev->name = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? "roce" : "iwarp";
+	adev->name = cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2 ?
+		"roce" : "iwarp";
 
 	ret = auxiliary_device_init(adev);
 	if (ret) {
@@ -337,7 +334,7 @@ int ice_plug_aux_dev(struct ice_pf *pf)
 	}
 
 	mutex_lock(&pf->adev_mutex);
-	pf->adev = adev;
+	cdev->adev = adev;
 	mutex_unlock(&pf->adev_mutex);
 
 	return 0;
@@ -351,8 +348,8 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
 	struct auxiliary_device *adev;
 
 	mutex_lock(&pf->adev_mutex);
-	adev = pf->adev;
-	pf->adev = NULL;
+	adev = pf->cdev_info->adev;
+	pf->cdev_info->adev = NULL;
 	mutex_unlock(&pf->adev_mutex);
 
 	if (adev) {
@@ -367,7 +364,9 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
  */
 int ice_init_rdma(struct ice_pf *pf)
 {
+	struct iidc_rdma_priv_dev_info *privd;
 	struct device *dev = &pf->pdev->dev;
+	struct iidc_rdma_core_dev_info *cdev;
 	int ret;
 
 	if (!ice_is_rdma_ena(pf)) {
@@ -375,30 +374,50 @@ int ice_init_rdma(struct ice_pf *pf)
 		return 0;
 	}
 
+	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return -ENOMEM;
+
+	pf->cdev_info = cdev;
+
+	privd = kzalloc(sizeof(*privd), GFP_KERNEL);
+	if (!privd) {
+		ret = -ENOMEM;
+		goto err_privd_alloc;
+	}
+
+	privd->pf_id = pf->hw.pf_id;
 	ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX),
 		       GFP_KERNEL);
 	if (ret) {
 		dev_err(dev, "Failed to allocate device ID for AUX driver\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_alloc_xa;
 	}
 
-	/* Reserve vector resources */
-	ret = ice_alloc_rdma_qvectors(pf);
-	if (ret < 0) {
-		dev_err(dev, "failed to reserve vectors for RDMA\n");
-		goto err_reserve_rdma_qvector;
-	}
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	cdev->iidc_priv = privd;
+	privd->netdev = pf->vsi[0]->netdev;
+
+	privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr;
+	cdev->pdev = pf->pdev;
+	privd->vport_id = pf->vsi[0]->vsi_num;
+
+	pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	ice_setup_dcb_qos_info(pf, &privd->qos_info);
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
 		goto err_plug_aux_dev;
 	return 0;
 
 err_plug_aux_dev:
-	ice_free_rdma_qvector(pf);
-err_reserve_rdma_qvector:
-	pf->adev = NULL;
+	pf->cdev_info->adev = NULL;
 	xa_erase(&ice_aux_id, pf->aux_idx);
+err_alloc_xa:
+	kfree(privd);
+err_privd_alloc:
+	kfree(cdev);
+	pf->cdev_info = NULL;
+
 	return ret;
 }
 
@@ -412,6 +431,8 @@ void ice_deinit_rdma(struct ice_pf *pf)
 		return;
 
 	ice_unplug_aux_dev(pf);
-	ice_free_rdma_qvector(pf);
 	xa_erase(&ice_aux_id, pf->aux_idx);
+	kfree(pf->cdev_info->iidc_priv);
+	kfree(pf->cdev_info);
+	pf->cdev_info = NULL;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h
index 4b0c86757df9..17dbfcfb6a2a 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc_int.h
+++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h
@@ -4,10 +4,11 @@
 #ifndef _ICE_IDC_INT_H_
 #define _ICE_IDC_INT_H_
 
-#include <linux/net/intel/iidc.h>
+#include <linux/net/intel/iidc_rdma.h>
+#include <linux/net/intel/iidc_rdma_ice.h>
 
 struct ice_pf;
 
-void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event);
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event);
 
 #endif /* !_ICE_IDC_INT_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index ad82ff7d1995..30801fd375f0 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -20,6 +20,19 @@ ice_init_irq_tracker(struct ice_pf *pf, unsigned int max_vectors,
 	xa_init_flags(&pf->irq_tracker.entries, XA_FLAGS_ALLOC);
 }
 
+static int
+ice_init_virt_irq_tracker(struct ice_pf *pf, u32 base, u32 num_entries)
+{
+	pf->virt_irq_tracker.bm = bitmap_zalloc(num_entries, GFP_KERNEL);
+	if (!pf->virt_irq_tracker.bm)
+		return -ENOMEM;
+
+	pf->virt_irq_tracker.num_entries = num_entries;
+	pf->virt_irq_tracker.base = base;
+
+	return 0;
+}
+
 /**
  * ice_deinit_irq_tracker - free xarray tracker
  * @pf: board private structure
@@ -29,6 +42,11 @@ static void ice_deinit_irq_tracker(struct ice_pf *pf)
 	xa_destroy(&pf->irq_tracker.entries);
 }
 
+static void ice_deinit_virt_irq_tracker(struct ice_pf *pf)
+{
+	bitmap_free(pf->virt_irq_tracker.bm);
+}
+
 /**
  * ice_free_irq_res - free a block of resources
  * @pf: board private structure
@@ -45,7 +63,7 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index)
 /**
  * ice_get_irq_res - get an interrupt resource
  * @pf: board private structure
- * @dyn_only: force entry to be dynamically allocated
+ * @dyn_allowed: allow entry to be dynamically allocated
  *
  * Allocate new irq entry in the free slot of the tracker. Since xarray
  * is used, always allocate new entry at the lowest possible index. Set
@@ -53,11 +71,12 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index)
  *
  * Returns allocated irq entry or NULL on failure.
  */
-static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
+static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf,
+					     bool dyn_allowed)
 {
-	struct xa_limit limit = { .max = pf->irq_tracker.num_entries,
+	struct xa_limit limit = { .max = pf->irq_tracker.num_entries - 1,
 				  .min = 0 };
-	unsigned int num_static = pf->irq_tracker.num_static;
+	unsigned int num_static = pf->irq_tracker.num_static - 1;
 	struct ice_irq_entry *entry;
 	unsigned int index;
 	int ret;
@@ -66,9 +85,9 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 	if (!entry)
 		return NULL;
 
-	/* skip preallocated entries if the caller says so */
-	if (dyn_only)
-		limit.min = num_static;
+	/* only already allocated if the caller says so */
+	if (!dyn_allowed)
+		limit.max = num_static;
 
 	ret = xa_alloc(&pf->irq_tracker.entries, &index, entry, limit,
 		       GFP_KERNEL);
@@ -78,161 +97,18 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 		entry = NULL;
 	} else {
 		entry->index = index;
-		entry->dynamic = index >= num_static;
+		entry->dynamic = index > num_static;
 	}
 
 	return entry;
 }
 
-/**
- * ice_reduce_msix_usage - Reduce usage of MSI-X vectors
- * @pf: board private structure
- * @v_remain: number of remaining MSI-X vectors to be distributed
- *
- * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled.
- * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of
- * remaining vectors.
- */
-static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain)
-{
-	int v_rdma;
-
-	if (!ice_is_rdma_ena(pf)) {
-		pf->num_lan_msix = v_remain;
-		return;
-	}
-
-	/* RDMA needs at least 1 interrupt in addition to AEQ MSIX */
-	v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1;
-
-	if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) {
-		dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n");
-		clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
-
-		pf->num_rdma_msix = 0;
-		pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX;
-	} else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) ||
-		   (v_remain - v_rdma < v_rdma)) {
-		/* Support minimum RDMA and give remaining vectors to LAN MSIX
-		 */
-		pf->num_rdma_msix = ICE_MIN_RDMA_MSIX;
-		pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX;
-	} else {
-		/* Split remaining MSIX with RDMA after accounting for AEQ MSIX
-		 */
-		pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 +
-				    ICE_RDMA_NUM_AEQ_MSIX;
-		pf->num_lan_msix = v_remain - pf->num_rdma_msix;
-	}
-}
-
-/**
- * ice_ena_msix_range - Request a range of MSIX vectors from the OS
- * @pf: board private structure
- *
- * Compute the number of MSIX vectors wanted and request from the OS. Adjust
- * device usage if there are not enough vectors. Return the number of vectors
- * reserved or negative on failure.
- */
-static int ice_ena_msix_range(struct ice_pf *pf)
+#define ICE_RDMA_AEQ_MSIX 1
+static int ice_get_default_msix_amount(struct ice_pf *pf)
 {
-	int num_cpus, hw_num_msix, v_other, v_wanted, v_actual;
-	struct device *dev = ice_pf_to_dev(pf);
-	int err;
-
-	hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors;
-	num_cpus = num_online_cpus();
-
-	/* LAN miscellaneous handler */
-	v_other = ICE_MIN_LAN_OICR_MSIX;
-
-	/* Flow Director */
-	if (test_bit(ICE_FLAG_FD_ENA, pf->flags))
-		v_other += ICE_FDIR_MSIX;
-
-	/* switchdev */
-	v_other += ICE_ESWITCH_MSIX;
-
-	v_wanted = v_other;
-
-	/* LAN traffic */
-	pf->num_lan_msix = num_cpus;
-	v_wanted += pf->num_lan_msix;
-
-	/* RDMA auxiliary driver */
-	if (ice_is_rdma_ena(pf)) {
-		pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX;
-		v_wanted += pf->num_rdma_msix;
-	}
-
-	if (v_wanted > hw_num_msix) {
-		int v_remain;
-
-		dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n",
-			 v_wanted, hw_num_msix);
-
-		if (hw_num_msix < ICE_MIN_MSIX) {
-			err = -ERANGE;
-			goto exit_err;
-		}
-
-		v_remain = hw_num_msix - v_other;
-		if (v_remain < ICE_MIN_LAN_TXRX_MSIX) {
-			v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX;
-			v_remain = ICE_MIN_LAN_TXRX_MSIX;
-		}
-
-		ice_reduce_msix_usage(pf, v_remain);
-		v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other;
-
-		dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n",
-			   pf->num_lan_msix);
-		if (ice_is_rdma_ena(pf))
-			dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n",
-				   pf->num_rdma_msix);
-	}
-
-	/* actually reserve the vectors */
-	v_actual = pci_alloc_irq_vectors(pf->pdev, ICE_MIN_MSIX, v_wanted,
-					 PCI_IRQ_MSIX);
-	if (v_actual < 0) {
-		dev_err(dev, "unable to reserve MSI-X vectors\n");
-		err = v_actual;
-		goto exit_err;
-	}
-
-	if (v_actual < v_wanted) {
-		dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
-			 v_wanted, v_actual);
-
-		if (v_actual < ICE_MIN_MSIX) {
-			/* error if we can't get minimum vectors */
-			pci_free_irq_vectors(pf->pdev);
-			err = -ERANGE;
-			goto exit_err;
-		} else {
-			int v_remain = v_actual - v_other;
-
-			if (v_remain < ICE_MIN_LAN_TXRX_MSIX)
-				v_remain = ICE_MIN_LAN_TXRX_MSIX;
-
-			ice_reduce_msix_usage(pf, v_remain);
-
-			dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n",
-				   pf->num_lan_msix);
-
-			if (ice_is_rdma_ena(pf))
-				dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n",
-					   pf->num_rdma_msix);
-		}
-	}
-
-	return v_actual;
-
-exit_err:
-	pf->num_rdma_msix = 0;
-	pf->num_lan_msix = 0;
-	return err;
+	return ICE_MIN_LAN_OICR_MSIX + num_online_cpus() +
+	       (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? ICE_FDIR_MSIX : 0) +
+	       (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_AEQ_MSIX : 0);
 }
 
 /**
@@ -243,6 +119,7 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf)
 {
 	pci_free_irq_vectors(pf->pdev);
 	ice_deinit_irq_tracker(pf);
+	ice_deinit_virt_irq_tracker(pf);
 }
 
 /**
@@ -252,27 +129,38 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf)
 int ice_init_interrupt_scheme(struct ice_pf *pf)
 {
 	int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
-	int vectors, max_vectors;
+	int vectors;
 
-	vectors = ice_ena_msix_range(pf);
+	/* load default PF MSI-X range */
+	if (!pf->msix.min)
+		pf->msix.min = ICE_MIN_MSIX;
 
-	if (vectors < 0)
-		return -ENOMEM;
+	if (!pf->msix.max)
+		pf->msix.max = min(total_vectors,
+				   ice_get_default_msix_amount(pf));
+
+	pf->msix.total = total_vectors;
+	pf->msix.rest = total_vectors - pf->msix.max;
 
 	if (pci_msix_can_alloc_dyn(pf->pdev))
-		max_vectors = total_vectors;
+		vectors = pf->msix.min;
 	else
-		max_vectors = vectors;
+		vectors = pf->msix.max;
+
+	vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors,
+					PCI_IRQ_MSIX);
+	if (vectors < 0)
+		return vectors;
 
-	ice_init_irq_tracker(pf, max_vectors, vectors);
+	ice_init_irq_tracker(pf, pf->msix.max, vectors);
 
-	return 0;
+	return ice_init_virt_irq_tracker(pf, pf->msix.max, pf->msix.rest);
 }
 
 /**
  * ice_alloc_irq - Allocate new interrupt vector
  * @pf: board private structure
- * @dyn_only: force dynamic allocation of the interrupt
+ * @dyn_allowed: allow dynamic allocation of the interrupt
  *
  * Allocate new interrupt vector for a given owner id.
  * return struct msi_map with interrupt details and track
@@ -285,27 +173,22 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
  * interrupt will be allocated with pci_msix_alloc_irq_at.
  *
  * Some callers may only support dynamically allocated interrupts.
- * This is indicated with dyn_only flag.
+ * This is indicated with dyn_allowed flag.
  *
  * On failure, return map with negative .index. The caller
  * is expected to check returned map index.
  *
  */
-struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only)
+struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed)
 {
-	int sriov_base_vector = pf->sriov_base_vector;
 	struct msi_map map = { .index = -ENOENT };
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_irq_entry *entry;
 
-	entry = ice_get_irq_res(pf, dyn_only);
+	entry = ice_get_irq_res(pf, dyn_allowed);
 	if (!entry)
 		return map;
 
-	/* fail if we're about to violate SRIOV vectors space */
-	if (sriov_base_vector && entry->index >= sriov_base_vector)
-		goto exit_free_res;
-
 	if (pci_msix_can_alloc_dyn(pf->pdev) && entry->dynamic) {
 		map = pci_msix_alloc_irq_at(pf->pdev, entry->index, NULL);
 		if (map.index < 0)
@@ -353,26 +236,40 @@ void ice_free_irq(struct ice_pf *pf, struct msi_map map)
 }
 
 /**
- * ice_get_max_used_msix_vector - Get the max used interrupt vector
- * @pf: board private structure
+ * ice_virt_get_irqs - get irqs for SR-IOV usacase
+ * @pf: pointer to PF structure
+ * @needed: number of irqs to get
  *
- * Return index of maximum used interrupt vectors with respect to the
- * beginning of the MSIX table. Take into account that some interrupts
- * may have been dynamically allocated after MSIX was initially enabled.
+ * This returns the first MSI-X vector index in PF space that is used by this
+ * VF. This index is used when accessing PF relative registers such as
+ * GLINT_VECT2FUNC and GLINT_DYN_CTL.
+ * This will always be the OICR index in the AVF driver so any functionality
+ * using vf->first_vector_idx for queue configuration_id: id of VF which will
+ * use this irqs
  */
-int ice_get_max_used_msix_vector(struct ice_pf *pf)
+int ice_virt_get_irqs(struct ice_pf *pf, u32 needed)
 {
-	unsigned long start, index, max_idx;
-	void *entry;
+	int res = bitmap_find_next_zero_area(pf->virt_irq_tracker.bm,
+					     pf->virt_irq_tracker.num_entries,
+					     0, needed, 0);
 
-	/* Treat all preallocated interrupts as used */
-	start = pf->irq_tracker.num_static;
-	max_idx = start - 1;
+	if (res >= pf->virt_irq_tracker.num_entries)
+		return -ENOENT;
 
-	xa_for_each_start(&pf->irq_tracker.entries, index, entry, start) {
-		if (index > max_idx)
-			max_idx = index;
-	}
+	bitmap_set(pf->virt_irq_tracker.bm, res, needed);
+
+	/* conversion from number in bitmap to global irq index */
+	return res + pf->virt_irq_tracker.base;
+}
 
-	return max_idx;
+/**
+ * ice_virt_free_irqs - free irqs used by the VF
+ * @pf: pointer to PF structure
+ * @index: first index to be free
+ * @irqs: number of irqs to free
+ */
+void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs)
+{
+	bitmap_clear(pf->virt_irq_tracker.bm, index - pf->virt_irq_tracker.base,
+		     irqs);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.h b/drivers/net/ethernet/intel/ice/ice_irq.h
index f35efc08575e..b2f9dbafd57e 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.h
+++ b/drivers/net/ethernet/intel/ice/ice_irq.h
@@ -15,11 +15,22 @@ struct ice_irq_tracker {
 	u16 num_static;	/* preallocated entries */
 };
 
+struct ice_virt_irq_tracker {
+	unsigned long *bm;	/* bitmap to track irq usage */
+	u32 num_entries;
+	/* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
+	 * number of MSIX vectors needed for all SR-IOV VFs from the number of
+	 * MSIX vectors allowed on this PF.
+	 */
+	u32 base;
+};
+
 int ice_init_interrupt_scheme(struct ice_pf *pf);
 void ice_clear_interrupt_scheme(struct ice_pf *pf);
 
 struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only);
 void ice_free_irq(struct ice_pf *pf, struct msi_map map);
-int ice_get_max_used_msix_vector(struct ice_pf *pf);
 
+int ice_virt_get_irqs(struct ice_pf *pf, u32 needed);
+void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs);
 #endif
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 1ccb572ce285..2410aee59fb2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -1001,6 +1001,28 @@ static void ice_lag_link(struct ice_lag *lag)
 }
 
 /**
+ * ice_lag_config_eswitch - configure eswitch to work with LAG
+ * @lag: lag info struct
+ * @netdev: active network interface device struct
+ *
+ * Updates all port representors in eswitch to use @netdev for Tx.
+ *
+ * Configures the netdev to keep dst metadata (also used in representor Tx).
+ * This is required for an uplink without switchdev mode configured.
+ */
+static void ice_lag_config_eswitch(struct ice_lag *lag,
+				   struct net_device *netdev)
+{
+	struct ice_repr *repr;
+	unsigned long id;
+
+	xa_for_each(&lag->pf->eswitch.reprs, id, repr)
+		repr->dst->u.port_info.lower_dev = netdev;
+
+	netif_keep_dst(netdev);
+}
+
+/**
  * ice_lag_unlink - handle unlink event
  * @lag: LAG info struct
  */
@@ -1021,6 +1043,9 @@ static void ice_lag_unlink(struct ice_lag *lag)
 			ice_lag_move_vf_nodes(lag, act_port, pri_port);
 		lag->primary = false;
 		lag->active_port = ICE_LAG_INVALID_PORT;
+
+		/* Config primary's eswitch back to normal operation. */
+		ice_lag_config_eswitch(lag, lag->netdev);
 	} else {
 		struct ice_lag *primary_lag;
 
@@ -1296,12 +1321,18 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 		 */
 		if (!primary_lag) {
 			lag->primary = true;
+			if (!ice_is_switchdev_running(lag->pf))
+				return;
+
 			/* Configure primary's SWID to be shared */
 			ice_lag_primary_swid(lag, true);
 			primary_lag = lag;
 		} else {
 			u16 swid;
 
+			if (!ice_is_switchdev_running(primary_lag->pf))
+				return;
+
 			swid = primary_lag->pf->hw.port_info->sw_id;
 			ice_lag_set_swid(swid, lag, true);
 			ice_lag_add_prune_list(primary_lag, lag->pf);
@@ -1419,6 +1450,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 				ice_lag_move_vf_nodes(lag, prim_port,
 						      event_port);
 			lag->active_port = event_port;
+			ice_lag_config_eswitch(lag, event_netdev);
 			return;
 		}
 
@@ -1428,6 +1460,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 		/* new active port */
 		ice_lag_move_vf_nodes(lag, lag->active_port, event_port);
 		lag->active_port = event_port;
+		ice_lag_config_eswitch(lag, event_netdev);
 	} else {
 		/* port not set as currently active (e.g. new active port
 		 * has already claimed the nodes and filters
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 611577ebc29d..77ba26538b07 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -229,7 +229,7 @@ struct ice_32b_rx_flex_desc_nic {
 	__le16 status_error1;
 	u8 flexi_flags2;
 	u8 ts_low;
-	__le16 l2tag2_1st;
+	__le16 raw_csum;
 	__le16 l2tag2_2nd;
 
 	/* Qword 3 */
@@ -371,29 +371,21 @@ enum ice_rx_flex_desc_status_error_1_bits {
 	ICE_RX_FLEX_DESC_STATUS1_LAST /* this entry must be last!!! */
 };
 
-#define ICE_RXQ_CTX_SIZE_DWORDS		8
-#define ICE_RXQ_CTX_SZ			(ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
 #define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS	22
 #define ICE_TX_DRBELL_Q_CTX_SIZE_DWORDS	5
 #define GLTCLAN_CQ_CNTX(i, CQ)		(GLTCLAN_CQ_CNTX0(CQ) + ((i) * 0x0800))
 
-/* RLAN Rx queue context data
- *
- * The sizes of the variables may be larger than needed due to crossing byte
- * boundaries. If we do not have the width of the variable set to the correct
- * size then we could end up shifting bits off the top of the variable when the
- * variable is at the top of a byte and crosses over into the next byte.
- */
+/* RLAN Rx queue context data */
 struct ice_rlan_ctx {
 	u16 head;
-	u16 cpuid; /* bigger than needed, see above for reason */
+	u8 cpuid;
 #define ICE_RLAN_BASE_S 7
 	u64 base;
 	u16 qlen;
 #define ICE_RLAN_CTX_DBUF_S 7
-	u16 dbuf; /* bigger than needed, see above for reason */
+	u8 dbuf;
 #define ICE_RLAN_CTX_HBUF_S 6
-	u16 hbuf; /* bigger than needed, see above for reason */
+	u8 hbuf;
 	u8 dtype;
 	u8 dsize;
 	u8 crcstrip;
@@ -401,29 +393,15 @@ struct ice_rlan_ctx {
 	u8 hsplit_0;
 	u8 hsplit_1;
 	u8 showiv;
-	u32 rxmax; /* bigger than needed, see above for reason */
+	u16 rxmax;
 	u8 tphrdesc_ena;
 	u8 tphwdesc_ena;
 	u8 tphdata_ena;
 	u8 tphhead_ena;
-	u16 lrxqthresh; /* bigger than needed, see above for reason */
+	u8 lrxqthresh;
 	u8 prefena;	/* NOTE: normally must be set to 1 at init */
 };
 
-struct ice_ctx_ele {
-	u16 offset;
-	u16 size_of;
-	u16 width;
-	u16 lsb;
-};
-
-#define ICE_CTX_STORE(_struct, _ele, _width, _lsb) {	\
-	.offset = offsetof(struct _struct, _ele),	\
-	.size_of = sizeof_field(struct _struct, _ele),	\
-	.width = _width,				\
-	.lsb = _lsb,					\
-}
-
 /* for hsplit_0 field of Rx RLAN context */
 enum ice_rlan_ctx_rx_hsplit_0 {
 	ICE_RLAN_RX_HSPLIT_0_NO_SPLIT		= 0,
@@ -500,10 +478,15 @@ enum ice_tx_desc_len_fields {
 struct ice_tx_ctx_desc {
 	__le32 tunneling_params;
 	__le16 l2tag2;
-	__le16 rsvd;
+	__le16 gcs;
 	__le64 qw1;
 };
 
+#define ICE_TX_GCS_DESC_START_M		GENMASK(7, 0)
+#define ICE_TX_GCS_DESC_OFFSET_M	GENMASK(11, 8)
+#define ICE_TX_GCS_DESC_TYPE_M		GENMASK(14, 12)
+#define ICE_TX_GCS_DESC_CSUM_PSH	1
+
 #define ICE_TXD_CTX_QW1_CMD_S	4
 #define ICE_TXD_CTX_QW1_CMD_M	(0x7FUL << ICE_TXD_CTX_QW1_CMD_S)
 
@@ -551,18 +534,12 @@ enum ice_tx_ctx_desc_eipt_offload {
 #define ICE_LAN_TXQ_MAX_QGRPS	127
 #define ICE_LAN_TXQ_MAX_QDIS	1023
 
-/* Tx queue context data
- *
- * The sizes of the variables may be larger than needed due to crossing byte
- * boundaries. If we do not have the width of the variable set to the correct
- * size then we could end up shifting bits off the top of the variable when the
- * variable is at the top of a byte and crosses over into the next byte.
- */
+/* Tx queue context data */
 struct ice_tlan_ctx {
 #define ICE_TLAN_CTX_BASE_S	7
 	u64 base;		/* base is defined in 128-byte units */
 	u8 port_num;
-	u16 cgd_num;		/* bigger than needed, see above for reason */
+	u8 cgd_num;
 	u8 pf_num;
 	u16 vmvf_num;
 	u8 vmvf_type;
@@ -573,7 +550,7 @@ struct ice_tlan_ctx {
 	u8 tsyn_ena;
 	u8 internal_usage_flag;
 	u8 alt_vlan;
-	u16 cpuid;		/* bigger than needed, see above for reason */
+	u8 cpuid;
 	u8 wb_mode;
 	u8 tphrd_desc;
 	u8 tphrd;
@@ -582,7 +559,7 @@ struct ice_tlan_ctx {
 	u16 qnum_in_func;
 	u8 itr_notification_mode;
 	u8 adjust_prof_id;
-	u32 qlen;		/* bigger than needed, see above for reason */
+	u16 qlen;
 	u8 quanta_prof_idx;
 	u8 tso_ena;
 	u16 tso_qnum;
@@ -590,7 +567,6 @@ struct ice_tlan_ctx {
 	u8 drop_ena;
 	u8 cache_prof_idx;
 	u8 pkt_shaper_prof_idx;
-	u8 int_q_state;	/* width not needed - internal - DO NOT WRITE!!! */
 };
 
 #endif /* _ICE_LAN_TX_RX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a7d45a8ce7ac..03bb16191237 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -157,6 +157,16 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
 	}
 }
 
+static u16 ice_get_rxq_count(struct ice_pf *pf)
+{
+	return min(ice_get_avail_rxq_count(pf), num_online_cpus());
+}
+
+static u16 ice_get_txq_count(struct ice_pf *pf)
+{
+	return min(ice_get_avail_txq_count(pf), num_online_cpus());
+}
+
 /**
  * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI
  * @vsi: the VSI being configured
@@ -178,9 +188,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 			vsi->alloc_txq = vsi->req_txq;
 			vsi->num_txq = vsi->req_txq;
 		} else {
-			vsi->alloc_txq = min3(pf->num_lan_msix,
-					      ice_get_avail_txq_count(pf),
-					      (u16)num_online_cpus());
+			vsi->alloc_txq = ice_get_txq_count(pf);
 		}
 
 		pf->num_lan_tx = vsi->alloc_txq;
@@ -193,17 +201,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 				vsi->alloc_rxq = vsi->req_rxq;
 				vsi->num_rxq = vsi->req_rxq;
 			} else {
-				vsi->alloc_rxq = min3(pf->num_lan_msix,
-						      ice_get_avail_rxq_count(pf),
-						      (u16)num_online_cpus());
+				vsi->alloc_rxq = ice_get_rxq_count(pf);
 			}
 		}
 
 		pf->num_lan_rx = vsi->alloc_rxq;
 
-		vsi->num_q_vectors = min_t(int, pf->num_lan_msix,
-					   max_t(int, vsi->alloc_rxq,
-						 vsi->alloc_txq));
+		vsi->num_q_vectors = max(vsi->alloc_rxq, vsi->alloc_txq);
 		break;
 	case ICE_VSI_SF:
 		vsi->alloc_txq = 1;
@@ -567,6 +571,8 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)
 			return -ENOMEM;
 	}
 
+	vsi->irq_dyn_alloc = pci_msix_can_alloc_dyn(vsi->back->pdev);
+
 	switch (vsi->type) {
 	case ICE_VSI_PF:
 	case ICE_VSI_SF:
@@ -827,7 +833,13 @@ bool ice_is_safe_mode(struct ice_pf *pf)
  */
 bool ice_is_rdma_ena(struct ice_pf *pf)
 {
-	return test_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+	union devlink_param_value value;
+	int err;
+
+	err = devl_param_driverinit_value_get(priv_to_devlink(pf),
+					      DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+					      &value);
+	return err ? test_bit(ICE_FLAG_RDMA_ENA, pf->flags) : value.vbool;
 }
 
 /**
@@ -1173,12 +1185,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 static void
 ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 {
-	struct ice_pf *pf = vsi->back;
 	u16 qcount, qmap;
 	u8 offset = 0;
 	int pow;
 
-	qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix);
+	qcount = vsi->num_rxq;
 
 	pow = order_base_2(qcount);
 	qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset);
@@ -1420,6 +1431,10 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->dev = dev;
 		ring->count = vsi->num_rx_desc;
 		ring->cached_phctime = pf->ptp.cached_phc_time;
+
+		if (ice_is_feature_supported(pf, ICE_F_GCS))
+			ring->flags |= ICE_RX_FLAGS_RING_GCS;
+
 		WRITE_ONCE(vsi->rx_rings[i], ring);
 	}
 
@@ -1700,6 +1715,12 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf)
 	return true;
 }
 
+#define ICE_FW_MODE_REC_M BIT(1)
+bool ice_is_recovery_mode(struct ice_hw *hw)
+{
+	return rd32(hw, GL_MNG_FWSM) & ICE_FW_MODE_REC_M;
+}
+
 /**
  * ice_update_eth_stats - Update VSI-specific ethernet statistics counters
  * @vsi: the VSI to be updated
@@ -1758,9 +1779,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi)
  * @prio: priority for the RXDID for this queue
  * @ena_ts: true to enable timestamp and false to disable timestamp
  */
-void
-ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
-			bool ena_ts)
+void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
+			     bool ena_ts)
 {
 	int regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
 
@@ -2045,12 +2065,15 @@ static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
 }
 
 /**
- * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling
+ * ice_vsi_cfg_sw_lldp - Config switch rules for LLDP packet handling
  * @vsi: the VSI being configured
  * @tx: bool to determine Tx or Rx rule
  * @create: bool to determine create or remove Rule
+ *
+ * Adding an ethtype Tx rule to the uplink VSI results in it being applied
+ * to the whole port, so LLDP transmission for VFs will be blocked too.
  */
-void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
+void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 {
 	int (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag,
 			enum ice_sw_fwd_act_type act);
@@ -2065,19 +2088,59 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 		status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_TX,
 				  ICE_DROP_PACKET);
 	} else {
-		if (ice_fw_supports_lldp_fltr_ctrl(&pf->hw)) {
-			status = ice_lldp_fltr_add_remove(&pf->hw, vsi->vsi_num,
-							  create);
-		} else {
+		if (!test_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags)) {
 			status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_RX,
 					  ICE_FWD_TO_VSI);
+			if (!status || !create)
+				goto report;
+
+			dev_info(dev,
+				 "Failed to add generic LLDP Rx filter on VSI %i error: %d, falling back to specialized AQ control\n",
+				 vsi->vsi_num, status);
 		}
+
+		status = ice_lldp_fltr_add_remove(&pf->hw, vsi, create);
+		if (!status)
+			set_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags);
+
 	}
 
+report:
 	if (status)
-		dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %d\n",
-			create ? "adding" : "removing", tx ? "TX" : "RX",
-			vsi->vsi_num, status);
+		dev_warn(dev, "Failed to %s %s LLDP rule on VSI %i error: %d\n",
+			 create ? "add" : "remove", tx ? "Tx" : "Rx",
+			 vsi->vsi_num, status);
+}
+
+/**
+ * ice_cfg_sw_rx_lldp - Enable/disable software handling of LLDP
+ * @pf: the PF being configured
+ * @enable: enable or disable
+ *
+ * Configure switch rules to enable/disable LLDP handling by software
+ * across PF.
+ */
+void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable)
+{
+	struct ice_vsi *vsi;
+	struct ice_vf *vf;
+	unsigned int bkt;
+
+	vsi = ice_get_main_vsi(pf);
+	ice_vsi_cfg_sw_lldp(vsi, false, enable);
+
+	if (!test_bit(ICE_FLAG_SRIOV_ENA, pf->flags))
+		return;
+
+	ice_for_each_vf(pf, bkt, vf) {
+		vsi = ice_get_vf_vsi(vf);
+
+		if (WARN_ON(!vsi))
+			continue;
+
+		if (ice_vf_is_lldp_ena(vf))
+			ice_vsi_cfg_sw_lldp(vsi, false, enable);
+	}
 }
 
 /**
@@ -2508,7 +2571,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params)
 	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) {
 		ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX,
 				 ICE_DROP_PACKET);
-		ice_cfg_sw_lldp(vsi, true, true);
+		ice_vsi_cfg_sw_lldp(vsi, true, true);
 	}
 
 	if (!vsi->agg_node)
@@ -2576,7 +2639,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		return;
 
 	vsi->irqs_ready = false;
-	ice_free_cpu_rx_rmap(vsi);
 
 	ice_for_each_q_vector(vsi, i) {
 		int irq_num;
@@ -2589,12 +2651,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		      vsi->q_vectors[i]->num_ring_rx))
 			continue;
 
-		/* clear the affinity notifier in the IRQ descriptor */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-
-		/* clear the affinity_hint in the IRQ descriptor */
-		irq_update_affinity_hint(irq_num, NULL);
 		synchronize_irq(irq_num);
 		devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]);
 	}
@@ -2749,11 +2805,18 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
 {
 	struct net_device *netdev = vsi->netdev;
-	int q_idx;
+	int q_idx, v_idx;
 
 	if (!netdev)
 		return;
 
+	/* Clear the NAPI's interrupt number */
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+
+		netif_napi_set_irq(&q_vector->napi, -1);
+	}
+
 	ice_for_each_txq(vsi, q_idx)
 		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL);
 
@@ -2805,9 +2868,11 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	/* The Rx rule will only exist to remove if the LLDP FW
 	 * engine is currently stopped
 	 */
-	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
-	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
-		ice_cfg_sw_lldp(vsi, false, false);
+	if (!ice_is_safe_mode(pf) &&
+	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags) &&
+	    (vsi->type == ICE_VSI_PF || (vsi->type == ICE_VSI_VF &&
+	     ice_vf_is_lldp_ena(vsi->vf))))
+		ice_vsi_cfg_sw_lldp(vsi, false, false);
 
 	ice_vsi_decfg(vsi);
 
@@ -3876,15 +3941,17 @@ void ice_init_feature_support(struct ice_pf *pf)
 			ice_set_feature_support(pf, ICE_F_CGU);
 		if (ice_is_clock_mux_in_netlist(&pf->hw))
 			ice_set_feature_support(pf, ICE_F_SMA_CTRL);
-		if (ice_gnss_is_gps_present(&pf->hw))
+		if (ice_gnss_is_module_present(&pf->hw))
 			ice_set_feature_support(pf, ICE_F_GNSS);
 		break;
 	default:
 		break;
 	}
 
-	if (pf->hw.mac_type == ICE_MAC_E830)
+	if (pf->hw.mac_type == ICE_MAC_E830) {
 		ice_set_feature_support(pf, ICE_F_MBX_LIMIT);
+		ice_set_feature_support(pf, ICE_F_GCS);
+	}
 }
 
 /**
@@ -3931,24 +3998,6 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx)
 }
 
 /**
- * ice_vsi_ctx_set_allow_override - allow destination override on VSI
- * @ctx: pointer to VSI ctx structure
- */
-void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx)
-{
-	ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
-}
-
-/**
- * ice_vsi_ctx_clear_allow_override - turn off destination override on VSI
- * @ctx: pointer to VSI ctx structure
- */
-void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx)
-{
-	ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
-}
-
-/**
  * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit
  * @vsi: pointer to VSI structure
  * @set: set or unset the bit
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 10d6fc479a32..654516c5fc3e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -29,7 +29,8 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 
 int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi);
 
-void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
+void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
+void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable);
 
 int ice_set_link(struct ice_vsi *vsi, bool ena);
 
@@ -90,6 +91,7 @@ void ice_set_q_vector_intrl(struct ice_q_vector *q_vector);
 
 bool ice_is_safe_mode(struct ice_pf *pf);
 bool ice_is_rdma_ena(struct ice_pf *pf);
+bool ice_is_recovery_mode(struct ice_hw *hw);
 bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi);
 bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi);
 int ice_set_dflt_vsi(struct ice_vsi *vsi);
@@ -104,10 +106,6 @@ ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *))
 void ice_vsi_ctx_set_antispoof(struct ice_vsi_ctx *ctx);
 
 void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx);
-
-void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx);
-
-void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx);
 int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set);
 int ice_vsi_add_vlan_zero(struct ice_vsi *vsi);
 int ice_vsi_del_vlan_zero(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 1eaa4428fd24..0a11b4281092 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -14,7 +14,7 @@
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
 #include "devlink/devlink.h"
-#include "devlink/devlink_port.h"
+#include "devlink/port.h"
 #include "ice_sf_eth.h"
 #include "ice_hwmon.h"
 /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the
@@ -37,7 +37,7 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";
 #define ICE_DDP_PKG_FILE	ICE_DDP_PKG_PATH "ice.pkg"
 
 MODULE_DESCRIPTION(DRV_SUMMARY);
-MODULE_IMPORT_NS(LIBIE);
+MODULE_IMPORT_NS("LIBIE");
 MODULE_LICENSE("GPL v2");
 MODULE_FIRMWARE(ICE_DDP_PKG_FILE);
 
@@ -1144,7 +1144,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	if (link_up == old_link && link_speed == old_link_speed)
 		return 0;
 
-	ice_ptp_link_change(pf, pf->hw.pf_id, link_up);
+	ice_ptp_link_change(pf, link_up);
 
 	if (ice_is_dcb_active(pf)) {
 		if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
@@ -1567,6 +1567,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		case ice_aqc_opc_lldp_set_mib_change:
 			ice_dcb_process_lldp_set_mib_change(pf, &event);
 			break;
+		case ice_aqc_opc_get_health_status:
+			ice_process_health_status_event(pf, &event);
+			break;
 		default:
 			dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n",
 				qtype, opcode);
@@ -1714,7 +1717,7 @@ static int ice_service_task_stop(struct ice_pf *pf)
 	ret = test_and_set_bit(ICE_SERVICE_DIS, pf->state);
 
 	if (pf->serv_tmr.function)
-		del_timer_sync(&pf->serv_tmr);
+		timer_delete_sync(&pf->serv_tmr);
 	if (pf->serv_task.func)
 		cancel_work_sync(&pf->serv_task);
 
@@ -1740,7 +1743,7 @@ static void ice_service_task_restart(struct ice_pf *pf)
  */
 static void ice_service_timer(struct timer_list *t)
 {
-	struct ice_pf *pf = from_timer(pf, t, serv_tmr);
+	struct ice_pf *pf = timer_container_of(pf, t, serv_tmr);
 
 	mod_timer(&pf->serv_tmr, round_jiffies(pf->serv_tmr_period + jiffies));
 	ice_service_task_schedule(pf);
@@ -1816,6 +1819,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_TX_PQM, pf_num, vf_num,
+				     event, queue);
 		wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
 	}
 
@@ -1829,6 +1834,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_TX_TCLAN, pf_num, vf_num,
+				     event, queue);
 		wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX);
 	}
 
@@ -1842,6 +1849,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_rx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_RX, pf_num, vf_num, event,
+				     queue);
 		wr32(hw, GL_MDET_RX, 0xffffffff);
 	}
 
@@ -2355,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf)
 	}
 }
 
+static void ice_service_task_recovery_mode(struct work_struct *work)
+{
+	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
+
+	set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state);
+	ice_clean_adminq_subtask(pf);
+
+	ice_service_task_complete(pf);
+
+	mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100));
+}
+
 /**
  * ice_service_task - manage and run subtasks
  * @work: pointer to work_struct contained by the PF struct
@@ -2364,9 +2385,11 @@ static void ice_service_task(struct work_struct *work)
 	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
 	unsigned long start_time = jiffies;
 
-	/* subtasks */
+	if (pf->health_reporters.tx_hang_buf.tx_ring) {
+		ice_report_tx_hang(pf);
+		pf->health_reporters.tx_hang_buf.tx_ring = NULL;
+	}
 
-	/* process reset requests first */
 	ice_reset_subtask(pf);
 
 	/* bail if a reset/recovery cycle is pending or rebuild failed */
@@ -2378,11 +2401,11 @@ static void ice_service_task(struct work_struct *work)
 	}
 
 	if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) {
-		struct iidc_event *event;
+		struct iidc_rdma_event *event;
 
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (event) {
-			set_bit(IIDC_EVENT_CRIT_ERR, event->type);
+			set_bit(IIDC_RDMA_EVENT_CRIT_ERR, event->type);
 			/* report the entire OICR value to AUX driver */
 			swap(event->reg, pf->oicr_err_reg);
 			ice_send_event_to_aux(pf, event);
@@ -2401,11 +2424,11 @@ static void ice_service_task(struct work_struct *work)
 		ice_plug_aux_dev(pf);
 
 	if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) {
-		struct iidc_event *event;
+		struct iidc_rdma_event *event;
 
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (event) {
-			set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type);
+			set_bit(IIDC_RDMA_EVENT_AFTER_MTU_CHANGE, event->type);
 			ice_send_event_to_aux(pf, event);
 			kfree(event);
 		}
@@ -2505,34 +2528,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
 }
 
 /**
- * ice_irq_affinity_notify - Callback for affinity changes
- * @notify: context as to what irq was changed
- * @mask: the new affinity mask
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * so that we may register to receive changes to the irq affinity masks.
- */
-static void
-ice_irq_affinity_notify(struct irq_affinity_notify *notify,
-			const cpumask_t *mask)
-{
-	struct ice_q_vector *q_vector =
-		container_of(notify, struct ice_q_vector, affinity_notify);
-
-	cpumask_copy(&q_vector->affinity_mask, mask);
-}
-
-/**
- * ice_irq_affinity_release - Callback for affinity notifier release
- * @ref: internal core kernel usage
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * to inform the current notification subscriber that they will no longer
- * receive notifications.
- */
-static void ice_irq_affinity_release(struct kref __always_unused *ref) {}
-
-/**
  * ice_vsi_ena_irq - Enable IRQ for the given VSI
  * @vsi: the VSI being configured
  */
@@ -2595,19 +2590,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 				   err);
 			goto free_q_irqs;
 		}
-
-		/* register for affinity change notifications */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL)) {
-			struct irq_affinity_notify *affinity_notify;
-
-			affinity_notify = &q_vector->affinity_notify;
-			affinity_notify->notify = ice_irq_affinity_notify;
-			affinity_notify->release = ice_irq_affinity_release;
-			irq_set_affinity_notifier(irq_num, affinity_notify);
-		}
-
-		/* assign the mask for this irq */
-		irq_update_affinity_hint(irq_num, &q_vector->affinity_mask);
 	}
 
 	err = ice_set_cpu_rx_rmap(vsi);
@@ -2623,9 +2605,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 free_q_irqs:
 	while (vector--) {
 		irq_num = vsi->q_vectors[vector]->irq.virq;
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-		irq_update_affinity_hint(irq_num, NULL);
 		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;
@@ -2762,6 +2741,27 @@ void ice_map_xdp_rings(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_unmap_xdp_rings - Unmap XDP rings from interrupt vectors
+ * @vsi: the VSI with XDP rings being unmapped
+ */
+static void ice_unmap_xdp_rings(struct ice_vsi *vsi)
+{
+	int v_idx;
+
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+		struct ice_tx_ring *ring;
+
+		ice_for_each_tx_ring(ring, q_vector->tx)
+			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
+				break;
+
+		/* restore the value of last node prior to XDP setup */
+		q_vector->tx.tx_ring = ring;
+	}
+}
+
+/**
  * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
  * @vsi: VSI to bring up Tx rings used by XDP
  * @prog: bpf program that will be assigned to VSI
@@ -2824,7 +2824,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 	if (status) {
 		dev_err(dev, "Failed VSI LAN queue config for XDP, error: %d\n",
 			status);
-		goto clear_xdp_rings;
+		goto unmap_xdp_rings;
 	}
 
 	/* assign the prog only when it's not already present on VSI;
@@ -2840,6 +2840,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 		ice_vsi_assign_bpf_prog(vsi, prog);
 
 	return 0;
+unmap_xdp_rings:
+	ice_unmap_xdp_rings(vsi);
 clear_xdp_rings:
 	ice_for_each_xdp_txq(vsi, i)
 		if (vsi->xdp_rings[i]) {
@@ -2856,6 +2858,8 @@ err_map_xdp:
 	mutex_unlock(&pf->avail_q_mutex);
 
 	devm_kfree(dev, vsi->xdp_rings);
+	vsi->xdp_rings = NULL;
+
 	return -ENOMEM;
 }
 
@@ -2871,7 +2875,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	struct ice_pf *pf = vsi->back;
-	int i, v_idx;
+	int i;
 
 	/* q_vectors are freed in reset path so there's no point in detaching
 	 * rings
@@ -2879,17 +2883,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 	if (cfg_type == ICE_XDP_CFG_PART)
 		goto free_qmap;
 
-	ice_for_each_q_vector(vsi, v_idx) {
-		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
-		struct ice_tx_ring *ring;
-
-		ice_for_each_tx_ring(ring, q_vector->tx)
-			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
-				break;
-
-		/* restore the value of last node prior to XDP setup */
-		q_vector->tx.tx_ring = ring;
-	}
+	ice_unmap_xdp_rings(vsi);
 
 free_qmap:
 	mutex_lock(&pf->avail_q_mutex);
@@ -3034,11 +3028,14 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		xdp_ring_err = ice_vsi_determine_xdp_res(vsi);
 		if (xdp_ring_err) {
 			NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP");
+			goto resume_if;
 		} else {
 			xdp_ring_err = ice_prepare_xdp_rings(vsi, prog,
 							     ICE_XDP_CFG_FULL);
-			if (xdp_ring_err)
+			if (xdp_ring_err) {
 				NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
+				goto resume_if;
+			}
 		}
 		xdp_features_set_redirect_target(vsi->netdev, true);
 		/* reallocate Rx queues that are used for zero-copy */
@@ -3056,6 +3053,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed");
 	}
 
+resume_if:
 	if (if_running)
 		ret = ice_up(vsi);
 
@@ -3281,22 +3279,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 	if (oicr & PFINT_OICR_TSYN_TX_M) {
 		ena_mask &= ~PFINT_OICR_TSYN_TX_M;
-		if (ice_pf_state_is_nominal(pf) &&
-		    pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) {
-			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
-			unsigned long flags;
-			u8 idx;
-
-			spin_lock_irqsave(&tx->lock, flags);
-			idx = find_next_bit_wrap(tx->in_use, tx->len,
-						 tx->last_ll_ts_idx_read + 1);
-			if (idx != tx->len)
-				ice_ptp_req_tx_single_tstamp(tx, idx);
-			spin_unlock_irqrestore(&tx->lock, flags);
-		} else if (ice_ptp_pf_handles_tx_interrupt(pf)) {
-			set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
-			ret = IRQ_WAKE_THREAD;
-		}
+
+		ret = ice_ptp_ts_irq(pf);
 	}
 
 	if (oicr & PFINT_OICR_TSYN_EVNT_M) {
@@ -3666,6 +3650,15 @@ void ice_set_netdev_features(struct net_device *netdev)
 	 */
 	netdev->hw_features |= NETIF_F_RXFCS;
 
+	/* Allow core to manage IRQs affinity */
+	netif_set_affinity_auto(netdev);
+
+	/* Mutual exclusivity for TSO and GCS is enforced by the set features
+	 * ndo callback.
+	 */
+	if (ice_is_feature_supported(pf, ICE_F_GCS))
+		netdev->hw_features |= NETIF_F_HW_CSUM;
+
 	netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE);
 }
 
@@ -4043,8 +4036,7 @@ static void ice_set_pf_caps(struct ice_pf *pf)
 	}
 
 	clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
-	if (func_caps->common_cap.ieee_1588 &&
-	    !(pf->hw.mac_type == ICE_MAC_E830))
+	if (func_caps->common_cap.ieee_1588)
 		set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
 
 	pf->max_pf_txqs = func_caps->common_cap.num_txq;
@@ -4741,55 +4733,12 @@ static void ice_decfg_netdev(struct ice_vsi *vsi)
 	vsi->netdev = NULL;
 }
 
-/**
- * ice_wait_for_fw - wait for full FW readiness
- * @hw: pointer to the hardware structure
- * @timeout: milliseconds that can elapse before timing out
- */
-static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
-{
-	int fw_loading;
-	u32 elapsed = 0;
-
-	while (elapsed <= timeout) {
-		fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
-
-		/* firmware was not yet loaded, we have to wait more */
-		if (fw_loading) {
-			elapsed += 100;
-			msleep(100);
-			continue;
-		}
-		return 0;
-	}
-
-	return -ETIMEDOUT;
-}
-
 int ice_init_dev(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	int err;
 
-	err = ice_init_hw(hw);
-	if (err) {
-		dev_err(dev, "ice_init_hw failed: %d\n", err);
-		return err;
-	}
-
-	/* Some cards require longer initialization times
-	 * due to necessity of loading FW from an external source.
-	 * This can take even half a minute.
-	 */
-	if (ice_is_pf_c827(hw)) {
-		err = ice_wait_for_fw(hw, 30000);
-		if (err) {
-			dev_err(dev, "ice_wait_for_fw timed out");
-			return err;
-		}
-	}
-
 	ice_init_feature_support(pf);
 
 	err = ice_init_ddp_config(hw, pf);
@@ -4810,7 +4759,7 @@ int ice_init_dev(struct ice_pf *pf)
 	err = ice_init_pf(pf);
 	if (err) {
 		dev_err(dev, "ice_init_pf failed: %d\n", err);
-		goto err_init_pf;
+		return err;
 	}
 
 	pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port;
@@ -4834,7 +4783,7 @@ int ice_init_dev(struct ice_pf *pf)
 	if (err) {
 		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
 		err = -EIO;
-		goto err_init_interrupt_scheme;
+		goto unroll_pf_init;
 	}
 
 	/* In case of MSIX we are going to setup the misc vector right here
@@ -4845,17 +4794,15 @@ int ice_init_dev(struct ice_pf *pf)
 	err = ice_req_irq_msix_misc(pf);
 	if (err) {
 		dev_err(dev, "setup of misc vector failed: %d\n", err);
-		goto err_req_irq_msix_misc;
+		goto unroll_irq_scheme_init;
 	}
 
 	return 0;
 
-err_req_irq_msix_misc:
+unroll_irq_scheme_init:
 	ice_clear_interrupt_scheme(pf);
-err_init_interrupt_scheme:
+unroll_pf_init:
 	ice_deinit_pf(pf);
-err_init_pf:
-	ice_deinit_hw(hw);
 	return err;
 }
 
@@ -5088,12 +5035,14 @@ static int ice_init_devlink(struct ice_pf *pf)
 
 	ice_devlink_init_regions(pf);
 	ice_devlink_register(pf);
+	ice_health_init(pf);
 
 	return 0;
 }
 
 static void ice_deinit_devlink(struct ice_pf *pf)
 {
+	ice_health_deinit(pf);
 	ice_devlink_unregister(pf);
 	ice_devlink_destroy_regions(pf);
 	ice_devlink_unregister_params(pf);
@@ -5107,6 +5056,12 @@ static int ice_init(struct ice_pf *pf)
 	if (err)
 		return err;
 
+	if (pf->hw.mac_type == ICE_MAC_E830) {
+		err = pci_enable_ptm(pf->pdev, NULL);
+		if (err)
+			dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n");
+	}
+
 	err = ice_alloc_vsis(pf);
 	if (err)
 		goto err_alloc_vsis;
@@ -5206,11 +5161,12 @@ int ice_load(struct ice_pf *pf)
 
 	ice_napi_add(vsi);
 
+	ice_init_features(pf);
+
 	err = ice_init_rdma(pf);
 	if (err)
 		goto err_init_rdma;
 
-	ice_init_features(pf);
 	ice_service_task_restart(pf);
 
 	clear_bit(ICE_DOWN, pf->state);
@@ -5218,6 +5174,7 @@ int ice_load(struct ice_pf *pf)
 	return 0;
 
 err_init_rdma:
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 err_tc_indir_block_register:
 	ice_unregister_netdev(vsi);
@@ -5241,14 +5198,44 @@ void ice_unload(struct ice_pf *pf)
 
 	devl_assert_locked(priv_to_devlink(pf));
 
-	ice_deinit_features(pf);
 	ice_deinit_rdma(pf);
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 	ice_unregister_netdev(vsi);
 	ice_devlink_destroy_pf_port(pf);
 	ice_decfg_netdev(vsi);
 }
 
+static int ice_probe_recovery_mode(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	int err;
+
+	dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n");
+
+	INIT_HLIST_HEAD(&pf->aq_wait_list);
+	spin_lock_init(&pf->aq_wait_lock);
+	init_waitqueue_head(&pf->aq_wait_queue);
+
+	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
+	pf->serv_tmr_period = HZ;
+	INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode);
+	clear_bit(ICE_SERVICE_SCHED, pf->state);
+	err = ice_create_all_ctrlq(&pf->hw);
+	if (err)
+		return err;
+
+	scoped_guard(devl, priv_to_devlink(pf)) {
+		err = ice_init_devlink(pf);
+		if (err)
+			return err;
+	}
+
+	ice_service_task_restart(pf);
+
+	return 0;
+}
+
 /**
  * ice_probe - Device initialization routine
  * @pdev: PCI device information struct
@@ -5312,13 +5299,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	}
 
 	pci_set_master(pdev);
-
-	adapter = ice_adapter_get(pdev);
-	if (IS_ERR(adapter))
-		return PTR_ERR(adapter);
-
 	pf->pdev = pdev;
-	pf->adapter = adapter;
 	pci_set_drvdata(pdev, pf);
 	set_bit(ICE_DOWN, pf->state);
 	/* Disable service task until DOWN bit is cleared */
@@ -5346,29 +5327,47 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		hw->debug_mask = debug;
 #endif
 
+	if (ice_is_recovery_mode(hw))
+		return ice_probe_recovery_mode(pf);
+
+	err = ice_init_hw(hw);
+	if (err) {
+		dev_err(dev, "ice_init_hw failed: %d\n", err);
+		return err;
+	}
+
+	adapter = ice_adapter_get(pdev);
+	if (IS_ERR(adapter)) {
+		err = PTR_ERR(adapter);
+		goto unroll_hw_init;
+	}
+	pf->adapter = adapter;
+
 	err = ice_init(pf);
 	if (err)
-		goto err_init;
+		goto unroll_adapter;
 
 	devl_lock(priv_to_devlink(pf));
 	err = ice_load(pf);
 	if (err)
-		goto err_load;
+		goto unroll_init;
 
 	err = ice_init_devlink(pf);
 	if (err)
-		goto err_init_devlink;
+		goto unroll_load;
 	devl_unlock(priv_to_devlink(pf));
 
 	return 0;
 
-err_init_devlink:
+unroll_load:
 	ice_unload(pf);
-err_load:
+unroll_init:
 	devl_unlock(priv_to_devlink(pf));
 	ice_deinit(pf);
-err_init:
+unroll_adapter:
 	ice_adapter_put(pdev);
+unroll_hw_init:
+	ice_deinit_hw(hw);
 	return err;
 }
 
@@ -5448,6 +5447,14 @@ static void ice_remove(struct pci_dev *pdev)
 		msleep(100);
 	}
 
+	if (ice_is_recovery_mode(&pf->hw)) {
+		ice_service_task_stop(pf);
+		scoped_guard(devl, priv_to_devlink(pf)) {
+			ice_deinit_devlink(pf);
+		}
+		return;
+	}
+
 	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
 		set_bit(ICE_VF_RESETS_DISABLED, pf->state);
 		ice_free_vfs(pf);
@@ -6408,10 +6415,12 @@ ice_set_vlan_filtering_features(struct ice_vsi *vsi, netdev_features_t features)
 	int err = 0;
 
 	/* support Single VLAN Mode (SVM) and Double VLAN Mode (DVM) by checking
-	 * if either bit is set
+	 * if either bit is set. In switchdev mode Rx filtering should never be
+	 * enabled.
 	 */
-	if (features &
-	    (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER))
+	if ((features &
+	     (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)) &&
+	     !ice_is_eswitch_mode_switchdev(vsi->back))
 		err = vlan_ops->ena_rx_filtering(vsi);
 	else
 		err = vlan_ops->dis_rx_filtering(vsi);
@@ -6565,6 +6574,18 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 	if (changed & NETIF_F_LOOPBACK)
 		ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK));
 
+	/* Due to E830 hardware limitations, TSO (NETIF_F_ALL_TSO) with GCS
+	 * (NETIF_F_HW_CSUM) is not supported.
+	 */
+	if (ice_is_feature_supported(pf, ICE_F_GCS) &&
+	    ((features & NETIF_F_HW_CSUM) && (features & NETIF_F_ALL_TSO))) {
+		if (netdev->features & NETIF_F_HW_CSUM)
+			dev_err(ice_pf_to_dev(pf), "To enable TSO, you must first disable HW checksum.\n");
+		else
+			dev_err(ice_pf_to_dev(pf), "To enable HW checksum, you must first disable TSO.\n");
+		return -EIO;
+	}
+
 	return ret;
 }
 
@@ -6788,7 +6809,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 		ice_print_link_msg(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
-		ice_ptp_link_change(pf, pf->hw.pf_id, true);
+		ice_ptp_link_change(pf, true);
 	}
 
 	/* Perform an initial read of the statistics registers now to
@@ -7258,7 +7279,7 @@ int ice_down(struct ice_vsi *vsi)
 
 	if (vsi->netdev) {
 		vlan_err = ice_vsi_del_vlan_zero(vsi);
-		ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false);
+		ice_ptp_link_change(vsi->back, false);
 		netif_carrier_off(vsi->netdev);
 		netif_tx_disable(vsi->netdev);
 	}
@@ -7791,6 +7812,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	/* if we get here, reset flow is successful */
 	clear_bit(ICE_RESET_FAILED, pf->state);
 
+	ice_health_clear(pf);
+
 	ice_plug_aux_dev(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
@@ -8281,16 +8304,18 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 
 	if (tx_ring) {
 		struct ice_hw *hw = &pf->hw;
-		u32 head, val = 0;
+		u32 head, intr = 0;
 
 		head = FIELD_GET(QTX_COMM_HEAD_HEAD_M,
 				 rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])));
 		/* Read interrupt register */
-		val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
+		intr = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
 
 		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %u, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, txqueue, tx_ring->next_to_clean,
-			    head, tx_ring->next_to_use, val);
+			    head, tx_ring->next_to_use, intr);
+
+		ice_prep_tx_hang_report(pf, tx_ring, vsi->vsi_num, head, intr);
 	}
 
 	pf->tx_timeout_last_recovery = jiffies;
@@ -8324,11 +8349,16 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
  * @np: net device to configure
  * @filter_dev: device on which filter is added
  * @cls_flower: offload data
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was successfully added or deleted,
+ *	   negative error code otherwise.
  */
 static int
 ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 			struct net_device *filter_dev,
-			struct flow_cls_offload *cls_flower)
+			struct flow_cls_offload *cls_flower,
+			bool ingress)
 {
 	struct ice_vsi *vsi = np->vsi;
 
@@ -8337,7 +8367,7 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 
 	switch (cls_flower->command) {
 	case FLOW_CLS_REPLACE:
-		return ice_add_cls_flower(filter_dev, vsi, cls_flower);
+		return ice_add_cls_flower(filter_dev, vsi, cls_flower, ingress);
 	case FLOW_CLS_DESTROY:
 		return ice_del_cls_flower(vsi, cls_flower);
 	default:
@@ -8346,20 +8376,46 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 }
 
 /**
- * ice_setup_tc_block_cb - callback handler registered for TC block
+ * ice_setup_tc_block_cb_ingress - callback handler for ingress TC block
  * @type: TC SETUP type
  * @type_data: TC flower offload data that contains user input
  * @cb_priv: netdev private data
+ *
+ * Return: 0 if the setup was successful, negative error code otherwise.
  */
 static int
-ice_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+ice_setup_tc_block_cb_ingress(enum tc_setup_type type, void *type_data,
+			      void *cb_priv)
 {
 	struct ice_netdev_priv *np = cb_priv;
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return ice_setup_tc_cls_flower(np, np->vsi->netdev,
-					       type_data);
+					       type_data, true);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
+ * ice_setup_tc_block_cb_egress - callback handler for egress TC block
+ * @type: TC SETUP type
+ * @type_data: TC flower offload data that contains user input
+ * @cb_priv: netdev private data
+ *
+ * Return: 0 if the setup was successful, negative error code otherwise.
+ */
+static int
+ice_setup_tc_block_cb_egress(enum tc_setup_type type, void *type_data,
+			     void *cb_priv)
+{
+	struct ice_netdev_priv *np = cb_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return ice_setup_tc_cls_flower(np, np->vsi->netdev,
+					       type_data, false);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -9304,27 +9360,45 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 	     void *type_data)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	enum flow_block_binder_type binder_type;
+	struct iidc_rdma_core_dev_info *cdev;
 	struct ice_pf *pf = np->vsi->back;
+	flow_setup_cb_t *flower_handler;
 	bool locked = false;
 	int err;
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
+		binder_type =
+			((struct flow_block_offload *)type_data)->binder_type;
+
+		switch (binder_type) {
+		case FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS:
+			flower_handler = ice_setup_tc_block_cb_ingress;
+			break;
+		case FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS:
+			flower_handler = ice_setup_tc_block_cb_egress;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
 		return flow_block_cb_setup_simple(type_data,
 						  &ice_block_cb_list,
-						  ice_setup_tc_block_cb,
-						  np, np, true);
+						  flower_handler,
+						  np, np, false);
 	case TC_SETUP_QDISC_MQPRIO:
 		if (ice_is_eswitch_mode_switchdev(pf)) {
 			netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n");
 			return -EOPNOTSUPP;
 		}
 
-		if (pf->adev) {
+		cdev = pf->cdev_info;
+		if (cdev && cdev->adev) {
 			mutex_lock(&pf->adev_mutex);
-			device_lock(&pf->adev->dev);
+			device_lock(&cdev->adev->dev);
 			locked = true;
-			if (pf->adev->dev.driver) {
+			if (cdev->adev->dev.driver) {
 				netdev_err(netdev, "Cannot change qdisc when RDMA is active\n");
 				err = -EBUSY;
 				goto adev_unlock;
@@ -9338,7 +9412,7 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 
 adev_unlock:
 		if (locked) {
-			device_unlock(&pf->adev->dev);
+			device_unlock(&cdev->adev->dev);
 			mutex_unlock(&pf->adev_mutex);
 		}
 		return err;
@@ -9374,7 +9448,7 @@ ice_indr_setup_block_cb(enum tc_setup_type type, void *type_data,
 	case TC_SETUP_CLSFLOWER:
 		return ice_setup_tc_cls_flower(np, priv->netdev,
 					       (struct flow_cls_offload *)
-					       type_data);
+					       type_data, false);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index 6509d807627c..4f56d53d56b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -257,7 +257,6 @@ ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size,
 /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
 #define ICE_BST_TCAM_TABLE_SIZE		256
 #define ICE_BST_TCAM_KEY_SIZE		20
-#define ICE_BST_KEY_TCAM_SIZE		19
 
 /* Boost TCAM item */
 struct ice_bst_tcam_item {
@@ -401,7 +400,6 @@ u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag);
 #define ICE_PARSER_GPR_NUM	128
 #define ICE_PARSER_FLG_NUM	64
 #define ICE_PARSER_ERR_NUM	16
-#define ICE_BST_KEY_SIZE	10
 #define ICE_MARKER_ID_SIZE	9
 #define ICE_MARKER_MAX_SIZE	\
 		(ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1)
@@ -431,13 +429,13 @@ struct ice_parser_rt {
 	u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV];
 	u16 pkt_len;
 	u16 po;
-	u8 bst_key[ICE_BST_KEY_SIZE];
+	u8 bst_key[ICE_BST_TCAM_KEY_SIZE];
 	struct ice_pg_cam_key pg_key;
+	u8 pg_prio;
 	struct ice_alu *alu0;
 	struct ice_alu *alu1;
 	struct ice_alu *alu2;
 	struct ice_pg_cam_action *action;
-	u8 pg_prio;
 	struct ice_gpr_pu pu;
 	u8 markers[ICE_MARKER_ID_SIZE];
 	bool protocols[ICE_PO_PAIR_SIZE];
diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
index dedf5e854e4b..3995d662e050 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
@@ -125,22 +125,20 @@ static void ice_bst_key_init(struct ice_parser_rt *rt,
 	else
 		key[idd] = imem->b_kb.prio;
 
-	idd = ICE_BST_KEY_TCAM_SIZE - 1;
+	idd = ICE_BST_TCAM_KEY_SIZE - 2;
 	for (i = idd; i >= 0; i--) {
 		int j;
 
 		j = ho + idd - i;
 		if (j < ICE_PARSER_MAX_PKT_LEN)
-			key[i] = rt->pkt_buf[ho + idd - i];
+			key[i] = rt->pkt_buf[j];
 		else
 			key[i] = 0;
 	}
 
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n");
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n",
-		  key[0], key[1], key[2], key[3], key[4],
-		  key[5], key[6], key[7], key[8], key[9]);
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n");
+	ice_debug_array_w_prefix(rt->psr->hw, ICE_DBG_PARSER,
+				 KBUILD_MODNAME ": Generated Boost TCAM Key",
+				 key, ICE_BST_TCAM_KEY_SIZE);
 }
 
 static u16 ice_bit_rev_u16(u16 v, int len)
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index a999fface272..55cad824c5b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -16,28 +16,28 @@ static const char ice_pin_names[][64] = {
 };
 
 static const struct ice_ptp_pin_desc ice_pin_desc_e82x[] = {
-	/* name,        gpio */
-	{  TIME_SYNC, {  4, -1 }},
-	{  ONE_PPS,   { -1,  5 }},
+	/* name,        gpio,       delay */
+	{  TIME_SYNC, {  4, -1 }, { 0,  0 }},
+	{  ONE_PPS,   { -1,  5 }, { 0, 11 }},
 };
 
 static const struct ice_ptp_pin_desc ice_pin_desc_e825c[] = {
-	/* name,        gpio */
-	{  SDP0,      {  0,  0 }},
-	{  SDP1,      {  1,  1 }},
-	{  SDP2,      {  2,  2 }},
-	{  SDP3,      {  3,  3 }},
-	{  TIME_SYNC, {  4, -1 }},
-	{  ONE_PPS,   { -1,  5 }},
+	/* name,        gpio,       delay */
+	{  SDP0,      {  0,  0 }, { 15, 14 }},
+	{  SDP1,      {  1,  1 }, { 15, 14 }},
+	{  SDP2,      {  2,  2 }, { 15, 14 }},
+	{  SDP3,      {  3,  3 }, { 15, 14 }},
+	{  TIME_SYNC, {  4, -1 }, { 11,  0 }},
+	{  ONE_PPS,   { -1,  5 }, {  0,  9 }},
 };
 
 static const struct ice_ptp_pin_desc ice_pin_desc_e810[] = {
-	/* name,      gpio */
-	{  SDP0,    {  0, 0 }},
-	{  SDP1,    {  1, 1 }},
-	{  SDP2,    {  2, 2 }},
-	{  SDP3,    {  3, 3 }},
-	{  ONE_PPS, { -1, 5 }},
+	/* name,        gpio,       delay */
+	{  SDP0,      {  0,  0 }, { 0, 1 }},
+	{  SDP1,      {  1,  1 }, { 0, 1 }},
+	{  SDP2,      {  2,  2 }, { 0, 1 }},
+	{  SDP3,      {  3,  3 }, { 0, 1 }},
+	{  ONE_PPS,   { -1,  5 }, { 0, 1 }},
 };
 
 static const char ice_pin_names_nvm[][64] = {
@@ -49,12 +49,12 @@ static const char ice_pin_names_nvm[][64] = {
 };
 
 static const struct ice_ptp_pin_desc ice_pin_desc_e810_sma[] = {
-	/* name,   gpio */
-	{  GNSS, {  1, -1 }},
-	{  SMA1, {  1,  0 }},
-	{  UFL1, { -1,  0 }},
-	{  SMA2, {  3,  2 }},
-	{  UFL2, {  3, -1 }},
+	/* name,   gpio,       delay */
+	{  GNSS, {  1, -1 }, { 0, 0 }},
+	{  SMA1, {  1,  0 }, { 0, 1 }},
+	{  UFL1, { -1,  0 }, { 0, 1 }},
+	{  SMA2, {  3,  2 }, { 0, 1 }},
+	{  UFL2, {  3, -1 }, { 0, 0 }},
 };
 
 static struct ice_pf *ice_get_ctrl_pf(struct ice_pf *pf)
@@ -298,18 +298,30 @@ void ice_ptp_restore_timestamp_mode(struct ice_pf *pf)
  * @sts: Optional parameter for holding a pair of system timestamps from
  *       the system clock. Will be ignored if NULL is given.
  */
-static u64
-ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts)
+u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+			     struct ptp_system_timestamp *sts)
 {
 	struct ice_hw *hw = &pf->hw;
 	u32 hi, lo, lo2;
 	u8 tmr_idx;
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	tmr_idx = ice_get_ptp_src_clock_index(hw);
 	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	/* Read the system timestamp pre PHC read */
 	ptp_read_system_prets(sts);
 
+	if (hw->mac_type == ICE_MAC_E830) {
+		u64 clk_time = rd64(hw, E830_GLTSYN_TIME_L(tmr_idx));
+
+		/* Read the system timestamp post PHC read */
+		ptp_read_system_postts(sts);
+
+		return clk_time;
+	}
+
 	lo = rd32(hw, GLTSYN_TIME_L(tmr_idx));
 
 	/* Read the system timestamp post PHC read */
@@ -464,7 +476,9 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx)
  */
 void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx)
 {
+	struct ice_e810_params *params;
 	struct ice_ptp_port *ptp_port;
+	unsigned long flags;
 	struct sk_buff *skb;
 	struct ice_pf *pf;
 
@@ -473,6 +487,7 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx)
 
 	ptp_port = container_of(tx, struct ice_ptp_port, tx);
 	pf = ptp_port_to_pf(ptp_port);
+	params = &pf->hw.ptp.phy.e810;
 
 	/* Drop packets which have waited for more than 2 seconds */
 	if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) {
@@ -489,11 +504,17 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx)
 
 	ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx);
 
+	spin_lock_irqsave(&params->atqbal_wq.lock, flags);
+
+	params->atqbal_flags |= ATQBAL_FLAGS_INTR_IN_PROGRESS;
+
 	/* Write TS index to read to the PF register so the FW can read it */
-	wr32(&pf->hw, PF_SB_ATQBAL,
-	     TS_LL_READ_TS_INTR | FIELD_PREP(TS_LL_READ_TS_IDX, idx) |
-	     TS_LL_READ_TS);
+	wr32(&pf->hw, REG_LL_PROXY_H,
+	     REG_LL_PROXY_H_TS_INTR_ENA | FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) |
+	     REG_LL_PROXY_H_EXEC);
 	tx->last_ll_ts_idx_read = idx;
+
+	spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
 }
 
 /**
@@ -504,35 +525,52 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx)
 {
 	struct skb_shared_hwtstamps shhwtstamps = {};
 	u8 idx = tx->last_ll_ts_idx_read;
+	struct ice_e810_params *params;
 	struct ice_ptp_port *ptp_port;
 	u64 raw_tstamp, tstamp;
 	bool drop_ts = false;
 	struct sk_buff *skb;
+	unsigned long flags;
+	struct device *dev;
 	struct ice_pf *pf;
-	u32 val;
+	u32 reg_ll_high;
 
 	if (!tx->init || tx->last_ll_ts_idx_read < 0)
 		return;
 
 	ptp_port = container_of(tx, struct ice_ptp_port, tx);
 	pf = ptp_port_to_pf(ptp_port);
+	dev = ice_pf_to_dev(pf);
+	params = &pf->hw.ptp.phy.e810;
 
 	ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx);
 
-	val = rd32(&pf->hw, PF_SB_ATQBAL);
+	spin_lock_irqsave(&params->atqbal_wq.lock, flags);
+
+	if (!(params->atqbal_flags & ATQBAL_FLAGS_INTR_IN_PROGRESS))
+		dev_dbg(dev, "%s: low latency interrupt request not in progress?\n",
+			__func__);
+
+	/* Read the low 32 bit value */
+	raw_tstamp = rd32(&pf->hw, REG_LL_PROXY_L);
+	/* Read the status together with high TS part */
+	reg_ll_high = rd32(&pf->hw, REG_LL_PROXY_H);
+
+	/* Wake up threads waiting on low latency interface */
+	params->atqbal_flags &= ~ATQBAL_FLAGS_INTR_IN_PROGRESS;
+
+	wake_up_locked(&params->atqbal_wq);
+
+	spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
 
 	/* When the bit is cleared, the TS is ready in the register */
-	if (val & TS_LL_READ_TS) {
+	if (reg_ll_high & REG_LL_PROXY_H_EXEC) {
 		dev_err(ice_pf_to_dev(pf), "Failed to get the Tx tstamp - FW not ready");
 		return;
 	}
 
 	/* High 8 bit value of the TS is on the bits 16:23 */
-	raw_tstamp = FIELD_GET(TS_LL_READ_TS_HIGH, val);
-	raw_tstamp <<= 32;
-
-	/* Read the low 32 bit value */
-	raw_tstamp |= (u64)rd32(&pf->hw, PF_SB_ATQBAH);
+	raw_tstamp |= ((u64)FIELD_GET(REG_LL_PROXY_H_TS_HIGH, reg_ll_high)) << 32;
 
 	/* Devices using this interface always verify the timestamp differs
 	 * relative to the last cached timestamp value.
@@ -946,28 +984,6 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 }
 
 /**
- * ice_ptp_init_tx_eth56g - Initialize tracking for Tx timestamps
- * @pf: Board private structure
- * @tx: the Tx tracking structure to initialize
- * @port: the port this structure tracks
- *
- * Initialize the Tx timestamp tracker for this port. ETH56G PHYs
- * have independent memory blocks for all ports.
- *
- * Return: 0 for success, -ENOMEM when failed to allocate Tx tracker
- */
-static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx,
-				  u8 port)
-{
-	tx->block = port;
-	tx->offset = 0;
-	tx->len = INDEX_PER_PORT_ETH56G;
-	tx->has_ready_bitmap = 1;
-
-	return ice_ptp_alloc_tx_tracker(tx);
-}
-
-/**
  * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps
  * @pf: Board private structure
  * @tx: the Tx tracking structure to initialize
@@ -977,9 +993,11 @@ static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx,
  * the timestamp block is shared for all ports in the same quad. To avoid
  * ports using the same timestamp index, logically break the block of
  * registers into chunks based on the port number.
+ *
+ * Return: 0 on success, -ENOMEM when out of memory
  */
-static int
-ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
+static int ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx,
+				u8 port)
 {
 	tx->block = ICE_GET_QUAD_NUM(port);
 	tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X;
@@ -990,24 +1008,27 @@ ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 }
 
 /**
- * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps
+ * ice_ptp_init_tx - Initialize tracking for Tx timestamps
  * @pf: Board private structure
  * @tx: the Tx tracking structure to initialize
+ * @port: the port this structure tracks
+ *
+ * Initialize the Tx timestamp tracker for this PF. For all PHYs except E82X,
+ * each port has its own block of timestamps, independent of the other ports.
  *
- * Initialize the Tx timestamp tracker for this PF. For E810 devices, each
- * port has its own block of timestamps, independent of the other ports.
+ * Return: 0 on success, -ENOMEM when out of memory
  */
-static int
-ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx)
+static int ice_ptp_init_tx(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 {
-	tx->block = pf->hw.port_info->lport;
+	tx->block = port;
 	tx->offset = 0;
-	tx->len = INDEX_PER_PORT_E810;
+	tx->len = INDEX_PER_PORT;
+
 	/* The E810 PHY does not provide a timestamp ready bitmap. Instead,
 	 * verify new timestamps against cached copy of the last read
 	 * timestamp.
 	 */
-	tx->has_ready_bitmap = 0;
+	tx->has_ready_bitmap = pf->hw.mac_type != ICE_MAC_E810;
 
 	return ice_ptp_alloc_tx_tracker(tx);
 }
@@ -1292,20 +1313,21 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port)
 	struct ice_hw *hw = &pf->hw;
 	int err;
 
-	if (ice_is_e810(hw))
-		return 0;
-
 	mutex_lock(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_stop_phy_timer_eth56g(hw, port, true);
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+		err = 0;
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
 		err = ice_stop_phy_timer_e82x(hw, port, true);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_stop_phy_timer_eth56g(hw, port, true);
+		break;
 	default:
 		err = -ENODEV;
 	}
@@ -1335,19 +1357,17 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 	unsigned long flags;
 	int err;
 
-	if (ice_is_e810(hw))
-		return 0;
-
 	if (!ptp_port->link_up)
 		return ice_ptp_port_phy_stop(ptp_port);
 
 	mutex_lock(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_start_phy_timer_eth56g(hw, port);
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+		err = 0;
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		/* Start the PHY timer in Vernier mode */
 		kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
@@ -1372,6 +1392,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 		kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work,
 					   0);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_start_phy_timer_eth56g(hw, port);
+		break;
 	default:
 		err = -ENODEV;
 	}
@@ -1388,10 +1411,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 /**
  * ice_ptp_link_change - Reconfigure PTP after link status change
  * @pf: Board private structure
- * @port: Port for which the PHY start is set
  * @linkup: Link is up or down
  */
-void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
+void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 {
 	struct ice_ptp_port *ptp_port;
 	struct ice_hw *hw = &pf->hw;
@@ -1399,14 +1421,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	if (pf->ptp.state != ICE_PTP_READY)
 		return;
 
-	if (WARN_ON_ONCE(port >= hw->ptp.num_lports))
-		return;
-
 	ptp_port = &pf->ptp.port;
-	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
-		port *= 2;
-	if (WARN_ON_ONCE(ptp_port->port_num != port))
-		return;
 
 	/* Update cached link status for this port immediately */
 	ptp_port->link_up = linkup;
@@ -1414,12 +1429,14 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	/* Skip HW writes if reset is in progress */
 	if (pf->hw.reset_ongoing)
 		return;
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
-		/* Do not reconfigure E810 PHY */
+
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+		/* Do not reconfigure E810 or E830 PHY */
 		return;
-	case ICE_PHY_ETH56G:
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
 		ice_ptp_port_phy_restart(ptp_port);
 		return;
 	default:
@@ -1447,46 +1464,45 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold)
 
 	ice_ptp_reset_ts_memory(hw);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G: {
-		int port;
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+		return 0;
+	case ICE_MAC_GENERIC: {
+		int quad;
 
-		for (port = 0; port < hw->ptp.num_lports; port++) {
+		for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports);
+		     quad++) {
 			int err;
 
-			err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold);
+			err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold);
 			if (err) {
-				dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n",
-					port, err);
+				dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n",
+					quad, err);
 				return err;
 			}
 		}
 
 		return 0;
 	}
-	case ICE_PHY_E82X: {
-		int quad;
+	case ICE_MAC_GENERIC_3K_E825: {
+		int port;
 
-		for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports);
-		     quad++) {
+		for (port = 0; port < hw->ptp.num_lports; port++) {
 			int err;
 
-			err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold);
+			err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold);
 			if (err) {
-				dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n",
-					quad, err);
+				dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n",
+					port, err);
 				return err;
 			}
 		}
 
 		return 0;
 	}
-	case ICE_PHY_E810:
-		return 0;
-	case ICE_PHY_UNSUP:
+	case ICE_MAC_UNKNOWN:
 	default:
-		dev_warn(dev, "%s: Unexpected PHY model %d\n", __func__,
-			 ice_get_phy_model(hw));
 		return -EOPNOTSUPP;
 	}
 }
@@ -1566,18 +1582,29 @@ void ice_ptp_extts_event(struct ice_pf *pf)
 	 * Event is defined in GLTSYN_EVNT_0 register
 	 */
 	for (chan = 0; chan < GLTSYN_EVNT_H_IDX_MAX; chan++) {
+		int pin_desc_idx;
+
 		/* Check if channel is enabled */
-		if (pf->ptp.ext_ts_irq & (1 << chan)) {
-			lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx));
-			hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx));
-			event.timestamp = (((u64)hi) << 32) | lo;
-			event.type = PTP_CLOCK_EXTTS;
-			event.index = chan;
-
-			/* Fire event */
-			ptp_clock_event(pf->ptp.clock, &event);
-			pf->ptp.ext_ts_irq &= ~(1 << chan);
+		if (!(pf->ptp.ext_ts_irq & (1 << chan)))
+			continue;
+
+		lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx));
+		hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx));
+		event.timestamp = (u64)hi << 32 | lo;
+
+		/* Add delay compensation */
+		pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_EXTTS, chan);
+		if (pin_desc_idx >= 0) {
+			const struct ice_ptp_pin_desc *desc;
+
+			desc = &pf->ptp.ice_pin_desc[pin_desc_idx];
+			event.timestamp -= desc->delay[0];
 		}
+
+		event.type = PTP_CLOCK_EXTTS;
+		event.index = chan;
+		pf->ptp.ext_ts_irq &= ~(1 << chan);
+		ptp_clock_event(pf->ptp.clock, &event);
 	}
 }
 
@@ -1600,14 +1627,6 @@ static int ice_ptp_cfg_extts(struct ice_pf *pf, struct ptp_extts_request *rq,
 	int pin_desc_idx;
 	u8 tmr_idx;
 
-	/* Reject requests with unsupported flags */
-
-	if (rq->flags & ~(PTP_ENABLE_FEATURE |
-			  PTP_RISING_EDGE |
-			  PTP_FALLING_EDGE |
-			  PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	chan = rq->index;
 
@@ -1711,7 +1730,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan,
 	/* 0. Reset mode & out_en in AUX_OUT */
 	wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0);
 
-	if (ice_is_e825c(hw)) {
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) {
 		int err;
 
 		/* Enable/disable CGU 1PPS output for E825C */
@@ -1754,6 +1773,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan,
 				  8 + chan + (tmr_idx * 4));
 
 	wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val);
+	ice_flush(hw);
 
 	return 0;
 }
@@ -1772,19 +1792,17 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan,
 static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 			      int on)
 {
+	unsigned int gpio_pin, prop_delay_ns;
 	u64 clk, period, start, phase;
 	struct ice_hw *hw = &pf->hw;
-	unsigned int gpio_pin;
 	int pin_desc_idx;
 
-	if (rq->flags & ~PTP_PEROUT_PHASE)
-		return -EOPNOTSUPP;
-
 	pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_PEROUT, rq->index);
 	if (pin_desc_idx < 0)
 		return -EIO;
 
 	gpio_pin = pf->ptp.ice_pin_desc[pin_desc_idx].gpio[1];
+	prop_delay_ns = pf->ptp.ice_pin_desc[pin_desc_idx].delay[1];
 	period = rq->period.sec * NSEC_PER_SEC + rq->period.nsec;
 
 	/* If we're disabling the output or period is 0, clear out CLKO and TGT
@@ -1794,7 +1812,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 		return ice_ptp_write_perout(hw, rq->index, gpio_pin, 0, 0);
 
 	if (strncmp(pf->ptp.pin_desc[pin_desc_idx].name, "1PPS", 64) == 0 &&
-	    period != NSEC_PER_SEC && hw->ptp.phy_model == ICE_PHY_E82X) {
+	    period != NSEC_PER_SEC && hw->mac_type == ICE_MAC_GENERIC) {
 		dev_err(ice_pf_to_dev(pf), "1PPS pin supports only 1 s period\n");
 		return -EOPNOTSUPP;
 	}
@@ -1813,14 +1831,15 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 		div64_u64_rem(start, period, &phase);
 
 	/* If we have only phase or start time is in the past, start the timer
-	 * at the next multiple of period, maintaining phase.
+	 * at the next multiple of period, maintaining phase at least 0.5 second
+	 * from now, so we have time to write it to HW.
 	 */
-	clk = ice_ptp_read_src_clk_reg(pf, NULL);
-	if (rq->flags & PTP_PEROUT_PHASE || start <= clk - ice_prop_delay(hw))
+	clk = ice_ptp_read_src_clk_reg(pf, NULL) + NSEC_PER_MSEC * 500;
+	if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns)
 		start = div64_u64(clk + period - 1, period) * period + phase;
 
 	/* Compensate for propagation delay from the generator to the pin. */
-	start -= ice_prop_delay(hw);
+	start -= prop_delay_ns;
 
 	return ice_ptp_write_perout(hw, rq->index, gpio_pin, start, period);
 }
@@ -2048,7 +2067,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	/* For Vernier mode on E82X, we need to recalibrate after new settime.
 	 * Start with marking timestamps as invalid.
 	 */
-	if (ice_get_phy_model(hw) == ICE_PHY_E82X) {
+	if (hw->mac_type == ICE_MAC_GENERIC) {
 		err = ice_ptp_clear_phy_offset_ready_e82x(hw);
 		if (err)
 			dev_warn(ice_pf_to_dev(pf), "Failed to mark timestamps as invalid before settime\n");
@@ -2072,7 +2091,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	ice_ptp_enable_all_perout(pf);
 
 	/* Recalibrate and re-enable timestamp blocks for E822/E823 */
-	if (ice_get_phy_model(hw) == ICE_PHY_E82X)
+	if (hw->mac_type == ICE_MAC_GENERIC)
 		ice_ptp_restart_all_phy(pf);
 exit:
 	if (err) {
@@ -2150,93 +2169,158 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
 	return 0;
 }
 
+/**
+ * struct ice_crosststamp_cfg - Device cross timestamp configuration
+ * @lock_reg: The hardware semaphore lock to use
+ * @lock_busy: Bit in the semaphore lock indicating the lock is busy
+ * @ctl_reg: The hardware register to request cross timestamp
+ * @ctl_active: Bit in the control register to request cross timestamp
+ * @art_time_l: Lower 32-bits of ART system time
+ * @art_time_h: Upper 32-bits of ART system time
+ * @dev_time_l: Lower 32-bits of device time (per timer index)
+ * @dev_time_h: Upper 32-bits of device time (per timer index)
+ */
+struct ice_crosststamp_cfg {
+	/* HW semaphore lock register */
+	u32 lock_reg;
+	u32 lock_busy;
+
+	/* Capture control register */
+	u32 ctl_reg;
+	u32 ctl_active;
+
+	/* Time storage */
+	u32 art_time_l;
+	u32 art_time_h;
+	u32 dev_time_l[2];
+	u32 dev_time_h[2];
+};
+
+static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e82x = {
+	.lock_reg = PFHH_SEM,
+	.lock_busy = PFHH_SEM_BUSY_M,
+	.ctl_reg = GLHH_ART_CTL,
+	.ctl_active = GLHH_ART_CTL_ACTIVE_M,
+	.art_time_l = GLHH_ART_TIME_L,
+	.art_time_h = GLHH_ART_TIME_H,
+	.dev_time_l[0] = GLTSYN_HHTIME_L(0),
+	.dev_time_h[0] = GLTSYN_HHTIME_H(0),
+	.dev_time_l[1] = GLTSYN_HHTIME_L(1),
+	.dev_time_h[1] = GLTSYN_HHTIME_H(1),
+};
+
 #ifdef CONFIG_ICE_HWTS
+static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e830 = {
+	.lock_reg = E830_PFPTM_SEM,
+	.lock_busy = E830_PFPTM_SEM_BUSY_M,
+	.ctl_reg = E830_GLPTM_ART_CTL,
+	.ctl_active = E830_GLPTM_ART_CTL_ACTIVE_M,
+	.art_time_l = E830_GLPTM_ART_TIME_L,
+	.art_time_h = E830_GLPTM_ART_TIME_H,
+	.dev_time_l[0] = E830_GLTSYN_PTMTIME_L(0),
+	.dev_time_h[0] = E830_GLTSYN_PTMTIME_H(0),
+	.dev_time_l[1] = E830_GLTSYN_PTMTIME_L(1),
+	.dev_time_h[1] = E830_GLTSYN_PTMTIME_H(1),
+};
+
+#endif /* CONFIG_ICE_HWTS */
+/**
+ * struct ice_crosststamp_ctx - Device cross timestamp context
+ * @snapshot: snapshot of system clocks for historic interpolation
+ * @pf: pointer to the PF private structure
+ * @cfg: pointer to hardware configuration for cross timestamp
+ */
+struct ice_crosststamp_ctx {
+	struct system_time_snapshot snapshot;
+	struct ice_pf *pf;
+	const struct ice_crosststamp_cfg *cfg;
+};
+
 /**
- * ice_ptp_get_syncdevicetime - Get the cross time stamp info
+ * ice_capture_crosststamp - Capture a device/system cross timestamp
  * @device: Current device time
  * @system: System counter value read synchronously with device time
- * @ctx: Context provided by timekeeping code
+ * @__ctx: Context passed from ice_ptp_getcrosststamp
  *
  * Read device and system (ART) clock simultaneously and return the corrected
  * clock values in ns.
+ *
+ * Return: zero on success, or a negative error code on failure.
  */
-static int
-ice_ptp_get_syncdevicetime(ktime_t *device,
-			   struct system_counterval_t *system,
-			   void *ctx)
+static int ice_capture_crosststamp(ktime_t *device,
+				   struct system_counterval_t *system,
+				   void *__ctx)
 {
-	struct ice_pf *pf = (struct ice_pf *)ctx;
-	struct ice_hw *hw = &pf->hw;
-	u32 hh_lock, hh_art_ctl;
-	int i;
+	struct ice_crosststamp_ctx *ctx = __ctx;
+	const struct ice_crosststamp_cfg *cfg;
+	u32 lock, ctl, ts_lo, ts_hi, tmr_idx;
+	struct ice_pf *pf;
+	struct ice_hw *hw;
+	int err;
+	u64 ts;
 
-#define MAX_HH_HW_LOCK_TRIES	5
-#define MAX_HH_CTL_LOCK_TRIES	100
+	cfg = ctx->cfg;
+	pf = ctx->pf;
+	hw = &pf->hw;
 
-	for (i = 0; i < MAX_HH_HW_LOCK_TRIES; i++) {
-		/* Get the HW lock */
-		hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id));
-		if (hh_lock & PFHH_SEM_BUSY_M) {
-			usleep_range(10000, 15000);
-			continue;
-		}
-		break;
-	}
-	if (hh_lock & PFHH_SEM_BUSY_M) {
-		dev_err(ice_pf_to_dev(pf), "PTP failed to get hh lock\n");
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
+	if (tmr_idx > 1)
+		return -EINVAL;
+
+	/* Poll until we obtain the cross-timestamp hardware semaphore */
+	err = rd32_poll_timeout(hw, cfg->lock_reg, lock,
+				!(lock & cfg->lock_busy),
+				10 * USEC_PER_MSEC, 50 * USEC_PER_MSEC);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "PTP failed to get cross timestamp lock\n");
 		return -EBUSY;
 	}
 
+	/* Snapshot system time for historic interpolation */
+	ktime_get_snapshot(&ctx->snapshot);
+
 	/* Program cmd to master timer */
 	ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME);
 
 	/* Start the ART and device clock sync sequence */
-	hh_art_ctl = rd32(hw, GLHH_ART_CTL);
-	hh_art_ctl = hh_art_ctl | GLHH_ART_CTL_ACTIVE_M;
-	wr32(hw, GLHH_ART_CTL, hh_art_ctl);
-
-	for (i = 0; i < MAX_HH_CTL_LOCK_TRIES; i++) {
-		/* Wait for sync to complete */
-		hh_art_ctl = rd32(hw, GLHH_ART_CTL);
-		if (hh_art_ctl & GLHH_ART_CTL_ACTIVE_M) {
-			udelay(1);
-			continue;
-		} else {
-			u32 hh_ts_lo, hh_ts_hi, tmr_idx;
-			u64 hh_ts;
-
-			tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
-			/* Read ART time */
-			hh_ts_lo = rd32(hw, GLHH_ART_TIME_L);
-			hh_ts_hi = rd32(hw, GLHH_ART_TIME_H);
-			hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo;
-			system->cycles = hh_ts;
-			system->cs_id = CSID_X86_ART;
-			/* Read Device source clock time */
-			hh_ts_lo = rd32(hw, GLTSYN_HHTIME_L(tmr_idx));
-			hh_ts_hi = rd32(hw, GLTSYN_HHTIME_H(tmr_idx));
-			hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo;
-			*device = ns_to_ktime(hh_ts);
-			break;
-		}
-	}
+	ctl = rd32(hw, cfg->ctl_reg);
+	ctl |= cfg->ctl_active;
+	wr32(hw, cfg->ctl_reg, ctl);
 
+	/* Poll until hardware completes the capture */
+	err = rd32_poll_timeout(hw, cfg->ctl_reg, ctl, !(ctl & cfg->ctl_active),
+				5, 20 * USEC_PER_MSEC);
+	if (err)
+		goto err_timeout;
+
+	/* Read ART system time */
+	ts_lo = rd32(hw, cfg->art_time_l);
+	ts_hi = rd32(hw, cfg->art_time_h);
+	ts = ((u64)ts_hi << 32) | ts_lo;
+	system->cycles = ts;
+	system->cs_id = CSID_X86_ART;
+	system->use_nsecs = true;
+
+	/* Read Device source clock time */
+	ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]);
+	ts_hi = rd32(hw, cfg->dev_time_h[tmr_idx]);
+	ts = ((u64)ts_hi << 32) | ts_lo;
+	*device = ns_to_ktime(ts);
+
+err_timeout:
 	/* Clear the master timer */
 	ice_ptp_src_cmd(hw, ICE_PTP_NOP);
 
 	/* Release HW lock */
-	hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id));
-	hh_lock = hh_lock & ~PFHH_SEM_BUSY_M;
-	wr32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), hh_lock);
+	lock = rd32(hw, cfg->lock_reg);
+	lock &= ~cfg->lock_busy;
+	wr32(hw, cfg->lock_reg, lock);
 
-	if (i == MAX_HH_CTL_LOCK_TRIES)
-		return -ETIMEDOUT;
-
-	return 0;
+	return err;
 }
 
 /**
- * ice_ptp_getcrosststamp_e82x - Capture a device cross timestamp
+ * ice_ptp_getcrosststamp - Capture a device cross timestamp
  * @info: the driver's PTP info structure
  * @cts: The memory to fill the cross timestamp info
  *
@@ -2244,22 +2328,36 @@ ice_ptp_get_syncdevicetime(ktime_t *device,
  * clock. Fill the cross timestamp information and report it back to the
  * caller.
  *
- * This is only valid for E822 and E823 devices which have support for
- * generating the cross timestamp via PCIe PTM.
- *
  * In order to correctly correlate the ART timestamp back to the TSC time, the
  * CPU must have X86_FEATURE_TSC_KNOWN_FREQ.
+ *
+ * Return: zero on success, or a negative error code on failure.
  */
-static int
-ice_ptp_getcrosststamp_e82x(struct ptp_clock_info *info,
-			    struct system_device_crosststamp *cts)
+static int ice_ptp_getcrosststamp(struct ptp_clock_info *info,
+				  struct system_device_crosststamp *cts)
 {
 	struct ice_pf *pf = ptp_info_to_pf(info);
+	struct ice_crosststamp_ctx ctx = {
+		.pf = pf,
+	};
+
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
+		ctx.cfg = &ice_crosststamp_cfg_e82x;
+		break;
+#ifdef CONFIG_ICE_HWTS
+	case ICE_MAC_E830:
+		ctx.cfg = &ice_crosststamp_cfg_e830;
+		break;
+#endif /* CONFIG_ICE_HWTS */
+	default:
+		return -EOPNOTSUPP;
+	}
 
-	return get_device_system_crosststamp(ice_ptp_get_syncdevicetime,
-					     pf, NULL, cts);
+	return get_device_system_crosststamp(ice_capture_crosststamp, &ctx,
+					     &ctx.snapshot, cts);
 }
-#endif /* CONFIG_ICE_HWTS */
 
 /**
  * ice_ptp_get_ts_config - ioctl interface to read the timestamping config
@@ -2520,13 +2618,9 @@ static int ice_ptp_parse_sdp_entries(struct ice_pf *pf, __le16 *entries,
  */
 static void ice_ptp_set_funcs_e82x(struct ice_pf *pf)
 {
-#ifdef CONFIG_ICE_HWTS
-	if (boot_cpu_has(X86_FEATURE_ART) &&
-	    boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ))
-		pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp_e82x;
+	pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp;
 
-#endif /* CONFIG_ICE_HWTS */
-	if (ice_is_e825c(&pf->hw)) {
+	if (pf->hw.mac_type == ICE_MAC_GENERIC_3K_E825) {
 		pf->ptp.ice_pin_desc = ice_pin_desc_e825c;
 		pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e825c);
 	} else {
@@ -2593,6 +2687,28 @@ err:
 }
 
 /**
+ * ice_ptp_set_funcs_e830 - Set specialized functions for E830 support
+ * @pf: Board private structure
+ *
+ * Assign functions to the PTP capabiltiies structure for E830 devices.
+ * Functions which operate across all device families should be set directly
+ * in ice_ptp_set_caps. Only add functions here which are distinct for E830
+ * devices.
+ */
+static void ice_ptp_set_funcs_e830(struct ice_pf *pf)
+{
+#ifdef CONFIG_ICE_HWTS
+	if (pcie_ptm_enabled(pf->pdev) && boot_cpu_has(X86_FEATURE_ART))
+		pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp;
+
+#endif /* CONFIG_ICE_HWTS */
+	/* Rest of the config is the same as base E810 */
+	pf->ptp.ice_pin_desc = ice_pin_desc_e810;
+	pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810);
+	ice_ptp_setup_pin_cfg(pf);
+}
+
+/**
  * ice_ptp_set_caps - Set PTP capabilities
  * @pf: Board private structure
  */
@@ -2614,10 +2730,25 @@ static void ice_ptp_set_caps(struct ice_pf *pf)
 	info->enable = ice_ptp_gpio_enable;
 	info->verify = ice_verify_pin;
 
-	if (ice_is_e810(&pf->hw))
+	info->supported_extts_flags = PTP_RISING_EDGE |
+				      PTP_FALLING_EDGE |
+				      PTP_STRICT_FLAGS;
+	info->supported_perout_flags = PTP_PEROUT_PHASE;
+
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_E810:
 		ice_ptp_set_funcs_e810(pf);
-	else
+		return;
+	case ICE_MAC_E830:
+		ice_ptp_set_funcs_e830(pf);
+		return;
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
 		ice_ptp_set_funcs_e82x(pf);
+		return;
+	default:
+		return;
+	}
 }
 
 /**
@@ -2728,6 +2859,65 @@ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf)
 }
 
 /**
+ * ice_ptp_ts_irq - Process the PTP Tx timestamps in IRQ context
+ * @pf: Board private structure
+ *
+ * Return: IRQ_WAKE_THREAD if Tx timestamp read has to be handled in the bottom
+ *         half of the interrupt and IRQ_HANDLED otherwise.
+ */
+irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+		/* E810 capable of low latency timestamping with interrupt can
+		 * request a single timestamp in the top half and wait for
+		 * a second LL TS interrupt from the FW when it's ready.
+		 */
+		if (hw->dev_caps.ts_dev_info.ts_ll_int_read) {
+			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
+			u8 idx;
+
+			if (!ice_pf_state_is_nominal(pf))
+				return IRQ_HANDLED;
+
+			spin_lock(&tx->lock);
+			idx = find_next_bit_wrap(tx->in_use, tx->len,
+						 tx->last_ll_ts_idx_read + 1);
+			if (idx != tx->len)
+				ice_ptp_req_tx_single_tstamp(tx, idx);
+			spin_unlock(&tx->lock);
+
+			return IRQ_HANDLED;
+		}
+		fallthrough; /* non-LL_TS E810 */
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
+		/* All other devices process timestamps in the bottom half due
+		 * to sleeping or polling.
+		 */
+		if (!ice_ptp_pf_handles_tx_interrupt(pf))
+			return IRQ_HANDLED;
+
+		set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
+		return IRQ_WAKE_THREAD;
+	case ICE_MAC_E830:
+		/* E830 can read timestamps in the top half using rd32() */
+		if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) {
+			/* Process outstanding Tx timestamps. If there
+			 * is more work, re-arm the interrupt to trigger again.
+			 */
+			wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M);
+			ice_flush(hw);
+		}
+		return IRQ_HANDLED;
+	default:
+		return IRQ_HANDLED;
+	}
+}
+
+/**
  * ice_ptp_maybe_trigger_tx_interrupt - Trigger Tx timstamp interrupt
  * @pf: Board private structure
  *
@@ -2747,7 +2937,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf)
 	bool trigger_oicr = false;
 	unsigned int i;
 
-	if (ice_is_e810(hw))
+	if (!pf->ptp.port.tx.has_ready_bitmap)
 		return;
 
 	if (!ice_pf_src_tmr_owned(pf))
@@ -2794,6 +2984,32 @@ static void ice_ptp_periodic_work(struct kthread_work *work)
 }
 
 /**
+ * ice_ptp_prepare_rebuild_sec - Prepare second NAC for PTP reset or rebuild
+ * @pf: Board private structure
+ * @rebuild: rebuild if true, prepare if false
+ * @reset_type: the reset type being performed
+ */
+static void ice_ptp_prepare_rebuild_sec(struct ice_pf *pf, bool rebuild,
+					enum ice_reset_req reset_type)
+{
+	struct list_head *entry;
+
+	list_for_each(entry, &pf->adapter->ports.ports) {
+		struct ice_ptp_port *port = list_entry(entry,
+						       struct ice_ptp_port,
+						       list_node);
+		struct ice_pf *peer_pf = ptp_port_to_pf(port);
+
+		if (!ice_is_primary(&peer_pf->hw)) {
+			if (rebuild)
+				ice_ptp_rebuild(peer_pf, reset_type);
+			else
+				ice_ptp_prepare_for_reset(peer_pf, reset_type);
+		}
+	}
+}
+
+/**
  * ice_ptp_prepare_for_reset - Prepare PTP for reset
  * @pf: Board private structure
  * @reset_type: the reset type being performed
@@ -2801,6 +3017,7 @@ static void ice_ptp_periodic_work(struct kthread_work *work)
 void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 {
 	struct ice_ptp *ptp = &pf->ptp;
+	struct ice_hw *hw = &pf->hw;
 	u8 src_tmr;
 
 	if (ptp->state != ICE_PTP_READY)
@@ -2816,6 +3033,9 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 	if (reset_type == ICE_RESET_PFR)
 		return;
 
+	if (ice_pf_src_tmr_owned(pf) && hw->mac_type == ICE_MAC_GENERIC_3K_E825)
+		ice_ptp_prepare_rebuild_sec(pf, false, reset_type);
+
 	ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx);
 
 	/* Disable periodic outputs */
@@ -2882,14 +3102,12 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf)
 	 */
 	ice_ptp_flush_all_tx_tracker(pf);
 
-	if (!ice_is_e810(hw)) {
-		/* Enable quad interrupts */
-		err = ice_ptp_cfg_phy_interrupt(pf, true, 1);
-		if (err)
-			return err;
+	/* Enable quad interrupts */
+	err = ice_ptp_cfg_phy_interrupt(pf, true, 1);
+	if (err)
+		return err;
 
-		ice_ptp_restart_all_phy(pf);
-	}
+	ice_ptp_restart_all_phy(pf);
 
 	/* Re-enable all periodic outputs and external timestamp events */
 	ice_ptp_enable_all_perout(pf);
@@ -2939,12 +3157,6 @@ err:
 	dev_err(ice_pf_to_dev(pf), "PTP reset failed %d\n", err);
 }
 
-static bool ice_is_primary(struct ice_hw *hw)
-{
-	return ice_is_e825c(hw) && ice_is_dual(hw) ?
-		!!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : true;
-}
-
 static int ice_ptp_setup_adapter(struct ice_pf *pf)
 {
 	if (!ice_pf_src_tmr_owned(pf) || !ice_is_primary(&pf->hw))
@@ -2960,7 +3172,7 @@ static int ice_ptp_setup_pf(struct ice_pf *pf)
 	struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf);
 	struct ice_ptp *ptp = &pf->ptp;
 
-	if (WARN_ON(!ctrl_ptp) || ice_get_phy_model(&pf->hw) == ICE_PHY_UNSUP)
+	if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN)
 		return -ENODEV;
 
 	INIT_LIST_HEAD(&ptp->port.list_node);
@@ -2977,7 +3189,7 @@ static void ice_ptp_cleanup_pf(struct ice_pf *pf)
 {
 	struct ice_ptp *ptp = &pf->ptp;
 
-	if (ice_get_phy_model(&pf->hw) != ICE_PHY_UNSUP) {
+	if (pf->hw.mac_type != ICE_MAC_UNKNOWN) {
 		mutex_lock(&pf->adapter->ports.lock);
 		list_del(&ptp->port.list_node);
 		mutex_unlock(&pf->adapter->ports.lock);
@@ -3080,7 +3292,7 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp)
 	/* Allocate a kworker for handling work required for the ports
 	 * connected to the PTP hardware clock.
 	 */
-	kworker = kthread_create_worker(0, "ice-ptp-%s",
+	kworker = kthread_run_worker(0, "ice-ptp-%s",
 					dev_name(ice_pf_to_dev(pf)));
 	if (IS_ERR(kworker))
 		return PTR_ERR(kworker);
@@ -3097,6 +3309,8 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp)
  * ice_ptp_init_port - Initialize PTP port structure
  * @pf: Board private structure
  * @ptp_port: PTP port structure
+ *
+ * Return: 0 on success, -ENODEV on invalid MAC type, -ENOMEM on failed alloc.
  */
 static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 {
@@ -3104,16 +3318,14 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 
 	mutex_init(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx,
-					      ptp_port->port_num);
-	case ICE_PHY_E810:
-		return ice_ptp_init_tx_e810(pf, &ptp_port->tx);
-	case ICE_PHY_E82X:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_init_tx(pf, &ptp_port->tx, ptp_port->port_num);
+	case ICE_MAC_GENERIC:
 		kthread_init_delayed_work(&ptp_port->ov_work,
 					  ice_ptp_wait_for_offsets);
-
 		return ice_ptp_init_tx_e82x(pf, &ptp_port->tx,
 					    ptp_port->port_num);
 	default:
@@ -3132,8 +3344,8 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
  */
 static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf)
 {
-	switch (ice_get_phy_model(&pf->hw)) {
-	case ICE_PHY_E82X:
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_GENERIC:
 		/* E822 based PHY has the clock owner process the interrupt
 		 * for all ports.
 		 */
@@ -3168,6 +3380,12 @@ void ice_ptp_init(struct ice_pf *pf)
 
 	ptp->state = ICE_PTP_INITIALIZING;
 
+	if (hw->lane_num < 0) {
+		err = hw->lane_num;
+		goto err_exit;
+	}
+	ptp->port.port_num = hw->lane_num;
+
 	ice_ptp_init_hw(hw);
 
 	ice_ptp_init_tx_interrupt_mode(pf);
@@ -3188,10 +3406,6 @@ void ice_ptp_init(struct ice_pf *pf)
 	if (err)
 		goto err_exit;
 
-	ptp->port.port_num = hw->pf_id;
-	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
-		ptp->port.port_num = hw->pf_id * 2;
-
 	err = ice_ptp_init_port(pf, &ptp->port);
 	if (err)
 		goto err_exit;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 824e73b677a4..3b769a0cad00 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -128,8 +128,7 @@ struct ice_ptp_tx {
 /* Quad and port information for initializing timestamp blocks */
 #define INDEX_PER_QUAD			64
 #define INDEX_PER_PORT_E82X		16
-#define INDEX_PER_PORT_E810		64
-#define INDEX_PER_PORT_ETH56G		64
+#define INDEX_PER_PORT			64
 
 /**
  * struct ice_ptp_port - data used to initialize an external port for PTP
@@ -211,6 +210,7 @@ enum ice_ptp_pin_nvm {
  * struct ice_ptp_pin_desc - hardware pin description data
  * @name_idx: index of the name of pin in ice_pin_names
  * @gpio: the associated GPIO input and output pins
+ * @delay: input and output signal delays in nanoseconds
  *
  * Structure describing a PTP-capable GPIO pin that extends ptp_pin_desc array
  * for the device. Device families have separate sets of available pins with
@@ -219,6 +219,7 @@ enum ice_ptp_pin_nvm {
 struct ice_ptp_pin_desc {
 	int name_idx;
 	int gpio[2];
+	unsigned int delay[2];
 };
 
 /**
@@ -302,6 +303,9 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb);
 void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx);
 void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx);
 enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf);
+irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf);
+u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+			     struct ptp_system_timestamp *sts);
 
 u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
 			const struct ice_pkt_ctx *pkt_ctx);
@@ -310,7 +314,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf,
 			       enum ice_reset_req reset_type);
 void ice_ptp_init(struct ice_pf *pf);
 void ice_ptp_release(struct ice_pf *pf);
-void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup);
+void ice_ptp_link_change(struct ice_pf *pf, bool linkup);
 #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
 {
@@ -340,6 +344,17 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf)
 	return true;
 }
 
+static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
+{
+	return IRQ_HANDLED;
+}
+
+static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+					   struct ptp_system_timestamp *sts)
+{
+	return 0;
+}
+
 static inline u64
 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
 		    const struct ice_pkt_ctx *pkt_ctx)
@@ -358,7 +373,7 @@ static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf,
 }
 static inline void ice_ptp_init(struct ice_pf *pf) { }
 static inline void ice_ptp_release(struct ice_pf *pf) { }
-static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
+static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 {
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
index 585ce200c60f..003cdfada3ca 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
@@ -10,70 +10,25 @@
 /* Constants defined for the PTP 1588 clock hardware. */
 
 const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES] = {
-	/* ETH56G_PHY_REG_PTP */
-	{
-		/* base_addr */
-		{
-			0x092000,
-			0x126000,
-			0x1BA000,
-			0x24E000,
-			0x2E2000,
-		},
-		/* step */
-		0x98,
+	[ETH56G_PHY_REG_PTP] = {
+		.base_addr = 0x092000,
+		.step = 0x98,
 	},
-	/* ETH56G_PHY_MEM_PTP */
-	{
-		/* base_addr */
-		{
-			0x093000,
-			0x127000,
-			0x1BB000,
-			0x24F000,
-			0x2E3000,
-		},
-		/* step */
-		0x200,
+	[ETH56G_PHY_MEM_PTP] = {
+		.base_addr = 0x093000,
+		.step = 0x200,
 	},
-	/* ETH56G_PHY_REG_XPCS */
-	{
-		/* base_addr */
-		{
-			0x000000,
-			0x009400,
-			0x128000,
-			0x1BC000,
-			0x250000,
-		},
-		/* step */
-		0x21000,
+	[ETH56G_PHY_REG_XPCS] = {
+		.base_addr = 0x000000,
+		.step = 0x21000,
 	},
-	/* ETH56G_PHY_REG_MAC */
-	{
-		/* base_addr */
-		{
-			0x085000,
-			0x119000,
-			0x1AD000,
-			0x241000,
-			0x2D5000,
-		},
-		/* step */
-		0x1000,
+	[ETH56G_PHY_REG_MAC] = {
+		.base_addr = 0x085000,
+		.step = 0x1000,
 	},
-	/* ETH56G_PHY_REG_GPCS */
-	{
-		/* base_addr */
-		{
-			0x084000,
-			0x118000,
-			0x1AC000,
-			0x240000,
-			0x2D4000,
-		},
-		/* step */
-		0x400,
+	[ETH56G_PHY_REG_GPCS] = {
+		.base_addr = 0x084000,
+		.step = 0x400,
 	},
 };
 
@@ -131,7 +86,7 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = {
 		.rx_offset = {
 			.serdes = 0xffffeb27, /* -10.42424 */
 			.no_fec = 0xffffcccd, /* -25.6 */
-			.fc = 0xfffe0014, /* -255.96 */
+			.fc = 0xfffc557b, /* -469.26 */
 			.sfd = 0x4a4, /* 2.32 */
 			.bs_ds = 0x32 /* 0.0969697 */
 		}
@@ -341,8 +296,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = {
 		823437500, /* 823.4375 MHz PLL */
 		/* nominal_incval */
 		0x136e44fabULL,
-		/* pps_delay */
-		11,
 	},
 
 	/* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */
@@ -351,8 +304,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = {
 		783360000, /* 783.36 MHz */
 		/* nominal_incval */
 		0x146cc2177ULL,
-		/* pps_delay */
-		12,
 	},
 
 	/* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */
@@ -361,8 +312,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = {
 		796875000, /* 796.875 MHz */
 		/* nominal_incval */
 		0x141414141ULL,
-		/* pps_delay */
-		12,
 	},
 
 	/* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */
@@ -371,8 +320,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = {
 		816000000, /* 816 MHz */
 		/* nominal_incval */
 		0x139b9b9baULL,
-		/* pps_delay */
-		12,
 	},
 
 	/* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */
@@ -381,8 +328,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = {
 		830078125, /* 830.78125 MHz */
 		/* nominal_incval */
 		0x134679aceULL,
-		/* pps_delay */
-		11,
 	},
 
 	/* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */
@@ -391,8 +336,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = {
 		783360000, /* 783.36 MHz */
 		/* nominal_incval */
 		0x146cc2177ULL,
-		/* pps_delay */
-		12,
 	},
 };
 
@@ -761,9 +704,9 @@ const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD] = {
 		/* rx_desk_rsgb_par */
 		644531250, /* 644.53125 MHz Reed Solomon gearbox */
 		/* tx_desk_rsgb_pcs */
-		644531250, /* 644.53125 MHz Reed Solomon gearbox */
+		390625000, /* 390.625 MHz Reed Solomon gearbox */
 		/* rx_desk_rsgb_pcs */
-		644531250, /* 644.53125 MHz Reed Solomon gearbox */
+		390625000, /* 390.625 MHz Reed Solomon gearbox */
 		/* tx_fixed_delay */
 		1620,
 		/* pmd_adj_divisor */
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index dfd49732bd5b..ccac84eb34c9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -240,7 +240,7 @@ static int ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val)
 {
 	struct ice_sbq_msg_input cgu_msg = {
 		.opcode = ice_sbq_msg_rd,
-		.dest_dev = cgu,
+		.dest_dev = ice_sbq_dev_cgu,
 		.msg_addr_low = addr
 	};
 	int err;
@@ -272,7 +272,7 @@ static int ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val)
 {
 	struct ice_sbq_msg_input cgu_msg = {
 		.opcode = ice_sbq_msg_wr,
-		.dest_dev = cgu,
+		.dest_dev = ice_sbq_dev_cgu,
 		.msg_addr_low = addr,
 		.data = val
 	};
@@ -391,7 +391,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 
 	/* Log the current clock configuration */
 	ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.ts_pll_enable ? "enabled" : "disabled",
+		  str_enabled_disabled(dw24.ts_pll_enable),
 		  ice_clk_src_str(dw24.time_ref_sel),
 		  ice_clk_freq_str(dw9.time_ref_freq_sel),
 		  bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked");
@@ -469,7 +469,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw,
 
 	/* Log the current clock configuration */
 	ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.ts_pll_enable ? "enabled" : "disabled",
+		  str_enabled_disabled(dw24.ts_pll_enable),
 		  ice_clk_src_str(dw24.time_ref_sel),
 		  ice_clk_freq_str(dw9.time_ref_freq_sel),
 		  bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked");
@@ -546,7 +546,7 @@ static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw,
 
 	/* Log the current clock configuration */
 	ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.ts_pll_enable ? "enabled" : "disabled",
+		  str_enabled_disabled(dw24.ts_pll_enable),
 		  ice_clk_src_str(dw23.time_ref_sel),
 		  ice_clk_freq_str(dw9.time_ref_freq_sel),
 		  ro_lock.plllock_true_lock_cri ? "locked" : "unlocked");
@@ -651,7 +651,7 @@ static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw,
 
 	/* Log the current clock configuration */
 	ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n",
-		  dw24.ts_pll_enable ? "enabled" : "disabled",
+		  str_enabled_disabled(dw24.ts_pll_enable),
 		  ice_clk_src_str(dw23.time_ref_sel),
 		  ice_clk_freq_str(dw9.time_ref_freq_sel),
 		  ro_lock.plllock_true_lock_cri ? "locked" : "unlocked");
@@ -746,7 +746,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw)
 	int err;
 
 	/* Disable sticky lock detection so lock err reported is accurate */
-	if (ice_is_e825c(hw))
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825)
 		err = ice_cfg_cgu_pll_dis_sticky_bits_e825c(hw);
 	else
 		err = ice_cfg_cgu_pll_dis_sticky_bits_e82x(hw);
@@ -756,7 +756,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw)
 	/* Configure the CGU PLL using the parameters from the function
 	 * capabilities.
 	 */
-	if (ice_is_e825c(hw))
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825)
 		err = ice_cfg_cgu_pll_e825c(hw, ts_info->time_ref,
 					    (enum ice_clk_src)ts_info->clk_src);
 	else
@@ -827,8 +827,9 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
 	/* Certain hardware families share the same register values for the
 	 * port register and source timer register.
 	 */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810;
 	default:
 		break;
@@ -873,8 +874,12 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
  */
 void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u32 cmd_val = ice_ptp_tmr_cmd_to_src_reg(hw, cmd);
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	wr32(hw, GLTSYN_CMD, cmd_val);
 }
 
@@ -890,41 +895,78 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
 {
 	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD);
 	ice_flush(hw);
 }
 
+/**
+ * ice_ptp_cfg_sync_delay - Configure PHC to PHY synchronization delay
+ * @hw: pointer to HW struct
+ * @delay: delay between PHC and PHY SYNC command execution in nanoseconds
+ */
+static void ice_ptp_cfg_sync_delay(const struct ice_hw *hw, u32 delay)
+{
+	wr32(hw, GLTSYN_SYNC_DLAY, delay);
+	ice_flush(hw);
+}
+
 /* 56G PHY device functions
  *
  * The following functions operate on devices with the ETH 56G PHY.
  */
 
 /**
+ * ice_ptp_get_dest_dev_e825 - get destination PHY for given port number
+ * @hw: pointer to the HW struct
+ * @port: destination port
+ *
+ * Return: destination sideband queue PHY device.
+ */
+static enum ice_sbq_dev_id ice_ptp_get_dest_dev_e825(struct ice_hw *hw,
+						     u8 port)
+{
+	u8 curr_phy, tgt_phy;
+
+	tgt_phy = port >= hw->ptp.ports_per_phy;
+	curr_phy = hw->lane_num >= hw->ptp.ports_per_phy;
+	/* In the driver, lanes 4..7 are in fact 0..3 on a second PHY.
+	 * On a single complex E825C, PHY 0 is always destination device phy_0
+	 * and PHY 1 is phy_0_peer.
+	 * On dual complex E825C, device phy_0 points to PHY on a current
+	 * complex and phy_0_peer to PHY on a different complex.
+	 */
+	if ((!ice_is_dual(hw) && tgt_phy == 1) ||
+	    (ice_is_dual(hw) && tgt_phy != curr_phy))
+		return ice_sbq_dev_phy_0_peer;
+	else
+		return ice_sbq_dev_phy_0;
+}
+
+/**
  * ice_write_phy_eth56g - Write a PHY port register
  * @hw: pointer to the HW struct
- * @phy_idx: PHY index
+ * @port: destination port
  * @addr: PHY register address
  * @val: Value to write
  *
  * Return: 0 on success, other error codes when failed to write to PHY
  */
-static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
-				u32 val)
+static int ice_write_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 val)
 {
-	struct ice_sbq_msg_input phy_msg;
+	struct ice_sbq_msg_input msg = {
+		.dest_dev = ice_ptp_get_dest_dev_e825(hw, port),
+		.opcode = ice_sbq_msg_wr,
+		.msg_addr_low = lower_16_bits(addr),
+		.msg_addr_high = upper_16_bits(addr),
+		.data = val
+	};
 	int err;
 
-	phy_msg.opcode = ice_sbq_msg_wr;
-
-	phy_msg.msg_addr_low = lower_16_bits(addr);
-	phy_msg.msg_addr_high = upper_16_bits(addr);
-
-	phy_msg.data = val;
-	phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx];
-
-	err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD);
-
+	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
 	if (err)
 		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
 			  err);
@@ -935,41 +977,36 @@ static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
 /**
  * ice_read_phy_eth56g - Read a PHY port register
  * @hw: pointer to the HW struct
- * @phy_idx: PHY index
+ * @port: destination port
  * @addr: PHY register address
  * @val: Value to write
  *
  * Return: 0 on success, other error codes when failed to read from PHY
  */
-static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
-			       u32 *val)
+static int ice_read_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 *val)
 {
-	struct ice_sbq_msg_input phy_msg;
+	struct ice_sbq_msg_input msg = {
+		.dest_dev = ice_ptp_get_dest_dev_e825(hw, port),
+		.opcode = ice_sbq_msg_rd,
+		.msg_addr_low = lower_16_bits(addr),
+		.msg_addr_high = upper_16_bits(addr)
+	};
 	int err;
 
-	phy_msg.opcode = ice_sbq_msg_rd;
-
-	phy_msg.msg_addr_low = lower_16_bits(addr);
-	phy_msg.msg_addr_high = upper_16_bits(addr);
-
-	phy_msg.data = 0;
-	phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx];
-
-	err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD);
-	if (err) {
+	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	if (err)
 		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
 			  err);
-		return err;
-	}
-
-	*val = phy_msg.data;
+	else
+		*val = msg.data;
 
-	return 0;
+	return err;
 }
 
 /**
  * ice_phy_res_address_eth56g - Calculate a PHY port register address
- * @port: Port number to be written
+ * @hw: pointer to the HW struct
+ * @lane: Lane number to be written
  * @res_type: resource type (register/memory)
  * @offset: Offset from PHY port register base
  * @addr: The result address
@@ -978,17 +1015,19 @@ static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr,
  * * %0      - success
  * * %EINVAL - invalid port number or resource type
  */
-static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type,
-				      u32 offset, u32 *addr)
+static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane,
+				      enum eth56g_res_type res_type,
+				      u32 offset,
+				      u32 *addr)
 {
-	u8 lane = port % ICE_PORTS_PER_QUAD;
-	u8 phy = ICE_GET_QUAD_NUM(port);
-
 	if (res_type >= NUM_ETH56G_PHY_RES)
 		return -EINVAL;
 
-	*addr = eth56g_phy_res[res_type].base[phy] +
+	/* Lanes 4..7 are in fact 0..3 on a second PHY */
+	lane %= hw->ptp.ports_per_phy;
+	*addr = eth56g_phy_res[res_type].base_addr +
 		lane * eth56g_phy_res[res_type].step + offset;
+
 	return 0;
 }
 
@@ -1008,19 +1047,17 @@ static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type,
 static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 				 u32 val, enum eth56g_res_type res_type)
 {
-	u8 phy_port = port % hw->ptp.ports_per_phy;
-	u8 phy_idx = port / hw->ptp.ports_per_phy;
 	u32 addr;
 	int err;
 
 	if (port >= hw->ptp.num_lports)
 		return -EINVAL;
 
-	err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr);
+	err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr);
 	if (err)
 		return err;
 
-	return ice_write_phy_eth56g(hw, phy_idx, addr, val);
+	return ice_write_phy_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -1039,19 +1076,17 @@ static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 static int ice_read_port_eth56g(struct ice_hw *hw, u8 port, u32 offset,
 				u32 *val, enum eth56g_res_type res_type)
 {
-	u8 phy_port = port % hw->ptp.ports_per_phy;
-	u8 phy_idx = port / hw->ptp.ports_per_phy;
 	u32 addr;
 	int err;
 
 	if (port >= hw->ptp.num_lports)
 		return -EINVAL;
 
-	err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr);
+	err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr);
 	if (err)
 		return err;
 
-	return ice_read_phy_eth56g(hw, phy_idx, addr, val);
+	return ice_read_phy_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -1201,6 +1236,56 @@ static int ice_write_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset,
 }
 
 /**
+ * ice_write_quad_ptp_reg_eth56g - Write a PHY quad register
+ * @hw: pointer to the HW struct
+ * @offset: PHY register offset
+ * @port: Port number
+ * @val: Value to write
+ *
+ * Return:
+ * * %0     - success
+ * * %EIO  - invalid port number or resource type
+ * * %other - failed to write to PHY
+ */
+static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
+					 u32 offset, u32 val)
+{
+	u32 addr;
+
+	if (port >= hw->ptp.num_lports)
+		return -EIO;
+
+	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset;
+
+	return ice_write_phy_eth56g(hw, port, addr, val);
+}
+
+/**
+ * ice_read_quad_ptp_reg_eth56g - Read a PHY quad register
+ * @hw: pointer to the HW struct
+ * @offset: PHY register offset
+ * @port: Port number
+ * @val: Value to read
+ *
+ * Return:
+ * * %0     - success
+ * * %EIO  - invalid port number or resource type
+ * * %other - failed to read from PHY
+ */
+static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
+					u32 offset, u32 *val)
+{
+	u32 addr;
+
+	if (port >= hw->ptp.num_lports)
+		return -EIO;
+
+	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset;
+
+	return ice_read_phy_eth56g(hw, port, addr, val);
+}
+
+/**
  * ice_is_64b_phy_reg_eth56g - Check if this is a 64bit PHY register
  * @low_addr: the low address to check
  * @high_addr: on return, contains the high address of the 64bit register
@@ -1518,8 +1603,8 @@ static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx,
 	 * lower 8 bits in the low register, and the upper 32 bits in the high
 	 * register.
 	 */
-	*tstamp = ((u64)hi) << TS_PHY_HIGH_S | ((u64)lo & TS_PHY_LOW_M);
-
+	*tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_40B_LOW_M, lo);
 	return 0;
 }
 
@@ -1918,7 +2003,6 @@ ice_phy_get_speed_eth56g(struct ice_link_status *li)
  */
 static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 {
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
 	u32 val;
 	int err;
 
@@ -1933,8 +2017,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 	switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) {
 	case ICE_ETH56G_LNK_SPD_1G:
 	case ICE_ETH56G_LNK_SPD_2_5G:
-		err = ice_read_ptp_reg_eth56g(hw, port_blk,
-					      PHY_GPCS_CONFIG_REG0, &val);
+		err = ice_read_quad_ptp_reg_eth56g(hw, port,
+						   PHY_GPCS_CONFIG_REG0, &val);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to read PHY_GPCS_CONFIG_REG0, status: %d",
 				  err);
@@ -1945,8 +2029,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
 		val |= FIELD_PREP(PHY_GPCS_CONFIG_REG0_TX_THR_M,
 				  ICE_ETH56G_NOMINAL_TX_THRESH);
 
-		err = ice_write_ptp_reg_eth56g(hw, port_blk,
-					       PHY_GPCS_CONFIG_REG0, val);
+		err = ice_write_quad_ptp_reg_eth56g(hw, port,
+						    PHY_GPCS_CONFIG_REG0, val);
 		if (err) {
 			ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_GPCS_CONFIG_REG0, status: %d",
 				  err);
@@ -1987,50 +2071,47 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port)
  */
 int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port)
 {
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
-	u8 blk_port = port & (ICE_PORTS_PER_QUAD - 1);
+	u8 quad_lane = port % ICE_PORTS_PER_QUAD;
+	u32 addr, val, peer_delay;
 	bool enable, sfd_ena;
-	u32 val, peer_delay;
 	int err;
 
 	enable = hw->ptp.phy.eth56g.onestep_ena;
 	peer_delay = hw->ptp.phy.eth56g.peer_delay;
 	sfd_ena = hw->ptp.phy.eth56g.sfd_ena;
 
-	/* PHY_PTP_1STEP_CONFIG */
-	err = ice_read_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, &val);
+	addr = PHY_PTP_1STEP_CONFIG;
+	err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &val);
 	if (err)
 		return err;
 
 	if (enable)
-		val |= blk_port;
+		val |= BIT(quad_lane);
 	else
-		val &= ~blk_port;
+		val &= ~BIT(quad_lane);
 
 	val &= ~(PHY_PTP_1STEP_T1S_UP64_M | PHY_PTP_1STEP_T1S_DELTA_M);
 
-	err = ice_write_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, val);
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
 	if (err)
 		return err;
 
-	/* PHY_PTP_1STEP_PEER_DELAY */
+	addr = PHY_PTP_1STEP_PEER_DELAY(quad_lane);
 	val = FIELD_PREP(PHY_PTP_1STEP_PD_DELAY_M, peer_delay);
 	if (peer_delay)
 		val |= PHY_PTP_1STEP_PD_ADD_PD_M;
 	val |= PHY_PTP_1STEP_PD_DLY_V_M;
-	err = ice_write_ptp_reg_eth56g(hw, port_blk,
-				       PHY_PTP_1STEP_PEER_DELAY(blk_port), val);
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
 	if (err)
 		return err;
 
 	val &= ~PHY_PTP_1STEP_PD_DLY_V_M;
-	err = ice_write_ptp_reg_eth56g(hw, port_blk,
-				       PHY_PTP_1STEP_PEER_DELAY(blk_port), val);
+	err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val);
 	if (err)
 		return err;
 
-	/* PHY_MAC_XIF_MODE */
-	err = ice_read_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, &val);
+	addr = PHY_MAC_XIF_MODE;
+	err = ice_read_mac_reg_eth56g(hw, port, addr, &val);
 	if (err)
 		return err;
 
@@ -2050,7 +2131,7 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port)
 	       FIELD_PREP(PHY_MAC_XIF_TS_BIN_MODE_M, enable) |
 	       FIELD_PREP(PHY_MAC_XIF_TS_SFD_ENA_M, sfd_ena);
 
-	return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, val);
+	return ice_write_mac_reg_eth56g(hw, port, addr, val);
 }
 
 /**
@@ -2092,21 +2173,22 @@ static u32 ice_ptp_calc_bitslip_eth56g(struct ice_hw *hw, u8 port, u32 bs,
 				       bool fc, bool rs,
 				       enum ice_eth56g_link_spd spd)
 {
-	u8 port_offset = port & (ICE_PORTS_PER_QUAD - 1);
-	u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1);
 	u32 bitslip;
 	int err;
 
 	if (!bs || rs)
 		return 0;
 
-	if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G)
+	if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G) {
 		err = ice_read_gpcs_reg_eth56g(hw, port, PHY_GPCS_BITSLIP,
 					       &bitslip);
-	else
-		err = ice_read_ptp_reg_eth56g(hw, port_blk,
-					      PHY_REG_SD_BIT_SLIP(port_offset),
-					      &bitslip);
+	} else {
+		u8 quad_lane = port % ICE_PORTS_PER_QUAD;
+		u32 addr;
+
+		addr = PHY_REG_SD_BIT_SLIP(quad_lane);
+		err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &bitslip);
+	}
 	if (err)
 		return 0;
 
@@ -2350,6 +2432,7 @@ int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold)
 static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port,
 					    u64 *phy_time, u64 *phc_time)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u64 tx_time, rx_time;
 	u32 zo, lo;
 	u8 tmr_idx;
@@ -2369,8 +2452,13 @@ static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port,
 	ice_ptp_exec_tmr_cmd(hw);
 
 	/* Read the captured PHC time from the shadow time registers */
-	zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx));
-	lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx));
+	if (ice_is_primary(hw)) {
+		zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx));
+		lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx));
+	} else {
+		zo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_0(tmr_idx));
+		lo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_L(tmr_idx));
+	}
 	*phc_time = (u64)lo << 32 | zo;
 
 	/* Read the captured PHY time from the PHY shadow registers */
@@ -2507,6 +2595,7 @@ int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset)
  */
 int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u32 lo, hi;
 	u64 incval;
 	u8 tmr_idx;
@@ -2532,8 +2621,13 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 	if (err)
 		return err;
 
-	lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx));
-	hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx));
+	if (ice_is_primary(hw)) {
+		lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx));
+		hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx));
+	} else {
+		lo = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_L(tmr_idx));
+		hi = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_H(tmr_idx));
+	}
 	incval = (u64)hi << 32 | lo;
 
 	err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, incval);
@@ -2564,37 +2658,15 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 }
 
 /**
- * ice_sb_access_ena_eth56g - Enable SB devices (PHY and others) access
+ * ice_ptp_init_phc_e825 - Perform E825 specific PHC initialization
  * @hw: pointer to HW struct
- * @enable: Enable or disable access
  *
- * Enable sideband devices (PHY and others) access.
- */
-static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable)
-{
-	u32 val = rd32(hw, PF_SB_REM_DEV_CTL);
-
-	if (enable)
-		val |= BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1);
-	else
-		val &= ~(BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1));
-
-	wr32(hw, PF_SB_REM_DEV_CTL, val);
-}
-
-/**
- * ice_ptp_init_phc_eth56g - Perform E82X specific PHC initialization
- * @hw: pointer to HW struct
- *
- * Perform PHC initialization steps specific to E82X devices.
+ * Perform E825-specific PTP hardware clock initialization steps.
  *
- * Return:
- * * %0     - success
- * * %other - failed to initialize CGU
+ * Return: 0 on success, negative error code otherwise.
  */
-static int ice_ptp_init_phc_eth56g(struct ice_hw *hw)
+static int ice_ptp_init_phc_e825(struct ice_hw *hw)
 {
-	ice_sb_access_ena_eth56g(hw, true);
 	/* Initialize the Clock Generation Unit */
 	return ice_init_cgu_e82x(hw);
 }
@@ -2666,59 +2738,21 @@ static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port,
 }
 
 /**
- * ice_is_muxed_topo - detect breakout 2x50G topology for E825C
- * @hw: pointer to the HW struct
- *
- * Return: true if it's 2x50 breakout topology, false otherwise
- */
-static bool ice_is_muxed_topo(struct ice_hw *hw)
-{
-	u8 link_topo;
-	bool mux;
-	u32 val;
-
-	val = rd32(hw, GLGEN_SWITCH_MODE_CONFIG);
-	mux = FIELD_GET(GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M, val);
-	val = rd32(hw, GLGEN_MAC_LINK_TOPO);
-	link_topo = FIELD_GET(GLGEN_MAC_LINK_TOPO_LINK_TOPO_M, val);
-
-	return (mux && link_topo == ICE_LINK_TOPO_UP_TO_2_LINKS);
-}
-
-/**
- * ice_ptp_init_phy_e825c - initialize PHY parameters
+ * ice_ptp_init_phy_e825 - initialize PHY parameters
  * @hw: pointer to the HW struct
  */
-static void ice_ptp_init_phy_e825c(struct ice_hw *hw)
+static void ice_ptp_init_phy_e825(struct ice_hw *hw)
 {
 	struct ice_ptp_hw *ptp = &hw->ptp;
 	struct ice_eth56g_params *params;
-	u8 phy;
 
-	ptp->phy_model = ICE_PHY_ETH56G;
 	params = &ptp->phy.eth56g;
 	params->onestep_ena = false;
 	params->peer_delay = 0;
 	params->sfd_ena = false;
-	params->phy_addr[0] = eth56g_phy_0;
-	params->phy_addr[1] = eth56g_phy_1;
 	params->num_phys = 2;
 	ptp->ports_per_phy = 4;
 	ptp->num_lports = params->num_phys * ptp->ports_per_phy;
-
-	ice_sb_access_ena_eth56g(hw, true);
-	for (phy = 0; phy < params->num_phys; phy++) {
-		u32 phy_rev;
-		int err;
-
-		err = ice_read_phy_eth56g(hw, phy, PHY_REG_REVISION, &phy_rev);
-		if (err || phy_rev != PHY_REVISION_ETH56G) {
-			ptp->phy_model = ICE_PHY_UNSUP;
-			return;
-		}
-	}
-
-	ptp->is_2x50g_muxed_topo = ice_is_muxed_topo(hw);
 }
 
 /* E822 family functions
@@ -2737,10 +2771,9 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
 				  struct ice_sbq_msg_input *msg, u8 port,
 				  u16 offset)
 {
-	int phy_port, phy, quadtype;
+	int phy_port, quadtype;
 
 	phy_port = port % hw->ptp.ports_per_phy;
-	phy = port / hw->ptp.ports_per_phy;
 	quadtype = ICE_GET_QUAD_NUM(port) %
 		   ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy);
 
@@ -2752,12 +2785,7 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
 		msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port);
 	}
 
-	if (phy == 0)
-		msg->dest_dev = rmn_0;
-	else if (phy == 1)
-		msg->dest_dev = rmn_1;
-	else
-		msg->dest_dev = rmn_2;
+	msg->dest_dev = ice_sbq_dev_phy_0;
 }
 
 /**
@@ -3080,7 +3108,7 @@ static int ice_fill_quad_msg_e82x(struct ice_hw *hw,
 	if (quad >= ICE_GET_QUAD_NUM(hw->ptp.num_lports))
 		return -EINVAL;
 
-	msg->dest_dev = rmn_0;
+	msg->dest_dev = ice_sbq_dev_phy_0;
 
 	if (!(quad % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy)))
 		addr = Q_0_BASE + offset;
@@ -3199,7 +3227,8 @@ ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
 	 * lower 8 bits in the low register, and the upper 32 bits in the high
 	 * register.
 	 */
-	*tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | FIELD_PREP(TS_PHY_LOW_M, lo);
+	*tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_40B_LOW_M, lo);
 
 	return 0;
 }
@@ -4772,7 +4801,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold)
  */
 static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp)
 {
-	ptp->phy_model = ICE_PHY_E82X;
 	ptp->num_lports = 8;
 	ptp->ports_per_phy = 8;
 }
@@ -4799,7 +4827,7 @@ static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val)
 	msg.msg_addr_low = lower_16_bits(addr);
 	msg.msg_addr_high = upper_16_bits(addr);
 	msg.opcode = ice_sbq_msg_rd;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 
 	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
 	if (err) {
@@ -4829,7 +4857,7 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val)
 	msg.msg_addr_low = lower_16_bits(addr);
 	msg.msg_addr_high = upper_16_bits(addr);
 	msg.opcode = ice_sbq_msg_wr;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 	msg.data = val;
 
 	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
@@ -4856,33 +4884,46 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val)
 static int
 ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo)
 {
+	struct ice_e810_params *params = &hw->ptp.phy.e810;
+	unsigned long flags;
 	u32 val;
-	u8 i;
+	int err;
+
+	spin_lock_irqsave(&params->atqbal_wq.lock, flags);
+
+	/* Wait for any pending in-progress low latency interrupt */
+	err = wait_event_interruptible_locked_irq(params->atqbal_wq,
+						  !(params->atqbal_flags &
+						    ATQBAL_FLAGS_INTR_IN_PROGRESS));
+	if (err) {
+		spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
+		return err;
+	}
 
 	/* Write TS index to read to the PF register so the FW can read it */
-	val = FIELD_PREP(TS_LL_READ_TS_IDX, idx) | TS_LL_READ_TS;
-	wr32(hw, PF_SB_ATQBAL, val);
+	val = FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | REG_LL_PROXY_H_EXEC;
+	wr32(hw, REG_LL_PROXY_H, val);
 
 	/* Read the register repeatedly until the FW provides us the TS */
-	for (i = TS_LL_READ_RETRIES; i > 0; i--) {
-		val = rd32(hw, PF_SB_ATQBAL);
+	err = read_poll_timeout_atomic(rd32, val,
+				       !FIELD_GET(REG_LL_PROXY_H_EXEC, val), 10,
+				       REG_LL_PROXY_H_TIMEOUT_US, false, hw,
+				       REG_LL_PROXY_H);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n");
+		spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
+		return err;
+	}
 
-		/* When the bit is cleared, the TS is ready in the register */
-		if (!(FIELD_GET(TS_LL_READ_TS, val))) {
-			/* High 8 bit value of the TS is on the bits 16:23 */
-			*hi = FIELD_GET(TS_LL_READ_TS_HIGH, val);
+	/* High 8 bit value of the TS is on the bits 16:23 */
+	*hi = FIELD_GET(REG_LL_PROXY_H_TS_HIGH, val);
 
-			/* Read the low 32 bit value and set the TS valid bit */
-			*lo = rd32(hw, PF_SB_ATQBAH) | TS_VALID;
-			return 0;
-		}
+	/* Read the low 32 bit value and set the TS valid bit */
+	*lo = rd32(hw, REG_LL_PROXY_L) | TS_VALID;
 
-		udelay(10);
-	}
+	spin_unlock_irqrestore(&params->atqbal_wq.lock, flags);
 
-	/* FW failed to provide the TS in time */
-	ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n");
-	return -EINVAL;
+	return 0;
 }
 
 /**
@@ -4953,7 +4994,8 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp)
 	/* For E810 devices, the timestamp is reported with the lower 32 bits
 	 * in the low register, and the upper 8 bits in the high register.
 	 */
-	*tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M);
+	*tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_EXT_40B_LOW_M, lo);
 
 	return 0;
 }
@@ -5016,8 +5058,7 @@ static int ice_ptp_init_phc_e810(struct ice_hw *hw)
 	u8 tmr_idx;
 	int err;
 
-	/* Ensure synchronization delay is zero */
-	wr32(hw, GLTSYN_SYNC_DLAY, 0);
+	ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY);
 
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx),
@@ -5065,6 +5106,55 @@ static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time)
 }
 
 /**
+ * ice_ptp_prep_phy_adj_ll_e810 - Prep PHY ports for a time adjustment
+ * @hw: pointer to HW struct
+ * @adj: adjustment value to program
+ *
+ * Use the low latency firmware interface to program PHY time adjustment to
+ * all PHY ports.
+ *
+ * Return: 0 on success, -EBUSY on timeout
+ */
+static int ice_ptp_prep_phy_adj_ll_e810(struct ice_hw *hw, s32 adj)
+{
+	const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+	struct ice_e810_params *params = &hw->ptp.phy.e810;
+	u32 val;
+	int err;
+
+	spin_lock_irq(&params->atqbal_wq.lock);
+
+	/* Wait for any pending in-progress low latency interrupt */
+	err = wait_event_interruptible_locked_irq(params->atqbal_wq,
+						  !(params->atqbal_flags &
+						    ATQBAL_FLAGS_INTR_IN_PROGRESS));
+	if (err) {
+		spin_unlock_irq(&params->atqbal_wq.lock);
+		return err;
+	}
+
+	wr32(hw, REG_LL_PROXY_L, adj);
+	val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_ADJ) |
+	      FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC;
+	wr32(hw, REG_LL_PROXY_H, val);
+
+	/* Read the register repeatedly until the FW indicates completion */
+	err = read_poll_timeout_atomic(rd32, val,
+				       !FIELD_GET(REG_LL_PROXY_H_EXEC, val),
+				       10, REG_LL_PROXY_H_TIMEOUT_US, false, hw,
+				       REG_LL_PROXY_H);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer adjustment using low latency interface\n");
+		spin_unlock_irq(&params->atqbal_wq.lock);
+		return err;
+	}
+
+	spin_unlock_irq(&params->atqbal_wq.lock);
+
+	return 0;
+}
+
+/**
  * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment
  * @hw: pointer to HW struct
  * @adj: adjustment value to program
@@ -5082,6 +5172,9 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj)
 	u8 tmr_idx;
 	int err;
 
+	if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update)
+		return ice_ptp_prep_phy_adj_ll_e810(hw, adj);
+
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
 	/* Adjustments are represented as signed 2's complement values in
@@ -5105,6 +5198,56 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj)
 }
 
 /**
+ * ice_ptp_prep_phy_incval_ll_e810 - Prep PHY ports increment value change
+ * @hw: pointer to HW struct
+ * @incval: The new 40bit increment value to prepare
+ *
+ * Use the low latency firmware interface to program PHY time increment value
+ * for all PHY ports.
+ *
+ * Return: 0 on success, -EBUSY on timeout
+ */
+static int ice_ptp_prep_phy_incval_ll_e810(struct ice_hw *hw, u64 incval)
+{
+	const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+	struct ice_e810_params *params = &hw->ptp.phy.e810;
+	u32 val;
+	int err;
+
+	spin_lock_irq(&params->atqbal_wq.lock);
+
+	/* Wait for any pending in-progress low latency interrupt */
+	err = wait_event_interruptible_locked_irq(params->atqbal_wq,
+						  !(params->atqbal_flags &
+						    ATQBAL_FLAGS_INTR_IN_PROGRESS));
+	if (err) {
+		spin_unlock_irq(&params->atqbal_wq.lock);
+		return err;
+	}
+
+	wr32(hw, REG_LL_PROXY_L, lower_32_bits(incval));
+	val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_FREQ) |
+	      FIELD_PREP(REG_LL_PROXY_H_TS_HIGH, (u8)upper_32_bits(incval)) |
+	      FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC;
+	wr32(hw, REG_LL_PROXY_H, val);
+
+	/* Read the register repeatedly until the FW indicates completion */
+	err = read_poll_timeout_atomic(rd32, val,
+				       !FIELD_GET(REG_LL_PROXY_H_EXEC, val),
+				       10, REG_LL_PROXY_H_TIMEOUT_US, false, hw,
+				       REG_LL_PROXY_H);
+	if (err) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer increment using low latency interface\n");
+		spin_unlock_irq(&params->atqbal_wq.lock);
+		return err;
+	}
+
+	spin_unlock_irq(&params->atqbal_wq.lock);
+
+	return 0;
+}
+
+/**
  * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change
  * @hw: pointer to HW struct
  * @incval: The new 40bit increment value to prepare
@@ -5119,6 +5262,9 @@ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval)
 	u8 tmr_idx;
 	int err;
 
+	if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update)
+		return ice_ptp_prep_phy_incval_ll_e810(hw, incval);
+
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	low = lower_32_bits(incval);
 	high = upper_32_bits(incval);
@@ -5178,68 +5324,6 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready)
  */
 
 /**
- * ice_get_pca9575_handle
- * @hw: pointer to the hw struct
- * @pca9575_handle: GPIO controller's handle
- *
- * Find and return the GPIO controller's handle in the netlist.
- * When found - the value will be cached in the hw structure and following calls
- * will return cached value
- */
-static int
-ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
-{
-	struct ice_aqc_get_link_topo *cmd;
-	struct ice_aq_desc desc;
-	int status;
-	u8 idx;
-
-	/* If handle was read previously return cached value */
-	if (hw->io_expander_handle) {
-		*pca9575_handle = hw->io_expander_handle;
-		return 0;
-	}
-
-	/* If handle was not detected read it from the netlist */
-	cmd = &desc.params.get_link_topo;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
-
-	/* Set node type to GPIO controller */
-	cmd->addr.topo_params.node_type_ctx =
-		(ICE_AQC_LINK_TOPO_NODE_TYPE_M &
-		 ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL);
-
-#define SW_PCA9575_SFP_TOPO_IDX		2
-#define SW_PCA9575_QSFP_TOPO_IDX	1
-
-	/* Check if the SW IO expander controlling SMA exists in the netlist. */
-	if (hw->device_id == ICE_DEV_ID_E810C_SFP)
-		idx = SW_PCA9575_SFP_TOPO_IDX;
-	else if (hw->device_id == ICE_DEV_ID_E810C_QSFP)
-		idx = SW_PCA9575_QSFP_TOPO_IDX;
-	else
-		return -EOPNOTSUPP;
-
-	cmd->addr.topo_params.index = idx;
-
-	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
-	if (status)
-		return -EOPNOTSUPP;
-
-	/* Verify if we found the right IO expander type */
-	if (desc.params.get_link_topo.node_part_num !=
-		ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
-		return -EOPNOTSUPP;
-
-	/* If present save the handle and return it */
-	hw->io_expander_handle =
-		le16_to_cpu(desc.params.get_link_topo.addr.handle);
-	*pca9575_handle = hw->io_expander_handle;
-
-	return 0;
-}
-
-/**
  * ice_read_sma_ctrl
  * @hw: pointer to the hw struct
  * @data: pointer to data to be read from the GPIO controller
@@ -5304,37 +5388,6 @@ int ice_write_sma_ctrl(struct ice_hw *hw, u8 data)
 }
 
 /**
- * ice_read_pca9575_reg
- * @hw: pointer to the hw struct
- * @offset: GPIO controller register offset
- * @data: pointer to data to be read from the GPIO controller
- *
- * Read the register from the GPIO controller
- */
-int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data)
-{
-	struct ice_aqc_link_topo_addr link_topo;
-	__le16 addr;
-	u16 handle;
-	int err;
-
-	memset(&link_topo, 0, sizeof(link_topo));
-
-	err = ice_get_pca9575_handle(hw, &handle);
-	if (err)
-		return err;
-
-	link_topo.handle = cpu_to_le16(handle);
-	link_topo.topo_params.node_type_ctx =
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M,
-			   ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED);
-
-	addr = cpu_to_le16((u16)offset);
-
-	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
-}
-
-/**
  * ice_ptp_read_sdp_ac - read SDP available connections section from NVM
  * @hw: pointer to the HW struct
  * @entries: returns the SDP available connections section from NVM
@@ -5400,16 +5453,138 @@ exit:
  */
 static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp)
 {
-	ptp->phy_model = ICE_PHY_E810;
+	ptp->num_lports = 8;
+	ptp->ports_per_phy = 4;
+
+	init_waitqueue_head(&ptp->phy.e810.atqbal_wq);
+}
+
+/* E830 functions
+ *
+ * The following functions operate on the E830 series devices.
+ *
+ */
+
+/**
+ * ice_ptp_init_phc_e830 - Perform E830 specific PHC initialization
+ * @hw: pointer to HW struct
+ *
+ * Perform E830-specific PTP hardware clock initialization steps.
+ */
+static void ice_ptp_init_phc_e830(const struct ice_hw *hw)
+{
+	ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY);
+}
+
+/**
+ * ice_ptp_write_direct_incval_e830 - Prep PHY port increment value change
+ * @hw: pointer to HW struct
+ * @incval: The new 40bit increment value to prepare
+ *
+ * Prepare the PHY port for a new increment value by programming the PHC
+ * GLTSYN_INCVAL_L and GLTSYN_INCVAL_H registers. The actual change is
+ * completed by FW automatically.
+ */
+static void ice_ptp_write_direct_incval_e830(const struct ice_hw *hw,
+					     u64 incval)
+{
+	u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	wr32(hw, GLTSYN_INCVAL_L(tmr_idx), lower_32_bits(incval));
+	wr32(hw, GLTSYN_INCVAL_H(tmr_idx), upper_32_bits(incval));
+}
+
+/**
+ * ice_ptp_write_direct_phc_time_e830 - Prepare PHY port with initial time
+ * @hw: Board private structure
+ * @time: Time to initialize the PHY port clock to
+ *
+ * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the
+ * initial clock time. The time will not actually be programmed until the
+ * driver issues an ICE_PTP_INIT_TIME command.
+ *
+ * The time value is the upper 32 bits of the PHY timer, usually in units of
+ * nominal nanoseconds.
+ */
+static void ice_ptp_write_direct_phc_time_e830(const struct ice_hw *hw,
+					       u64 time)
+{
+	u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	wr32(hw, GLTSYN_TIME_0(tmr_idx), 0);
+	wr32(hw, GLTSYN_TIME_L(tmr_idx), lower_32_bits(time));
+	wr32(hw, GLTSYN_TIME_H(tmr_idx), upper_32_bits(time));
+}
+
+/**
+ * ice_ptp_port_cmd_e830 - Prepare all external PHYs for a timer command
+ * @hw: pointer to HW struct
+ * @cmd: Command to be sent to the port
+ *
+ * Prepare the external PHYs connected to this device for a timer sync
+ * command.
+ *
+ * Return: 0 on success, negative error code when PHY write failed
+ */
+static int ice_ptp_port_cmd_e830(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+{
+	u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd);
+
+	return ice_write_phy_reg_e810(hw, E830_ETH_GLTSYN_CMD, val);
+}
+
+/**
+ * ice_read_phy_tstamp_e830 - Read a PHY timestamp out of the external PHY
+ * @hw: pointer to the HW struct
+ * @idx: the timestamp index to read
+ * @tstamp: on return, the 40bit timestamp value
+ *
+ * Read a 40bit timestamp value out of the timestamp block of the external PHY
+ * on the E830 device.
+ */
+static void ice_read_phy_tstamp_e830(const struct ice_hw *hw, u8 idx,
+				     u64 *tstamp)
+{
+	u32 hi, lo;
+
+	hi = rd32(hw, E830_PRTTSYN_TXTIME_H(idx));
+	lo = rd32(hw, E830_PRTTSYN_TXTIME_L(idx));
+
+	/* For E830 devices, the timestamp is reported with the lower 32 bits
+	 * in the low register, and the upper 8 bits in the high register.
+	 */
+	*tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_EXT_40B_LOW_M, lo);
+}
+
+/**
+ * ice_get_phy_tx_tstamp_ready_e830 - Read Tx memory status register
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to read
+ * @tstamp_ready: contents of the Tx memory status register
+ */
+static void ice_get_phy_tx_tstamp_ready_e830(const struct ice_hw *hw, u8 port,
+					     u64 *tstamp_ready)
+{
+	*tstamp_ready = rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_H);
+	*tstamp_ready <<= 32;
+	*tstamp_ready |= rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_L);
+}
+
+/**
+ * ice_ptp_init_phy_e830 - initialize PHY parameters
+ * @ptp: pointer to the PTP HW struct
+ */
+static void ice_ptp_init_phy_e830(struct ice_ptp_hw *ptp)
+{
 	ptp->num_lports = 8;
 	ptp->ports_per_phy = 4;
 }
 
 /* Device agnostic functions
  *
- * The following functions implement shared behavior common to both E822 and
- * E810 devices, possibly calling a device specific implementation where
- * necessary.
+ * The following functions implement shared behavior common to all devices,
+ * possibly calling a device specific implementation where necessary.
  */
 
 /**
@@ -5472,14 +5647,22 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 {
 	struct ice_ptp_hw *ptp = &hw->ptp;
 
-	if (ice_is_e822(hw) || ice_is_e823(hw))
-		ice_ptp_init_phy_e82x(ptp);
-	else if (ice_is_e810(hw))
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		ice_ptp_init_phy_e810(ptp);
-	else if (ice_is_e825c(hw))
-		ice_ptp_init_phy_e825c(hw);
-	else
-		ptp->phy_model = ICE_PHY_UNSUP;
+		break;
+	case ICE_MAC_E830:
+		ice_ptp_init_phy_e830(ptp);
+		break;
+	case ICE_MAC_GENERIC:
+		ice_ptp_init_phy_e82x(ptp);
+		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		ice_ptp_init_phy_e825(hw);
+		break;
+	default:
+		return;
+	}
 }
 
 /**
@@ -5500,11 +5683,11 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port,
 				  enum ice_ptp_tmr_cmd cmd)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_write_port_cmd_eth56g(hw, port, cmd);
-	case ICE_PHY_E82X:
+	switch (hw->mac_type) {
+	case ICE_MAC_GENERIC:
 		return ice_ptp_write_port_cmd_e82x(hw, port, cmd);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_write_port_cmd_eth56g(hw, port, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5565,9 +5748,11 @@ static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	u32 port;
 
 	/* PHY models which can program all ports simultaneously */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_ptp_port_cmd_e810(hw, cmd);
+	case ICE_MAC_E830:
+		return ice_ptp_port_cmd_e830(hw, cmd);
 	default:
 		break;
 	}
@@ -5638,23 +5823,29 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time)
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
 	/* Source timers */
+	/* For E830 we don't need to use shadow registers, its automatic */
+	if (hw->mac_type == ICE_MAC_E830) {
+		ice_ptp_write_direct_phc_time_e830(hw, time);
+		return 0;
+	}
+
 	wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time));
 	wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time));
 	wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0);
 
 	/* PHY timers */
 	/* Fill Rx and Tx ports and send msg to PHY */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_time_eth56g(hw,
-						   (u32)(time & 0xFFFFFFFF));
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_time_eth56g(hw,
+						   (u32)(time & 0xFFFFFFFF));
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5686,20 +5877,26 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval)
 
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
+	/* For E830 we don't need to use shadow registers, its automatic */
+	if (hw->mac_type == ICE_MAC_E830) {
+		ice_ptp_write_direct_incval_e830(hw, incval);
+		return 0;
+	}
+
 	/* Shadow Adjust */
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval));
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval));
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_incval_eth56g(hw, incval);
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_incval_e810(hw, incval);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_incval_e82x(hw, incval);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_incval_eth56g(hw, incval);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5759,16 +5956,19 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0);
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_adj_eth56g(hw, adj);
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_adj_e810(hw, adj);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_E830:
+		/* E830 sync PHYs automatically after setting GLTSYN_SHADJ */
+		return 0;
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_adj_e82x(hw, adj);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_adj_eth56g(hw, adj);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5792,13 +5992,16 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
  */
 int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_read_phy_tstamp_e810(hw, block, idx, tstamp);
-	case ICE_PHY_E82X:
+	case ICE_MAC_E830:
+		ice_read_phy_tstamp_e830(hw, idx, tstamp);
+		return 0;
+	case ICE_MAC_GENERIC:
 		return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5822,13 +6025,13 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
  */
 int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_clear_ptp_tstamp_eth56g(hw, block, idx);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_clear_phy_tstamp_e810(hw, block, idx);
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_clear_phy_tstamp_e82x(hw, block, idx);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_clear_ptp_tstamp_eth56g(hw, block, idx);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5885,14 +6088,14 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx)
  */
 void ice_ptp_reset_ts_memory(struct ice_hw *hw)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		ice_ptp_reset_ts_memory_eth56g(hw);
-		break;
-	case ICE_PHY_E82X:
+	switch (hw->mac_type) {
+	case ICE_MAC_GENERIC:
 		ice_ptp_reset_ts_memory_e82x(hw);
 		break;
-	case ICE_PHY_E810:
+	case ICE_MAC_GENERIC_3K_E825:
+		ice_ptp_reset_ts_memory_eth56g(hw);
+		break;
+	case ICE_MAC_E810:
 	default:
 		return;
 	}
@@ -5914,13 +6117,16 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 	/* Clear event err indications for auxiliary pins */
 	(void)rd32(hw, GLTSYN_STAT(src_idx));
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_init_phc_eth56g(hw);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_ptp_init_phc_e810(hw);
-	case ICE_PHY_E82X:
+	case ICE_MAC_E830:
+		ice_ptp_init_phc_e830(hw);
+		return 0;
+	case ICE_MAC_GENERIC:
 		return ice_ptp_init_phc_e82x(hw);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_init_phc_e825(hw);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5939,17 +6145,19 @@ int ice_ptp_init_phc(struct ice_hw *hw)
  */
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_get_phy_tx_tstamp_ready_eth56g(hw, block,
-							  tstamp_ready);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_get_phy_tx_tstamp_ready_e810(hw, block,
 							tstamp_ready);
-	case ICE_PHY_E82X:
+	case ICE_MAC_E830:
+		ice_get_phy_tx_tstamp_ready_e830(hw, block, tstamp_ready);
+		return 0;
+	case ICE_MAC_GENERIC:
 		return ice_get_phy_tx_tstamp_ready_e82x(hw, block,
 							tstamp_ready);
-		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_get_phy_tx_tstamp_ready_eth56g(hw, block,
+							  tstamp_ready);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 47af7c5c79b8..83f20fa7ace7 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -65,14 +65,14 @@ enum ice_eth56g_link_spd {
 
 /**
  * struct ice_phy_reg_info_eth56g - ETH56G PHY register parameters
- * @base: base address for each PHY block
+ * @base_addr: base address for each PHY block
  * @step: step between PHY lanes
  *
  * Characteristic information for the various PHY register parameters in the
  * ETH56G devices
  */
 struct ice_phy_reg_info_eth56g {
-	u32 base[NUM_ETH56G_PHY_RES];
+	u32 base_addr;
 	u32 step;
 };
 
@@ -80,7 +80,6 @@ struct ice_phy_reg_info_eth56g {
  * struct ice_time_ref_info_e82x
  * @pll_freq: Frequency of PLL that drives timer ticks in Hz
  * @nominal_incval: increment to generate nanoseconds in GLTSYN_TIME_L
- * @pps_delay: propagation delay of the PPS output signal
  *
  * Characteristic information for the various TIME_REF sources possible in the
  * E822 devices
@@ -88,7 +87,6 @@ struct ice_phy_reg_info_eth56g {
 struct ice_time_ref_info_e82x {
 	u64 pll_freq;
 	u64 nominal_incval;
-	u8 pps_delay;
 };
 
 /**
@@ -326,8 +324,7 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD];
  */
 #define ICE_E810_PLL_FREQ		812500000
 #define ICE_PTP_NOMINAL_INCVAL_E810	0x13b13b13bULL
-#define ICE_E810_OUT_PROP_DELAY_NS	1
-#define ICE_E825C_OUT_PROP_DELAY_NS	11
+#define ICE_E810_E830_SYNC_DELAY	0
 
 /* Device agnostic functions */
 u8 ice_get_ptp_src_clock_index(struct ice_hw *hw);
@@ -389,11 +386,6 @@ static inline u64 ice_e82x_nominal_incval(enum ice_time_ref_freq time_ref)
 	return e82x_time_ref[time_ref].nominal_incval;
 }
 
-static inline u64 ice_e82x_pps_delay(enum ice_time_ref_freq time_ref)
-{
-	return e82x_time_ref[time_ref].pps_delay;
-}
-
 /* E822 Vernier calibration functions */
 int ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset);
 int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port);
@@ -404,7 +396,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold);
 /* E810 family functions */
 int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data);
 int ice_write_sma_ctrl(struct ice_hw *hw, u8 data);
-int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data);
 int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries);
 int ice_cgu_get_num_pins(struct ice_hw *hw, bool input);
 enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input);
@@ -432,20 +423,6 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port);
 #define ICE_ETH56G_NOMINAL_THRESH4	0x7777
 #define ICE_ETH56G_NOMINAL_TX_THRESH	0x6
 
-static inline u64 ice_prop_delay(const struct ice_hw *hw)
-{
-	switch (hw->ptp.phy_model) {
-	case ICE_PHY_ETH56G:
-		return ICE_E825C_OUT_PROP_DELAY_NS;
-	case ICE_PHY_E810:
-		return ICE_E810_OUT_PROP_DELAY_NS;
-	case ICE_PHY_E82X:
-		return ice_e82x_pps_delay(ice_e82x_time_ref(hw));
-	default:
-		return 0;
-	}
-}
-
 /**
  * ice_get_base_incval - Get base clock increment value
  * @hw: pointer to the HW struct
@@ -454,23 +431,19 @@ static inline u64 ice_prop_delay(const struct ice_hw *hw)
  */
 static inline u64 ice_get_base_incval(struct ice_hw *hw)
 {
-	switch (hw->ptp.phy_model) {
-	case ICE_PHY_ETH56G:
-		return ICE_ETH56G_NOMINAL_INCVAL;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		return ICE_PTP_NOMINAL_INCVAL_E810;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_e82x_nominal_incval(ice_e82x_time_ref(hw));
+	case ICE_MAC_GENERIC_3K_E825:
+		return ICE_ETH56G_NOMINAL_INCVAL;
 	default:
 		return 0;
 	}
 }
 
-static inline bool ice_is_dual(struct ice_hw *hw)
-{
-	return !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M);
-}
-
 #define PFTSYN_SEM_BYTES	4
 
 #define ICE_PTP_CLOCK_INDEX_0	0x00
@@ -673,28 +646,41 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 /* E810 timer command register */
 #define E810_ETH_GLTSYN_CMD		0x03000344
 
+/* E830 timer command register */
+#define E830_ETH_GLTSYN_CMD		0x00088814
+
+/* E810 PHC time register */
+#define E830_GLTSYN_TIME_L(_tmr_idx)	(0x0008A000 + 0x1000 * (_tmr_idx))
+
 /* Source timer incval macros */
 #define INCVAL_HIGH_M			0xFF
 
-/* Timestamp block macros */
+/* PHY 40b registers macros */
+#define PHY_EXT_40B_LOW_M		GENMASK(31, 0)
+#define PHY_EXT_40B_HIGH_M		GENMASK_ULL(39, 32)
+#define PHY_40B_LOW_M			GENMASK(7, 0)
+#define PHY_40B_HIGH_M			GENMASK_ULL(39, 8)
 #define TS_VALID			BIT(0)
 #define TS_LOW_M			0xFFFFFFFF
 #define TS_HIGH_M			0xFF
 #define TS_HIGH_S			32
 
-#define TS_PHY_LOW_M			0xFF
-#define TS_PHY_HIGH_M			0xFFFFFFFF
-#define TS_PHY_HIGH_S			8
-
 #define BYTES_PER_IDX_ADDR_L_U		8
 #define BYTES_PER_IDX_ADDR_L		4
 
 /* Tx timestamp low latency read definitions */
-#define TS_LL_READ_RETRIES		200
-#define TS_LL_READ_TS_HIGH		GENMASK(23, 16)
-#define TS_LL_READ_TS_IDX		GENMASK(29, 24)
-#define TS_LL_READ_TS_INTR		BIT(30)
-#define TS_LL_READ_TS			BIT(31)
+#define REG_LL_PROXY_H_TIMEOUT_US	2000
+#define REG_LL_PROXY_H_PHY_TMR_CMD_M	GENMASK(7, 6)
+#define REG_LL_PROXY_H_PHY_TMR_CMD_ADJ	0x1
+#define REG_LL_PROXY_H_PHY_TMR_CMD_FREQ	0x2
+#define REG_LL_PROXY_H_TS_HIGH		GENMASK(23, 16)
+#define REG_LL_PROXY_H_PHY_TMR_IDX_M	BIT(24)
+#define REG_LL_PROXY_H_TS_IDX		GENMASK(29, 24)
+#define REG_LL_PROXY_H_TS_INTR_ENA	BIT(30)
+#define REG_LL_PROXY_H_EXEC		BIT(31)
+
+#define REG_LL_PROXY_L			PF_SB_ATQBAH
+#define REG_LL_PROXY_H			PF_SB_ATQBAL
 
 /* Internal PHY timestamp address */
 #define TS_L(a, idx) ((a) + ((idx) * BYTES_PER_IDX_ADDR_L_U))
@@ -789,36 +775,19 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 #define PHY_MAC_XIF_TS_SFD_ENA_M	ICE_M(0x1, 20)
 #define PHY_MAC_XIF_GMII_TS_SEL_M	ICE_M(0x1, 21)
 
-/* GPCS config register */
-#define PHY_GPCS_CONFIG_REG0		0x268
-#define PHY_GPCS_CONFIG_REG0_TX_THR_M	ICE_M(0xF, 24)
-#define PHY_GPCS_BITSLIP		0x5C
-
 #define PHY_TS_INT_CONFIG_THRESHOLD_M	ICE_M(0x3F, 0)
 #define PHY_TS_INT_CONFIG_ENA_M		BIT(6)
 
-/* 1-step PTP config */
-#define PHY_PTP_1STEP_CONFIG		0x270
-#define PHY_PTP_1STEP_T1S_UP64_M	ICE_M(0xF, 4)
-#define PHY_PTP_1STEP_T1S_DELTA_M	ICE_M(0xF, 8)
-#define PHY_PTP_1STEP_PEER_DELAY(_port)	(0x274 + 4 * (_port))
-#define PHY_PTP_1STEP_PD_ADD_PD_M	ICE_M(0x1, 0)
-#define PHY_PTP_1STEP_PD_DELAY_M	ICE_M(0x3fffffff, 1)
-#define PHY_PTP_1STEP_PD_DLY_V_M	ICE_M(0x1, 31)
-
 /* Macros to derive offsets for TimeStampLow and TimeStampHigh */
 #define PHY_TSTAMP_L(x) (((x) * 8) + 0)
 #define PHY_TSTAMP_U(x) (((x) * 8) + 4)
 
-#define PHY_REG_REVISION		0x85000
-
 #define PHY_REG_DESKEW_0		0x94
 #define PHY_REG_DESKEW_0_RLEVEL		GENMASK(6, 0)
 #define PHY_REG_DESKEW_0_RLEVEL_FRAC	GENMASK(9, 7)
 #define PHY_REG_DESKEW_0_RLEVEL_FRAC_W	3
 #define PHY_REG_DESKEW_0_VALID		GENMASK(10, 10)
 
-#define PHY_REG_GPCS_BITSLIP		0x5C
 #define PHY_REG_SD_BIT_SLIP(_port_offset)	(0x29C + 4 * (_port_offset))
 #define PHY_REVISION_ETH56G		0x10200
 #define PHY_VENDOR_TXLANE_THRESH	0x2000C
@@ -838,7 +807,21 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 #define PHY_MAC_BLOCKTIME		0x50
 #define PHY_MAC_MARKERTIME		0x54
 #define PHY_MAC_TX_OFFSET		0x58
+#define PHY_GPCS_BITSLIP		0x5C
 
 #define PHY_PTP_INT_STATUS		0x7FD140
 
+/* ETH56G registers shared per quad */
+/* GPCS config register */
+#define PHY_GPCS_CONFIG_REG0		0x268
+#define PHY_GPCS_CONFIG_REG0_TX_THR_M	GENMASK(27, 24)
+/* 1-step PTP config */
+#define PHY_PTP_1STEP_CONFIG		0x270
+#define PHY_PTP_1STEP_T1S_UP64_M	GENMASK(7, 4)
+#define PHY_PTP_1STEP_T1S_DELTA_M	GENMASK(11, 8)
+#define PHY_PTP_1STEP_PEER_DELAY(_quad_lane)	(0x274 + 4 * (_quad_lane))
+#define PHY_PTP_1STEP_PD_ADD_PD_M	BIT(0)
+#define PHY_PTP_1STEP_PD_DELAY_M	GENMASK(30, 1)
+#define PHY_PTP_1STEP_PD_DLY_V_M	BIT(31)
+
 #endif /* _ICE_PTP_HW_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 970a99a52bf1..cb08746556a6 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -4,7 +4,7 @@
 #include "ice.h"
 #include "ice_eswitch.h"
 #include "devlink/devlink.h"
-#include "devlink/devlink_port.h"
+#include "devlink/port.h"
 #include "ice_sriov.h"
 #include "ice_tc_lib.h"
 #include "ice_dcb_lib.h"
@@ -219,7 +219,8 @@ ice_repr_setup_tc_cls_flower(struct ice_repr *repr,
 {
 	switch (flower->command) {
 	case FLOW_CLS_REPLACE:
-		return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower);
+		return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower,
+					  true);
 	case FLOW_CLS_DESTROY:
 		return ice_del_cls_flower(repr->src_vsi, flower);
 	default:
@@ -336,6 +337,7 @@ void ice_repr_destroy(struct ice_repr *repr)
 static void ice_repr_rem_vf(struct ice_repr *repr)
 {
 	ice_eswitch_decfg_vsi(repr->src_vsi, repr->parent_mac);
+	ice_pass_vf_tx_lldp(repr->src_vsi, true);
 	unregister_netdev(repr->netdev);
 	ice_devlink_destroy_vf_port(repr->vf);
 	ice_virtchnl_set_dflt_ops(repr->vf);
@@ -417,6 +419,10 @@ static int ice_repr_add_vf(struct ice_repr *repr)
 	if (err)
 		goto err_netdev;
 
+	err = ice_drop_vf_tx_lldp(repr->src_vsi, true);
+	if (err)
+		goto err_drop_lldp;
+
 	err = ice_eswitch_cfg_vsi(repr->src_vsi, repr->parent_mac);
 	if (err)
 		goto err_cfg_vsi;
@@ -429,6 +435,8 @@ static int ice_repr_add_vf(struct ice_repr *repr)
 	return 0;
 
 err_cfg_vsi:
+	ice_pass_vf_tx_lldp(repr->src_vsi, true);
+err_drop_lldp:
 	unregister_netdev(repr->netdev);
 err_netdev:
 	ice_devlink_destroy_vf_port(vf);
diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
index 3b0054faf70c..183dd5457d6a 100644
--- a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
@@ -46,13 +46,10 @@ struct ice_sbq_evt_desc {
 	u8 data[24];
 };
 
-enum ice_sbq_msg_dev {
-	eth56g_phy_0	= 0x02,
-	rmn_0		= 0x02,
-	rmn_1		= 0x03,
-	rmn_2		= 0x04,
-	cgu		= 0x06,
-	eth56g_phy_1	= 0x0D,
+enum ice_sbq_dev_id {
+	ice_sbq_dev_phy_0	= 0x02,
+	ice_sbq_dev_cgu		= 0x06,
+	ice_sbq_dev_phy_0_peer	= 0x0D,
 };
 
 enum ice_sbq_msg_opcode {
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 6ca13c5dcb14..d9d09296d1d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -85,6 +85,27 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid)
 }
 
 /**
+ * ice_sched_find_next_vsi_node - find the next node for a given VSI
+ * @vsi_node: VSI support node to start search with
+ *
+ * Return: Next VSI support node, or NULL.
+ *
+ * The function returns a pointer to the next node from the VSI layer
+ * assigned to the given VSI, or NULL if there is no such a node.
+ */
+static struct ice_sched_node *
+ice_sched_find_next_vsi_node(struct ice_sched_node *vsi_node)
+{
+	unsigned int vsi_handle = vsi_node->vsi_handle;
+
+	while ((vsi_node = vsi_node->sibling) != NULL)
+		if (vsi_node->vsi_handle == vsi_handle)
+			break;
+
+	return vsi_node;
+}
+
+/**
  * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd
  * @hw: pointer to the HW struct
  * @cmd_opc: cmd opcode
@@ -1084,8 +1105,10 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 		if (parent->num_children < max_child_nodes) {
 			new_num_nodes = max_child_nodes - parent->num_children;
 		} else {
-			/* This parent is full, try the next sibling */
-			parent = parent->sibling;
+			/* This parent is full,
+			 * try the next available sibling.
+			 */
+			parent = ice_sched_find_next_vsi_node(parent);
 			/* Don't modify the first node TEID memory if the
 			 * first node was added already in the above call.
 			 * Instead send some temp memory for all other
@@ -1528,12 +1551,23 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 	/* get the first queue group node from VSI sub-tree */
 	qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	while (qgrp_node) {
+		struct ice_sched_node *next_vsi_node;
+
 		/* make sure the qgroup node is part of the VSI subtree */
 		if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node))
 			if (qgrp_node->num_children < max_children &&
 			    qgrp_node->owner == owner)
 				break;
 		qgrp_node = qgrp_node->sibling;
+		if (qgrp_node)
+			continue;
+
+		next_vsi_node = ice_sched_find_next_vsi_node(vsi_node);
+		if (!next_vsi_node)
+			break;
+
+		vsi_node = next_vsi_node;
+		qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	}
 
 	/* Select the best queue group */
@@ -1604,16 +1638,16 @@ ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node,
 /**
  * ice_sched_calc_vsi_child_nodes - calculate number of VSI child nodes
  * @hw: pointer to the HW struct
- * @num_qs: number of queues
+ * @num_new_qs: number of new queues that will be added to the tree
  * @num_nodes: num nodes array
  *
  * This function calculates the number of VSI child nodes based on the
  * number of queues.
  */
 static void
-ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes)
+ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_new_qs, u16 *num_nodes)
 {
-	u16 num = num_qs;
+	u16 num = num_new_qs;
 	u8 i, qgl, vsil;
 
 	qgl = ice_sched_get_qgrp_layer(hw);
@@ -1779,7 +1813,11 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle,
 		if (!parent)
 			return -EIO;
 
-		if (i == vsil)
+		/* Do not modify the VSI handle for already existing VSI nodes,
+		 * (if no new VSI node was added to the tree).
+		 * Assign the VSI handle only to newly added VSI nodes.
+		 */
+		if (i == vsil && num_added)
 			parent->vsi_handle = vsi_handle;
 	}
 
@@ -1813,6 +1851,41 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc)
 }
 
 /**
+ * ice_sched_recalc_vsi_support_nodes - recalculate VSI support nodes count
+ * @hw: pointer to the HW struct
+ * @vsi_node: pointer to the leftmost VSI node that needs to be extended
+ * @new_numqs: new number of queues that has to be handled by the VSI
+ * @new_num_nodes: pointer to nodes count table to modify the VSI layer entry
+ *
+ * This function recalculates the number of supported nodes that need to
+ * be added after adding more Tx queues for a given VSI.
+ * The number of new VSI support nodes that shall be added will be saved
+ * to the @new_num_nodes table for the VSI layer.
+ */
+static void
+ice_sched_recalc_vsi_support_nodes(struct ice_hw *hw,
+				   struct ice_sched_node *vsi_node,
+				   unsigned int new_numqs, u16 *new_num_nodes)
+{
+	u32 vsi_nodes_cnt = 1;
+	u32 max_queue_cnt = 1;
+	u32 qgl, vsil;
+
+	qgl = ice_sched_get_qgrp_layer(hw);
+	vsil = ice_sched_get_vsi_layer(hw);
+
+	for (u32 i = vsil; i <= qgl; i++)
+		max_queue_cnt *= hw->max_children[i];
+
+	while ((vsi_node = ice_sched_find_next_vsi_node(vsi_node)) != NULL)
+		vsi_nodes_cnt++;
+
+	if (new_numqs > (max_queue_cnt * vsi_nodes_cnt))
+		new_num_nodes[vsil] = DIV_ROUND_UP(new_numqs, max_queue_cnt) -
+				      vsi_nodes_cnt;
+}
+
+/**
  * ice_sched_update_vsi_child_nodes - update VSI child nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -1863,15 +1936,25 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 			return status;
 	}
 
-	if (new_numqs)
-		ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes);
-	/* Keep the max number of queue configuration all the time. Update the
-	 * tree only if number of queues > previous number of queues. This may
+	ice_sched_recalc_vsi_support_nodes(hw, vsi_node,
+					   new_numqs, new_num_nodes);
+	ice_sched_calc_vsi_child_nodes(hw, new_numqs - prev_numqs,
+				       new_num_nodes);
+
+	/* Never decrease the number of queues in the tree. Update the tree
+	 * only if number of queues > previous number of queues. This may
 	 * leave some extra nodes in the tree if number of queues < previous
 	 * number but that wouldn't harm anything. Removing those extra nodes
 	 * may complicate the code if those nodes are part of SRL or
 	 * individually rate limited.
+	 * Also, add the required VSI support nodes if the existing ones cannot
+	 * handle the requested new number of queues.
 	 */
+	status = ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node,
+						 new_num_nodes);
+	if (status)
+		return status;
+
 	status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node,
 					       new_num_nodes, owner);
 	if (status)
@@ -2013,6 +2096,58 @@ static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node)
 }
 
 /**
+ * ice_sched_rm_vsi_subtree - remove all nodes assigned to a given VSI
+ * @pi: port information structure
+ * @vsi_node: pointer to the leftmost node of the VSI to be removed
+ * @owner: LAN or RDMA
+ * @tc: TC number
+ *
+ * Return: Zero in case of success, or -EBUSY if the VSI has leaf nodes in TC.
+ *
+ * This function removes all the VSI support nodes associated with a given VSI
+ * and its LAN or RDMA children nodes from the scheduler tree.
+ */
+static int
+ice_sched_rm_vsi_subtree(struct ice_port_info *pi,
+			 struct ice_sched_node *vsi_node, u8 owner, u8 tc)
+{
+	u16 vsi_handle = vsi_node->vsi_handle;
+	bool all_vsi_nodes_removed = true;
+	int j = 0;
+
+	while (vsi_node) {
+		struct ice_sched_node *next_vsi_node;
+
+		if (ice_sched_is_leaf_node_present(vsi_node)) {
+			ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", tc);
+			return -EBUSY;
+		}
+		while (j < vsi_node->num_children) {
+			if (vsi_node->children[j]->owner == owner)
+				ice_free_sched_node(pi, vsi_node->children[j]);
+			else
+				j++;
+		}
+
+		next_vsi_node = ice_sched_find_next_vsi_node(vsi_node);
+
+		/* remove the VSI if it has no children */
+		if (!vsi_node->num_children)
+			ice_free_sched_node(pi, vsi_node);
+		else
+			all_vsi_nodes_removed = false;
+
+		vsi_node = next_vsi_node;
+	}
+
+	/* clean up aggregator related VSI info if any */
+	if (all_vsi_nodes_removed)
+		ice_sched_rm_agg_vsi_info(pi, vsi_handle);
+
+	return 0;
+}
+
+/**
  * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -2038,7 +2173,6 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 
 	ice_for_each_traffic_class(i) {
 		struct ice_sched_node *vsi_node, *tc_node;
-		u8 j = 0;
 
 		tc_node = ice_sched_get_tc_node(pi, i);
 		if (!tc_node)
@@ -2048,31 +2182,12 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 		if (!vsi_node)
 			continue;
 
-		if (ice_sched_is_leaf_node_present(vsi_node)) {
-			ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", i);
-			status = -EBUSY;
+		status = ice_sched_rm_vsi_subtree(pi, vsi_node, owner, i);
+		if (status)
 			goto exit_sched_rm_vsi_cfg;
-		}
-		while (j < vsi_node->num_children) {
-			if (vsi_node->children[j]->owner == owner) {
-				ice_free_sched_node(pi, vsi_node->children[j]);
 
-				/* reset the counter again since the num
-				 * children will be updated after node removal
-				 */
-				j = 0;
-			} else {
-				j++;
-			}
-		}
-		/* remove the VSI if it has no children */
-		if (!vsi_node->num_children) {
-			ice_free_sched_node(pi, vsi_node);
-			vsi_ctx->sched.vsi_node[i] = NULL;
+		vsi_ctx->sched.vsi_node[i] = NULL;
 
-			/* clean up aggregator related VSI info if any */
-			ice_sched_rm_agg_vsi_info(pi, vsi_handle);
-		}
 		if (owner == ICE_SCHED_NODE_OWNER_LAN)
 			vsi_ctx->sched.max_lanq[i] = 0;
 		else
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
index 75d7147e1c01..1a2c94375ca7 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -5,8 +5,8 @@
 #include "ice_txrx.h"
 #include "ice_fltr.h"
 #include "ice_sf_eth.h"
-#include "devlink/devlink_port.h"
 #include "devlink/devlink.h"
+#include "devlink/port.h"
 
 static const struct net_device_ops ice_sf_netdev_ops = {
 	.ndo_open = ice_open,
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index b83f99c01d91..0e4dc1a5cff0 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf)
 
 	hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) {
 		hash_del_rcu(&vf->entry);
+		ice_deinitialize_vf_entry(vf);
 		ice_put_vf(vf);
 	}
 }
@@ -62,6 +63,7 @@ static void ice_free_vf_res(struct ice_vf *vf)
 	if (vf->lan_vsi_idx != ICE_NO_VSI) {
 		ice_vf_vsi_release(vf);
 		vf->num_mac = 0;
+		vf->num_mac_lldp = 0;
 	}
 
 	last_vector_idx = vf->first_vector_idx + vf->num_msix - 1;
@@ -123,27 +125,6 @@ static void ice_dis_vf_mappings(struct ice_vf *vf)
 }
 
 /**
- * ice_sriov_free_msix_res - Reset/free any used MSIX resources
- * @pf: pointer to the PF structure
- *
- * Since no MSIX entries are taken from the pf->irq_tracker then just clear
- * the pf->sriov_base_vector.
- *
- * Returns 0 on success, and -EINVAL on error.
- */
-static int ice_sriov_free_msix_res(struct ice_pf *pf)
-{
-	if (!pf)
-		return -EINVAL;
-
-	bitmap_free(pf->sriov_irq_bm);
-	pf->sriov_irq_size = 0;
-	pf->sriov_base_vector = 0;
-
-	return 0;
-}
-
-/**
  * ice_free_vfs - Free all VFs
  * @pf: pointer to the PF structure
  */
@@ -177,6 +158,7 @@ void ice_free_vfs(struct ice_pf *pf)
 
 		ice_eswitch_detach_vf(pf, vf);
 		ice_dis_vf_qs(vf);
+		ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix);
 
 		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
 			/* disable VF qp mappings and set VF disable state */
@@ -193,16 +175,9 @@ void ice_free_vfs(struct ice_pf *pf)
 			wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
 		}
 
-		/* clear malicious info since the VF is getting released */
-		if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
-			list_del(&vf->mbx_info.list_entry);
-
 		mutex_unlock(&vf->cfg_lock);
 	}
 
-	if (ice_sriov_free_msix_res(pf))
-		dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n");
-
 	vfs->num_qps_per = 0;
 	ice_free_vf_entries(pf);
 
@@ -372,40 +347,6 @@ void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
 }
 
 /**
- * ice_sriov_set_msix_res - Set any used MSIX resources
- * @pf: pointer to PF structure
- * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs
- *
- * This function allows SR-IOV resources to be taken from the end of the PF's
- * allowed HW MSIX vectors so that the irq_tracker will not be affected. We
- * just set the pf->sriov_base_vector and return success.
- *
- * If there are not enough resources available, return an error. This should
- * always be caught by ice_set_per_vf_res().
- *
- * Return 0 on success, and -EINVAL when there are not enough MSIX vectors
- * in the PF's space available for SR-IOV.
- */
-static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
-{
-	u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
-	int vectors_used = ice_get_max_used_msix_vector(pf);
-	int sriov_base_vector;
-
-	sriov_base_vector = total_vectors - num_msix_needed;
-
-	/* make sure we only grab irq_tracker entries from the list end and
-	 * that we have enough available MSIX vectors
-	 */
-	if (sriov_base_vector < vectors_used)
-		return -EINVAL;
-
-	pf->sriov_base_vector = sriov_base_vector;
-
-	return 0;
-}
-
-/**
  * ice_set_per_vf_res - check if vectors and queues are available
  * @pf: pointer to the PF structure
  * @num_vfs: the number of SR-IOV VFs being configured
@@ -429,11 +370,9 @@ static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
  */
 static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 {
-	int vectors_used = ice_get_max_used_msix_vector(pf);
 	u16 num_msix_per_vf, num_txq, num_rxq, avail_qs;
 	int msix_avail_per_vf, msix_avail_for_sriov;
 	struct device *dev = ice_pf_to_dev(pf);
-	int err;
 
 	lockdep_assert_held(&pf->vfs.table_lock);
 
@@ -441,8 +380,7 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 		return -EINVAL;
 
 	/* determine MSI-X resources per VF */
-	msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors -
-		vectors_used;
+	msix_avail_for_sriov = pf->virt_irq_tracker.num_entries;
 	msix_avail_per_vf = msix_avail_for_sriov / num_vfs;
 	if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) {
 		num_msix_per_vf = ICE_NUM_VF_MSIX_MED;
@@ -481,13 +419,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 		return -ENOSPC;
 	}
 
-	err = ice_sriov_set_msix_res(pf, num_msix_per_vf * num_vfs);
-	if (err) {
-		dev_err(dev, "Unable to set MSI-X resources for %d VFs, err %d\n",
-			num_vfs, err);
-		return err;
-	}
-
 	/* only allow equal Tx/Rx queue count (i.e. queue pairs) */
 	pf->vfs.num_qps_per = min_t(int, num_txq, num_rxq);
 	pf->vfs.num_msix_per = num_msix_per_vf;
@@ -498,52 +429,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 }
 
 /**
- * ice_sriov_get_irqs - get irqs for SR-IOV usacase
- * @pf: pointer to PF structure
- * @needed: number of irqs to get
- *
- * This returns the first MSI-X vector index in PF space that is used by this
- * VF. This index is used when accessing PF relative registers such as
- * GLINT_VECT2FUNC and GLINT_DYN_CTL.
- * This will always be the OICR index in the AVF driver so any functionality
- * using vf->first_vector_idx for queue configuration_id: id of VF which will
- * use this irqs
- *
- * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are
- * allocated from the end of global irq index. First bit in sriov_irq_bm means
- * last irq index etc. It simplifies extension of SRIOV vectors.
- * They will be always located from sriov_base_vector to the last irq
- * index. While increasing/decreasing sriov_base_vector can be moved.
- */
-static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed)
-{
-	int res = bitmap_find_next_zero_area(pf->sriov_irq_bm,
-					     pf->sriov_irq_size, 0, needed, 0);
-	/* conversion from number in bitmap to global irq index */
-	int index = pf->sriov_irq_size - res - needed;
-
-	if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector)
-		return -ENOENT;
-
-	bitmap_set(pf->sriov_irq_bm, res, needed);
-	return index;
-}
-
-/**
- * ice_sriov_free_irqs - free irqs used by the VF
- * @pf: pointer to PF structure
- * @vf: pointer to VF structure
- */
-static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf)
-{
-	/* Move back from first vector index to first index in bitmap */
-	int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix;
-
-	bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix);
-	vf->first_vector_idx = 0;
-}
-
-/**
  * ice_init_vf_vsi_res - initialize/setup VF VSI resources
  * @vf: VF to initialize/setup the VSI for
  *
@@ -556,7 +441,7 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf)
 	struct ice_vsi *vsi;
 	int err;
 
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0)
 		return -ENOMEM;
 
@@ -856,16 +741,10 @@ err_free_entries:
  */
 static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 {
-	int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	int ret;
 
-	pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL);
-	if (!pf->sriov_irq_bm)
-		return -ENOMEM;
-	pf->sriov_irq_size = total_vectors;
-
 	/* Disable global interrupt 0 so we don't try to handle the VFLR. */
 	wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index),
 	     ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
@@ -918,7 +797,6 @@ err_unroll_intr:
 	/* rearm interrupts here */
 	ice_irq_dynamic_ena(hw, NULL, NULL);
 	clear_bit(ICE_OICR_INTR_DIS, pf->state);
-	bitmap_free(pf->sriov_irq_bm);
 	return ret;
 }
 
@@ -992,16 +870,7 @@ u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev)
 {
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 
-	return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf);
-}
-
-static int ice_sriov_move_base_vector(struct ice_pf *pf, int move)
-{
-	if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf))
-		return -ENOMEM;
-
-	pf->sriov_base_vector -= move;
-	return 0;
+	return pf->virt_irq_tracker.num_entries;
 }
 
 static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
@@ -1020,7 +889,8 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
 			continue;
 
 		ice_dis_vf_mappings(tmp_vf);
-		ice_sriov_free_irqs(pf, tmp_vf);
+		ice_virt_free_irqs(pf, tmp_vf->first_vector_idx,
+				   tmp_vf->num_msix);
 
 		vf_ids[to_remap] = tmp_vf->vf_id;
 		to_remap += 1;
@@ -1032,7 +902,7 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
 			continue;
 
 		tmp_vf->first_vector_idx =
-			ice_sriov_get_irqs(pf, tmp_vf->num_msix);
+			ice_virt_get_irqs(pf, tmp_vf->num_msix);
 		/* there is no need to rebuild VSI as we are only changing the
 		 * vector indexes not amount of MSI-X or queues
 		 */
@@ -1105,20 +975,15 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	prev_msix = vf->num_msix;
 	prev_queues = vf->num_vf_qs;
 
-	if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) {
-		ice_put_vf(vf);
-		return -ENOSPC;
-	}
-
 	ice_dis_vf_mappings(vf);
-	ice_sriov_free_irqs(pf, vf);
+	ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix);
 
 	/* Remap all VFs beside the one is now configured */
 	ice_sriov_remap_vectors(pf, vf->vf_id);
 
 	vf->num_msix = msix_vec_count;
 	vf->num_vf_qs = queues;
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0)
 		goto unroll;
 
@@ -1147,7 +1012,8 @@ unroll:
 
 	vf->num_msix = prev_msix;
 	vf->num_vf_qs = prev_queues;
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0) {
 		ice_put_vf(vf);
 		return -EINVAL;
@@ -1537,6 +1403,9 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted)
 
 	mutex_lock(&vf->cfg_lock);
 
+	while (!trusted && vf->num_mac_lldp)
+		ice_vf_update_mac_lldp_num(vf, ice_get_vf_vsi(vf), false);
+
 	vf->trusted = trusted;
 	ice_reset_vf(vf, ICE_VF_RESET_NOTIFY);
 	dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n",
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 0e740342e294..9d9a7edd3618 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -3146,7 +3146,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 		u16 vsi_handle_arr[2];
 
 		/* A rule already exists with the new VSI being added */
-		if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id)
+		if (cur_fltr->vsi_handle == new_fltr->vsi_handle)
 			return -EEXIST;
 
 		vsi_handle_arr[0] = cur_fltr->vsi_handle;
@@ -4784,7 +4784,8 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts,
 			 */
 			if (found && recp[i].tun_type == rinfo->tun_type &&
 			    recp[i].need_pass_l2 == rinfo->need_pass_l2 &&
-			    recp[i].allow_pass_l2 == rinfo->allow_pass_l2)
+			    recp[i].allow_pass_l2 == rinfo->allow_pass_l2 &&
+			    recp[i].priority == rinfo->priority)
 				return i; /* Return the recipe ID */
 		}
 	}
@@ -5977,7 +5978,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw,
 
 		/* A rule already exists with the new VSI being added */
 		if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
-			return 0;
+			return -EEXIST;
 
 		/* Update the previously created VSI list set with
 		 * the new VSI ID passed in
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index ea39b999a0d0..fb9ea7f8ef44 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -12,14 +12,11 @@
 /**
  * ice_tc_count_lkups - determine lookup count for switch filter
  * @flags: TC-flower flags
- * @headers: Pointer to TC flower filter header structure
  * @fltr: Pointer to outer TC filter structure
  *
- * Determine lookup count based on TC flower input for switch filter.
+ * Return: lookup count based on TC flower input for a switch filter.
  */
-static int
-ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers,
-		   struct ice_tc_flower_fltr *fltr)
+static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_fltr *fltr)
 {
 	int lkups_cnt = 1; /* 0th lookup is metadata */
 
@@ -684,26 +681,26 @@ static int ice_tc_setup_action(struct net_device *filter_dev,
 	fltr->action.fltr_act = action;
 
 	if (ice_is_port_repr_netdev(filter_dev) &&
-	    ice_is_port_repr_netdev(target_dev)) {
+	    ice_is_port_repr_netdev(target_dev) &&
+	    fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
 		repr = ice_netdev_to_repr(target_dev);
 
 		fltr->dest_vsi = repr->src_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
 	} else if (ice_is_port_repr_netdev(filter_dev) &&
-		   ice_tc_is_dev_uplink(target_dev)) {
+		   ice_tc_is_dev_uplink(target_dev) &&
+		   fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
 		repr = ice_netdev_to_repr(filter_dev);
 
 		fltr->dest_vsi = repr->src_vsi->back->eswitch.uplink_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
 	} else if (ice_tc_is_dev_uplink(filter_dev) &&
-		   ice_is_port_repr_netdev(target_dev)) {
+		   ice_is_port_repr_netdev(target_dev) &&
+		   fltr->direction == ICE_ESWITCH_FLTR_INGRESS) {
 		repr = ice_netdev_to_repr(target_dev);
 
 		fltr->dest_vsi = repr->src_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
 	} else {
 		NL_SET_ERR_MSG_MOD(fltr->extack,
-				   "Unsupported netdevice in switchdev mode");
+				   "The action is not supported for this netdevice");
 		return -EINVAL;
 	}
 
@@ -716,13 +713,11 @@ ice_tc_setup_drop_action(struct net_device *filter_dev,
 {
 	fltr->action.fltr_act = ICE_DROP_PACKET;
 
-	if (ice_is_port_repr_netdev(filter_dev)) {
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
-	} else if (ice_tc_is_dev_uplink(filter_dev)) {
-		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
-	} else {
+	if (!ice_tc_is_dev_uplink(filter_dev) &&
+	    !(ice_is_port_repr_netdev(filter_dev) &&
+	      fltr->direction == ICE_ESWITCH_FLTR_INGRESS)) {
 		NL_SET_ERR_MSG_MOD(fltr->extack,
-				   "Unsupported netdevice in switchdev mode");
+				   "The action is not supported for this netdevice");
 		return -EINVAL;
 	}
 
@@ -767,10 +762,157 @@ static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
 	return 0;
 }
 
+static bool ice_is_fltr_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	return fltr->outer_headers.l2_key.n_proto == htons(ETH_P_LLDP);
+}
+
+static bool ice_is_fltr_pf_tx_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	struct ice_vsi *vsi = fltr->src_vsi, *uplink;
+
+	if (!ice_is_switchdev_running(vsi->back))
+		return false;
+
+	uplink = vsi->back->eswitch.uplink_vsi;
+	return vsi == uplink && fltr->action.fltr_act == ICE_DROP_PACKET &&
+	       ice_is_fltr_lldp(fltr) &&
+	       fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+	       fltr->flags == ICE_TC_FLWR_FIELD_ETH_TYPE_ID;
+}
+
+static bool ice_is_fltr_vf_tx_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	struct ice_vsi *vsi = fltr->src_vsi, *uplink;
+
+	uplink = vsi->back->eswitch.uplink_vsi;
+	return fltr->src_vsi->type == ICE_VSI_VF && ice_is_fltr_lldp(fltr) &&
+	       fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+	       fltr->dest_vsi == uplink;
+}
+
+static struct ice_tc_flower_fltr *
+ice_find_pf_tx_lldp_fltr(struct ice_pf *pf)
+{
+	struct ice_tc_flower_fltr *fltr;
+
+	hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node)
+		if (ice_is_fltr_pf_tx_lldp(fltr))
+			return fltr;
+
+	return NULL;
+}
+
+static bool ice_any_vf_lldp_tx_ena(struct ice_pf *pf)
+{
+	struct ice_vf *vf;
+	unsigned int bkt;
+
+	ice_for_each_vf(pf, bkt, vf)
+		if (vf->lldp_tx_ena)
+			return true;
+
+	return false;
+}
+
+int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit)
+{
+	struct ice_rule_query_data remove_entry = {
+		.rid = vsi->vf->lldp_recipe_id,
+		.rule_id = vsi->vf->lldp_rule_id,
+		.vsi_handle = vsi->idx,
+	};
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	if (vsi->vf->lldp_tx_ena)
+		return 0;
+
+	if (!deinit && !ice_find_pf_tx_lldp_fltr(vsi->back))
+		return -EINVAL;
+
+	if (!deinit && ice_any_vf_lldp_tx_ena(pf))
+		return -EINVAL;
+
+	err = ice_rem_adv_rule_by_id(&pf->hw, &remove_entry);
+	if (!err)
+		vsi->vf->lldp_tx_ena = true;
+
+	return err;
+}
+
+int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init)
+{
+	struct ice_rule_query_data rule_added;
+	struct ice_adv_rule_info rinfo = {
+		.priority = 7,
+		.src_vsi = vsi->idx,
+		.sw_act = {
+			.src = vsi->idx,
+			.flag = ICE_FLTR_TX,
+			.fltr_act = ICE_DROP_PACKET,
+			.vsi_handle = vsi->idx,
+		},
+		.flags_info.act_valid = true,
+	};
+	struct ice_adv_lkup_elem list[3];
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	if (!init && !vsi->vf->lldp_tx_ena)
+		return 0;
+
+	memset(list, 0, sizeof(list));
+	ice_rule_add_direction_metadata(&list[0]);
+	ice_rule_add_src_vsi_metadata(&list[1]);
+	list[2].type = ICE_ETYPE_OL;
+	list[2].h_u.ethertype.ethtype_id = htons(ETH_P_LLDP);
+	list[2].m_u.ethertype.ethtype_id = htons(0xFFFF);
+
+	err = ice_add_adv_rule(&pf->hw, list, ARRAY_SIZE(list), &rinfo,
+			       &rule_added);
+	if (err) {
+		dev_err(&pf->pdev->dev,
+			"Failed to add an LLDP rule to VSI 0x%X: %d\n",
+			vsi->idx, err);
+	} else {
+		vsi->vf->lldp_recipe_id = rule_added.rid;
+		vsi->vf->lldp_rule_id = rule_added.rule_id;
+		vsi->vf->lldp_tx_ena = false;
+	}
+
+	return err;
+}
+
+static void ice_handle_add_pf_lldp_drop_rule(struct ice_vsi *vsi)
+{
+	struct ice_tc_flower_fltr *fltr;
+	struct ice_pf *pf = vsi->back;
+
+	hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) {
+		if (!ice_is_fltr_vf_tx_lldp(fltr))
+			continue;
+		ice_pass_vf_tx_lldp(fltr->src_vsi, true);
+		break;
+	}
+}
+
+static void ice_handle_del_pf_lldp_drop_rule(struct ice_pf *pf)
+{
+	int i;
+
+	/* Make the VF LLDP fwd to uplink rule dormant */
+	ice_for_each_vsi(pf, i) {
+		struct ice_vsi *vf_vsi = pf->vsi[i];
+
+		if (vf_vsi && vf_vsi->type == ICE_VSI_VF)
+			ice_drop_vf_tx_lldp(vf_vsi, false);
+	}
+}
+
 static int
 ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 {
-	struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers;
 	struct ice_adv_rule_info rule_info = { 0 };
 	struct ice_rule_query_data rule_added;
 	struct ice_hw *hw = &vsi->back->hw;
@@ -785,7 +927,10 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		return -EOPNOTSUPP;
 	}
 
-	lkups_cnt = ice_tc_count_lkups(flags, headers, fltr);
+	if (ice_is_fltr_vf_tx_lldp(fltr))
+		return ice_pass_vf_tx_lldp(vsi, false);
+
+	lkups_cnt = ice_tc_count_lkups(flags, fltr);
 	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
 	if (!list)
 		return -ENOMEM;
@@ -814,6 +959,11 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		rule_info.sw_act.src = hw->pf_id;
 		rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
 	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+		   !fltr->dest_vsi && vsi == vsi->back->eswitch.uplink_vsi) {
+		/* PF to Uplink */
+		rule_info.sw_act.flag |= ICE_FLTR_TX;
+		rule_info.sw_act.src = vsi->idx;
+	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
 		   fltr->dest_vsi == vsi->back->eswitch.uplink_vsi) {
 		/* VF to Uplink */
 		rule_info.sw_act.flag |= ICE_FLTR_TX;
@@ -846,11 +996,17 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because it already exist");
 		ret = -EINVAL;
 		goto exit;
+	} else if (ret == -ENOSPC) {
+		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter: insufficient space available.");
+		goto exit;
 	} else if (ret) {
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter due to error");
 		goto exit;
 	}
 
+	if (ice_is_fltr_pf_tx_lldp(fltr))
+		ice_handle_add_pf_lldp_drop_rule(vsi);
+
 	/* store the output params, which are needed later for removing
 	 * advanced switch filter
 	 */
@@ -985,7 +1141,6 @@ static int
 ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			   struct ice_tc_flower_fltr *tc_fltr)
 {
-	struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers;
 	struct ice_adv_rule_info rule_info = {0};
 	struct ice_rule_query_data rule_added;
 	struct ice_adv_lkup_elem *list;
@@ -1021,7 +1176,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			return PTR_ERR(dest_vsi);
 	}
 
-	lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr);
+	lkups_cnt = ice_tc_count_lkups(flags, tc_fltr);
 	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
 	if (!list)
 		return -ENOMEM;
@@ -1056,8 +1211,13 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			tc_fltr->action.fwd.q.hw_queue, lkups_cnt);
 		break;
 	case ICE_DROP_PACKET:
-		rule_info.sw_act.flag |= ICE_FLTR_RX;
-		rule_info.sw_act.src = hw->pf_id;
+		if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
+			rule_info.sw_act.flag |= ICE_FLTR_TX;
+			rule_info.sw_act.src = vsi->idx;
+		} else {
+			rule_info.sw_act.flag |= ICE_FLTR_RX;
+			rule_info.sw_act.src = hw->pf_id;
+		}
 		rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI;
 		break;
 	default:
@@ -1071,6 +1231,10 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 				   "Unable to add filter because it already exist");
 		ret = -EINVAL;
 		goto exit;
+	} else if (ret == -ENOSPC) {
+		NL_SET_ERR_MSG_MOD(tc_fltr->extack,
+				   "Unable to add filter: insufficient space available.");
+		goto exit;
 	} else if (ret) {
 		NL_SET_ERR_MSG_MOD(tc_fltr->extack,
 				   "Unable to add filter due to error");
@@ -1463,11 +1627,16 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule,
  * @filter_dev: Pointer to device on which filter is being added
  * @f: Pointer to struct flow_cls_offload
  * @fltr: Pointer to filter structure
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was parsed successfully, -EINVAL if the flower
+ *	   cannot be parsed, -EOPNOTSUPP if such filter cannot be configured
+ *	   for the given VSI.
  */
 static int
 ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 		     struct flow_cls_offload *f,
-		     struct ice_tc_flower_fltr *fltr)
+		     struct ice_tc_flower_fltr *fltr, bool ingress)
 {
 	struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers;
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
@@ -1551,6 +1720,20 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 			fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID;
 		}
 
+		if (!ingress) {
+			bool switchdev =
+				ice_is_eswitch_mode_switchdev(vsi->back);
+
+			if (switchdev != (n_proto_key == ETH_P_LLDP)) {
+				NL_SET_ERR_MSG_FMT_MOD(fltr->extack,
+						       "%sLLDP filtering is not supported on egress in %s mode",
+						       switchdev ? "Non-" : "",
+						       switchdev ? "switchdev" :
+								   "legacy");
+				return -EOPNOTSUPP;
+			}
+		}
+
 		headers->l2_key.n_proto = cpu_to_be16(n_proto_key);
 		headers->l2_mask.n_proto = cpu_to_be16(n_proto_mask);
 		headers->l3_key.ip_proto = match.key->ip_proto;
@@ -1726,6 +1909,14 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 			return -EINVAL;
 		}
 	}
+
+	/* Ingress filter on representor results in an egress filter in HW
+	 * and vice versa
+	 */
+	ingress = ice_is_port_repr_netdev(filter_dev) ? !ingress : ingress;
+	fltr->direction = ingress ? ICE_ESWITCH_FLTR_INGRESS :
+				    ICE_ESWITCH_FLTR_EGRESS;
+
 	return 0;
 }
 
@@ -1939,6 +2130,12 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 	struct ice_pf *pf = vsi->back;
 	int err;
 
+	if (ice_is_fltr_pf_tx_lldp(fltr))
+		ice_handle_del_pf_lldp_drop_rule(pf);
+
+	if (ice_is_fltr_vf_tx_lldp(fltr))
+		return ice_drop_vf_tx_lldp(vsi, false);
+
 	rule_rem.rid = fltr->rid;
 	rule_rem.rule_id = fltr->rule_id;
 	rule_rem.vsi_handle = fltr->dest_vsi_handle;
@@ -1975,14 +2172,18 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
  * @vsi: Pointer to VSI
  * @f: Pointer to flower offload structure
  * @__fltr: Pointer to struct ice_tc_flower_fltr
+ * @ingress: if the rule is added to an ingress block
  *
  * This function parses TC-flower input fields, parses action,
  * and adds a filter.
+ *
+ * Return: 0 if the filter was successfully added,
+ *	   negative error code otherwise.
  */
 static int
 ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi,
 		struct flow_cls_offload *f,
-		struct ice_tc_flower_fltr **__fltr)
+		struct ice_tc_flower_fltr **__fltr, bool ingress)
 {
 	struct ice_tc_flower_fltr *fltr;
 	int err;
@@ -1999,7 +2200,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi,
 	fltr->src_vsi = vsi;
 	INIT_HLIST_NODE(&fltr->tc_flower_node);
 
-	err = ice_parse_cls_flower(netdev, vsi, f, fltr);
+	err = ice_parse_cls_flower(netdev, vsi, f, fltr, ingress);
 	if (err < 0)
 		goto err;
 
@@ -2042,10 +2243,13 @@ ice_find_tc_flower_fltr(struct ice_pf *pf, unsigned long cookie)
  * @netdev: Pointer to filter device
  * @vsi: Pointer to VSI
  * @cls_flower: Pointer to flower offload structure
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was successfully added,
+ *	   negative error code otherwise.
  */
-int
-ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
-		   struct flow_cls_offload *cls_flower)
+int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower, bool ingress)
 {
 	struct netlink_ext_ack *extack = cls_flower->common.extack;
 	struct net_device *vsi_netdev = vsi->netdev;
@@ -2080,7 +2284,7 @@ ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
 	}
 
 	/* prep and add TC-flower filter in HW */
-	err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr);
+	err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr, ingress);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index d84f153517ec..8a3ab2f22af9 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -211,13 +211,14 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf)
 }
 
 struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue);
-int
-ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
-		   struct flow_cls_offload *cls_flower);
-int
-ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower);
+int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower, bool ingress);
+int ice_del_cls_flower(struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower);
 void ice_replay_tc_fltrs(struct ice_pf *pf);
 bool ice_is_tunnel_supported(struct net_device *dev);
+int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init);
+int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit);
 
 static inline bool ice_is_forward_action(enum ice_sw_fwd_act_type fltr_act)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 5d2d7736fd5f..0e5107fe62ad 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -527,15 +527,14 @@ err:
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
- * @rx_buf: Rx buffer to store the XDP action
  * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
-static void
+static u32
 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
-	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
+	    union ice_32b_rx_flex_desc *eop_desc)
 {
 	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
@@ -574,7 +573,7 @@ out_failure:
 		ret = ICE_XDP_CONSUMED;
 	}
 exit:
-	ice_set_rx_bufs_act(xdp, rx_ring, ret);
+	return ret;
 }
 
 /**
@@ -860,10 +859,8 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 		xdp_buff_set_frags_flag(xdp);
 	}
 
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
+	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS))
 		return -ENOMEM;
-	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
@@ -924,7 +921,6 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 	struct ice_rx_buf *rx_buf;
 
 	rx_buf = &rx_ring->rx_buf[ntc];
-	rx_buf->pgcnt = page_count(rx_buf->page);
 	prefetchw(rx_buf->page);
 
 	if (!size)
@@ -941,6 +937,31 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 }
 
 /**
+ * ice_get_pgcnts - grab page_count() for gathered fragments
+ * @rx_ring: Rx descriptor ring to store the page counts on
+ *
+ * This function is intended to be called right before running XDP
+ * program so that the page recycling mechanism will be able to take
+ * a correct decision regarding underlying pages; this is done in such
+ * way as XDP program can change the refcount of page
+ */
+static void ice_get_pgcnts(struct ice_rx_ring *rx_ring)
+{
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
+	struct ice_rx_buf *rx_buf;
+	u32 cnt = rx_ring->count;
+
+	for (int i = 0; i < nr_frags; i++) {
+		rx_buf = &rx_ring->rx_buf[idx];
+		rx_buf->pgcnt = page_count(rx_buf->page);
+
+		if (++idx == cnt)
+			idx = 0;
+	}
+}
+
+/**
  * ice_build_skb - Build skb around an existing buffer
  * @rx_ring: Rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
@@ -1051,12 +1072,12 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 				rx_buf->page_offset + headlen, size,
 				xdp->frame_sz);
 	} else {
-		/* buffer is unused, change the act that should be taken later
-		 * on; data was copied onto skb's linear part so there's no
+		/* buffer is unused, restore biased page count in Rx buffer;
+		 * data was copied onto skb's linear part so there's no
 		 * need for adjusting page offset and we can reuse this buffer
 		 * as-is
 		 */
-		rx_buf->act = ICE_SKB_CONSUMED;
+		rx_buf->pagecnt_bias++;
 	}
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
@@ -1104,6 +1125,65 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
 }
 
 /**
+ * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags
+ * @rx_ring: Rx ring with all the auxiliary data
+ * @xdp: XDP buffer carrying linear + frags part
+ * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage
+ * @ntc: a current next_to_clean value to be stored at rx_ring
+ * @verdict: return code from XDP program execution
+ *
+ * Walk through gathered fragments and satisfy internal page
+ * recycle mechanism; we take here an action related to verdict
+ * returned by XDP program;
+ */
+static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+			    u32 *xdp_xmit, u32 ntc, u32 verdict)
+{
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
+	u32 cnt = rx_ring->count;
+	u32 post_xdp_frags = 1;
+	struct ice_rx_buf *buf;
+	int i;
+
+	if (unlikely(xdp_buff_has_frags(xdp)))
+		post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags;
+
+	for (i = 0; i < post_xdp_frags; i++) {
+		buf = &rx_ring->rx_buf[idx];
+
+		if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+			*xdp_xmit |= verdict;
+		} else if (verdict & ICE_XDP_CONSUMED) {
+			buf->pagecnt_bias++;
+		} else if (verdict == ICE_XDP_PASS) {
+			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+		}
+
+		ice_put_rx_buf(rx_ring, buf);
+
+		if (++idx == cnt)
+			idx = 0;
+	}
+	/* handle buffers that represented frags released by XDP prog;
+	 * for these we keep pagecnt_bias as-is; refcount from struct page
+	 * has been decremented within XDP prog and we do not have to increase
+	 * the biased refcnt
+	 */
+	for (; i < nr_frags; i++) {
+		buf = &rx_ring->rx_buf[idx];
+		ice_put_rx_buf(rx_ring, buf);
+		if (++idx == cnt)
+			idx = 0;
+	}
+
+	xdp->data = NULL;
+	rx_ring->first_desc = ntc;
+	rx_ring->nr_frags = 0;
+}
+
+/**
  * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: Rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
@@ -1120,15 +1200,13 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
 	unsigned int offset = rx_ring->rx_offset;
 	struct xdp_buff *xdp = &rx_ring->xdp;
-	u32 cached_ntc = rx_ring->first_desc;
 	struct ice_tx_ring *xdp_ring = NULL;
 	struct bpf_prog *xdp_prog = NULL;
 	u32 ntc = rx_ring->next_to_clean;
+	u32 cached_ntu, xdp_verdict;
 	u32 cnt = rx_ring->count;
 	u32 xdp_xmit = 0;
-	u32 cached_ntu;
 	bool failure;
-	u32 first;
 
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	if (xdp_prog) {
@@ -1190,6 +1268,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
 			xdp_buff_clear_frags_flag(xdp);
 		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
+			ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED);
 			break;
 		}
 		if (++ntc == cnt)
@@ -1199,15 +1278,15 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
-		if (rx_buf->act == ICE_XDP_PASS)
+		ice_get_pgcnts(rx_ring);
+		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
+		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
 		total_rx_pkts++;
 
-		xdp->data = NULL;
-		rx_ring->first_desc = ntc;
-		rx_ring->nr_frags = 0;
+		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+
 		continue;
 construct_skb:
 		if (likely(ice_ring_uses_build_skb(rx_ring)))
@@ -1217,18 +1296,12 @@ construct_skb:
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
-			rx_buf->act = ICE_XDP_CONSUMED;
-			if (unlikely(xdp_buff_has_frags(xdp)))
-				ice_set_rx_bufs_act(xdp, rx_ring,
-						    ICE_XDP_CONSUMED);
-			xdp->data = NULL;
-			rx_ring->first_desc = ntc;
-			rx_ring->nr_frags = 0;
-			break;
+			xdp_verdict = ICE_XDP_CONSUMED;
 		}
-		xdp->data = NULL;
-		rx_ring->first_desc = ntc;
-		rx_ring->nr_frags = 0;
+		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+
+		if (!skb)
+			break;
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
 		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
@@ -1257,23 +1330,6 @@ construct_skb:
 		total_rx_pkts++;
 	}
 
-	first = rx_ring->first_desc;
-	while (cached_ntc != first) {
-		struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc];
-
-		if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-			xdp_xmit |= buf->act;
-		} else if (buf->act & ICE_XDP_CONSUMED) {
-			buf->pagecnt_bias++;
-		} else if (buf->act == ICE_XDP_PASS) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-		}
-
-		ice_put_rx_buf(rx_ring, buf);
-		if (++cached_ntc >= cnt)
-			cached_ntc = 0;
-	}
 	rx_ring->next_to_clean = ntc;
 	/* return up to cleaned_count buffers to hardware */
 	failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
@@ -1753,6 +1809,7 @@ dma_error:
 static
 int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 {
+	const struct ice_tx_ring *tx_ring = off->tx_ring;
 	u32 l4_len = 0, l3_len = 0, l2_len = 0;
 	struct sk_buff *skb = first->skb;
 	union {
@@ -1902,6 +1959,30 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	l3_len = l4.hdr - ip.hdr;
 	offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S;
 
+	if ((tx_ring->netdev->features & NETIF_F_HW_CSUM) &&
+	    !(first->tx_flags & ICE_TX_FLAGS_TSO) &&
+	    !skb_csum_is_sctp(skb)) {
+		/* Set GCS */
+		u16 csum_start = (skb->csum_start - skb->mac_header) / 2;
+		u16 csum_offset = skb->csum_offset / 2;
+		u16 gcs_params;
+
+		gcs_params = FIELD_PREP(ICE_TX_GCS_DESC_START_M, csum_start) |
+			     FIELD_PREP(ICE_TX_GCS_DESC_OFFSET_M, csum_offset) |
+			     FIELD_PREP(ICE_TX_GCS_DESC_TYPE_M,
+					ICE_TX_GCS_DESC_CSUM_PSH);
+
+		/* Unlike legacy HW checksums, GCS requires a context
+		 * descriptor.
+		 */
+		off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX;
+		off->cd_gcs_params = gcs_params;
+		/* Fill out CSO info in data descriptors */
+		off->td_offset |= offset;
+		off->td_cmd |= cmd;
+		return 1;
+	}
+
 	/* Enable L4 checksum offloads */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
@@ -2359,17 +2440,20 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 
 	/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
 	eth = (struct ethhdr *)skb_mac_header(skb);
-	if (unlikely((skb->priority == TC_PRIO_CONTROL ||
-		      eth->h_proto == htons(ETH_P_LLDP)) &&
-		     vsi->type == ICE_VSI_PF &&
-		     vsi->port_info->qos_cfg.is_sw_lldp))
+
+	if ((ice_is_switchdev_running(vsi->back) ||
+	     ice_lag_is_switchdev_running(vsi->back)) &&
+	    vsi->type != ICE_VSI_SF)
+		ice_eswitch_set_target_vsi(skb, &offload);
+	else if (unlikely((skb->priority == TC_PRIO_CONTROL ||
+			   eth->h_proto == htons(ETH_P_LLDP)) &&
+			   vsi->type == ICE_VSI_PF &&
+			   vsi->port_info->qos_cfg.is_sw_lldp))
 		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
 					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
 					ICE_TXD_CTX_QW1_CMD_S);
 
 	ice_tstamp(tx_ring, skb, first, &offload);
-	if (ice_is_switchdev_running(vsi->back) && vsi->type != ICE_VSI_SF)
-		ice_eswitch_set_target_vsi(skb, &offload);
 
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
 		struct ice_tx_ctx_desc *cdesc;
@@ -2383,7 +2467,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 		/* setup context descriptor */
 		cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params);
 		cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2);
-		cdesc->rsvd = cpu_to_le16(0);
+		cdesc->gcs = cpu_to_le16(offload.cd_gcs_params);
 		cdesc->qw1 = cpu_to_le64(offload.cd_qw1);
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index cb347c852ba9..a4b1e9514632 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -193,6 +193,7 @@ struct ice_tx_offload_params {
 	u32 td_l2tag1;
 	u32 cd_tunnel_params;
 	u16 cd_l2tag2;
+	u16 cd_gcs_params;
 	u8 header_len;
 };
 
@@ -201,7 +202,6 @@ struct ice_rx_buf {
 	struct page *page;
 	unsigned int page_offset;
 	unsigned int pgcnt;
-	unsigned int act;
 	unsigned int pagecnt_bias;
 };
 
@@ -367,6 +367,7 @@ struct ice_rx_ring {
 #define ICE_RX_FLAGS_RING_BUILD_SKB	BIT(1)
 #define ICE_RX_FLAGS_CRC_STRIP_DIS	BIT(2)
 #define ICE_RX_FLAGS_MULTIDEV		BIT(3)
+#define ICE_RX_FLAGS_RING_GCS		BIT(4)
 	u8 flags;
 	/* CL5 - 5th cacheline starts here */
 	struct xdp_rxq_info xdp_rxq;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 2719f0e20933..45cfaabc41cb 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -81,6 +81,23 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring,
 }
 
 /**
+ * ice_rx_gcs - Set generic checksum in skb
+ * @skb: skb currently being received and modified
+ * @rx_desc: receive descriptor
+ */
+static void ice_rx_gcs(struct sk_buff *skb,
+		       const union ice_32b_rx_flex_desc *rx_desc)
+{
+	const struct ice_32b_rx_flex_desc_nic *desc;
+	u16 csum;
+
+	desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	csum = (__force u16)desc->raw_csum;
+	skb->csum = csum_unfold((__force __sum16)swab16(csum));
+}
+
+/**
  * ice_rx_csum - Indicate in skb if checksum is good
  * @ring: the ring we care about
  * @skb: skb currently being received and modified
@@ -107,6 +124,15 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	rx_status0 = le16_to_cpu(rx_desc->wb.status_error0);
 	rx_status1 = le16_to_cpu(rx_desc->wb.status_error1);
 
+	if ((ring->flags & ICE_RX_FLAGS_RING_GCS) &&
+	    rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC &&
+	    (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP ||
+	     decoded.inner_prot == LIBETH_RX_PT_INNER_UDP ||
+	     decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) {
+		ice_rx_gcs(skb, rx_desc);
+		return;
+	}
+
 	/* check if HW has decoded the packet and checksum */
 	if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
 		return;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 79f960c6680d..6cf32b404127 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -6,49 +6,6 @@
 #include "ice.h"
 
 /**
- * ice_set_rx_bufs_act - propagate Rx buffer action to frags
- * @xdp: XDP buffer representing frame (linear and frags part)
- * @rx_ring: Rx ring struct
- * act: action to store onto Rx buffers related to XDP buffer parts
- *
- * Set action that should be taken before putting Rx buffer from first frag
- * to the last.
- */
-static inline void
-ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
-		    const unsigned int act)
-{
-	u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
-	u32 nr_frags = rx_ring->nr_frags + 1;
-	u32 idx = rx_ring->first_desc;
-	u32 cnt = rx_ring->count;
-	struct ice_rx_buf *buf;
-
-	for (int i = 0; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[idx];
-		buf->act = act;
-
-		if (++idx == cnt)
-			idx = 0;
-	}
-
-	/* adjust pagecnt_bias on frags freed by XDP prog */
-	if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) {
-		u32 delta = rx_ring->nr_frags - sinfo_frags;
-
-		while (delta) {
-			if (idx == 0)
-				idx = cnt - 1;
-			else
-				idx--;
-			buf = &rx_ring->rx_buf[idx];
-			buf->pagecnt_bias--;
-			delta--;
-		}
-	}
-}
-
-/**
  * ice_test_staterr - tests bits in Rx descriptor status and error fields
  * @status_err_n: Rx descriptor status_error0 or status_error1 bits
  * @stat_err_bits: value to mask
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index adb168860711..3d68f465952d 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -18,6 +18,8 @@
 #include "ice_sbq_cmd.h"
 #include "ice_vlan_mode.h"
 #include "ice_fwlog.h"
+#include <linux/wait.h>
+#include <net/dscp.h>
 
 static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc)
 {
@@ -368,6 +370,7 @@ struct ice_ts_func_info {
 #define ICE_TS_TMR1_ENA_M		BIT(26)
 #define ICE_TS_LL_TX_TS_READ_M		BIT(28)
 #define ICE_TS_LL_TX_TS_INT_READ_M	BIT(29)
+#define ICE_TS_LL_PHY_TMR_UPDATE_M	BIT(30)
 
 struct ice_ts_dev_info {
 	/* Device specific info */
@@ -382,6 +385,7 @@ struct ice_ts_dev_info {
 	u8 tmr1_ena;
 	u8 ts_ll_read;
 	u8 ts_ll_int_read;
+	u8 ll_phy_tmr_update;
 };
 
 #define ICE_NAC_TOPO_PRIMARY_M	BIT(0)
@@ -692,7 +696,6 @@ struct ice_dcb_app_priority_table {
 
 #define ICE_MAX_USER_PRIORITY	8
 #define ICE_DCBX_MAX_APPS	64
-#define ICE_DSCP_NUM_VAL	64
 #define ICE_LLDPDU_SIZE		1500
 #define ICE_TLV_STATUS_OPER	0x1
 #define ICE_TLV_STATUS_SYNC	0x2
@@ -715,9 +718,9 @@ struct ice_dcbx_cfg {
 	u8 pfc_mode;
 	struct ice_dcb_app_priority_table app[ICE_DCBX_MAX_APPS];
 	/* when DSCP mapping defined by user set its bit to 1 */
-	DECLARE_BITMAP(dscp_mapped, ICE_DSCP_NUM_VAL);
+	DECLARE_BITMAP(dscp_mapped, DSCP_MAX);
 	/* array holding DSCP -> UP/TC values for DSCP L3 QoS mode */
-	u8 dscp_map[ICE_DSCP_NUM_VAL];
+	u8 dscp_map[DSCP_MAX];
 	u8 dcbx_mode;
 #define ICE_DCBX_MODE_CEE	0x1
 #define ICE_DCBX_MODE_IEEE	0x2
@@ -848,26 +851,26 @@ struct ice_mbx_data {
 #define ICE_PORTS_PER_QUAD	4
 #define ICE_GET_QUAD_NUM(port) ((port) / ICE_PORTS_PER_QUAD)
 
+#define ATQBAL_FLAGS_INTR_IN_PROGRESS	BIT(0)
+
+struct ice_e810_params {
+	/* The wait queue lock also protects the low latency interface */
+	wait_queue_head_t atqbal_wq;
+	unsigned int atqbal_flags;
+};
+
 struct ice_eth56g_params {
 	u8 num_phys;
-	u8 phy_addr[2];
 	bool onestep_ena;
 	bool sfd_ena;
 	u32 peer_delay;
 };
 
 union ice_phy_params {
+	struct ice_e810_params e810;
 	struct ice_eth56g_params eth56g;
 };
 
-/* PHY model */
-enum ice_phy_model {
-	ICE_PHY_UNSUP = -1,
-	ICE_PHY_E810 = 1,
-	ICE_PHY_E82X,
-	ICE_PHY_ETH56G,
-};
-
 /* Global Link Topology */
 enum ice_global_link_topo {
 	ICE_LINK_TOPO_UP_TO_2_LINKS,
@@ -877,11 +880,9 @@ enum ice_global_link_topo {
 };
 
 struct ice_ptp_hw {
-	enum ice_phy_model phy_model;
 	union ice_phy_params phy;
 	u8 num_lports;
 	u8 ports_per_phy;
-	bool is_2x50g_muxed_topo;
 };
 
 /* Port hardware description */
@@ -969,6 +970,7 @@ struct ice_hw {
 	u8 intrl_gran;
 
 	struct ice_ptp_hw ptp;
+	s8 lane_num;
 
 	/* Active package version (currently active) */
 	struct ice_pkg_ver active_pkg_ver;
@@ -1216,4 +1218,9 @@ struct ice_aq_get_set_rss_lut_params {
 #define ICE_FW_API_REPORT_DFLT_CFG_MIN		7
 #define ICE_FW_API_REPORT_DFLT_CFG_PATCH	3
 
+/* AQ API version for Health Status support */
+#define ICE_FW_API_HEALTH_REPORT_MAJ		1
+#define ICE_FW_API_HEALTH_REPORT_MIN		7
+#define ICE_FW_API_HEALTH_REPORT_PATCH		6
+
 #endif /* _ICE_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index c7c0c2f50c26..48cd533e93b7 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -226,6 +226,7 @@ static void ice_vf_clear_counters(struct ice_vf *vf)
 		vsi->num_vlan = 0;
 
 	vf->num_mac = 0;
+	vf->num_mac_lldp = 0;
 	memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events));
 	memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events));
 }
@@ -1036,6 +1037,14 @@ void ice_initialize_vf_entry(struct ice_vf *vf)
 	mutex_init(&vf->cfg_lock);
 }
 
+void ice_deinitialize_vf_entry(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+
+	if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+		list_del(&vf->mbx_info.list_entry);
+}
+
 /**
  * ice_dis_vf_qs - Disable the VF queues
  * @vf: pointer to the VF structure
@@ -1393,3 +1402,28 @@ struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi)
 	rcu_read_unlock();
 	return ctrl_vsi;
 }
+
+/**
+ * ice_vf_update_mac_lldp_num - update the VF's number of LLDP addresses
+ * @vf: a VF to add the address to
+ * @vsi: the corresponding VSI
+ * @incr: is the rule added or removed
+ */
+void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi,
+				bool incr)
+{
+	bool lldp_by_fw = test_bit(ICE_FLAG_FW_LLDP_AGENT, vsi->back->flags);
+	bool was_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw;
+	bool is_ena;
+
+	if (WARN_ON(!vsi)) {
+		vf->num_mac_lldp = 0;
+		return;
+	}
+
+	vf->num_mac_lldp += incr ? 1 : -1;
+	is_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw;
+
+	if (was_ena != is_ena)
+		ice_vsi_cfg_sw_lldp(vsi, false, is_ena);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index 4261fe1c2bcd..482f4285fd35 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -124,6 +124,10 @@ struct ice_vf {
 	u8 spoofchk:1;
 	u8 link_forced:1;
 	u8 link_up:1;			/* only valid if VF link is forced */
+	u8 lldp_tx_ena:1;
+
+	u32 ptp_caps;
+
 	unsigned int min_tx_rate;	/* Minimum Tx bandwidth limit in Mbps */
 	unsigned int max_tx_rate;	/* Maximum Tx bandwidth limit in Mbps */
 	DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS);	/* VF runtime states */
@@ -131,6 +135,7 @@ struct ice_vf {
 	unsigned long vf_caps;		/* VF's adv. capabilities */
 	u8 num_req_qs;			/* num of queue pairs requested by VF */
 	u16 num_mac;
+	u16 num_mac_lldp;
 	u16 num_vf_qs;			/* num of queue configured per VF */
 	u8 vlan_strip_ena;		/* Outer and Inner VLAN strip enable */
 #define ICE_INNER_VLAN_STRIP_ENA	BIT(0)
@@ -146,6 +151,9 @@ struct ice_vf {
 	/* devlink port data */
 	struct devlink_port devlink_port;
 
+	u16 lldp_recipe_id;
+	u16 lldp_rule_id;
+
 	u16 num_msix;			/* num of MSI-X configured on this VF */
 	struct ice_vf_qs_bw qs_bw[ICE_MAX_RSS_QS_PER_VF];
 };
@@ -177,6 +185,11 @@ static inline u16 ice_vf_get_port_vlan_tpid(struct ice_vf *vf)
 	return vf->port_vlan_info.tpid;
 }
 
+static inline bool ice_vf_is_lldp_ena(struct ice_vf *vf)
+{
+	return vf->num_mac_lldp && vf->trusted;
+}
+
 /* VF Hash Table access functions
  *
  * These functions provide abstraction for interacting with the VF hash table.
@@ -242,6 +255,8 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m);
 int ice_reset_vf(struct ice_vf *vf, u32 flags);
 void ice_reset_all_vfs(struct ice_pf *pf);
 struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi);
+void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi,
+				bool incr);
 #else /* CONFIG_PCI_IOV */
 static inline struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 0c7e77c0a09f..5392b0404986 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -24,6 +24,7 @@
 #endif
 
 void ice_initialize_vf_entry(struct ice_vf *vf);
+void ice_deinitialize_vf_entry(struct ice_vf *vf);
 void ice_dis_vf_qs(struct ice_vf *vf);
 int ice_check_vf_init(struct ice_vf *vf);
 enum virtchnl_status_code ice_err_to_virt_err(int err);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index f445e33b2028..eeeb9968e477 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -498,6 +498,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS;
 
+	if (vf->driver_caps & VIRTCHNL_VF_CAP_PTP)
+		vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_PTP;
+
 	vfres->num_vsis = 1;
 	/* Tx and Rx queue are equal for VF */
 	vfres->num_queue_pairs = vsi->num_txq;
@@ -562,7 +565,7 @@ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id)
  *
  * check for the valid queue ID
  */
-static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid)
+static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u16 qid)
 {
 	/* allocated Tx and Rx queues should be always equal for VF VSI */
 	return qid < vsi->alloc_txq;
@@ -1862,15 +1865,33 @@ static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg)
 
 	for (i = 0; i < qbw->num_queues; i++) {
 		if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 &&
-		    qbw->cfg[i].shaper.peak > vf->max_tx_rate)
+		    qbw->cfg[i].shaper.peak > vf->max_tx_rate) {
 			dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n",
 				 qbw->cfg[i].queue_id, vf->vf_id,
 				 vf->max_tx_rate);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
 		if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 &&
-		    qbw->cfg[i].shaper.committed < vf->min_tx_rate)
+		    qbw->cfg[i].shaper.committed < vf->min_tx_rate) {
 			dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n",
 				 qbw->cfg[i].queue_id, vf->vf_id,
-				 vf->max_tx_rate);
+				 vf->min_tx_rate);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].queue_id > vf->num_vf_qs) {
+			dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure invalid queue_id\n",
+				 vf->vf_id);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].tc >= ICE_MAX_TRAFFIC_CLASS) {
+			dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure a traffic class higher than allowed\n",
+				 vf->vf_id);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
 	}
 
 	for (i = 0; i < qbw->num_queues; i++) {
@@ -1900,13 +1921,21 @@ err:
  */
 static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 {
+	u16 quanta_prof_id, quanta_size, start_qid, num_queues, end_qid, i;
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	u16 quanta_prof_id, quanta_size, start_qid, end_qid, i;
 	struct virtchnl_quanta_cfg *qquanta =
 		(struct virtchnl_quanta_cfg *)msg;
 	struct ice_vsi *vsi;
 	int ret;
 
+	start_qid = qquanta->queue_select.start_queue_id;
+	num_queues = qquanta->queue_select.num_queues;
+
+	if (check_add_overflow(start_qid, num_queues, &end_qid)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto err;
@@ -1918,8 +1947,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	end_qid = qquanta->queue_select.start_queue_id +
-		  qquanta->queue_select.num_queues;
 	if (end_qid > ICE_MAX_RSS_QS_PER_VF ||
 	    end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
 		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
@@ -1948,7 +1975,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	start_qid = qquanta->queue_select.start_queue_id;
 	for (i = start_qid; i < end_qid; i++)
 		vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id;
 
@@ -1975,6 +2001,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	struct ice_vsi *vsi;
 	u8 act_prt, pri_prt;
 	int i = -1, q_idx;
+	bool ena_ts;
 
 	lag = pf->lag;
 	mutex_lock(&pf->lag_mutex);
@@ -2104,9 +2131,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 				rxdid = ICE_RXDID_LEGACY_1;
 			}
 
+			ena_ts = ((vf->driver_caps &
+				  VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) &&
+				  (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) &&
+				  (qpi->rxq.flags & VIRTCHNL_PTP_RX_TSTAMP));
+
 			ice_write_qrxflxp_cntxt(&vsi->back->hw,
-						vsi->rxq_map[q_idx],
-						rxdid, 0x03, false);
+						vsi->rxq_map[q_idx], rxdid,
+						ICE_RXDID_PRIO, ena_ts);
 		}
 	}
 
@@ -2234,6 +2266,51 @@ ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr)
 }
 
 /**
+ * ice_is_mc_lldp_eth_addr - check if the given MAC is a multicast LLDP address
+ * @mac: address to check
+ *
+ * Return: true if the address is one of the three possible LLDP multicast
+ *	   addresses, false otherwise.
+ */
+static bool ice_is_mc_lldp_eth_addr(const u8 *mac)
+{
+	const u8 lldp_mac_base[] = {0x01, 0x80, 0xc2, 0x00, 0x00};
+
+	if (memcmp(mac, lldp_mac_base, sizeof(lldp_mac_base)))
+		return false;
+
+	return (mac[5] == 0x0e || mac[5] == 0x03 || mac[5] == 0x00);
+}
+
+/**
+ * ice_vc_can_add_mac - check if the VF is allowed to add a given MAC
+ * @vf: a VF to add the address to
+ * @mac: address to check
+ *
+ * Return: true if the VF is allowed to add such MAC address, false otherwise.
+ */
+static bool ice_vc_can_add_mac(const struct ice_vf *vf, const u8 *mac)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+
+	if (is_unicast_ether_addr(mac) &&
+	    !ice_can_vf_change_mac((struct ice_vf *)vf)) {
+		dev_err(dev,
+			"VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
+		return false;
+	}
+
+	if (!vf->trusted && ice_is_mc_lldp_eth_addr(mac)) {
+		dev_warn(dev,
+			 "An untrusted VF %u is attempting to configure an LLDP multicast address\n",
+			 vf->vf_id);
+		return false;
+	}
+
+	return true;
+}
+
+/**
  * ice_vc_add_mac_addr - attempt to add the MAC address passed in
  * @vf: pointer to the VF info
  * @vsi: pointer to the VF's VSI
@@ -2251,10 +2328,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 	if (ether_addr_equal(mac_addr, vf->dev_lan_addr))
 		return 0;
 
-	if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) {
-		dev_err(dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
+	if (!ice_vc_can_add_mac(vf, mac_addr))
 		return -EPERM;
-	}
 
 	ret = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI);
 	if (ret == -EEXIST) {
@@ -2269,6 +2344,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 		return ret;
 	} else {
 		vf->num_mac++;
+		if (ice_is_mc_lldp_eth_addr(mac_addr))
+			ice_vf_update_mac_lldp_num(vf, vsi, true);
 	}
 
 	ice_vfhw_mac_add(vf, vc_ether_addr);
@@ -2363,6 +2440,8 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 	ice_vfhw_mac_del(vf, vc_ether_addr);
 
 	vf->num_mac--;
+	if (ice_is_mc_lldp_eth_addr(mac_addr))
+		ice_vf_update_mac_lldp_num(vf, vsi, false);
 
 	return 0;
 }
@@ -3031,8 +3110,8 @@ err:
 static int ice_vc_query_rxdid(struct ice_vf *vf)
 {
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_supported_rxdids rxdid = {};
 	struct ice_pf *pf = vf->pf;
+	u64 rxdid;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -3044,7 +3123,7 @@ static int ice_vc_query_rxdid(struct ice_vf *vf)
 		goto err;
 	}
 
-	rxdid.supported_rxdids = pf->supported_rxdids;
+	rxdid = pf->supported_rxdids;
 
 err:
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS,
@@ -4092,6 +4171,59 @@ out:
 				     v_ret, NULL, 0);
 }
 
+static int ice_vc_get_ptp_cap(struct ice_vf *vf,
+			      const struct virtchnl_ptp_caps *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	u32 caps = VIRTCHNL_1588_PTP_CAP_RX_TSTAMP |
+		   VIRTCHNL_1588_PTP_CAP_READ_PHC;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto err;
+
+	v_ret = VIRTCHNL_STATUS_SUCCESS;
+
+	if (msg->caps & caps)
+		vf->ptp_caps = caps;
+
+err:
+	/* send the response back to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_CAPS, v_ret,
+				     (u8 *)&vf->ptp_caps,
+				     sizeof(struct virtchnl_ptp_caps));
+}
+
+static int ice_vc_get_phc_time(struct ice_vf *vf)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	struct virtchnl_phc_time *phc_time = NULL;
+	struct ice_pf *pf = vf->pf;
+	u32 len = 0;
+	int ret;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto err;
+
+	v_ret = VIRTCHNL_STATUS_SUCCESS;
+
+	phc_time = kzalloc(sizeof(*phc_time), GFP_KERNEL);
+	if (!phc_time) {
+		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+		goto err;
+	}
+
+	len = sizeof(*phc_time);
+
+	phc_time->time = ice_ptp_read_src_clk_reg(pf, NULL);
+
+err:
+	/* send the response back to the VF */
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_TIME, v_ret,
+				    (u8 *)phc_time, len);
+	kfree(phc_time);
+	return ret;
+}
+
 static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.get_ver_msg = ice_vc_get_ver_msg,
 	.get_vf_res_msg = ice_vc_get_vf_res_msg,
@@ -4128,6 +4260,11 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.get_qos_caps = ice_vc_get_qos_caps,
 	.cfg_q_bw = ice_vc_cfg_q_bw,
 	.cfg_q_quanta = ice_vc_cfg_q_quanta,
+	.get_ptp_cap = ice_vc_get_ptp_cap,
+	.get_phc_time = ice_vc_get_phc_time,
+	/* If you add a new op here please make sure to add it to
+	 * ice_virtchnl_repr_ops as well.
+	 */
 };
 
 /**
@@ -4185,7 +4322,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg)
 		}
 
 		ice_vfhw_mac_add(vf, &al->list[i]);
-		vf->num_mac++;
 		break;
 	}
 
@@ -4258,6 +4394,11 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = {
 	.dis_vlan_stripping_v2_msg = ice_vc_dis_vlan_stripping_v2_msg,
 	.ena_vlan_insertion_v2_msg = ice_vc_ena_vlan_insertion_v2_msg,
 	.dis_vlan_insertion_v2_msg = ice_vc_dis_vlan_insertion_v2_msg,
+	.get_qos_caps = ice_vc_get_qos_caps,
+	.cfg_q_bw = ice_vc_cfg_q_bw,
+	.cfg_q_quanta = ice_vc_cfg_q_quanta,
+	.get_ptp_cap = ice_vc_get_ptp_cap,
+	.get_phc_time = ice_vc_get_phc_time,
 };
 
 /**
@@ -4495,6 +4636,12 @@ error_handler:
 	case VIRTCHNL_OP_CONFIG_QUANTA:
 		err = ops->cfg_q_quanta(vf, msg);
 		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		err = ops->get_ptp_cap(vf, (const void *)msg);
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		err = ops->get_phc_time(vf);
+		break;
 	case VIRTCHNL_OP_UNKNOWN:
 	default:
 		dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode,
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
index 0c629aef9baf..222990f229d5 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
@@ -26,6 +26,9 @@
 #define ICE_MAX_MACADDR_PER_VF		18
 #define ICE_FLEX_DESC_RXDID_MAX_NUM	64
 
+/* Priority to be compared against previous priority from the pipe */
+#define ICE_RXDID_PRIO			0x03
+
 /* VFs only get a single VSI. For ice hardware, the VF does not need to know
  * its VSI index. However, the virtchnl interface requires a VSI number,
  * mainly due to legacy hardware.
@@ -72,6 +75,9 @@ struct ice_virtchnl_ops {
 	int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg);
 	int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg);
 	int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg);
+	int (*get_ptp_cap)(struct ice_vf *vf,
+			   const struct virtchnl_ptp_caps *msg);
+	int (*get_phc_time)(struct ice_vf *vf);
 };
 
 #ifdef CONFIG_PCI_IOV
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
index c105a82ee136..a3d1579a619a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
@@ -84,6 +84,12 @@ static const u32 fdir_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER,
 };
 
+/* VIRTCHNL_VF_CAP_PTP */
+static const u32 ptp_allowlist_opcodes[] = {
+	VIRTCHNL_OP_1588_PTP_GET_CAPS,
+	VIRTCHNL_OP_1588_PTP_GET_TIME,
+};
+
 static const u32 tc_allowlist_opcodes[] = {
 	VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW,
 	VIRTCHNL_OP_CONFIG_QUANTA,
@@ -110,6 +116,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = {
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes),
+	ALLOW_ITEM(VIRTCHNL_VF_CAP_PTP, ptp_allowlist_opcodes),
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 14e3f0f89c78..ae83c3914e29 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -832,21 +832,27 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 		      struct virtchnl_proto_hdrs *proto,
 		      struct virtchnl_fdir_fltr_conf *conf)
 {
-	u8 *pkt_buf, *msk_buf __free(kfree);
+	u8 *pkt_buf, *msk_buf __free(kfree) = NULL;
 	struct ice_parser_result rslt;
 	struct ice_pf *pf = vf->pf;
+	u16 pkt_len, udp_port = 0;
 	struct ice_parser *psr;
 	int status = -ENOMEM;
 	struct ice_hw *hw;
-	u16 udp_port = 0;
 
-	pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL);
-	msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL);
+	pkt_len = proto->raw.pkt_len;
+
+	if (!pkt_len || pkt_len > VIRTCHNL_MAX_SIZE_RAW_PACKET)
+		return -EINVAL;
+
+	pkt_buf = kzalloc(pkt_len, GFP_KERNEL);
+	msk_buf = kzalloc(pkt_len, GFP_KERNEL);
+
 	if (!pkt_buf || !msk_buf)
 		goto err_mem_alloc;
 
-	memcpy(pkt_buf, proto->raw.spec, proto->raw.pkt_len);
-	memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len);
+	memcpy(pkt_buf, proto->raw.spec, pkt_len);
+	memcpy(msk_buf, proto->raw.mask, pkt_len);
 
 	hw = &pf->hw;
 
@@ -862,7 +868,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 	if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN))
 		ice_parser_vxlan_tunnel_set(psr, udp_port, true);
 
-	status = ice_parser_run(psr, pkt_buf, proto->raw.pkt_len, &rslt);
+	status = ice_parser_run(psr, pkt_buf, pkt_len, &rslt);
 	if (status)
 		goto err_parser_destroy;
 
@@ -876,7 +882,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 	}
 
 	status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf,
-					 proto->raw.pkt_len, ICE_BLK_FD,
+					 pkt_len, ICE_BLK_FD,
 					 conf->prof);
 	if (status)
 		goto err_parser_profile_init;
@@ -885,7 +891,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 		ice_parser_profile_dump(hw, conf->prof);
 
 	/* Store raw flow info into @conf */
-	conf->pkt_len = proto->raw.pkt_len;
+	conf->pkt_len = pkt_len;
 	conf->pkt_buf = pkt_buf;
 	conf->parser_ena = true;
 
@@ -1444,7 +1450,8 @@ err_free_pkt:
  */
 static void ice_vf_fdir_timer(struct timer_list *t)
 {
-	struct ice_vf_fdir_ctx *ctx_irq = from_timer(ctx_irq, t, rx_tmr);
+	struct ice_vf_fdir_ctx *ctx_irq = timer_container_of(ctx_irq, t,
+							     rx_tmr);
 	struct ice_vf_fdir_ctx *ctx_done;
 	struct ice_vf_fdir *fdir;
 	unsigned long flags;
@@ -1515,7 +1522,7 @@ ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi,
 	memcpy(&ctx_done->rx_desc, rx_desc, sizeof(*rx_desc));
 	spin_unlock_irqrestore(&fdir->ctx_lock, flags);
 
-	ret = del_timer(&ctx_irq->rx_tmr);
+	ret = timer_delete(&ctx_irq->rx_tmr);
 	if (!ret)
 		dev_err(dev, "VF %d: Unexpected inactive timer!\n", vf->vf_id);
 
@@ -1910,7 +1917,7 @@ static void ice_vc_fdir_clear_irq_ctx(struct ice_vf *vf)
 	struct ice_vf_fdir_ctx *ctx = &vf->fdir.ctx_irq;
 	unsigned long flags;
 
-	del_timer(&ctx->rx_tmr);
+	timer_delete(&ctx->rx_tmr);
 	spin_lock_irqsave(&vf->fdir.ctx_lock, flags);
 	ctx->flags &= ~ICE_VF_FDIR_CTX_VALID;
 	spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags);
@@ -2091,6 +2098,11 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	pf = vf->pf;
 	dev = ice_pf_to_dev(pf);
 	vf_vsi = ice_get_vf_vsi(vf);
+	if (!vf_vsi) {
+		dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id);
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err_exit;
+	}
 
 #define ICE_VF_MAX_FDIR_FILTERS	128
 	if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 334ae945d640..a3a4eaa17739 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019, Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
 #include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 #include "ice.h"
@@ -801,35 +802,6 @@ out_failure:
 	return result;
 }
 
-static int
-ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
-		 struct xdp_buff *xdp, const unsigned int size)
-{
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first);
-
-	if (!size)
-		return 0;
-
-	if (!xdp_buff_has_frags(first)) {
-		sinfo->nr_frags = 0;
-		sinfo->xdp_frags_size = 0;
-		xdp_buff_set_frags_flag(first);
-	}
-
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		xsk_buff_free(first);
-		return -ENOMEM;
-	}
-
-	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start),
-				   XDP_PACKET_HEADROOM, size);
-	sinfo->xdp_frags_size += size;
-	xsk_buff_add_frag(xdp);
-
-	return 0;
-}
-
 /**
  * ice_clean_rx_irq_zc - consumes packets from the hardware ring
  * @rx_ring: AF_XDP Rx ring
@@ -895,7 +867,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
 
 		if (!first) {
 			first = xdp;
-		} else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) {
+		} else if (likely(size) && !xsk_buff_add_frag(first, xdp)) {
+			xsk_buff_free(first);
 			break;
 		}
 
@@ -1017,7 +990,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
 	struct ice_tx_desc *tx_desc;
 	u32 i;
 
-	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+	unrolled_count(PKTS_PER_BATCH)
+	for (i = 0; i < PKTS_PER_BATCH; i++) {
 		dma_addr_t dma;
 
 		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 45adeb513253..8dc5d55e26c5 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -7,14 +7,6 @@
 
 #define PKTS_PER_BATCH 8
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 8") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct ice_vsi;
 
 #ifdef CONFIG_XDP_SOCKETS
diff --git a/drivers/net/ethernet/intel/idpf/Kconfig b/drivers/net/ethernet/intel/idpf/Kconfig
index 1addd663acad..2c359a8551c7 100644
--- a/drivers/net/ethernet/intel/idpf/Kconfig
+++ b/drivers/net/ethernet/intel/idpf/Kconfig
@@ -4,6 +4,7 @@
 config IDPF
 	tristate "Intel(R) Infrastructure Data Path Function Support"
 	depends on PCI_MSI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select DIMLIB
 	select LIBETH
 	help
diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile
index 2ce01a0b5898..83ac5e296382 100644
--- a/drivers/net/ethernet/intel/idpf/Makefile
+++ b/drivers/net/ethernet/intel/idpf/Makefile
@@ -17,3 +17,6 @@ idpf-y := \
 	idpf_vf_dev.o
 
 idpf-$(CONFIG_IDPF_SINGLEQ)	+= idpf_singleq_txrx.o
+
+idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_ptp.o
+idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_virtchnl_ptp.o
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 66544faab710..1e812c3f62f9 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -143,6 +143,7 @@ enum idpf_vport_state {
  * @vport_id: Vport identifier
  * @link_speed_mbps: Link speed in mbps
  * @vport_idx: Relative vport index
+ * @max_tx_hdr_size: Max header length hardware can support
  * @state: See enum idpf_vport_state
  * @netstats: Packet and byte stats
  * @stats_lock: Lock to protect stats update
@@ -153,6 +154,7 @@ struct idpf_netdev_priv {
 	u32 vport_id;
 	u32 link_speed_mbps;
 	u16 vport_idx;
+	u16 max_tx_hdr_size;
 	enum idpf_vport_state state;
 	struct rtnl_link_stats64 netstats;
 	spinlock_t stats_lock;
@@ -189,6 +191,7 @@ struct idpf_vport_max_q {
  * @mb_intr_reg_init: Mailbox interrupt register initialization
  * @reset_reg_init: Reset register initialization
  * @trigger_reset: Trigger a reset to occur
+ * @ptp_reg_init: PTP register initialization
  */
 struct idpf_reg_ops {
 	void (*ctlq_reg_init)(struct idpf_ctlq_create_info *cq);
@@ -197,6 +200,7 @@ struct idpf_reg_ops {
 	void (*reset_reg_init)(struct idpf_adapter *adapter);
 	void (*trigger_reset)(struct idpf_adapter *adapter,
 			      enum idpf_flags trig_cause);
+	void (*ptp_reg_init)(const struct idpf_adapter *adapter);
 };
 
 /**
@@ -290,6 +294,9 @@ struct idpf_port_stats {
  * @port_stats: per port csum, header split, and other offload stats
  * @link_up: True if link is up
  * @sw_marker_wq: workqueue for marker packets
+ * @tx_tstamp_caps: Capabilities negotiated for Tx timestamping
+ * @tstamp_config: The Tx tstamp config
+ * @tstamp_task: Tx timestamping task
  */
 struct idpf_vport {
 	u16 num_txq;
@@ -334,6 +341,10 @@ struct idpf_vport {
 	bool link_up;
 
 	wait_queue_head_t sw_marker_wq;
+
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct kernel_hwtstamp_config tstamp_config;
+	struct work_struct tstamp_task;
 };
 
 /**
@@ -478,6 +489,13 @@ struct idpf_vport_config {
 
 struct idpf_vc_xn_manager;
 
+#define idpf_for_each_vport(adapter, iter) \
+	for (struct idpf_vport **__##iter = &(adapter)->vports[0], \
+	     *iter = (adapter)->max_vports ? *__##iter : NULL; \
+	     iter; \
+	     iter = (++__##iter) < &(adapter)->vports[(adapter)->max_vports] ? \
+	     *__##iter : NULL)
+
 /**
  * struct idpf_adapter - Device data struct generated on probe
  * @pdev: PCI device struct given on probe
@@ -530,6 +548,7 @@ struct idpf_vc_xn_manager;
  * @vector_lock: Lock to protect vector distribution
  * @queue_lock: Lock to protect queue distribution
  * @vc_buf_lock: Lock to protect virtchnl buffer
+ * @ptp: Storage for PTP-related data
  */
 struct idpf_adapter {
 	struct pci_dev *pdev;
@@ -587,6 +606,8 @@ struct idpf_adapter {
 	struct mutex vector_lock;
 	struct mutex queue_lock;
 	struct mutex vc_buf_lock;
+
+	struct idpf_ptp *ptp;
 };
 
 /**
@@ -629,13 +650,13 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 	VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4	|\
 	VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6)
 
-#define IDPF_CAP_RX_CSUM_L4V4 (\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP)
+#define IDPF_CAP_TX_CSUM_L4V4 (\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP	|\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_UDP)
 
-#define IDPF_CAP_RX_CSUM_L4V6 (\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
+#define IDPF_CAP_TX_CSUM_L4V6 (\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP	|\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP)
 
 #define IDPF_CAP_RX_CSUM (\
 	VIRTCHNL2_CAP_RX_CSUM_L3_IPV4		|\
@@ -644,11 +665,9 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP	|\
 	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
 
-#define IDPF_CAP_SCTP_CSUM (\
+#define IDPF_CAP_TX_SCTP_CSUM (\
 	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP)
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP)
 
 #define IDPF_CAP_TUNNEL_TX_CSUM (\
 	VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL	|\
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
index 4849590a5591..48b8e184f3db 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
@@ -96,7 +96,7 @@ static void idpf_ctlq_init_rxq_bufs(struct idpf_ctlq_info *cq)
  */
 static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq)
 {
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	/* free ring buffers and the ring itself */
 	idpf_ctlq_dealloc_ring_res(hw, cq);
@@ -104,8 +104,7 @@ static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq)
 	/* Set ring_size to 0 to indicate uninitialized queue */
 	cq->ring_size = 0;
 
-	mutex_unlock(&cq->cq_lock);
-	mutex_destroy(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 }
 
 /**
@@ -173,7 +172,7 @@ int idpf_ctlq_add(struct idpf_hw *hw,
 
 	idpf_ctlq_init_regs(hw, cq, is_rxq);
 
-	mutex_init(&cq->cq_lock);
+	spin_lock_init(&cq->cq_lock);
 
 	list_add(&cq->cq_list, &hw->cq_list_head);
 
@@ -272,7 +271,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	int err = 0;
 	int i;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	/* Ensure there are enough descriptors to send all messages */
 	num_desc_avail = IDPF_CTLQ_DESC_UNUSED(cq);
@@ -332,7 +331,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	wr32(hw, cq->reg.tail, cq->next_to_use);
 
 err_unlock:
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	return err;
 }
@@ -364,7 +363,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 	if (*clean_count > cq->ring_size)
 		return -EBADR;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	ntc = cq->next_to_clean;
 
@@ -376,6 +375,9 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 		if (!(le16_to_cpu(desc->flags) & IDPF_CTLQ_FLAG_DD))
 			break;
 
+		/* Ensure no other fields are read until DD flag is checked */
+		dma_rmb();
+
 		/* strip off FW internal code */
 		desc_err = le16_to_cpu(desc->ret_val) & 0xff;
 
@@ -394,7 +396,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 
 	cq->next_to_clean = ntc;
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	/* Return number of descriptors actually cleaned */
 	*clean_count = i;
@@ -432,7 +434,7 @@ int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	if (*buff_count > 0)
 		buffs_avail = true;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	if (tbp >= cq->ring_size)
 		tbp = 0;
@@ -521,7 +523,7 @@ post_buffs_out:
 		wr32(hw, cq->reg.tail, cq->next_to_post);
 	}
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	/* return the number of buffers that were not posted */
 	*buff_count = *buff_count - i;
@@ -549,7 +551,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 	u16 i;
 
 	/* take the lock before we start messing with the ring */
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	ntc = cq->next_to_clean;
 
@@ -563,6 +565,9 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 		if (!(flags & IDPF_CTLQ_FLAG_DD))
 			break;
 
+		/* Ensure no other fields are read until DD flag is checked */
+		dma_rmb();
+
 		q_msg[i].vmvf_type = (flags &
 				      (IDPF_CTLQ_FLAG_FTYPE_VM |
 				       IDPF_CTLQ_FLAG_FTYPE_PF)) >>
@@ -608,7 +613,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 
 	cq->next_to_clean = ntc;
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	*num_q_msg = i;
 	if (*num_q_msg == 0)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
index e8e046ef2f0d..3414c5f9a831 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
@@ -99,7 +99,7 @@ struct idpf_ctlq_info {
 
 	enum idpf_ctlq_type cq_type;
 	int q_id;
-	struct mutex cq_lock;		/* control queue lock */
+	spinlock_t cq_lock;		/* control queue lock */
 	/* used for interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
@@ -123,9 +123,12 @@ struct idpf_ctlq_info {
 /**
  * enum idpf_mbx_opc - PF/VF mailbox commands
  * @idpf_mbq_opc_send_msg_to_cp: used by PF or VF to send a message to its CP
+ * @idpf_mbq_opc_send_msg_to_peer_drv: used by PF or VF to send a message to
+ *				       any peer driver
  */
 enum idpf_mbx_opc {
 	idpf_mbq_opc_send_msg_to_cp		= 0x0801,
+	idpf_mbq_opc_send_msg_to_peer_drv	= 0x0804,
 };
 
 /* API supported for control queue management */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c
index 6c913a703df6..3fae81f1f988 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c
@@ -4,6 +4,7 @@
 #include "idpf.h"
 #include "idpf_lan_pf_regs.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
 
 #define IDPF_PF_ITR_IDX_SPACING		0x4
 
@@ -101,6 +102,9 @@ static int idpf_intr_reg_init(struct idpf_vport *vport)
 		intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S;
 		intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S;
 		intr->dyn_ctl_wb_on_itr_m = PF_GLINT_DYN_CTL_WB_ON_ITR_M;
+		intr->dyn_ctl_swint_trig_m = PF_GLINT_DYN_CTL_SWINT_TRIG_M;
+		intr->dyn_ctl_sw_itridx_ena_m =
+			PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_M;
 
 		spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing,
 					       IDPF_PF_ITR_IDX_SPACING);
@@ -146,6 +150,18 @@ static void idpf_trigger_reset(struct idpf_adapter *adapter,
 }
 
 /**
+ * idpf_ptp_reg_init - Initialize required registers
+ * @adapter: Driver specific private structure
+ *
+ * Set the bits required for enabling shtime and cmd execution
+ */
+static void idpf_ptp_reg_init(const struct idpf_adapter *adapter)
+{
+	adapter->ptp->cmd.shtime_enable_mask = PF_GLTSYN_CMD_SYNC_SHTIME_EN_M;
+	adapter->ptp->cmd.exec_cmd_mask = PF_GLTSYN_CMD_SYNC_EXEC_CMD_M;
+}
+
+/**
  * idpf_reg_ops_init - Initialize register API function pointers
  * @adapter: Driver specific private structure
  */
@@ -156,6 +172,7 @@ static void idpf_reg_ops_init(struct idpf_adapter *adapter)
 	adapter->dev_ops.reg_ops.mb_intr_reg_init = idpf_mb_intr_reg_init;
 	adapter->dev_ops.reg_ops.reset_reg_init = idpf_reset_reg_init;
 	adapter->dev_ops.reg_ops.trigger_reset = idpf_trigger_reset;
+	adapter->dev_ops.reg_ops.ptp_reg_init = idpf_ptp_reg_init;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 59b1a1a09996..eaf7a2606faa 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2023 Intel Corporation */
 
 #include "idpf.h"
+#include "idpf_ptp.h"
 
 /**
  * idpf_get_rxnfc - command to get RX flow classification rules
@@ -46,7 +47,7 @@ static u32 idpf_get_rxfh_key_size(struct net_device *netdev)
 	struct idpf_vport_user_config_data *user_config;
 
 	if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
-		return -EOPNOTSUPP;
+		return 0;
 
 	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 
@@ -65,7 +66,7 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev)
 	struct idpf_vport_user_config_data *user_config;
 
 	if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
-		return -EOPNOTSUPP;
+		return 0;
 
 	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 
@@ -1312,6 +1313,71 @@ static int idpf_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+/**
+ * idpf_get_timestamp_filters - Get the supported timestamping mode
+ * @vport: Virtual port structure
+ * @info: ethtool timestamping info structure
+ *
+ * Get the Tx/Rx timestamp filters.
+ */
+static void idpf_get_timestamp_filters(const struct idpf_vport *vport,
+				       struct kernel_ethtool_ts_info *info)
+{
+	info->so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+
+	if (!vport->tx_tstamp_caps ||
+	    vport->adapter->ptp->tx_tstamp_access == IDPF_PTP_NONE)
+		return;
+
+	info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
+				 SOF_TIMESTAMPING_TX_HARDWARE;
+
+	info->tx_types |= BIT(HWTSTAMP_TX_ON);
+}
+
+/**
+ * idpf_get_ts_info - Get device PHC association
+ * @netdev: network interface device structure
+ * @info: ethtool timestamping info structure
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_get_ts_info(struct net_device *netdev,
+			    struct kernel_ethtool_ts_info *info)
+{
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport *vport;
+	int err = 0;
+
+	if (!mutex_trylock(&np->adapter->vport_ctrl_lock))
+		return -EBUSY;
+
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->adapter->ptp) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	if (idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP) &&
+	    vport->adapter->ptp->clock) {
+		info->phc_index = ptp_clock_index(vport->adapter->ptp->clock);
+		idpf_get_timestamp_filters(vport, info);
+	} else {
+		pci_dbg(vport->adapter->pdev, "PTP clock not detected\n");
+		err = ethtool_op_get_ts_info(netdev, info);
+	}
+
+unlock:
+	mutex_unlock(&np->adapter->vport_ctrl_lock);
+
+	return err;
+}
+
 static const struct ethtool_ops idpf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
@@ -1336,6 +1402,7 @@ static const struct ethtool_ops idpf_ethtool_ops = {
 	.get_ringparam		= idpf_get_ringparam,
 	.set_ringparam		= idpf_set_ringparam,
 	.get_link_ksettings	= idpf_get_link_ksettings,
+	.get_ts_info		= idpf_get_ts_info,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
index 24edb8a6ec2e..cc9aa2b6a14a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
@@ -53,6 +53,10 @@
 #define PF_FW_ATQH_ATQH_M		GENMASK(9, 0)
 #define PF_FW_ATQT			(PF_FW_BASE + 0x24)
 
+/* Timesync registers */
+#define PF_GLTSYN_CMD_SYNC_EXEC_CMD_M	GENMASK(1, 0)
+#define PF_GLTSYN_CMD_SYNC_SHTIME_EN_M	BIT(2)
+
 /* Interrupts */
 #define PF_GLINT_BASE			0x08900000
 #define PF_GLINT_DYN_CTL(_INT)		(PF_GLINT_BASE + ((_INT) * 0x1000))
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
index 8c7f8ef8f1a1..7492d1713243 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
@@ -282,7 +282,18 @@ struct idpf_flex_tx_tso_ctx_qw {
 	u8 flex;
 };
 
-struct idpf_flex_tx_ctx_desc {
+union idpf_flex_tx_ctx_desc {
+	/* DTYPE = IDPF_TX_DESC_DTYPE_CTX (0x01) */
+	struct {
+		__le64 qw0;
+#define IDPF_TX_CTX_L2TAG2_M	GENMASK_ULL(47, 32)
+		__le64 qw1;
+#define IDPF_TX_CTX_DTYPE_M	GENMASK_ULL(3, 0)
+#define IDPF_TX_CTX_CMD_M	GENMASK_ULL(15, 4)
+#define IDPF_TX_CTX_TSYN_REG_M	GENMASK_ULL(47, 30)
+#define IDPF_TX_CTX_MSS_M	GENMASK_ULL(50, 63)
+	} tsyn;
+
 	/* DTYPE = IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX (0x05) */
 	struct {
 		struct idpf_flex_tx_tso_ctx_qw qw0;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index b4fbb99bfad2..80382ff4a5fa 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -3,6 +3,7 @@
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
 
 static const struct net_device_ops idpf_netdev_ops;
 
@@ -144,22 +145,6 @@ static int idpf_mb_intr_req_irq(struct idpf_adapter *adapter)
 }
 
 /**
- * idpf_set_mb_vec_id - Set vector index for mailbox
- * @adapter: adapter structure to access the vector chunks
- *
- * The first vector id in the requested vector chunks from the CP is for
- * the mailbox
- */
-static void idpf_set_mb_vec_id(struct idpf_adapter *adapter)
-{
-	if (adapter->req_vec_chunks)
-		adapter->mb_vector.v_idx =
-			le16_to_cpu(adapter->caps.mailbox_vector_id);
-	else
-		adapter->mb_vector.v_idx = 0;
-}
-
-/**
  * idpf_mb_intr_init - Initialize the mailbox interrupt
  * @adapter: adapter structure to store the mailbox vector
  */
@@ -349,7 +334,7 @@ int idpf_intr_req(struct idpf_adapter *adapter)
 		goto free_irq;
 	}
 
-	idpf_set_mb_vec_id(adapter);
+	adapter->mb_vector.v_idx = le16_to_cpu(adapter->caps.mailbox_vector_id);
 
 	vecids = kcalloc(total_vecs, sizeof(u16), GFP_KERNEL);
 	if (!vecids) {
@@ -703,8 +688,10 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 {
 	struct idpf_adapter *adapter = vport->adapter;
 	struct idpf_vport_config *vport_config;
+	netdev_features_t other_offloads = 0;
+	netdev_features_t csum_offloads = 0;
+	netdev_features_t tso_offloads = 0;
 	netdev_features_t dflt_features;
-	netdev_features_t offloads = 0;
 	struct idpf_netdev_priv *np;
 	struct net_device *netdev;
 	u16 idx = vport->idx;
@@ -721,6 +708,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 		np->vport = vport;
 		np->vport_idx = vport->idx;
 		np->vport_id = vport->vport_id;
+		np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
 		vport->netdev = netdev;
 
 		return idpf_init_mac_addr(vport, netdev);
@@ -738,6 +726,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	np->adapter = adapter;
 	np->vport_idx = vport->idx;
 	np->vport_id = vport->vport_id;
+	np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
 
 	spin_lock_init(&np->stats_lock);
 
@@ -766,54 +755,34 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 
 	if (idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
 		dflt_features |= NETIF_F_RXHASH;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V4))
-		dflt_features |= NETIF_F_IP_CSUM;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V6))
-		dflt_features |= NETIF_F_IPV6_CSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V4))
+		csum_offloads |= NETIF_F_IP_CSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V6))
+		csum_offloads |= NETIF_F_IPV6_CSUM;
 	if (idpf_is_cap_ena(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM))
-		dflt_features |= NETIF_F_RXCSUM;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_SCTP_CSUM))
-		dflt_features |= NETIF_F_SCTP_CRC;
+		csum_offloads |= NETIF_F_RXCSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_SCTP_CSUM))
+		csum_offloads |= NETIF_F_SCTP_CRC;
 
 	if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV4_TCP))
-		dflt_features |= NETIF_F_TSO;
+		tso_offloads |= NETIF_F_TSO;
 	if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV6_TCP))
-		dflt_features |= NETIF_F_TSO6;
+		tso_offloads |= NETIF_F_TSO6;
 	if (idpf_is_cap_ena_all(adapter, IDPF_SEG_CAPS,
 				VIRTCHNL2_CAP_SEG_IPV4_UDP |
 				VIRTCHNL2_CAP_SEG_IPV6_UDP))
-		dflt_features |= NETIF_F_GSO_UDP_L4;
+		tso_offloads |= NETIF_F_GSO_UDP_L4;
 	if (idpf_is_cap_ena_all(adapter, IDPF_RSC_CAPS, IDPF_CAP_RSC))
-		offloads |= NETIF_F_GRO_HW;
-	/* advertise to stack only if offloads for encapsulated packets is
-	 * supported
-	 */
-	if (idpf_is_cap_ena(vport->adapter, IDPF_SEG_CAPS,
-			    VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL)) {
-		offloads |= NETIF_F_GSO_UDP_TUNNEL	|
-			    NETIF_F_GSO_GRE		|
-			    NETIF_F_GSO_GRE_CSUM	|
-			    NETIF_F_GSO_PARTIAL		|
-			    NETIF_F_GSO_UDP_TUNNEL_CSUM	|
-			    NETIF_F_GSO_IPXIP4		|
-			    NETIF_F_GSO_IPXIP6		|
-			    0;
-
-		if (!idpf_is_cap_ena_all(vport->adapter, IDPF_CSUM_CAPS,
-					 IDPF_CAP_TUNNEL_TX_CSUM))
-			netdev->gso_partial_features |=
-				NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
-		netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
-		offloads |= NETIF_F_TSO_MANGLEID;
-	}
+		other_offloads |= NETIF_F_GRO_HW;
 	if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LOOPBACK))
-		offloads |= NETIF_F_LOOPBACK;
+		other_offloads |= NETIF_F_LOOPBACK;
 
-	netdev->features |= dflt_features;
-	netdev->hw_features |= dflt_features | offloads;
-	netdev->hw_enc_features |= dflt_features | offloads;
+	netdev->features |= dflt_features | csum_offloads | tso_offloads;
+	netdev->hw_features |=  netdev->features | other_offloads;
+	netdev->vlan_features |= netdev->features | other_offloads;
+	netdev->hw_enc_features |= dflt_features | other_offloads;
 	idpf_set_ethtool_ops(netdev);
+	netif_set_affinity_auto(netdev);
 	SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
 
 	/* carrier off on init to avoid Tx hangs */
@@ -927,15 +896,19 @@ static int idpf_stop(struct net_device *netdev)
 static void idpf_decfg_netdev(struct idpf_vport *vport)
 {
 	struct idpf_adapter *adapter = vport->adapter;
+	u16 idx = vport->idx;
 
 	kfree(vport->rx_ptype_lkup);
 	vport->rx_ptype_lkup = NULL;
 
-	unregister_netdev(vport->netdev);
-	free_netdev(vport->netdev);
+	if (test_and_clear_bit(IDPF_VPORT_REG_NETDEV,
+			       adapter->vport_config[idx]->flags)) {
+		unregister_netdev(vport->netdev);
+		free_netdev(vport->netdev);
+	}
 	vport->netdev = NULL;
 
-	adapter->netdevs[vport->idx] = NULL;
+	adapter->netdevs[idx] = NULL;
 }
 
 /**
@@ -1127,11 +1100,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 
 	num_max_q = max(max_q->max_txq, max_q->max_rxq);
 	vport->q_vector_idxs = kcalloc(num_max_q, sizeof(u16), GFP_KERNEL);
-	if (!vport->q_vector_idxs) {
-		kfree(vport);
+	if (!vport->q_vector_idxs)
+		goto free_vport;
 
-		return NULL;
-	}
 	idpf_vport_init(vport, max_q);
 
 	/* This alloc is done separate from the LUT because it's not strictly
@@ -1141,11 +1112,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	 */
 	rss_data = &adapter->vport_config[idx]->user_config.rss_data;
 	rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL);
-	if (!rss_data->rss_key) {
-		kfree(vport);
+	if (!rss_data->rss_key)
+		goto free_vector_idxs;
 
-		return NULL;
-	}
 	/* Initialize default rss key */
 	netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size);
 
@@ -1158,6 +1127,13 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	adapter->next_vport = idpf_get_free_slot(adapter);
 
 	return vport;
+
+free_vector_idxs:
+	kfree(vport->q_vector_idxs);
+free_vport:
+	kfree(vport);
+
+	return NULL;
 }
 
 /**
@@ -1536,13 +1512,22 @@ void idpf_init_task(struct work_struct *work)
 	}
 
 	for (index = 0; index < adapter->max_vports; index++) {
-		if (adapter->netdevs[index] &&
-		    !test_bit(IDPF_VPORT_REG_NETDEV,
-			      adapter->vport_config[index]->flags)) {
-			register_netdev(adapter->netdevs[index]);
-			set_bit(IDPF_VPORT_REG_NETDEV,
-				adapter->vport_config[index]->flags);
+		struct net_device *netdev = adapter->netdevs[index];
+		struct idpf_vport_config *vport_config;
+
+		vport_config = adapter->vport_config[index];
+
+		if (!netdev ||
+		    test_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags))
+			continue;
+
+		err = register_netdev(netdev);
+		if (err) {
+			dev_err(&pdev->dev, "failed to register netdev for vport %d: %pe\n",
+				index, ERR_PTR(err));
+			continue;
 		}
+		set_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags);
 	}
 
 	/* As all the required vports are created, clear the reset flag
@@ -1816,11 +1801,19 @@ void idpf_vc_event_task(struct work_struct *work)
 	if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags))
 		return;
 
-	if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags) ||
-	    test_bit(IDPF_HR_DRV_LOAD, adapter->flags)) {
-		set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags);
-		idpf_init_hard_reset(adapter);
-	}
+	if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags))
+		goto func_reset;
+
+	if (test_bit(IDPF_HR_DRV_LOAD, adapter->flags))
+		goto drv_load;
+
+	return;
+
+func_reset:
+	idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+drv_load:
+	set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags);
+	idpf_init_hard_reset(adapter);
 }
 
 /**
@@ -2159,8 +2152,13 @@ static int idpf_open(struct net_device *netdev)
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
+	err = idpf_set_real_num_queues(vport);
+	if (err)
+		goto unlock;
+
 	err = idpf_vport_open(vport);
 
+unlock:
 	idpf_vport_ctrl_unlock(netdev);
 
 	return err;
@@ -2200,8 +2198,8 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 					     struct net_device *netdev,
 					     netdev_features_t features)
 {
-	struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
-	struct idpf_adapter *adapter = vport->adapter;
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	u16 max_tx_hdr_size = np->max_tx_hdr_size;
 	size_t len;
 
 	/* No point in doing any of this if neither checksum nor GSO are
@@ -2224,7 +2222,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 		goto unsupported;
 
 	len = skb_network_header_len(skb);
-	if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+	if (unlikely(len > max_tx_hdr_size))
 		goto unsupported;
 
 	if (!skb->encapsulation)
@@ -2237,7 +2235,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 
 	/* IPLEN can support at most 127 dwords */
 	len = skb_inner_network_header_len(skb);
-	if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+	if (unlikely(len > max_tx_hdr_size))
 		goto unsupported;
 
 	/* No need to validate L4LEN as TCP is the only protocol with a
@@ -2316,8 +2314,12 @@ void *idpf_alloc_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem, u64 size)
 	struct idpf_adapter *adapter = hw->back;
 	size_t sz = ALIGN(size, 4096);
 
-	mem->va = dma_alloc_coherent(&adapter->pdev->dev, sz,
-				     &mem->pa, GFP_KERNEL);
+	/* The control queue resources are freed under a spinlock, contiguous
+	 * pages will avoid IOMMU remapping and the use vmap (and vunmap in
+	 * dma_free_*() path.
+	 */
+	mem->va = dma_alloc_attrs(&adapter->pdev->dev, sz, &mem->pa,
+				  GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS);
 	mem->size = sz;
 
 	return mem->va;
@@ -2332,13 +2334,67 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem)
 {
 	struct idpf_adapter *adapter = hw->back;
 
-	dma_free_coherent(&adapter->pdev->dev, mem->size,
-			  mem->va, mem->pa);
+	dma_free_attrs(&adapter->pdev->dev, mem->size,
+		       mem->va, mem->pa, DMA_ATTR_FORCE_CONTIGUOUS);
 	mem->size = 0;
 	mem->va = NULL;
 	mem->pa = 0;
 }
 
+static int idpf_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct idpf_vport *vport;
+	int err;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->link_up) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EPERM;
+	}
+
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) &&
+	    !idpf_ptp_is_vport_rx_tstamp_ena(vport)) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EOPNOTSUPP;
+	}
+
+	err = idpf_ptp_set_timestamp_mode(vport, config);
+
+	idpf_vport_ctrl_unlock(netdev);
+
+	return err;
+}
+
+static int idpf_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
+{
+	struct idpf_vport *vport;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->link_up) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EPERM;
+	}
+
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) &&
+	    !idpf_ptp_is_vport_rx_tstamp_ena(vport)) {
+		idpf_vport_ctrl_unlock(netdev);
+		return 0;
+	}
+
+	*config = vport->tstamp_config;
+
+	idpf_vport_ctrl_unlock(netdev);
+
+	return 0;
+}
+
 static const struct net_device_ops idpf_netdev_ops = {
 	.ndo_open = idpf_open,
 	.ndo_stop = idpf_stop,
@@ -2351,4 +2407,6 @@ static const struct net_device_ops idpf_netdev_ops = {
 	.ndo_get_stats64 = idpf_get_stats64,
 	.ndo_set_features = idpf_set_features,
 	.ndo_tx_timeout = idpf_tx_timeout,
+	.ndo_hwtstamp_get = idpf_hwtstamp_get,
+	.ndo_hwtstamp_set = idpf_hwtstamp_set,
 };
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index db476b3314c8..0efd9c0c7a90 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -8,7 +8,7 @@
 #define DRV_SUMMARY	"Intel(R) Infrastructure Data Path Function Linux Driver"
 
 MODULE_DESCRIPTION(DRV_SUMMARY);
-MODULE_IMPORT_NS(LIBETH);
+MODULE_IMPORT_NS("LIBETH");
 MODULE_LICENSE("GPL");
 
 /**
@@ -87,7 +87,12 @@ destroy_wqs:
  */
 static void idpf_shutdown(struct pci_dev *pdev)
 {
-	idpf_remove(pdev);
+	struct idpf_adapter *adapter = pci_get_drvdata(pdev);
+
+	cancel_delayed_work_sync(&adapter->serv_task);
+	cancel_delayed_work_sync(&adapter->vc_event_task);
+	idpf_vc_core_deinit(adapter);
+	idpf_deinit_dflt_mbx(adapter);
 
 	if (system_state == SYSTEM_POWER_OFF)
 		pci_set_power_state(pdev, PCI_D3hot);
@@ -163,6 +168,10 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free;
 	}
 
+	err = pci_enable_ptm(pdev, NULL);
+	if (err)
+		pci_dbg(pdev, "PCIe PTM is not supported by PCIe bus/controller\n");
+
 	/* set up for high or low dma */
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (err) {
@@ -174,7 +183,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, adapter);
 
-	adapter->init_wq = alloc_workqueue("%s-%s-init", 0, 0,
+	adapter->init_wq = alloc_workqueue("%s-%s-init",
+					   WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					   dev_driver_string(dev),
 					   dev_name(dev));
 	if (!adapter->init_wq) {
@@ -183,7 +193,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free;
 	}
 
-	adapter->serv_wq = alloc_workqueue("%s-%s-service", 0, 0,
+	adapter->serv_wq = alloc_workqueue("%s-%s-service",
+					   WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					   dev_driver_string(dev),
 					   dev_name(dev));
 	if (!adapter->serv_wq) {
@@ -192,8 +203,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_serv_wq_alloc;
 	}
 
-	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", 0, 0,
-					  dev_driver_string(dev),
+	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", WQ_UNBOUND | WQ_HIGHPRI,
+					  0, dev_driver_string(dev),
 					  dev_name(dev));
 	if (!adapter->mbx_wq) {
 		dev_err(dev, "Failed to allocate mailbox workqueue\n");
@@ -201,7 +212,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_mbx_wq_alloc;
 	}
 
-	adapter->stats_wq = alloc_workqueue("%s-%s-stats", 0, 0,
+	adapter->stats_wq = alloc_workqueue("%s-%s-stats",
+					    WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					    dev_driver_string(dev),
 					    dev_name(dev));
 	if (!adapter->stats_wq) {
@@ -210,7 +222,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_stats_wq_alloc;
 	}
 
-	adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", 0, 0,
+	adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event",
+					       WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					       dev_driver_string(dev),
 					       dev_name(dev));
 	if (!adapter->vc_event_wq) {
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
new file mode 100644
index 000000000000..4f8725c85332
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -0,0 +1,873 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_ptp.h"
+
+/**
+ * idpf_ptp_get_access - Determine the access type of the PTP features
+ * @adapter: Driver specific private structure
+ * @direct: Capability that indicates the direct access
+ * @mailbox: Capability that indicates the mailbox access
+ *
+ * Return: the type of supported access for the PTP feature.
+ */
+static enum idpf_ptp_access
+idpf_ptp_get_access(const struct idpf_adapter *adapter, u32 direct, u32 mailbox)
+{
+	if (adapter->ptp->caps & direct)
+		return IDPF_PTP_DIRECT;
+	else if (adapter->ptp->caps & mailbox)
+		return IDPF_PTP_MAILBOX;
+	else
+		return IDPF_PTP_NONE;
+}
+
+/**
+ * idpf_ptp_get_features_access - Determine the access type of PTP features
+ * @adapter: Driver specific private structure
+ *
+ * Fulfill the adapter structure with type of the supported PTP features
+ * access.
+ */
+void idpf_ptp_get_features_access(const struct idpf_adapter *adapter)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+	u32 direct, mailbox;
+
+	/* Get the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB;
+	ptp->get_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Set the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME;
+	ptp->set_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Adjust the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK;
+	mailbox = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB;
+	ptp->adj_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Tx timestamping */
+	direct = VIRTCHNL2_CAP_PTP_TX_TSTAMPS;
+	mailbox = VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB;
+	ptp->tx_tstamp_access = idpf_ptp_get_access(adapter,
+						    direct,
+						    mailbox);
+}
+
+/**
+ * idpf_ptp_enable_shtime - Enable shadow time and execute a command
+ * @adapter: Driver specific private structure
+ */
+static void idpf_ptp_enable_shtime(struct idpf_adapter *adapter)
+{
+	u32 shtime_enable, exec_cmd;
+
+	/* Get offsets */
+	shtime_enable = adapter->ptp->cmd.shtime_enable_mask;
+	exec_cmd = adapter->ptp->cmd.exec_cmd_mask;
+
+	/* Set the shtime en and the sync field */
+	writel(shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync);
+	writel(exec_cmd | shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync);
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg_direct - Read directly the main timer value
+ * @adapter: Driver specific private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored when NULL is given.
+ *
+ * Return: the device clock time.
+ */
+static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter,
+					    struct ptp_system_timestamp *sts)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+	u32 hi, lo;
+
+	spin_lock(&ptp->read_dev_clk_lock);
+
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	idpf_ptp_enable_shtime(adapter);
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	lo = readl(ptp->dev_clk_regs.dev_clk_ns_l);
+	hi = readl(ptp->dev_clk_regs.dev_clk_ns_h);
+
+	spin_unlock(&ptp->read_dev_clk_lock);
+
+	return ((u64)hi << 32) | lo;
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg_mailbox - Read the main timer value through mailbox
+ * @adapter: Driver specific private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored when NULL is given.
+ * @src_clk: Returned main timer value in nanoseconds unit
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_read_src_clk_reg_mailbox(struct idpf_adapter *adapter,
+					     struct ptp_system_timestamp *sts,
+					     u64 *src_clk)
+{
+	struct idpf_ptp_dev_timers clk_time;
+	int err;
+
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	err = idpf_ptp_get_dev_clk_time(adapter, &clk_time);
+	if (err)
+		return err;
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	*src_clk = clk_time.dev_clk_time_ns;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg - Read the main timer value
+ * @adapter: Driver specific private structure
+ * @src_clk: Returned main timer value in nanoseconds unit
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored if NULL is given.
+ *
+ * Return: the device clock time on success, -errno otherwise.
+ */
+static int idpf_ptp_read_src_clk_reg(struct idpf_adapter *adapter, u64 *src_clk,
+				     struct ptp_system_timestamp *sts)
+{
+	switch (adapter->ptp->get_dev_clk_time_access) {
+	case IDPF_PTP_NONE:
+		return -EOPNOTSUPP;
+	case IDPF_PTP_MAILBOX:
+		return idpf_ptp_read_src_clk_reg_mailbox(adapter, sts, src_clk);
+	case IDPF_PTP_DIRECT:
+		*src_clk = idpf_ptp_read_src_clk_reg_direct(adapter, sts);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_gettimex64 - Get the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure to hold the current time value
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored if NULL is given.
+ *
+ * Return: the device clock value in ns, after converting it into a timespec
+ * struct on success, -errno otherwise.
+ */
+static int idpf_ptp_gettimex64(struct ptp_clock_info *info,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	u64 time_ns;
+	int err;
+
+	err = idpf_ptp_read_src_clk_reg(adapter, &time_ns, sts);
+	if (err)
+		return -EACCES;
+
+	*ts = ns_to_timespec64(time_ns);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_update_phctime_rxq_grp - Update the cached PHC time for a given Rx
+ *				     queue group.
+ * @grp: receive queue group in which Rx timestamp is enabled
+ * @split: Indicates whether the queue model is split or single queue
+ * @systime: Cached system time
+ */
+static void
+idpf_ptp_update_phctime_rxq_grp(const struct idpf_rxq_group *grp, bool split,
+				u64 systime)
+{
+	struct idpf_rx_queue *rxq;
+	u16 i;
+
+	if (!split) {
+		for (i = 0; i < grp->singleq.num_rxq; i++) {
+			rxq = grp->singleq.rxqs[i];
+			if (rxq)
+				WRITE_ONCE(rxq->cached_phc_time, systime);
+		}
+	} else {
+		for (i = 0; i < grp->splitq.num_rxq_sets; i++) {
+			rxq = &grp->splitq.rxq_sets[i]->rxq;
+			if (rxq)
+				WRITE_ONCE(rxq->cached_phc_time, systime);
+		}
+	}
+}
+
+/**
+ * idpf_ptp_update_cached_phctime - Update the cached PHC time values
+ * @adapter: Driver specific private structure
+ *
+ * This function updates the system time values which are cached in the adapter
+ * structure and the Rx queues.
+ *
+ * This function must be called periodically to ensure that the cached value
+ * is never more than 2 seconds old.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_update_cached_phctime(struct idpf_adapter *adapter)
+{
+	u64 systime;
+	int err;
+
+	err = idpf_ptp_read_src_clk_reg(adapter, &systime, NULL);
+	if (err)
+		return -EACCES;
+
+	/* Update the cached PHC time stored in the adapter structure.
+	 * These values are used to extend Tx timestamp values to 64 bit
+	 * expected by the stack.
+	 */
+	WRITE_ONCE(adapter->ptp->cached_phc_time, systime);
+	WRITE_ONCE(adapter->ptp->cached_phc_jiffies, jiffies);
+
+	idpf_for_each_vport(adapter, vport) {
+		bool split;
+
+		if (!vport || !vport->rxq_grps)
+			continue;
+
+		split = idpf_is_queue_model_split(vport->rxq_model);
+
+		for (u16 i = 0; i < vport->num_rxq_grp; i++) {
+			struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+
+			idpf_ptp_update_phctime_rxq_grp(grp, split, systime);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_settime64 - Set the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure that holds the new time value
+ *
+ * Set the device clock to the user input value. The conversion from timespec
+ * to ns happens in the write function.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_settime64(struct ptp_clock_info *info,
+			      const struct timespec64 *ts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	int err;
+	u64 ns;
+
+	access = adapter->ptp->set_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	ns = timespec64_to_ns(ts);
+
+	err = idpf_ptp_set_dev_clk_time(adapter, ns);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to set the time, err: %pe\n",
+			ERR_PTR(err));
+		return err;
+	}
+
+	err = idpf_ptp_update_cached_phctime(adapter);
+	if (err)
+		pci_warn(adapter->pdev,
+			 "Unable to immediately update cached PHC time\n");
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adjtime_nonatomic - Do a non-atomic clock adjustment
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta)
+{
+	struct timespec64 now, then;
+	int err;
+
+	err = idpf_ptp_gettimex64(info, &now, NULL);
+	if (err)
+		return err;
+
+	then = ns_to_timespec64(delta);
+	now = timespec64_add(now, then);
+
+	return idpf_ptp_settime64(info, &now);
+}
+
+/**
+ * idpf_ptp_adjtime - Adjust the time of the clock by the indicated delta
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	int err;
+
+	access = adapter->ptp->adj_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	/* Hardware only supports atomic adjustments using signed 32-bit
+	 * integers. For any adjustment outside this range, perform
+	 * a non-atomic get->adjust->set flow.
+	 */
+	if (delta > S32_MAX || delta < S32_MIN)
+		return idpf_ptp_adjtime_nonatomic(info, delta);
+
+	err = idpf_ptp_adj_dev_clk_time(adapter, delta);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to adjust the clock with delta %lld err: %pe\n",
+			delta, ERR_PTR(err));
+		return err;
+	}
+
+	err = idpf_ptp_update_cached_phctime(adapter);
+	if (err)
+		pci_warn(adapter->pdev,
+			 "Unable to immediately update cached PHC time\n");
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adjfine - Adjust clock increment rate
+ * @info: the driver's PTP info structure
+ * @scaled_ppm: Parts per million with 16-bit fractional field
+ *
+ * Adjust the frequency of the clock by the indicated scaled ppm from the
+ * base frequency.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	u64 incval, diff;
+	int err;
+
+	access = adapter->ptp->adj_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	incval = adapter->ptp->base_incval;
+
+	diff = adjust_by_scaled_ppm(incval, scaled_ppm);
+	err = idpf_ptp_adj_dev_clk_fine(adapter, diff);
+	if (err)
+		pci_err(adapter->pdev, "Failed to adjust clock increment rate for scaled ppm %ld %pe\n",
+			scaled_ppm, ERR_PTR(err));
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_verify_pin - Verify if pin supports requested pin function
+ * @info: the driver's PTP info structure
+ * @pin: Pin index
+ * @func: Assigned function
+ * @chan: Assigned channel
+ *
+ * Return: EOPNOTSUPP as not supported yet.
+ */
+static int idpf_ptp_verify_pin(struct ptp_clock_info *info, unsigned int pin,
+			       enum ptp_pin_function func, unsigned int chan)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * idpf_ptp_gpio_enable - Enable/disable ancillary features of PHC
+ * @info: the driver's PTP info structure
+ * @rq: The requested feature to change
+ * @on: Enable/disable flag
+ *
+ * Return: EOPNOTSUPP as not supported yet.
+ */
+static int idpf_ptp_gpio_enable(struct ptp_clock_info *info,
+				struct ptp_clock_request *rq, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * idpf_ptp_tstamp_extend_32b_to_64b - Convert a 32b nanoseconds Tx or Rx
+ *				       timestamp value to 64b.
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_timestamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ *
+ * Return: Tx timestamp value extended to 64 bits based on cached PHC time.
+ */
+u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp)
+{
+	u32 delta, phc_time_lo;
+	u64 ns;
+
+	/* Extract the lower 32 bits of the PHC time */
+	phc_time_lo = (u32)cached_phc_time;
+
+	/* Calculate the delta between the lower 32bits of the cached PHC
+	 * time and the in_timestamp value.
+	 */
+	delta = in_timestamp - phc_time_lo;
+
+	if (delta > U32_MAX / 2) {
+		/* Reverse the delta calculation here */
+		delta = phc_time_lo - in_timestamp;
+		ns = cached_phc_time - delta;
+	} else {
+		ns = cached_phc_time + delta;
+	}
+
+	return ns;
+}
+
+/**
+ * idpf_ptp_extend_ts - Convert a 40b timestamp to 64b nanoseconds
+ * @vport: Virtual port structure
+ * @in_tstamp: Ingress/egress timestamp value
+ *
+ * It is assumed that the caller verifies the timestamp is valid prior to
+ * calling this function.
+ *
+ * Extract the 32bit nominal nanoseconds and extend them. Use the cached PHC
+ * time stored in the device private PTP structure as the basis for timestamp
+ * extension.
+ *
+ * Return: Tx timestamp value extended to 64 bits.
+ */
+u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp)
+{
+	struct idpf_ptp *ptp = vport->adapter->ptp;
+	unsigned long discard_time;
+
+	discard_time = ptp->cached_phc_jiffies + 2 * HZ;
+
+	if (time_is_before_jiffies(discard_time))
+		return 0;
+
+	return idpf_ptp_tstamp_extend_32b_to_64b(ptp->cached_phc_time,
+						 lower_32_bits(in_tstamp));
+}
+
+/**
+ * idpf_ptp_request_ts - Request an available Tx timestamp index
+ * @tx_q: Transmit queue on which the Tx timestamp is requested
+ * @skb: The SKB to associate with this timestamp request
+ * @idx: Index of the Tx timestamp latch
+ *
+ * Request tx timestamp index negotiated during PTP init that will be set into
+ * Tx descriptor.
+ *
+ * Return: 0 and the index that can be provided to Tx descriptor on success,
+ * -errno otherwise.
+ */
+int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			u32 *idx)
+{
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp;
+	struct list_head *head;
+
+	/* Get the index from the free latches list */
+	spin_lock(&tx_q->cached_tstamp_caps->latches_lock);
+
+	head = &tx_q->cached_tstamp_caps->latches_free;
+	if (list_empty(head)) {
+		spin_unlock(&tx_q->cached_tstamp_caps->latches_lock);
+		return -ENOBUFS;
+	}
+
+	ptp_tx_tstamp = list_first_entry(head, struct idpf_ptp_tx_tstamp,
+					 list_member);
+	list_del(&ptp_tx_tstamp->list_member);
+
+	ptp_tx_tstamp->skb = skb_get(skb);
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	/* Move the element to the used latches list */
+	list_add(&ptp_tx_tstamp->list_member,
+		 &tx_q->cached_tstamp_caps->latches_in_use);
+	spin_unlock(&tx_q->cached_tstamp_caps->latches_lock);
+
+	*idx = ptp_tx_tstamp->idx;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_set_rx_tstamp - Enable or disable Rx timestamping
+ * @vport: Virtual port structure
+ * @rx_filter: Receive timestamp filter
+ */
+static void idpf_ptp_set_rx_tstamp(struct idpf_vport *vport, int rx_filter)
+{
+	bool enable = true, splitq;
+
+	splitq = idpf_is_queue_model_split(vport->rxq_model);
+
+	if (rx_filter == HWTSTAMP_FILTER_NONE) {
+		enable = false;
+		vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	} else {
+		vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL;
+	}
+
+	for (u16 i = 0; i < vport->num_rxq_grp; i++) {
+		struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+		struct idpf_rx_queue *rx_queue;
+		u16 j, num_rxq;
+
+		if (splitq)
+			num_rxq = grp->splitq.num_rxq_sets;
+		else
+			num_rxq = grp->singleq.num_rxq;
+
+		for (j = 0; j < num_rxq; j++) {
+			if (splitq)
+				rx_queue = &grp->splitq.rxq_sets[j]->rxq;
+			else
+				rx_queue = grp->singleq.rxqs[j];
+
+			if (enable)
+				idpf_queue_set(PTP, rx_queue);
+			else
+				idpf_queue_clear(PTP, rx_queue);
+		}
+	}
+}
+
+/**
+ * idpf_ptp_set_timestamp_mode - Setup driver for requested timestamp mode
+ * @vport: Virtual port structure
+ * @config: Hwtstamp settings requested or saved
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+				struct kernel_hwtstamp_config *config)
+{
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+	case HWTSTAMP_TX_ON:
+		if (!idpf_ptp_is_vport_tx_tstamp_ena(vport))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	vport->tstamp_config.tx_type = config->tx_type;
+	idpf_ptp_set_rx_tstamp(vport, config->rx_filter);
+	*config = vport->tstamp_config;
+
+	return 0;
+}
+
+/**
+ * idpf_tstamp_task - Delayed task to handle Tx tstamps
+ * @work: work_struct handle
+ */
+void idpf_tstamp_task(struct work_struct *work)
+{
+	struct idpf_vport *vport;
+
+	vport = container_of(work, struct idpf_vport, tstamp_task);
+
+	idpf_ptp_get_tx_tstamp(vport);
+}
+
+/**
+ * idpf_ptp_do_aux_work - Do PTP periodic work
+ * @info: Driver's PTP info structure
+ *
+ * Return: Number of jiffies to periodic work.
+ */
+static long idpf_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+
+	idpf_ptp_update_cached_phctime(adapter);
+
+	return msecs_to_jiffies(500);
+}
+
+/**
+ * idpf_ptp_set_caps - Set PTP capabilities
+ * @adapter: Driver specific private structure
+ *
+ * This function sets the PTP functions.
+ */
+static void idpf_ptp_set_caps(const struct idpf_adapter *adapter)
+{
+	struct ptp_clock_info *info = &adapter->ptp->info;
+
+	snprintf(info->name, sizeof(info->name), "%s-%s-clk",
+		 KBUILD_MODNAME, pci_name(adapter->pdev));
+
+	info->owner = THIS_MODULE;
+	info->max_adj = adapter->ptp->max_adj;
+	info->gettimex64 = idpf_ptp_gettimex64;
+	info->settime64 = idpf_ptp_settime64;
+	info->adjfine = idpf_ptp_adjfine;
+	info->adjtime = idpf_ptp_adjtime;
+	info->verify = idpf_ptp_verify_pin;
+	info->enable = idpf_ptp_gpio_enable;
+	info->do_aux_work = idpf_ptp_do_aux_work;
+}
+
+/**
+ * idpf_ptp_create_clock - Create PTP clock device for userspace
+ * @adapter: Driver specific private structure
+ *
+ * This function creates a new PTP clock device.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_create_clock(const struct idpf_adapter *adapter)
+{
+	struct ptp_clock *clock;
+
+	idpf_ptp_set_caps(adapter);
+
+	/* Attempt to register the clock before enabling the hardware. */
+	clock = ptp_clock_register(&adapter->ptp->info,
+				   &adapter->pdev->dev);
+	if (IS_ERR(clock)) {
+		pci_err(adapter->pdev, "PTP clock creation failed: %pe\n",
+			clock);
+		return PTR_ERR(clock);
+	}
+
+	adapter->ptp->clock = clock;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_release_vport_tstamp - Release the Tx timestamps trakcers for a
+ *				   given vport.
+ * @vport: Virtual port structure
+ *
+ * Remove the queues and delete lists that tracks Tx timestamp entries for a
+ * given vport.
+ */
+static void idpf_ptp_release_vport_tstamp(struct idpf_vport *vport)
+{
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp;
+	struct list_head *head;
+
+	cancel_work_sync(&vport->tstamp_task);
+
+	/* Remove list with free latches */
+	spin_lock_bh(&vport->tx_tstamp_caps->latches_lock);
+
+	head = &vport->tx_tstamp_caps->latches_free;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	/* Remove list with latches in use */
+	head = &vport->tx_tstamp_caps->latches_in_use;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	spin_unlock_bh(&vport->tx_tstamp_caps->latches_lock);
+
+	kfree(vport->tx_tstamp_caps);
+	vport->tx_tstamp_caps = NULL;
+}
+
+/**
+ * idpf_ptp_release_tstamp - Release the Tx timestamps trackers
+ * @adapter: Driver specific private structure
+ *
+ * Remove the queues and delete lists that tracks Tx timestamp entries.
+ */
+static void idpf_ptp_release_tstamp(struct idpf_adapter *adapter)
+{
+	idpf_for_each_vport(adapter, vport) {
+		if (!idpf_ptp_is_vport_tx_tstamp_ena(vport))
+			continue;
+
+		idpf_ptp_release_vport_tstamp(vport);
+	}
+}
+
+/**
+ * idpf_ptp_get_txq_tstamp_capability - Verify the timestamping capability
+ *					for a given tx queue.
+ * @txq: Transmit queue
+ *
+ * Since performing timestamp flows requires reading the device clock value and
+ * the support in the Control Plane, the function checks both factors and
+ * summarizes the support for the timestamping.
+ *
+ * Return: true if the timestamping is supported, false otherwise.
+ */
+bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq)
+{
+	if (!txq || !txq->cached_tstamp_caps)
+		return false;
+	else if (txq->cached_tstamp_caps->access)
+		return true;
+	else
+		return false;
+}
+
+/**
+ * idpf_ptp_init - Initialize PTP hardware clock support
+ * @adapter: Driver specific private structure
+ *
+ * Set up the device for interacting with the PTP hardware clock for all
+ * functions. Function will allocate and register a ptp_clock with the
+ * PTP_1588_CLOCK infrastructure.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_init(struct idpf_adapter *adapter)
+{
+	struct timespec64 ts;
+	int err;
+
+	if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP)) {
+		pci_dbg(adapter->pdev, "PTP capability is not detected\n");
+		return -EOPNOTSUPP;
+	}
+
+	adapter->ptp = kzalloc(sizeof(*adapter->ptp), GFP_KERNEL);
+	if (!adapter->ptp)
+		return -ENOMEM;
+
+	/* add a back pointer to adapter */
+	adapter->ptp->adapter = adapter;
+
+	if (adapter->dev_ops.reg_ops.ptp_reg_init)
+		adapter->dev_ops.reg_ops.ptp_reg_init(adapter);
+
+	err = idpf_ptp_get_caps(adapter);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to get PTP caps err %d\n", err);
+		goto free_ptp;
+	}
+
+	err = idpf_ptp_create_clock(adapter);
+	if (err)
+		goto free_ptp;
+
+	if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		ptp_schedule_worker(adapter->ptp->clock, 0);
+
+	/* Write the default increment time value if the clock adjustments
+	 * are enabled.
+	 */
+	if (adapter->ptp->adj_dev_clk_time_access != IDPF_PTP_NONE) {
+		err = idpf_ptp_adj_dev_clk_fine(adapter,
+						adapter->ptp->base_incval);
+		if (err)
+			goto remove_clock;
+	}
+
+	/* Write the initial time value if the set time operation is enabled */
+	if (adapter->ptp->set_dev_clk_time_access != IDPF_PTP_NONE) {
+		ts = ktime_to_timespec64(ktime_get_real());
+		err = idpf_ptp_settime64(&adapter->ptp->info, &ts);
+		if (err)
+			goto remove_clock;
+	}
+
+	spin_lock_init(&adapter->ptp->read_dev_clk_lock);
+
+	pci_dbg(adapter->pdev, "PTP init successful\n");
+
+	return 0;
+
+remove_clock:
+	if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		ptp_cancel_worker_sync(adapter->ptp->clock);
+
+	ptp_clock_unregister(adapter->ptp->clock);
+	adapter->ptp->clock = NULL;
+
+free_ptp:
+	kfree(adapter->ptp);
+	adapter->ptp = NULL;
+
+	return err;
+}
+
+/**
+ * idpf_ptp_release - Clear PTP hardware clock support
+ * @adapter: Driver specific private structure
+ */
+void idpf_ptp_release(struct idpf_adapter *adapter)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+
+	if (!ptp)
+		return;
+
+	if (ptp->tx_tstamp_access != IDPF_PTP_NONE &&
+	    ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		idpf_ptp_release_tstamp(adapter);
+
+	if (ptp->clock) {
+		if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+			ptp_cancel_worker_sync(adapter->ptp->clock);
+
+		ptp_clock_unregister(ptp->clock);
+	}
+
+	kfree(ptp);
+	adapter->ptp = NULL;
+}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
new file mode 100644
index 000000000000..a876749d6116
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -0,0 +1,362 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef _IDPF_PTP_H
+#define _IDPF_PTP_H
+
+#include <linux/ptp_clock_kernel.h>
+
+/**
+ * struct idpf_ptp_cmd - PTP command masks
+ * @exec_cmd_mask: mask to trigger command execution
+ * @shtime_enable_mask: mask to enable shadow time
+ */
+struct idpf_ptp_cmd {
+	u32 exec_cmd_mask;
+	u32 shtime_enable_mask;
+};
+
+/* struct idpf_ptp_dev_clk_regs - PTP device registers
+ * @dev_clk_ns_l: low part of the device clock register
+ * @dev_clk_ns_h: high part of the device clock register
+ * @phy_clk_ns_l: low part of the PHY clock register
+ * @phy_clk_ns_h: high part of the PHY clock register
+ * @incval_l: low part of the increment value register
+ * @incval_h: high part of the increment value register
+ * @shadj_l: low part of the shadow adjust register
+ * @shadj_h: high part of the shadow adjust register
+ * @phy_incval_l: low part of the PHY increment value register
+ * @phy_incval_h: high part of the PHY increment value register
+ * @phy_shadj_l: low part of the PHY shadow adjust register
+ * @phy_shadj_h: high part of the PHY shadow adjust register
+ * @cmd: PTP command register
+ * @phy_cmd: PHY command register
+ * @cmd_sync: PTP command synchronization register
+ */
+struct idpf_ptp_dev_clk_regs {
+	/* Main clock */
+	void __iomem *dev_clk_ns_l;
+	void __iomem *dev_clk_ns_h;
+
+	/* PHY timer */
+	void __iomem *phy_clk_ns_l;
+	void __iomem *phy_clk_ns_h;
+
+	/* Main timer adjustments */
+	void __iomem *incval_l;
+	void __iomem *incval_h;
+	void __iomem *shadj_l;
+	void __iomem *shadj_h;
+
+	/* PHY timer adjustments */
+	void __iomem *phy_incval_l;
+	void __iomem *phy_incval_h;
+	void __iomem *phy_shadj_l;
+	void __iomem *phy_shadj_h;
+
+	/* Command */
+	void __iomem *cmd;
+	void __iomem *phy_cmd;
+	void __iomem *cmd_sync;
+};
+
+/**
+ * enum idpf_ptp_access - the type of access to PTP operations
+ * @IDPF_PTP_NONE: no access
+ * @IDPF_PTP_DIRECT: direct access through BAR registers
+ * @IDPF_PTP_MAILBOX: access through mailbox messages
+ */
+enum idpf_ptp_access {
+	IDPF_PTP_NONE = 0,
+	IDPF_PTP_DIRECT,
+	IDPF_PTP_MAILBOX,
+};
+
+/**
+ * struct idpf_ptp_secondary_mbx - PTP secondary mailbox
+ * @peer_mbx_q_id: PTP mailbox queue ID
+ * @peer_id: Peer ID for PTP Device Control daemon
+ * @valid: indicates whether secondary mailblox is supported by the Control
+ *	   Plane
+ */
+struct idpf_ptp_secondary_mbx {
+	u16 peer_mbx_q_id;
+	u16 peer_id;
+	bool valid:1;
+};
+
+/**
+ * enum idpf_ptp_tx_tstamp_state - Tx timestamp states
+ * @IDPF_PTP_FREE: Tx timestamp index free to use
+ * @IDPF_PTP_REQUEST: Tx timestamp index set to the Tx descriptor
+ * @IDPF_PTP_READ_VALUE: Tx timestamp value ready to be read
+ */
+enum idpf_ptp_tx_tstamp_state {
+	IDPF_PTP_FREE,
+	IDPF_PTP_REQUEST,
+	IDPF_PTP_READ_VALUE,
+};
+
+/**
+ * struct idpf_ptp_tx_tstamp_status - Parameters to track Tx timestamp
+ * @skb: the pointer to the SKB that received the completion tag
+ * @state: the state of the Tx timestamp
+ */
+struct idpf_ptp_tx_tstamp_status {
+	struct sk_buff *skb;
+	enum idpf_ptp_tx_tstamp_state state;
+};
+
+/**
+ * struct idpf_ptp_tx_tstamp - Parameters for Tx timestamping
+ * @list_member: the list member structure
+ * @tx_latch_reg_offset_l: Tx tstamp latch low register offset
+ * @tx_latch_reg_offset_h: Tx tstamp latch high register offset
+ * @skb: the pointer to the SKB for this timestamp request
+ * @tstamp: the Tx tstamp value
+ * @idx: the index of the Tx tstamp
+ */
+struct idpf_ptp_tx_tstamp {
+	struct list_head list_member;
+	u32 tx_latch_reg_offset_l;
+	u32 tx_latch_reg_offset_h;
+	struct sk_buff *skb;
+	u64 tstamp;
+	u32 idx;
+};
+
+/**
+ * struct idpf_ptp_vport_tx_tstamp_caps - Tx timestamp capabilities
+ * @vport_id: the vport id
+ * @num_entries: the number of negotiated Tx timestamp entries
+ * @tstamp_ns_lo_bit: first bit for nanosecond part of the timestamp
+ * @latches_lock: the lock to the lists of free/used timestamp indexes
+ * @status_lock: the lock to the status tracker
+ * @access: indicates an access to Tx timestamp
+ * @latches_free: the list of the free Tx timestamps latches
+ * @latches_in_use: the list of the used Tx timestamps latches
+ * @tx_tstamp_status: Tx tstamp status tracker
+ */
+struct idpf_ptp_vport_tx_tstamp_caps {
+	u32 vport_id;
+	u16 num_entries;
+	u16 tstamp_ns_lo_bit;
+	spinlock_t latches_lock;
+	spinlock_t status_lock;
+	bool access:1;
+	struct list_head latches_free;
+	struct list_head latches_in_use;
+	struct idpf_ptp_tx_tstamp_status tx_tstamp_status[];
+};
+
+/**
+ * struct idpf_ptp - PTP parameters
+ * @info: structure defining PTP hardware capabilities
+ * @clock: pointer to registered PTP clock device
+ * @adapter: back pointer to the adapter
+ * @base_incval: base increment value of the PTP clock
+ * @max_adj: maximum adjustment of the PTP clock
+ * @cmd: HW specific command masks
+ * @cached_phc_time: a cached copy of the PHC time for timestamp extension
+ * @cached_phc_jiffies: jiffies when cached_phc_time was last updated
+ * @dev_clk_regs: the set of registers to access the device clock
+ * @caps: PTP capabilities negotiated with the Control Plane
+ * @get_dev_clk_time_access: access type for getting the device clock time
+ * @set_dev_clk_time_access: access type for setting the device clock time
+ * @adj_dev_clk_time_access: access type for the adjusting the device clock
+ * @tx_tstamp_access: access type for the Tx timestamp value read
+ * @rsv: reserved bits
+ * @secondary_mbx: parameters for using dedicated PTP mailbox
+ * @read_dev_clk_lock: spinlock protecting access to the device clock read
+ *		       operation executed by the HW latch
+ */
+struct idpf_ptp {
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct idpf_adapter *adapter;
+	u64 base_incval;
+	u64 max_adj;
+	struct idpf_ptp_cmd cmd;
+	u64 cached_phc_time;
+	unsigned long cached_phc_jiffies;
+	struct idpf_ptp_dev_clk_regs dev_clk_regs;
+	u32 caps;
+	enum idpf_ptp_access get_dev_clk_time_access:2;
+	enum idpf_ptp_access set_dev_clk_time_access:2;
+	enum idpf_ptp_access adj_dev_clk_time_access:2;
+	enum idpf_ptp_access tx_tstamp_access:2;
+	u8 rsv;
+	struct idpf_ptp_secondary_mbx secondary_mbx;
+	spinlock_t read_dev_clk_lock;
+};
+
+/**
+ * idpf_ptp_info_to_adapter - get driver adapter struct from ptp_clock_info
+ * @info: pointer to ptp_clock_info struct
+ *
+ * Return: pointer to the corresponding adapter struct
+ */
+static inline struct idpf_adapter *
+idpf_ptp_info_to_adapter(const struct ptp_clock_info *info)
+{
+	const struct idpf_ptp *ptp = container_of_const(info, struct idpf_ptp,
+							info);
+	return ptp->adapter;
+}
+
+/**
+ * struct idpf_ptp_dev_timers - System time and device time values
+ * @sys_time_ns: system time value expressed in nanoseconds
+ * @dev_clk_time_ns: device clock time value expressed in nanoseconds
+ */
+struct idpf_ptp_dev_timers {
+	u64 sys_time_ns;
+	u64 dev_clk_time_ns;
+};
+
+/**
+ * idpf_ptp_is_vport_tx_tstamp_ena - Verify the Tx timestamping enablement for
+ *				     a given vport.
+ * @vport: Virtual port structure
+ *
+ * Tx timestamp capabilities are negotiated with the Control Plane only if the
+ * device clock value can be read, Tx timestamp access type is different than
+ * NONE, and the PTP clock for the adapter is created. When all those conditions
+ * are satisfied, Tx timestamp feature is enabled and tx_tstamp_caps is
+ * allocated and fulfilled.
+ *
+ * Return: true if the Tx timestamping is enabled, false otherwise.
+ */
+static inline bool idpf_ptp_is_vport_tx_tstamp_ena(struct idpf_vport *vport)
+{
+	if (!vport->tx_tstamp_caps)
+		return false;
+	else
+		return true;
+}
+
+/**
+ * idpf_ptp_is_vport_rx_tstamp_ena - Verify the Rx timestamping enablement for
+ *				     a given vport.
+ * @vport: Virtual port structure
+ *
+ * Rx timestamp feature is enabled if the PTP clock for the adapter is created
+ * and it is possible to read the value of the device clock. The second
+ * assumption comes from the need to extend the Rx timestamp value to 64 bit
+ * based on the current device clock time.
+ *
+ * Return: true if the Rx timestamping is enabled, false otherwise.
+ */
+static inline bool idpf_ptp_is_vport_rx_tstamp_ena(struct idpf_vport *vport)
+{
+	if (!vport->adapter->ptp ||
+	    vport->adapter->ptp->get_dev_clk_time_access == IDPF_PTP_NONE)
+		return false;
+	else
+		return true;
+}
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+int idpf_ptp_init(struct idpf_adapter *adapter);
+void idpf_ptp_release(struct idpf_adapter *adapter);
+int idpf_ptp_get_caps(struct idpf_adapter *adapter);
+void idpf_ptp_get_features_access(const struct idpf_adapter *adapter);
+bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq);
+int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			      struct idpf_ptp_dev_timers *dev_clk_time);
+int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time);
+int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval);
+int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta);
+int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport);
+int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport);
+int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+				struct kernel_hwtstamp_config *config);
+u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp);
+u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp);
+int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			u32 *idx);
+void idpf_tstamp_task(struct work_struct *work);
+#else /* CONFIG_PTP_1588_CLOCK */
+static inline int idpf_ptp_init(struct idpf_adapter *adapter)
+{
+	return 0;
+}
+
+static inline void idpf_ptp_release(struct idpf_adapter *adapter) { }
+
+static inline int idpf_ptp_get_caps(struct idpf_adapter *adapter)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+idpf_ptp_get_features_access(const struct idpf_adapter *adapter) { }
+
+static inline bool
+idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq)
+{
+	return false;
+}
+
+static inline int
+idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			  struct idpf_ptp_dev_timers *dev_clk_time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter,
+					    u64 time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter,
+					    u64 incval)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter,
+					    s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+			    struct kernel_hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u32 in_tstamp)
+{
+	return 0;
+}
+
+static inline u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time,
+						    u32 in_timestamp)
+{
+	return 0;
+}
+
+static inline int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q,
+				      struct sk_buff *skb, u32 *idx)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void idpf_tstamp_task(struct work_struct *work) { }
+#endif /* CONFIG_PTP_1588_CLOCK */
+#endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index dfd7cf1d9aa0..993c354aa27a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -362,17 +362,18 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 {
 	struct idpf_tx_offload_params offload = { };
 	struct idpf_tx_buf *first;
+	int csum, tso, needed;
 	unsigned int count;
 	__be16 protocol;
-	int csum, tso;
 
 	count = idpf_tx_desc_count_required(tx_q, skb);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
-	if (idpf_tx_maybe_stop_common(tx_q,
-				      count + IDPF_TX_DESCS_PER_CACHE_LINE +
-				      IDPF_TX_DESCS_FOR_CTX)) {
+	needed = count + IDPF_TX_DESCS_PER_CACHE_LINE + IDPF_TX_DESCS_FOR_CTX;
+	if (!netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+				       IDPF_DESC_UNUSED(tx_q),
+				       needed, needed)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
 		u64_stats_update_begin(&tx_q->stats_sync);
@@ -595,7 +596,7 @@ static bool idpf_rx_singleq_is_non_eop(const union virtchnl2_rx_desc *rx_desc)
  */
 static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq,
 				 struct sk_buff *skb,
-				 struct idpf_rx_csum_decoded csum_bits,
+				 struct libeth_rx_csum csum_bits,
 				 struct libeth_rx_pt decoded)
 {
 	bool ipv4, ipv6;
@@ -661,10 +662,10 @@ checksum_fail:
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits = { };
+	struct libeth_rx_csum csum_bits = { };
 	u32 rx_error, rx_status;
 	u64 qword;
 
@@ -696,10 +697,10 @@ idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc)
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_singleq_flex_csum(const union virtchnl2_rx_desc *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits = { };
+	struct libeth_rx_csum csum_bits = { };
 	u16 rx_status0, rx_status1;
 
 	rx_status0 = le16_to_cpu(rx_desc->flex_nic_wb.status_error0);
@@ -798,7 +799,7 @@ idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q,
 				   u16 ptype)
 {
 	struct libeth_rx_pt decoded = rx_q->rx_ptype_lkup[ptype];
-	struct idpf_rx_csum_decoded csum_bits;
+	struct libeth_rx_csum csum_bits;
 
 	/* modifies the skb - consumes the enet header */
 	skb->protocol = eth_type_trans(skb, rx_q->netdev);
@@ -900,14 +901,14 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q,
  */
 static void
 idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
-				    struct idpf_rx_extracted *fields)
+				    struct libeth_rqe_info *fields)
 {
 	u64 qword;
 
 	qword = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len);
 
-	fields->size = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword);
-	fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword);
+	fields->len = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword);
+	fields->ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword);
 }
 
 /**
@@ -923,12 +924,12 @@ idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
  */
 static void
 idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
-				    struct idpf_rx_extracted *fields)
+				    struct libeth_rqe_info *fields)
 {
-	fields->size = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M,
-				 le16_to_cpu(rx_desc->flex_nic_wb.pkt_len));
-	fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M,
-				     le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0));
+	fields->len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M,
+				le16_to_cpu(rx_desc->flex_nic_wb.pkt_len));
+	fields->ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M,
+				  le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0));
 }
 
 /**
@@ -941,7 +942,7 @@ idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
 static void
 idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q,
 			       const union virtchnl2_rx_desc *rx_desc,
-			       struct idpf_rx_extracted *fields)
+			       struct libeth_rqe_info *fields)
 {
 	if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M)
 		idpf_rx_singleq_extract_base_fields(rx_desc, fields);
@@ -966,7 +967,7 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 
 	/* Process Rx packets bounded by budget */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {
-		struct idpf_rx_extracted fields = { };
+		struct libeth_rqe_info fields = { };
 		union virtchnl2_rx_desc *rx_desc;
 		struct idpf_rx_buf *rx_buf;
 
@@ -992,13 +993,13 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 		idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields);
 
 		rx_buf = &rx_q->rx_buf[ntc];
-		if (!libeth_rx_sync_for_cpu(rx_buf, fields.size))
+		if (!libeth_rx_sync_for_cpu(rx_buf, fields.len))
 			goto skip_data;
 
 		if (skb)
-			idpf_rx_add_frag(rx_buf, skb, fields.size);
+			idpf_rx_add_frag(rx_buf, skb, fields.len);
 		else
-			skb = idpf_rx_build_skb(rx_buf, fields.size);
+			skb = idpf_rx_build_skb(rx_buf, fields.len);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb)
@@ -1033,8 +1034,8 @@ skip_data:
 		total_rx_bytes += skb->len;
 
 		/* protocol */
-		idpf_rx_singleq_process_skb_fields(rx_q, skb,
-						   rx_desc, fields.rx_ptype);
+		idpf_rx_singleq_process_skb_fields(rx_q, skb, rx_desc,
+						   fields.ptype);
 
 		/* send completed skb up the stack */
 		napi_gro_receive(rx_q->pp->p.napi, skb);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index da2a5becf62f..5cf440e09d0a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -5,6 +5,7 @@
 #include <net/libeth/tx.h>
 
 #include "idpf.h"
+#include "idpf_ptp.h"
 #include "idpf_virtchnl.h"
 
 struct idpf_tx_stash {
@@ -1107,6 +1108,8 @@ void idpf_vport_queues_rel(struct idpf_vport *vport)
  */
 static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
 {
+	struct idpf_ptp_vport_tx_tstamp_caps *caps = vport->tx_tstamp_caps;
+	struct work_struct *tstamp_task = &vport->tstamp_task;
 	int i, j, k = 0;
 
 	vport->txqs = kcalloc(vport->num_txq, sizeof(*vport->txqs),
@@ -1121,6 +1124,12 @@ static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
 		for (j = 0; j < tx_grp->num_txq; j++, k++) {
 			vport->txqs[k] = tx_grp->txqs[j];
 			vport->txqs[k]->idx = k;
+
+			if (!caps)
+				continue;
+
+			vport->txqs[k]->cached_tstamp_caps = caps;
+			vport->txqs[k]->tstamp_task = tstamp_task;
 		}
 	}
 
@@ -1655,6 +1664,40 @@ static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q)
 }
 
 /**
+ * idpf_tx_read_tstamp - schedule a work to read Tx timestamp value
+ * @txq: queue to read the timestamp from
+ * @skb: socket buffer to provide Tx timestamp value
+ *
+ * Schedule a work to read Tx timestamp value generated once the packet is
+ * transmitted.
+ */
+static void idpf_tx_read_tstamp(struct idpf_tx_queue *txq, struct sk_buff *skb)
+{
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct idpf_ptp_tx_tstamp_status *tx_tstamp_status;
+
+	tx_tstamp_caps = txq->cached_tstamp_caps;
+	spin_lock_bh(&tx_tstamp_caps->status_lock);
+
+	for (u32 i = 0; i < tx_tstamp_caps->num_entries; i++) {
+		tx_tstamp_status = &tx_tstamp_caps->tx_tstamp_status[i];
+		if (tx_tstamp_status->state != IDPF_PTP_FREE)
+			continue;
+
+		tx_tstamp_status->skb = skb;
+		tx_tstamp_status->state = IDPF_PTP_REQUEST;
+
+		/* Fetch timestamp from completion descriptor through
+		 * virtchnl msg to report to stack.
+		 */
+		queue_work(system_unbound_wq, txq->tstamp_task);
+		break;
+	}
+
+	spin_unlock_bh(&tx_tstamp_caps->status_lock);
+}
+
+/**
  * idpf_tx_clean_stashed_bufs - clean bufs that were stored for
  * out of order completions
  * @txq: queue to clean
@@ -1682,6 +1725,11 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
 			continue;
 
 		hash_del(&stash->hlist);
+
+		if (stash->buf.type == LIBETH_SQE_SKB &&
+		    (skb_shinfo(stash->buf.skb)->tx_flags & SKBTX_IN_PROGRESS))
+			idpf_tx_read_tstamp(txq, stash->buf.skb);
+
 		libeth_tx_complete(&stash->buf, &cp);
 
 		/* Push shadow buf back onto stack */
@@ -1876,8 +1924,12 @@ static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
 		     idpf_tx_buf_compl_tag(tx_buf) != compl_tag))
 		return false;
 
-	if (tx_buf->type == LIBETH_SQE_SKB)
+	if (tx_buf->type == LIBETH_SQE_SKB) {
+		if (skb_shinfo(tx_buf->skb)->tx_flags & SKBTX_IN_PROGRESS)
+			idpf_tx_read_tstamp(txq, tx_buf->skb);
+
 		libeth_tx_complete(tx_buf, &cp);
+	}
 
 	idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
 
@@ -2127,11 +2179,24 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 				    struct idpf_tx_splitq_params *params,
 				    u16 td_cmd, u16 size)
 {
-	desc->flow.qw1.cmd_dtype = (u16)params->dtype | td_cmd;
+	*(u32 *)&desc->flow.qw1.cmd_dtype = (u8)(params->dtype | td_cmd);
 	desc->flow.qw1.rxr_bufsize = cpu_to_le16((u16)size);
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
 
+/* Global conditions to tell whether the txq (and related resources)
+ * has room to allow the use of "size" descriptors.
+ */
+static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
+{
+	if (IDPF_DESC_UNUSED(tx_q) < size ||
+	    IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
+		IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq) ||
+	    IDPF_TX_BUF_RSV_LOW(tx_q))
+		return 0;
+	return 1;
+}
+
 /**
  * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
  * @tx_q: the queue to be checked
@@ -2142,29 +2207,11 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
 				     unsigned int descs_needed)
 {
-	if (idpf_tx_maybe_stop_common(tx_q, descs_needed))
-		goto out;
-
-	/* If there are too many outstanding completions expected on the
-	 * completion queue, stop the TX queue to give the device some time to
-	 * catch up
-	 */
-	if (unlikely(IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
-		     IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq)))
-		goto splitq_stop;
-
-	/* Also check for available book keeping buffers; if we are low, stop
-	 * the queue to wait for more completions
-	 */
-	if (unlikely(IDPF_TX_BUF_RSV_LOW(tx_q)))
-		goto splitq_stop;
-
-	return 0;
-
-splitq_stop:
-	netif_stop_subqueue(tx_q->netdev, tx_q->idx);
+	if (netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+				      idpf_txq_has_room(tx_q, descs_needed),
+				      1, 1))
+		return 0;
 
-out:
 	u64_stats_update_begin(&tx_q->stats_sync);
 	u64_stats_inc(&tx_q->q_stats.q_busy);
 	u64_stats_update_end(&tx_q->stats_sync);
@@ -2190,12 +2237,6 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 	tx_q->next_to_use = val;
 
-	if (idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED)) {
-		u64_stats_update_begin(&tx_q->stats_sync);
-		u64_stats_inc(&tx_q->q_stats.q_busy);
-		u64_stats_update_end(&tx_q->stats_sync);
-	}
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
@@ -2296,7 +2337,7 @@ void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
 		 * descriptor. Reset that here.
 		 */
 		tx_desc = &txq->flex_tx[idx];
-		memset(tx_desc, 0, sizeof(struct idpf_flex_tx_ctx_desc));
+		memset(tx_desc, 0, sizeof(*tx_desc));
 		if (idx == 0)
 			idx = txq->desc_count;
 		idx--;
@@ -2448,6 +2489,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 			 * rest of the packet.
 			 */
 			tx_buf->type = LIBETH_SQE_EMPTY;
+			idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
 
 			/* Adjust the DMA offset and the remaining size of the
 			 * fragment.  On the first iteration of this loop,
@@ -2698,10 +2740,10 @@ static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
  * Since the TX buffer rings mimics the descriptor ring, update the tx buffer
  * ring entry to reflect that this index is a context descriptor
  */
-static struct idpf_flex_tx_ctx_desc *
+static union idpf_flex_tx_ctx_desc *
 idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
 {
-	struct idpf_flex_tx_ctx_desc *desc;
+	union idpf_flex_tx_ctx_desc *desc;
 	int i = txq->next_to_use;
 
 	txq->tx_buf[i].type = LIBETH_SQE_CTX;
@@ -2731,6 +2773,73 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb)
 	return NETDEV_TX_OK;
 }
 
+#if (IS_ENABLED(CONFIG_PTP_1588_CLOCK))
+/**
+ * idpf_tx_tstamp - set up context descriptor for hardware timestamp
+ * @tx_q: queue to send buffer on
+ * @skb: pointer to the SKB we're sending
+ * @off: pointer to the offload struct
+ *
+ * Return: Positive index number on success, negative otherwise.
+ */
+static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			  struct idpf_tx_offload_params *off)
+{
+	int err, idx;
+
+	/* only timestamp the outbound packet if the user has requested it */
+	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
+		return -1;
+
+	if (!idpf_ptp_get_txq_tstamp_capability(tx_q))
+		return -1;
+
+	/* Tx timestamps cannot be sampled when doing TSO */
+	if (off->tx_flags & IDPF_TX_FLAGS_TSO)
+		return -1;
+
+	/* Grab an open timestamp slot */
+	err = idpf_ptp_request_ts(tx_q, skb, &idx);
+	if (err) {
+		u64_stats_update_begin(&tx_q->stats_sync);
+		u64_stats_inc(&tx_q->q_stats.tstamp_skipped);
+		u64_stats_update_end(&tx_q->stats_sync);
+
+		return -1;
+	}
+
+	off->tx_flags |= IDPF_TX_FLAGS_TSYN;
+
+	return idx;
+}
+
+/**
+ * idpf_tx_set_tstamp_desc - Set the Tx descriptor fields needed to generate
+ *			     PHY Tx timestamp
+ * @ctx_desc: Context descriptor
+ * @idx: Index of the Tx timestamp latch
+ */
+static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
+				    u32 idx)
+{
+	ctx_desc->tsyn.qw1 = le64_encode_bits(IDPF_TX_DESC_DTYPE_CTX,
+					      IDPF_TX_CTX_DTYPE_M) |
+			     le64_encode_bits(IDPF_TX_CTX_DESC_TSYN,
+					      IDPF_TX_CTX_CMD_M) |
+			     le64_encode_bits(idx, IDPF_TX_CTX_TSYN_REG_M);
+}
+#else /* CONFIG_PTP_1588_CLOCK */
+static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			  struct idpf_tx_offload_params *off)
+{
+	return -1;
+}
+
+static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
+				    u32 idx)
+{ }
+#endif /* CONFIG_PTP_1588_CLOCK */
+
 /**
  * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors
  * @skb: send buffer
@@ -2742,9 +2851,10 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 					struct idpf_tx_queue *tx_q)
 {
 	struct idpf_tx_splitq_params tx_params = { };
+	union idpf_flex_tx_ctx_desc *ctx_desc;
 	struct idpf_tx_buf *first;
 	unsigned int count;
-	int tso;
+	int tso, idx;
 
 	count = idpf_tx_desc_count_required(tx_q, skb);
 	if (unlikely(!count))
@@ -2764,8 +2874,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 	if (tso) {
 		/* If tso is needed, set up context desc */
-		struct idpf_flex_tx_ctx_desc *ctx_desc =
-			idpf_tx_splitq_get_ctx_desc(tx_q);
+		ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q);
 
 		ctx_desc->tso.qw1.cmd_dtype =
 				cpu_to_le16(IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX |
@@ -2783,6 +2892,12 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		u64_stats_update_end(&tx_q->stats_sync);
 	}
 
+	idx = idpf_tx_tstamp(tx_q, skb, &tx_params.offload);
+	if (idx != -1) {
+		ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q);
+		idpf_tx_set_tstamp_desc(ctx_desc, idx);
+	}
+
 	/* record the location of the first descriptor for this packet */
 	first = &tx_q->tx_buf[tx_q->next_to_use];
 	first->skb = skb;
@@ -2894,7 +3009,7 @@ idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb,
  * skb->protocol must be set before this function is called
  */
 static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
-			 struct idpf_rx_csum_decoded csum_bits,
+			 struct libeth_rx_csum csum_bits,
 			 struct libeth_rx_pt decoded)
 {
 	bool ipv4, ipv6;
@@ -2922,7 +3037,7 @@ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	if (unlikely(csum_bits.l4e))
 		goto checksum_fail;
 
-	if (csum_bits.raw_csum_inv ||
+	if (!csum_bits.raw_csum_valid ||
 	    decoded.inner_prot == LIBETH_RX_PT_INNER_SCTP) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		return;
@@ -2945,10 +3060,10 @@ checksum_fail:
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum = { };
+	struct libeth_rx_csum csum = { };
 	u8 qword0, qword1;
 
 	qword0 = rx_desc->status_err0_qw0;
@@ -2964,9 +3079,9 @@ idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *
 			       qword1);
 	csum.ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M,
 				   qword0);
-	csum.raw_csum_inv =
-		le16_get_bits(rx_desc->ptype_err_fflags0,
-			      VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M);
+	csum.raw_csum_valid =
+		!le16_get_bits(rx_desc->ptype_err_fflags0,
+			       VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M);
 	csum.raw_csum = le16_to_cpu(rx_desc->misc.raw_cs);
 
 	return csum;
@@ -3007,14 +3122,11 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 		return -EINVAL;
 
 	rsc_segments = DIV_ROUND_UP(skb->data_len, rsc_seg_len);
-	if (unlikely(rsc_segments == 1))
-		return 0;
 
 	NAPI_GRO_CB(skb)->count = rsc_segments;
 	skb_shinfo(skb)->gso_size = rsc_seg_len;
 
 	skb_reset_network_header(skb);
-	len = skb->len - skb_transport_offset(skb);
 
 	if (ipv4) {
 		struct iphdr *ipv4h = ip_hdr(skb);
@@ -3023,6 +3135,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		/* Reset and set transport header offset in skb */
 		skb_set_transport_header(skb, sizeof(struct iphdr));
+		len = skb->len - skb_transport_offset(skb);
 
 		/* Compute the TCP pseudo header checksum*/
 		tcp_hdr(skb)->check =
@@ -3032,6 +3145,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 		skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+		len = skb->len - skb_transport_offset(skb);
 		tcp_hdr(skb)->check =
 			~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0);
 	}
@@ -3046,6 +3160,33 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 }
 
 /**
+ * idpf_rx_hwtstamp - check for an RX timestamp and pass up the stack
+ * @rxq: pointer to the rx queue that receives the timestamp
+ * @rx_desc: pointer to rx descriptor containing timestamp
+ * @skb: skb to put timestamp in
+ */
+static void
+idpf_rx_hwtstamp(const struct idpf_rx_queue *rxq,
+		 const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
+		 struct sk_buff *skb)
+{
+	u64 cached_time, ts_ns;
+	u32 ts_high;
+
+	if (!(rx_desc->ts_low & VIRTCHNL2_RX_FLEX_TSTAMP_VALID))
+		return;
+
+	cached_time = READ_ONCE(rxq->cached_phc_time);
+
+	ts_high = le32_to_cpu(rx_desc->ts_high);
+	ts_ns = idpf_ptp_tstamp_extend_32b_to_64b(cached_time, ts_high);
+
+	*skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) {
+		.hwtstamp = ns_to_ktime(ts_ns),
+	};
+}
+
+/**
  * idpf_rx_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rxq: Rx descriptor ring packet is being transacted on
  * @skb: pointer to current skb being populated
@@ -3059,7 +3200,7 @@ static int
 idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 			   const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits;
+	struct libeth_rx_csum csum_bits;
 	struct libeth_rx_pt decoded;
 	u16 rx_ptype;
 
@@ -3070,7 +3211,11 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	/* process RSS/hash */
 	idpf_rx_hash(rxq, skb, rx_desc, decoded);
 
+	if (idpf_queue_has(PTP, rxq))
+		idpf_rx_hwtstamp(rxq, rx_desc, skb);
+
 	skb->protocol = eth_type_trans(skb, rxq->netdev);
+	skb_record_rx_queue(skb, rxq->idx);
 
 	if (le16_get_bits(rx_desc->hdrlen_flags,
 			  VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M))
@@ -3079,8 +3224,6 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	csum_bits = idpf_rx_splitq_extract_csum_bits(rx_desc);
 	idpf_rx_csum(rxq, skb, csum_bits, decoded);
 
-	skb_record_rx_queue(skb, rxq->idx);
-
 	return 0;
 }
 
@@ -3553,8 +3696,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport)
 		q_vector->tx = NULL;
 		kfree(q_vector->rx);
 		q_vector->rx = NULL;
-
-		free_cpumask_var(q_vector->affinity_mask);
 	}
 
 	kfree(vport->q_vectors);
@@ -3581,8 +3722,6 @@ static void idpf_vport_intr_rel_irq(struct idpf_vport *vport)
 		vidx = vport->q_vector_idxs[vector];
 		irq_num = adapter->msix_entries[vidx].vector;
 
-		/* clear the affinity_mask in the IRQ descriptor */
-		irq_set_affinity_hint(irq_num, NULL);
 		kfree(free_irq(irq_num, q_vector));
 	}
 }
@@ -3603,21 +3742,31 @@ static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport)
 /**
  * idpf_vport_intr_buildreg_itr - Enable default interrupt generation settings
  * @q_vector: pointer to q_vector
- * @type: itr index
- * @itr: itr value
  */
-static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector,
-					const int type, u16 itr)
+static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector)
 {
-	u32 itr_val;
+	u32 itr_val = q_vector->intr_reg.dyn_ctl_intena_m;
+	int type = IDPF_NO_ITR_UPDATE_IDX;
+	u16 itr = 0;
+
+	if (q_vector->wb_on_itr) {
+		/*
+		 * Trigger a software interrupt when exiting wb_on_itr, to make
+		 * sure we catch any pending write backs that might have been
+		 * missed due to interrupt state transition.
+		 */
+		itr_val |= q_vector->intr_reg.dyn_ctl_swint_trig_m |
+			   q_vector->intr_reg.dyn_ctl_sw_itridx_ena_m;
+		type = IDPF_SW_ITR_UPDATE_IDX;
+		itr = IDPF_ITR_20K;
+	}
 
 	itr &= IDPF_ITR_MASK;
 	/* Don't clear PBA because that can cause lost interrupts that
 	 * came in while we were cleaning/polling
 	 */
-	itr_val = q_vector->intr_reg.dyn_ctl_intena_m |
-		  (type << q_vector->intr_reg.dyn_ctl_itridx_s) |
-		  (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1));
+	itr_val |= (type << q_vector->intr_reg.dyn_ctl_itridx_s) |
+		   (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1));
 
 	return itr_val;
 }
@@ -3715,9 +3864,8 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector)
 	/* net_dim() updates ITR out-of-band using a work item */
 	idpf_net_dim(q_vector);
 
+	intval = idpf_vport_intr_buildreg_itr(q_vector);
 	q_vector->wb_on_itr = false;
-	intval = idpf_vport_intr_buildreg_itr(q_vector,
-					      IDPF_NO_ITR_UPDATE_IDX, 0);
 
 	writel(intval, q_vector->intr_reg.dyn_ctl);
 }
@@ -3761,8 +3909,6 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport)
 				   "Request_irq failed, error: %d\n", err);
 			goto free_q_irqs;
 		}
-		/* assign the mask for this irq */
-		irq_set_affinity_hint(irq_num, q_vector->affinity_mask);
 	}
 
 	return 0;
@@ -4023,6 +4169,14 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 		return budget;
 	}
 
+	/* Switch to poll mode in the tear-down path after sending disable
+	 * queues virtchnl message, as the interrupts will be disabled after
+	 * that.
+	 */
+	if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
+							 q_vector->tx[0])))
+		return budget;
+
 	work_done = min_t(int, work_done, budget - 1);
 
 	/* Exit the polling mode, but don't re-enable interrupts if stack might
@@ -4033,15 +4187,7 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 	else
 		idpf_vport_intr_set_wb_on_itr(q_vector);
 
-	/* Switch to poll mode in the tear-down path after sending disable
-	 * queues virtchnl message, as the interrupts will be disabled after
-	 * that
-	 */
-	if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
-							 q_vector->tx[0])))
-		return budget;
-	else
-		return work_done;
+	return work_done;
 }
 
 /**
@@ -4174,7 +4320,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport)
 static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 {
 	int (*napi_poll)(struct napi_struct *napi, int budget);
-	u16 v_idx;
+	u16 v_idx, qv_idx;
+	int irq_num;
 
 	if (idpf_is_queue_model_split(vport->txq_model))
 		napi_poll = idpf_vport_splitq_napi_poll;
@@ -4183,12 +4330,12 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 
 	for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
 		struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx];
+		qv_idx = vport->q_vector_idxs[v_idx];
+		irq_num = vport->adapter->msix_entries[qv_idx].vector;
 
-		netif_napi_add(vport->netdev, &q_vector->napi, napi_poll);
-
-		/* only set affinity_mask if the CPU is online */
-		if (cpu_online(v_idx))
-			cpumask_set_cpu(v_idx, q_vector->affinity_mask);
+		netif_napi_add_config(vport->netdev, &q_vector->napi,
+				      napi_poll, v_idx);
+		netif_napi_set_irq(&q_vector->napi, irq_num);
 	}
 }
 
@@ -4232,9 +4379,6 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
 		q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC;
 		q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0;
 
-		if (!zalloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL))
-			goto error;
-
 		q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx),
 				       GFP_KERNEL);
 		if (!q_vector->tx)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 9c1fe84108ed..36a0f828a6f8 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -142,6 +142,7 @@ do {								\
 #define IDPF_TX_FLAGS_IPV4		BIT(1)
 #define IDPF_TX_FLAGS_IPV6		BIT(2)
 #define IDPF_TX_FLAGS_TUNNEL		BIT(3)
+#define IDPF_TX_FLAGS_TSYN		BIT(4)
 
 union idpf_tx_flex_desc {
 	struct idpf_flex_tx_desc q; /* queue based scheduling */
@@ -213,25 +214,6 @@ enum idpf_tx_ctx_desc_eipt_offload {
 	IDPF_TX_CTX_EXT_IP_IPV4         = 0x3
 };
 
-/* Checksum offload bits decoded from the receive descriptor. */
-struct idpf_rx_csum_decoded {
-	u32 l3l4p : 1;
-	u32 ipe : 1;
-	u32 eipe : 1;
-	u32 eudpe : 1;
-	u32 ipv6exadd : 1;
-	u32 l4e : 1;
-	u32 pprs : 1;
-	u32 nat : 1;
-	u32 raw_csum_inv : 1;
-	u32 raw_csum : 16;
-};
-
-struct idpf_rx_extracted {
-	unsigned int size;
-	u16 rx_ptype;
-};
-
 #define IDPF_TX_COMPLQ_CLEAN_BUDGET	256
 #define IDPF_TX_MIN_PKT_LEN		17
 #define IDPF_TX_DESCS_FOR_SKB_DATA_PTR	1
@@ -308,6 +290,8 @@ struct idpf_ptype_state {
  * @__IDPF_Q_POLL_MODE: Enable poll mode
  * @__IDPF_Q_CRC_EN: enable CRC offload in singleq mode
  * @__IDPF_Q_HSPLIT_EN: enable header split on Rx (splitq)
+ * @__IDPF_Q_PTP: indicates whether the Rx timestamping is enabled for the
+ *		  queue
  * @__IDPF_Q_FLAGS_NBITS: Must be last
  */
 enum idpf_queue_flags_t {
@@ -318,6 +302,7 @@ enum idpf_queue_flags_t {
 	__IDPF_Q_POLL_MODE,
 	__IDPF_Q_CRC_EN,
 	__IDPF_Q_HSPLIT_EN,
+	__IDPF_Q_PTP,
 
 	__IDPF_Q_FLAGS_NBITS,
 };
@@ -354,6 +339,8 @@ struct idpf_vec_regs {
  * @dyn_ctl_itridx_m: Mask for ITR index
  * @dyn_ctl_intrvl_s: Register bit offset for ITR interval
  * @dyn_ctl_wb_on_itr_m: Mask for WB on ITR feature
+ * @dyn_ctl_sw_itridx_ena_m: Mask for SW ITR index
+ * @dyn_ctl_swint_trig_m: Mask for dyn_ctl SW triggered interrupt enable
  * @rx_itr: RX ITR register
  * @tx_itr: TX ITR register
  * @icr_ena: Interrupt cause register offset
@@ -367,6 +354,8 @@ struct idpf_intr_reg {
 	u32 dyn_ctl_itridx_m;
 	u32 dyn_ctl_intrvl_s;
 	u32 dyn_ctl_wb_on_itr_m;
+	u32 dyn_ctl_sw_itridx_ena_m;
+	u32 dyn_ctl_swint_trig_m;
 	void __iomem *rx_itr;
 	void __iomem *tx_itr;
 	void __iomem *icr_ena;
@@ -397,7 +386,6 @@ struct idpf_intr_reg {
  * @rx_intr_mode: Dynamic ITR or not
  * @rx_itr_idx: RX ITR index
  * @v_idx: Vector index
- * @affinity_mask: CPU affinity mask
  */
 struct idpf_q_vector {
 	__cacheline_group_begin_aligned(read_mostly);
@@ -434,13 +422,12 @@ struct idpf_q_vector {
 	__cacheline_group_begin_aligned(cold);
 	u16 v_idx;
 
-	cpumask_var_t affinity_mask;
 	__cacheline_group_end_aligned(cold);
 };
-libeth_cacheline_set_assert(struct idpf_q_vector, 112,
+libeth_cacheline_set_assert(struct idpf_q_vector, 120,
 			    24 + sizeof(struct napi_struct) +
 			    2 * sizeof(struct dim),
-			    8 + sizeof(cpumask_var_t));
+			    8);
 
 struct idpf_rx_queue_stats {
 	u64_stats_t packets;
@@ -460,6 +447,7 @@ struct idpf_tx_queue_stats {
 	u64_stats_t q_busy;
 	u64_stats_t skb_drops;
 	u64_stats_t dma_map_errs;
+	u64_stats_t tstamp_skipped;
 };
 
 #define IDPF_ITR_DYNAMIC	1
@@ -471,6 +459,8 @@ struct idpf_tx_queue_stats {
 #define IDPF_ITR_IS_DYNAMIC(itr_mode) (itr_mode)
 #define IDPF_ITR_TX_DEF		IDPF_ITR_20K
 #define IDPF_ITR_RX_DEF		IDPF_ITR_20K
+/* Index used for 'SW ITR' update in DYN_CTL register */
+#define IDPF_SW_ITR_UPDATE_IDX	2
 /* Index used for 'No ITR' update in DYN_CTL register */
 #define IDPF_NO_ITR_UPDATE_IDX	3
 #define IDPF_ITR_IDX_SPACING(spacing, dflt)	(spacing ? spacing : dflt)
@@ -509,6 +499,7 @@ struct idpf_txq_stash {
  * @next_to_alloc: RX buffer to allocate at
  * @skb: Pointer to the skb
  * @truesize: data buffer truesize in singleq
+ * @cached_phc_time: Cached PHC time for the Rx queue
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_rx_queue_stats
  * @q_id: Queue id
@@ -556,6 +547,7 @@ struct idpf_rx_queue {
 
 	struct sk_buff *skb;
 	u32 truesize;
+	u64 cached_phc_time;
 
 	struct u64_stats_sync stats_sync;
 	struct idpf_rx_queue_stats q_stats;
@@ -575,7 +567,7 @@ struct idpf_rx_queue {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
-			    80 + sizeof(struct u64_stats_sync),
+			    88 + sizeof(struct u64_stats_sync),
 			    32);
 
 /**
@@ -632,6 +624,8 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @compl_tag_bufid_m: Completion tag buffer id mask
  * @compl_tag_cur_gen: Used to keep track of current completion tag generation
  * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
+ * @cached_tstamp_caps: Tx timestamp capabilities negotiated with the CP
+ * @tstamp_task: Work that handles Tx timestamp read
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_tx_queue_stats
  * @q_id: Queue id
@@ -645,7 +639,7 @@ struct idpf_tx_queue {
 		struct idpf_base_tx_desc *base_tx;
 		struct idpf_base_tx_ctx_desc *base_ctx;
 		union idpf_tx_flex_desc *flex_tx;
-		struct idpf_flex_tx_ctx_desc *flex_ctx;
+		union idpf_flex_tx_ctx_desc *flex_ctx;
 
 		void *desc_ring;
 	};
@@ -681,6 +675,9 @@ struct idpf_tx_queue {
 	u16 compl_tag_cur_gen;
 	u16 compl_tag_gen_max;
 
+	struct idpf_ptp_vport_tx_tstamp_caps *cached_tstamp_caps;
+	struct work_struct *tstamp_task;
+
 	struct u64_stats_sync stats_sync;
 	struct idpf_tx_queue_stats q_stats;
 	__cacheline_group_end_aligned(read_write);
@@ -694,7 +691,7 @@ struct idpf_tx_queue {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
-			    88 + sizeof(struct u64_stats_sync),
+			    112 + sizeof(struct u64_stats_sync),
 			    24);
 
 /**
@@ -934,7 +931,7 @@ static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector)
 	if (!q_vector)
 		return NUMA_NO_NODE;
 
-	cpu = cpumask_first(q_vector->affinity_mask);
+	cpu = cpumask_first(&q_vector->napi.config->affinity_mask);
 
 	return cpu < nr_cpu_ids ? cpu_to_mem(cpu) : NUMA_NO_NODE;
 }
@@ -1052,12 +1049,4 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rxq,
 				      u16 cleaned_count);
 int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off);
 
-static inline bool idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q,
-					     u32 needed)
-{
-	return !netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
-					  IDPF_DESC_UNUSED(tx_q),
-					  needed, needed);
-}
-
 #endif /* !_IDPF_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
index aad62e270ae4..aba828abcb17 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
@@ -101,6 +101,9 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport)
 		intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S;
 		intr->dyn_ctl_intrvl_s = VF_INT_DYN_CTLN_INTERVAL_S;
 		intr->dyn_ctl_wb_on_itr_m = VF_INT_DYN_CTLN_WB_ON_ITR_M;
+		intr->dyn_ctl_swint_trig_m = VF_INT_DYN_CTLN_SWINT_TRIG_M;
+		intr->dyn_ctl_sw_itridx_ena_m =
+			VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_M;
 
 		spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing,
 					       IDPF_VF_ITR_IDX_SPACING);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index d46c95f91b0d..24febaaa8fbb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -5,88 +5,7 @@
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
-
-#define IDPF_VC_XN_MIN_TIMEOUT_MSEC	2000
-#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
-#define IDPF_VC_XN_IDX_M		GENMASK(7, 0)
-#define IDPF_VC_XN_SALT_M		GENMASK(15, 8)
-#define IDPF_VC_XN_RING_LEN		U8_MAX
-
-/**
- * enum idpf_vc_xn_state - Virtchnl transaction status
- * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used
- * @IDPF_VC_XN_WAITING: expecting a reply, not yet received
- * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received,
- *				  buffer updated
- * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there
- *				 was an error, buffer not updated
- * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down
- * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the
- *		      return context; a callback may be provided to handle
- *		      return
- */
-enum idpf_vc_xn_state {
-	IDPF_VC_XN_IDLE = 1,
-	IDPF_VC_XN_WAITING,
-	IDPF_VC_XN_COMPLETED_SUCCESS,
-	IDPF_VC_XN_COMPLETED_FAILED,
-	IDPF_VC_XN_SHUTDOWN,
-	IDPF_VC_XN_ASYNC,
-};
-
-struct idpf_vc_xn;
-/* Callback for asynchronous messages */
-typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
-			    const struct idpf_ctlq_msg *);
-
-/**
- * struct idpf_vc_xn - Data structure representing virtchnl transactions
- * @completed: virtchnl event loop uses that to signal when a reply is
- *	       available, uses kernel completion API
- * @state: virtchnl event loop stores the data below, protected by the
- *	   completion's lock.
- * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
- *	      truncated on its way to the receiver thread according to
- *	      reply_buf.iov_len.
- * @reply: Reference to the buffer(s) where the reply data should be written
- *	   to. May be 0-length (then NULL address permitted) if the reply data
- *	   should be ignored.
- * @async_handler: if sent asynchronously, a callback can be provided to handle
- *		   the reply when it's received
- * @vc_op: corresponding opcode sent with this transaction
- * @idx: index used as retrieval on reply receive, used for cookie
- * @salt: changed every message to make unique, used for cookie
- */
-struct idpf_vc_xn {
-	struct completion completed;
-	enum idpf_vc_xn_state state;
-	size_t reply_sz;
-	struct kvec reply;
-	async_vc_cb async_handler;
-	u32 vc_op;
-	u8 idx;
-	u8 salt;
-};
-
-/**
- * struct idpf_vc_xn_params - Parameters for executing transaction
- * @send_buf: kvec for send buffer
- * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length
- * @timeout_ms: timeout to wait for reply
- * @async: send message asynchronously, will not wait on completion
- * @async_handler: If sent asynchronously, optional callback handler. The user
- *		   must be careful when using async handlers as the memory for
- *		   the recv_buf _cannot_ be on stack if this is async.
- * @vc_op: virtchnl op to send
- */
-struct idpf_vc_xn_params {
-	struct kvec send_buf;
-	struct kvec recv_buf;
-	int timeout_ms;
-	bool async;
-	async_vc_cb async_handler;
-	u32 vc_op;
-};
+#include "idpf_ptp.h"
 
 /**
  * struct idpf_vc_xn_manager - Manager for tracking transactions
@@ -235,6 +154,55 @@ err_kfree:
 	return err;
 }
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+/**
+ * idpf_ptp_is_mb_msg - Check if the message is PTP-related
+ * @op: virtchnl opcode
+ *
+ * Return: true if msg is PTP-related, false otherwise.
+ */
+static bool idpf_ptp_is_mb_msg(u32 op)
+{
+	switch (op) {
+	case VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_GET_CROSS_TIME:
+	case VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE:
+	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS:
+	case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * idpf_prepare_ptp_mb_msg - Prepare PTP related message
+ *
+ * @adapter: Driver specific private structure
+ * @op: virtchnl opcode
+ * @ctlq_msg: Corresponding control queue message
+ */
+static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op,
+				    struct idpf_ctlq_msg *ctlq_msg)
+{
+	/* If the message is PTP-related and the secondary mailbox is available,
+	 * send the message through the secondary mailbox.
+	 */
+	if (!idpf_ptp_is_mb_msg(op) || !adapter->ptp->secondary_mbx.valid)
+		return;
+
+	ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_peer_drv;
+	ctlq_msg->func_id = adapter->ptp->secondary_mbx.peer_mbx_q_id;
+	ctlq_msg->host_id = adapter->ptp->secondary_mbx.peer_id;
+}
+#else /* !CONFIG_PTP_1588_CLOCK */
+static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op,
+				    struct idpf_ctlq_msg *ctlq_msg)
+{ }
+#endif /* CONFIG_PTP_1588_CLOCK */
+
 /**
  * idpf_send_mb_msg - Send message over mailbox
  * @adapter: Driver specific private structure
@@ -278,6 +246,9 @@ int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op,
 
 	ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_cp;
 	ctlq_msg->func_id = 0;
+
+	idpf_prepare_ptp_mb_msg(adapter, op, ctlq_msg);
+
 	ctlq_msg->data_len = msg_size;
 	ctlq_msg->cookie.mbx.chnl_opcode = op;
 	ctlq_msg->cookie.mbx.chnl_retval = 0;
@@ -376,7 +347,7 @@ static void idpf_vc_xn_init(struct idpf_vc_xn_manager *vcxn_mngr)
  * All waiting threads will be woken-up and their transaction aborted. Further
  * operations on that object will fail.
  */
-static void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr)
+void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr)
 {
 	int i;
 
@@ -449,8 +420,8 @@ static void idpf_vc_xn_push_free(struct idpf_vc_xn_manager *vcxn_mngr,
  * >= @recv_buf.iov_len, but we never overflow @@recv_buf_iov_base). < 0 for
  * error.
  */
-static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
-			       const struct idpf_vc_xn_params *params)
+ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
+			const struct idpf_vc_xn_params *params)
 {
 	const struct kvec *send_buf = &params->send_buf;
 	struct idpf_vc_xn *xn;
@@ -517,8 +488,10 @@ static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
 		retval = -ENXIO;
 		goto only_unlock;
 	case IDPF_VC_XN_WAITING:
-		dev_notice_ratelimited(&adapter->pdev->dev, "Transaction timed-out (op %d, %dms)\n",
-				       params->vc_op, params->timeout_ms);
+		dev_notice_ratelimited(&adapter->pdev->dev,
+				       "Transaction timed-out (op:%d cookie:%04x vc_op:%d salt:%02x timeout:%dms)\n",
+				       params->vc_op, cookie, xn->vc_op,
+				       xn->salt, params->timeout_ms);
 		retval = -ETIME;
 		break;
 	case IDPF_VC_XN_COMPLETED_SUCCESS:
@@ -612,14 +585,16 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter,
 		return -EINVAL;
 	}
 	xn = &adapter->vcxn_mngr->ring[xn_idx];
+	idpf_vc_xn_lock(xn);
 	salt = FIELD_GET(IDPF_VC_XN_SALT_M, msg_info);
 	if (xn->salt != salt) {
-		dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (%02x != %02x)\n",
-				    xn->salt, salt);
+		dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (exp:%d@%02x(%d) != got:%d@%02x)\n",
+				    xn->vc_op, xn->salt, xn->state,
+				    ctlq_msg->cookie.mbx.chnl_opcode, salt);
+		idpf_vc_xn_unlock(xn);
 		return -EINVAL;
 	}
 
-	idpf_vc_xn_lock(xn);
 	switch (xn->state) {
 	case IDPF_VC_XN_WAITING:
 		/* success */
@@ -896,7 +871,8 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 			    VIRTCHNL2_CAP_MACFILTER		|
 			    VIRTCHNL2_CAP_SPLITQ_QSCHED		|
 			    VIRTCHNL2_CAP_PROMISC		|
-			    VIRTCHNL2_CAP_LOOPBACK);
+			    VIRTCHNL2_CAP_LOOPBACK		|
+			    VIRTCHNL2_CAP_PTP);
 
 	xn_params.vc_op = VIRTCHNL2_OP_GET_CAPS;
 	xn_params.send_buf.iov_base = &caps;
@@ -3025,6 +3001,11 @@ restart:
 		goto err_intr_req;
 	}
 
+	err = idpf_ptp_init(adapter);
+	if (err)
+		pci_err(adapter->pdev, "PTP init failed, err=%pe\n",
+			ERR_PTR(err));
+
 	idpf_init_avail_queues(adapter);
 
 	/* Skew the delay for init tasks for each function based on fn number
@@ -3077,12 +3058,22 @@ init_failed:
  */
 void idpf_vc_core_deinit(struct idpf_adapter *adapter)
 {
+	bool remove_in_prog;
+
 	if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags))
 		return;
 
+	/* Avoid transaction timeouts when called during reset */
+	remove_in_prog = test_bit(IDPF_REMOVE_IN_PROG, adapter->flags);
+	if (!remove_in_prog)
+		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+
+	idpf_ptp_release(adapter);
 	idpf_deinit_task(adapter);
 	idpf_intr_rel(adapter);
-	idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+
+	if (remove_in_prog)
+		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
 
 	cancel_delayed_work_sync(&adapter->serv_task);
 	cancel_delayed_work_sync(&adapter->mbx_task);
@@ -3145,6 +3136,7 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	u16 rx_itr[] = {2, 8, 32, 96, 128};
 	struct idpf_rss_data *rss_data;
 	u16 idx = vport->idx;
+	int err;
 
 	vport_config = adapter->vport_config[idx];
 	rss_data = &vport_config->user_config.rss_data;
@@ -3179,6 +3171,18 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	idpf_vport_alloc_vec_indexes(vport);
 
 	vport->crc_enable = adapter->crc_enable;
+
+	if (!(vport_msg->vport_flags &
+	      cpu_to_le16(VIRTCHNL2_VPORT_UPLINK_PORT)))
+		return;
+
+	err = idpf_ptp_get_vport_tstamps_caps(vport);
+	if (err) {
+		pci_dbg(vport->adapter->pdev, "Tx timestamping not supported\n");
+		return;
+	}
+
+	INIT_WORK(&vport->tstamp_task, idpf_tstamp_task);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
index 83da5d8da56b..77578206bada 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
@@ -4,6 +4,88 @@
 #ifndef _IDPF_VIRTCHNL_H_
 #define _IDPF_VIRTCHNL_H_
 
+#define IDPF_VC_XN_MIN_TIMEOUT_MSEC	2000
+#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
+#define IDPF_VC_XN_IDX_M		GENMASK(7, 0)
+#define IDPF_VC_XN_SALT_M		GENMASK(15, 8)
+#define IDPF_VC_XN_RING_LEN		U8_MAX
+
+/**
+ * enum idpf_vc_xn_state - Virtchnl transaction status
+ * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used
+ * @IDPF_VC_XN_WAITING: expecting a reply, not yet received
+ * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received, buffer
+ *				  updated
+ * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there
+ *				 was an error, buffer not updated
+ * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down
+ * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the
+ *		      return context; a callback may be provided to handle
+ *		      return
+ */
+enum idpf_vc_xn_state {
+	IDPF_VC_XN_IDLE = 1,
+	IDPF_VC_XN_WAITING,
+	IDPF_VC_XN_COMPLETED_SUCCESS,
+	IDPF_VC_XN_COMPLETED_FAILED,
+	IDPF_VC_XN_SHUTDOWN,
+	IDPF_VC_XN_ASYNC,
+};
+
+struct idpf_vc_xn;
+/* Callback for asynchronous messages */
+typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
+			    const struct idpf_ctlq_msg *);
+
+/**
+ * struct idpf_vc_xn - Data structure representing virtchnl transactions
+ * @completed: virtchnl event loop uses that to signal when a reply is
+ *	       available, uses kernel completion API
+ * @state: virtchnl event loop stores the data below, protected by the
+ *	   completion's lock.
+ * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
+ *	      truncated on its way to the receiver thread according to
+ *	      reply_buf.iov_len.
+ * @reply: Reference to the buffer(s) where the reply data should be written
+ *	   to. May be 0-length (then NULL address permitted) if the reply data
+ *	   should be ignored.
+ * @async_handler: if sent asynchronously, a callback can be provided to handle
+ *		   the reply when it's received
+ * @vc_op: corresponding opcode sent with this transaction
+ * @idx: index used as retrieval on reply receive, used for cookie
+ * @salt: changed every message to make unique, used for cookie
+ */
+struct idpf_vc_xn {
+	struct completion completed;
+	enum idpf_vc_xn_state state;
+	size_t reply_sz;
+	struct kvec reply;
+	async_vc_cb async_handler;
+	u32 vc_op;
+	u8 idx;
+	u8 salt;
+};
+
+/**
+ * struct idpf_vc_xn_params - Parameters for executing transaction
+ * @send_buf: kvec for send buffer
+ * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length
+ * @timeout_ms: timeout to wait for reply
+ * @async: send message asynchronously, will not wait on completion
+ * @async_handler: If sent asynchronously, optional callback handler. The user
+ *		   must be careful when using async handlers as the memory for
+ *		   the recv_buf _cannot_ be on stack if this is async.
+ * @vc_op: virtchnl op to send
+ */
+struct idpf_vc_xn_params {
+	struct kvec send_buf;
+	struct kvec recv_buf;
+	int timeout_ms;
+	bool async;
+	async_vc_cb async_handler;
+	u32 vc_op;
+};
+
 struct idpf_adapter;
 struct idpf_netdev_priv;
 struct idpf_vec_regs;
@@ -11,6 +93,8 @@ struct idpf_vport;
 struct idpf_vport_max_q;
 struct idpf_vport_user_config_data;
 
+ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
+			const struct idpf_vc_xn_params *params);
 int idpf_init_dflt_mbx(struct idpf_adapter *adapter);
 void idpf_deinit_dflt_mbx(struct idpf_adapter *adapter);
 int idpf_vc_core_init(struct idpf_adapter *adapter);
@@ -66,5 +150,6 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport);
 int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs);
 int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get);
 int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get);
+void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr);
 
 #endif /* _IDPF_VIRTCHNL_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
new file mode 100644
index 000000000000..bdcc54a5fb56
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -0,0 +1,615 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_ptp.h"
+#include "idpf_virtchnl.h"
+
+/**
+ * idpf_ptp_get_caps - Send virtchnl get ptp capabilities message
+ * @adapter: Driver specific private structure
+ *
+ * Send virtchnl get PTP capabilities message.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int idpf_ptp_get_caps(struct idpf_adapter *adapter)
+{
+	struct virtchnl2_ptp_get_caps *recv_ptp_caps_msg __free(kfree) = NULL;
+	struct virtchnl2_ptp_get_caps send_ptp_caps_msg = {
+		.caps = cpu_to_le32(VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME |
+				    VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME |
+				    VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB |
+				    VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB)
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_CAPS,
+		.send_buf.iov_base = &send_ptp_caps_msg,
+		.send_buf.iov_len = sizeof(send_ptp_caps_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets;
+	struct virtchnl2_ptp_clk_reg_offsets clock_offsets;
+	struct idpf_ptp_secondary_mbx *scnd_mbx;
+	struct idpf_ptp *ptp = adapter->ptp;
+	enum idpf_ptp_access access_type;
+	u32 temp_offset;
+	int reply_sz;
+
+	recv_ptp_caps_msg = kzalloc(sizeof(struct virtchnl2_ptp_get_caps),
+				    GFP_KERNEL);
+	if (!recv_ptp_caps_msg)
+		return -ENOMEM;
+
+	xn_params.recv_buf.iov_base = recv_ptp_caps_msg;
+	xn_params.recv_buf.iov_len = sizeof(*recv_ptp_caps_msg);
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	else if (reply_sz != sizeof(*recv_ptp_caps_msg))
+		return -EIO;
+
+	ptp->caps = le32_to_cpu(recv_ptp_caps_msg->caps);
+	ptp->base_incval = le64_to_cpu(recv_ptp_caps_msg->base_incval);
+	ptp->max_adj = le32_to_cpu(recv_ptp_caps_msg->max_adj);
+
+	scnd_mbx = &ptp->secondary_mbx;
+	scnd_mbx->peer_mbx_q_id = le16_to_cpu(recv_ptp_caps_msg->peer_mbx_q_id);
+
+	/* if the ptp_mb_q_id holds invalid value (0xffff), the secondary
+	 * mailbox is not supported.
+	 */
+	scnd_mbx->valid = scnd_mbx->peer_mbx_q_id != 0xffff;
+	if (scnd_mbx->valid)
+		scnd_mbx->peer_id = recv_ptp_caps_msg->peer_id;
+
+	/* Determine the access type for the PTP features */
+	idpf_ptp_get_features_access(adapter);
+
+	access_type = ptp->get_dev_clk_time_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		goto discipline_clock;
+
+	clock_offsets = recv_ptp_caps_msg->clk_offsets;
+
+	temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_l);
+	ptp->dev_clk_regs.dev_clk_ns_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_h);
+	ptp->dev_clk_regs.dev_clk_ns_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_l);
+	ptp->dev_clk_regs.phy_clk_ns_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_h);
+	ptp->dev_clk_regs.phy_clk_ns_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.cmd_sync_trigger);
+	ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset);
+
+discipline_clock:
+	access_type = ptp->adj_dev_clk_time_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		return 0;
+
+	clk_adj_offsets = recv_ptp_caps_msg->clk_adj_offsets;
+
+	/* Device clock offsets */
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_cmd_type);
+	ptp->dev_clk_regs.cmd = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_l);
+	ptp->dev_clk_regs.incval_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_h);
+	ptp->dev_clk_regs.incval_h = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_l);
+	ptp->dev_clk_regs.shadj_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_h);
+	ptp->dev_clk_regs.shadj_h = idpf_get_reg_addr(adapter, temp_offset);
+
+	/* PHY clock offsets */
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_cmd_type);
+	ptp->dev_clk_regs.phy_cmd = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_l);
+	ptp->dev_clk_regs.phy_incval_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_h);
+	ptp->dev_clk_regs.phy_incval_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_l);
+	ptp->dev_clk_regs.phy_shadj_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_h);
+	ptp->dev_clk_regs.phy_shadj_h = idpf_get_reg_addr(adapter, temp_offset);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_dev_clk_time - Send virtchnl get device clk time message
+ * @adapter: Driver specific private structure
+ * @dev_clk_time: Pointer to the device clock structure where the value is set
+ *
+ * Send virtchnl get time message to get the time of the clock.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			      struct idpf_ptp_dev_timers *dev_clk_time)
+{
+	struct virtchnl2_ptp_get_dev_clk_time get_dev_clk_time_msg;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME,
+		.send_buf.iov_base = &get_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(get_dev_clk_time_msg),
+		.recv_buf.iov_base = &get_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(get_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+	u64 dev_time;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(get_dev_clk_time_msg))
+		return -EIO;
+
+	dev_time = le64_to_cpu(get_dev_clk_time_msg.dev_time_ns);
+	dev_clk_time->dev_clk_time_ns = dev_time;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_set_dev_clk_time - Send virtchnl set device time message
+ * @adapter: Driver specific private structure
+ * @time: New time value
+ *
+ * Send virtchnl set time message to set the time of the clock.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time)
+{
+	struct virtchnl2_ptp_set_dev_clk_time set_dev_clk_time_msg = {
+		.dev_time_ns = cpu_to_le64(time),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME,
+		.send_buf.iov_base = &set_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(set_dev_clk_time_msg),
+		.recv_buf.iov_base = &set_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(set_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(set_dev_clk_time_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adj_dev_clk_time - Send virtchnl adj device clock time message
+ * @adapter: Driver specific private structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Send virtchnl adj time message to adjust the clock by the indicated delta.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta)
+{
+	struct virtchnl2_ptp_adj_dev_clk_time adj_dev_clk_time_msg = {
+		.delta = cpu_to_le64(delta),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME,
+		.send_buf.iov_base = &adj_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(adj_dev_clk_time_msg),
+		.recv_buf.iov_base = &adj_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(adj_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(adj_dev_clk_time_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adj_dev_clk_fine - Send virtchnl adj time message
+ * @adapter: Driver specific private structure
+ * @incval: Source timer increment value per clock cycle
+ *
+ * Send virtchnl adj fine message to adjust the frequency of the clock by
+ * incval.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval)
+{
+	struct virtchnl2_ptp_adj_dev_clk_fine adj_dev_clk_fine_msg = {
+		.incval = cpu_to_le64(incval),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE,
+		.send_buf.iov_base = &adj_dev_clk_fine_msg,
+		.send_buf.iov_len = sizeof(adj_dev_clk_fine_msg),
+		.recv_buf.iov_base = &adj_dev_clk_fine_msg,
+		.recv_buf.iov_len = sizeof(adj_dev_clk_fine_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(adj_dev_clk_fine_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_vport_tstamps_caps - Send virtchnl to get tstamps caps for vport
+ * @vport: Virtual port structure
+ *
+ * Send virtchnl get vport tstamps caps message to receive the set of tstamp
+ * capabilities per vport.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_caps send_tx_tstamp_caps;
+	struct virtchnl2_ptp_get_vport_tx_tstamp_caps *rcv_tx_tstamp_caps;
+	struct virtchnl2_ptp_tx_tstamp_latch_caps tx_tstamp_latch_caps;
+	struct idpf_ptp_vport_tx_tstamp_caps *tstamp_caps;
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS,
+		.send_buf.iov_base = &send_tx_tstamp_caps,
+		.send_buf.iov_len = sizeof(send_tx_tstamp_caps),
+		.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	enum idpf_ptp_access tstamp_access, get_dev_clk_access;
+	struct idpf_ptp *ptp = vport->adapter->ptp;
+	struct list_head *head;
+	int err = 0, reply_sz;
+	u16 num_latches;
+	u32 size;
+
+	if (!ptp)
+		return -EOPNOTSUPP;
+
+	tstamp_access = ptp->tx_tstamp_access;
+	get_dev_clk_access = ptp->get_dev_clk_time_access;
+	if (tstamp_access == IDPF_PTP_NONE ||
+	    get_dev_clk_access == IDPF_PTP_NONE)
+		return -EOPNOTSUPP;
+
+	rcv_tx_tstamp_caps = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!rcv_tx_tstamp_caps)
+		return -ENOMEM;
+
+	send_tx_tstamp_caps.vport_id = cpu_to_le32(vport->vport_id);
+	xn_params.recv_buf.iov_base = rcv_tx_tstamp_caps;
+
+	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+	if (reply_sz < 0) {
+		err = reply_sz;
+		goto get_tstamp_caps_out;
+	}
+
+	num_latches = le16_to_cpu(rcv_tx_tstamp_caps->num_latches);
+	size = struct_size(rcv_tx_tstamp_caps, tstamp_latches, num_latches);
+	if (reply_sz != size) {
+		err = -EIO;
+		goto get_tstamp_caps_out;
+	}
+
+	size = struct_size(tstamp_caps, tx_tstamp_status, num_latches);
+	tstamp_caps = kzalloc(size, GFP_KERNEL);
+	if (!tstamp_caps) {
+		err = -ENOMEM;
+		goto get_tstamp_caps_out;
+	}
+
+	tstamp_caps->access = true;
+	tstamp_caps->num_entries = num_latches;
+
+	INIT_LIST_HEAD(&tstamp_caps->latches_in_use);
+	INIT_LIST_HEAD(&tstamp_caps->latches_free);
+
+	spin_lock_init(&tstamp_caps->latches_lock);
+	spin_lock_init(&tstamp_caps->status_lock);
+
+	tstamp_caps->tstamp_ns_lo_bit = rcv_tx_tstamp_caps->tstamp_ns_lo_bit;
+
+	for (u16 i = 0; i < tstamp_caps->num_entries; i++) {
+		__le32 offset_l, offset_h;
+
+		ptp_tx_tstamp = kzalloc(sizeof(*ptp_tx_tstamp), GFP_KERNEL);
+		if (!ptp_tx_tstamp) {
+			err = -ENOMEM;
+			goto err_free_ptp_tx_stamp_list;
+		}
+
+		tx_tstamp_latch_caps = rcv_tx_tstamp_caps->tstamp_latches[i];
+
+		if (tstamp_access != IDPF_PTP_DIRECT)
+			goto skip_offsets;
+
+		offset_l = tx_tstamp_latch_caps.tx_latch_reg_offset_l;
+		offset_h = tx_tstamp_latch_caps.tx_latch_reg_offset_h;
+		ptp_tx_tstamp->tx_latch_reg_offset_l = le32_to_cpu(offset_l);
+		ptp_tx_tstamp->tx_latch_reg_offset_h = le32_to_cpu(offset_h);
+
+skip_offsets:
+		ptp_tx_tstamp->idx = tx_tstamp_latch_caps.index;
+
+		list_add(&ptp_tx_tstamp->list_member,
+			 &tstamp_caps->latches_free);
+
+		tstamp_caps->tx_tstamp_status[i].state = IDPF_PTP_FREE;
+	}
+
+	vport->tx_tstamp_caps = tstamp_caps;
+	kfree(rcv_tx_tstamp_caps);
+
+	return 0;
+
+err_free_ptp_tx_stamp_list:
+	head = &tstamp_caps->latches_free;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	kfree(tstamp_caps);
+get_tstamp_caps_out:
+	kfree(rcv_tx_tstamp_caps);
+
+	return err;
+}
+
+/**
+ * idpf_ptp_update_tstamp_tracker - Update the Tx timestamp tracker based on
+ *				    the skb compatibility.
+ * @caps: Tx timestamp capabilities that monitor the latch status
+ * @skb: skb for which the tstamp value is returned through virtchnl message
+ * @current_state: Current state of the Tx timestamp latch
+ * @expected_state: Expected state of the Tx timestamp latch
+ *
+ * Find a proper skb tracker for which the Tx timestamp is received and change
+ * the state to expected value.
+ *
+ * Return: true if the tracker has been found and updated, false otherwise.
+ */
+static bool
+idpf_ptp_update_tstamp_tracker(struct idpf_ptp_vport_tx_tstamp_caps *caps,
+			       struct sk_buff *skb,
+			       enum idpf_ptp_tx_tstamp_state current_state,
+			       enum idpf_ptp_tx_tstamp_state expected_state)
+{
+	bool updated = false;
+
+	spin_lock(&caps->status_lock);
+	for (u16 i = 0; i < caps->num_entries; i++) {
+		struct idpf_ptp_tx_tstamp_status *status;
+
+		status = &caps->tx_tstamp_status[i];
+
+		if (skb == status->skb && status->state == current_state) {
+			status->state = expected_state;
+			updated = true;
+			break;
+		}
+	}
+	spin_unlock(&caps->status_lock);
+
+	return updated;
+}
+
+/**
+ * idpf_ptp_get_tstamp_value - Get the Tx timestamp value and provide it
+ *			       back to the skb.
+ * @vport: Virtual port structure
+ * @tstamp_latch: Tx timestamp latch structure fulfilled by the Control Plane
+ * @ptp_tx_tstamp: Tx timestamp latch to add to the free list
+ *
+ * Read the value of the Tx timestamp for a given latch received from the
+ * Control Plane, extend it to 64 bit and provide back to the skb.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int
+idpf_ptp_get_tstamp_value(struct idpf_vport *vport,
+			  struct virtchnl2_ptp_tx_tstamp_latch *tstamp_latch,
+			  struct idpf_ptp_tx_tstamp *ptp_tx_tstamp)
+{
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct skb_shared_hwtstamps shhwtstamps;
+	bool state_upd = false;
+	u8 tstamp_ns_lo_bit;
+	u64 tstamp;
+
+	tx_tstamp_caps = vport->tx_tstamp_caps;
+	tstamp_ns_lo_bit = tx_tstamp_caps->tstamp_ns_lo_bit;
+
+	ptp_tx_tstamp->tstamp = le64_to_cpu(tstamp_latch->tstamp);
+	ptp_tx_tstamp->tstamp >>= tstamp_ns_lo_bit;
+
+	state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps,
+						   ptp_tx_tstamp->skb,
+						   IDPF_PTP_READ_VALUE,
+						   IDPF_PTP_FREE);
+	if (!state_upd)
+		return -EINVAL;
+
+	tstamp = idpf_ptp_extend_ts(vport, ptp_tx_tstamp->tstamp);
+	shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+	skb_tstamp_tx(ptp_tx_tstamp->skb, &shhwtstamps);
+	consume_skb(ptp_tx_tstamp->skb);
+
+	list_add(&ptp_tx_tstamp->list_member,
+		 &tx_tstamp_caps->latches_free);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_tx_tstamp_async_handler - Async callback for getting Tx tstamps
+ * @adapter: Driver specific private structure
+ * @xn: transaction for message
+ * @ctlq_msg: received message
+ *
+ * Read the tstamps Tx tstamp values from a received message and put them
+ * directly to the skb. The number of timestamps to read is specified by
+ * the virtchnl message.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int
+idpf_ptp_get_tx_tstamp_async_handler(struct idpf_adapter *adapter,
+				     struct idpf_vc_xn *xn,
+				     const struct idpf_ctlq_msg *ctlq_msg)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_latches *recv_tx_tstamp_msg;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct virtchnl2_ptp_tx_tstamp_latch tstamp_latch;
+	struct idpf_ptp_tx_tstamp *tx_tstamp, *tmp;
+	struct idpf_vport *tstamp_vport = NULL;
+	struct list_head *head;
+	u16 num_latches;
+	u32 vport_id;
+	int err = 0;
+
+	recv_tx_tstamp_msg = ctlq_msg->ctx.indirect.payload->va;
+	vport_id = le32_to_cpu(recv_tx_tstamp_msg->vport_id);
+
+	idpf_for_each_vport(adapter, vport) {
+		if (!vport)
+			continue;
+
+		if (vport->vport_id == vport_id) {
+			tstamp_vport = vport;
+			break;
+		}
+	}
+
+	if (!tstamp_vport || !tstamp_vport->tx_tstamp_caps)
+		return -EINVAL;
+
+	tx_tstamp_caps = tstamp_vport->tx_tstamp_caps;
+	num_latches = le16_to_cpu(recv_tx_tstamp_msg->num_latches);
+
+	spin_lock_bh(&tx_tstamp_caps->latches_lock);
+	head = &tx_tstamp_caps->latches_in_use;
+
+	for (u16 i = 0; i < num_latches; i++) {
+		tstamp_latch = recv_tx_tstamp_msg->tstamp_latches[i];
+
+		if (!tstamp_latch.valid)
+			continue;
+
+		if (list_empty(head)) {
+			err = -ENOBUFS;
+			goto unlock;
+		}
+
+		list_for_each_entry_safe(tx_tstamp, tmp, head, list_member) {
+			if (tstamp_latch.index == tx_tstamp->idx) {
+				list_del(&tx_tstamp->list_member);
+				err = idpf_ptp_get_tstamp_value(tstamp_vport,
+								&tstamp_latch,
+								tx_tstamp);
+				if (err)
+					goto unlock;
+
+				break;
+			}
+		}
+	}
+
+unlock:
+	spin_unlock_bh(&tx_tstamp_caps->latches_lock);
+
+	return err;
+}
+
+/**
+ * idpf_ptp_get_tx_tstamp - Send virtchnl get Tx timestamp latches message
+ * @vport: Virtual port structure
+ *
+ * Send virtchnl get Tx tstamp message to read the value of the HW timestamp.
+ * The message contains a list of indexes set in the Tx descriptors.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_latches *send_tx_tstamp_msg;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+		.async = true,
+		.async_handler = idpf_ptp_get_tx_tstamp_async_handler,
+	};
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp;
+	int reply_sz, size, msg_size;
+	struct list_head *head;
+	bool state_upd;
+	u16 id = 0;
+
+	tx_tstamp_caps = vport->tx_tstamp_caps;
+	head = &tx_tstamp_caps->latches_in_use;
+
+	size = struct_size(send_tx_tstamp_msg, tstamp_latches,
+			   tx_tstamp_caps->num_entries);
+	send_tx_tstamp_msg = kzalloc(size, GFP_KERNEL);
+	if (!send_tx_tstamp_msg)
+		return -ENOMEM;
+
+	spin_lock_bh(&tx_tstamp_caps->latches_lock);
+	list_for_each_entry(ptp_tx_tstamp, head, list_member) {
+		u8 idx;
+
+		state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps,
+							   ptp_tx_tstamp->skb,
+							   IDPF_PTP_REQUEST,
+							   IDPF_PTP_READ_VALUE);
+		if (!state_upd)
+			continue;
+
+		idx = ptp_tx_tstamp->idx;
+		send_tx_tstamp_msg->tstamp_latches[id].index = idx;
+		id++;
+	}
+	spin_unlock_bh(&tx_tstamp_caps->latches_lock);
+
+	msg_size = struct_size(send_tx_tstamp_msg, tstamp_latches, id);
+	send_tx_tstamp_msg->vport_id = cpu_to_le32(vport->vport_id);
+	send_tx_tstamp_msg->num_latches = cpu_to_le16(id);
+	xn_params.send_buf.iov_base = send_tx_tstamp_msg;
+	xn_params.send_buf.iov_len = msg_size;
+
+	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+	kfree(send_tx_tstamp_msg);
+
+	return min(reply_sz, 0);
+}
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 63deb120359c..11b8f6f05799 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -68,6 +68,16 @@ enum virtchnl2_op {
 	VIRTCHNL2_OP_ADD_MAC_ADDR		= 535,
 	VIRTCHNL2_OP_DEL_MAC_ADDR		= 536,
 	VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE	= 537,
+
+	/* TimeSync opcodes */
+	VIRTCHNL2_OP_PTP_GET_CAPS			= 541,
+	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP		= 542,
+	VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME		= 543,
+	VIRTCHNL2_OP_PTP_GET_CROSS_TIME			= 544,
+	VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME		= 545,
+	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE		= 546,
+	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME		= 547,
+	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS	= 548,
 };
 
 /**
@@ -560,6 +570,14 @@ struct virtchnl2_queue_reg_chunks {
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
 
 /**
+ * enum virtchnl2_vport_flags - Vport flags that indicate vport capabilities.
+ * @VIRTCHNL2_VPORT_UPLINK_PORT: Representatives of underlying physical ports
+ */
+enum virtchnl2_vport_flags {
+	VIRTCHNL2_VPORT_UPLINK_PORT	= BIT(0),
+};
+
+/**
  * struct virtchnl2_create_vport - Create vport config info.
  * @vport_type: See enum virtchnl2_vport_type.
  * @txq_model: See virtchnl2_queue_model.
@@ -577,7 +595,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
  * @max_mtu: Max MTU. CP populates this field on response.
  * @vport_id: Vport id. CP populates this field on response.
  * @default_mac_addr: Default MAC address.
- * @pad: Padding.
+ * @vport_flags: See enum virtchnl2_vport_flags.
  * @rx_desc_ids: See VIRTCHNL2_RX_DESC_IDS definitions.
  * @tx_desc_ids: See VIRTCHNL2_TX_DESC_IDS definitions.
  * @pad1: Padding.
@@ -610,7 +628,7 @@ struct virtchnl2_create_vport {
 	__le16 max_mtu;
 	__le32 vport_id;
 	u8 default_mac_addr[ETH_ALEN];
-	__le16 pad;
+	__le16 vport_flags;
 	__le64 rx_desc_ids;
 	__le64 tx_desc_ids;
 	u8 pad1[72];
@@ -1270,4 +1288,296 @@ struct virtchnl2_promisc_info {
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_promisc_info);
 
+/**
+ * enum virtchnl2_ptp_caps - PTP capabilities
+ * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME: direct access to get the time of
+ *					   device clock
+ * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB: mailbox access to get the time of
+ *					      device clock
+ * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME: direct access to cross timestamp
+ * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB: mailbox access to cross timestamp
+ * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME: direct access to set the time of
+ *					   device clock
+ * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB: mailbox access to set the time of
+ *					      device clock
+ * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK: direct access to adjust the time of device
+ *				      clock
+ * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB: mailbox access to adjust the time of
+ *					 device clock
+ * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS: direct access to the Tx timestamping
+ * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB: mailbox access to the Tx timestamping
+ *
+ * PF/VF negotiates a set of supported PTP capabilities with the Control Plane.
+ * There are two access methods - mailbox (_MB) and direct.
+ * PTP capabilities enables Main Timer operations: get/set/adjust Main Timer,
+ * cross timestamping and the Tx timestamping.
+ */
+enum virtchnl2_ptp_caps {
+	VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME		= BIT(0),
+	VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB	= BIT(1),
+	VIRTCHNL2_CAP_PTP_GET_CROSS_TIME		= BIT(2),
+	VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB		= BIT(3),
+	VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME		= BIT(4),
+	VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB	= BIT(5),
+	VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK		= BIT(6),
+	VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB		= BIT(7),
+	VIRTCHNL2_CAP_PTP_TX_TSTAMPS			= BIT(8),
+	VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB			= BIT(9),
+};
+
+/**
+ * struct virtchnl2_ptp_clk_reg_offsets - Offsets of device and PHY clocks
+ *					  registers.
+ * @dev_clk_ns_l: Device clock low register offset
+ * @dev_clk_ns_h: Device clock high register offset
+ * @phy_clk_ns_l: PHY clock low register offset
+ * @phy_clk_ns_h: PHY clock high register offset
+ * @cmd_sync_trigger: The command sync trigger register offset
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_clk_reg_offsets {
+	__le32 dev_clk_ns_l;
+	__le32 dev_clk_ns_h;
+	__le32 phy_clk_ns_l;
+	__le32 phy_clk_ns_h;
+	__le32 cmd_sync_trigger;
+	u8 pad[4];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_ptp_clk_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_cross_time_reg_offsets - Offsets of the device cross
+ *						 time registers.
+ * @sys_time_ns_l: System time low register offset
+ * @sys_time_ns_h: System time high register offset
+ * @cmd_sync_trigger: The command sync trigger register offset
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_cross_time_reg_offsets {
+	__le32 sys_time_ns_l;
+	__le32 sys_time_ns_h;
+	__le32 cmd_sync_trigger;
+	u8 pad[4];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_cross_time_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_clk_adj_reg_offsets - Offsets of device and PHY clocks
+ *					      adjustments registers.
+ * @dev_clk_cmd_type: Device clock command type register offset
+ * @dev_clk_incval_l: Device clock increment value low register offset
+ * @dev_clk_incval_h: Device clock increment value high registers offset
+ * @dev_clk_shadj_l: Device clock shadow adjust low register offset
+ * @dev_clk_shadj_h: Device clock shadow adjust high register offset
+ * @phy_clk_cmd_type: PHY timer command type register offset
+ * @phy_clk_incval_l: PHY timer increment value low register offset
+ * @phy_clk_incval_h: PHY timer increment value high register offset
+ * @phy_clk_shadj_l: PHY timer shadow adjust low register offset
+ * @phy_clk_shadj_h: PHY timer shadow adjust high register offset
+ */
+struct virtchnl2_ptp_clk_adj_reg_offsets {
+	__le32 dev_clk_cmd_type;
+	__le32 dev_clk_incval_l;
+	__le32 dev_clk_incval_h;
+	__le32 dev_clk_shadj_l;
+	__le32 dev_clk_shadj_h;
+	__le32 phy_clk_cmd_type;
+	__le32 phy_clk_incval_l;
+	__le32 phy_clk_incval_h;
+	__le32 phy_clk_shadj_l;
+	__le32 phy_clk_shadj_h;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(40, virtchnl2_ptp_clk_adj_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_tx_tstamp_latch_caps - PTP Tx timestamp latch
+ *					       capabilities.
+ * @tx_latch_reg_offset_l: Tx timestamp latch low register offset
+ * @tx_latch_reg_offset_h: Tx timestamp latch high register offset
+ * @index: Latch index provided to the Tx descriptor
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_tx_tstamp_latch_caps {
+	__le32 tx_latch_reg_offset_l;
+	__le32 tx_latch_reg_offset_h;
+	u8 index;
+	u8 pad[7];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch_caps);
+
+/**
+ * struct virtchnl2_ptp_get_vport_tx_tstamp_caps - Structure that defines Tx
+ *						   tstamp entries.
+ * @vport_id: Vport number
+ * @num_latches: Total number of latches
+ * @tstamp_ns_lo_bit: First bit for nanosecond part of the timestamp
+ * @tstamp_ns_hi_bit: Last bit for nanosecond part of the timestamp
+ * @pad: Padding for future tstamp granularity extensions
+ * @tstamp_latches: Capabilities of Tx timestamp entries
+ *
+ * PF/VF sends this message to negotiate the Tx timestamp latches for each
+ * Vport.
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS.
+ */
+struct virtchnl2_ptp_get_vport_tx_tstamp_caps {
+	__le32 vport_id;
+	__le16 num_latches;
+	u8 tstamp_ns_lo_bit;
+	u8 tstamp_ns_hi_bit;
+	u8 pad[8];
+
+	struct virtchnl2_ptp_tx_tstamp_latch_caps tstamp_latches[]
+						  __counted_by_le(num_latches);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_caps);
+
+/**
+ * struct virtchnl2_ptp_get_caps - Get PTP capabilities
+ * @caps: PTP capability bitmap. See enum virtchnl2_ptp_caps
+ * @max_adj: The maximum possible frequency adjustment
+ * @base_incval: The default timer increment value
+ * @peer_mbx_q_id: ID of the PTP Device Control daemon queue
+ * @peer_id: Peer ID for PTP Device Control daemon
+ * @secondary_mbx: Indicates to the driver that it should create a secondary
+ *		   mailbox to inetract with control plane for PTP
+ * @pad: Padding for future extensions
+ * @clk_offsets: Main timer and PHY registers offsets
+ * @cross_time_offsets: Cross time registers offsets
+ * @clk_adj_offsets: Offsets needed to adjust the PHY and the main timer
+ *
+ * PF/VF sends this message to negotiate PTP capabilities. CP updates bitmap
+ * with supported features and fulfills appropriate structures.
+ * If HW uses primary MBX for PTP: secondary_mbx is set to false.
+ * If HW uses secondary MBX for PTP: secondary_mbx is set to true.
+ *	Control plane has 2 MBX and the driver has 1 MBX, send to peer
+ *	driver may be used to send a message using valid ptp_peer_mb_q_id and
+ *	ptp_peer_id.
+ * If HW does not use send to peer driver: secondary_mbx is no care field and
+ * peer_mbx_q_id holds invalid value (0xFFFF).
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_CAPS.
+ */
+struct virtchnl2_ptp_get_caps {
+	__le32 caps;
+	__le32 max_adj;
+	__le64 base_incval;
+	__le16 peer_mbx_q_id;
+	u8 peer_id;
+	u8 secondary_mbx;
+	u8 pad[4];
+
+	struct virtchnl2_ptp_clk_reg_offsets clk_offsets;
+	struct virtchnl2_ptp_cross_time_reg_offsets cross_time_offsets;
+	struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(104, virtchnl2_ptp_get_caps);
+
+/**
+ * struct virtchnl2_ptp_tx_tstamp_latch - Structure that describes tx tstamp
+ *					  values, index and validity.
+ * @tstamp: Timestamp value
+ * @index: Timestamp index from which the value is read
+ * @valid: Timestamp validity
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_tx_tstamp_latch {
+	__le64 tstamp;
+	u8 index;
+	u8 valid;
+	u8 pad[6];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch);
+
+/**
+ * struct virtchnl2_ptp_get_vport_tx_tstamp_latches - Tx timestamp latches
+ *						      associated with the vport.
+ * @vport_id: Number of vport that requests the timestamp
+ * @num_latches: Number of latches
+ * @get_devtime_with_txtstmp: Flag to request device time along with Tx timestamp
+ * @pad: Padding for future extensions
+ * @device_time: device time if get_devtime_with_txtstmp was set in request
+ * @tstamp_latches: PTP TX timestamp latch
+ *
+ * PF/VF sends this message to receive a specified number of timestamps
+ * entries.
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP.
+ */
+struct virtchnl2_ptp_get_vport_tx_tstamp_latches {
+	__le32 vport_id;
+	__le16 num_latches;
+	u8 get_devtime_with_txtstmp;
+	u8 pad[1];
+	__le64 device_time;
+
+	struct virtchnl2_ptp_tx_tstamp_latch tstamp_latches[]
+					     __counted_by_le(num_latches);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_latches);
+
+/**
+ * struct virtchnl2_ptp_get_dev_clk_time - Associated with message
+ *					   VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME.
+ * @dev_time_ns: Device clock time value in nanoseconds
+ *
+ * PF/VF sends this message to receive the time from the main timer.
+ */
+struct virtchnl2_ptp_get_dev_clk_time {
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_get_dev_clk_time);
+
+/**
+ * struct virtchnl2_ptp_get_cross_time: Associated with message
+ *					VIRTCHNL2_OP_PTP_GET_CROSS_TIME.
+ * @sys_time_ns: System counter value expressed in nanoseconds, read
+ *		 synchronously with device time
+ * @dev_time_ns: Device clock time value expressed in nanoseconds
+ *
+ * PF/VF sends this message to receive the cross time.
+ */
+struct virtchnl2_ptp_get_cross_time {
+	__le64 sys_time_ns;
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_cross_time);
+
+/**
+ * struct virtchnl2_ptp_set_dev_clk_time: Associated with message
+ *					  VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME.
+ * @dev_time_ns: Device time value expressed in nanoseconds to set
+ *
+ * PF/VF sends this message to set the time of the main timer.
+ */
+struct virtchnl2_ptp_set_dev_clk_time {
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_set_dev_clk_time);
+
+/**
+ * struct virtchnl2_ptp_adj_dev_clk_fine: Associated with message
+ *					  VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE.
+ * @incval: Source timer increment value per clock cycle
+ *
+ * PF/VF sends this message to adjust the frequency of the main timer by the
+ * indicated increment value.
+ */
+struct virtchnl2_ptp_adj_dev_clk_fine {
+	__le64 incval;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_fine);
+
+/**
+ * struct virtchnl2_ptp_adj_dev_clk_time: Associated with message
+ *					  VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME.
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * PF/VF sends this message to adjust the time of the main timer by the delta.
+ */
+struct virtchnl2_ptp_adj_dev_clk_time {
+	__le64 delta;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_time);
+
 #endif /* _VIRTCHNL_2_H_ */
diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile
index 463c0d26b9d4..6c1b702fd992 100644
--- a/drivers/net/ethernet/intel/igb/Makefile
+++ b/drivers/net/ethernet/intel/igb/Makefile
@@ -8,4 +8,4 @@ obj-$(CONFIG_IGB) += igb.o
 
 igb-y := igb_main.o igb_ethtool.o e1000_82575.o \
 	 e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \
-	 e1000_i210.o igb_ptp.o igb_hwmon.o
+	 e1000_i210.o igb_ptp.o igb_hwmon.o igb_xsk.o
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 3c2dc7bdebb5..f34ead8243e9 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -18,8 +18,10 @@
 #include <linux/i2c-algo-bit.h>
 #include <linux/pci.h>
 #include <linux/mdio.h>
+#include <linux/lockdep.h>
 
 #include <net/xdp.h>
+#include <net/xdp_sock_drv.h>
 
 struct igb_adapter;
 
@@ -86,6 +88,7 @@ struct igb_adapter;
 #define IGB_XDP_CONSUMED	BIT(0)
 #define IGB_XDP_TX		BIT(1)
 #define IGB_XDP_REDIR		BIT(2)
+#define IGB_XDP_EXIT		BIT(3)
 
 struct vf_data_storage {
 	unsigned char vf_mac_addresses[ETH_ALEN];
@@ -255,6 +258,7 @@ enum igb_tx_flags {
 enum igb_tx_buf_type {
 	IGB_TYPE_SKB = 0,
 	IGB_TYPE_XDP,
+	IGB_TYPE_XSK
 };
 
 /* wrapper around a pointer to a socket buffer,
@@ -320,6 +324,7 @@ struct igb_ring {
 	union {				/* array of buffer info structs */
 		struct igb_tx_buffer *tx_buffer_info;
 		struct igb_rx_buffer *rx_buffer_info;
+		struct xdp_buff **rx_buffer_info_zc;
 	};
 	void *desc;			/* descriptor ring memory */
 	unsigned long flags;		/* ring specific flags */
@@ -357,6 +362,7 @@ struct igb_ring {
 		};
 	};
 	struct xdp_rxq_info xdp_rxq;
+	struct xsk_buff_pool *xsk_pool;
 } ____cacheline_internodealigned_in_smp;
 
 struct igb_q_vector {
@@ -384,7 +390,9 @@ enum e1000_ring_flags_t {
 	IGB_RING_FLAG_RX_SCTP_CSUM,
 	IGB_RING_FLAG_RX_LB_VLAN_BSWAP,
 	IGB_RING_FLAG_TX_CTX_IDX,
-	IGB_RING_FLAG_TX_DETECT_HANG
+	IGB_RING_FLAG_TX_DETECT_HANG,
+	IGB_RING_FLAG_TX_DISABLED,
+	IGB_RING_FLAG_RX_ALLOC_FAILED,
 };
 
 #define ring_uses_large_buffer(ring) \
@@ -715,6 +723,8 @@ enum igb_boards {
 
 extern char igb_driver_name[];
 
+void igb_set_queue_napi(struct igb_adapter *adapter, int q_idx,
+			struct napi_struct *napi);
 int igb_xmit_xdp_ring(struct igb_adapter *adapter,
 		      struct igb_ring *ring,
 		      struct xdp_frame *xdpf);
@@ -731,12 +741,21 @@ int igb_setup_tx_resources(struct igb_ring *);
 int igb_setup_rx_resources(struct igb_ring *);
 void igb_free_tx_resources(struct igb_ring *);
 void igb_free_rx_resources(struct igb_ring *);
+void igb_clean_tx_ring(struct igb_ring *tx_ring);
+void igb_clean_rx_ring(struct igb_ring *rx_ring);
 void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *);
 void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *);
+void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status);
+void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets,
+			 unsigned int bytes);
 void igb_setup_tctl(struct igb_adapter *);
 void igb_setup_rctl(struct igb_adapter *);
 void igb_setup_srrctl(struct igb_adapter *, struct igb_ring *);
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *);
+int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp);
+void igb_process_skb_fields(struct igb_ring *rx_ring,
+			    union e1000_adv_rx_desc *rx_desc,
+			    struct sk_buff *skb);
 void igb_alloc_rx_buffers(struct igb_ring *, u16);
 void igb_update_stats(struct igb_adapter *);
 bool igb_has_link(struct igb_adapter *adapter);
@@ -797,6 +816,33 @@ static inline struct netdev_queue *txring_txq(const struct igb_ring *tx_ring)
 	return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
 }
 
+/* This function assumes __netif_tx_lock is held by the caller. */
+static inline void igb_xdp_ring_update_tail(struct igb_ring *ring)
+{
+	lockdep_assert_held(&txring_txq(ring)->_xmit_lock);
+
+	/* Force memory writes to complete before letting h/w know there
+	 * are new descriptors to fetch.
+	 */
+	wmb();
+	writel(ring->next_to_use, ring->tail);
+}
+
+static inline struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter)
+{
+	unsigned int r_idx = smp_processor_id();
+
+	if (r_idx >= adapter->num_tx_queues)
+		r_idx = r_idx % adapter->num_tx_queues;
+
+	return adapter->tx_ring[r_idx];
+}
+
+static inline bool igb_xdp_is_enabled(struct igb_adapter *adapter)
+{
+	return !!READ_ONCE(adapter->xdp_prog);
+}
+
 int igb_add_filter(struct igb_adapter *adapter,
 		   struct igb_nfc_filter *input);
 int igb_erase_filter(struct igb_adapter *adapter,
@@ -807,4 +853,17 @@ int igb_add_mac_steering_filter(struct igb_adapter *adapter,
 int igb_del_mac_steering_filter(struct igb_adapter *adapter,
 				const u8 *addr, u8 queue, u8 flags);
 
+struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter,
+				   struct igb_ring *ring);
+int igb_xsk_pool_setup(struct igb_adapter *adapter,
+		       struct xsk_buff_pool *pool,
+		       u16 qid);
+bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring,
+			     struct xsk_buff_pool *xsk_pool, u16 count);
+void igb_clean_rx_ring_zc(struct igb_ring *rx_ring);
+int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector,
+			struct xsk_buff_pool *xsk_pool, const int budget);
+bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool);
+int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags);
+
 #endif /* _IGB_H_ */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 08578980b651..b76a154e635e 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -33,7 +33,6 @@
 #include <linux/bpf_trace.h>
 #include <linux/pm_runtime.h>
 #include <linux/etherdevice.h>
-#include <linux/lockdep.h>
 #ifdef CONFIG_IGB_DCA
 #include <linux/dca.h>
 #endif
@@ -116,8 +115,6 @@ static void igb_configure_tx(struct igb_adapter *);
 static void igb_configure_rx(struct igb_adapter *);
 static void igb_clean_all_tx_rings(struct igb_adapter *);
 static void igb_clean_all_rx_rings(struct igb_adapter *);
-static void igb_clean_tx_ring(struct igb_ring *);
-static void igb_clean_rx_ring(struct igb_ring *);
 static void igb_set_rx_mode(struct net_device *);
 static void igb_update_phy_info(struct timer_list *);
 static void igb_watchdog(struct timer_list *);
@@ -475,12 +472,17 @@ rx_ring_summary:
 
 		for (i = 0; i < rx_ring->count; i++) {
 			const char *next_desc;
-			struct igb_rx_buffer *buffer_info;
-			buffer_info = &rx_ring->rx_buffer_info[i];
+			dma_addr_t dma = (dma_addr_t)0;
+			struct igb_rx_buffer *buffer_info = NULL;
 			rx_desc = IGB_RX_DESC(rx_ring, i);
 			u0 = (struct my_u0 *)rx_desc;
 			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
 
+			if (!rx_ring->xsk_pool) {
+				buffer_info = &rx_ring->rx_buffer_info[i];
+				dma = buffer_info->dma;
+			}
+
 			if (i == rx_ring->next_to_use)
 				next_desc = " NTU";
 			else if (i == rx_ring->next_to_clean)
@@ -500,11 +502,11 @@ rx_ring_summary:
 					"R  ", i,
 					le64_to_cpu(u0->a),
 					le64_to_cpu(u0->b),
-					(u64)buffer_info->dma,
+					(u64)dma,
 					next_desc);
 
 				if (netif_msg_pktdata(adapter) &&
-				    buffer_info->dma && buffer_info->page) {
+				    buffer_info && dma && buffer_info->page) {
 					print_hex_dump(KERN_INFO, "",
 					  DUMP_PREFIX_ADDRESS,
 					  16, 1,
@@ -637,6 +639,10 @@ static int __init igb_init_module(void)
 	dca_register_notify(&dca_notifier);
 #endif
 	ret = pci_register_driver(&igb_driver);
+#ifdef CONFIG_IGB_DCA
+	if (ret)
+		dca_unregister_notify(&dca_notifier);
+#endif
 	return ret;
 }
 
@@ -941,6 +947,9 @@ static int igb_request_msix(struct igb_adapter *adapter)
 				  q_vector);
 		if (err)
 			goto err_free;
+
+		netif_napi_set_irq(&q_vector->napi,
+				   adapter->msix_entries[vector].vector);
 	}
 
 	igb_configure_msix(adapter);
@@ -1188,7 +1197,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		return -ENOMEM;
 
 	/* initialize NAPI */
-	netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll);
+	netif_napi_add_config(adapter->netdev, &q_vector->napi, igb_poll,
+			      v_idx);
 
 	/* tie q_vector and adapter together */
 	adapter->q_vector[v_idx] = q_vector;
@@ -1986,7 +1996,11 @@ static void igb_configure(struct igb_adapter *adapter)
 	 */
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct igb_ring *ring = adapter->rx_ring[i];
-		igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
+		if (ring->xsk_pool)
+			igb_alloc_rx_buffers_zc(ring, ring->xsk_pool,
+						igb_desc_unused(ring));
+		else
+			igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
 	}
 }
 
@@ -2086,6 +2100,22 @@ static void igb_check_swap_media(struct igb_adapter *adapter)
 	wr32(E1000_CTRL_EXT, ctrl_ext);
 }
 
+void igb_set_queue_napi(struct igb_adapter *adapter, int vector,
+			struct napi_struct *napi)
+{
+	struct igb_q_vector *q_vector = adapter->q_vector[vector];
+
+	if (q_vector->rx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->rx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, napi);
+
+	if (q_vector->tx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->tx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, napi);
+}
+
 /**
  *  igb_up - Open the interface and prepare it to handle traffic
  *  @adapter: board private structure
@@ -2093,6 +2123,7 @@ static void igb_check_swap_media(struct igb_adapter *adapter)
 int igb_up(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int i;
 
 	/* hardware has been reset, we need to reload some things */
@@ -2100,8 +2131,11 @@ int igb_up(struct igb_adapter *adapter)
 
 	clear_bit(__IGB_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&(adapter->q_vector[i]->napi));
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igb_set_queue_napi(adapter, i, napi);
+	}
 
 	if (adapter->flags & IGB_FLAG_HAS_MSIX)
 		igb_configure_msix(adapter);
@@ -2171,12 +2205,13 @@ void igb_down(struct igb_adapter *adapter)
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		if (adapter->q_vector[i]) {
 			napi_synchronize(&adapter->q_vector[i]->napi);
+			igb_set_queue_napi(adapter, i, NULL);
 			napi_disable(&adapter->q_vector[i]->napi);
 		}
 	}
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	/* record the stats before reset*/
 	spin_lock(&adapter->stats64_lock);
@@ -2907,37 +2942,20 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf)
 
 static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
+	struct igb_adapter *adapter = netdev_priv(dev);
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return igb_xdp_setup(dev, xdp);
+	case XDP_SETUP_XSK_POOL:
+		return igb_xsk_pool_setup(adapter, xdp->xsk.pool,
+					  xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
 }
 
-/* This function assumes __netif_tx_lock is held by the caller. */
-static void igb_xdp_ring_update_tail(struct igb_ring *ring)
-{
-	lockdep_assert_held(&txring_txq(ring)->_xmit_lock);
-
-	/* Force memory writes to complete before letting h/w know there
-	 * are new descriptors to fetch.
-	 */
-	wmb();
-	writel(ring->next_to_use, ring->tail);
-}
-
-static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter)
-{
-	unsigned int r_idx = smp_processor_id();
-
-	if (r_idx >= adapter->num_tx_queues)
-		r_idx = r_idx % adapter->num_tx_queues;
-
-	return adapter->tx_ring[r_idx];
-}
-
-static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp)
+int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp)
 {
 	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 	int cpu = smp_processor_id();
@@ -2951,7 +2969,8 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp)
 	/* During program transitions its possible adapter->xdp_prog is assigned
 	 * but ring has not been configured yet. In this case simply abort xmit.
 	 */
-	tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL;
+	tx_ring = igb_xdp_is_enabled(adapter) ?
+		igb_xdp_tx_queue_mapping(adapter) : NULL;
 	if (unlikely(!tx_ring))
 		return IGB_XDP_CONSUMED;
 
@@ -2984,10 +3003,14 @@ static int igb_xdp_xmit(struct net_device *dev, int n,
 	/* During program transitions its possible adapter->xdp_prog is assigned
 	 * but ring has not been configured yet. In this case simply abort xmit.
 	 */
-	tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL;
+	tx_ring = igb_xdp_is_enabled(adapter) ?
+		igb_xdp_tx_queue_mapping(adapter) : NULL;
 	if (unlikely(!tx_ring))
 		return -ENXIO;
 
+	if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags)))
+		return -ENXIO;
+
 	nq = txring_txq(tx_ring);
 	__netif_tx_lock(nq, cpu);
 
@@ -3038,6 +3061,7 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_setup_tc		= igb_setup_tc,
 	.ndo_bpf		= igb_xdp,
 	.ndo_xdp_xmit		= igb_xdp_xmit,
+	.ndo_xsk_wakeup         = igb_xsk_wakeup,
 };
 
 /**
@@ -3334,7 +3358,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
-	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
 
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
@@ -3860,8 +3885,8 @@ static void igb_remove(struct pci_dev *pdev)
 	 * disable watchdog from being rescheduled.
 	 */
 	set_bit(__IGB_DOWN, &adapter->state);
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
@@ -4113,8 +4138,9 @@ static int igb_sw_init(struct igb_adapter *adapter)
 static int __igb_open(struct net_device *netdev, bool resuming)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct e1000_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
+	struct e1000_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int err;
 	int i;
 
@@ -4166,8 +4192,11 @@ static int __igb_open(struct net_device *netdev, bool resuming)
 	/* From here on the code is the same as igb_up() */
 	clear_bit(__IGB_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&(adapter->q_vector[i]->napi));
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igb_set_queue_napi(adapter, i, napi);
+	}
 
 	/* Clear any pending interrupts. */
 	rd32(E1000_TSICR);
@@ -4360,6 +4389,8 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
 	u64 tdba = ring->dma;
 	int reg_idx = ring->reg_idx;
 
+	WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring));
+
 	wr32(E1000_TDLEN(reg_idx),
 	     ring->count * sizeof(union e1000_adv_tx_desc));
 	wr32(E1000_TDBAL(reg_idx),
@@ -4420,7 +4451,8 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-			       rx_ring->queue_index, 0);
+			       rx_ring->queue_index,
+			       rx_ring->q_vector->napi.napi_id);
 	if (res < 0) {
 		dev_err(dev, "Failed to register xdp_rxq index %u\n",
 			rx_ring->queue_index);
@@ -4716,12 +4748,17 @@ void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring)
 	struct e1000_hw *hw = &adapter->hw;
 	int reg_idx = ring->reg_idx;
 	u32 srrctl = 0;
+	u32 buf_size;
 
-	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
-	if (ring_uses_large_buffer(ring))
-		srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	if (ring->xsk_pool)
+		buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+	else if (ring_uses_large_buffer(ring))
+		buf_size = IGB_RXBUFFER_3072;
 	else
-		srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+		buf_size = IGB_RXBUFFER_2048;
+
+	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
+	srrctl |= buf_size >> E1000_SRRCTL_BSIZEPKT_SHIFT;
 	srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
 	if (hw->mac.type >= e1000_82580)
 		srrctl |= E1000_SRRCTL_TIMESTAMP;
@@ -4753,8 +4790,17 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	u32 rxdctl = 0;
 
 	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
-	WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-					   MEM_TYPE_PAGE_SHARED, NULL));
+	WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring));
+	if (ring->xsk_pool) {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_XSK_BUFF_POOL,
+						   NULL));
+		xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+	} else {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_PAGE_SHARED,
+						   NULL));
+	}
 
 	/* disable the queue */
 	wr32(E1000_RXDCTL(reg_idx), 0);
@@ -4781,9 +4827,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	rxdctl |= IGB_RX_HTHRESH << 8;
 	rxdctl |= IGB_RX_WTHRESH << 16;
 
-	/* initialize rx_buffer_info */
-	memset(ring->rx_buffer_info, 0,
-	       sizeof(struct igb_rx_buffer) * ring->count);
+	if (ring->xsk_pool)
+		memset(ring->rx_buffer_info_zc, 0,
+		       sizeof(*ring->rx_buffer_info_zc) * ring->count);
+	else
+		memset(ring->rx_buffer_info, 0,
+		       sizeof(*ring->rx_buffer_info) * ring->count);
 
 	/* initialize Rx descriptor 0 */
 	rx_desc = IGB_RX_DESC(ring, 0);
@@ -4884,19 +4933,24 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter)
  *  igb_clean_tx_ring - Free Tx Buffers
  *  @tx_ring: ring to be cleaned
  **/
-static void igb_clean_tx_ring(struct igb_ring *tx_ring)
+void igb_clean_tx_ring(struct igb_ring *tx_ring)
 {
 	u16 i = tx_ring->next_to_clean;
 	struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
+	u32 xsk_frames = 0;
 
 	while (i != tx_ring->next_to_use) {
 		union e1000_adv_tx_desc *eop_desc, *tx_desc;
 
 		/* Free all the Tx ring sk_buffs or xdp frames */
-		if (tx_buffer->type == IGB_TYPE_SKB)
+		if (tx_buffer->type == IGB_TYPE_SKB) {
 			dev_kfree_skb_any(tx_buffer->skb);
-		else
+		} else if (tx_buffer->type == IGB_TYPE_XDP) {
 			xdp_return_frame(tx_buffer->xdpf);
+		} else if (tx_buffer->type == IGB_TYPE_XSK) {
+			xsk_frames++;
+			goto skip_for_xsk;
+		}
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -4927,6 +4981,7 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring)
 					       DMA_TO_DEVICE);
 		}
 
+skip_for_xsk:
 		tx_buffer->next_to_watch = NULL;
 
 		/* move us one more past the eop_desc for start of next pkt */
@@ -4941,6 +4996,9 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring)
 	/* reset BQL for queue */
 	netdev_tx_reset_queue(txring_txq(tx_ring));
 
+	if (tx_ring->xsk_pool && xsk_frames)
+		xsk_tx_completed(tx_ring->xsk_pool, xsk_frames);
+
 	/* reset next_to_use and next_to_clean */
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
@@ -4971,8 +5029,13 @@ void igb_free_rx_resources(struct igb_ring *rx_ring)
 
 	rx_ring->xdp_prog = NULL;
 	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	vfree(rx_ring->rx_buffer_info);
-	rx_ring->rx_buffer_info = NULL;
+	if (rx_ring->xsk_pool) {
+		vfree(rx_ring->rx_buffer_info_zc);
+		rx_ring->rx_buffer_info_zc = NULL;
+	} else {
+		vfree(rx_ring->rx_buffer_info);
+		rx_ring->rx_buffer_info = NULL;
+	}
 
 	/* if not set, then don't free */
 	if (!rx_ring->desc)
@@ -5003,13 +5066,18 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter)
  *  igb_clean_rx_ring - Free Rx Buffers per Queue
  *  @rx_ring: ring to free buffers from
  **/
-static void igb_clean_rx_ring(struct igb_ring *rx_ring)
+void igb_clean_rx_ring(struct igb_ring *rx_ring)
 {
 	u16 i = rx_ring->next_to_clean;
 
 	dev_kfree_skb(rx_ring->skb);
 	rx_ring->skb = NULL;
 
+	if (rx_ring->xsk_pool) {
+		igb_clean_rx_ring_zc(rx_ring);
+		goto skip_for_xsk;
+	}
+
 	/* Free all the Rx ring sk_buffs */
 	while (i != rx_ring->next_to_alloc) {
 		struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
@@ -5037,6 +5105,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 			i = 0;
 	}
 
+skip_for_xsk:
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
@@ -5396,7 +5465,8 @@ static void igb_spoof_check(struct igb_adapter *adapter)
  */
 static void igb_update_phy_info(struct timer_list *t)
 {
-	struct igb_adapter *adapter = from_timer(adapter, t, phy_info_timer);
+	struct igb_adapter *adapter = timer_container_of(adapter, t,
+							 phy_info_timer);
 	igb_get_phy_info(&adapter->hw);
 }
 
@@ -5486,7 +5556,8 @@ static void igb_check_lvmmc(struct igb_adapter *adapter)
  **/
 static void igb_watchdog(struct timer_list *t)
 {
-	struct igb_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct igb_adapter *adapter = timer_container_of(adapter, t,
+							 watchdog_timer);
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
 }
@@ -5686,11 +5757,29 @@ no_wait:
 	if (adapter->flags & IGB_FLAG_HAS_MSIX) {
 		u32 eics = 0;
 
-		for (i = 0; i < adapter->num_q_vectors; i++)
-			eics |= adapter->q_vector[i]->eims_value;
-		wr32(E1000_EICS, eics);
+		for (i = 0; i < adapter->num_q_vectors; i++) {
+			struct igb_q_vector *q_vector = adapter->q_vector[i];
+			struct igb_ring *rx_ring;
+
+			if (!q_vector->rx.ring)
+				continue;
+
+			rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index];
+
+			if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
+				eics |= q_vector->eims_value;
+				clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			}
+		}
+		if (eics)
+			wr32(E1000_EICS, eics);
 	} else {
-		wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		struct igb_ring *rx_ring = adapter->rx_ring[0];
+
+		if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
+			clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		}
 	}
 
 	igb_spoof_check(adapter);
@@ -6463,6 +6552,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
+	if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags)))
+		return NETDEV_TX_BUSY;
+
 	/* record the location of the first descriptor for this packet */
 	first = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
 	first->type = IGB_TYPE_SKB;
@@ -6618,7 +6710,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD;
 
-	if (adapter->xdp_prog) {
+	if (igb_xdp_is_enabled(adapter)) {
 		int i;
 
 		for (i = 0; i < adapter->num_rx_queues; i++) {
@@ -8191,6 +8283,7 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	struct igb_q_vector *q_vector = container_of(napi,
 						     struct igb_q_vector,
 						     napi);
+	struct xsk_buff_pool *xsk_pool;
 	bool clean_complete = true;
 	int work_done = 0;
 
@@ -8202,7 +8295,12 @@ static int igb_poll(struct napi_struct *napi, int budget)
 		clean_complete = igb_clean_tx_irq(q_vector, budget);
 
 	if (q_vector->rx.ring) {
-		int cleaned = igb_clean_rx_irq(q_vector, budget);
+		int cleaned;
+
+		xsk_pool = READ_ONCE(q_vector->rx.ring->xsk_pool);
+		cleaned = xsk_pool ?
+			igb_clean_rx_irq_zc(q_vector, xsk_pool, budget) :
+			igb_clean_rx_irq(q_vector, budget);
 
 		work_done += cleaned;
 		if (cleaned >= budget)
@@ -8231,13 +8329,18 @@ static int igb_poll(struct napi_struct *napi, int budget)
  **/
 static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 {
-	struct igb_adapter *adapter = q_vector->adapter;
-	struct igb_ring *tx_ring = q_vector->tx.ring;
-	struct igb_tx_buffer *tx_buffer;
-	union e1000_adv_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
+	struct igb_adapter *adapter = q_vector->adapter;
 	unsigned int budget = q_vector->tx.work_limit;
+	struct igb_ring *tx_ring = q_vector->tx.ring;
 	unsigned int i = tx_ring->next_to_clean;
+	union e1000_adv_tx_desc *tx_desc;
+	struct igb_tx_buffer *tx_buffer;
+	struct xsk_buff_pool *xsk_pool;
+	int cpu = smp_processor_id();
+	bool xsk_xmit_done = true;
+	struct netdev_queue *nq;
+	u32 xsk_frames = 0;
 
 	if (test_bit(__IGB_DOWN, &adapter->state))
 		return true;
@@ -8268,10 +8371,14 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 		total_packets += tx_buffer->gso_segs;
 
 		/* free the skb */
-		if (tx_buffer->type == IGB_TYPE_SKB)
+		if (tx_buffer->type == IGB_TYPE_SKB) {
 			napi_consume_skb(tx_buffer->skb, napi_budget);
-		else
+		} else if (tx_buffer->type == IGB_TYPE_XDP) {
 			xdp_return_frame(tx_buffer->xdpf);
+		} else if (tx_buffer->type == IGB_TYPE_XSK) {
+			xsk_frames++;
+			goto skip_for_xsk;
+		}
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -8303,6 +8410,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 			}
 		}
 
+skip_for_xsk:
 		/* move us one more past the eop_desc for start of next pkt */
 		tx_buffer++;
 		tx_desc++;
@@ -8331,6 +8439,21 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 	q_vector->tx.total_bytes += total_bytes;
 	q_vector->tx.total_packets += total_packets;
 
+	xsk_pool = READ_ONCE(tx_ring->xsk_pool);
+	if (xsk_pool) {
+		if (xsk_frames)
+			xsk_tx_completed(xsk_pool, xsk_frames);
+		if (xsk_uses_need_wakeup(xsk_pool))
+			xsk_set_tx_need_wakeup(xsk_pool);
+
+		nq = txring_txq(tx_ring);
+		__netif_tx_lock(nq, cpu);
+		/* Avoid transmit queue timeout since we share it with the slow path */
+		txq_trans_cond_update(nq);
+		xsk_xmit_done = igb_xmit_zc(tx_ring, xsk_pool);
+		__netif_tx_unlock(nq);
+	}
+
 	if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) {
 		struct e1000_hw *hw = &adapter->hw;
 
@@ -8393,7 +8516,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 		}
 	}
 
-	return !!budget;
+	return !!budget && xsk_xmit_done;
 }
 
 /**
@@ -8584,9 +8707,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 	return skb;
 }
 
-static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
-				   struct igb_ring *rx_ring,
-				   struct xdp_buff *xdp)
+static int igb_run_xdp(struct igb_adapter *adapter, struct igb_ring *rx_ring,
+		       struct xdp_buff *xdp)
 {
 	int err, result = IGB_XDP_PASS;
 	struct bpf_prog *xdp_prog;
@@ -8626,7 +8748,7 @@ out_failure:
 		break;
 	}
 xdp_out:
-	return ERR_PTR(-result);
+	return result;
 }
 
 static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring,
@@ -8752,10 +8874,6 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring,
 				union e1000_adv_rx_desc *rx_desc,
 				struct sk_buff *skb)
 {
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	if (unlikely((igb_test_staterr(rx_desc,
 				       E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) {
 		struct net_device *netdev = rx_ring->netdev;
@@ -8782,9 +8900,9 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring,
  *  order to populate the hash, checksum, VLAN, timestamp, protocol, and
  *  other fields within the skb.
  **/
-static void igb_process_skb_fields(struct igb_ring *rx_ring,
-				   union e1000_adv_rx_desc *rx_desc,
-				   struct sk_buff *skb)
+void igb_process_skb_fields(struct igb_ring *rx_ring,
+			    union e1000_adv_rx_desc *rx_desc,
+			    struct sk_buff *skb)
 {
 	struct net_device *dev = rx_ring->netdev;
 
@@ -8866,6 +8984,38 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring,
 	rx_buffer->page = NULL;
 }
 
+void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status)
+{
+	int cpu = smp_processor_id();
+	struct netdev_queue *nq;
+
+	if (status & IGB_XDP_REDIR)
+		xdp_do_flush();
+
+	if (status & IGB_XDP_TX) {
+		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);
+
+		nq = txring_txq(tx_ring);
+		__netif_tx_lock(nq, cpu);
+		igb_xdp_ring_update_tail(tx_ring);
+		__netif_tx_unlock(nq);
+	}
+}
+
+void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets,
+			 unsigned int bytes)
+{
+	struct igb_ring *ring = q_vector->rx.ring;
+
+	u64_stats_update_begin(&ring->rx_syncp);
+	ring->rx_stats.packets += packets;
+	ring->rx_stats.bytes += bytes;
+	u64_stats_update_end(&ring->rx_syncp);
+
+	q_vector->rx.total_packets += packets;
+	q_vector->rx.total_bytes += bytes;
+}
+
 static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 {
 	unsigned int total_bytes = 0, total_packets = 0;
@@ -8873,12 +9023,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	struct igb_ring *rx_ring = q_vector->rx.ring;
 	u16 cleaned_count = igb_desc_unused(rx_ring);
 	struct sk_buff *skb = rx_ring->skb;
-	int cpu = smp_processor_id();
 	unsigned int xdp_xmit = 0;
-	struct netdev_queue *nq;
 	struct xdp_buff xdp;
 	u32 frame_sz = 0;
 	int rx_buf_pgcnt;
+	int xdp_res = 0;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)
@@ -8936,12 +9085,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
 			xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size);
 #endif
-			skb = igb_run_xdp(adapter, rx_ring, &xdp);
+			xdp_res = igb_run_xdp(adapter, rx_ring, &xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			unsigned int xdp_res = -PTR_ERR(skb);
-
+		if (xdp_res) {
 			if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) {
 				xdp_xmit |= xdp_res;
 				igb_rx_buffer_flip(rx_ring, rx_buffer, size);
@@ -8960,9 +9107,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 						&xdp, timestamp);
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_failed++;
 			rx_buffer->pagecnt_bias++;
+			set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 			break;
 		}
 
@@ -8974,7 +9122,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 			continue;
 
 		/* verify the packet layout is correct */
-		if (igb_cleanup_headers(rx_ring, rx_desc, skb)) {
+		if (xdp_res || igb_cleanup_headers(rx_ring, rx_desc, skb)) {
 			skb = NULL;
 			continue;
 		}
@@ -8997,24 +9145,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	/* place incomplete frames back on ring for completion */
 	rx_ring->skb = skb;
 
-	if (xdp_xmit & IGB_XDP_REDIR)
-		xdp_do_flush();
-
-	if (xdp_xmit & IGB_XDP_TX) {
-		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);
-
-		nq = txring_txq(tx_ring);
-		__netif_tx_lock(nq, cpu);
-		igb_xdp_ring_update_tail(tx_ring);
-		__netif_tx_unlock(nq);
-	}
+	if (xdp_xmit)
+		igb_finalize_xdp(adapter, xdp_xmit);
 
-	u64_stats_update_begin(&rx_ring->rx_syncp);
-	rx_ring->rx_stats.packets += total_packets;
-	rx_ring->rx_stats.bytes += total_bytes;
-	u64_stats_update_end(&rx_ring->rx_syncp);
-	q_vector->rx.total_packets += total_packets;
-	q_vector->rx.total_bytes += total_bytes;
+	igb_update_rx_stats(q_vector, total_packets, total_bytes);
 
 	if (cleaned_count)
 		igb_alloc_rx_buffers(rx_ring, cleaned_count);
@@ -9036,6 +9170,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 	page = dev_alloc_pages(igb_rx_pg_order(rx_ring));
 	if (unlikely(!page)) {
 		rx_ring->rx_stats.alloc_failed++;
+		set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 		return false;
 	}
 
@@ -9052,6 +9187,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		__free_pages(page, igb_rx_pg_order(rx_ring));
 
 		rx_ring->rx_stats.alloc_failed++;
+		set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 		return false;
 	}
 
@@ -9590,8 +9726,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev,
 	if (state == pci_channel_io_perm_failure)
 		return PCI_ERS_RESULT_DISCONNECT;
 
+	rtnl_lock();
 	if (netif_running(netdev))
 		igb_down(adapter);
+	rtnl_unlock();
+
 	pci_disable_device(pdev);
 
 	/* Request a slot reset. */
@@ -9650,16 +9789,21 @@ static void igb_io_resume(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
+	rtnl_lock();
 	if (netif_running(netdev)) {
 		if (!test_bit(__IGB_DOWN, &adapter->state)) {
 			dev_dbg(&pdev->dev, "Resuming from non-fatal error, do nothing.\n");
+			rtnl_unlock();
 			return;
 		}
+
 		if (igb_up(adapter)) {
 			dev_err(&pdev->dev, "igb_up failed after reset\n");
+			rtnl_unlock();
 			return;
 		}
 	}
+	rtnl_unlock();
 
 	netif_device_attach(netdev);
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index f94570556120..793c96016288 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -502,11 +502,10 @@ static int igb_ptp_feature_enable_82580(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
+		/* Both the rising and falling edge are timestamped */
+		if (rq->extts.flags & PTP_STRICT_FLAGS &&
+		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
+		    (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES)
 			return -EOPNOTSUPP;
 
 		if (on) {
@@ -652,13 +651,6 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
-			return -EOPNOTSUPP;
-
 		/* Reject requests failing to enable both edges. */
 		if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -1350,6 +1342,9 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.n_per_out = IGB_N_PEROUT;
 		adapter->ptp_caps.n_pins = IGB_N_SDP;
 		adapter->ptp_caps.pps = 0;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
@@ -1372,6 +1367,9 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.n_ext_ts = IGB_N_EXTTS;
 		adapter->ptp_caps.n_per_out = IGB_N_PEROUT;
 		adapter->ptp_caps.n_pins = IGB_N_SDP;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.pps = 1;
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c
new file mode 100644
index 000000000000..5cf67ba29269
--- /dev/null
+++ b/drivers/net/ethernet/intel/igb/igb_xsk.c
@@ -0,0 +1,563 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Intel Corporation. */
+
+#include <linux/bpf_trace.h>
+#include <net/xdp_sock_drv.h>
+#include <net/xdp.h>
+
+#include "e1000_hw.h"
+#include "igb.h"
+
+static int igb_realloc_rx_buffer_info(struct igb_ring *ring, bool pool_present)
+{
+	int size = pool_present ?
+		sizeof(*ring->rx_buffer_info_zc) * ring->count :
+		sizeof(*ring->rx_buffer_info) * ring->count;
+	void *buff_info = vmalloc(size);
+
+	if (!buff_info)
+		return -ENOMEM;
+
+	if (pool_present) {
+		vfree(ring->rx_buffer_info);
+		ring->rx_buffer_info = NULL;
+		ring->rx_buffer_info_zc = buff_info;
+	} else {
+		vfree(ring->rx_buffer_info_zc);
+		ring->rx_buffer_info_zc = NULL;
+		ring->rx_buffer_info = buff_info;
+	}
+
+	return 0;
+}
+
+static void igb_txrx_ring_disable(struct igb_adapter *adapter, u16 qid)
+{
+	struct igb_ring *tx_ring = adapter->tx_ring[qid];
+	struct igb_ring *rx_ring = adapter->rx_ring[qid];
+	struct e1000_hw *hw = &adapter->hw;
+
+	set_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags);
+
+	wr32(E1000_TXDCTL(tx_ring->reg_idx), 0);
+	wr32(E1000_RXDCTL(rx_ring->reg_idx), 0);
+
+	synchronize_net();
+
+	/* Rx/Tx share the same napi context. */
+	napi_disable(&rx_ring->q_vector->napi);
+
+	igb_clean_tx_ring(tx_ring);
+	igb_clean_rx_ring(rx_ring);
+
+	memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats));
+	memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats));
+}
+
+static void igb_txrx_ring_enable(struct igb_adapter *adapter, u16 qid)
+{
+	struct igb_ring *tx_ring = adapter->tx_ring[qid];
+	struct igb_ring *rx_ring = adapter->rx_ring[qid];
+
+	igb_configure_tx_ring(adapter, tx_ring);
+	igb_configure_rx_ring(adapter, rx_ring);
+
+	synchronize_net();
+
+	clear_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags);
+
+	/* call igb_desc_unused which always leaves
+	 * at least 1 descriptor unused to make sure
+	 * next_to_use != next_to_clean
+	 */
+	if (rx_ring->xsk_pool)
+		igb_alloc_rx_buffers_zc(rx_ring, rx_ring->xsk_pool,
+					igb_desc_unused(rx_ring));
+	else
+		igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring));
+
+	/* Rx/Tx share the same napi context. */
+	napi_enable(&rx_ring->q_vector->napi);
+}
+
+struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter,
+				   struct igb_ring *ring)
+{
+	int qid = ring->queue_index;
+	struct xsk_buff_pool *pool;
+
+	pool = xsk_get_pool_from_qid(adapter->netdev, qid);
+
+	if (!igb_xdp_is_enabled(adapter))
+		return NULL;
+
+	return (pool && pool->dev) ? pool : NULL;
+}
+
+static int igb_xsk_pool_enable(struct igb_adapter *adapter,
+			       struct xsk_buff_pool *pool,
+			       u16 qid)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct igb_ring *rx_ring;
+	bool if_running;
+	int err;
+
+	if (qid >= adapter->num_rx_queues)
+		return -EINVAL;
+
+	if (qid >= netdev->real_num_rx_queues ||
+	    qid >= netdev->real_num_tx_queues)
+		return -EINVAL;
+
+	err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IGB_RX_DMA_ATTR);
+	if (err)
+		return err;
+
+	rx_ring = adapter->rx_ring[qid];
+	if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter);
+	if (if_running)
+		igb_txrx_ring_disable(adapter, qid);
+
+	if (if_running) {
+		err = igb_realloc_rx_buffer_info(rx_ring, true);
+		if (!err) {
+			igb_txrx_ring_enable(adapter, qid);
+			/* Kick start the NAPI context so that receiving will start */
+			err = igb_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX);
+		}
+
+		if (err) {
+			xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int igb_xsk_pool_disable(struct igb_adapter *adapter, u16 qid)
+{
+	struct xsk_buff_pool *pool;
+	struct igb_ring *rx_ring;
+	bool if_running;
+	int err;
+
+	pool = xsk_get_pool_from_qid(adapter->netdev, qid);
+	if (!pool)
+		return -EINVAL;
+
+	rx_ring = adapter->rx_ring[qid];
+	if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter);
+	if (if_running)
+		igb_txrx_ring_disable(adapter, qid);
+
+	xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR);
+
+	if (if_running) {
+		err = igb_realloc_rx_buffer_info(rx_ring, false);
+		if (err)
+			return err;
+
+		igb_txrx_ring_enable(adapter, qid);
+	}
+
+	return 0;
+}
+
+int igb_xsk_pool_setup(struct igb_adapter *adapter,
+		       struct xsk_buff_pool *pool,
+		       u16 qid)
+{
+	return pool ? igb_xsk_pool_enable(adapter, pool, qid) :
+		igb_xsk_pool_disable(adapter, qid);
+}
+
+static u16 igb_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
+			     union e1000_adv_rx_desc *rx_desc, u16 count)
+{
+	dma_addr_t dma;
+	u16 buffs;
+	int i;
+
+	/* nothing to do */
+	if (!count)
+		return 0;
+
+	buffs = xsk_buff_alloc_batch(pool, xdp, count);
+	for (i = 0; i < buffs; i++) {
+		dma = xsk_buff_xdp_get_dma(*xdp);
+		rx_desc->read.pkt_addr = cpu_to_le64(dma);
+		rx_desc->wb.upper.length = 0;
+
+		rx_desc++;
+		xdp++;
+	}
+
+	return buffs;
+}
+
+bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring,
+			     struct xsk_buff_pool *xsk_pool, u16 count)
+{
+	u32 nb_buffs_extra = 0, nb_buffs = 0;
+	union e1000_adv_rx_desc *rx_desc;
+	u16 ntu = rx_ring->next_to_use;
+	u16 total_count = count;
+	struct xdp_buff **xdp;
+
+	rx_desc = IGB_RX_DESC(rx_ring, ntu);
+	xdp = &rx_ring->rx_buffer_info_zc[ntu];
+
+	if (ntu + count >= rx_ring->count) {
+		nb_buffs_extra = igb_fill_rx_descs(xsk_pool, xdp, rx_desc,
+						   rx_ring->count - ntu);
+		if (nb_buffs_extra != rx_ring->count - ntu) {
+			ntu += nb_buffs_extra;
+			goto exit;
+		}
+		rx_desc = IGB_RX_DESC(rx_ring, 0);
+		xdp = rx_ring->rx_buffer_info_zc;
+		ntu = 0;
+		count -= nb_buffs_extra;
+	}
+
+	nb_buffs = igb_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
+	ntu += nb_buffs;
+	if (ntu == rx_ring->count)
+		ntu = 0;
+
+	/* clear the length for the next_to_use descriptor */
+	rx_desc = IGB_RX_DESC(rx_ring, ntu);
+	rx_desc->wb.upper.length = 0;
+
+exit:
+	if (rx_ring->next_to_use != ntu) {
+		rx_ring->next_to_use = ntu;
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.  (Only
+		 * applicable for weak-ordered memory model archs,
+		 * such as IA-64).
+		 */
+		wmb();
+		writel(ntu, rx_ring->tail);
+	}
+
+	return total_count == (nb_buffs + nb_buffs_extra);
+}
+
+void igb_clean_rx_ring_zc(struct igb_ring *rx_ring)
+{
+	u16 ntc = rx_ring->next_to_clean;
+	u16 ntu = rx_ring->next_to_use;
+
+	while (ntc != ntu) {
+		struct xdp_buff *xdp = rx_ring->rx_buffer_info_zc[ntc];
+
+		xsk_buff_free(xdp);
+		ntc++;
+		if (ntc >= rx_ring->count)
+			ntc = 0;
+	}
+}
+
+static struct sk_buff *igb_construct_skb_zc(struct igb_ring *rx_ring,
+					    struct xdp_buff *xdp,
+					    ktime_t timestamp)
+{
+	unsigned int totalsize = xdp->data_end - xdp->data_meta;
+	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct sk_buff *skb;
+
+	net_prefetch(xdp->data_meta);
+
+	/* allocate a skb to store the frags */
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize);
+	if (unlikely(!skb))
+		return NULL;
+
+	if (timestamp)
+		skb_hwtstamps(skb)->hwtstamp = timestamp;
+
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+	       ALIGN(totalsize, sizeof(long)));
+
+	if (metasize) {
+		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
+
+	return skb;
+}
+
+static int igb_run_xdp_zc(struct igb_adapter *adapter, struct igb_ring *rx_ring,
+			  struct xdp_buff *xdp, struct xsk_buff_pool *xsk_pool,
+			  struct bpf_prog *xdp_prog)
+{
+	int err, result = IGB_XDP_PASS;
+	u32 act;
+
+	prefetchw(xdp->data_hard_start); /* xdp_frame write */
+
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+
+	if (likely(act == XDP_REDIRECT)) {
+		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
+		if (!err)
+			return IGB_XDP_REDIR;
+
+		if (xsk_uses_need_wakeup(xsk_pool) &&
+		    err == -ENOBUFS)
+			result = IGB_XDP_EXIT;
+		else
+			result = IGB_XDP_CONSUMED;
+		goto out_failure;
+	}
+
+	switch (act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		result = igb_xdp_xmit_back(adapter, xdp);
+		if (result == IGB_XDP_CONSUMED)
+			goto out_failure;
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+out_failure:
+		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
+		fallthrough;
+	case XDP_DROP:
+		result = IGB_XDP_CONSUMED;
+		break;
+	}
+
+	return result;
+}
+
+int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector,
+			struct xsk_buff_pool *xsk_pool, const int budget)
+{
+	struct igb_adapter *adapter = q_vector->adapter;
+	unsigned int total_bytes = 0, total_packets = 0;
+	struct igb_ring *rx_ring = q_vector->rx.ring;
+	u32 ntc = rx_ring->next_to_clean;
+	struct bpf_prog *xdp_prog;
+	unsigned int xdp_xmit = 0;
+	bool failure = false;
+	u16 entries_to_alloc;
+	struct sk_buff *skb;
+
+	/* xdp_prog cannot be NULL in the ZC path */
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+
+	while (likely(total_packets < budget)) {
+		union e1000_adv_rx_desc *rx_desc;
+		ktime_t timestamp = 0;
+		struct xdp_buff *xdp;
+		unsigned int size;
+		int xdp_res = 0;
+
+		rx_desc = IGB_RX_DESC(rx_ring, ntc);
+		size = le16_to_cpu(rx_desc->wb.upper.length);
+		if (!size)
+			break;
+
+		/* This memory barrier is needed to keep us from reading
+		 * any other fields out of the rx_desc until we know the
+		 * descriptor has been written back
+		 */
+		dma_rmb();
+
+		xdp = rx_ring->rx_buffer_info_zc[ntc];
+		xsk_buff_set_size(xdp, size);
+		xsk_buff_dma_sync_for_cpu(xdp);
+
+		/* pull rx packet timestamp if available and valid */
+		if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+			int ts_hdr_len;
+
+			ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector,
+							 xdp->data,
+							 &timestamp);
+
+			xdp->data += ts_hdr_len;
+			xdp->data_meta += ts_hdr_len;
+			size -= ts_hdr_len;
+		}
+
+		xdp_res = igb_run_xdp_zc(adapter, rx_ring, xdp, xsk_pool,
+					 xdp_prog);
+
+		if (xdp_res) {
+			if (likely(xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR))) {
+				xdp_xmit |= xdp_res;
+			} else if (xdp_res == IGB_XDP_EXIT) {
+				failure = true;
+				break;
+			} else if (xdp_res == IGB_XDP_CONSUMED) {
+				xsk_buff_free(xdp);
+			}
+
+			total_packets++;
+			total_bytes += size;
+			ntc++;
+			if (ntc == rx_ring->count)
+				ntc = 0;
+			continue;
+		}
+
+		skb = igb_construct_skb_zc(rx_ring, xdp, timestamp);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_failed++;
+			set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			break;
+		}
+
+		xsk_buff_free(xdp);
+		ntc++;
+		if (ntc == rx_ring->count)
+			ntc = 0;
+
+		if (eth_skb_pad(skb))
+			continue;
+
+		/* probably a little skewed due to removing CRC */
+		total_bytes += skb->len;
+
+		/* populate checksum, timestamp, VLAN, and protocol */
+		igb_process_skb_fields(rx_ring, rx_desc, skb);
+
+		napi_gro_receive(&q_vector->napi, skb);
+
+		/* update budget accounting */
+		total_packets++;
+	}
+
+	rx_ring->next_to_clean = ntc;
+
+	if (xdp_xmit)
+		igb_finalize_xdp(adapter, xdp_xmit);
+
+	igb_update_rx_stats(q_vector, total_packets, total_bytes);
+
+	entries_to_alloc = igb_desc_unused(rx_ring);
+	if (entries_to_alloc >= IGB_RX_BUFFER_WRITE)
+		failure |= !igb_alloc_rx_buffers_zc(rx_ring, xsk_pool,
+						    entries_to_alloc);
+
+	if (xsk_uses_need_wakeup(xsk_pool)) {
+		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
+			xsk_set_rx_need_wakeup(xsk_pool);
+		else
+			xsk_clear_rx_need_wakeup(xsk_pool);
+
+		return (int)total_packets;
+	}
+	return failure ? budget : (int)total_packets;
+}
+
+bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool)
+{
+	unsigned int budget = igb_desc_unused(tx_ring);
+	u32 cmd_type, olinfo_status, nb_pkts, i = 0;
+	struct xdp_desc *descs = xsk_pool->tx_descs;
+	union e1000_adv_tx_desc *tx_desc = NULL;
+	struct igb_tx_buffer *tx_buffer_info;
+	unsigned int total_bytes = 0;
+	dma_addr_t dma;
+
+	if (!netif_carrier_ok(tx_ring->netdev))
+		return true;
+
+	if (test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))
+		return true;
+
+	nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
+	if (!nb_pkts)
+		return true;
+
+	while (nb_pkts-- > 0) {
+		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
+
+		tx_buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+		tx_buffer_info->bytecount = descs[i].len;
+		tx_buffer_info->type = IGB_TYPE_XSK;
+		tx_buffer_info->xdpf = NULL;
+		tx_buffer_info->gso_segs = 1;
+		tx_buffer_info->time_stamp = jiffies;
+
+		tx_desc = IGB_TX_DESC(tx_ring, tx_ring->next_to_use);
+		tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
+		/* put descriptor type bits */
+		cmd_type = E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_DEXT |
+			   E1000_ADVTXD_DCMD_IFCS;
+		olinfo_status = descs[i].len << E1000_ADVTXD_PAYLEN_SHIFT;
+
+		/* FIXME: This sets the Report Status (RS) bit for every
+		 * descriptor. One nice to have optimization would be to set it
+		 * only for the last descriptor in the whole batch. See Intel
+		 * ice driver for an example on how to do it.
+		 */
+		cmd_type |= descs[i].len | IGB_TXD_DCMD;
+		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+
+		total_bytes += descs[i].len;
+
+		i++;
+		tx_ring->next_to_use++;
+		tx_buffer_info->next_to_watch = tx_desc;
+		if (tx_ring->next_to_use == tx_ring->count)
+			tx_ring->next_to_use = 0;
+	}
+
+	netdev_tx_sent_queue(txring_txq(tx_ring), total_bytes);
+	igb_xdp_ring_update_tail(tx_ring);
+
+	return nb_pkts < budget;
+}
+
+int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+	struct e1000_hw *hw = &adapter->hw;
+	struct igb_ring *ring;
+	u32 eics = 0;
+
+	if (test_bit(__IGB_DOWN, &adapter->state))
+		return -ENETDOWN;
+
+	if (!igb_xdp_is_enabled(adapter))
+		return -EINVAL;
+
+	if (qid >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[qid];
+
+	if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags))
+		return -ENETDOWN;
+
+	if (!READ_ONCE(ring->xsk_pool))
+		return -EINVAL;
+
+	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
+		/* Cause software interrupt */
+		if (adapter->flags & IGB_FLAG_HAS_MSIX) {
+			eics |= ring->q_vector->eims_value;
+			wr32(E1000_EICS, eics);
+		} else {
+			wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 02044aa2181b..e55dd9345833 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1592,7 +1592,7 @@ void igbvf_down(struct igbvf_adapter *adapter)
 
 	igbvf_irq_disable(adapter);
 
-	del_timer_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
 
 	/* record the stats before reset*/
 	igbvf_update_stats(adapter);
@@ -1900,7 +1900,8 @@ static bool igbvf_has_link(struct igbvf_adapter *adapter)
  **/
 static void igbvf_watchdog(struct timer_list *t)
 {
-	struct igbvf_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct igbvf_adapter *adapter = timer_container_of(adapter, t,
+							   watchdog_timer);
 
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
@@ -2912,7 +2913,7 @@ static void igbvf_remove(struct pci_dev *pdev)
 	 * disable it from being rescheduled.
 	 */
 	set_bit(__IGBVF_DOWN, &adapter->state);
-	del_timer_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index eac0f966e0e4..859a15e4ccba 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -40,6 +40,11 @@ void igc_ethtool_set_ops(struct net_device *);
 
 #define IGC_MAX_TX_TSTAMP_REGS		4
 
+struct igc_fpe_t {
+	struct ethtool_mmsv mmsv;
+	u32 tx_min_frag_size;
+};
+
 enum igc_mac_filter_type {
 	IGC_MAC_FILTER_TYPE_DST = 0,
 	IGC_MAC_FILTER_TYPE_SRC
@@ -319,6 +324,7 @@ struct igc_adapter {
 	struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */
 	ktime_t ptp_reset_start; /* Reset time in clock mono */
 	struct system_time_snapshot snapshot;
+	struct mutex ptm_lock; /* Only allow one PTM transaction at a time */
 
 	char fw_version[32];
 
@@ -332,6 +338,8 @@ struct igc_adapter {
 		struct timespec64 period;
 	} perout[IGC_N_PEROUT];
 
+	struct igc_fpe_t fpe;
+
 	/* LEDs */
 	struct mutex led_mutex;
 	struct igc_led_classdev *leds;
@@ -386,11 +394,11 @@ extern char igc_driver_name[];
 #define IGC_FLAG_RX_LEGACY		BIT(16)
 #define IGC_FLAG_TSN_QBV_ENABLED	BIT(17)
 #define IGC_FLAG_TSN_QAV_ENABLED	BIT(18)
-#define IGC_FLAG_TSN_LEGACY_ENABLED	BIT(19)
+#define IGC_FLAG_TSN_PREEMPT_ENABLED	BIT(19)
 
 #define IGC_FLAG_TSN_ANY_ENABLED				\
 	(IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED |	\
-	 IGC_FLAG_TSN_LEGACY_ENABLED)
+	 IGC_FLAG_TSN_PREEMPT_ENABLED)
 
 #define IGC_FLAG_RSS_FIELD_IPV4_UDP	BIT(6)
 #define IGC_FLAG_RSS_FIELD_IPV6_UDP	BIT(7)
@@ -577,6 +585,7 @@ struct igc_metadata_request {
 	struct xsk_tx_metadata *meta;
 	struct igc_ring *tx_ring;
 	u32 cmd_type;
+	u16 used_desc;
 };
 
 struct igc_q_vector {
@@ -734,7 +743,10 @@ struct igc_nfc_rule *igc_get_nfc_rule(struct igc_adapter *adapter,
 				      u32 location);
 int igc_add_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule);
 void igc_del_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule);
-
+void igc_disable_empty_addr_recv(struct igc_adapter *adapter);
+int igc_enable_empty_addr_recv(struct igc_adapter *adapter);
+struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu);
+void igc_flush_tx_descriptors(struct igc_ring *ring);
 void igc_ptp_init(struct igc_adapter *adapter);
 void igc_ptp_reset(struct igc_adapter *adapter);
 void igc_ptp_suspend(struct igc_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index 9fae8bdec2a7..1613b562d17c 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -68,6 +68,10 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw)
 	u32 eecd = rd32(IGC_EECD);
 	u16 size;
 
+	/* failed to read reg and got all F's */
+	if (!(~eecd))
+		return -ENXIO;
+
 	size = FIELD_GET(IGC_EECD_SIZE_EX_MASK, eecd);
 
 	/* Added to a constant, "size" becomes the left-shift value
@@ -221,6 +225,8 @@ static s32 igc_get_invariants_base(struct igc_hw *hw)
 
 	/* NVM initialization */
 	ret_val = igc_init_nvm_params_base(hw);
+	if (ret_val)
+		goto out;
 	switch (hw->mac.type) {
 	case igc_i225:
 		ret_val = igc_init_nvm_params_i225(hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
index bf8cdfbba9ff..6320eabb72fe 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.h
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -49,6 +49,7 @@ struct igc_adv_tx_context_desc {
 #define IGC_ADVTXD_DCMD_DEXT	0x20000000 /* Descriptor extension (1=Adv) */
 #define IGC_ADVTXD_DCMD_VLE	0x40000000 /* VLAN pkt enable */
 #define IGC_ADVTXD_DCMD_TSE	0x80000000 /* TCP Seg enable */
+#define IGC_ADVTXD_PAYLEN_MASK	0XFFFFC000 /* Adv desc PAYLEN mask */
 #define IGC_ADVTXD_PAYLEN_SHIFT	14 /* Adv desc PAYLEN shift */
 
 #define IGC_RAR_ENTRIES		16
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 8e449904aa7d..7189dfc389ad 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -308,6 +308,8 @@
 #define IGC_TXD_DTYP_C		0x00000000 /* Context Descriptor */
 #define IGC_TXD_POPTS_IXSM	0x01       /* Insert IP checksum */
 #define IGC_TXD_POPTS_TXSM	0x02       /* Insert TCP/UDP checksum */
+#define IGC_TXD_POPTS_SMD_MASK	0x3000     /* Indicates whether it's SMD-V or SMD-R */
+
 #define IGC_TXD_CMD_EOP		0x01000000 /* End of Packet */
 #define IGC_TXD_CMD_IC		0x04000000 /* Insert Checksum */
 #define IGC_TXD_CMD_DEXT	0x20000000 /* Desc extension (0 = legacy) */
@@ -363,6 +365,8 @@
 #define IGC_SRRCTL_TIMER0SEL(timer)	(((timer) & 0x3) << 17)
 
 /* Receive Descriptor bit definitions */
+#define IGC_RXD_STAT_SMD_TYPE_V	0x01	/* SMD-V Packet */
+#define IGC_RXD_STAT_SMD_TYPE_R	0x02	/* SMD-R Packet */
 #define IGC_RXD_STAT_EOP	0x02	/* End of Packet */
 #define IGC_RXD_STAT_IXSM	0x04	/* Ignore checksum */
 #define IGC_RXD_STAT_UDPCS	0x10	/* UDP xsum calculated */
@@ -372,7 +376,8 @@
 #define IGC_RXDEXT_STATERR_LB	0x00040000
 
 /* Advanced Receive Descriptor bit definitions */
-#define IGC_RXDADV_STAT_TSIP	0x08000 /* timestamp in packet */
+#define IGC_RXDADV_STAT_SMD_TYPE_MASK	0x06000
+#define IGC_RXDADV_STAT_TSIP		0x08000 /* timestamp in packet */
 
 #define IGC_RXDEXT_STATERR_L4E		0x20000000
 #define IGC_RXDEXT_STATERR_IPE		0x40000000
@@ -396,11 +401,47 @@
 #define IGC_RCTL_PMCF		0x00800000 /* pass MAC control frames */
 #define IGC_RCTL_SECRC		0x04000000 /* Strip Ethernet CRC */
 
-#define I225_RXPBSIZE_DEFAULT	0x000000A2 /* RXPBSIZE default */
-#define I225_TXPBSIZE_DEFAULT	0x04000014 /* TXPBSIZE default */
-#define IGC_RXPBS_CFG_TS_EN	0x80000000 /* Timestamp in Rx buffer */
-
-#define IGC_TXPBSIZE_TSN	0x04145145 /* 5k bytes buffer for each queue */
+/* Mask for RX packet buffer size */
+#define IGC_RXPBSIZE_EXP_MASK		GENMASK(5, 0)
+#define IGC_BMC2OSPBSIZE_MASK		GENMASK(11, 6)
+#define IGC_RXPBSIZE_BE_MASK		GENMASK(17, 12)
+/* Mask for timestamp in RX buffer */
+#define IGC_RXPBS_CFG_TS_EN_MASK	GENMASK(31, 31)
+/* High-priority RX packet buffer size (KB). Used for Express traffic when preemption is enabled */
+#define IGC_RXPBSIZE_EXP(x)		FIELD_PREP(IGC_RXPBSIZE_EXP_MASK, (x))
+/* BMC to OS packet buffer size in KB */
+#define IGC_BMC2OSPBSIZE(x)		FIELD_PREP(IGC_BMC2OSPBSIZE_MASK, (x))
+/* Low-priority RX packet buffer size (KB). Used for BE traffic when preemption is enabled */
+#define IGC_RXPBSIZE_BE(x)		FIELD_PREP(IGC_RXPBSIZE_BE_MASK, (x))
+/* Enable RX packet buffer for timestamp descriptor, saving 16 bytes per packet if set */
+#define IGC_RXPBS_CFG_TS_EN		FIELD_PREP(IGC_RXPBS_CFG_TS_EN_MASK, 1)
+/* Default value following I225/I226 SW User Manual Section 8.3.1 */
+#define IGC_RXPBSIZE_EXP_BMC_DEFAULT ( \
+	IGC_RXPBSIZE_EXP(34) | IGC_BMC2OSPBSIZE(2))
+#define IGC_RXPBSIZE_EXP_BMC_BE_TSN ( \
+	IGC_RXPBSIZE_EXP(15) | IGC_BMC2OSPBSIZE(2) | IGC_RXPBSIZE_BE(15))
+
+/* Mask for TX packet buffer size */
+#define IGC_TXPB0SIZE_MASK		GENMASK(5, 0)
+#define IGC_TXPB1SIZE_MASK		GENMASK(11, 6)
+#define IGC_TXPB2SIZE_MASK		GENMASK(17, 12)
+#define IGC_TXPB3SIZE_MASK		GENMASK(23, 18)
+/* Mask for OS to BMC packet buffer size */
+#define IGC_OS2BMCPBSIZE_MASK		GENMASK(29, 24)
+/* TX Packet buffer size in KB */
+#define IGC_TXPB0SIZE(x)		FIELD_PREP(IGC_TXPB0SIZE_MASK, (x))
+#define IGC_TXPB1SIZE(x)		FIELD_PREP(IGC_TXPB1SIZE_MASK, (x))
+#define IGC_TXPB2SIZE(x)		FIELD_PREP(IGC_TXPB2SIZE_MASK, (x))
+#define IGC_TXPB3SIZE(x)		FIELD_PREP(IGC_TXPB3SIZE_MASK, (x))
+/* OS to BMC packet buffer size in KB */
+#define IGC_OS2BMCPBSIZE(x)		FIELD_PREP(IGC_OS2BMCPBSIZE_MASK, (x))
+/* Default value following I225/I226 SW User Manual Section 8.3.2 */
+#define IGC_TXPBSIZE_DEFAULT ( \
+	IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \
+	IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4))
+#define IGC_TXPBSIZE_TSN ( \
+	IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \
+	IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4))
 
 #define IGC_DTXMXPKTSZ_TSN	0x19 /* 1600 bytes of max TX DMA packet size */
 #define IGC_DTXMXPKTSZ_DEFAULT	0x98 /* 9728-byte Jumbo frames */
@@ -539,8 +580,10 @@
 
 /* Transmit Scheduling */
 #define IGC_TQAVCTRL_TRANSMIT_MODE_TSN	0x00000001
+#define IGC_TQAVCTRL_PREEMPT_ENA	0x00000002
 #define IGC_TQAVCTRL_ENHANCED_QAV	0x00000008
 #define IGC_TQAVCTRL_FUTSCDDIS		0x00000080
+#define IGC_TQAVCTRL_MIN_FRAG_MASK	0x0000C000
 
 #define IGC_TXQCTL_QUEUE_MODE_LAUNCHT	0x00000001
 #define IGC_TXQCTL_STRICT_CYCLE		0x00000002
@@ -574,7 +617,10 @@
 #define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x3f) << 2)
 #define IGC_PTM_CTRL_PTM_TO(usec)	(((usec) & 0xff) << 8)
 
-#define IGC_PTM_SHORT_CYC_DEFAULT	1   /* Default short cycle interval */
+/* A short cycle time of 1us theoretically should work, but appears to be too
+ * short in practice.
+ */
+#define IGC_PTM_SHORT_CYC_DEFAULT	4   /* Default short cycle interval */
 #define IGC_PTM_CYC_TIME_DEFAULT	5   /* Default PTM cycle time */
 #define IGC_PTM_TIMEOUT_DEFAULT		255 /* Default timeout for PTM errors */
 
@@ -593,6 +639,7 @@
 #define IGC_PTM_STAT_T4M1_OVFL		BIT(3) /* T4 minus T1 overflow */
 #define IGC_PTM_STAT_ADJUST_1ST		BIT(4) /* 1588 timer adjusted during 1st PTM cycle */
 #define IGC_PTM_STAT_ADJUST_CYC		BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */
+#define IGC_PTM_STAT_ALL		GENMASK(5, 0) /* Used to clear all status */
 
 /* PCIe PTM Cycle Control */
 #define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec)	((msec) & 0x3ff) /* PTM Cycle Time (msec) */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 817838677817..3fc1eded9605 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -8,6 +8,7 @@
 
 #include "igc.h"
 #include "igc_diag.h"
+#include "igc_tsn.h"
 
 /* forward declaration */
 struct igc_stats {
@@ -1781,6 +1782,83 @@ static int igc_ethtool_set_eee(struct net_device *netdev,
 	return 0;
 }
 
+static int igc_ethtool_get_mm(struct net_device *netdev,
+			      struct ethtool_mm_state *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_fpe_t *fpe = &adapter->fpe;
+
+	ethtool_mmsv_get_mm(&fpe->mmsv, cmd);
+	cmd->tx_min_frag_size = fpe->tx_min_frag_size;
+	cmd->rx_min_frag_size = IGC_RX_MIN_FRAG_SIZE;
+
+	return 0;
+}
+
+static int igc_ethtool_set_mm(struct net_device *netdev,
+			      struct ethtool_mm_cfg *cmd,
+			      struct netlink_ext_ack *extack)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_fpe_t *fpe = &adapter->fpe;
+
+	fpe->tx_min_frag_size = igc_fpe_get_supported_frag_size(cmd->tx_min_frag_size);
+	if (fpe->tx_min_frag_size != cmd->tx_min_frag_size)
+		NL_SET_ERR_MSG_MOD(extack,
+				   "tx-min-frag-size value set is unsupported. Rounded up to supported value (64, 128, 192, 256)");
+
+	if (fpe->mmsv.pmac_enabled != cmd->pmac_enabled) {
+		if (cmd->pmac_enabled)
+			static_branch_inc(&igc_fpe_enabled);
+		else
+			static_branch_dec(&igc_fpe_enabled);
+	}
+
+	ethtool_mmsv_set_mm(&fpe->mmsv, cmd);
+
+	return igc_tsn_offload_apply(adapter);
+}
+
+/**
+ * igc_ethtool_get_frame_ass_error - Get the frame assembly error count.
+ * @reg_value: Register value for IGC_PRMEXCPRCNT
+ * Return: The count of frame assembly errors.
+ */
+static u64 igc_ethtool_get_frame_ass_error(u32 reg_value)
+{
+	/* Out of order statistics */
+	u32 ooo_frame_cnt, ooo_frag_cnt;
+	u32 miss_frame_frag_cnt;
+
+	ooo_frame_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAME_CNT, reg_value);
+	ooo_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAG_CNT, reg_value);
+	miss_frame_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT,
+					reg_value);
+
+	return ooo_frame_cnt + ooo_frag_cnt + miss_frame_frag_cnt;
+}
+
+static u64 igc_ethtool_get_frame_smd_error(u32 reg_value)
+{
+	return FIELD_GET(IGC_PRMEXCPRCNT_OOO_SMDC, reg_value);
+}
+
+static void igc_ethtool_get_mm_stats(struct net_device *dev,
+				     struct ethtool_mm_stats *stats)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 reg_value;
+
+	reg_value = rd32(IGC_PRMEXCPRCNT);
+
+	stats->MACMergeFrameAssErrorCount = igc_ethtool_get_frame_ass_error(reg_value);
+	stats->MACMergeFrameSmdErrorCount = igc_ethtool_get_frame_smd_error(reg_value);
+	stats->MACMergeFrameAssOkCount = rd32(IGC_PRMPTDRCNT);
+	stats->MACMergeFragCountRx = rd32(IGC_PRMEVNTRCNT);
+	stats->MACMergeFragCountTx = rd32(IGC_PRMEVNTTCNT);
+}
+
 static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 					  struct ethtool_link_ksettings *cmd)
 {
@@ -2076,6 +2154,9 @@ static const struct ethtool_ops igc_ethtool_ops = {
 	.get_link_ksettings	= igc_ethtool_get_link_ksettings,
 	.set_link_ksettings	= igc_ethtool_set_link_ksettings,
 	.self_test		= igc_ethtool_diag_test,
+	.get_mm			= igc_ethtool_get_mm,
+	.get_mm_stats		= igc_ethtool_get_mm_stats,
+	.set_mm			= igc_ethtool_set_mm,
 };
 
 void igc_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index d9d1a1a11daf..be8a49a86d09 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -279,9 +279,4 @@ struct net_device *igc_get_hw_dev(struct igc_hw *hw);
 #define hw_dbg(format, arg...) \
 	netdev_dbg(igc_get_hw_dev(hw), format, ##arg)
 
-s32  igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value);
-s32  igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value);
-void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value);
-void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value);
-
 #endif /* _IGC_HW_H_ */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 27872bdea9bd..031c332f66c4 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1092,10 +1092,12 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 
 	dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE);
 	if (dma_mapping_error(ring->dev, dma)) {
-		netdev_err_once(ring->netdev, "Failed to map DMA for TX\n");
+		net_err_ratelimited("%s: DMA mapping error for empty frame\n",
+				    netdev_name(ring->netdev));
 		return -ENOMEM;
 	}
 
+	buffer->type = IGC_TX_BUFFER_TYPE_SKB;
 	buffer->skb = skb;
 	buffer->protocol = 0;
 	buffer->bytecount = skb->len;
@@ -1107,20 +1109,12 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 	return 0;
 }
 
-static int igc_init_tx_empty_descriptor(struct igc_ring *ring,
-					struct sk_buff *skb,
-					struct igc_tx_buffer *first)
+static void igc_init_tx_empty_descriptor(struct igc_ring *ring,
+					 struct sk_buff *skb,
+					 struct igc_tx_buffer *first)
 {
 	union igc_adv_tx_desc *desc;
 	u32 cmd_type, olinfo_status;
-	int err;
-
-	if (!igc_desc_unused(ring))
-		return -EBUSY;
-
-	err = igc_init_empty_frame(ring, first, skb);
-	if (err)
-		return err;
 
 	cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
 		   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
@@ -1139,8 +1133,6 @@ static int igc_init_tx_empty_descriptor(struct igc_ring *ring,
 	ring->next_to_use++;
 	if (ring->next_to_use == ring->count)
 		ring->next_to_use = 0;
-
-	return 0;
 }
 
 #define IGC_EMPTY_FRAME_SIZE 60
@@ -1566,6 +1558,40 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s
 	return false;
 }
 
+static int igc_insert_empty_frame(struct igc_ring *tx_ring)
+{
+	struct igc_tx_buffer *empty_info;
+	struct sk_buff *empty_skb;
+	void *data;
+	int ret;
+
+	empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	empty_skb = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC);
+	if (unlikely(!empty_skb)) {
+		net_err_ratelimited("%s: skb alloc error for empty frame\n",
+				    netdev_name(tx_ring->netdev));
+		return -ENOMEM;
+	}
+
+	data = skb_put(empty_skb, IGC_EMPTY_FRAME_SIZE);
+	memset(data, 0, IGC_EMPTY_FRAME_SIZE);
+
+	/* Prepare DMA mapping and Tx buffer information */
+	ret = igc_init_empty_frame(tx_ring, empty_info, empty_skb);
+	if (unlikely(ret)) {
+		dev_kfree_skb_any(empty_skb);
+		return ret;
+	}
+
+	/* Prepare advanced context descriptor for empty packet */
+	igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0);
+
+	/* Prepare advanced data descriptor for empty packet */
+	igc_init_tx_empty_descriptor(tx_ring, empty_skb, empty_info);
+
+	return 0;
+}
+
 static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 				       struct igc_ring *tx_ring)
 {
@@ -1585,6 +1611,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	 *	+ 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD,
 	 *	+ 2 desc gap to keep tail from touching head,
 	 *	+ 1 desc for context descriptor,
+	 *	+ 2 desc for inserting an empty packet for launch time,
 	 * otherwise try next time
 	 */
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
@@ -1604,24 +1631,16 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty);
 
 	if (insert_empty) {
-		struct igc_tx_buffer *empty_info;
-		struct sk_buff *empty;
-		void *data;
-
-		empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
-		empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC);
-		if (!empty)
-			goto done;
-
-		data = skb_put(empty, IGC_EMPTY_FRAME_SIZE);
-		memset(data, 0, IGC_EMPTY_FRAME_SIZE);
-
-		igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0);
-
-		if (igc_init_tx_empty_descriptor(tx_ring,
-						 empty,
-						 empty_info) < 0)
-			dev_kfree_skb_any(empty);
+		/* Reset the launch time if the required empty frame fails to
+		 * be inserted. However, this packet is not dropped, so it
+		 * "dirties" the current Qbv cycle. This ensures that the
+		 * upcoming packet, which is scheduled in the next Qbv cycle,
+		 * does not require an empty frame. This way, the launch time
+		 * continues to function correctly despite the current failure
+		 * to insert the empty frame.
+		 */
+		if (igc_insert_empty_frame(tx_ring))
+			launch_time = 0;
 	}
 
 done:
@@ -1649,7 +1668,8 @@ done:
 		if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags;
-			if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_USE_CYCLES)
+			if (skb->sk &&
+			    READ_ONCE(skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC)
 				tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1;
 		} else {
 			adapter->tx_hwtstamp_skipped++;
@@ -2123,10 +2143,6 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring,
 				union igc_adv_rx_desc *rx_desc,
 				struct sk_buff *skb)
 {
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) {
 		struct net_device *netdev = rx_ring->netdev;
 
@@ -2448,8 +2464,7 @@ unmap:
 	return -ENOMEM;
 }
 
-static struct igc_ring *igc_xdp_get_tx_ring(struct igc_adapter *adapter,
-					    int cpu)
+struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu)
 {
 	int index = cpu;
 
@@ -2473,7 +2488,7 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp)
 	if (unlikely(!xdpf))
 		return -EFAULT;
 
-	ring = igc_xdp_get_tx_ring(adapter, cpu);
+	ring = igc_get_tx_ring(adapter, cpu);
 	nq = txring_txq(ring);
 
 	__netif_tx_lock(nq, cpu);
@@ -2515,8 +2530,7 @@ out_failure:
 	}
 }
 
-static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
-					struct xdp_buff *xdp)
+static int igc_xdp_run_prog(struct igc_adapter *adapter, struct xdp_buff *xdp)
 {
 	struct bpf_prog *prog;
 	int res;
@@ -2530,11 +2544,11 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
 	res = __igc_xdp_run_prog(adapter, prog, xdp);
 
 out:
-	return ERR_PTR(-res);
+	return res;
 }
 
 /* This function assumes __netif_tx_lock is held by the caller. */
-static void igc_flush_tx_descriptors(struct igc_ring *ring)
+void igc_flush_tx_descriptors(struct igc_ring *ring)
 {
 	/* Once tail pointer is updated, hardware can fetch the descriptors
 	 * any time so we issue a write membar here to ensure all memory
@@ -2551,7 +2565,7 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status)
 	struct igc_ring *ring;
 
 	if (status & IGC_XDP_TX) {
-		ring = igc_xdp_get_tx_ring(adapter, cpu);
+		ring = igc_get_tx_ring(adapter, cpu);
 		nq = txring_txq(ring);
 
 		__netif_tx_lock(nq, cpu);
@@ -2585,6 +2599,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = igc_desc_unused(rx_ring);
 	int xdp_status = 0, rx_buffer_pgcnt;
+	int xdp_res = 0;
 
 	while (likely(total_packets < budget)) {
 		struct igc_xdp_buff ctx = { .rx_ts = NULL };
@@ -2622,6 +2637,14 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			size -= IGC_TS_HDR_LEN;
 		}
 
+		if (igc_fpe_is_pmac_enabled(adapter) &&
+		    igc_fpe_handle_mpacket(adapter, rx_desc, size, pktbuf)) {
+			/* Advance the ring next-to-clean */
+			igc_is_non_eop(rx_ring, rx_desc);
+			cleaned_count++;
+			continue;
+		}
+
 		if (!skb) {
 			xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq);
 			xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring),
@@ -2630,12 +2653,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			xdp_buff_clear_frags_flag(&ctx.xdp);
 			ctx.rx_desc = rx_desc;
 
-			skb = igc_xdp_run_prog(adapter, &ctx.xdp);
+			xdp_res = igc_xdp_run_prog(adapter, &ctx.xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			unsigned int xdp_res = -PTR_ERR(skb);
-
+		if (xdp_res) {
 			switch (xdp_res) {
 			case IGC_XDP_CONSUMED:
 				rx_buffer->pagecnt_bias++;
@@ -2657,7 +2678,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			skb = igc_construct_skb(rx_ring, rx_buffer, &ctx);
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_failed++;
 			rx_buffer->pagecnt_bias++;
 			set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
@@ -2672,7 +2693,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			continue;
 
 		/* verify the packet layout is correct */
-		if (igc_cleanup_headers(rx_ring, rx_desc, skb)) {
+		if (xdp_res || igc_cleanup_headers(rx_ring, rx_desc, skb)) {
 			skb = NULL;
 			continue;
 		}
@@ -2707,8 +2728,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 }
 
 static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
-					    struct xdp_buff *xdp)
+					    struct igc_xdp_buff *ctx)
 {
+	struct xdp_buff *xdp = &ctx->xdp;
 	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
@@ -2727,27 +2749,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
 		__skb_pull(skb, metasize);
 	}
 
+	if (ctx->rx_ts) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV;
+		skb_hwtstamps(skb)->netdev_data = ctx->rx_ts;
+	}
+
 	return skb;
 }
 
 static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 				union igc_adv_rx_desc *desc,
-				struct xdp_buff *xdp,
-				ktime_t timestamp)
+				struct igc_xdp_buff *ctx)
 {
 	struct igc_ring *ring = q_vector->rx.ring;
 	struct sk_buff *skb;
 
-	skb = igc_construct_skb_zc(ring, xdp);
+	skb = igc_construct_skb_zc(ring, ctx);
 	if (!skb) {
 		ring->rx_stats.alloc_failed++;
 		set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags);
 		return;
 	}
 
-	if (timestamp)
-		skb_hwtstamps(skb)->hwtstamp = timestamp;
-
 	if (igc_cleanup_headers(ring, desc, skb))
 		return;
 
@@ -2783,7 +2806,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		union igc_adv_rx_desc *desc;
 		struct igc_rx_buffer *bi;
 		struct igc_xdp_buff *ctx;
-		ktime_t timestamp = 0;
 		unsigned int size;
 		int res;
 
@@ -2813,6 +2835,8 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 			 */
 			bi->xdp->data_meta += IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
+		} else {
+			ctx->rx_ts = NULL;
 		}
 
 		bi->xdp->data_end = bi->xdp->data + size;
@@ -2821,7 +2845,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		res = __igc_xdp_run_prog(adapter, prog, bi->xdp);
 		switch (res) {
 		case IGC_XDP_PASS:
-			igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp);
+			igc_dispatch_skb_zc(q_vector, desc, ctx);
 			fallthrough;
 		case IGC_XDP_CONSUMED:
 			xsk_buff_free(bi->xdp);
@@ -2955,9 +2979,48 @@ static u64 igc_xsk_fill_timestamp(void *_priv)
 	return *(u64 *)_priv;
 }
 
+static void igc_xsk_request_launch_time(u64 launch_time, void *_priv)
+{
+	struct igc_metadata_request *meta_req = _priv;
+	struct igc_ring *tx_ring = meta_req->tx_ring;
+	__le32 launch_time_offset;
+	bool insert_empty = false;
+	bool first_flag = false;
+	u16 used_desc = 0;
+
+	if (!tx_ring->launchtime_enable)
+		return;
+
+	launch_time_offset = igc_tx_launchtime(tx_ring,
+					       ns_to_ktime(launch_time),
+					       &first_flag, &insert_empty);
+	if (insert_empty) {
+		/* Disregard the launch time request if the required empty frame
+		 * fails to be inserted.
+		 */
+		if (igc_insert_empty_frame(tx_ring))
+			return;
+
+		meta_req->tx_buffer =
+			&tx_ring->tx_buffer_info[tx_ring->next_to_use];
+		/* Inserting an empty packet requires two descriptors:
+		 * one data descriptor and one context descriptor.
+		 */
+		used_desc += 2;
+	}
+
+	/* Use one context descriptor to specify launch time and first flag. */
+	igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0);
+	used_desc += 1;
+
+	/* Update the number of used descriptors in this request */
+	meta_req->used_desc += used_desc;
+}
+
 const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = {
 	.tmo_request_timestamp		= igc_xsk_request_timestamp,
 	.tmo_fill_timestamp		= igc_xsk_fill_timestamp,
+	.tmo_request_launch_time	= igc_xsk_request_launch_time,
 };
 
 static void igc_xdp_xmit_zc(struct igc_ring *ring)
@@ -2980,7 +3043,13 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 	ntu = ring->next_to_use;
 	budget = igc_desc_unused(ring);
 
-	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
+	/* Packets with launch time require one data descriptor and one context
+	 * descriptor. When the launch time falls into the next Qbv cycle, we
+	 * may need to insert an empty packet, which requires two more
+	 * descriptors. Therefore, to be safe, we always ensure we have at least
+	 * 4 descriptors available.
+	 */
+	while (budget >= 4 && xsk_tx_peek_desc(pool, &xdp_desc)) {
 		struct igc_metadata_request meta_req;
 		struct xsk_tx_metadata *meta = NULL;
 		struct igc_tx_buffer *bi;
@@ -3001,9 +3070,19 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		meta_req.tx_ring = ring;
 		meta_req.tx_buffer = bi;
 		meta_req.meta = meta;
+		meta_req.used_desc = 0;
 		xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops,
 					&meta_req);
 
+		/* xsk_tx_metadata_request() may have updated next_to_use */
+		ntu = ring->next_to_use;
+
+		/* xsk_tx_metadata_request() may have updated Tx buffer info */
+		bi = meta_req.tx_buffer;
+
+		/* xsk_tx_metadata_request() may use a few descriptors */
+		budget -= meta_req.used_desc;
+
 		tx_desc = IGC_TX_DESC(ring, ntu);
 		tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type);
 		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
@@ -3021,9 +3100,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		ntu++;
 		if (ntu == ring->count)
 			ntu = 0;
+
+		ring->next_to_use = ntu;
+		budget--;
 	}
 
-	ring->next_to_use = ntu;
 	if (tx_desc) {
 		igc_flush_tx_descriptors(ring);
 		xsk_tx_release(pool);
@@ -3071,6 +3152,11 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD)))
 			break;
 
+		if (igc_fpe_is_pmac_enabled(adapter) &&
+		    igc_fpe_transmitted_smd_v(tx_desc))
+			ethtool_mmsv_event_handle(&adapter->fpe.mmsv,
+						  ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET);
+
 		/* Hold the completions while there's a pending tx hardware
 		 * timestamp request from XDP Tx metadata.
 		 */
@@ -3963,6 +4049,30 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 }
 
 /**
+ * igc_enable_empty_addr_recv - Enable Rx of packets with all-zeroes MAC address
+ * @adapter: Pointer to the igc_adapter structure.
+ *
+ * Frame preemption verification requires that packets with the all-zeroes
+ * MAC address are allowed to be received by the driver. This function adds the
+ * all-zeroes destination address to the list of acceptable addresses.
+ *
+ * Return: 0 on success, negative value otherwise.
+ */
+int igc_enable_empty_addr_recv(struct igc_adapter *adapter)
+{
+	u8 empty[ETH_ALEN] = {};
+
+	return igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty, -1);
+}
+
+void igc_disable_empty_addr_recv(struct igc_adapter *adapter)
+{
+	u8 empty[ETH_ALEN] = {};
+
+	igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty);
+}
+
+/**
  * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
  * @netdev: network interface device structure
  *
@@ -4948,6 +5058,22 @@ static int igc_sw_init(struct igc_adapter *adapter)
 	return 0;
 }
 
+static void igc_set_queue_napi(struct igc_adapter *adapter, int vector,
+			       struct napi_struct *napi)
+{
+	struct igc_q_vector *q_vector = adapter->q_vector[vector];
+
+	if (q_vector->rx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->rx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, napi);
+
+	if (q_vector->tx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->tx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, napi);
+}
+
 /**
  * igc_up - Open the interface and prepare it to handle traffic
  * @adapter: board private structure
@@ -4955,6 +5081,7 @@ static int igc_sw_init(struct igc_adapter *adapter)
 void igc_up(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int i = 0;
 
 	/* hardware has been reset, we need to reload some things */
@@ -4962,8 +5089,11 @@ void igc_up(struct igc_adapter *adapter)
 
 	clear_bit(__IGC_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&adapter->q_vector[i]->napi);
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igc_set_queue_napi(adapter, i, napi);
+	}
 
 	if (adapter->msix_entries)
 		igc_configure_msix(adapter);
@@ -5192,12 +5322,13 @@ void igc_down(struct igc_adapter *adapter)
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		if (adapter->q_vector[i]) {
 			napi_synchronize(&adapter->q_vector[i]->napi);
+			igc_set_queue_napi(adapter, i, NULL);
 			napi_disable(&adapter->q_vector[i]->napi);
 		}
 	}
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	/* record the stats before reset*/
 	spin_lock(&adapter->stats64_lock);
@@ -5216,6 +5347,9 @@ void igc_down(struct igc_adapter *adapter)
 	igc_disable_all_tx_rings_hw(adapter);
 	igc_clean_all_tx_rings(adapter);
 	igc_clean_all_rx_rings(adapter);
+
+	if (adapter->fpe.mmsv.pmac_enabled)
+		ethtool_mmsv_stop(&adapter->fpe.mmsv);
 }
 
 void igc_reinit_locked(struct igc_adapter *adapter)
@@ -5576,6 +5710,9 @@ static int igc_request_msix(struct igc_adapter *adapter)
 				  q_vector);
 		if (err)
 			goto err_free;
+
+		netif_napi_set_irq(&q_vector->napi,
+				   adapter->msix_entries[vector].vector);
 	}
 
 	igc_configure_msix(adapter);
@@ -5612,7 +5749,8 @@ static void igc_clear_interrupt_scheme(struct igc_adapter *adapter)
  */
 static void igc_update_phy_info(struct timer_list *t)
 {
-	struct igc_adapter *adapter = from_timer(adapter, t, phy_info_timer);
+	struct igc_adapter *adapter = timer_container_of(adapter, t,
+							 phy_info_timer);
 
 	igc_get_phy_info(&adapter->hw);
 }
@@ -5654,7 +5792,8 @@ bool igc_has_link(struct igc_adapter *adapter)
  */
 static void igc_watchdog(struct timer_list *t)
 {
-	struct igc_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	struct igc_adapter *adapter = timer_container_of(adapter, t,
+							 watchdog_timer);
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
 }
@@ -5737,6 +5876,10 @@ static void igc_watchdog_task(struct work_struct *work)
 			 */
 			igc_tsn_adjust_txtime_offset(adapter);
 
+			if (adapter->fpe.mmsv.pmac_enabled)
+				ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv,
+							       true);
+
 			if (adapter->link_speed != SPEED_1000)
 				goto no_wait;
 
@@ -5772,6 +5915,10 @@ no_wait:
 			netdev_info(netdev, "NIC Link is Down\n");
 			netif_carrier_off(netdev);
 
+			if (adapter->fpe.mmsv.pmac_enabled)
+				ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv,
+							       false);
+
 			/* link state has changed, schedule phy info update */
 			if (!test_bit(__IGC_DOWN, &adapter->state))
 				mod_timer(&adapter->phy_info_timer,
@@ -6018,6 +6165,7 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = adapter->pdev;
 	struct igc_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int err = 0;
 	int i = 0;
 
@@ -6053,8 +6201,11 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 
 	clear_bit(__IGC_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&adapter->q_vector[i]->napi);
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igc_set_queue_napi(adapter, i, napi);
+	}
 
 	/* Clear any pending interrupts. */
 	rd32(IGC_ICR);
@@ -6337,6 +6488,10 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	if (!validate_schedule(adapter, qopt))
 		return -EINVAL;
 
+	/* preemptible isn't supported yet */
+	if (qopt->mqprio.preemptible_tcs)
+		return -EOPNOTSUPP;
+
 	igc_ptp_read(adapter, &now);
 
 	if (igc_tsn_is_taprio_activated_by_user(adapter) &&
@@ -6577,13 +6732,14 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
 				 struct tc_mqprio_qopt_offload *mqprio)
 {
 	struct igc_hw *hw = &adapter->hw;
-	int i;
+	int err, i;
 
 	if (hw->mac.type != igc_i225)
 		return -EOPNOTSUPP;
 
 	if (!mqprio->qopt.num_tc) {
 		adapter->strict_priority_enable = false;
+		netdev_reset_tc(adapter->netdev);
 		goto apply;
 	}
 
@@ -6614,6 +6770,21 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
 	igc_save_mqprio_params(adapter, mqprio->qopt.num_tc,
 			       mqprio->qopt.offset);
 
+	err = netdev_set_num_tc(adapter->netdev, adapter->num_tc);
+	if (err)
+		return err;
+
+	for (i = 0; i < adapter->num_tc; i++) {
+		err = netdev_set_tc_queue(adapter->netdev, i, 1,
+					  adapter->queue_per_tc[i]);
+		if (err)
+			return err;
+	}
+
+	/* In case the card is configured with less than four queues. */
+	for (; i < IGC_MAX_TX_QUEUES; i++)
+		adapter->queue_per_tc[i] = i;
+
 	mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
 apply:
@@ -6677,7 +6848,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
-	ring = igc_xdp_get_tx_ring(adapter, cpu);
+	ring = igc_get_tx_ring(adapter, cpu);
 	nq = txring_txq(ring);
 
 	__netif_tx_lock(nq, cpu);
@@ -6779,45 +6950,6 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_get_tstamp		= igc_get_tstamp,
 };
 
-/* PCIe configuration access */
-void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value)
-{
-	struct igc_adapter *adapter = hw->back;
-
-	pci_read_config_word(adapter->pdev, reg, value);
-}
-
-void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value)
-{
-	struct igc_adapter *adapter = hw->back;
-
-	pci_write_config_word(adapter->pdev, reg, *value);
-}
-
-s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
-{
-	struct igc_adapter *adapter = hw->back;
-
-	if (!pci_is_pcie(adapter->pdev))
-		return -IGC_ERR_CONFIG;
-
-	pcie_capability_read_word(adapter->pdev, reg, value);
-
-	return IGC_SUCCESS;
-}
-
-s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
-{
-	struct igc_adapter *adapter = hw->back;
-
-	if (!pci_is_pcie(adapter->pdev))
-		return -IGC_ERR_CONFIG;
-
-	pcie_capability_write_word(adapter->pdev, reg, *value);
-
-	return IGC_SUCCESS;
-}
-
 u32 igc_rd32(struct igc_hw *hw, u32 reg)
 {
 	struct igc_adapter *igc = container_of(hw, struct igc_adapter, hw);
@@ -6983,6 +7115,10 @@ static int igc_probe(struct pci_dev *pdev,
 	adapter->port_num = hw->bus.func;
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
+	/* Disable ASPM L1.2 on I226 devices to avoid packet loss */
+	if (igc_is_device_id_i226(hw))
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+
 	err = pci_save_state(pdev);
 	if (err)
 		goto err_ioremap;
@@ -7062,6 +7198,9 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
 
+	/* enable HW vlan tag insertion/stripping by default */
+	netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
+
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
@@ -7094,8 +7233,8 @@ static int igc_probe(struct pci_dev *pdev,
 	}
 
 	/* configure RXPBSIZE and TXPBSIZE */
-	wr32(IGC_RXPBS, I225_RXPBSIZE_DEFAULT);
-	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+	wr32(IGC_RXPBS, IGC_RXPBSIZE_EXP_BMC_DEFAULT);
+	wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT);
 
 	timer_setup(&adapter->watchdog_timer, igc_watchdog, 0);
 	timer_setup(&adapter->phy_info_timer, igc_update_phy_info, 0);
@@ -7103,8 +7242,8 @@ static int igc_probe(struct pci_dev *pdev,
 	INIT_WORK(&adapter->reset_task, igc_reset_task);
 	INIT_WORK(&adapter->watchdog_task, igc_watchdog_task);
 
-	hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	adapter->hrtimer.function = &igc_qbv_scheduling_timer;
+	hrtimer_setup(&adapter->hrtimer, &igc_qbv_scheduling_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	/* Initialize link properties that are user-changeable */
 	adapter->fc_autoneg = true;
@@ -7127,6 +7266,8 @@ static int igc_probe(struct pci_dev *pdev,
 
 	igc_tsn_clear_schedule(adapter);
 
+	igc_fpe_init(adapter);
+
 	/* reset the hardware with the new settings */
 	igc_reset(adapter);
 
@@ -7168,6 +7309,7 @@ static int igc_probe(struct pci_dev *pdev,
 
 err_register:
 	igc_release_hw_control(adapter);
+	igc_ptp_stop(adapter);
 err_eeprom:
 	if (!igc_check_reset_block(hw))
 		igc_reset_phy(hw);
@@ -7209,8 +7351,8 @@ static void igc_remove(struct pci_dev *pdev)
 
 	set_bit(__IGC_DOWN, &adapter->state);
 
-	del_timer_sync(&adapter->watchdog_timer);
-	del_timer_sync(&adapter->phy_info_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->phy_info_timer);
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
@@ -7338,7 +7480,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev)
 	netif_rx(skb);
 }
 
-static int igc_resume(struct device *dev)
+static int __igc_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -7362,6 +7504,9 @@ static int igc_resume(struct device *dev)
 	pci_enable_wake(pdev, PCI_D3hot, 0);
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
+	if (igc_is_device_id_i226(hw))
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+
 	if (igc_init_interrupt_scheme(adapter, true)) {
 		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
@@ -7381,7 +7526,11 @@ static int igc_resume(struct device *dev)
 	wr32(IGC_WUS, ~0);
 
 	if (netif_running(netdev)) {
+		if (!rpm)
+			rtnl_lock();
 		err = __igc_open(netdev, true);
+		if (!rpm)
+			rtnl_unlock();
 		if (!err)
 			netif_device_attach(netdev);
 	}
@@ -7389,9 +7538,14 @@ static int igc_resume(struct device *dev)
 	return err;
 }
 
+static int igc_resume(struct device *dev)
+{
+	return __igc_resume(dev, false);
+}
+
 static int igc_runtime_resume(struct device *dev)
 {
-	return igc_resume(dev);
+	return __igc_resume(dev, true);
 }
 
 static int igc_suspend(struct device *dev)
@@ -7436,14 +7590,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev,
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
+	rtnl_lock();
 	netif_device_detach(netdev);
 
-	if (state == pci_channel_io_perm_failure)
+	if (state == pci_channel_io_perm_failure) {
+		rtnl_unlock();
 		return PCI_ERS_RESULT_DISCONNECT;
+	}
 
 	if (netif_running(netdev))
 		igc_down(adapter);
 	pci_disable_device(pdev);
+	rtnl_unlock();
 
 	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -7454,7 +7612,7 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev,
  *  @pdev: Pointer to PCI device
  *
  *  Restart the card from scratch, as if from a cold-boot. Implementation
- *  resembles the first-half of the igc_resume routine.
+ *  resembles the first-half of the __igc_resume routine.
  **/
 static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 {
@@ -7474,6 +7632,9 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 		pci_enable_wake(pdev, PCI_D3hot, 0);
 		pci_enable_wake(pdev, PCI_D3cold, 0);
 
+		if (igc_is_device_id_i226(hw))
+			pci_disable_link_state_locked(pdev, PCIE_LINK_STATE_L1_2);
+
 		/* In case of PCI error, adapter loses its HW address
 		 * so we should re-assign it here.
 		 */
@@ -7493,7 +7654,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
  *
  *  This callback is called when the error recovery driver tells us that
  *  its OK to resume normal operation. Implementation resembles the
- *  second-half of the igc_resume routine.
+ *  second-half of the __igc_resume routine.
  */
 static void igc_io_resume(struct pci_dev *pdev)
 {
diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.c b/drivers/net/ethernet/intel/igc/igc_nvm.c
index 58f81aba0144..efd121c03967 100644
--- a/drivers/net/ethernet/intel/igc/igc_nvm.c
+++ b/drivers/net/ethernet/intel/igc/igc_nvm.c
@@ -36,56 +36,6 @@ static s32 igc_poll_eerd_eewr_done(struct igc_hw *hw, int ee_reg)
 }
 
 /**
- * igc_acquire_nvm - Generic request for access to EEPROM
- * @hw: pointer to the HW structure
- *
- * Set the EEPROM access request bit and wait for EEPROM access grant bit.
- * Return successful if access grant bit set, else clear the request for
- * EEPROM access and return -IGC_ERR_NVM (-1).
- */
-s32 igc_acquire_nvm(struct igc_hw *hw)
-{
-	s32 timeout = IGC_NVM_GRANT_ATTEMPTS;
-	u32 eecd = rd32(IGC_EECD);
-	s32 ret_val = 0;
-
-	wr32(IGC_EECD, eecd | IGC_EECD_REQ);
-	eecd = rd32(IGC_EECD);
-
-	while (timeout) {
-		if (eecd & IGC_EECD_GNT)
-			break;
-		udelay(5);
-		eecd = rd32(IGC_EECD);
-		timeout--;
-	}
-
-	if (!timeout) {
-		eecd &= ~IGC_EECD_REQ;
-		wr32(IGC_EECD, eecd);
-		hw_dbg("Could not acquire NVM grant\n");
-		ret_val = -IGC_ERR_NVM;
-	}
-
-	return ret_val;
-}
-
-/**
- * igc_release_nvm - Release exclusive access to EEPROM
- * @hw: pointer to the HW structure
- *
- * Stop any current commands to the EEPROM and clear the EEPROM request bit.
- */
-void igc_release_nvm(struct igc_hw *hw)
-{
-	u32 eecd;
-
-	eecd = rd32(IGC_EECD);
-	eecd &= ~IGC_EECD_REQ;
-	wr32(IGC_EECD, eecd);
-}
-
-/**
  * igc_read_nvm_eerd - Reads EEPROM using EERD register
  * @hw: pointer to the HW structure
  * @offset: offset of word in the EEPROM to read
diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.h b/drivers/net/ethernet/intel/igc/igc_nvm.h
index f9fc2e9cfb03..ab78d0c64547 100644
--- a/drivers/net/ethernet/intel/igc/igc_nvm.h
+++ b/drivers/net/ethernet/intel/igc/igc_nvm.h
@@ -4,8 +4,6 @@
 #ifndef _IGC_NVM_H_
 #define _IGC_NVM_H_
 
-s32 igc_acquire_nvm(struct igc_hw *hw);
-void igc_release_nvm(struct igc_hw *hw);
 s32 igc_read_mac_addr(struct igc_hw *hw);
 s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data);
 s32 igc_validate_nvm_checksum(struct igc_hw *hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 946edbad4302..f4f5c28615d3 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -257,13 +257,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
-			return -EOPNOTSUPP;
-
 		/* Reject requests failing to enable both edges. */
 		if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -300,10 +293,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
-		/* Reject requests with unsupported flags */
-		if (rq->perout.flags)
-			return -EOPNOTSUPP;
-
 		if (on) {
 			pin = ptp_find_pin(igc->ptp_clock, PTP_PF_PEROUT,
 					   rq->perout.index);
@@ -974,45 +963,62 @@ static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat)
 	}
 }
 
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_trigger() */
+static void igc_ptm_trigger(struct igc_hw *hw)
+{
+	u32 ctrl;
+
+	/* To "manually" start the PTM cycle we need to set the
+	 * trigger (TRIG) bit
+	 */
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl |= IGC_PTM_CTRL_TRIG;
+	wr32(IGC_PTM_CTRL, ctrl);
+	/* Perform flush after write to CTRL register otherwise
+	 * transaction may not start
+	 */
+	wrfl();
+}
+
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_reset() */
+static void igc_ptm_reset(struct igc_hw *hw)
+{
+	u32 ctrl;
+
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl &= ~IGC_PTM_CTRL_TRIG;
+	wr32(IGC_PTM_CTRL, ctrl);
+	/* Write to clear all status */
+	wr32(IGC_PTM_STAT, IGC_PTM_STAT_ALL);
+}
+
 static int igc_phc_get_syncdevicetime(ktime_t *device,
 				      struct system_counterval_t *system,
 				      void *ctx)
 {
-	u32 stat, t2_curr_h, t2_curr_l, ctrl;
 	struct igc_adapter *adapter = ctx;
 	struct igc_hw *hw = &adapter->hw;
+	u32 stat, t2_curr_h, t2_curr_l;
 	int err, count = 100;
 	ktime_t t1, t2_curr;
 
-	/* Get a snapshot of system clocks to use as historic value. */
-	ktime_get_snapshot(&adapter->snapshot);
-
+	/* Doing this in a loop because in the event of a
+	 * badly timed (ha!) system clock adjustment, we may
+	 * get PTM errors from the PCI root, but these errors
+	 * are transitory. Repeating the process returns valid
+	 * data eventually.
+	 */
 	do {
-		/* Doing this in a loop because in the event of a
-		 * badly timed (ha!) system clock adjustment, we may
-		 * get PTM errors from the PCI root, but these errors
-		 * are transitory. Repeating the process returns valid
-		 * data eventually.
-		 */
-
-		/* To "manually" start the PTM cycle we need to clear and
-		 * then set again the TRIG bit.
-		 */
-		ctrl = rd32(IGC_PTM_CTRL);
-		ctrl &= ~IGC_PTM_CTRL_TRIG;
-		wr32(IGC_PTM_CTRL, ctrl);
-		ctrl |= IGC_PTM_CTRL_TRIG;
-		wr32(IGC_PTM_CTRL, ctrl);
+		/* Get a snapshot of system clocks to use as historic value. */
+		ktime_get_snapshot(&adapter->snapshot);
 
-		/* The cycle only starts "for real" when software notifies
-		 * that it has read the registers, this is done by setting
-		 * VALID bit.
-		 */
-		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+		igc_ptm_trigger(hw);
 
 		err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat,
 					 stat, IGC_PTM_STAT_SLEEP,
 					 IGC_PTM_STAT_TIMEOUT);
+		igc_ptm_reset(hw);
+
 		if (err < 0) {
 			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
 			return err;
@@ -1021,15 +1027,7 @@ static int igc_phc_get_syncdevicetime(ktime_t *device,
 		if ((stat & IGC_PTM_STAT_VALID) == IGC_PTM_STAT_VALID)
 			break;
 
-		if (stat & ~IGC_PTM_STAT_VALID) {
-			/* An error occurred, log it. */
-			igc_ptm_log_error(adapter, stat);
-			/* The STAT register is write-1-to-clear (W1C),
-			 * so write the previous error status to clear it.
-			 */
-			wr32(IGC_PTM_STAT, stat);
-			continue;
-		}
+		igc_ptm_log_error(adapter, stat);
 	} while (--count);
 
 	if (!count) {
@@ -1061,9 +1059,16 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 {
 	struct igc_adapter *adapter = container_of(ptp, struct igc_adapter,
 						   ptp_caps);
+	int ret;
+
+	/* This blocks until any in progress PTM transactions complete */
+	mutex_lock(&adapter->ptm_lock);
 
-	return get_device_system_crosststamp(igc_phc_get_syncdevicetime,
-					     adapter, &adapter->snapshot, cts);
+	ret = get_device_system_crosststamp(igc_phc_get_syncdevicetime,
+					    adapter, &adapter->snapshot, cts);
+	mutex_unlock(&adapter->ptm_lock);
+
+	return ret;
 }
 
 static int igc_ptp_getcyclesx64(struct ptp_clock_info *ptp,
@@ -1146,6 +1151,9 @@ void igc_ptp_init(struct igc_adapter *adapter)
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.n_ext_ts = IGC_N_EXTTS;
 		adapter->ptp_caps.n_per_out = IGC_N_PEROUT;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.n_pins = IGC_N_SDP;
 		adapter->ptp_caps.verify = igc_ptp_verify_pin;
 
@@ -1162,6 +1170,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	spin_lock_init(&adapter->ptp_tx_lock);
 	spin_lock_init(&adapter->free_timer_lock);
 	spin_lock_init(&adapter->tmreg_lock);
+	mutex_init(&adapter->ptm_lock);
 
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
@@ -1174,6 +1183,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	if (IS_ERR(adapter->ptp_clock)) {
 		adapter->ptp_clock = NULL;
 		netdev_err(netdev, "ptp_clock_register failed\n");
+		mutex_destroy(&adapter->ptm_lock);
 	} else if (adapter->ptp_clock) {
 		netdev_info(netdev, "PHC added\n");
 		adapter->ptp_flags |= IGC_PTP_ENABLED;
@@ -1203,10 +1213,12 @@ static void igc_ptm_stop(struct igc_adapter *adapter)
 	struct igc_hw *hw = &adapter->hw;
 	u32 ctrl;
 
+	mutex_lock(&adapter->ptm_lock);
 	ctrl = rd32(IGC_PTM_CTRL);
 	ctrl &= ~IGC_PTM_CTRL_EN;
 
 	wr32(IGC_PTM_CTRL, ctrl);
+	mutex_unlock(&adapter->ptm_lock);
 }
 
 /**
@@ -1237,13 +1249,18 @@ void igc_ptp_suspend(struct igc_adapter *adapter)
  **/
 void igc_ptp_stop(struct igc_adapter *adapter)
 {
+	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+		return;
+
 	igc_ptp_suspend(adapter);
 
+	adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		netdev_info(adapter->netdev, "PHC removed\n");
 		adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	}
+	mutex_destroy(&adapter->ptm_lock);
 }
 
 /**
@@ -1255,13 +1272,18 @@ void igc_ptp_stop(struct igc_adapter *adapter)
 void igc_ptp_reset(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
-	u32 cycle_ctrl, ctrl;
+	u32 cycle_ctrl, ctrl, stat;
 	unsigned long flags;
 	u32 timadj;
 
+	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+		return;
+
 	/* reset the tstamp_config */
 	igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
 
+	mutex_lock(&adapter->ptm_lock);
+
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 
 	switch (adapter->hw.mac.type) {
@@ -1290,14 +1312,19 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 		ctrl = IGC_PTM_CTRL_EN |
 			IGC_PTM_CTRL_START_NOW |
 			IGC_PTM_CTRL_SHRT_CYC(IGC_PTM_SHORT_CYC_DEFAULT) |
-			IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT) |
-			IGC_PTM_CTRL_TRIG;
+			IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT);
 
 		wr32(IGC_PTM_CTRL, ctrl);
 
 		/* Force the first cycle to run. */
-		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+		igc_ptm_trigger(hw);
 
+		if (readx_poll_timeout_atomic(rd32, IGC_PTM_STAT, stat,
+					      stat, IGC_PTM_STAT_SLEEP,
+					      IGC_PTM_STAT_TIMEOUT))
+			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
+
+		igc_ptm_reset(hw);
 		break;
 	default:
 		/* No work to do. */
@@ -1314,5 +1341,7 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 out:
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
 
+	mutex_unlock(&adapter->ptm_lock);
+
 	wrfl();
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 12ddc5793651..f343c6bfc6be 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -222,6 +222,22 @@
 
 #define IGC_FTQF(_n)	(0x059E0 + (4 * (_n)))  /* 5-tuple Queue Fltr */
 
+/* Time sync registers - preemption statistics */
+#define IGC_PRMPTDRCNT		0x04284	/* Good RX Preempted Packets */
+#define IGC_PRMEVNTTCNT		0x04298	/* TX Preemption event counter */
+#define IGC_PRMEVNTRCNT		0x0429C	/* RX Preemption event counter */
+
+ /* Preemption Exception Counter */
+ #define IGC_PRMEXCPRCNT				0x42A0
+/* Received out of order packets with SMD-C */
+#define IGC_PRMEXCPRCNT_OOO_SMDC			0x000000FF
+/* Received out of order packets with SMD-C and wrong Frame CNT */
+#define IGC_PRMEXCPRCNT_OOO_FRAME_CNT			0x0000FF00
+/* Received out of order packets with SMD-C and wrong Frag CNT */
+#define IGC_PRMEXCPRCNT_OOO_FRAG_CNT			0x00FF0000
+/* Received packets with SMD-S and wrong Frag CNT and Frame CNT */
+#define IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT		0xFF000000
+
 /* Transmit Scheduling Registers */
 #define IGC_TQAVCTRL		0x3570
 #define IGC_TXQCTL(_n)		(0x3344 + 0x4 * (_n))
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index 1e44374ca1ff..f22cc4d4f459 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -2,9 +2,143 @@
 /* Copyright (c)  2019 Intel Corporation */
 
 #include "igc.h"
+#include "igc_base.h"
 #include "igc_hw.h"
 #include "igc_tsn.h"
 
+#define MIN_MULTPLIER_TX_MIN_FRAG	0
+#define MAX_MULTPLIER_TX_MIN_FRAG	3
+/* Frag size is based on the Section 8.12.2 of the SW User Manual */
+#define TX_MIN_FRAG_SIZE		64
+#define TX_MAX_FRAG_SIZE	(TX_MIN_FRAG_SIZE * \
+				 (MAX_MULTPLIER_TX_MIN_FRAG + 1))
+
+DEFINE_STATIC_KEY_FALSE(igc_fpe_enabled);
+
+static int igc_fpe_init_smd_frame(struct igc_ring *ring,
+				  struct igc_tx_buffer *buffer,
+				  struct sk_buff *skb)
+{
+	dma_addr_t dma = dma_map_single(ring->dev, skb->data, skb->len,
+					DMA_TO_DEVICE);
+
+	if (dma_mapping_error(ring->dev, dma)) {
+		netdev_err_once(ring->netdev, "Failed to map DMA for TX\n");
+		return -ENOMEM;
+	}
+
+	buffer->skb = skb;
+	buffer->protocol = 0;
+	buffer->bytecount = skb->len;
+	buffer->gso_segs = 1;
+	buffer->time_stamp = jiffies;
+	dma_unmap_len_set(buffer, len, skb->len);
+	dma_unmap_addr_set(buffer, dma, dma);
+
+	return 0;
+}
+
+static int igc_fpe_init_tx_descriptor(struct igc_ring *ring,
+				      struct sk_buff *skb,
+				      enum igc_txd_popts_type type)
+{
+	u32 cmd_type, olinfo_status = 0;
+	struct igc_tx_buffer *buffer;
+	union igc_adv_tx_desc *desc;
+	int err;
+
+	if (!igc_desc_unused(ring))
+		return -EBUSY;
+
+	buffer = &ring->tx_buffer_info[ring->next_to_use];
+	err = igc_fpe_init_smd_frame(ring, buffer, skb);
+	if (err)
+		return err;
+
+	cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
+		   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
+		   buffer->bytecount;
+
+	olinfo_status |= FIELD_PREP(IGC_ADVTXD_PAYLEN_MASK, buffer->bytecount);
+
+	switch (type) {
+	case SMD_V:
+	case SMD_R:
+		olinfo_status |= FIELD_PREP(IGC_TXD_POPTS_SMD_MASK, type);
+		break;
+	}
+
+	desc = IGC_TX_DESC(ring, ring->next_to_use);
+	desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+	desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+	desc->read.buffer_addr = cpu_to_le64(dma_unmap_addr(buffer, dma));
+
+	netdev_tx_sent_queue(txring_txq(ring), skb->len);
+
+	buffer->next_to_watch = desc;
+	ring->next_to_use = (ring->next_to_use + 1) % ring->count;
+
+	return 0;
+}
+
+static int igc_fpe_xmit_smd_frame(struct igc_adapter *adapter,
+				  enum igc_txd_popts_type type)
+{
+	int cpu = smp_processor_id();
+	struct netdev_queue *nq;
+	struct igc_ring *ring;
+	struct sk_buff *skb;
+	int err;
+
+	ring = igc_get_tx_ring(adapter, cpu);
+	nq = txring_txq(ring);
+
+	skb = alloc_skb(SMD_FRAME_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put_zero(skb, SMD_FRAME_SIZE);
+
+	__netif_tx_lock(nq, cpu);
+
+	err = igc_fpe_init_tx_descriptor(ring, skb, type);
+	igc_flush_tx_descriptors(ring);
+
+	__netif_tx_unlock(nq);
+
+	return err;
+}
+
+static void igc_fpe_send_mpacket(struct ethtool_mmsv *mmsv,
+				 enum ethtool_mpacket type)
+{
+	struct igc_fpe_t *fpe = container_of(mmsv, struct igc_fpe_t, mmsv);
+	struct igc_adapter *adapter;
+	int err;
+
+	adapter = container_of(fpe, struct igc_adapter, fpe);
+
+	if (type == ETHTOOL_MPACKET_VERIFY) {
+		err = igc_fpe_xmit_smd_frame(adapter, SMD_V);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error sending SMD-V\n");
+	} else if (type == ETHTOOL_MPACKET_RESPONSE) {
+		err = igc_fpe_xmit_smd_frame(adapter, SMD_R);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error sending SMD-R frame\n");
+	}
+}
+
+static const struct ethtool_mmsv_ops igc_mmsv_ops = {
+	.send_mpacket = igc_fpe_send_mpacket,
+};
+
+void igc_fpe_init(struct igc_adapter *adapter)
+{
+	adapter->fpe.tx_min_frag_size = TX_MIN_FRAG_SIZE;
+	ethtool_mmsv_init(&adapter->fpe.mmsv, adapter->netdev, &igc_mmsv_ops);
+}
+
 static bool is_any_launchtime(struct igc_adapter *adapter)
 {
 	int i;
@@ -37,17 +171,16 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
 {
 	unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED;
 
-	if (adapter->taprio_offload_enable)
-		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
 
-	if (is_any_launchtime(adapter))
+	if (adapter->taprio_offload_enable || is_any_launchtime(adapter) ||
+	    adapter->strict_priority_enable)
 		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
 
 	if (is_cbs_enabled(adapter))
 		new_flags |= IGC_FLAG_TSN_QAV_ENABLED;
 
-	if (adapter->strict_priority_enable)
-		new_flags |= IGC_FLAG_TSN_LEGACY_ENABLED;
+	if (adapter->fpe.mmsv.pmac_enabled)
+		new_flags |= IGC_FLAG_TSN_PREEMPT_ENABLED;
 
 	return new_flags;
 }
@@ -125,6 +258,29 @@ static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc)
 	wr32(IGC_TXARB, txarb);
 }
 
+/**
+ * igc_tsn_set_rxpbsize - Set the receive packet buffer size
+ * @adapter: Pointer to the igc_adapter structure
+ * @rxpbs_exp_bmc_be: Value to set the receive packet buffer size, including
+ *                    express buffer, BMC buffer, and Best Effort buffer
+ *
+ * The IGC_RXPBS register value may include allocations for the Express buffer,
+ * BMC buffer, Best Effort buffer, and the timestamp descriptor buffer
+ * (IGC_RXPBS_CFG_TS_EN).
+ */
+static void igc_tsn_set_rxpbsize(struct igc_adapter *adapter,
+				 u32 rxpbs_exp_bmc_be)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 rxpbs = rd32(IGC_RXPBS);
+
+	rxpbs &= ~(IGC_RXPBSIZE_EXP_MASK | IGC_BMC2OSPBSIZE_MASK |
+		   IGC_RXPBSIZE_BE_MASK);
+	rxpbs |= rxpbs_exp_bmc_be;
+
+	wr32(IGC_RXPBS, rxpbs);
+}
+
 /* Returns the TSN specific registers to their default values after
  * the adapter is reset.
  */
@@ -136,15 +292,18 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 	int i;
 
 	wr32(IGC_GTXOFFSET, 0);
-	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+	wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT);
 	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);
 
+	igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_DEFAULT);
+
 	if (igc_is_device_id_i226(hw))
 		igc_tsn_restore_retx_default(adapter);
 
 	tqavctrl = rd32(IGC_TQAVCTRL);
 	tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN |
-		      IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS);
+		      IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS |
+		      IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK);
 
 	wr32(IGC_TQAVCTRL, tqavctrl);
 
@@ -157,16 +316,12 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 	wr32(IGC_QBVCYCLET_S, 0);
 	wr32(IGC_QBVCYCLET, NSEC_PER_SEC);
 
-	/* Reset mqprio TC configuration. */
-	netdev_reset_tc(adapter->netdev);
-
 	/* Restore the default Tx arbitration: Priority 0 has the highest
 	 * priority and is assigned to queue 0 and so on and so forth.
 	 */
 	igc_tsn_tx_arb(adapter, queue_per_tc);
 
 	adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED;
-	adapter->flags &= ~IGC_FLAG_TSN_LEGACY_ENABLED;
 
 	return 0;
 }
@@ -190,53 +345,51 @@ static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter)
 	wr32(IGC_RETX_CTL, retxctl);
 }
 
+static u8 igc_fpe_get_frag_size_mult(const struct igc_fpe_t *fpe)
+{
+	u8 mult = (fpe->tx_min_frag_size / TX_MIN_FRAG_SIZE) - 1;
+
+	return clamp_t(u8, mult, MIN_MULTPLIER_TX_MIN_FRAG,
+		       MAX_MULTPLIER_TX_MIN_FRAG);
+}
+
+u32 igc_fpe_get_supported_frag_size(u32 frag_size)
+{
+	const u32 supported_sizes[] = {64, 128, 192, 256};
+
+	/* Find the smallest supported size that is >= frag_size */
+	for (int i = 0; i < ARRAY_SIZE(supported_sizes); i++) {
+		if (frag_size <= supported_sizes[i])
+			return supported_sizes[i];
+	}
+
+	/* Should not happen */
+	return TX_MAX_FRAG_SIZE;
+}
+
 static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 	u32 tqavctrl, baset_l, baset_h;
 	u32 sec, nsec, cycle;
 	ktime_t base_time, systim;
+	u32 frag_size_mult;
 	int i;
 
 	wr32(IGC_TSAUXC, 0);
 	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN);
 	wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN);
 
+	igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_BE_TSN);
+
 	if (igc_is_device_id_i226(hw))
 		igc_tsn_set_retx_qbvfullthreshold(adapter);
 
 	if (adapter->strict_priority_enable) {
-		int err;
-
-		err = netdev_set_num_tc(adapter->netdev, adapter->num_tc);
-		if (err)
-			return err;
-
-		for (i = 0; i < adapter->num_tc; i++) {
-			err = netdev_set_tc_queue(adapter->netdev, i, 1,
-						  adapter->queue_per_tc[i]);
-			if (err)
-				return err;
-		}
-
-		/* In case the card is configured with less than four queues. */
-		for (; i < IGC_MAX_TX_QUEUES; i++)
-			adapter->queue_per_tc[i] = i;
-
 		/* Configure queue priorities according to the user provided
 		 * mapping.
 		 */
 		igc_tsn_tx_arb(adapter, adapter->queue_per_tc);
-
-		/* Enable legacy TSN mode which will do strict priority without
-		 * any other TSN features.
-		 */
-		tqavctrl = rd32(IGC_TQAVCTRL);
-		tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN;
-		tqavctrl &= ~IGC_TQAVCTRL_ENHANCED_QAV;
-		wr32(IGC_TQAVCTRL, tqavctrl);
-
-		return 0;
 	}
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
@@ -361,10 +514,16 @@ skip_cbs:
 		wr32(IGC_TXQCTL(i), txqctl);
 	}
 
-	tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS;
-
+	tqavctrl = rd32(IGC_TQAVCTRL) & ~(IGC_TQAVCTRL_FUTSCDDIS |
+		   IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK);
 	tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV;
 
+	if (adapter->fpe.mmsv.pmac_enabled)
+		tqavctrl |= IGC_TQAVCTRL_PREEMPT_ENA;
+
+	frag_size_mult = igc_fpe_get_frag_size_mult(&adapter->fpe);
+	tqavctrl |= FIELD_PREP(IGC_TQAVCTRL_MIN_FRAG_MASK, frag_size_mult);
+
 	adapter->qbv_count++;
 
 	cycle = adapter->cycle_time;
@@ -425,6 +584,14 @@ int igc_tsn_reset(struct igc_adapter *adapter)
 	unsigned int new_flags;
 	int err = 0;
 
+	if (adapter->fpe.mmsv.pmac_enabled) {
+		err = igc_enable_empty_addr_recv(adapter);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error adding empty address to MAC filter\n");
+	} else {
+		igc_disable_empty_addr_recv(adapter);
+	}
+
 	new_flags = igc_tsn_new_flags(adapter);
 
 	if (!(new_flags & IGC_FLAG_TSN_ANY_ENABLED))
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h
index 98ec845a86bf..c2a77229207b 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.h
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.h
@@ -4,9 +4,61 @@
 #ifndef _IGC_TSN_H_
 #define _IGC_TSN_H_
 
+#define IGC_RX_MIN_FRAG_SIZE		60
+#define SMD_FRAME_SIZE			60
+
+enum igc_txd_popts_type {
+	SMD_V = 0x01,
+	SMD_R = 0x02,
+};
+
+DECLARE_STATIC_KEY_FALSE(igc_fpe_enabled);
+
+void igc_fpe_init(struct igc_adapter *adapter);
+u32 igc_fpe_get_supported_frag_size(u32 frag_size);
 int igc_tsn_offload_apply(struct igc_adapter *adapter);
 int igc_tsn_reset(struct igc_adapter *adapter);
 void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter);
 bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter);
 
+static inline bool igc_fpe_is_pmac_enabled(struct igc_adapter *adapter)
+{
+	return static_branch_unlikely(&igc_fpe_enabled) &&
+	       adapter->fpe.mmsv.pmac_enabled;
+}
+
+static inline bool igc_fpe_handle_mpacket(struct igc_adapter *adapter,
+					  union igc_adv_rx_desc *rx_desc,
+					  unsigned int size, void *pktbuf)
+{
+	u32 status_error = le32_to_cpu(rx_desc->wb.upper.status_error);
+	int smd;
+
+	smd = FIELD_GET(IGC_RXDADV_STAT_SMD_TYPE_MASK, status_error);
+	if (smd != IGC_RXD_STAT_SMD_TYPE_V && smd != IGC_RXD_STAT_SMD_TYPE_R)
+		return false;
+
+	if (size == SMD_FRAME_SIZE && mem_is_zero(pktbuf, SMD_FRAME_SIZE)) {
+		struct ethtool_mmsv *mmsv = &adapter->fpe.mmsv;
+		enum ethtool_mmsv_event event;
+
+		if (smd == IGC_RXD_STAT_SMD_TYPE_V)
+			event = ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET;
+		else
+			event = ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET;
+
+		ethtool_mmsv_event_handle(mmsv, event);
+	}
+
+	return true;
+}
+
+static inline bool igc_fpe_transmitted_smd_v(union igc_adv_tx_desc *tx_desc)
+{
+	u32 olinfo_status = le32_to_cpu(tx_desc->read.olinfo_status);
+	u8 smd = FIELD_GET(IGC_TXD_POPTS_SMD_MASK, olinfo_status);
+
+	return smd == SMD_V;
+}
+
 #endif /* _IGC_BASE_H */
diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c
index e27af72aada8..9eb47b4beb06 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.c
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.c
@@ -13,6 +13,8 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	struct net_device *dev = adapter->netdev;
 	bool if_running = netif_running(dev);
 	struct bpf_prog *old_prog;
+	bool need_update;
+	unsigned int i;
 
 	if (dev->mtu > ETH_DATA_LEN) {
 		/* For now, the driver doesn't support XDP functionality with
@@ -22,8 +24,14 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 		return -EOPNOTSUPP;
 	}
 
-	if (if_running)
-		igc_close(dev);
+	need_update = !!adapter->xdp_prog != !!prog;
+	if (if_running && need_update) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			igc_disable_rx_ring(adapter->rx_ring[i]);
+			igc_disable_tx_ring(adapter->tx_ring[i]);
+			napi_disable(&adapter->rx_ring[i]->q_vector->napi);
+		}
+	}
 
 	old_prog = xchg(&adapter->xdp_prog, prog);
 	if (old_prog)
@@ -34,8 +42,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	else
 		xdp_features_clear_redirect_target(dev);
 
-	if (if_running)
-		igc_open(dev);
+	if (if_running && need_update) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			napi_enable(&adapter->rx_ring[i]->q_vector->napi);
+			igc_enable_tx_ring(adapter->tx_ring[i]);
+			igc_enable_rx_ring(adapter->rx_ring[i]);
+		}
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile
index 965e5ce1b326..2e7738f41c58 100644
--- a/drivers/net/ethernet/intel/ixgbe/Makefile
+++ b/drivers/net/ethernet/intel/ixgbe/Makefile
@@ -1,15 +1,17 @@
 # SPDX-License-Identifier: GPL-2.0
-# Copyright(c) 1999 - 2018 Intel Corporation.
+# Copyright(c) 1999 - 2024 Intel Corporation.
 #
 # Makefile for the Intel(R) 10GbE PCI Express ethernet driver
 #
 
+subdir-ccflags-y += -I$(src)
 obj-$(CONFIG_IXGBE) += ixgbe.o
 
 ixgbe-y := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
            ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
            ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \
-           ixgbe_xsk.o
+           ixgbe_xsk.o ixgbe_e610.o devlink/devlink.o ixgbe_fw_update.o \
+	   devlink/region.o
 
 ixgbe-$(CONFIG_IXGBE_DCB) +=  ixgbe_dcb.o ixgbe_dcb_82598.o \
                               ixgbe_dcb_82599.o ixgbe_dcb_nl.o
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
new file mode 100644
index 000000000000..54f1b83dfe42
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
@@ -0,0 +1,557 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Intel Corporation. */
+
+#include "ixgbe.h"
+#include "devlink.h"
+#include "ixgbe_fw_update.h"
+
+struct ixgbe_info_ctx {
+	char buf[128];
+	struct ixgbe_orom_info pending_orom;
+	struct ixgbe_nvm_info pending_nvm;
+	struct ixgbe_netlist_info pending_netlist;
+	struct ixgbe_hw_dev_caps dev_caps;
+};
+
+enum ixgbe_devlink_version_type {
+	IXGBE_DL_VERSION_RUNNING,
+	IXGBE_DL_VERSION_STORED
+};
+
+static void ixgbe_info_get_dsn(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx)
+{
+	u8 dsn[8];
+
+	/* Copy the DSN into an array in Big Endian format */
+	put_unaligned_be64(pci_get_dsn(adapter->pdev), dsn);
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%8phD", dsn);
+}
+
+static void ixgbe_info_orom_ver(struct ixgbe_adapter *adapter,
+				struct ixgbe_info_ctx *ctx,
+				enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_nvm_version nvm_ver;
+
+	ctx->buf[0] = '\0';
+
+	if (hw->mac.type == ixgbe_mac_e610) {
+		struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
+
+		if (type == IXGBE_DL_VERSION_STORED &&
+		    ctx->dev_caps.common_cap.nvm_update_pending_orom)
+			orom = &ctx->pending_orom;
+
+		snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u",
+			 orom->major, orom->build, orom->patch);
+		return;
+	}
+
+	ixgbe_get_oem_prod_version(hw, &nvm_ver);
+	if (nvm_ver.oem_valid) {
+		snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x",
+			 nvm_ver.oem_major, nvm_ver.oem_minor,
+			 nvm_ver.oem_release);
+
+		return;
+	}
+
+	ixgbe_get_orom_version(hw, &nvm_ver);
+	if (nvm_ver.or_valid)
+		snprintf(ctx->buf, sizeof(ctx->buf), "%d.%d.%d",
+			 nvm_ver.or_major, nvm_ver.or_build, nvm_ver.or_patch);
+}
+
+static void ixgbe_info_eetrack(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_nvm_version nvm_ver;
+
+	if (hw->mac.type == ixgbe_mac_e610) {
+		u32 eetrack = hw->flash.nvm.eetrack;
+
+		if (type == IXGBE_DL_VERSION_STORED &&
+		    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+			eetrack = ctx->pending_nvm.eetrack;
+
+		snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", eetrack);
+		return;
+	}
+
+	ixgbe_get_oem_prod_version(hw, &nvm_ver);
+
+	/* No ETRACK version for OEM */
+	if (nvm_ver.oem_valid) {
+		ctx->buf[0] = '\0';
+		return;
+	}
+
+	ixgbe_get_etk_id(hw, &nvm_ver);
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", nvm_ver.etk_id);
+}
+
+static void ixgbe_info_fw_api(struct ixgbe_adapter *adapter,
+			      struct ixgbe_info_ctx *ctx)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u",
+		 hw->api_maj_ver, hw->api_min_ver, hw->api_patch);
+}
+
+static void ixgbe_info_fw_build(struct ixgbe_adapter *adapter,
+				struct ixgbe_info_ctx *ctx)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", hw->fw_build);
+}
+
+static void ixgbe_info_fw_srev(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+		nvm = &ctx->pending_nvm;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u", nvm->srev);
+}
+
+static void ixgbe_info_orom_srev(struct ixgbe_adapter *adapter,
+				 struct ixgbe_info_ctx *ctx,
+				 enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_orom)
+		orom = &ctx->pending_orom;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u", orom->srev);
+}
+
+static void ixgbe_info_nvm_ver(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+		nvm = &ctx->pending_nvm;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%x.%02x", nvm->major, nvm->minor);
+}
+
+static void ixgbe_info_netlist_ver(struct ixgbe_adapter *adapter,
+				   struct ixgbe_info_ctx *ctx,
+				   enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_netlist_info *netlist = &adapter->hw.flash.netlist;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_netlist)
+		netlist = &ctx->pending_netlist;
+
+	/* The netlist version fields are BCD formatted */
+	snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x-%x.%x.%x",
+		 netlist->major, netlist->minor,
+		 netlist->type >> 16, netlist->type & 0xFFFF,
+		 netlist->rev, netlist->cust_ver);
+}
+
+static void ixgbe_info_netlist_build(struct ixgbe_adapter *adapter,
+				     struct ixgbe_info_ctx *ctx,
+				     enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_netlist_info *netlist = &adapter->hw.flash.netlist;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_netlist)
+		netlist = &ctx->pending_netlist;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", netlist->hash);
+}
+
+static int ixgbe_set_ctx_dev_caps(struct ixgbe_hw *hw,
+				  struct ixgbe_info_ctx *ctx,
+				  struct netlink_ext_ack *extack)
+{
+	bool *pending_orom, *pending_nvm, *pending_netlist;
+	int err;
+
+	err = ixgbe_discover_dev_caps(hw, &ctx->dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to discover device capabilities");
+		return err;
+	}
+
+	pending_orom = &ctx->dev_caps.common_cap.nvm_update_pending_orom;
+	pending_nvm = &ctx->dev_caps.common_cap.nvm_update_pending_nvm;
+	pending_netlist = &ctx->dev_caps.common_cap.nvm_update_pending_netlist;
+
+	if (*pending_orom) {
+		err = ixgbe_get_inactive_orom_ver(hw, &ctx->pending_orom);
+		if (err)
+			*pending_orom = false;
+	}
+
+	if (*pending_nvm) {
+		err = ixgbe_get_inactive_nvm_ver(hw, &ctx->pending_nvm);
+		if (err)
+			*pending_nvm = false;
+	}
+
+	if (*pending_netlist) {
+		err = ixgbe_get_inactive_netlist_ver(hw, &ctx->pending_netlist);
+		if (err)
+			*pending_netlist = false;
+	}
+
+	return 0;
+}
+
+static int ixgbe_devlink_info_get_e610(struct ixgbe_adapter *adapter,
+				       struct devlink_info_req *req,
+				       struct ixgbe_info_ctx *ctx)
+{
+	int err;
+
+	ixgbe_info_fw_api(adapter, ctx);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_MGMT_API,
+					       ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_build(adapter, ctx);
+	err = devlink_info_version_running_put(req, "fw.mgmt.build", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_srev(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.mgmt.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_orom_srev(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.undi.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_nvm_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.psid.api", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.netlist", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_build(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	return devlink_info_version_running_put(req, "fw.netlist.build",
+						ctx->buf);
+}
+
+static int
+ixgbe_devlink_pending_info_get_e610(struct ixgbe_adapter *adapter,
+				    struct devlink_info_req *req,
+				    struct ixgbe_info_ctx *ctx)
+{
+	int err;
+
+	ixgbe_info_orom_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req,
+					      DEVLINK_INFO_VERSION_GENERIC_FW_UNDI,
+					      ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_eetrack(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req,
+					      DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID,
+					      ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_srev(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.mgmt.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_orom_srev(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.undi.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_nvm_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.psid.api", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.netlist", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_build(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	return devlink_info_version_stored_put(req, "fw.netlist.build",
+					       ctx->buf);
+}
+
+static int ixgbe_devlink_info_get(struct devlink *devlink,
+				  struct devlink_info_req *req,
+				  struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_info_ctx *ctx;
+	int err;
+
+	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	if (hw->mac.type == ixgbe_mac_e610)
+		ixgbe_refresh_fw_version(adapter);
+
+	ixgbe_info_get_dsn(adapter, ctx);
+	err = devlink_info_serial_number_put(req, ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	err = hw->eeprom.ops.read_pba_string(hw, ctx->buf, sizeof(ctx->buf));
+	if (err)
+		goto free_ctx;
+
+	err = devlink_info_version_fixed_put(req,
+					     DEVLINK_INFO_VERSION_GENERIC_BOARD_ID,
+					     ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	ixgbe_info_orom_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_UNDI,
+					       ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	ixgbe_info_eetrack(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID,
+					       ctx->buf);
+	if (err || hw->mac.type != ixgbe_mac_e610)
+		goto free_ctx;
+
+	err = ixgbe_set_ctx_dev_caps(hw, ctx, extack);
+	if (err)
+		goto free_ctx;
+
+	err = ixgbe_devlink_info_get_e610(adapter, req, ctx);
+	if (err)
+		goto free_ctx;
+
+	err = ixgbe_devlink_pending_info_get_e610(adapter, req, ctx);
+free_ctx:
+	kfree(ctx);
+	return err;
+}
+
+/**
+ * ixgbe_devlink_reload_empr_start - Start EMP reset to activate new firmware
+ * @devlink: pointer to the devlink instance to reload
+ * @netns_change: if true, the network namespace is changing
+ * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE
+ * @limit: limits on what reload should do, such as not resetting
+ * @extack: netlink extended ACK structure
+ *
+ * Allow user to activate new Embedded Management Processor firmware by
+ * issuing device specific EMP reset. Called in response to
+ * a DEVLINK_CMD_RELOAD with the DEVLINK_RELOAD_ACTION_FW_ACTIVATE.
+ *
+ * Note that teardown and rebuild of the driver state happens automatically as
+ * part of an interrupt and watchdog task. This is because all physical
+ * functions on the device must be able to reset when an EMP reset occurs from
+ * any source.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_devlink_reload_empr_start(struct devlink *devlink,
+					   bool netns_change,
+					   enum devlink_reload_action action,
+					   enum devlink_reload_limit limit,
+					   struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 pending;
+	int err;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return -EOPNOTSUPP;
+
+	err = ixgbe_get_pending_updates(adapter, &pending, extack);
+	if (err)
+		return err;
+
+	/* Pending is a bitmask of which flash banks have a pending update,
+	 * including the main NVM bank, the Option ROM bank, and the netlist
+	 * bank. If any of these bits are set, then there is a pending update
+	 * waiting to be activated.
+	 */
+	if (!pending) {
+		NL_SET_ERR_MSG_MOD(extack, "No pending firmware update");
+		return -ECANCELED;
+	}
+
+	if (adapter->fw_emp_reset_disabled) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "EMP reset is not available. To activate firmware, a reboot or power cycle is needed");
+		return -ECANCELED;
+	}
+
+	err = ixgbe_aci_nvm_update_empr(hw);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to trigger EMP device reset to reload firmware");
+
+	return err;
+}
+
+/*Wait for 10 sec with 0.5 sec tic. EMPR takes no less than half of a sec */
+#define IXGBE_DEVLINK_RELOAD_TIMEOUT_SEC	20
+
+/**
+ * ixgbe_devlink_reload_empr_finish - finishes EMP reset
+ * @devlink: pointer to the devlink instance
+ * @action: the action to perform.
+ * @limit: limits on what reload should do
+ * @actions_performed: actions performed
+ * @extack: netlink extended ACK structure
+ *
+ * Wait for new NVM to be loaded during EMP reset.
+ *
+ * Return: -ETIME when timer is exceeded, 0 on success.
+ */
+static int ixgbe_devlink_reload_empr_finish(struct devlink *devlink,
+					    enum devlink_reload_action action,
+					    enum devlink_reload_limit limit,
+					    u32 *actions_performed,
+					    struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i = 0;
+	u32 fwsm;
+
+	do {
+		/* Just right away after triggering EMP reset the FWSM register
+		 * may be not cleared yet, so begin the loop with the delay
+		 * in order to not check the not updated register.
+		 */
+		mdelay(500);
+
+		fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
+
+		if (i++ >= IXGBE_DEVLINK_RELOAD_TIMEOUT_SEC)
+			return -ETIME;
+
+	} while (!(fwsm & IXGBE_FWSM_FW_VAL_BIT));
+
+	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE);
+
+	adapter->flags2 &= ~(IXGBE_FLAG2_API_MISMATCH |
+			     IXGBE_FLAG2_FW_ROLLBACK);
+
+	return 0;
+}
+
+static const struct devlink_ops ixgbe_devlink_ops = {
+	.info_get = ixgbe_devlink_info_get,
+	.supported_flash_update_params =
+		DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
+	.flash_update = ixgbe_flash_pldm_image,
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE),
+	.reload_down = ixgbe_devlink_reload_empr_start,
+	.reload_up = ixgbe_devlink_reload_empr_finish,
+};
+
+/**
+ * ixgbe_allocate_devlink - Allocate devlink instance
+ * @dev: device to allocate devlink for
+ *
+ * Allocate a devlink instance for this physical function.
+ *
+ * Return: pointer to the device adapter structure on success,
+ * ERR_PTR(-ENOMEM) when allocation failed.
+ */
+struct ixgbe_adapter *ixgbe_allocate_devlink(struct device *dev)
+{
+	struct ixgbe_adapter *adapter;
+	struct devlink *devlink;
+
+	devlink = devlink_alloc(&ixgbe_devlink_ops, sizeof(*adapter), dev);
+	if (!devlink)
+		return ERR_PTR(-ENOMEM);
+
+	adapter = devlink_priv(devlink);
+	adapter->devlink = devlink;
+
+	return adapter;
+}
+
+/**
+ * ixgbe_devlink_set_switch_id - Set unique switch ID based on PCI DSN
+ * @adapter: pointer to the device adapter structure
+ * @ppid: struct with switch id information
+ */
+static void ixgbe_devlink_set_switch_id(struct ixgbe_adapter *adapter,
+					struct netdev_phys_item_id *ppid)
+{
+	u64 id = pci_get_dsn(adapter->pdev);
+
+	ppid->id_len = sizeof(id);
+	put_unaligned_be64(id, &ppid->id);
+}
+
+/**
+ * ixgbe_devlink_register_port - Register devlink port
+ * @adapter: pointer to the device adapter structure
+ *
+ * Create and register a devlink_port for this physical function.
+ *
+ * Return: 0 on success, error code on failure.
+ */
+int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter)
+{
+	struct devlink_port *devlink_port = &adapter->devlink_port;
+	struct devlink *devlink = adapter->devlink;
+	struct device *dev = &adapter->pdev->dev;
+	struct devlink_port_attrs attrs = {};
+	int err;
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+	attrs.phys.port_number = adapter->hw.bus.func;
+	ixgbe_devlink_set_switch_id(adapter, &attrs.switch_id);
+
+	devlink_port_attrs_set(devlink_port, &attrs);
+
+	err = devl_port_register(devlink, devlink_port, 0);
+	if (err) {
+		dev_err(dev,
+			"devlink port registration failed, err %d\n", err);
+	}
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h
new file mode 100644
index 000000000000..381558058048
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025, Intel Corporation. */
+
+#ifndef _IXGBE_DEVLINK_H_
+#define _IXGBE_DEVLINK_H_
+
+struct ixgbe_adapter *ixgbe_allocate_devlink(struct device *dev);
+int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter);
+void ixgbe_devlink_init_regions(struct ixgbe_adapter *adapter);
+void ixgbe_devlink_destroy_regions(struct ixgbe_adapter *adapter);
+
+#endif /* _IXGBE_DEVLINK_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/region.c b/drivers/net/ethernet/intel/ixgbe/devlink/region.c
new file mode 100644
index 000000000000..76f6571c3c34
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/region.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Intel Corporation. */
+
+#include "ixgbe.h"
+#include "devlink.h"
+
+#define IXGBE_DEVLINK_READ_BLK_SIZE (1024 * 1024)
+
+static const struct devlink_region_ops ixgbe_nvm_region_ops;
+static const struct devlink_region_ops ixgbe_sram_region_ops;
+
+static int ixgbe_devlink_parse_region(struct ixgbe_hw *hw,
+				      const struct devlink_region_ops *ops,
+				      bool *read_shadow_ram, u32 *nvm_size)
+{
+	if (ops == &ixgbe_nvm_region_ops) {
+		*read_shadow_ram = false;
+		*nvm_size = hw->flash.flash_size;
+	} else if (ops == &ixgbe_sram_region_ops) {
+		*read_shadow_ram = true;
+		*nvm_size = hw->flash.sr_words * 2u;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_nvm_snapshot - Capture a snapshot of the NVM content
+ * @devlink: the devlink instance
+ * @ops: the devlink region being snapshotted
+ * @extack: extended ACK response structure
+ * @data: on exit points to snapshot data buffer
+ *
+ * This function is called in response to the DEVLINK_CMD_REGION_NEW cmd.
+ *
+ * Capture a snapshot of the whole requested NVM region.
+ *
+ * No need to worry with freeing @data, devlink core takes care if it.
+ *
+ * Return: 0 on success, -EOPNOTSUPP for unsupported regions, -EBUSY when
+ * cannot lock NVM, -ENOMEM when cannot alloc mem and -EIO when error
+ * occurs during reading.
+ */
+static int ixgbe_devlink_nvm_snapshot(struct devlink *devlink,
+				      const struct devlink_region_ops *ops,
+				      struct netlink_ext_ack *extack, u8 **data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool read_shadow_ram;
+	u8 *nvm_data, *buf;
+	u32 nvm_size, left;
+	u8 num_blks;
+	int err;
+
+	err = ixgbe_devlink_parse_region(hw, ops, &read_shadow_ram, &nvm_size);
+	if (err)
+		return err;
+
+	nvm_data = kvzalloc(nvm_size, GFP_KERNEL);
+	if (!nvm_data)
+		return -ENOMEM;
+
+	num_blks = DIV_ROUND_UP(nvm_size, IXGBE_DEVLINK_READ_BLK_SIZE);
+	buf = nvm_data;
+	left = nvm_size;
+
+	for (int i = 0; i < num_blks; i++) {
+		u32 read_sz = min_t(u32, IXGBE_DEVLINK_READ_BLK_SIZE, left);
+
+		/* Need to acquire NVM lock during each loop run because the
+		 * total period of reading whole NVM is longer than the maximum
+		 * period the lock can be taken defined by the IXGBE_NVM_TIMEOUT.
+		 */
+		err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to acquire NVM semaphore");
+			kvfree(nvm_data);
+			return -EBUSY;
+		}
+
+		err = ixgbe_read_flat_nvm(hw, i * IXGBE_DEVLINK_READ_BLK_SIZE,
+					  &read_sz, buf, read_shadow_ram);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to read RAM content");
+			ixgbe_release_nvm(hw);
+			kvfree(nvm_data);
+			return -EIO;
+		}
+
+		ixgbe_release_nvm(hw);
+
+		buf += read_sz;
+		left -= read_sz;
+	}
+
+	*data = nvm_data;
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_devcaps_snapshot - Capture a snapshot of device capabilities
+ * @devlink: the devlink instance
+ * @ops: the devlink region being snapshotted
+ * @extack: extended ACK response structure
+ * @data: on exit points to snapshot data buffer
+ *
+ * This function is called in response to the DEVLINK_CMD_REGION_NEW for
+ * the device-caps devlink region.
+ *
+ * Capture a snapshot of the device capabilities reported by firmware.
+ *
+ * No need to worry with freeing @data, devlink core takes care if it.
+ *
+ * Return: 0 on success, -ENOMEM when cannot alloc mem, or return code of
+ * the reading operation.
+ */
+static int ixgbe_devlink_devcaps_snapshot(struct devlink *devlink,
+					  const struct devlink_region_ops *ops,
+					  struct netlink_ext_ack *extack,
+					  u8 **data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_aci_cmd_list_caps_elem *caps;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	caps = kvzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!caps)
+		return -ENOMEM;
+
+	err = ixgbe_aci_list_caps(hw, caps, IXGBE_ACI_MAX_BUFFER_SIZE, NULL,
+				  ixgbe_aci_opc_list_dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to read device capabilities");
+		kvfree(caps);
+		return err;
+	}
+
+	*data = (u8 *)caps;
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_nvm_read - Read a portion of NVM flash content
+ * @devlink: the devlink instance
+ * @ops: the devlink region to snapshot
+ * @extack: extended ACK response structure
+ * @offset: the offset to start at
+ * @size: the amount to read
+ * @data: the data buffer to read into
+ *
+ * This function is called in response to DEVLINK_CMD_REGION_READ to directly
+ * read a section of the NVM contents.
+ *
+ * Read from either the nvm-flash region either shadow-ram region.
+ *
+ * Return: 0 on success, -EOPNOTSUPP for unsupported regions, -EBUSY when
+ * cannot lock NVM, -ERANGE when buffer limit exceeded and -EIO when error
+ * occurs during reading.
+ */
+static int ixgbe_devlink_nvm_read(struct devlink *devlink,
+				  const struct devlink_region_ops *ops,
+				  struct netlink_ext_ack *extack,
+				  u64 offset, u32 size, u8 *data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool read_shadow_ram;
+	u32 nvm_size;
+	int err;
+
+	err = ixgbe_devlink_parse_region(hw, ops, &read_shadow_ram, &nvm_size);
+	if (err)
+		return err;
+
+	if (offset + size > nvm_size) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot read beyond the region size");
+		return -ERANGE;
+	}
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
+		return -EBUSY;
+	}
+
+	err = ixgbe_read_flat_nvm(hw, (u32)offset, &size, data, read_shadow_ram);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents");
+		ixgbe_release_nvm(hw);
+		return -EIO;
+	}
+
+	ixgbe_release_nvm(hw);
+	return 0;
+}
+
+static const struct devlink_region_ops ixgbe_nvm_region_ops = {
+	.name = "nvm-flash",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_nvm_snapshot,
+	.read = ixgbe_devlink_nvm_read,
+};
+
+static const struct devlink_region_ops ixgbe_sram_region_ops = {
+	.name = "shadow-ram",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_nvm_snapshot,
+	.read = ixgbe_devlink_nvm_read,
+};
+
+static const struct devlink_region_ops ixgbe_devcaps_region_ops = {
+	.name = "device-caps",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_devcaps_snapshot,
+};
+
+/**
+ * ixgbe_devlink_init_regions - Initialize devlink regions
+ * @adapter: adapter instance
+ *
+ * Create devlink regions used to enable access to dump the contents of the
+ * flash memory of the device.
+ */
+void ixgbe_devlink_init_regions(struct ixgbe_adapter *adapter)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct device *dev = &adapter->pdev->dev;
+	u64 nvm_size, sram_size;
+
+	if (adapter->hw.mac.type != ixgbe_mac_e610)
+		return;
+
+	nvm_size = adapter->hw.flash.flash_size;
+	adapter->nvm_region = devl_region_create(devlink, &ixgbe_nvm_region_ops,
+						 1, nvm_size);
+	if (IS_ERR(adapter->nvm_region)) {
+		dev_err(dev,
+			"Failed to create NVM devlink region, err %ld\n",
+			PTR_ERR(adapter->nvm_region));
+		adapter->nvm_region = NULL;
+	}
+
+	sram_size = adapter->hw.flash.sr_words * 2u;
+	adapter->sram_region = devl_region_create(devlink, &ixgbe_sram_region_ops,
+						  1, sram_size);
+	if (IS_ERR(adapter->sram_region)) {
+		dev_err(dev,
+			"Failed to create shadow-ram devlink region, err %ld\n",
+			PTR_ERR(adapter->sram_region));
+		adapter->sram_region = NULL;
+	}
+
+	adapter->devcaps_region = devl_region_create(devlink,
+						     &ixgbe_devcaps_region_ops,
+						     10, IXGBE_ACI_MAX_BUFFER_SIZE);
+	if (IS_ERR(adapter->devcaps_region)) {
+		dev_err(dev,
+			"Failed to create device-caps devlink region, err %ld\n",
+			PTR_ERR(adapter->devcaps_region));
+		adapter->devcaps_region = NULL;
+	}
+}
+
+/**
+ * ixgbe_devlink_destroy_regions - Destroy devlink regions
+ * @adapter: adapter instance
+ *
+ * Remove previously created regions for this adapter instance.
+ */
+void ixgbe_devlink_destroy_regions(struct ixgbe_adapter *adapter)
+{
+	if (adapter->hw.mac.type != ixgbe_mac_e610)
+		return;
+
+	if (adapter->nvm_region)
+		devl_region_destroy(adapter->nvm_region);
+
+	if (adapter->sram_region)
+		devl_region_destroy(adapter->sram_region);
+
+	if (adapter->devcaps_region)
+		devl_region_destroy(adapter->devcaps_region);
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 559b443c409f..47311b134a7a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef _IXGBE_H_
 #define _IXGBE_H_
@@ -17,9 +17,12 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 
+#include <net/devlink.h>
+
 #include "ixgbe_type.h"
 #include "ixgbe_common.h"
 #include "ixgbe_dcb.h"
+#include "ixgbe_e610.h"
 #if IS_ENABLED(CONFIG_FCOE)
 #define IXGBE_FCOE
 #include "ixgbe_fcoe.h"
@@ -173,6 +176,7 @@ enum ixgbe_tx_flags {
 #define VMDQ_P(p)   ((p) + adapter->ring_feature[RING_F_VMDQ].offset)
 #define IXGBE_82599_VF_DEVICE_ID        0x10ED
 #define IXGBE_X540_VF_DEVICE_ID         0x1515
+#define IXGBE_E610_VF_DEVICE_ID		0x57AD
 
 #define UPDATE_VF_COUNTER_32bit(reg, last_counter, counter)	\
 	{							\
@@ -610,6 +614,11 @@ struct ixgbe_adapter {
 	struct bpf_prog *xdp_prog;
 	struct pci_dev *pdev;
 	struct mii_bus *mii_bus;
+	struct devlink *devlink;
+	struct devlink_port devlink_port;
+	struct devlink_region *nvm_region;
+	struct devlink_region *sram_region;
+	struct devlink_region *devcaps_region;
 
 	unsigned long state;
 
@@ -654,6 +663,7 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP		BIT(9)
 #define IXGBE_FLAG2_PTP_PPS_ENABLED		BIT(10)
 #define IXGBE_FLAG2_PHY_INTERRUPT		BIT(11)
+#define IXGBE_FLAG2_FW_ASYNC_EVENT		BIT(12)
 #define IXGBE_FLAG2_VLAN_PROMISC		BIT(13)
 #define IXGBE_FLAG2_EEE_CAPABLE			BIT(14)
 #define IXGBE_FLAG2_EEE_ENABLED			BIT(15)
@@ -661,6 +671,11 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG2_IPSEC_ENABLED		BIT(17)
 #define IXGBE_FLAG2_VF_IPSEC_ENABLED		BIT(18)
 #define IXGBE_FLAG2_AUTO_DISABLE_VF		BIT(19)
+#define IXGBE_FLAG2_PHY_FW_LOAD_FAILED		BIT(20)
+#define IXGBE_FLAG2_NO_MEDIA			BIT(21)
+#define IXGBE_FLAG2_MOD_POWER_UNSUPPORTED	BIT(22)
+#define IXGBE_FLAG2_API_MISMATCH		BIT(23)
+#define IXGBE_FLAG2_FW_ROLLBACK			BIT(24)
 
 	/* Tx fast path data */
 	int num_tx_queues;
@@ -749,6 +764,8 @@ struct ixgbe_adapter {
 	u32 atr_sample_rate;
 	spinlock_t fdir_perfect_lock;
 
+	bool fw_emp_reset_disabled;
+
 #ifdef IXGBE_FCOE
 	struct ixgbe_fcoe fcoe;
 #endif /* IXGBE_FCOE */
@@ -793,6 +810,7 @@ struct ixgbe_adapter {
 	u32 vferr_refcount;
 	struct ixgbe_mac_addr *mac_table;
 	struct kobject *info_kobj;
+	u16 lse_mask;
 #ifdef CONFIG_IXGBE_HWMON
 	struct hwmon_buff *ixgbe_hwmon_buff;
 #endif /* CONFIG_IXGBE_HWMON */
@@ -823,6 +841,17 @@ struct ixgbe_adapter {
 	spinlock_t vfs_lock;
 };
 
+struct ixgbe_netdevice_priv {
+	struct ixgbe_adapter *adapter;
+};
+
+static inline struct ixgbe_adapter *ixgbe_from_netdev(struct net_device *netdev)
+{
+	struct ixgbe_netdevice_priv *priv = netdev_priv(netdev);
+
+	return priv->adapter;
+}
+
 static inline int ixgbe_determine_xdp_q_idx(int cpu)
 {
 	if (static_key_enabled(&ixgbe_xdp_locking_key))
@@ -849,6 +878,7 @@ static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		return IXGBE_MAX_RSS_INDICES_X550;
 	default:
 		return 0;
@@ -874,6 +904,7 @@ enum ixgbe_state_t {
 	__IXGBE_PTP_RUNNING,
 	__IXGBE_PTP_TX_IN_PROGRESS,
 	__IXGBE_RESET_REQUESTED,
+	__IXGBE_PHY_INIT_COMPLETE,
 };
 
 struct ixgbe_cb {
@@ -896,6 +927,7 @@ enum ixgbe_boards {
 	board_x550em_x_fw,
 	board_x550em_a,
 	board_x550em_a_fw,
+	board_e610,
 };
 
 extern const struct ixgbe_info ixgbe_82598_info;
@@ -906,6 +938,7 @@ extern const struct ixgbe_info ixgbe_X550EM_x_info;
 extern const struct ixgbe_info ixgbe_x550em_x_fw_info;
 extern const struct ixgbe_info ixgbe_x550em_a_info;
 extern const struct ixgbe_info ixgbe_x550em_a_fw_info;
+extern const struct ixgbe_info ixgbe_e610_info;
 #ifdef CONFIG_IXGBE_DCB
 extern const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops;
 #endif
@@ -934,6 +967,8 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter);
 int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter);
 bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
 			 u16 subdevice_id);
+void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter);
+void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter);
 #ifdef CONFIG_PCI_IOV
 void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter);
 #endif
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index 4aaaea3b5f8f..444da982593f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -1169,6 +1169,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_82598 = {
 	.calc_checksum          = &ixgbe_calc_eeprom_checksum_generic,
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_generic,
 	.update_checksum	= &ixgbe_update_eeprom_checksum_generic,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_82598 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index cdaf087b4e85..d5b1b974b4a3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -1615,6 +1615,7 @@ int ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		IXGBE_WRITE_REG(hw, IXGBE_FDIRSCTPM, ~fdirtcpm);
 		break;
 	default:
@@ -2229,6 +2230,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_82599 = {
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_generic,
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_generic,
 	.update_checksum	= &ixgbe_update_eeprom_checksum_generic,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_82599 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 3be1bfb16498..5784d5d1896e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -58,6 +58,7 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw)
 		switch (hw->device_id) {
 		case IXGBE_DEV_ID_X550EM_A_SFP:
 		case IXGBE_DEV_ID_X550EM_A_SFP_N:
+		case IXGBE_DEV_ID_E610_SFP:
 			supported = false;
 			break;
 		default:
@@ -88,6 +89,8 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw)
 		case IXGBE_DEV_ID_X550EM_A_10G_T:
 		case IXGBE_DEV_ID_X550EM_A_1G_T:
 		case IXGBE_DEV_ID_X550EM_A_1G_T_L:
+		case IXGBE_DEV_ID_E610_10G_T:
+		case IXGBE_DEV_ID_E610_2_5G_T:
 			supported = true;
 			break;
 		default:
@@ -329,6 +332,7 @@ int ixgbe_start_hw_generic(struct ixgbe_hw *hw)
  * Devices in the second generation:
  *     82599
  *     X540
+ *     E610
  **/
 int ixgbe_start_hw_gen2(struct ixgbe_hw *hw)
 {
@@ -469,9 +473,14 @@ int ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw)
 		}
 	}
 
-	if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) {
+	if (hw->mac.type == ixgbe_mac_X550 ||
+	    hw->mac.type == ixgbe_mac_X540 ||
+	    hw->mac.type == ixgbe_mac_e610) {
 		if (hw->phy.id == 0)
 			hw->phy.ops.identify(hw);
+	}
+
+	if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) {
 		hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECL, MDIO_MMD_PCS, &i);
 		hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECH, MDIO_MMD_PCS, &i);
 		hw->phy.ops.read_reg(hw, IXGBE_LDPCECL, MDIO_MMD_PCS, &i);
@@ -660,7 +669,11 @@ int ixgbe_get_bus_info_generic(struct ixgbe_hw *hw)
 	hw->bus.type = ixgbe_bus_type_pci_express;
 
 	/* Get the negotiated link width and speed from PCI config space */
-	link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS);
+	if (hw->mac.type == ixgbe_mac_e610)
+		link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS_E610);
+	else
+		link_status = ixgbe_read_pci_cfg_word(hw,
+						      IXGBE_PCI_LINK_STATUS);
 
 	hw->bus.width = ixgbe_convert_bus_width(link_status);
 	hw->bus.speed = ixgbe_convert_bus_speed(link_status);
@@ -2918,6 +2931,10 @@ u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw)
 		pcie_offset = IXGBE_PCIE_MSIX_82599_CAPS;
 		max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599;
 		break;
+	case ixgbe_mac_e610:
+		pcie_offset = IXGBE_PCIE_MSIX_E610_CAPS;
+		max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599;
+		break;
 	default:
 		return 1;
 	}
@@ -3366,7 +3383,8 @@ int ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
 		*speed = IXGBE_LINK_SPEED_1GB_FULL;
 		break;
 	case IXGBE_LINKS_SPEED_100_82599:
-		if ((hw->mac.type >= ixgbe_mac_X550) &&
+		if ((hw->mac.type >= ixgbe_mac_X550 ||
+		     hw->mac.type == ixgbe_mac_e610) &&
 		    (links_reg & IXGBE_LINKS_SPEED_NON_STD))
 			*speed = IXGBE_LINK_SPEED_5GB_FULL;
 		else
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
index 6493abf189de..6639069ad528 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
@@ -194,6 +194,8 @@ u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg);
 	dev_err(&adapter->pdev->dev, format, ## arg)
 #define e_dev_notice(format, arg...) \
 	dev_notice(&adapter->pdev->dev, format, ## arg)
+#define e_dbg(msglvl, format, arg...) \
+	netif_dbg(adapter, msglvl, adapter->netdev, format, ## arg)
 #define e_info(msglvl, format, arg...) \
 	netif_info(adapter, msglvl, adapter->netdev, format, ## arg)
 #define e_err(msglvl, format, arg...) \
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index f2709b10c2e5..3dd5a16a14df 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include "ixgbe.h"
 #include <linux/dcbnl.h>
@@ -118,14 +118,14 @@ static int ixgbe_copy_dcb_cfg(struct ixgbe_adapter *adapter, int tc_max)
 
 static u8 ixgbe_dcbnl_get_state(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return !!(adapter->flags & IXGBE_FLAG_DCB_ENABLED);
 }
 
 static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* Fail command if not in CEE mode */
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
@@ -142,7 +142,7 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
 static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev,
 					 u8 *perm_addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i, j;
 
 	memset(perm_addr, 0xff, MAX_ADDR_LEN);
@@ -154,6 +154,7 @@ static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev,
 	case ixgbe_mac_82599EB:
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		for (j = 0; j < netdev->addr_len; j++, i++)
 			perm_addr[i] = adapter->hw.mac.san_addr[j];
 		break;
@@ -166,7 +167,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 					 u8 prio, u8 bwg_id, u8 bw_pct,
 					 u8 up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (prio != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type = prio;
@@ -183,7 +184,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 					  u8 bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] = bw_pct;
 }
@@ -192,7 +193,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 					 u8 prio, u8 bwg_id, u8 bw_pct,
 					 u8 up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (prio != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type = prio;
@@ -209,7 +210,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 					  u8 bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] = bw_pct;
 }
@@ -218,7 +219,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 					 u8 *prio, u8 *bwg_id, u8 *bw_pct,
 					 u8 *up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*prio = adapter->dcb_cfg.tc_config[tc].path[0].prio_type;
 	*bwg_id = adapter->dcb_cfg.tc_config[tc].path[0].bwg_id;
@@ -229,7 +230,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 					  u8 *bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*bw_pct = adapter->dcb_cfg.bw_percentage[0][bwg_id];
 }
@@ -238,7 +239,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 					 u8 *prio, u8 *bwg_id, u8 *bw_pct,
 					 u8 *up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*prio = adapter->dcb_cfg.tc_config[tc].path[1].prio_type;
 	*bwg_id = adapter->dcb_cfg.tc_config[tc].path[1].bwg_id;
@@ -249,7 +250,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 					  u8 *bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*bw_pct = adapter->dcb_cfg.bw_percentage[1][bwg_id];
 }
@@ -257,7 +258,7 @@ static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 				    u8 setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc = setting;
 	if (adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc !=
@@ -268,14 +269,14 @@ static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
 				    u8 *setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*setting = adapter->dcb_cfg.tc_config[priority].dcb_pfc;
 }
 
 static void ixgbe_dcbnl_devreset(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
@@ -294,7 +295,7 @@ static void ixgbe_dcbnl_devreset(struct net_device *dev)
 
 static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg;
 	struct ixgbe_hw *hw = &adapter->hw;
 	int ret = DCB_NO_HW_CHG;
@@ -382,7 +383,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 
 static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	switch (capid) {
 	case DCB_CAP_ATTR_PG:
@@ -419,7 +420,7 @@ static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap)
 
 static int ixgbe_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
 		switch (tcid) {
@@ -446,14 +447,14 @@ static int ixgbe_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num)
 
 static u8 ixgbe_dcbnl_getpfcstate(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return adapter->dcb_cfg.pfc_mode_enable;
 }
 
 static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.pfc_mode_enable = state;
 }
@@ -470,7 +471,7 @@ static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
  */
 static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct dcb_app app = {
 				.selector = idtype,
 				.protocol = id,
@@ -485,7 +486,7 @@ static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
 static int ixgbe_dcbnl_ieee_getets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets;
 
 	ets->ets_cap = adapter->dcb_cfg.num_tcs.pg_tcs;
@@ -505,7 +506,7 @@ static int ixgbe_dcbnl_ieee_getets(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	int i, err;
 	__u8 max_tc = 0;
@@ -558,7 +559,7 @@ static int ixgbe_dcbnl_ieee_setets(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc;
 	int i;
 
@@ -583,7 +584,7 @@ static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u8 *prio_tc;
 	int err;
@@ -615,7 +616,7 @@ static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev,
 				   struct dcb_app *app)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int err;
 
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
@@ -660,7 +661,7 @@ static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev,
 				   struct dcb_app *app)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int err;
 
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
@@ -704,13 +705,13 @@ static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev,
 
 static u8 ixgbe_dcbnl_getdcbx(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	return adapter->dcbx_cap;
 }
 
 static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_ets ets = {0};
 	struct ieee_pfc pfc = {0};
 	int err = 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
new file mode 100644
index 000000000000..71ea25de1bac
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -0,0 +1,3995 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024 Intel Corporation. */
+
+#include "ixgbe_common.h"
+#include "ixgbe_e610.h"
+#include "ixgbe_x550.h"
+#include "ixgbe_type.h"
+#include "ixgbe_x540.h"
+#include "ixgbe_mbx.h"
+#include "ixgbe_phy.h"
+
+/**
+ * ixgbe_should_retry_aci_send_cmd_execute - decide if ACI command should
+ * be resent
+ * @opcode: ACI opcode
+ *
+ * Check if ACI command should be sent again depending on the provided opcode.
+ * It may happen when CSR is busy during link state changes.
+ *
+ * Return: true if the sending command routine should be repeated,
+ * otherwise false.
+ */
+static bool ixgbe_should_retry_aci_send_cmd_execute(u16 opcode)
+{
+	switch (opcode) {
+	case ixgbe_aci_opc_disable_rxen:
+	case ixgbe_aci_opc_get_phy_caps:
+	case ixgbe_aci_opc_get_link_status:
+	case ixgbe_aci_opc_get_link_topo:
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * ixgbe_aci_send_cmd_execute - execute sending FW Admin Command to FW Admin
+ * Command Interface
+ * @hw: pointer to the HW struct
+ * @desc: descriptor describing the command
+ * @buf: buffer to use for indirect commands (NULL for direct commands)
+ * @buf_size: size of buffer for indirect commands (0 for direct commands)
+ *
+ * Admin Command is sent using CSR by setting descriptor and buffer in specific
+ * registers.
+ *
+ * Return: the exit code of the operation.
+ * * - 0 - success.
+ * * - -EIO - CSR mechanism is not enabled.
+ * * - -EBUSY - CSR mechanism is busy.
+ * * - -EINVAL - buf_size is too big or
+ * invalid argument buf or buf_size.
+ * * - -ETIME - Admin Command X command timeout.
+ * * - -EIO - Admin Command X invalid state of HICR register or
+ * Admin Command failed because of bad opcode was returned or
+ * Admin Command failed with error Y.
+ */
+static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
+				      struct ixgbe_aci_desc *desc,
+				      void *buf, u16 buf_size)
+{
+	u16 opcode, buf_tail_size = buf_size % 4;
+	u32 *raw_desc = (u32 *)desc;
+	u32 hicr, i, buf_tail = 0;
+	bool valid_buf = false;
+
+	hw->aci.last_status = IXGBE_ACI_RC_OK;
+
+	/* It's necessary to check if mechanism is enabled */
+	hicr = IXGBE_READ_REG(hw, IXGBE_PF_HICR);
+
+	if (!(hicr & IXGBE_PF_HICR_EN))
+		return -EIO;
+
+	if (hicr & IXGBE_PF_HICR_C) {
+		hw->aci.last_status = IXGBE_ACI_RC_EBUSY;
+		return -EBUSY;
+	}
+
+	opcode = le16_to_cpu(desc->opcode);
+
+	if (buf_size > IXGBE_ACI_MAX_BUFFER_SIZE)
+		return -EINVAL;
+
+	if (buf)
+		desc->flags |= cpu_to_le16(IXGBE_ACI_FLAG_BUF);
+
+	if (desc->flags & cpu_to_le16(IXGBE_ACI_FLAG_BUF)) {
+		if ((buf && !buf_size) ||
+		    (!buf && buf_size))
+			return -EINVAL;
+		if (buf && buf_size)
+			valid_buf = true;
+	}
+
+	if (valid_buf) {
+		if (buf_tail_size)
+			memcpy(&buf_tail, buf + buf_size - buf_tail_size,
+			       buf_tail_size);
+
+		if (((buf_size + 3) & ~0x3) > IXGBE_ACI_LG_BUF)
+			desc->flags |= cpu_to_le16(IXGBE_ACI_FLAG_LB);
+
+		desc->datalen = cpu_to_le16(buf_size);
+
+		if (desc->flags & cpu_to_le16(IXGBE_ACI_FLAG_RD)) {
+			for (i = 0; i < buf_size / 4; i++)
+				IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), ((u32 *)buf)[i]);
+			if (buf_tail_size)
+				IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), buf_tail);
+		}
+	}
+
+	/* Descriptor is written to specific registers */
+	for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++)
+		IXGBE_WRITE_REG(hw, IXGBE_PF_HIDA(i), raw_desc[i]);
+
+	/* SW has to set PF_HICR.C bit and clear PF_HICR.SV and
+	 * PF_HICR_EV
+	 */
+	hicr = (IXGBE_READ_REG(hw, IXGBE_PF_HICR) | IXGBE_PF_HICR_C) &
+	       ~(IXGBE_PF_HICR_SV | IXGBE_PF_HICR_EV);
+	IXGBE_WRITE_REG(hw, IXGBE_PF_HICR, hicr);
+
+#define MAX_SLEEP_RESP_US 1000
+#define MAX_TMOUT_RESP_SYNC_US 100000000
+
+	/* Wait for sync Admin Command response */
+	read_poll_timeout(IXGBE_READ_REG, hicr,
+			  (hicr & IXGBE_PF_HICR_SV) ||
+			  !(hicr & IXGBE_PF_HICR_C),
+			  MAX_SLEEP_RESP_US, MAX_TMOUT_RESP_SYNC_US, true, hw,
+			  IXGBE_PF_HICR);
+
+#define MAX_TMOUT_RESP_ASYNC_US 150000000
+
+	/* Wait for async Admin Command response */
+	read_poll_timeout(IXGBE_READ_REG, hicr,
+			  (hicr & IXGBE_PF_HICR_EV) ||
+			  !(hicr & IXGBE_PF_HICR_C),
+			  MAX_SLEEP_RESP_US, MAX_TMOUT_RESP_ASYNC_US, true, hw,
+			  IXGBE_PF_HICR);
+
+	/* Read sync Admin Command response */
+	if ((hicr & IXGBE_PF_HICR_SV)) {
+		for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) {
+			raw_desc[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIDA(i));
+			raw_desc[i] = raw_desc[i];
+		}
+	}
+
+	/* Read async Admin Command response */
+	if ((hicr & IXGBE_PF_HICR_EV) && !(hicr & IXGBE_PF_HICR_C)) {
+		for (i = 0; i < IXGBE_ACI_DESC_SIZE_IN_DWORDS; i++) {
+			raw_desc[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIDA_2(i));
+			raw_desc[i] = raw_desc[i];
+		}
+	}
+
+	/* Handle timeout and invalid state of HICR register */
+	if (hicr & IXGBE_PF_HICR_C)
+		return -ETIME;
+
+	if (!(hicr & IXGBE_PF_HICR_SV) && !(hicr & IXGBE_PF_HICR_EV))
+		return -EIO;
+
+	/* For every command other than 0x0014 treat opcode mismatch
+	 * as an error. Response to 0x0014 command read from HIDA_2
+	 * is a descriptor of an event which is expected to contain
+	 * different opcode than the command.
+	 */
+	if (desc->opcode != cpu_to_le16(opcode) &&
+	    opcode != ixgbe_aci_opc_get_fw_event)
+		return -EIO;
+
+	if (desc->retval) {
+		hw->aci.last_status = (enum ixgbe_aci_err)
+			le16_to_cpu(desc->retval);
+		return -EIO;
+	}
+
+	/* Write a response values to a buf */
+	if (valid_buf) {
+		for (i = 0; i < buf_size / 4; i++)
+			((u32 *)buf)[i] = IXGBE_READ_REG(hw, IXGBE_PF_HIBA(i));
+		if (buf_tail_size) {
+			buf_tail = IXGBE_READ_REG(hw, IXGBE_PF_HIBA(i));
+			memcpy(buf + buf_size - buf_tail_size, &buf_tail,
+			       buf_tail_size);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_send_cmd - send FW Admin Command to FW Admin Command Interface
+ * @hw: pointer to the HW struct
+ * @desc: descriptor describing the command
+ * @buf: buffer to use for indirect commands (NULL for direct commands)
+ * @buf_size: size of buffer for indirect commands (0 for direct commands)
+ *
+ * Helper function to send FW Admin Commands to the FW Admin Command Interface.
+ *
+ * Retry sending the FW Admin Command multiple times to the FW ACI
+ * if the EBUSY Admin Command error is returned.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc,
+		       void *buf, u16 buf_size)
+{
+	u16 opcode = le16_to_cpu(desc->opcode);
+	struct ixgbe_aci_desc desc_cpy;
+	enum ixgbe_aci_err last_status;
+	u8 idx = 0, *buf_cpy = NULL;
+	bool is_cmd_for_retry;
+	unsigned long timeout;
+	int err;
+
+	is_cmd_for_retry = ixgbe_should_retry_aci_send_cmd_execute(opcode);
+	if (is_cmd_for_retry) {
+		if (buf) {
+			buf_cpy = kmalloc(buf_size, GFP_KERNEL);
+			if (!buf_cpy)
+				return -ENOMEM;
+			*buf_cpy = *(u8 *)buf;
+		}
+		desc_cpy = *desc;
+	}
+
+	timeout = jiffies + msecs_to_jiffies(IXGBE_ACI_SEND_TIMEOUT_MS);
+	do {
+		mutex_lock(&hw->aci.lock);
+		err = ixgbe_aci_send_cmd_execute(hw, desc, buf, buf_size);
+		last_status = hw->aci.last_status;
+		mutex_unlock(&hw->aci.lock);
+
+		if (!is_cmd_for_retry || !err ||
+		    last_status != IXGBE_ACI_RC_EBUSY)
+			break;
+
+		if (buf)
+			memcpy(buf, buf_cpy, buf_size);
+		*desc = desc_cpy;
+
+		msleep(IXGBE_ACI_SEND_DELAY_TIME_MS);
+	} while (++idx < IXGBE_ACI_SEND_MAX_EXECUTE &&
+		 time_before(jiffies, timeout));
+
+	kfree(buf_cpy);
+
+	return err;
+}
+
+/**
+ * ixgbe_aci_check_event_pending - check if there are any pending events
+ * @hw: pointer to the HW struct
+ *
+ * Determine if there are any pending events.
+ *
+ * Return: true if there are any currently pending events
+ * otherwise false.
+ */
+bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw)
+{
+	u32 ep_bit_mask = hw->bus.func ? GL_FWSTS_EP_PF1 : GL_FWSTS_EP_PF0;
+	u32 fwsts = IXGBE_READ_REG(hw, GL_FWSTS);
+
+	return (fwsts & ep_bit_mask) ? true : false;
+}
+
+/**
+ * ixgbe_aci_get_event - get an event from ACI
+ * @hw: pointer to the HW struct
+ * @e: event information structure
+ * @pending: optional flag signaling that there are more pending events
+ *
+ * Obtain an event from ACI and return its content
+ * through 'e' using ACI command (0x0014).
+ * Provide information if there are more events
+ * to retrieve through 'pending'.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e,
+			bool *pending)
+{
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	if (!e || (!e->msg_buf && e->buf_len))
+		return -EINVAL;
+
+	mutex_lock(&hw->aci.lock);
+
+	/* Check if there are any events pending */
+	if (!ixgbe_aci_check_event_pending(hw)) {
+		err = -ENOENT;
+		goto aci_get_event_exit;
+	}
+
+	/* Obtain pending event */
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_fw_event);
+	err = ixgbe_aci_send_cmd_execute(hw, &desc, e->msg_buf, e->buf_len);
+	if (err)
+		goto aci_get_event_exit;
+
+	/* Returned 0x0014 opcode indicates that no event was obtained */
+	if (desc.opcode == cpu_to_le16(ixgbe_aci_opc_get_fw_event)) {
+		err = -ENOENT;
+		goto aci_get_event_exit;
+	}
+
+	/* Determine size of event data */
+	e->msg_len = min_t(u16, le16_to_cpu(desc.datalen), e->buf_len);
+	/* Write event descriptor to event info structure */
+	memcpy(&e->desc, &desc, sizeof(e->desc));
+
+	/* Check if there are any further events pending */
+	if (pending)
+		*pending = ixgbe_aci_check_event_pending(hw);
+
+aci_get_event_exit:
+	mutex_unlock(&hw->aci.lock);
+
+	return err;
+}
+
+/**
+ * ixgbe_fill_dflt_direct_cmd_desc - fill ACI descriptor with default values.
+ * @desc: pointer to the temp descriptor (non DMA mem)
+ * @opcode: the opcode can be used to decide which flags to turn off or on
+ *
+ * Helper function to fill the descriptor desc with default values
+ * and the provided opcode.
+ */
+void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode)
+{
+	/* Zero out the desc. */
+	memset(desc, 0, sizeof(*desc));
+	desc->opcode = cpu_to_le16(opcode);
+	desc->flags = cpu_to_le16(IXGBE_ACI_FLAG_SI);
+}
+
+/**
+ * ixgbe_aci_get_fw_ver - Get the firmware version
+ * @hw: pointer to the HW struct
+ *
+ * Get the firmware version using ACI command (0x0001).
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_aci_get_fw_ver(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_ver *resp;
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	resp = &desc.params.get_ver;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_ver);
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+	if (!err) {
+		hw->fw_branch = resp->fw_branch;
+		hw->fw_maj_ver = resp->fw_major;
+		hw->fw_min_ver = resp->fw_minor;
+		hw->fw_patch = resp->fw_patch;
+		hw->fw_build = le32_to_cpu(resp->fw_build);
+		hw->api_branch = resp->api_branch;
+		hw->api_maj_ver = resp->api_major;
+		hw->api_min_ver = resp->api_minor;
+		hw->api_patch = resp->api_patch;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_aci_req_res - request a common resource
+ * @hw: pointer to the HW struct
+ * @res: resource ID
+ * @access: access type
+ * @sdp_number: resource number
+ * @timeout: the maximum time in ms that the driver may hold the resource
+ *
+ * Requests a common resource using the ACI command (0x0008).
+ * Specifies the maximum time the driver may hold the resource.
+ * If the requested resource is currently occupied by some other driver,
+ * a busy return value is returned and the timeout field value indicates the
+ * maximum time the current owner has to free it.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_aci_req_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
+			     enum ixgbe_aci_res_access_type access,
+			     u8 sdp_number, u32 *timeout)
+{
+	struct ixgbe_aci_cmd_req_res *cmd_resp;
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	cmd_resp = &desc.params.res_owner;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_req_res);
+
+	cmd_resp->res_id = cpu_to_le16(res);
+	cmd_resp->access_type = cpu_to_le16(access);
+	cmd_resp->res_number = cpu_to_le32(sdp_number);
+	cmd_resp->timeout = cpu_to_le32(*timeout);
+	*timeout = 0;
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+
+	/* If the resource is held by some other driver, the command completes
+	 * with a busy return value and the timeout field indicates the maximum
+	 * time the current owner of the resource has to free it.
+	 */
+	if (!err || hw->aci.last_status == IXGBE_ACI_RC_EBUSY)
+		*timeout = le32_to_cpu(cmd_resp->timeout);
+
+	return err;
+}
+
+/**
+ * ixgbe_aci_release_res - release a common resource using ACI
+ * @hw: pointer to the HW struct
+ * @res: resource ID
+ * @sdp_number: resource number
+ *
+ * Release a common resource using ACI command (0x0009).
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_aci_release_res(struct ixgbe_hw *hw,
+				 enum ixgbe_aci_res_ids res, u8 sdp_number)
+{
+	struct ixgbe_aci_cmd_req_res *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.res_owner;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_release_res);
+
+	cmd->res_id = cpu_to_le16(res);
+	cmd->res_number = cpu_to_le32(sdp_number);
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_acquire_res - acquire the ownership of a resource
+ * @hw: pointer to the HW structure
+ * @res: resource ID
+ * @access: access type (read or write)
+ * @timeout: timeout in milliseconds
+ *
+ * Make an attempt to acquire the ownership of a resource using
+ * the ixgbe_aci_req_res to utilize ACI.
+ * In case if some other driver has previously acquired the resource and
+ * performed any necessary updates, the -EALREADY is returned,
+ * and the caller does not obtain the resource and has no further work to do.
+ * If needed, the function will poll until the current lock owner timeouts.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
+		      enum ixgbe_aci_res_access_type access, u32 timeout)
+{
+#define IXGBE_RES_POLLING_DELAY_MS	10
+	u32 delay = IXGBE_RES_POLLING_DELAY_MS;
+	u32 res_timeout = timeout;
+	u32 retry_timeout;
+	int err;
+
+	err = ixgbe_aci_req_res(hw, res, access, 0, &res_timeout);
+
+	/* A return code of -EALREADY means that another driver has
+	 * previously acquired the resource and performed any necessary updates;
+	 * in this case the caller does not obtain the resource and has no
+	 * further work to do.
+	 */
+	if (err == -EALREADY)
+		return err;
+
+	/* If necessary, poll until the current lock owner timeouts.
+	 * Set retry_timeout to the timeout value reported by the FW in the
+	 * response to the "Request Resource Ownership" (0x0008) Admin Command
+	 * as it indicates the maximum time the current owner of the resource
+	 * is allowed to hold it.
+	 */
+	retry_timeout = res_timeout;
+	while (err && retry_timeout && res_timeout) {
+		msleep(delay);
+		retry_timeout = (retry_timeout > delay) ?
+			retry_timeout - delay : 0;
+		err = ixgbe_aci_req_res(hw, res, access, 0, &res_timeout);
+
+		/* Success - lock acquired.
+		 * -EALREADY - lock free, no work to do.
+		 */
+		if (!err || err == -EALREADY)
+			break;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_release_res - release a common resource
+ * @hw: pointer to the HW structure
+ * @res: resource ID
+ *
+ * Release a common resource using ixgbe_aci_release_res.
+ */
+void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res)
+{
+	u32 total_delay = 0;
+	int err;
+
+	err = ixgbe_aci_release_res(hw, res, 0);
+
+	/* There are some rare cases when trying to release the resource
+	 * results in an admin command timeout, so handle them correctly.
+	 */
+	while (err == -ETIME &&
+	       total_delay < IXGBE_ACI_RELEASE_RES_TIMEOUT) {
+		usleep_range(1000, 1500);
+		err = ixgbe_aci_release_res(hw, res, 0);
+		total_delay++;
+	}
+}
+
+/**
+ * ixgbe_parse_e610_caps - Parse common device/function capabilities
+ * @hw: pointer to the HW struct
+ * @caps: pointer to common capabilities structure
+ * @elem: the capability element to parse
+ * @prefix: message prefix for tracing capabilities
+ *
+ * Given a capability element, extract relevant details into the common
+ * capability structure.
+ *
+ * Return: true if the capability matches one of the common capability ids,
+ * false otherwise.
+ */
+static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw,
+				  struct ixgbe_hw_caps *caps,
+				  struct ixgbe_aci_cmd_list_caps_elem *elem,
+				  const char *prefix)
+{
+	u32 logical_id = le32_to_cpu(elem->logical_id);
+	u32 phys_id = le32_to_cpu(elem->phys_id);
+	u32 number = le32_to_cpu(elem->number);
+	u16 cap = le16_to_cpu(elem->cap);
+
+	switch (cap) {
+	case IXGBE_ACI_CAPS_VALID_FUNCTIONS:
+		caps->valid_functions = number;
+		break;
+	case IXGBE_ACI_CAPS_SRIOV:
+		caps->sr_iov_1_1 = (number == 1);
+		break;
+	case IXGBE_ACI_CAPS_VMDQ:
+		caps->vmdq = (number == 1);
+		break;
+	case IXGBE_ACI_CAPS_DCB:
+		caps->dcb = (number == 1);
+		caps->active_tc_bitmap = logical_id;
+		caps->maxtc = phys_id;
+		break;
+	case IXGBE_ACI_CAPS_RSS:
+		caps->rss_table_size = number;
+		caps->rss_table_entry_width = logical_id;
+		break;
+	case IXGBE_ACI_CAPS_RXQS:
+		caps->num_rxq = number;
+		caps->rxq_first_id = phys_id;
+		break;
+	case IXGBE_ACI_CAPS_TXQS:
+		caps->num_txq = number;
+		caps->txq_first_id = phys_id;
+		break;
+	case IXGBE_ACI_CAPS_MSIX:
+		caps->num_msix_vectors = number;
+		caps->msix_vector_first_id = phys_id;
+		break;
+	case IXGBE_ACI_CAPS_NVM_VER:
+		break;
+	case IXGBE_ACI_CAPS_PENDING_NVM_VER:
+		caps->nvm_update_pending_nvm = true;
+		break;
+	case IXGBE_ACI_CAPS_PENDING_OROM_VER:
+		caps->nvm_update_pending_orom = true;
+		break;
+	case IXGBE_ACI_CAPS_PENDING_NET_VER:
+		caps->nvm_update_pending_netlist = true;
+		break;
+	case IXGBE_ACI_CAPS_NVM_MGMT:
+		caps->nvm_unified_update =
+			(number & IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT) ?
+			true : false;
+		break;
+	case IXGBE_ACI_CAPS_MAX_MTU:
+		caps->max_mtu = number;
+		break;
+	case IXGBE_ACI_CAPS_PCIE_RESET_AVOIDANCE:
+		caps->pcie_reset_avoidance = (number > 0);
+		break;
+	case IXGBE_ACI_CAPS_POST_UPDATE_RESET_RESTRICT:
+		caps->reset_restrict_support = (number == 1);
+		break;
+	case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0:
+	case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG1:
+	case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG2:
+	case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG3:
+	{
+		u8 index = cap - IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0;
+
+		caps->ext_topo_dev_img_ver_high[index] = number;
+		caps->ext_topo_dev_img_ver_low[index] = logical_id;
+		caps->ext_topo_dev_img_part_num[index] =
+			FIELD_GET(IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_M, phys_id);
+		caps->ext_topo_dev_img_load_en[index] =
+			(phys_id & IXGBE_EXT_TOPO_DEV_IMG_LOAD_EN) != 0;
+		caps->ext_topo_dev_img_prog_en[index] =
+			(phys_id & IXGBE_EXT_TOPO_DEV_IMG_PROG_EN) != 0;
+		break;
+	}
+	default:
+		/* Not one of the recognized common capabilities */
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * ixgbe_parse_valid_functions_cap - Parse IXGBE_ACI_CAPS_VALID_FUNCTIONS caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse IXGBE_ACI_CAPS_VALID_FUNCTIONS for device capabilities.
+ */
+static void
+ixgbe_parse_valid_functions_cap(struct ixgbe_hw *hw,
+				struct ixgbe_hw_dev_caps *dev_p,
+				struct ixgbe_aci_cmd_list_caps_elem *cap)
+{
+	dev_p->num_funcs = hweight32(le32_to_cpu(cap->number));
+}
+
+/**
+ * ixgbe_parse_vf_dev_caps - Parse IXGBE_ACI_CAPS_VF device caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse IXGBE_ACI_CAPS_VF for device capabilities.
+ */
+static void ixgbe_parse_vf_dev_caps(struct ixgbe_hw *hw,
+				    struct ixgbe_hw_dev_caps *dev_p,
+				    struct ixgbe_aci_cmd_list_caps_elem *cap)
+{
+	dev_p->num_vfs_exposed = le32_to_cpu(cap->number);
+}
+
+/**
+ * ixgbe_parse_vsi_dev_caps - Parse IXGBE_ACI_CAPS_VSI device caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse IXGBE_ACI_CAPS_VSI for device capabilities.
+ */
+static void ixgbe_parse_vsi_dev_caps(struct ixgbe_hw *hw,
+				     struct ixgbe_hw_dev_caps *dev_p,
+				     struct ixgbe_aci_cmd_list_caps_elem *cap)
+{
+	dev_p->num_vsi_allocd_to_host = le32_to_cpu(cap->number);
+}
+
+/**
+ * ixgbe_parse_fdir_dev_caps - Parse IXGBE_ACI_CAPS_FD device caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse IXGBE_ACI_CAPS_FD for device capabilities.
+ */
+static void ixgbe_parse_fdir_dev_caps(struct ixgbe_hw *hw,
+				      struct ixgbe_hw_dev_caps *dev_p,
+				      struct ixgbe_aci_cmd_list_caps_elem *cap)
+{
+	dev_p->num_flow_director_fltr = le32_to_cpu(cap->number);
+}
+
+/**
+ * ixgbe_parse_dev_caps - Parse device capabilities
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @buf: buffer containing the device capability records
+ * @cap_count: the number of capabilities
+ *
+ * Helper device to parse device (0x000B) capabilities list. For
+ * capabilities shared between device and function, this relies on
+ * ixgbe_parse_e610_caps.
+ *
+ * Loop through the list of provided capabilities and extract the relevant
+ * data into the device capabilities structured.
+ */
+static void ixgbe_parse_dev_caps(struct ixgbe_hw *hw,
+				 struct ixgbe_hw_dev_caps *dev_p,
+				 void *buf, u32 cap_count)
+{
+	struct ixgbe_aci_cmd_list_caps_elem *cap_resp;
+	u32 i;
+
+	cap_resp = (struct ixgbe_aci_cmd_list_caps_elem *)buf;
+
+	memset(dev_p, 0, sizeof(*dev_p));
+
+	for (i = 0; i < cap_count; i++) {
+		u16 cap = le16_to_cpu(cap_resp[i].cap);
+
+		ixgbe_parse_e610_caps(hw, &dev_p->common_cap, &cap_resp[i],
+				      "dev caps");
+
+		switch (cap) {
+		case IXGBE_ACI_CAPS_VALID_FUNCTIONS:
+			ixgbe_parse_valid_functions_cap(hw, dev_p,
+							&cap_resp[i]);
+			break;
+		case IXGBE_ACI_CAPS_VF:
+			ixgbe_parse_vf_dev_caps(hw, dev_p, &cap_resp[i]);
+			break;
+		case IXGBE_ACI_CAPS_VSI:
+			ixgbe_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]);
+			break;
+		case  IXGBE_ACI_CAPS_FD:
+			ixgbe_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]);
+			break;
+		default:
+			/* Don't list common capabilities as unknown */
+			break;
+		}
+	}
+}
+
+/**
+ * ixgbe_parse_vf_func_caps - Parse IXGBE_ACI_CAPS_VF function caps
+ * @hw: pointer to the HW struct
+ * @func_p: pointer to function capabilities structure
+ * @cap: pointer to the capability element to parse
+ *
+ * Extract function capabilities for IXGBE_ACI_CAPS_VF.
+ */
+static void ixgbe_parse_vf_func_caps(struct ixgbe_hw *hw,
+				     struct ixgbe_hw_func_caps *func_p,
+				     struct ixgbe_aci_cmd_list_caps_elem *cap)
+{
+	func_p->num_allocd_vfs = le32_to_cpu(cap->number);
+	func_p->vf_base_id = le32_to_cpu(cap->logical_id);
+}
+
+/**
+ * ixgbe_get_num_per_func - determine number of resources per PF
+ * @hw: pointer to the HW structure
+ * @max: value to be evenly split between each PF
+ *
+ * Determine the number of valid functions by going through the bitmap returned
+ * from parsing capabilities and use this to calculate the number of resources
+ * per PF based on the max value passed in.
+ *
+ * Return: the number of resources per PF or 0, if no PH are available.
+ */
+static u32 ixgbe_get_num_per_func(struct ixgbe_hw *hw, u32 max)
+{
+#define IXGBE_CAPS_VALID_FUNCS_M	GENMASK(7, 0)
+	u8 funcs = hweight8(hw->dev_caps.common_cap.valid_functions &
+			    IXGBE_CAPS_VALID_FUNCS_M);
+
+	return funcs ? (max / funcs) : 0;
+}
+
+/**
+ * ixgbe_parse_vsi_func_caps - Parse IXGBE_ACI_CAPS_VSI function caps
+ * @hw: pointer to the HW struct
+ * @func_p: pointer to function capabilities structure
+ * @cap: pointer to the capability element to parse
+ *
+ * Extract function capabilities for IXGBE_ACI_CAPS_VSI.
+ */
+static void ixgbe_parse_vsi_func_caps(struct ixgbe_hw *hw,
+				      struct ixgbe_hw_func_caps *func_p,
+				      struct ixgbe_aci_cmd_list_caps_elem *cap)
+{
+	func_p->guar_num_vsi = ixgbe_get_num_per_func(hw, IXGBE_MAX_VSI);
+}
+
+/**
+ * ixgbe_parse_func_caps - Parse function capabilities
+ * @hw: pointer to the HW struct
+ * @func_p: pointer to function capabilities structure
+ * @buf: buffer containing the function capability records
+ * @cap_count: the number of capabilities
+ *
+ * Helper function to parse function (0x000A) capabilities list. For
+ * capabilities shared between device and function, this relies on
+ * ixgbe_parse_e610_caps.
+ *
+ * Loop through the list of provided capabilities and extract the relevant
+ * data into the function capabilities structured.
+ */
+static void ixgbe_parse_func_caps(struct ixgbe_hw *hw,
+				  struct ixgbe_hw_func_caps *func_p,
+				  void *buf, u32 cap_count)
+{
+	struct ixgbe_aci_cmd_list_caps_elem *cap_resp;
+	u32 i;
+
+	cap_resp = (struct ixgbe_aci_cmd_list_caps_elem *)buf;
+
+	memset(func_p, 0, sizeof(*func_p));
+
+	for (i = 0; i < cap_count; i++) {
+		u16 cap = le16_to_cpu(cap_resp[i].cap);
+
+		ixgbe_parse_e610_caps(hw, &func_p->common_cap,
+				      &cap_resp[i], "func caps");
+
+		switch (cap) {
+		case IXGBE_ACI_CAPS_VF:
+			ixgbe_parse_vf_func_caps(hw, func_p, &cap_resp[i]);
+			break;
+		case IXGBE_ACI_CAPS_VSI:
+			ixgbe_parse_vsi_func_caps(hw, func_p, &cap_resp[i]);
+			break;
+		default:
+			/* Don't list common capabilities as unknown */
+			break;
+		}
+	}
+}
+
+/**
+ * ixgbe_aci_list_caps - query function/device capabilities
+ * @hw: pointer to the HW struct
+ * @buf: a buffer to hold the capabilities
+ * @buf_size: size of the buffer
+ * @cap_count: if not NULL, set to the number of capabilities reported
+ * @opc: capabilities type to discover, device or function
+ *
+ * Get the function (0x000A) or device (0x000B) capabilities description from
+ * firmware and store it in the buffer.
+ *
+ * If the cap_count pointer is not NULL, then it is set to the number of
+ * capabilities firmware will report. Note that if the buffer size is too
+ * small, it is possible the command will return -ENOMEM. The
+ * cap_count will still be updated in this case. It is recommended that the
+ * buffer size be set to IXGBE_ACI_MAX_BUFFER_SIZE (the largest possible
+ * buffer that firmware could return) to avoid this.
+ *
+ * Return: the exit code of the operation.
+ * Exit code of -ENOMEM means the buffer size is too small.
+ */
+int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size,
+			u32 *cap_count, enum ixgbe_aci_opc opc)
+{
+	struct ixgbe_aci_cmd_list_caps *cmd;
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	cmd = &desc.params.get_cap;
+
+	if (opc != ixgbe_aci_opc_list_func_caps &&
+	    opc != ixgbe_aci_opc_list_dev_caps)
+		return -EINVAL;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, opc);
+	err = ixgbe_aci_send_cmd(hw, &desc, buf, buf_size);
+
+	if (cap_count)
+		*cap_count = le32_to_cpu(cmd->count);
+
+	return err;
+}
+
+/**
+ * ixgbe_discover_dev_caps - Read and extract device capabilities
+ * @hw: pointer to the hardware structure
+ * @dev_caps: pointer to device capabilities structure
+ *
+ * Read the device capabilities and extract them into the dev_caps structure
+ * for later use.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_discover_dev_caps(struct ixgbe_hw *hw,
+			    struct ixgbe_hw_dev_caps *dev_caps)
+{
+	u32 cap_count;
+	u8 *cbuf;
+	int err;
+
+	cbuf = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!cbuf)
+		return -ENOMEM;
+
+	/* Although the driver doesn't know the number of capabilities the
+	 * device will return, we can simply send a 4KB buffer, the maximum
+	 * possible size that firmware can return.
+	 */
+	cap_count = IXGBE_ACI_MAX_BUFFER_SIZE /
+		    sizeof(struct ixgbe_aci_cmd_list_caps_elem);
+
+	err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE,
+				  &cap_count,
+				  ixgbe_aci_opc_list_dev_caps);
+	if (!err)
+		ixgbe_parse_dev_caps(hw, dev_caps, cbuf, cap_count);
+
+	kfree(cbuf);
+
+	return 0;
+}
+
+/**
+ * ixgbe_discover_func_caps - Read and extract function capabilities
+ * @hw: pointer to the hardware structure
+ * @func_caps: pointer to function capabilities structure
+ *
+ * Read the function capabilities and extract them into the func_caps structure
+ * for later use.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_discover_func_caps(struct ixgbe_hw *hw,
+			     struct ixgbe_hw_func_caps *func_caps)
+{
+	u32 cap_count;
+	u8 *cbuf;
+	int err;
+
+	cbuf = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!cbuf)
+		return -ENOMEM;
+
+	/* Although the driver doesn't know the number of capabilities the
+	 * device will return, we can simply send a 4KB buffer, the maximum
+	 * possible size that firmware can return.
+	 */
+	cap_count = IXGBE_ACI_MAX_BUFFER_SIZE /
+		    sizeof(struct ixgbe_aci_cmd_list_caps_elem);
+
+	err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE,
+				  &cap_count,
+				  ixgbe_aci_opc_list_func_caps);
+	if (!err)
+		ixgbe_parse_func_caps(hw, func_caps, cbuf, cap_count);
+
+	kfree(cbuf);
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_caps - get info about the HW
+ * @hw: pointer to the hardware structure
+ *
+ * Retrieve both device and function capabilities.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_caps(struct ixgbe_hw *hw)
+{
+	int err;
+
+	err = ixgbe_discover_dev_caps(hw, &hw->dev_caps);
+	if (err)
+		return err;
+
+	return ixgbe_discover_func_caps(hw, &hw->func_caps);
+}
+
+/**
+ * ixgbe_aci_disable_rxen - disable RX
+ * @hw: pointer to the HW struct
+ *
+ * Request a safe disable of Receive Enable using ACI command (0x000C).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_disable_rxen *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.disable_rxen;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_disable_rxen);
+
+	cmd->lport_num = hw->bus.func;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_aci_get_phy_caps - returns PHY capabilities
+ * @hw: pointer to the HW struct
+ * @qual_mods: report qualified modules
+ * @report_mode: report mode capabilities
+ * @pcaps: structure for PHY capabilities to be filled
+ *
+ * Returns the various PHY capabilities supported on the Port
+ * using ACI command (0x0600).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode,
+			   struct ixgbe_aci_cmd_get_phy_caps_data *pcaps)
+{
+	struct ixgbe_aci_cmd_get_phy_caps *cmd;
+	u16 pcaps_size = sizeof(*pcaps);
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	cmd = &desc.params.get_phy;
+
+	if (!pcaps || (report_mode & ~IXGBE_ACI_REPORT_MODE_M))
+		return -EINVAL;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_phy_caps);
+
+	if (qual_mods)
+		cmd->param0 |= cpu_to_le16(IXGBE_ACI_GET_PHY_RQM);
+
+	cmd->param0 |= cpu_to_le16(report_mode);
+	err = ixgbe_aci_send_cmd(hw, &desc, pcaps, pcaps_size);
+	if (!err && report_mode == IXGBE_ACI_REPORT_TOPO_CAP_MEDIA) {
+		hw->phy.phy_type_low = le64_to_cpu(pcaps->phy_type_low);
+		hw->phy.phy_type_high = le64_to_cpu(pcaps->phy_type_high);
+		memcpy(hw->link.link_info.module_type, &pcaps->module_type,
+		       sizeof(hw->link.link_info.module_type));
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_copy_phy_caps_to_cfg - Copy PHY ability data to configuration data
+ * @caps: PHY ability structure to copy data from
+ * @cfg: PHY configuration structure to copy data to
+ *
+ * Helper function to copy data from PHY capabilities data structure
+ * to PHY configuration data structure
+ */
+void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps,
+				struct ixgbe_aci_cmd_set_phy_cfg_data *cfg)
+{
+	if (!caps || !cfg)
+		return;
+
+	memset(cfg, 0, sizeof(*cfg));
+	cfg->phy_type_low = caps->phy_type_low;
+	cfg->phy_type_high = caps->phy_type_high;
+	cfg->caps = caps->caps;
+	cfg->low_power_ctrl_an = caps->low_power_ctrl_an;
+	cfg->eee_cap = caps->eee_cap;
+	cfg->eeer_value = caps->eeer_value;
+	cfg->link_fec_opt = caps->link_fec_options;
+	cfg->module_compliance_enforcement =
+		caps->module_compliance_enforcement;
+}
+
+/**
+ * ixgbe_aci_set_phy_cfg - set PHY configuration
+ * @hw: pointer to the HW struct
+ * @cfg: structure with PHY configuration data to be set
+ *
+ * Set the various PHY configuration parameters supported on the Port
+ * using ACI command (0x0601).
+ * One or more of the Set PHY config parameters may be ignored in an MFP
+ * mode as the PF may not have the privilege to set some of the PHY Config
+ * parameters.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw,
+			  struct ixgbe_aci_cmd_set_phy_cfg_data *cfg)
+{
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	if (!cfg)
+		return -EINVAL;
+
+	/* Ensure that only valid bits of cfg->caps can be turned on. */
+	cfg->caps &= IXGBE_ACI_PHY_ENA_VALID_MASK;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_phy_cfg);
+	desc.params.set_phy.lport_num = hw->bus.func;
+	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+
+	err = ixgbe_aci_send_cmd(hw, &desc, cfg, sizeof(*cfg));
+	if (!err)
+		hw->phy.curr_user_phy_cfg = *cfg;
+
+	return err;
+}
+
+/**
+ * ixgbe_aci_set_link_restart_an - set up link and restart AN
+ * @hw: pointer to the HW struct
+ * @ena_link: if true: enable link, if false: disable link
+ *
+ * Function sets up the link and restarts the Auto-Negotiation over the link.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link)
+{
+	struct ixgbe_aci_cmd_restart_an *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.restart_an;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_restart_an);
+
+	cmd->cmd_flags = IXGBE_ACI_RESTART_AN_LINK_RESTART;
+	cmd->lport_num = hw->bus.func;
+	if (ena_link)
+		cmd->cmd_flags |= IXGBE_ACI_RESTART_AN_LINK_ENABLE;
+	else
+		cmd->cmd_flags &= ~IXGBE_ACI_RESTART_AN_LINK_ENABLE;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_is_media_cage_present - check if media cage is present
+ * @hw: pointer to the HW struct
+ *
+ * Identify presence of media cage using the ACI command (0x06E0).
+ *
+ * Return: true if media cage is present, else false. If no cage, then
+ * media type is backplane or BASE-T.
+ */
+static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_link_topo *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.get_link_topo;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo);
+
+	cmd->addr.topo_params.node_type_ctx =
+		FIELD_PREP(IXGBE_ACI_LINK_TOPO_NODE_CTX_M,
+			   IXGBE_ACI_LINK_TOPO_NODE_CTX_PORT);
+
+	/* Set node type. */
+	cmd->addr.topo_params.node_type_ctx |=
+		FIELD_PREP(IXGBE_ACI_LINK_TOPO_NODE_TYPE_M,
+			   IXGBE_ACI_LINK_TOPO_NODE_TYPE_CAGE);
+
+	/* Node type cage can be used to determine if cage is present. If AQC
+	 * returns error (ENOENT), then no cage present. If no cage present then
+	 * connection type is backplane or BASE-T.
+	 */
+	return !ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL);
+}
+
+/**
+ * ixgbe_get_media_type_from_phy_type - Gets media type based on phy type
+ * @hw: pointer to the HW struct
+ *
+ * Try to identify the media type based on the phy type.
+ * If more than one media type, the ixgbe_media_type_unknown is returned.
+ * First, phy_type_low is checked, then phy_type_high.
+ * If none are identified, the ixgbe_media_type_unknown is returned
+ *
+ * Return: type of a media based on phy type in form of enum.
+ */
+static enum ixgbe_media_type
+ixgbe_get_media_type_from_phy_type(struct ixgbe_hw *hw)
+{
+	struct ixgbe_link_status *hw_link_info;
+
+	if (!hw)
+		return ixgbe_media_type_unknown;
+
+	hw_link_info = &hw->link.link_info;
+	if (hw_link_info->phy_type_low && hw_link_info->phy_type_high)
+		/* If more than one media type is selected, report unknown */
+		return ixgbe_media_type_unknown;
+
+	if (hw_link_info->phy_type_low) {
+		/* 1G SGMII is a special case where some DA cable PHYs
+		 * may show this as an option when it really shouldn't
+		 * be since SGMII is meant to be between a MAC and a PHY
+		 * in a backplane. Try to detect this case and handle it
+		 */
+		if (hw_link_info->phy_type_low == IXGBE_PHY_TYPE_LOW_1G_SGMII &&
+		    (hw_link_info->module_type[IXGBE_ACI_MOD_TYPE_IDENT] ==
+		    IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE ||
+		    hw_link_info->module_type[IXGBE_ACI_MOD_TYPE_IDENT] ==
+		    IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE))
+			return ixgbe_media_type_da;
+
+		switch (hw_link_info->phy_type_low) {
+		case IXGBE_PHY_TYPE_LOW_1000BASE_SX:
+		case IXGBE_PHY_TYPE_LOW_1000BASE_LX:
+		case IXGBE_PHY_TYPE_LOW_10GBASE_SR:
+		case IXGBE_PHY_TYPE_LOW_10GBASE_LR:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_SR:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_LR:
+			return ixgbe_media_type_fiber;
+		case IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC:
+		case IXGBE_PHY_TYPE_LOW_25G_AUI_AOC_ACC:
+			return ixgbe_media_type_fiber;
+		case IXGBE_PHY_TYPE_LOW_100BASE_TX:
+		case IXGBE_PHY_TYPE_LOW_1000BASE_T:
+		case IXGBE_PHY_TYPE_LOW_2500BASE_T:
+		case IXGBE_PHY_TYPE_LOW_5GBASE_T:
+		case IXGBE_PHY_TYPE_LOW_10GBASE_T:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_T:
+			return ixgbe_media_type_copper;
+		case IXGBE_PHY_TYPE_LOW_10G_SFI_DA:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_CR:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_CR_S:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_CR1:
+			return ixgbe_media_type_da;
+		case IXGBE_PHY_TYPE_LOW_25G_AUI_C2C:
+			if (ixgbe_is_media_cage_present(hw))
+				return ixgbe_media_type_aui;
+			fallthrough;
+		case IXGBE_PHY_TYPE_LOW_1000BASE_KX:
+		case IXGBE_PHY_TYPE_LOW_2500BASE_KX:
+		case IXGBE_PHY_TYPE_LOW_2500BASE_X:
+		case IXGBE_PHY_TYPE_LOW_5GBASE_KR:
+		case IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1:
+		case IXGBE_PHY_TYPE_LOW_10G_SFI_C2C:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_KR:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_KR1:
+		case IXGBE_PHY_TYPE_LOW_25GBASE_KR_S:
+			return ixgbe_media_type_backplane;
+		}
+	} else {
+		switch (hw_link_info->phy_type_high) {
+		case IXGBE_PHY_TYPE_HIGH_10BASE_T:
+			return ixgbe_media_type_copper;
+		}
+	}
+	return ixgbe_media_type_unknown;
+}
+
+/**
+ * ixgbe_update_link_info - update status of the HW network link
+ * @hw: pointer to the HW struct
+ *
+ * Update the status of the HW network link.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_update_link_info(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data *pcaps;
+	struct ixgbe_link_status *li;
+	int err;
+
+	if (!hw)
+		return -EINVAL;
+
+	li = &hw->link.link_info;
+
+	err = ixgbe_aci_get_link_info(hw, true, NULL);
+	if (err)
+		return err;
+
+	if (!(li->link_info & IXGBE_ACI_MEDIA_AVAILABLE))
+		return 0;
+
+	pcaps =	kzalloc(sizeof(*pcaps), GFP_KERNEL);
+	if (!pcaps)
+		return -ENOMEM;
+
+	err = ixgbe_aci_get_phy_caps(hw, false, IXGBE_ACI_REPORT_TOPO_CAP_MEDIA,
+				     pcaps);
+
+	if (!err)
+		memcpy(li->module_type, &pcaps->module_type,
+		       sizeof(li->module_type));
+
+	kfree(pcaps);
+
+	return err;
+}
+
+/**
+ * ixgbe_get_link_status - get status of the HW network link
+ * @hw: pointer to the HW struct
+ * @link_up: pointer to bool (true/false = linkup/linkdown)
+ *
+ * Variable link_up is true if link is up, false if link is down.
+ * The variable link_up is invalid if status is non zero. As a
+ * result of this call, link status reporting becomes enabled
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_link_status(struct ixgbe_hw *hw, bool *link_up)
+{
+	if (!hw || !link_up)
+		return -EINVAL;
+
+	if (hw->link.get_link_info) {
+		int err = ixgbe_update_link_info(hw);
+
+		if (err)
+			return err;
+	}
+
+	*link_up = hw->link.link_info.link_info & IXGBE_ACI_LINK_UP;
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_get_link_info - get the link status
+ * @hw: pointer to the HW struct
+ * @ena_lse: enable/disable LinkStatusEvent reporting
+ * @link: pointer to link status structure - optional
+ *
+ * Get the current Link Status using ACI command (0x607).
+ * The current link can be optionally provided to update
+ * the status.
+ *
+ * Return: the link status of the adapter.
+ */
+int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse,
+			    struct ixgbe_link_status *link)
+{
+	struct ixgbe_aci_cmd_get_link_status_data link_data = {};
+	struct ixgbe_aci_cmd_get_link_status *resp;
+	struct ixgbe_link_status *li_old, *li;
+	struct ixgbe_fc_info *hw_fc_info;
+	struct ixgbe_aci_desc desc;
+	bool tx_pause, rx_pause;
+	u8 cmd_flags;
+	int err;
+
+	if (!hw)
+		return -EINVAL;
+
+	li_old = &hw->link.link_info_old;
+	li = &hw->link.link_info;
+	hw_fc_info = &hw->fc;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_status);
+	cmd_flags = (ena_lse) ? IXGBE_ACI_LSE_ENA : IXGBE_ACI_LSE_DIS;
+	resp = &desc.params.get_link_status;
+	resp->cmd_flags = cpu_to_le16(cmd_flags);
+	resp->lport_num = hw->bus.func;
+
+	err = ixgbe_aci_send_cmd(hw, &desc, &link_data, sizeof(link_data));
+	if (err)
+		return err;
+
+	/* Save off old link status information. */
+	*li_old = *li;
+
+	/* Update current link status information. */
+	li->link_speed = le16_to_cpu(link_data.link_speed);
+	li->phy_type_low = le64_to_cpu(link_data.phy_type_low);
+	li->phy_type_high = le64_to_cpu(link_data.phy_type_high);
+	li->link_info = link_data.link_info;
+	li->link_cfg_err = link_data.link_cfg_err;
+	li->an_info = link_data.an_info;
+	li->ext_info = link_data.ext_info;
+	li->max_frame_size = le16_to_cpu(link_data.max_frame_size);
+	li->fec_info = link_data.cfg & IXGBE_ACI_FEC_MASK;
+	li->topo_media_conflict = link_data.topo_media_conflict;
+	li->pacing = link_data.cfg & (IXGBE_ACI_CFG_PACING_M |
+				      IXGBE_ACI_CFG_PACING_TYPE_M);
+
+	/* Update fc info. */
+	tx_pause = !!(link_data.an_info & IXGBE_ACI_LINK_PAUSE_TX);
+	rx_pause = !!(link_data.an_info & IXGBE_ACI_LINK_PAUSE_RX);
+	if (tx_pause && rx_pause)
+		hw_fc_info->current_mode = ixgbe_fc_full;
+	else if (tx_pause)
+		hw_fc_info->current_mode = ixgbe_fc_tx_pause;
+	else if (rx_pause)
+		hw_fc_info->current_mode = ixgbe_fc_rx_pause;
+	else
+		hw_fc_info->current_mode = ixgbe_fc_none;
+
+	li->lse_ena = !!(le16_to_cpu(resp->cmd_flags) &
+			 IXGBE_ACI_LSE_IS_ENABLED);
+
+	/* Save link status information. */
+	if (link)
+		*link = *li;
+
+	/* Flag cleared so calling functions don't call AQ again. */
+	hw->link.get_link_info = false;
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_set_event_mask - set event mask
+ * @hw: pointer to the HW struct
+ * @port_num: port number of the physical function
+ * @mask: event mask to be set
+ *
+ * Set the event mask using ACI command (0x0613).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask)
+{
+	struct ixgbe_aci_cmd_set_event_mask *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.set_event_mask;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_event_mask);
+
+	cmd->lport_num = port_num;
+
+	cmd->event_mask = cpu_to_le16(mask);
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_configure_lse - enable/disable link status events
+ * @hw: pointer to the HW struct
+ * @activate: true for enable lse, false otherwise
+ * @mask: event mask to be set; a set bit means deactivation of the
+ * corresponding event
+ *
+ * Set the event mask and then enable or disable link status events
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask)
+{
+	int err;
+
+	err = ixgbe_aci_set_event_mask(hw, (u8)hw->bus.func, mask);
+	if (err)
+		return err;
+
+	/* Enabling link status events generation by fw. */
+	return ixgbe_aci_get_link_info(hw, activate, NULL);
+}
+
+/**
+ * ixgbe_start_hw_e610 - Prepare hardware for Tx/Rx
+ * @hw: pointer to hardware structure
+ *
+ * Get firmware version and start the hardware using the generic
+ * start_hw() and ixgbe_start_hw_gen2() functions.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_start_hw_e610(struct ixgbe_hw *hw)
+{
+	int err;
+
+	err = ixgbe_aci_get_fw_ver(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_start_hw_generic(hw);
+	if (err)
+		return err;
+
+	ixgbe_start_hw_gen2(hw);
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_set_port_id_led - set LED value for the given port
+ * @hw: pointer to the HW struct
+ * @orig_mode: set LED original mode
+ *
+ * Set LED value for the given port (0x06E9)
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode)
+{
+	struct ixgbe_aci_cmd_set_port_id_led *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.set_port_id_led;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_port_id_led);
+
+	cmd->lport_num = (u8)hw->bus.func;
+	cmd->lport_num_valid = IXGBE_ACI_PORT_ID_PORT_NUM_VALID;
+
+	if (orig_mode)
+		cmd->ident_mode = IXGBE_ACI_PORT_IDENT_LED_ORIG;
+	else
+		cmd->ident_mode = IXGBE_ACI_PORT_IDENT_LED_BLINK;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_get_media_type_e610 - Gets media type
+ * @hw: pointer to the HW struct
+ *
+ * In order to get the media type, the function gets PHY
+ * capabilities and later on use them to identify the PHY type
+ * checking phy_type_high and phy_type_low.
+ *
+ * Return: the type of media in form of ixgbe_media_type enum
+ * or ixgbe_media_type_unknown in case of an error.
+ */
+enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data pcaps;
+	int rc;
+
+	rc = ixgbe_update_link_info(hw);
+	if (rc)
+		return ixgbe_media_type_unknown;
+
+	/* If there is no link but PHY (dongle) is available SW should use
+	 * Get PHY Caps admin command instead of Get Link Status, find most
+	 * significant bit that is set in PHY types reported by the command
+	 * and use it to discover media type.
+	 */
+	if (!(hw->link.link_info.link_info & IXGBE_ACI_LINK_UP) &&
+	    (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) {
+		int highest_bit;
+
+		/* Get PHY Capabilities */
+		rc = ixgbe_aci_get_phy_caps(hw, false,
+					    IXGBE_ACI_REPORT_TOPO_CAP_MEDIA,
+					    &pcaps);
+		if (rc)
+			return ixgbe_media_type_unknown;
+
+		highest_bit = fls64(le64_to_cpu(pcaps.phy_type_high));
+		if (highest_bit) {
+			hw->link.link_info.phy_type_high =
+				BIT_ULL(highest_bit - 1);
+			hw->link.link_info.phy_type_low = 0;
+		} else {
+			highest_bit = fls64(le64_to_cpu(pcaps.phy_type_low));
+			if (highest_bit) {
+				hw->link.link_info.phy_type_low =
+					BIT_ULL(highest_bit - 1);
+				hw->link.link_info.phy_type_high = 0;
+			}
+		}
+	}
+
+	/* Based on link status or search above try to discover media type. */
+	hw->phy.media_type = ixgbe_get_media_type_from_phy_type(hw);
+
+	return hw->phy.media_type;
+}
+
+/**
+ * ixgbe_setup_link_e610 - Set up link
+ * @hw: pointer to hardware structure
+ * @speed: new link speed
+ * @autoneg_wait: true when waiting for completion is needed
+ *
+ * Set up the link with the specified speed.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed,
+			  bool autoneg_wait)
+{
+	/* Simply request FW to perform proper PHY setup */
+	return hw->phy.ops.setup_link_speed(hw, speed, autoneg_wait);
+}
+
+/**
+ * ixgbe_check_link_e610 - Determine link and speed status
+ * @hw: pointer to hardware structure
+ * @speed: pointer to link speed
+ * @link_up: true when link is up
+ * @link_up_wait_to_complete: bool used to wait for link up or not
+ *
+ * Determine if the link is up and the current link speed
+ * using ACI command (0x0607).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_check_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
+			  bool *link_up, bool link_up_wait_to_complete)
+{
+	int err;
+	u32 i;
+
+	if (!speed || !link_up)
+		return -EINVAL;
+
+	/* Set get_link_info flag to ensure that fresh
+	 * link information will be obtained from FW
+	 * by sending Get Link Status admin command.
+	 */
+	hw->link.get_link_info = true;
+
+	/* Update link information in adapter context. */
+	err = ixgbe_get_link_status(hw, link_up);
+	if (err)
+		return err;
+
+	/* Wait for link up if it was requested. */
+	if (link_up_wait_to_complete && !(*link_up)) {
+		for (i = 0; i < hw->mac.max_link_up_time; i++) {
+			msleep(100);
+			hw->link.get_link_info = true;
+			err = ixgbe_get_link_status(hw, link_up);
+			if (err)
+				return err;
+			if (*link_up)
+				break;
+		}
+	}
+
+	/* Use link information in adapter context updated by the call
+	 * to ixgbe_get_link_status() to determine current link speed.
+	 * Link speed information is valid only when link up was
+	 * reported by FW.
+	 */
+	if (*link_up) {
+		switch (hw->link.link_info.link_speed) {
+		case IXGBE_ACI_LINK_SPEED_10MB:
+			*speed = IXGBE_LINK_SPEED_10_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_100MB:
+			*speed = IXGBE_LINK_SPEED_100_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_1000MB:
+			*speed = IXGBE_LINK_SPEED_1GB_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_2500MB:
+			*speed = IXGBE_LINK_SPEED_2_5GB_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_5GB:
+			*speed = IXGBE_LINK_SPEED_5GB_FULL;
+			break;
+		case IXGBE_ACI_LINK_SPEED_10GB:
+			*speed = IXGBE_LINK_SPEED_10GB_FULL;
+			break;
+		default:
+			*speed = IXGBE_LINK_SPEED_UNKNOWN;
+			break;
+		}
+	} else {
+		*speed = IXGBE_LINK_SPEED_UNKNOWN;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_link_capabilities_e610 - Determine link capabilities
+ * @hw: pointer to hardware structure
+ * @speed: pointer to link speed
+ * @autoneg: true when autoneg or autotry is enabled
+ *
+ * Determine speed and AN parameters of a link.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_link_capabilities_e610(struct ixgbe_hw *hw,
+				     ixgbe_link_speed *speed,
+				     bool *autoneg)
+{
+	if (!speed || !autoneg)
+		return -EINVAL;
+
+	*autoneg = true;
+	*speed = hw->phy.speeds_supported;
+
+	return 0;
+}
+
+/**
+ * ixgbe_cfg_phy_fc - Configure PHY Flow Control (FC) data based on FC mode
+ * @hw: pointer to hardware structure
+ * @cfg: PHY configuration data to set FC mode
+ * @req_mode: FC mode to configure
+ *
+ * Configures PHY Flow Control according to the provided configuration.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_cfg_phy_fc(struct ixgbe_hw *hw,
+		     struct ixgbe_aci_cmd_set_phy_cfg_data *cfg,
+		     enum ixgbe_fc_mode req_mode)
+{
+	u8 pause_mask = 0x0;
+
+	if (!cfg)
+		return -EINVAL;
+
+	switch (req_mode) {
+	case ixgbe_fc_full:
+		pause_mask |= IXGBE_ACI_PHY_EN_TX_LINK_PAUSE;
+		pause_mask |= IXGBE_ACI_PHY_EN_RX_LINK_PAUSE;
+		break;
+	case ixgbe_fc_rx_pause:
+		pause_mask |= IXGBE_ACI_PHY_EN_RX_LINK_PAUSE;
+		break;
+	case ixgbe_fc_tx_pause:
+		pause_mask |= IXGBE_ACI_PHY_EN_TX_LINK_PAUSE;
+		break;
+	default:
+		break;
+	}
+
+	/* Clear the old pause settings. */
+	cfg->caps &= ~(IXGBE_ACI_PHY_EN_TX_LINK_PAUSE |
+		IXGBE_ACI_PHY_EN_RX_LINK_PAUSE);
+
+	/* Set the new capabilities. */
+	cfg->caps |= pause_mask;
+
+	return 0;
+}
+
+/**
+ * ixgbe_setup_fc_e610 - Set up flow control
+ * @hw: pointer to hardware structure
+ *
+ * Set up flow control. This has to be done during init time.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_setup_fc_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data pcaps = {};
+	struct ixgbe_aci_cmd_set_phy_cfg_data cfg = {};
+	int err;
+
+	/* Get the current PHY config */
+	err = ixgbe_aci_get_phy_caps(hw, false,
+				     IXGBE_ACI_REPORT_ACTIVE_CFG, &pcaps);
+	if (err)
+		return err;
+
+	ixgbe_copy_phy_caps_to_cfg(&pcaps, &cfg);
+
+	/* Configure the set PHY data */
+	err = ixgbe_cfg_phy_fc(hw, &cfg, hw->fc.requested_mode);
+	if (err)
+		return err;
+
+	/* If the capabilities have changed, then set the new config */
+	if (cfg.caps != pcaps.caps) {
+		cfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT;
+
+		err = ixgbe_aci_set_phy_cfg(hw, &cfg);
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_fc_autoneg_e610 - Configure flow control
+ * @hw: pointer to hardware structure
+ *
+ * Configure Flow Control.
+ */
+void ixgbe_fc_autoneg_e610(struct ixgbe_hw *hw)
+{
+	int err;
+
+	/* Get current link err.
+	 * Current FC mode will be stored in the hw context.
+	 */
+	err = ixgbe_aci_get_link_info(hw, false, NULL);
+	if (err)
+		goto no_autoneg;
+
+	/* Check if the link is up */
+	if (!(hw->link.link_info.link_info & IXGBE_ACI_LINK_UP))
+		goto no_autoneg;
+
+	/* Check if auto-negotiation has completed */
+	if (!(hw->link.link_info.an_info & IXGBE_ACI_AN_COMPLETED))
+		goto no_autoneg;
+
+	hw->fc.fc_was_autonegged = true;
+	return;
+
+no_autoneg:
+	hw->fc.fc_was_autonegged = false;
+	hw->fc.current_mode = hw->fc.requested_mode;
+}
+
+/**
+ * ixgbe_disable_rx_e610 - Disable RX unit
+ * @hw: pointer to hardware structure
+ *
+ * Disable RX DMA unit on E610 with use of ACI command (0x000C).
+ *
+ * Return: the exit code of the operation.
+ */
+void ixgbe_disable_rx_e610(struct ixgbe_hw *hw)
+{
+	u32 rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
+	u32 pfdtxgswc;
+	int err;
+
+	if (!(rxctrl & IXGBE_RXCTRL_RXEN))
+		return;
+
+	pfdtxgswc = IXGBE_READ_REG(hw, IXGBE_PFDTXGSWC);
+	if (pfdtxgswc & IXGBE_PFDTXGSWC_VT_LBEN) {
+		pfdtxgswc &= ~IXGBE_PFDTXGSWC_VT_LBEN;
+		IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, pfdtxgswc);
+		hw->mac.set_lben = true;
+	} else {
+		hw->mac.set_lben = false;
+	}
+
+	err = ixgbe_aci_disable_rxen(hw);
+
+	/* If we fail - disable RX using register write */
+	if (err) {
+		rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
+		if (rxctrl & IXGBE_RXCTRL_RXEN) {
+			rxctrl &= ~IXGBE_RXCTRL_RXEN;
+			IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl);
+		}
+	}
+}
+
+/**
+ * ixgbe_fw_recovery_mode_e610 - Check FW NVM recovery mode
+ * @hw: pointer to hardware structure
+ *
+ * Check FW NVM recovery mode by reading the value of
+ * the dedicated register.
+ *
+ * Return: true if FW is in recovery mode, otherwise false.
+ */
+static bool ixgbe_fw_recovery_mode_e610(struct ixgbe_hw *hw)
+{
+	u32 fwsm = IXGBE_READ_REG(hw, IXGBE_GL_MNG_FWSM);
+
+	return !!(fwsm & IXGBE_GL_MNG_FWSM_RECOVERY_M);
+}
+
+/**
+ * ixgbe_fw_rollback_mode_e610 - Check FW NVM rollback mode
+ * @hw: pointer to hardware structure
+ *
+ * Check FW NVM rollback mode by reading the value of
+ * the dedicated register.
+ *
+ * Return: true if FW is in rollback mode, otherwise false.
+ */
+static bool ixgbe_fw_rollback_mode_e610(struct ixgbe_hw *hw)
+{
+	u32 fwsm = IXGBE_READ_REG(hw, IXGBE_GL_MNG_FWSM);
+
+	return !!(fwsm & IXGBE_GL_MNG_FWSM_ROLLBACK_M);
+}
+
+/**
+ * ixgbe_init_phy_ops_e610 - PHY specific init
+ * @hw: pointer to hardware structure
+ *
+ * Initialize any function pointers that were not able to be
+ * set during init_shared_code because the PHY type was not known.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_init_phy_ops_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_mac_info *mac = &hw->mac;
+	struct ixgbe_phy_info *phy = &hw->phy;
+
+	if (mac->ops.get_media_type(hw) == ixgbe_media_type_copper)
+		phy->ops.set_phy_power = ixgbe_set_phy_power_e610;
+	else
+		phy->ops.set_phy_power = NULL;
+
+	/* Identify the PHY */
+	return phy->ops.identify(hw);
+}
+
+/**
+ * ixgbe_identify_phy_e610 - Identify PHY
+ * @hw: pointer to hardware structure
+ *
+ * Determine PHY type, supported speeds and PHY ID.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_identify_phy_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data pcaps;
+	u64 phy_type_low, phy_type_high;
+	int err;
+
+	/* Set PHY type */
+	hw->phy.type = ixgbe_phy_fw;
+
+	err = ixgbe_aci_get_phy_caps(hw, false,
+				     IXGBE_ACI_REPORT_TOPO_CAP_MEDIA, &pcaps);
+	if (err)
+		return err;
+
+	if (!(pcaps.module_compliance_enforcement &
+	      IXGBE_ACI_MOD_ENFORCE_STRICT_MODE)) {
+		/* Handle lenient mode */
+		err = ixgbe_aci_get_phy_caps(hw, false,
+					     IXGBE_ACI_REPORT_TOPO_CAP_NO_MEDIA,
+					     &pcaps);
+		if (err)
+			return err;
+	}
+
+	/* Determine supported speeds */
+	hw->phy.speeds_supported = IXGBE_LINK_SPEED_UNKNOWN;
+	phy_type_high = le64_to_cpu(pcaps.phy_type_high);
+	phy_type_low = le64_to_cpu(pcaps.phy_type_low);
+
+	if (phy_type_high & IXGBE_PHY_TYPE_HIGH_10BASE_T ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_10M_SGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10_FULL;
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_100BASE_TX ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_100M_SGMII ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_100M_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_100_FULL;
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_1000BASE_T  ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_1000BASE_SX ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_1000BASE_LX ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_1000BASE_KX ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_1G_SGMII    ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_1G_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_1GB_FULL;
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_10GBASE_T       ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10G_SFI_DA      ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10GBASE_SR      ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10GBASE_LR      ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1  ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_10G_SFI_C2C     ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_10G_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10GB_FULL;
+
+	/* 2.5 and 5 Gbps link speeds must be excluded from the
+	 * auto-negotiation set used during driver initialization due to
+	 * compatibility issues with certain switches. Those issues do not
+	 * exist in case of E610 2.5G SKU device (0x57b1).
+	 */
+	if (!hw->phy.autoneg_advertised &&
+	    hw->device_id != IXGBE_DEV_ID_E610_2_5G_T)
+		hw->phy.autoneg_advertised = hw->phy.speeds_supported;
+
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_2500BASE_T   ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_2500BASE_X   ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_2500BASE_KX  ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_2500M_SGMII ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_2500M_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL;
+
+	if (!hw->phy.autoneg_advertised &&
+	    hw->device_id == IXGBE_DEV_ID_E610_2_5G_T)
+		hw->phy.autoneg_advertised = hw->phy.speeds_supported;
+
+	if (phy_type_low  & IXGBE_PHY_TYPE_LOW_5GBASE_T  ||
+	    phy_type_low  & IXGBE_PHY_TYPE_LOW_5GBASE_KR ||
+	    phy_type_high & IXGBE_PHY_TYPE_HIGH_5G_USXGMII)
+		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL;
+
+	/* Set PHY ID */
+	memcpy(&hw->phy.id, pcaps.phy_id_oui, sizeof(u32));
+
+	hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_10_FULL |
+				       IXGBE_LINK_SPEED_100_FULL |
+				       IXGBE_LINK_SPEED_1GB_FULL;
+	hw->phy.eee_speeds_advertised = hw->phy.eee_speeds_supported;
+
+	return 0;
+}
+
+/**
+ * ixgbe_identify_module_e610 - Identify SFP module type
+ * @hw: pointer to hardware structure
+ *
+ * Identify the SFP module type.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_identify_module_e610(struct ixgbe_hw *hw)
+{
+	bool media_available;
+	u8 module_type;
+	int err;
+
+	err = ixgbe_update_link_info(hw);
+	if (err)
+		return err;
+
+	media_available =
+		(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE);
+
+	if (media_available) {
+		hw->phy.sfp_type = ixgbe_sfp_type_unknown;
+
+		/* Get module type from hw context updated by
+		 * ixgbe_update_link_info()
+		 */
+		module_type = hw->link.link_info.module_type[IXGBE_ACI_MOD_TYPE_IDENT];
+
+		if ((module_type & IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE) ||
+		    (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE)) {
+			hw->phy.sfp_type = ixgbe_sfp_type_da_cu;
+		} else if (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_SR) {
+			hw->phy.sfp_type = ixgbe_sfp_type_sr;
+		} else if ((module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LR) ||
+			   (module_type & IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LRM)) {
+			hw->phy.sfp_type = ixgbe_sfp_type_lr;
+		}
+	} else {
+		hw->phy.sfp_type = ixgbe_sfp_type_not_present;
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_setup_phy_link_e610 - Sets up firmware-controlled PHYs
+ * @hw: pointer to hardware structure
+ *
+ * Set the parameters for the firmware-controlled PHYs.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_setup_phy_link_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data pcaps;
+	struct ixgbe_aci_cmd_set_phy_cfg_data pcfg;
+	u8 rmode = IXGBE_ACI_REPORT_TOPO_CAP_MEDIA;
+	u64 sup_phy_type_low, sup_phy_type_high;
+	u64 phy_type_low = 0, phy_type_high = 0;
+	int err;
+
+	err = ixgbe_aci_get_link_info(hw, false, NULL);
+	if (err)
+		return err;
+
+	/* If media is not available get default config. */
+	if (!(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE))
+		rmode = IXGBE_ACI_REPORT_DFLT_CFG;
+
+	err = ixgbe_aci_get_phy_caps(hw, false, rmode, &pcaps);
+	if (err)
+		return err;
+
+	sup_phy_type_low = le64_to_cpu(pcaps.phy_type_low);
+	sup_phy_type_high = le64_to_cpu(pcaps.phy_type_high);
+
+	/* Get Active configuration to avoid unintended changes. */
+	err = ixgbe_aci_get_phy_caps(hw, false, IXGBE_ACI_REPORT_ACTIVE_CFG,
+				     &pcaps);
+	if (err)
+		return err;
+
+	ixgbe_copy_phy_caps_to_cfg(&pcaps, &pcfg);
+
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) {
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_10BASE_T;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_10M_SGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_100BASE_TX;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_100M_SGMII;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_100M_USXGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1000BASE_T;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1000BASE_SX;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1000BASE_LX;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1000BASE_KX;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_1G_SGMII;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_1G_USXGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_2500BASE_T;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_2500BASE_X;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_2500BASE_KX;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_2500M_SGMII;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_2500M_USXGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_5GBASE_T;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_5GBASE_KR;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_5G_USXGMII;
+	}
+	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) {
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10GBASE_T;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10G_SFI_DA;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10GBASE_SR;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10GBASE_LR;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC;
+		phy_type_low  |= IXGBE_PHY_TYPE_LOW_10G_SFI_C2C;
+		phy_type_high |= IXGBE_PHY_TYPE_HIGH_10G_USXGMII;
+	}
+
+	/* Mask the set values to avoid requesting unsupported link types. */
+	phy_type_low &= sup_phy_type_low;
+	pcfg.phy_type_low = cpu_to_le64(phy_type_low);
+	phy_type_high &= sup_phy_type_high;
+	pcfg.phy_type_high = cpu_to_le64(phy_type_high);
+
+	if (pcfg.phy_type_high != pcaps.phy_type_high ||
+	    pcfg.phy_type_low != pcaps.phy_type_low ||
+	    pcfg.caps != pcaps.caps) {
+		pcfg.caps |= IXGBE_ACI_PHY_ENA_LINK;
+		pcfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT;
+
+		err = ixgbe_aci_set_phy_cfg(hw, &pcfg);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_set_phy_power_e610 - Control power for copper PHY
+ * @hw: pointer to hardware structure
+ * @on: true for on, false for off
+ *
+ * Set the power on/off of the PHY
+ * by getting its capabilities and setting the appropriate
+ * configuration parameters.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_set_phy_power_e610(struct ixgbe_hw *hw, bool on)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data phy_caps = {};
+	struct ixgbe_aci_cmd_set_phy_cfg_data phy_cfg = {};
+	int err;
+
+	err = ixgbe_aci_get_phy_caps(hw, false,
+				     IXGBE_ACI_REPORT_ACTIVE_CFG,
+				     &phy_caps);
+	if (err)
+		return err;
+
+	ixgbe_copy_phy_caps_to_cfg(&phy_caps, &phy_cfg);
+
+	if (on)
+		phy_cfg.caps &= ~IXGBE_ACI_PHY_ENA_LOW_POWER;
+	else
+		phy_cfg.caps |= IXGBE_ACI_PHY_ENA_LOW_POWER;
+
+	/* PHY is already in requested power mode. */
+	if (phy_caps.caps == phy_cfg.caps)
+		return 0;
+
+	phy_cfg.caps |= IXGBE_ACI_PHY_ENA_LINK;
+	phy_cfg.caps |= IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT;
+
+	return ixgbe_aci_set_phy_cfg(hw, &phy_cfg);
+}
+
+/**
+ * ixgbe_enter_lplu_e610 - Transition to low power states
+ * @hw: pointer to hardware structure
+ *
+ * Configures Low Power Link Up on transition to low power states
+ * (from D0 to non-D0). Link is required to enter LPLU so avoid resetting the
+ * X557 PHY immediately prior to entering LPLU.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_enter_lplu_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_phy_caps_data phy_caps = {};
+	struct ixgbe_aci_cmd_set_phy_cfg_data phy_cfg = {};
+	int err;
+
+	err = ixgbe_aci_get_phy_caps(hw, false,
+				     IXGBE_ACI_REPORT_ACTIVE_CFG,
+				     &phy_caps);
+	if (err)
+		return err;
+
+	ixgbe_copy_phy_caps_to_cfg(&phy_caps, &phy_cfg);
+
+	phy_cfg.low_power_ctrl_an |= IXGBE_ACI_PHY_EN_D3COLD_LOW_POWER_AUTONEG;
+
+	return ixgbe_aci_set_phy_cfg(hw, &phy_cfg);
+}
+
+/**
+ * ixgbe_init_eeprom_params_e610 - Initialize EEPROM params
+ * @hw: pointer to hardware structure
+ *
+ * Initialize the EEPROM parameters ixgbe_eeprom_info within the ixgbe_hw
+ * struct in order to set up EEPROM access.
+ *
+ * Return: the operation exit code.
+ */
+int ixgbe_init_eeprom_params_e610(struct ixgbe_hw *hw)
+{
+	struct ixgbe_eeprom_info *eeprom = &hw->eeprom;
+	u32 gens_stat;
+	u8 sr_size;
+
+	if (eeprom->type != ixgbe_eeprom_uninitialized)
+		return 0;
+
+	eeprom->type = ixgbe_flash;
+
+	gens_stat = IXGBE_READ_REG(hw, GLNVM_GENS);
+	sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat);
+
+	/* Switching to words (sr_size contains power of 2). */
+	eeprom->word_size = BIT(sr_size) * IXGBE_SR_WORDS_IN_1KB;
+
+	hw_dbg(hw, "Eeprom params: type = %d, size = %d\n", eeprom->type,
+	       eeprom->word_size);
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_get_netlist_node - get a node handle
+ * @hw: pointer to the hw struct
+ * @cmd: get_link_topo AQ structure
+ * @node_part_number: output node part number if node found
+ * @node_handle: output node handle parameter if node found
+ *
+ * Get the netlist node and assigns it to
+ * the provided handle using ACI command (0x06E0).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw,
+			       struct ixgbe_aci_cmd_get_link_topo *cmd,
+			       u8 *node_part_number, u16 *node_handle)
+{
+	struct ixgbe_aci_desc desc;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo);
+	desc.params.get_link_topo = *cmd;
+
+	if (ixgbe_aci_send_cmd(hw, &desc, NULL, 0))
+		return -EOPNOTSUPP;
+
+	if (node_handle)
+		*node_handle =
+			le16_to_cpu(desc.params.get_link_topo.addr.handle);
+	if (node_part_number)
+		*node_part_number = desc.params.get_link_topo.node_part_num;
+
+	return 0;
+}
+
+/**
+ * ixgbe_acquire_nvm - Generic request for acquiring the NVM ownership
+ * @hw: pointer to the HW structure
+ * @access: NVM access type (read or write)
+ *
+ * Request NVM ownership.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_acquire_nvm(struct ixgbe_hw *hw,
+		      enum ixgbe_aci_res_access_type access)
+{
+	u32 fla;
+
+	/* Skip if we are in blank NVM programming mode */
+	fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA);
+	if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0)
+		return 0;
+
+	return ixgbe_acquire_res(hw, IXGBE_NVM_RES_ID, access,
+				 IXGBE_NVM_TIMEOUT);
+}
+
+/**
+ * ixgbe_release_nvm - Generic request for releasing the NVM ownership
+ * @hw: pointer to the HW structure
+ *
+ * Release NVM ownership.
+ */
+void ixgbe_release_nvm(struct ixgbe_hw *hw)
+{
+	u32 fla;
+
+	/* Skip if we are in blank NVM programming mode */
+	fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA);
+	if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0)
+		return;
+
+	ixgbe_release_res(hw, IXGBE_NVM_RES_ID);
+}
+
+/**
+ * ixgbe_aci_read_nvm - read NVM
+ * @hw: pointer to the HW struct
+ * @module_typeid: module pointer location in words from the NVM beginning
+ * @offset: byte offset from the module beginning
+ * @length: length of the section to be read (in bytes from the offset)
+ * @data: command buffer (size [bytes] = length)
+ * @last_command: tells if this is the last command in a series
+ * @read_shadow_ram: tell if this is a shadow RAM read
+ *
+ * Read the NVM using ACI command (0x0701).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
+		       u16 length, void *data, bool last_command,
+		       bool read_shadow_ram)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct ixgbe_aci_desc desc;
+
+	if (offset > IXGBE_ACI_NVM_MAX_OFFSET)
+		return -EINVAL;
+
+	cmd = &desc.params.nvm;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_read);
+
+	if (!read_shadow_ram && module_typeid == IXGBE_ACI_NVM_START_POINT)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_FLASH_ONLY;
+
+	/* If this is the last command in a series, set the proper flag. */
+	if (last_command)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_LAST_CMD;
+	cmd->module_typeid = cpu_to_le16(module_typeid);
+	cmd->offset_low = cpu_to_le16(offset & 0xFFFF);
+	cmd->offset_high = (offset >> 16) & 0xFF;
+	cmd->length = cpu_to_le16(length);
+
+	return ixgbe_aci_send_cmd(hw, &desc, data, length);
+}
+
+/**
+ * ixgbe_aci_erase_nvm - erase NVM sector
+ * @hw: pointer to the HW struct
+ * @module_typeid: module pointer location in words from the NVM beginning
+ *
+ * Erase the NVM sector using the ACI command (0x0702).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct ixgbe_aci_desc desc;
+	__le16 len;
+	int err;
+
+	/* Read a length value from SR, so module_typeid is equal to 0,
+	 * calculate offset where module size is placed from bytes to words
+	 * set last command and read from SR values to true.
+	 */
+	err = ixgbe_aci_read_nvm(hw, 0, 2 * module_typeid + 2, 2, &len, true,
+				 true);
+	if (err)
+		return err;
+
+	cmd = &desc.params.nvm;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_erase);
+
+	cmd->module_typeid = cpu_to_le16(module_typeid);
+	cmd->length = len;
+	cmd->offset_low = 0;
+	cmd->offset_high = 0;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_aci_update_nvm - update NVM
+ * @hw: pointer to the HW struct
+ * @module_typeid: module pointer location in words from the NVM beginning
+ * @offset: byte offset from the module beginning
+ * @length: length of the section to be written (in bytes from the offset)
+ * @data: command buffer (size [bytes] = length)
+ * @last_command: tells if this is the last command in a series
+ * @command_flags: command parameters
+ *
+ * Update the NVM using the ACI command (0x0703).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid,
+			 u32 offset, u16 length, void *data,
+			 bool last_command, u8 command_flags)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.nvm;
+
+	/* In offset the highest byte must be zeroed. */
+	if (offset & 0xFF000000)
+		return -EINVAL;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_write);
+
+	cmd->cmd_flags |= command_flags;
+
+	/* If this is the last command in a series, set the proper flag. */
+	if (last_command)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_LAST_CMD;
+	cmd->module_typeid = cpu_to_le16(module_typeid);
+	cmd->offset_low = cpu_to_le16(offset & 0xFFFF);
+	cmd->offset_high = FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_U_MASK, offset);
+	cmd->length = cpu_to_le16(length);
+
+	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+
+	return ixgbe_aci_send_cmd(hw, &desc, data, length);
+}
+
+/**
+ * ixgbe_nvm_write_activate - NVM activate write
+ * @hw: pointer to the HW struct
+ * @cmd_flags: flags for write activate command
+ * @response_flags: response indicators from firmware
+ *
+ * Update the control word with the required banks' validity bits
+ * and dumps the Shadow RAM to flash using ACI command (0x0707).
+ *
+ * cmd_flags controls which banks to activate, the preservation level to use
+ * when activating the NVM bank, and whether an EMP reset is required for
+ * activation.
+ *
+ * Note that the 16bit cmd_flags value is split between two separate 1 byte
+ * flag values in the descriptor.
+ *
+ * On successful return of the firmware command, the response_flags variable
+ * is updated with the flags reported by firmware indicating certain status,
+ * such as whether EMP reset is enabled.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags,
+			     u8 *response_flags)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct ixgbe_aci_desc desc;
+	s32 err;
+
+	cmd = &desc.params.nvm;
+	ixgbe_fill_dflt_direct_cmd_desc(&desc,
+					ixgbe_aci_opc_nvm_write_activate);
+
+	cmd->cmd_flags = (u8)(cmd_flags & 0xFF);
+	cmd->offset_high = (u8)FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_A_MASK,
+					 cmd_flags);
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+	if (!err && response_flags)
+		*response_flags = cmd->cmd_flags;
+
+	return err;
+}
+
+/**
+ * ixgbe_nvm_validate_checksum - validate checksum
+ * @hw: pointer to the HW struct
+ *
+ * Verify NVM PFA checksum validity using ACI command (0x0706).
+ * If the checksum verification failed, IXGBE_ERR_NVM_CHECKSUM is returned.
+ * The function acquires and then releases the NVM ownership.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_nvm_checksum *cmd;
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err)
+		return err;
+
+	cmd = &desc.params.nvm_checksum;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_checksum);
+	cmd->flags = IXGBE_ACI_NVM_CHECKSUM_VERIFY;
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+
+	ixgbe_release_nvm(hw);
+
+	if (!err && cmd->checksum !=
+		cpu_to_le16(IXGBE_ACI_NVM_CHECKSUM_CORRECT)) {
+		struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter,
+							     hw);
+
+		err = -EIO;
+		netdev_err(adapter->netdev, "Invalid Shadow Ram checksum");
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_discover_flash_size - Discover the available flash size
+ * @hw: pointer to the HW struct
+ *
+ * The device flash could be up to 16MB in size. However, it is possible that
+ * the actual size is smaller. Use bisection to determine the accessible size
+ * of flash memory.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_discover_flash_size(struct ixgbe_hw *hw)
+{
+	u32 min_size = 0, max_size = IXGBE_ACI_NVM_MAX_OFFSET + 1;
+	int err;
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err)
+		return err;
+
+	while ((max_size - min_size) > 1) {
+		u32 offset = (max_size + min_size) / 2;
+		u32 len = 1;
+		u8 data;
+
+		err = ixgbe_read_flat_nvm(hw, offset, &len, &data, false);
+		if (err == -EIO &&
+		    hw->aci.last_status == IXGBE_ACI_RC_EINVAL) {
+			err = 0;
+			max_size = offset;
+		} else if (!err) {
+			min_size = offset;
+		} else {
+			/* an unexpected error occurred */
+			goto err_read_flat_nvm;
+		}
+	}
+
+	hw->flash.flash_size = max_size;
+
+err_read_flat_nvm:
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_sr_base_address - Read the value of a Shadow RAM pointer word
+ * @hw: pointer to the HW structure
+ * @offset: the word offset of the Shadow RAM word to read
+ * @pointer: pointer value read from Shadow RAM
+ *
+ * Read the given Shadow RAM word, and convert it to a pointer value specified
+ * in bytes. This function assumes the specified offset is a valid pointer
+ * word.
+ *
+ * Each pointer word specifies whether it is stored in word size or 4KB
+ * sector size by using the highest bit. The reported pointer value will be in
+ * bytes, intended for flat NVM reads.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_sr_base_address(struct ixgbe_hw *hw, u16 offset,
+				      u32 *pointer)
+{
+	u16 value;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, offset, &value);
+	if (err)
+		return err;
+
+	/* Determine if the pointer is in 4KB or word units */
+	if (value & IXGBE_SR_NVM_PTR_4KB_UNITS)
+		*pointer = (value & ~IXGBE_SR_NVM_PTR_4KB_UNITS) * SZ_4K;
+	else
+		*pointer = value * sizeof(u16);
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_sr_area_size - Read an area size from a Shadow RAM word
+ * @hw: pointer to the HW structure
+ * @offset: the word offset of the Shadow RAM to read
+ * @size: size value read from the Shadow RAM
+ *
+ * Read the given Shadow RAM word, and convert it to an area size value
+ * specified in bytes. This function assumes the specified offset is a valid
+ * area size word.
+ *
+ * Each area size word is specified in 4KB sector units. This function reports
+ * the size in bytes, intended for flat NVM reads.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_sr_area_size(struct ixgbe_hw *hw, u16 offset, u32 *size)
+{
+	u16 value;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, offset, &value);
+	if (err)
+		return err;
+
+	/* Area sizes are always specified in 4KB units */
+	*size = value * SZ_4K;
+
+	return 0;
+}
+
+/**
+ * ixgbe_determine_active_flash_banks - Discover active bank for each module
+ * @hw: pointer to the HW struct
+ *
+ * Read the Shadow RAM control word and determine which banks are active for
+ * the NVM, OROM, and Netlist modules. Also read and calculate the associated
+ * pointer and size. These values are then cached into the ixgbe_flash_info
+ * structure for later use in order to calculate the correct offset to read
+ * from the active module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_determine_active_flash_banks(struct ixgbe_hw *hw)
+{
+	struct ixgbe_bank_info *banks = &hw->flash.banks;
+	u16 ctrl_word;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, IXGBE_E610_SR_NVM_CTRL_WORD,
+				     &ctrl_word);
+	if (err)
+		return err;
+
+	if (FIELD_GET(IXGBE_SR_CTRL_WORD_1_M, ctrl_word) !=
+	    IXGBE_SR_CTRL_WORD_VALID)
+		return -ENODATA;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_NVM_BANK))
+		banks->nvm_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->nvm_bank = IXGBE_2ND_FLASH_BANK;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_OROM_BANK))
+		banks->orom_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->orom_bank = IXGBE_2ND_FLASH_BANK;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_NETLIST_BANK))
+		banks->netlist_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->netlist_bank = IXGBE_2ND_FLASH_BANK;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_1ST_NVM_BANK_PTR,
+					 &banks->nvm_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_NVM_BANK_SIZE,
+				      &banks->nvm_size);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_1ST_OROM_BANK_PTR,
+					 &banks->orom_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_OROM_BANK_SIZE,
+				      &banks->orom_size);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_NETLIST_BANK_PTR,
+					 &banks->netlist_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_NETLIST_BANK_SIZE,
+				      &banks->netlist_size);
+
+	return err;
+}
+
+/**
+ * ixgbe_get_flash_bank_offset - Get offset into requested flash bank
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive flash bank
+ * @module: the module to read from
+ *
+ * Based on the module, lookup the module offset from the beginning of the
+ * flash.
+ *
+ * Return: the flash offset. Note that a value of zero is invalid and must be
+ * treated as an error.
+ */
+static int ixgbe_get_flash_bank_offset(struct ixgbe_hw *hw,
+				       enum ixgbe_bank_select bank,
+				       u16 module)
+{
+	struct ixgbe_bank_info *banks = &hw->flash.banks;
+	enum ixgbe_flash_bank active_bank;
+	bool second_bank_active;
+	u32 offset, size;
+
+	switch (module) {
+	case IXGBE_E610_SR_1ST_NVM_BANK_PTR:
+		offset = banks->nvm_ptr;
+		size = banks->nvm_size;
+		active_bank = banks->nvm_bank;
+		break;
+	case IXGBE_E610_SR_1ST_OROM_BANK_PTR:
+		offset = banks->orom_ptr;
+		size = banks->orom_size;
+		active_bank = banks->orom_bank;
+		break;
+	case IXGBE_E610_SR_NETLIST_BANK_PTR:
+		offset = banks->netlist_ptr;
+		size = banks->netlist_size;
+		active_bank = banks->netlist_bank;
+		break;
+	default:
+		return 0;
+	}
+
+	switch (active_bank) {
+	case IXGBE_1ST_FLASH_BANK:
+		second_bank_active = false;
+		break;
+	case IXGBE_2ND_FLASH_BANK:
+		second_bank_active = true;
+		break;
+	default:
+		return 0;
+	}
+
+	/* The second flash bank is stored immediately following the first
+	 * bank. Based on whether the 1st or 2nd bank is active, and whether
+	 * we want the active or inactive bank, calculate the desired offset.
+	 */
+	switch (bank) {
+	case IXGBE_ACTIVE_FLASH_BANK:
+		return offset + (second_bank_active ? size : 0);
+	case IXGBE_INACTIVE_FLASH_BANK:
+		return offset + (second_bank_active ? 0 : size);
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_flash_module - Read a word from one of the main NVM modules
+ * @hw: pointer to the HW structure
+ * @bank: which bank of the module to read
+ * @module: the module to read
+ * @offset: the offset into the module in bytes
+ * @data: storage for the word read from the flash
+ * @length: bytes of data to read
+ *
+ * Read data from the specified flash module. The bank parameter indicates
+ * whether or not to read from the active bank or the inactive bank of that
+ * module.
+ *
+ * The word will be read using flat NVM access, and relies on the
+ * hw->flash.banks data being setup by ixgbe_determine_active_flash_banks()
+ * during initialization.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_flash_module(struct ixgbe_hw *hw,
+				   enum ixgbe_bank_select bank,
+				   u16 module, u32 offset, u8 *data, u32 length)
+{
+	u32 start;
+	int err;
+
+	start = ixgbe_get_flash_bank_offset(hw, bank, module);
+	if (!start)
+		return -EINVAL;
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err)
+		return err;
+
+	err = ixgbe_read_flat_nvm(hw, start + offset, &length, data, false);
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_nvm_module - Read from the active main NVM module
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from active or inactive NVM module
+ * @offset: offset into the NVM module to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the active NVM module. This includes the CSS
+ * header at the start of the NVM module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_nvm_module(struct ixgbe_hw *hw,
+				 enum ixgbe_bank_select bank,
+				 u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_1ST_NVM_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local,
+				      sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_netlist_module - Read data from the netlist module area
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive module
+ * @offset: offset into the netlist to read from
+ * @data: storage for returned word value
+ *
+ * Read a word from the specified netlist bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_netlist_module(struct ixgbe_hw *hw,
+				     enum ixgbe_bank_select bank,
+				     u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_NETLIST_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local, sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_orom_module - Read from the active Option ROM module
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from active or inactive OROM module
+ * @offset: offset into the OROM module to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the active Option ROM module of the flash.
+ * Note that unlike the NVM module, the CSS data is stored at the end of the
+ * module instead of at the beginning.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_orom_module(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_1ST_OROM_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local, sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_get_nvm_css_hdr_len - Read the CSS header length
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @hdr_len: storage for header length in words
+ *
+ * Read the CSS header length from the NVM CSS header and add the
+ * Authentication header size, and then convert to words.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_css_hdr_len(struct ixgbe_hw *hw,
+				     enum ixgbe_bank_select bank,
+				     u32 *hdr_len)
+{
+	u16 hdr_len_l, hdr_len_h;
+	u32 hdr_len_dword;
+	int err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_HDR_LEN_L,
+				    &hdr_len_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_HDR_LEN_H,
+				    &hdr_len_h);
+	if (err)
+		return err;
+
+	/* CSS header length is in DWORD, so convert to words and add
+	 * authentication header size.
+	 */
+	hdr_len_dword = (hdr_len_h << 16) | hdr_len_l;
+	*hdr_len = hdr_len_dword * 2 + IXGBE_NVM_AUTH_HEADER_LEN;
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_nvm_sr_copy - Read a word from the Shadow RAM copy
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive NVM module
+ * @offset: offset into the Shadow RAM copy to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the copy of the Shadow RAM found in the
+ * specified NVM module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_nvm_sr_copy(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  u32 offset, u16 *data)
+{
+	u32 hdr_len;
+	int err;
+
+	err = ixgbe_get_nvm_css_hdr_len(hw, bank, &hdr_len);
+	if (err)
+		return err;
+
+	hdr_len = round_up(hdr_len, IXGBE_HDR_LEN_ROUNDUP);
+
+	return ixgbe_read_nvm_module(hw, bank, hdr_len + offset, data);
+}
+
+/**
+ * ixgbe_get_nvm_srev - Read the security revision from the NVM CSS header
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @srev: storage for security revision
+ *
+ * Read the security revision out of the CSS header of the active NVM module
+ * bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_srev(struct ixgbe_hw *hw,
+			      enum ixgbe_bank_select bank, u32 *srev)
+{
+	u16 srev_l, srev_h;
+	int err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_SREV_L, &srev_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_SREV_H, &srev_h);
+	if (err)
+		return err;
+
+	*srev = (srev_h << 16) | srev_l;
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_orom_civd_data - Get the combo version information from Option ROM
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash module
+ * @civd: storage for the Option ROM CIVD data.
+ *
+ * Searches through the Option ROM flash contents to locate the CIVD data for
+ * the image.
+ *
+ * Return: the exit code of the operation.
+ */
+static int
+ixgbe_get_orom_civd_data(struct ixgbe_hw *hw, enum ixgbe_bank_select bank,
+			 struct ixgbe_orom_civd_info *civd)
+{
+	struct ixgbe_orom_civd_info tmp;
+	u32 offset;
+	int err;
+
+	/* The CIVD section is located in the Option ROM aligned to 512 bytes.
+	 * The first 4 bytes must contain the ASCII characters "$CIV".
+	 * A simple modulo 256 sum of all of the bytes of the structure must
+	 * equal 0.
+	 */
+	for (offset = 0; (offset + SZ_512) <= hw->flash.banks.orom_size;
+	     offset += SZ_512) {
+		u8 sum = 0;
+		u32 i;
+
+		err = ixgbe_read_flash_module(hw, bank,
+					      IXGBE_E610_SR_1ST_OROM_BANK_PTR,
+					      offset,
+					      (u8 *)&tmp, sizeof(tmp));
+		if (err)
+			return err;
+
+		/* Skip forward until we find a matching signature */
+		if (memcmp(IXGBE_OROM_CIV_SIGNATURE, tmp.signature,
+			   sizeof(tmp.signature)))
+			continue;
+
+		/* Verify that the simple checksum is zero */
+		for (i = 0; i < sizeof(tmp); i++)
+			sum += ((u8 *)&tmp)[i];
+
+		if (sum)
+			return -EDOM;
+
+		*civd = tmp;
+		return 0;
+	}
+
+	return -ENODATA;
+}
+
+/**
+ * ixgbe_get_orom_srev - Read the security revision from the OROM CSS header
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from active or inactive flash module
+ * @srev: storage for security revision
+ *
+ * Read the security revision out of the CSS header of the active OROM module
+ * bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_orom_srev(struct ixgbe_hw *hw,
+			       enum ixgbe_bank_select bank,
+			       u32 *srev)
+{
+	u32 orom_size_word = hw->flash.banks.orom_size / 2;
+	u32 css_start, hdr_len;
+	u16 srev_l, srev_h;
+	int err;
+
+	err = ixgbe_get_nvm_css_hdr_len(hw, bank, &hdr_len);
+	if (err)
+		return err;
+
+	if (orom_size_word < hdr_len)
+		return -EINVAL;
+
+	/* Calculate how far into the Option ROM the CSS header starts. Note
+	 * that ixgbe_read_orom_module takes a word offset.
+	 */
+	css_start = orom_size_word - hdr_len;
+	err = ixgbe_read_orom_module(hw, bank,
+				     css_start + IXGBE_NVM_CSS_SREV_L,
+				     &srev_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_orom_module(hw, bank,
+				     css_start + IXGBE_NVM_CSS_SREV_H,
+				     &srev_h);
+	if (err)
+		return err;
+
+	*srev = srev_h << 16 | srev_l;
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_orom_ver_info - Read Option ROM version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash module
+ * @orom: pointer to Option ROM info structure
+ *
+ * Read Option ROM version and security revision from the Option ROM flash
+ * section.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_orom_ver_info(struct ixgbe_hw *hw,
+				   enum ixgbe_bank_select bank,
+				   struct ixgbe_orom_info *orom)
+{
+	struct ixgbe_orom_civd_info civd;
+	u32 combo_ver;
+	int err;
+
+	err = ixgbe_get_orom_civd_data(hw, bank, &civd);
+	if (err)
+		return err;
+
+	combo_ver = le32_to_cpu(civd.combo_ver);
+
+	orom->major = (u8)FIELD_GET(IXGBE_OROM_VER_MASK, combo_ver);
+	orom->patch = (u8)FIELD_GET(IXGBE_OROM_VER_PATCH_MASK, combo_ver);
+	orom->build = (u16)FIELD_GET(IXGBE_OROM_VER_BUILD_MASK, combo_ver);
+
+	return ixgbe_get_orom_srev(hw, bank, &orom->srev);
+}
+
+/**
+ * ixgbe_get_inactive_orom_ver - Read Option ROM version from the inactive bank
+ * @hw: pointer to the HW structure
+ * @orom: storage for Option ROM version information
+ *
+ * Read the Option ROM version and security revision data for the inactive
+ * section of flash. Used to access version data for a pending update that has
+ * not yet been activated.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_orom_ver(struct ixgbe_hw *hw,
+				struct ixgbe_orom_info *orom)
+{
+	return ixgbe_get_orom_ver_info(hw, IXGBE_INACTIVE_FLASH_BANK, orom);
+}
+
+/**
+ * ixgbe_get_nvm_ver_info - Read NVM version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @nvm: pointer to NVM info structure
+ *
+ * Read the NVM EETRACK ID and map version of the main NVM image bank, filling
+ * in the nvm info structure.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_ver_info(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  struct ixgbe_nvm_info *nvm)
+{
+	u16 eetrack_lo, eetrack_hi, ver;
+	int err;
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank,
+				     IXGBE_E610_SR_NVM_DEV_STARTER_VER, &ver);
+	if (err)
+		return err;
+
+	nvm->major = FIELD_GET(IXGBE_E610_NVM_VER_HI_MASK, ver);
+	nvm->minor = FIELD_GET(IXGBE_E610_NVM_VER_LO_MASK, ver);
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank, IXGBE_E610_SR_NVM_EETRACK_LO,
+				     &eetrack_lo);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank, IXGBE_E610_SR_NVM_EETRACK_HI,
+				     &eetrack_hi);
+	if (err)
+		return err;
+
+	nvm->eetrack = (eetrack_hi << 16) | eetrack_lo;
+
+	ixgbe_get_nvm_srev(hw, bank, &nvm->srev);
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_inactive_nvm_ver - Read Option ROM version from the inactive bank
+ * @hw: pointer to the HW structure
+ * @nvm: storage for Option ROM version information
+ *
+ * Read the NVM EETRACK ID, Map version, and security revision of the
+ * inactive NVM bank. Used to access version data for a pending update that
+ * has not yet been activated.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_nvm_ver(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm)
+{
+	return ixgbe_get_nvm_ver_info(hw, IXGBE_INACTIVE_FLASH_BANK, nvm);
+}
+
+/**
+ * ixgbe_get_active_nvm_ver - Read Option ROM version from the active bank
+ * @hw: pointer to the HW structure
+ * @nvm: storage for Option ROM version information
+ *
+ * Reads the NVM EETRACK ID, Map version, and security revision of the
+ * active NVM bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_active_nvm_ver(struct ixgbe_hw *hw,
+				    struct ixgbe_nvm_info *nvm)
+{
+	return ixgbe_get_nvm_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK, nvm);
+}
+
+/**
+ * ixgbe_get_netlist_info - Read the netlist version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @netlist: pointer to netlist version info structure
+ *
+ * Get the netlist version information from the requested bank. Reads the Link
+ * Topology section to find the Netlist ID block and extract the relevant
+ * information into the netlist version structure.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_netlist_info(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  struct ixgbe_netlist_info *netlist)
+{
+	u16 module_id, length, node_count, i;
+	u16 *id_blk;
+	int err;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_NETLIST_TYPE_OFFSET,
+					&module_id);
+	if (err)
+		return err;
+
+	if (module_id != IXGBE_NETLIST_LINK_TOPO_MOD_ID)
+		return -EIO;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_LINK_TOPO_MODULE_LEN,
+					&length);
+	if (err)
+		return err;
+
+	/* Sanity check that we have at least enough words to store the
+	 * netlist ID block.
+	 */
+	if (length < IXGBE_NETLIST_ID_BLK_SIZE)
+		return -EIO;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_LINK_TOPO_NODE_COUNT,
+					&node_count);
+	if (err)
+		return err;
+
+	node_count &= IXGBE_LINK_TOPO_NODE_COUNT_M;
+
+	id_blk = kcalloc(IXGBE_NETLIST_ID_BLK_SIZE, sizeof(*id_blk), GFP_KERNEL);
+	if (!id_blk)
+		return -ENOMEM;
+
+	/* Read out the entire Netlist ID Block at once. */
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_NETLIST_BANK_PTR,
+				      IXGBE_NETLIST_ID_BLK_OFFSET(node_count) *
+				      sizeof(*id_blk), (u8 *)id_blk,
+				      IXGBE_NETLIST_ID_BLK_SIZE *
+				      sizeof(*id_blk));
+	if (err)
+		goto free_id_blk;
+
+	for (i = 0; i < IXGBE_NETLIST_ID_BLK_SIZE; i++)
+		id_blk[i] = le16_to_cpu(((__le16 *)id_blk)[i]);
+
+	netlist->major = id_blk[IXGBE_NETLIST_ID_BLK_MAJOR_VER_HIGH] << 16 |
+			 id_blk[IXGBE_NETLIST_ID_BLK_MAJOR_VER_LOW];
+	netlist->minor = id_blk[IXGBE_NETLIST_ID_BLK_MINOR_VER_HIGH] << 16 |
+			 id_blk[IXGBE_NETLIST_ID_BLK_MINOR_VER_LOW];
+	netlist->type = id_blk[IXGBE_NETLIST_ID_BLK_TYPE_HIGH] << 16 |
+			id_blk[IXGBE_NETLIST_ID_BLK_TYPE_LOW];
+	netlist->rev = id_blk[IXGBE_NETLIST_ID_BLK_REV_HIGH] << 16 |
+		       id_blk[IXGBE_NETLIST_ID_BLK_REV_LOW];
+	netlist->cust_ver = id_blk[IXGBE_NETLIST_ID_BLK_CUST_VER];
+	/* Read the left most 4 bytes of SHA */
+	netlist->hash = id_blk[IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(15)] << 16 |
+			id_blk[IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(14)];
+
+free_id_blk:
+	kfree(id_blk);
+	return err;
+}
+
+/**
+ * ixgbe_get_inactive_netlist_ver - Read netlist version from the inactive bank
+ * @hw: pointer to the HW struct
+ * @netlist: pointer to netlist version info structure
+ *
+ * Read the netlist version data from the inactive netlist bank. Used to
+ * extract version data of a pending flash update in order to display the
+ * version data.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_netlist_ver(struct ixgbe_hw *hw,
+				   struct ixgbe_netlist_info *netlist)
+{
+	return ixgbe_get_netlist_info(hw, IXGBE_INACTIVE_FLASH_BANK, netlist);
+}
+
+/**
+ * ixgbe_get_flash_data - get flash data
+ * @hw: pointer to the HW struct
+ *
+ * Read and populate flash data such as Shadow RAM size,
+ * max_timeout and blank_nvm_mode
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_flash_data(struct ixgbe_hw *hw)
+{
+	struct ixgbe_flash_info *flash = &hw->flash;
+	u32 fla, gens_stat;
+	u8 sr_size;
+	int err;
+
+	/* The SR size is stored regardless of the NVM programming mode
+	 * as the blank mode may be used in the factory line.
+	 */
+	gens_stat = IXGBE_READ_REG(hw, GLNVM_GENS);
+	sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat);
+
+	/* Switching to words (sr_size contains power of 2) */
+	flash->sr_words = BIT(sr_size) * (SZ_1K / sizeof(u16));
+
+	/* Check if we are in the normal or blank NVM programming mode */
+	fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA);
+	if (fla & IXGBE_GLNVM_FLA_LOCKED_M) {
+		flash->blank_nvm_mode = false;
+	} else {
+		flash->blank_nvm_mode = true;
+		return -EIO;
+	}
+
+	err = ixgbe_discover_flash_size(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_determine_active_flash_banks(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_get_nvm_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				     &flash->nvm);
+	if (err)
+		return err;
+
+	err = ixgbe_get_orom_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				      &flash->orom);
+	if (err)
+		return err;
+
+	err = ixgbe_get_netlist_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				     &flash->netlist);
+	return err;
+}
+
+/**
+ * ixgbe_aci_nvm_update_empr - update NVM using EMPR
+ * @hw: pointer to the HW struct
+ *
+ * Force EMP reset using ACI command (0x0709). This command allows SW to
+ * request an EMPR to activate new FW.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_desc desc;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_update_empr);
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/* ixgbe_nvm_set_pkg_data - NVM set package data
+ * @hw: pointer to the HW struct
+ * @del_pkg_data_flag: If is set then the current pkg_data store by FW
+ *		       is deleted.
+ *		       If bit is set to 1, then buffer should be size 0.
+ * @data: pointer to buffer
+ * @length: length of the buffer
+ *
+ * Set package data using ACI command (0x070A).
+ * This command is equivalent to the reception of
+ * a PLDM FW Update GetPackageData cmd. This command should be sent
+ * as part of the NVM update as the first cmd in the flow.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag,
+			   u8 *data, u16 length)
+{
+	struct ixgbe_aci_cmd_nvm_pkg_data *cmd;
+	struct ixgbe_aci_desc desc;
+
+	if (length != 0 && !data)
+		return -EINVAL;
+
+	cmd = &desc.params.pkg_data;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_pkg_data);
+	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+
+	if (del_pkg_data_flag)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_PKG_DELETE;
+
+	return ixgbe_aci_send_cmd(hw, &desc, data, length);
+}
+
+/* ixgbe_nvm_pass_component_tbl - NVM pass component table
+ * @hw: pointer to the HW struct
+ * @data: pointer to buffer
+ * @length: length of the buffer
+ * @transfer_flag: parameter for determining stage of the update
+ * @comp_response: a pointer to the response from the 0x070B ACI.
+ * @comp_response_code: a pointer to the response code from the 0x070B ACI.
+ *
+ * Pass component table using ACI command (0x070B). This command is equivalent
+ * to the reception of a PLDM FW Update PassComponentTable cmd.
+ * This command should be sent once per component. It can be only sent after
+ * Set Package Data cmd and before actual update. FW will assume these
+ * commands are going to be sent until the TransferFlag is set to End or
+ * StartAndEnd.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length,
+				 u8 transfer_flag, u8 *comp_response,
+				 u8 *comp_response_code)
+{
+	struct ixgbe_aci_cmd_nvm_pass_comp_tbl *cmd;
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	if (!data || !comp_response || !comp_response_code)
+		return -EINVAL;
+
+	cmd = &desc.params.pass_comp_tbl;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc,
+					ixgbe_aci_opc_nvm_pass_component_tbl);
+	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+
+	cmd->transfer_flag = transfer_flag;
+	err = ixgbe_aci_send_cmd(hw, &desc, data, length);
+	if (!err) {
+		*comp_response = cmd->component_response;
+		*comp_response_code = cmd->component_response_code;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_read_sr_word_aci - Reads Shadow RAM via ACI
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @data: word read from the Shadow RAM
+ *
+ * Reads one 16 bit word from the Shadow RAM using ixgbe_read_flat_nvm.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_read_sr_word_aci(struct ixgbe_hw  *hw, u16 offset, u16 *data)
+{
+	u32 bytes = sizeof(u16);
+	u16 data_local;
+	int err;
+
+	err = ixgbe_read_flat_nvm(hw, offset * sizeof(u16), &bytes,
+				  (u8 *)&data_local, true);
+	if (err)
+		return err;
+
+	*data = data_local;
+	return 0;
+}
+
+/**
+ * ixgbe_read_flat_nvm - Read portion of NVM by flat offset
+ * @hw: pointer to the HW struct
+ * @offset: offset from beginning of NVM
+ * @length: (in) number of bytes to read; (out) number of bytes actually read
+ * @data: buffer to return data in (sized to fit the specified length)
+ * @read_shadow_ram: if true, read from shadow RAM instead of NVM
+ *
+ * Reads a portion of the NVM, as a flat memory space. This function correctly
+ * breaks read requests across Shadow RAM sectors, prevents Shadow RAM size
+ * from being exceeded in case of Shadow RAM read requests and ensures that no
+ * single read request exceeds the maximum 4KB read for a single admin command.
+ *
+ * Returns an error code on failure. Note that the data pointer may be
+ * partially updated if some reads succeed before a failure.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_read_flat_nvm(struct ixgbe_hw  *hw, u32 offset, u32 *length,
+			u8 *data, bool read_shadow_ram)
+{
+	u32 inlen = *length;
+	u32 bytes_read = 0;
+	bool last_cmd;
+	int err;
+
+	/* Verify the length of the read if this is for the Shadow RAM */
+	if (read_shadow_ram && ((offset + inlen) >
+				(hw->eeprom.word_size * 2u)))
+		return -EINVAL;
+
+	do {
+		u32 read_size, sector_offset;
+
+		/* ixgbe_aci_read_nvm cannot read more than 4KB at a time.
+		 * Additionally, a read from the Shadow RAM may not cross over
+		 * a sector boundary. Conveniently, the sector size is also 4KB.
+		 */
+		sector_offset = offset % IXGBE_ACI_MAX_BUFFER_SIZE;
+		read_size = min_t(u32,
+				  IXGBE_ACI_MAX_BUFFER_SIZE - sector_offset,
+				  inlen - bytes_read);
+
+		last_cmd = !(bytes_read + read_size < inlen);
+
+		/* ixgbe_aci_read_nvm takes the length as a u16. Our read_size
+		 * is calculated using a u32, but the IXGBE_ACI_MAX_BUFFER_SIZE
+		 * maximum size guarantees that it will fit within the 2 bytes.
+		 */
+		err = ixgbe_aci_read_nvm(hw, IXGBE_ACI_NVM_START_POINT,
+					 offset, (u16)read_size,
+					 data + bytes_read, last_cmd,
+					 read_shadow_ram);
+		if (err)
+			break;
+
+		bytes_read += read_size;
+		offset += read_size;
+	} while (!last_cmd);
+
+	*length = bytes_read;
+	return err;
+}
+
+/**
+ * ixgbe_read_sr_buf_aci - Read Shadow RAM buffer via ACI
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM words to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Read 16 bit words (data buf) from the Shadow RAM. Acquire/release the NVM
+ * ownership.
+ *
+ * Return: the operation exit code.
+ */
+int ixgbe_read_sr_buf_aci(struct ixgbe_hw *hw, u16 offset, u16 *words,
+			  u16 *data)
+{
+	u32 bytes = *words * 2;
+	int err;
+
+	err = ixgbe_read_flat_nvm(hw, offset * 2, &bytes, (u8 *)data, true);
+	if (err)
+		return err;
+
+	*words = bytes / 2;
+
+	for (int i = 0; i < *words; i++)
+		data[i] = le16_to_cpu(((__le16 *)data)[i]);
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_ee_aci_e610 - Read EEPROM word using the admin command.
+ * @hw: pointer to hardware structure
+ * @offset: offset of  word in the EEPROM to read
+ * @data: word read from the EEPROM
+ *
+ * Reads a 16 bit word from the EEPROM using the ACI.
+ * If the EEPROM params are not initialized, the function
+ * initialize them before proceeding with reading.
+ * The function acquires and then releases the NVM ownership.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data)
+{
+	int err;
+
+	if (hw->eeprom.type == ixgbe_eeprom_uninitialized) {
+		err = hw->eeprom.ops.init_params(hw);
+		if (err)
+			return err;
+	}
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_word_aci(hw, offset, data);
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_ee_aci_buffer_e610 - Read EEPROM words via ACI
+ * @hw: pointer to hardware structure
+ * @offset: offset of words in the EEPROM to read
+ * @words: number of words to read
+ * @data: words to read from the EEPROM
+ *
+ * Read 16 bit words from the EEPROM via the ACI. Initialize the EEPROM params
+ * prior to the read. Acquire/release the NVM ownership.
+ *
+ * Return: the operation exit code.
+ */
+int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset,
+				  u16 words, u16 *data)
+{
+	int err;
+
+	if (hw->eeprom.type == ixgbe_eeprom_uninitialized) {
+		err = hw->eeprom.ops.init_params(hw);
+		if (err)
+			return err;
+	}
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_buf_aci(hw, offset, &words, data);
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_validate_eeprom_checksum_e610 - Validate EEPROM checksum
+ * @hw: pointer to hardware structure
+ * @checksum_val: calculated checksum
+ *
+ * Performs checksum calculation and validates the EEPROM checksum. If the
+ * caller does not need checksum_val, the value can be NULL.
+ * If the EEPROM params are not initialized, the function
+ * initialize them before proceeding.
+ * The function acquires and then releases the NVM ownership.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val)
+{
+	int err;
+
+	if (hw->eeprom.type == ixgbe_eeprom_uninitialized) {
+		err = hw->eeprom.ops.init_params(hw);
+		if (err)
+			return err;
+	}
+
+	err = ixgbe_nvm_validate_checksum(hw);
+	if (err)
+		return err;
+
+	if (checksum_val) {
+		u16 tmp_checksum;
+
+		err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+		if (err)
+			return err;
+
+		err = ixgbe_read_sr_word_aci(hw, IXGBE_E610_SR_SW_CHECKSUM_WORD,
+					     &tmp_checksum);
+		ixgbe_release_nvm(hw);
+
+		if (!err)
+			*checksum_val = tmp_checksum;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbe_reset_hw_e610 - Perform hardware reset
+ * @hw: pointer to hardware structure
+ *
+ * Resets the hardware by resetting the transmit and receive units, masks
+ * and clears all interrupts, and performs a reset.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_reset_hw_e610(struct ixgbe_hw *hw)
+{
+	u32 swfw_mask = hw->phy.phy_semaphore_mask;
+	u32 ctrl, i;
+	int err;
+
+	/* Call adapter stop to disable tx/rx and clear interrupts */
+	err = hw->mac.ops.stop_adapter(hw);
+	if (err)
+		goto reset_hw_out;
+
+	/* Flush pending Tx transactions. */
+	ixgbe_clear_tx_pending(hw);
+
+	hw->phy.ops.init(hw);
+mac_reset_top:
+	err = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask);
+	if (err)
+		return -EBUSY;
+	ctrl = IXGBE_CTRL_RST;
+	ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL);
+	IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl);
+	IXGBE_WRITE_FLUSH(hw);
+	hw->mac.ops.release_swfw_sync(hw, swfw_mask);
+
+	/* Poll for reset bit to self-clear indicating reset is complete */
+	for (i = 0; i < 10; i++) {
+		udelay(1);
+		ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL);
+		if (!(ctrl & IXGBE_CTRL_RST_MASK))
+			break;
+	}
+
+	if (ctrl & IXGBE_CTRL_RST_MASK) {
+		struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter,
+							     hw);
+
+		err = -EIO;
+		netdev_err(adapter->netdev, "Reset polling failed to complete.");
+	}
+
+	/* Double resets are required for recovery from certain error
+	 * conditions. Between resets, it is necessary to stall to allow time
+	 * for any pending HW events to complete.
+	 */
+	msleep(100);
+	if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) {
+		hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED;
+		goto mac_reset_top;
+	}
+
+	/* Set the Rx packet buffer size. */
+	IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(0), GENMASK(18, 17));
+
+	/* Store the permanent mac address */
+	hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr);
+
+	/* Maximum number of Receive Address Registers. */
+#define IXGBE_MAX_NUM_RAR		128
+
+	/* Store MAC address from RAR0, clear receive address registers, and
+	 * clear the multicast table.  Also reset num_rar_entries to the
+	 * maximum number of Receive Address Registers, since we modify this
+	 * value when programming the SAN MAC address.
+	 */
+	hw->mac.num_rar_entries = IXGBE_MAX_NUM_RAR;
+	hw->mac.ops.init_rx_addrs(hw);
+
+	/* Initialize bus function number */
+	hw->mac.ops.set_lan_id(hw);
+
+reset_hw_out:
+	return err;
+}
+
+/**
+ * ixgbe_get_pfa_module_tlv - Read sub module TLV from NVM PFA
+ * @hw: pointer to hardware structure
+ * @module_tlv: pointer to module TLV to return
+ * @module_tlv_len: pointer to module TLV length to return
+ * @module_type: module type requested
+ *
+ * Find the requested sub module TLV type from the Preserved Field
+ * Area (PFA) and returns the TLV pointer and length. The caller can
+ * use these to read the variable length TLV value.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_pfa_module_tlv(struct ixgbe_hw *hw, u16 *module_tlv,
+				    u16 *module_tlv_len, u16 module_type)
+{
+	u16 pfa_len, pfa_ptr, pfa_end_ptr;
+	u16 next_tlv;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, IXGBE_E610_SR_PFA_PTR, &pfa_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_ee_aci_e610(hw, pfa_ptr, &pfa_len);
+	if (err)
+		return err;
+
+	/* Starting with first TLV after PFA length, iterate through the list
+	 * of TLVs to find the requested one.
+	 */
+	next_tlv = pfa_ptr + 1;
+	pfa_end_ptr = pfa_ptr + pfa_len;
+	while (next_tlv < pfa_end_ptr) {
+		u16 tlv_sub_module_type, tlv_len;
+
+		/* Read TLV type */
+		err = ixgbe_read_ee_aci_e610(hw, next_tlv,
+					     &tlv_sub_module_type);
+		if (err)
+			break;
+
+		/* Read TLV length */
+		err = ixgbe_read_ee_aci_e610(hw, next_tlv + 1, &tlv_len);
+		if (err)
+			break;
+
+		if (tlv_sub_module_type == module_type) {
+			if (tlv_len) {
+				*module_tlv = next_tlv;
+				*module_tlv_len = tlv_len;
+				return 0;
+			}
+			return -EIO;
+		}
+		/* Check next TLV, i.e. current TLV pointer + length + 2 words
+		 * (for current TLV's type and length).
+		 */
+		next_tlv = next_tlv + tlv_len + 2;
+	}
+	/* Module does not exist */
+	return -ENODATA;
+}
+
+/**
+ * ixgbe_read_pba_string_e610 - Read PBA string from NVM
+ * @hw: pointer to hardware structure
+ * @pba_num: stores the part number string from the NVM
+ * @pba_num_size: part number string buffer length
+ *
+ * Read the part number string from the NVM.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_pba_string_e610(struct ixgbe_hw *hw, u8 *pba_num,
+				      u32 pba_num_size)
+{
+	u16 pba_tlv, pba_tlv_len;
+	u16 pba_word, pba_size;
+	int err;
+
+	*pba_num = '\0';
+
+	err = ixgbe_get_pfa_module_tlv(hw, &pba_tlv, &pba_tlv_len,
+				       IXGBE_E610_SR_PBA_BLOCK_PTR);
+	if (err)
+		return err;
+
+	/* pba_size is the next word */
+	err = ixgbe_read_ee_aci_e610(hw, (pba_tlv + 2), &pba_size);
+	if (err)
+		return err;
+
+	if (pba_tlv_len < pba_size)
+		return -EINVAL;
+
+	/* Subtract one to get PBA word count (PBA Size word is included in
+	 * total size).
+	 */
+	pba_size--;
+
+	if (pba_num_size < (((u32)pba_size * 2) + 1))
+		return -EINVAL;
+
+	for (u16 i = 0; i < pba_size; i++) {
+		err = ixgbe_read_ee_aci_e610(hw, (pba_tlv + 2 + 1) + i,
+					     &pba_word);
+		if (err)
+			return err;
+
+		pba_num[(i * 2)] = FIELD_GET(IXGBE_E610_SR_PBA_BLOCK_MASK,
+					     pba_word);
+		pba_num[(i * 2) + 1] = pba_word & 0xFF;
+	}
+
+	pba_num[(pba_size * 2)] = '\0';
+
+	return err;
+}
+
+static const struct ixgbe_mac_operations mac_ops_e610 = {
+	.init_hw			= ixgbe_init_hw_generic,
+	.start_hw			= ixgbe_start_hw_e610,
+	.clear_hw_cntrs			= ixgbe_clear_hw_cntrs_generic,
+	.enable_rx_dma			= ixgbe_enable_rx_dma_generic,
+	.get_mac_addr			= ixgbe_get_mac_addr_generic,
+	.get_device_caps		= ixgbe_get_device_caps_generic,
+	.stop_adapter			= ixgbe_stop_adapter_generic,
+	.set_lan_id			= ixgbe_set_lan_id_multi_port_pcie,
+	.set_rxpba			= ixgbe_set_rxpba_generic,
+	.check_link			= ixgbe_check_link_e610,
+	.blink_led_start		= ixgbe_blink_led_start_X540,
+	.blink_led_stop			= ixgbe_blink_led_stop_X540,
+	.set_rar			= ixgbe_set_rar_generic,
+	.clear_rar			= ixgbe_clear_rar_generic,
+	.set_vmdq			= ixgbe_set_vmdq_generic,
+	.set_vmdq_san_mac		= ixgbe_set_vmdq_san_mac_generic,
+	.clear_vmdq			= ixgbe_clear_vmdq_generic,
+	.init_rx_addrs			= ixgbe_init_rx_addrs_generic,
+	.update_mc_addr_list		= ixgbe_update_mc_addr_list_generic,
+	.enable_mc			= ixgbe_enable_mc_generic,
+	.disable_mc			= ixgbe_disable_mc_generic,
+	.clear_vfta			= ixgbe_clear_vfta_generic,
+	.set_vfta			= ixgbe_set_vfta_generic,
+	.fc_enable			= ixgbe_fc_enable_generic,
+	.set_fw_drv_ver			= ixgbe_set_fw_drv_ver_x550,
+	.init_uta_tables		= ixgbe_init_uta_tables_generic,
+	.set_mac_anti_spoofing		= ixgbe_set_mac_anti_spoofing,
+	.set_vlan_anti_spoofing		= ixgbe_set_vlan_anti_spoofing,
+	.set_source_address_pruning	=
+				ixgbe_set_source_address_pruning_x550,
+	.set_ethertype_anti_spoofing	=
+				ixgbe_set_ethertype_anti_spoofing_x550,
+	.disable_rx_buff		= ixgbe_disable_rx_buff_generic,
+	.enable_rx_buff			= ixgbe_enable_rx_buff_generic,
+	.enable_rx			= ixgbe_enable_rx_generic,
+	.disable_rx			= ixgbe_disable_rx_e610,
+	.led_on				= ixgbe_led_on_generic,
+	.led_off			= ixgbe_led_off_generic,
+	.init_led_link_act		= ixgbe_init_led_link_act_generic,
+	.reset_hw			= ixgbe_reset_hw_e610,
+	.get_fw_ver                     = ixgbe_aci_get_fw_ver,
+	.get_media_type			= ixgbe_get_media_type_e610,
+	.setup_link			= ixgbe_setup_link_e610,
+	.fw_recovery_mode		= ixgbe_fw_recovery_mode_e610,
+	.fw_rollback_mode		= ixgbe_fw_rollback_mode_e610,
+	.get_nvm_ver			= ixgbe_get_active_nvm_ver,
+	.get_link_capabilities		= ixgbe_get_link_capabilities_e610,
+	.get_bus_info			= ixgbe_get_bus_info_generic,
+	.acquire_swfw_sync		= ixgbe_acquire_swfw_sync_X540,
+	.release_swfw_sync		= ixgbe_release_swfw_sync_X540,
+	.init_swfw_sync			= ixgbe_init_swfw_sync_X540,
+	.prot_autoc_read		= prot_autoc_read_generic,
+	.prot_autoc_write		= prot_autoc_write_generic,
+	.setup_fc			= ixgbe_setup_fc_e610,
+	.fc_autoneg			= ixgbe_fc_autoneg_e610,
+};
+
+static const struct ixgbe_phy_operations phy_ops_e610 = {
+	.init				= ixgbe_init_phy_ops_e610,
+	.identify			= ixgbe_identify_phy_e610,
+	.identify_sfp			= ixgbe_identify_module_e610,
+	.setup_link_speed		= ixgbe_setup_phy_link_speed_generic,
+	.setup_link			= ixgbe_setup_phy_link_e610,
+	.enter_lplu			= ixgbe_enter_lplu_e610,
+};
+
+static const struct ixgbe_eeprom_operations eeprom_ops_e610 = {
+	.read				= ixgbe_read_ee_aci_e610,
+	.read_buffer			= ixgbe_read_ee_aci_buffer_e610,
+	.validate_checksum		= ixgbe_validate_eeprom_checksum_e610,
+	.read_pba_string		= ixgbe_read_pba_string_e610,
+	.init_params			= ixgbe_init_eeprom_params_e610,
+};
+
+const struct ixgbe_info ixgbe_e610_info = {
+	.mac			= ixgbe_mac_e610,
+	.get_invariants		= ixgbe_get_invariants_X540,
+	.mac_ops		= &mac_ops_e610,
+	.eeprom_ops		= &eeprom_ops_e610,
+	.phy_ops		= &phy_ops_e610,
+	.mbx_ops		= &mbx_ops_generic,
+	.mvals			= ixgbe_mvals_x550em_a,
+};
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
new file mode 100644
index 000000000000..bb31d65bd1c8
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IXGBE_E610_H_
+#define _IXGBE_E610_H_
+
+#include "ixgbe_type.h"
+
+int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc,
+		       void *buf, u16 buf_size);
+bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw);
+int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e,
+			bool *pending);
+void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode);
+int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
+		      enum ixgbe_aci_res_access_type access, u32 timeout);
+void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res);
+int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size,
+			u32 *cap_count, enum ixgbe_aci_opc opc);
+int ixgbe_discover_dev_caps(struct ixgbe_hw *hw,
+			    struct ixgbe_hw_dev_caps *dev_caps);
+int ixgbe_discover_func_caps(struct ixgbe_hw *hw,
+			     struct ixgbe_hw_func_caps *func_caps);
+int ixgbe_get_caps(struct ixgbe_hw *hw);
+int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw);
+int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode,
+			   struct ixgbe_aci_cmd_get_phy_caps_data *pcaps);
+void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps,
+				struct ixgbe_aci_cmd_set_phy_cfg_data *cfg);
+int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw,
+			  struct ixgbe_aci_cmd_set_phy_cfg_data *cfg);
+int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link);
+int ixgbe_update_link_info(struct ixgbe_hw *hw);
+int ixgbe_get_link_status(struct ixgbe_hw *hw, bool *link_up);
+int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse,
+			    struct ixgbe_link_status *link);
+int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask);
+int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask);
+int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode);
+enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw);
+int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed,
+			  bool autoneg_wait);
+int ixgbe_check_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
+			  bool *link_up, bool link_up_wait_to_complete);
+int ixgbe_get_link_capabilities_e610(struct ixgbe_hw *hw,
+				     ixgbe_link_speed *speed,
+				     bool *autoneg);
+int ixgbe_cfg_phy_fc(struct ixgbe_hw *hw,
+		     struct ixgbe_aci_cmd_set_phy_cfg_data *cfg,
+		     enum ixgbe_fc_mode req_mode);
+int ixgbe_setup_fc_e610(struct ixgbe_hw *hw);
+void ixgbe_fc_autoneg_e610(struct ixgbe_hw *hw);
+void ixgbe_disable_rx_e610(struct ixgbe_hw *hw);
+int ixgbe_init_phy_ops_e610(struct ixgbe_hw *hw);
+int ixgbe_identify_phy_e610(struct ixgbe_hw *hw);
+int ixgbe_identify_module_e610(struct ixgbe_hw *hw);
+int ixgbe_setup_phy_link_e610(struct ixgbe_hw *hw);
+int ixgbe_set_phy_power_e610(struct ixgbe_hw *hw, bool on);
+int ixgbe_enter_lplu_e610(struct ixgbe_hw *hw);
+int ixgbe_init_eeprom_params_e610(struct ixgbe_hw *hw);
+int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw,
+			       struct ixgbe_aci_cmd_get_link_topo *cmd,
+			       u8 *node_part_number, u16 *node_handle);
+int ixgbe_acquire_nvm(struct ixgbe_hw *hw,
+		      enum ixgbe_aci_res_access_type access);
+void ixgbe_release_nvm(struct ixgbe_hw *hw);
+int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
+		       u16 length, void *data, bool last_command,
+		       bool read_shadow_ram);
+int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw);
+int ixgbe_get_inactive_orom_ver(struct ixgbe_hw *hw,
+				struct ixgbe_orom_info *orom);
+int ixgbe_get_inactive_nvm_ver(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm);
+int ixgbe_get_inactive_netlist_ver(struct ixgbe_hw *hw,
+				   struct ixgbe_netlist_info *netlist);
+int ixgbe_read_sr_word_aci(struct ixgbe_hw  *hw, u16 offset, u16 *data);
+int ixgbe_read_flat_nvm(struct ixgbe_hw  *hw, u32 offset, u32 *length,
+			u8 *data, bool read_shadow_ram);
+int ixgbe_read_sr_buf_aci(struct ixgbe_hw *hw, u16 offset, u16 *words,
+			  u16 *data);
+int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data);
+int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset,
+				  u16 words, u16 *data);
+int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val);
+int ixgbe_reset_hw_e610(struct ixgbe_hw *hw);
+int ixgbe_get_flash_data(struct ixgbe_hw *hw);
+int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw);
+int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag,
+			   u8 *data, u16 length);
+int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length,
+				 u8 transfer_flag, u8 *comp_response,
+				 u8 *comp_response_code);
+int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid);
+int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid,
+			 u32 offset, u16 length, void *data,
+			 bool last_command, u8 command_flags);
+int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags,
+			     u8 *response_flags);
+
+#endif /* _IXGBE_E610_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 9482e0cca8b7..d8a919ab7027 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 /* ethtool support for ixgbe */
 
@@ -213,7 +213,7 @@ static void ixgbe_set_advertising_10gtypes(struct ixgbe_hw *hw,
 static int ixgbe_get_link_ksettings(struct net_device *netdev,
 				    struct ethtool_link_ksettings *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	ixgbe_link_speed supported_link;
 	bool autoneg = false;
@@ -458,7 +458,7 @@ static int ixgbe_get_link_ksettings(struct net_device *netdev,
 static int ixgbe_set_link_ksettings(struct net_device *netdev,
 				    const struct ethtool_link_ksettings *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 advertised, old;
 	int err = 0;
@@ -535,7 +535,7 @@ static int ixgbe_set_link_ksettings(struct net_device *netdev,
 static void ixgbe_get_pause_stats(struct net_device *netdev,
 				  struct ethtool_pause_stats *stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw_stats *hwstats = &adapter->stats;
 
 	stats->tx_pause_frames = hwstats->lxontxc + hwstats->lxofftxc;
@@ -545,7 +545,7 @@ static void ixgbe_get_pause_stats(struct net_device *netdev,
 static void ixgbe_get_pauseparam(struct net_device *netdev,
 				 struct ethtool_pauseparam *pause)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (ixgbe_device_supports_autoneg_fc(hw) &&
@@ -564,10 +564,26 @@ static void ixgbe_get_pauseparam(struct net_device *netdev,
 	}
 }
 
+static void ixgbe_set_pauseparam_finalize(struct net_device *netdev,
+					  struct ixgbe_fc_info *fc)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	/* If the thing changed then we'll update and use new autoneg. */
+	if (memcmp(fc, &hw->fc, sizeof(*fc))) {
+		hw->fc = *fc;
+		if (netif_running(netdev))
+			ixgbe_reinit_locked(adapter);
+		else
+			ixgbe_reset(adapter);
+	}
+}
+
 static int ixgbe_set_pauseparam(struct net_device *netdev,
 				struct ethtool_pauseparam *pause)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_fc_info fc = hw->fc;
 
@@ -592,27 +608,52 @@ static int ixgbe_set_pauseparam(struct net_device *netdev,
 	else
 		fc.requested_mode = ixgbe_fc_none;
 
-	/* if the thing changed then we'll update and use new autoneg */
-	if (memcmp(&fc, &hw->fc, sizeof(struct ixgbe_fc_info))) {
-		hw->fc = fc;
-		if (netif_running(netdev))
-			ixgbe_reinit_locked(adapter);
-		else
-			ixgbe_reset(adapter);
+	ixgbe_set_pauseparam_finalize(netdev, &fc);
+
+	return 0;
+}
+
+static int ixgbe_set_pauseparam_e610(struct net_device *netdev,
+				     struct ethtool_pauseparam *pause)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_fc_info fc = hw->fc;
+
+	if (!ixgbe_device_supports_autoneg_fc(hw))
+		return -EOPNOTSUPP;
+
+	if (pause->autoneg == AUTONEG_DISABLE) {
+		netdev_info(netdev,
+			    "Cannot disable autonegotiation on this device.\n");
+		return -EOPNOTSUPP;
 	}
 
+	fc.disable_fc_autoneg = false;
+
+	if (pause->rx_pause && pause->tx_pause)
+		fc.requested_mode = ixgbe_fc_full;
+	else if (pause->rx_pause)
+		fc.requested_mode = ixgbe_fc_rx_pause;
+	else if (pause->tx_pause)
+		fc.requested_mode = ixgbe_fc_tx_pause;
+	else
+		fc.requested_mode = ixgbe_fc_none;
+
+	ixgbe_set_pauseparam_finalize(netdev, &fc);
+
 	return 0;
 }
 
 static u32 ixgbe_get_msglevel(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	return adapter->msg_enable;
 }
 
 static void ixgbe_set_msglevel(struct net_device *netdev, u32 data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	adapter->msg_enable = data;
 }
 
@@ -627,7 +668,7 @@ static int ixgbe_get_regs_len(struct net_device *netdev)
 static void ixgbe_get_regs(struct net_device *netdev,
 			   struct ethtool_regs *regs, void *p)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 *regs_buff = p;
 	u8 i;
@@ -690,6 +731,7 @@ static void ixgbe_get_regs(struct net_device *netdev,
 		case ixgbe_mac_X550:
 		case ixgbe_mac_X550EM_x:
 		case ixgbe_mac_x550em_a:
+		case ixgbe_mac_e610:
 			regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL_82599(i));
 			regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH_82599(i));
 			break;
@@ -993,14 +1035,14 @@ static void ixgbe_get_regs(struct net_device *netdev,
 
 static int ixgbe_get_eeprom_len(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	return adapter->hw.eeprom.word_size * 2;
 }
 
 static int ixgbe_get_eeprom(struct net_device *netdev,
 			    struct ethtool_eeprom *eeprom, u8 *bytes)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 *eeprom_buff;
 	int first_word, last_word, eeprom_len;
@@ -1036,7 +1078,7 @@ static int ixgbe_get_eeprom(struct net_device *netdev,
 static int ixgbe_set_eeprom(struct net_device *netdev,
 			    struct ethtool_eeprom *eeprom, u8 *bytes)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 *eeprom_buff;
 	void *ptr;
@@ -1103,10 +1145,22 @@ err:
 	return ret_val;
 }
 
+void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	ixgbe_get_flash_data(hw);
+	ixgbe_set_fw_version_e610(adapter);
+}
+
 static void ixgbe_get_drvinfo(struct net_device *netdev,
 			      struct ethtool_drvinfo *drvinfo)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+
+	/* need to refresh info for e610 in case fw reloads in runtime */
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		ixgbe_refresh_fw_version(adapter);
 
 	strscpy(drvinfo->driver, ixgbe_driver_name, sizeof(drvinfo->driver));
 
@@ -1160,7 +1214,7 @@ static void ixgbe_get_ringparam(struct net_device *netdev,
 				struct kernel_ethtool_ringparam *kernel_ring,
 				struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *tx_ring = adapter->tx_ring[0];
 	struct ixgbe_ring *rx_ring = adapter->rx_ring[0];
 
@@ -1175,7 +1229,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
 			       struct kernel_ethtool_ringparam *kernel_ring,
 			       struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *temp_ring;
 	int i, j, err = 0;
 	u32 new_rx_count, new_tx_count;
@@ -1335,7 +1389,7 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset)
 static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 				    struct ethtool_stats *stats, u64 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct rtnl_link_stats64 temp;
 	const struct rtnl_link_stats64 *net_stats;
 	unsigned int start;
@@ -1613,6 +1667,7 @@ static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		toggle = 0x7FFFF30F;
 		test = reg_test_82599;
 		break;
@@ -1708,7 +1763,7 @@ static int ixgbe_eeprom_test(struct ixgbe_adapter *adapter, u64 *data)
 static irqreturn_t ixgbe_test_intr(int irq, void *data)
 {
 	struct net_device *netdev = (struct net_device *) data;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->test_icr |= IXGBE_READ_REG(&adapter->hw, IXGBE_EICR);
 
@@ -1874,6 +1929,7 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_DMATXCTL);
 		reg_data |= IXGBE_DMATXCTL_TE;
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_DMATXCTL, reg_data);
@@ -1935,6 +1991,7 @@ static int ixgbe_setup_loopback_test(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		reg_data = IXGBE_READ_REG(hw, IXGBE_MACC);
 		reg_data |= IXGBE_MACC_FLU;
 		IXGBE_WRITE_REG(hw, IXGBE_MACC, reg_data);
@@ -2179,7 +2236,7 @@ out:
 static void ixgbe_diag_test(struct net_device *netdev,
 			    struct ethtool_test *eth_test, u64 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	bool if_running = netif_running(netdev);
 
 	if (ixgbe_removed(adapter->hw.hw_addr)) {
@@ -2302,7 +2359,7 @@ static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter,
 static void ixgbe_get_wol(struct net_device *netdev,
 			  struct ethtool_wolinfo *wol)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	wol->supported = WAKE_UCAST | WAKE_MCAST |
 			 WAKE_BCAST | WAKE_MAGIC;
@@ -2324,7 +2381,7 @@ static void ixgbe_get_wol(struct net_device *netdev,
 
 static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE |
 			    WAKE_FILTER))
@@ -2349,9 +2406,53 @@ static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	return 0;
 }
 
+static int ixgbe_set_wol_acpi(struct net_device *netdev,
+			      struct ethtool_wolinfo *wol)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 grc;
+
+	if (ixgbe_wol_exclusion(adapter, wol))
+		return wol->wolopts ? -EOPNOTSUPP : 0;
+
+	/* disable APM wakeup */
+	grc = IXGBE_READ_REG(hw, IXGBE_GRC_X550EM_a);
+	grc &= ~IXGBE_GRC_APME;
+	IXGBE_WRITE_REG(hw, IXGBE_GRC_X550EM_a, grc);
+
+	/* erase existing filters */
+	IXGBE_WRITE_REG(hw, IXGBE_WUFC, 0);
+	adapter->wol = 0;
+
+	if (wol->wolopts & WAKE_UCAST)
+		adapter->wol |= IXGBE_WUFC_EX;
+	if (wol->wolopts & WAKE_MCAST)
+		adapter->wol |= IXGBE_WUFC_MC;
+	if (wol->wolopts & WAKE_BCAST)
+		adapter->wol |= IXGBE_WUFC_BC;
+
+	IXGBE_WRITE_REG(hw, IXGBE_WUC, IXGBE_WUC_PME_EN);
+	IXGBE_WRITE_REG(hw, IXGBE_WUFC, adapter->wol);
+
+	hw->wol_enabled = adapter->wol;
+	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
+
+	return 0;
+}
+
+static int ixgbe_set_wol_e610(struct net_device *netdev,
+			      struct ethtool_wolinfo *wol)
+{
+	if (wol->wolopts & (WAKE_UCAST | WAKE_MCAST | WAKE_BCAST))
+		return ixgbe_set_wol_acpi(netdev, wol);
+	else
+		return ixgbe_set_wol(netdev, wol);
+}
+
 static int ixgbe_nway_reset(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (netif_running(netdev))
 		ixgbe_reinit_locked(adapter);
@@ -2362,7 +2463,7 @@ static int ixgbe_nway_reset(struct net_device *netdev)
 static int ixgbe_set_phys_id(struct net_device *netdev,
 			     enum ethtool_phys_id_state state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!hw->mac.ops.led_on || !hw->mac.ops.led_off)
@@ -2390,12 +2491,32 @@ static int ixgbe_set_phys_id(struct net_device *netdev,
 	return 0;
 }
 
+static int ixgbe_set_phys_id_e610(struct net_device *netdev,
+				  enum ethtool_phys_id_state state)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	bool led_active;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		led_active = true;
+		break;
+	case ETHTOOL_ID_INACTIVE:
+		led_active = false;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ixgbe_aci_set_port_id_led(&adapter->hw, !led_active);
+}
+
 static int ixgbe_get_coalesce(struct net_device *netdev,
 			      struct ethtool_coalesce *ec,
 			      struct kernel_ethtool_coalesce *kernel_coal,
 			      struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* only valid if in constant ITR mode */
 	if (adapter->rx_itr_setting <= 1)
@@ -2451,7 +2572,7 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
 			      struct kernel_ethtool_coalesce *kernel_coal,
 			      struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_q_vector *q_vector;
 	int i;
 	u16 tx_itr_param, rx_itr_param, tx_itr_prev;
@@ -2677,7 +2798,7 @@ static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter)
 static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			   u32 *rule_locs)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
@@ -3065,7 +3186,7 @@ static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter,
 
 static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
@@ -3092,7 +3213,7 @@ static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev)
 
 static u32 ixgbe_rss_indir_size(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return ixgbe_rss_indir_tbl_entries(adapter);
 }
@@ -3112,7 +3233,7 @@ static void ixgbe_get_reta(struct ixgbe_adapter *adapter, u32 *indir)
 static int ixgbe_get_rxfh(struct net_device *netdev,
 			  struct ethtool_rxfh_param *rxfh)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
@@ -3130,7 +3251,7 @@ static int ixgbe_set_rxfh(struct net_device *netdev,
 			  struct ethtool_rxfh_param *rxfh,
 			  struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i;
 	u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
 
@@ -3172,7 +3293,7 @@ static int ixgbe_set_rxfh(struct net_device *netdev,
 static int ixgbe_get_ts_info(struct net_device *dev,
 			     struct kernel_ethtool_ts_info *info)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	/* we always support timestamping disabled */
 	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE);
@@ -3181,6 +3302,7 @@ static int ixgbe_get_ts_info(struct net_device *dev,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL);
 		break;
 	case ixgbe_mac_X540:
@@ -3247,7 +3369,7 @@ static unsigned int ixgbe_max_channels(struct ixgbe_adapter *adapter)
 static void ixgbe_get_channels(struct net_device *dev,
 			       struct ethtool_channels *ch)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	/* report maximum channels */
 	ch->max_combined = ixgbe_max_channels(adapter);
@@ -3284,7 +3406,7 @@ static void ixgbe_get_channels(struct net_device *dev,
 static int ixgbe_set_channels(struct net_device *dev,
 			      struct ethtool_channels *ch)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	unsigned int count = ch->combined_count;
 	u8 max_rss_indices = ixgbe_max_rss_indices(adapter);
 
@@ -3322,7 +3444,7 @@ static int ixgbe_set_channels(struct net_device *dev,
 static int ixgbe_get_module_info(struct net_device *dev,
 				       struct ethtool_modinfo *modinfo)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u8 sff8472_rev, addr_mode;
 	bool page_swap = false;
@@ -3368,7 +3490,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev,
 					 struct ethtool_eeprom *ee,
 					 u8 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	int status = -EFAULT;
 	u8 databyte = 0xFF;
@@ -3464,7 +3586,7 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata)
 
 static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE))
@@ -3478,7 +3600,7 @@ static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 
 static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ethtool_keee eee_data;
 	int ret_val;
@@ -3533,7 +3655,7 @@ static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata)
 
 static u32 ixgbe_get_priv_flags(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	u32 priv_flags = 0;
 
 	if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
@@ -3550,7 +3672,7 @@ static u32 ixgbe_get_priv_flags(struct net_device *netdev)
 
 static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	unsigned int flags2 = adapter->flags2;
 	unsigned int i;
 
@@ -3633,7 +3755,57 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.set_link_ksettings     = ixgbe_set_link_ksettings,
 };
 
+static const struct ethtool_ops ixgbe_ethtool_ops_e610 = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
+	.get_drvinfo            = ixgbe_get_drvinfo,
+	.get_regs_len           = ixgbe_get_regs_len,
+	.get_regs               = ixgbe_get_regs,
+	.get_wol                = ixgbe_get_wol,
+	.set_wol                = ixgbe_set_wol_e610,
+	.nway_reset             = ixgbe_nway_reset,
+	.get_link               = ethtool_op_get_link,
+	.get_eeprom_len         = ixgbe_get_eeprom_len,
+	.get_eeprom             = ixgbe_get_eeprom,
+	.set_eeprom             = ixgbe_set_eeprom,
+	.get_ringparam          = ixgbe_get_ringparam,
+	.set_ringparam          = ixgbe_set_ringparam,
+	.get_pause_stats	= ixgbe_get_pause_stats,
+	.get_pauseparam         = ixgbe_get_pauseparam,
+	.set_pauseparam         = ixgbe_set_pauseparam_e610,
+	.get_msglevel           = ixgbe_get_msglevel,
+	.set_msglevel           = ixgbe_set_msglevel,
+	.self_test              = ixgbe_diag_test,
+	.get_strings            = ixgbe_get_strings,
+	.set_phys_id            = ixgbe_set_phys_id_e610,
+	.get_sset_count         = ixgbe_get_sset_count,
+	.get_ethtool_stats      = ixgbe_get_ethtool_stats,
+	.get_coalesce           = ixgbe_get_coalesce,
+	.set_coalesce           = ixgbe_set_coalesce,
+	.get_rxnfc		= ixgbe_get_rxnfc,
+	.set_rxnfc		= ixgbe_set_rxnfc,
+	.get_rxfh_indir_size	= ixgbe_rss_indir_size,
+	.get_rxfh_key_size	= ixgbe_get_rxfh_key_size,
+	.get_rxfh		= ixgbe_get_rxfh,
+	.set_rxfh		= ixgbe_set_rxfh,
+	.get_eee		= ixgbe_get_eee,
+	.set_eee		= ixgbe_set_eee,
+	.get_channels		= ixgbe_get_channels,
+	.set_channels		= ixgbe_set_channels,
+	.get_priv_flags		= ixgbe_get_priv_flags,
+	.set_priv_flags		= ixgbe_set_priv_flags,
+	.get_ts_info		= ixgbe_get_ts_info,
+	.get_module_info	= ixgbe_get_module_info,
+	.get_module_eeprom	= ixgbe_get_module_eeprom,
+	.get_link_ksettings     = ixgbe_get_link_ksettings,
+	.set_link_ksettings     = ixgbe_set_link_ksettings,
+};
+
 void ixgbe_set_ethtool_ops(struct net_device *netdev)
 {
-	netdev->ethtool_ops = &ixgbe_ethtool_ops;
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		netdev->ethtool_ops = &ixgbe_ethtool_ops_e610;
+	else
+		netdev->ethtool_ops = &ixgbe_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index 955dced844a9..7dcf6ecd157b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -56,7 +56,7 @@ int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid)
 	if (xid >= netdev->fcoe_ddp_xid)
 		return 0;
 
-	adapter = netdev_priv(netdev);
+	adapter = ixgbe_from_netdev(netdev);
 	fcoe = &adapter->fcoe;
 	ddp = &fcoe->ddp[xid];
 	if (!ddp->udl)
@@ -153,7 +153,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid,
 	if (!netdev || !sgl)
 		return 0;
 
-	adapter = netdev_priv(netdev);
+	adapter = ixgbe_from_netdev(netdev);
 	if (xid >= netdev->fcoe_ddp_xid) {
 		e_warn(drv, "xid=0x%x out-of-range\n", xid);
 		return 0;
@@ -834,7 +834,7 @@ static void ixgbe_fcoe_ddp_disable(struct ixgbe_adapter *adapter)
  */
 int ixgbe_fcoe_enable(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_fcoe *fcoe = &adapter->fcoe;
 
 	atomic_inc(&fcoe->refcnt);
@@ -881,7 +881,7 @@ int ixgbe_fcoe_enable(struct net_device *netdev)
  */
 int ixgbe_fcoe_disable(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (!atomic_dec_and_test(&adapter->fcoe.refcnt))
 		return -EINVAL;
@@ -927,7 +927,7 @@ int ixgbe_fcoe_disable(struct net_device *netdev)
 int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type)
 {
 	u16 prefix = 0xffff;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_mac_info *mac = &adapter->hw.mac;
 
 	switch (type) {
@@ -967,7 +967,7 @@ int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type)
 int ixgbe_fcoe_get_hbainfo(struct net_device *netdev,
 			   struct netdev_fcoe_hbainfo *info)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u64 dsn;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
new file mode 100644
index 000000000000..49d3b66add7e
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
@@ -0,0 +1,707 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2025 Intel Corporation. */
+
+#include <linux/crc32.h>
+#include <linux/pldmfw.h>
+#include <linux/uuid.h>
+
+#include "ixgbe.h"
+#include "ixgbe_fw_update.h"
+
+struct ixgbe_fwu_priv {
+	struct pldmfw context;
+
+	struct ixgbe_adapter *adapter;
+	struct netlink_ext_ack *extack;
+
+	/* Track which NVM banks to activate at the end of the update */
+	u8 activate_flags;
+	bool emp_reset_available;
+};
+
+/**
+ * ixgbe_send_package_data - Send record package data to firmware
+ * @context: PLDM fw update structure
+ * @data: pointer to the package data
+ * @length: length of the package data
+ *
+ * Send a copy of the package data associated with the PLDM record matching
+ * this device to the firmware.
+ *
+ * Note that this function sends an AdminQ command that will fail unless the
+ * NVM resource has been acquired.
+ *
+ * Return: zero on success, or a negative error code on failure.
+ */
+static int ixgbe_send_package_data(struct pldmfw *context,
+				   const u8 *data, u16 length)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 *package_data;
+	int err;
+
+	package_data = kmemdup(data, length, GFP_KERNEL);
+	if (!package_data)
+		return -ENOMEM;
+
+	err = ixgbe_nvm_set_pkg_data(hw, false, package_data, length);
+
+	kfree(package_data);
+
+	return err;
+}
+
+/**
+ * ixgbe_check_component_response - Report firmware response to a component
+ * @adapter: device private data structure
+ * @response: indicates whether this component can be updated
+ * @code: code indicating reason for response
+ * @extack: netlink extended ACK structure
+ *
+ * Check whether firmware indicates if this component can be updated. Report
+ * a suitable error message over the netlink extended ACK if the component
+ * cannot be updated.
+ *
+ * Return: 0 if the component can be updated, or -ECANCELED if the
+ * firmware indicates the component cannot be updated.
+ */
+static int ixgbe_check_component_response(struct ixgbe_adapter *adapter,
+					  u8 response, u8 code,
+					  struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	switch (response) {
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED:
+		/* Firmware indicated this update is good to proceed. */
+		return 0;
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware recommends not updating, as it may result in a downgrade. Continuing anyways");
+		return 0;
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_NOT_BE_UPDATED:
+		NL_SET_ERR_MSG_MOD(extack, "Firmware has rejected updating.");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_PARTIAL_CHECK:
+		if (hw->mac.ops.fw_recovery_mode &&
+		    hw->mac.ops.fw_recovery_mode(hw))
+			return 0;
+		break;
+	}
+
+	switch (code) {
+	case IXGBE_ACI_NVM_PASS_COMP_STAMP_IDENTICAL_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is identical to running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_STAMP_LOWER:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is lower than running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_INVALID_STAMP_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is invalid");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_CONFLICT_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component table conflict occurred");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component pre-requisites not met");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_NOT_SUPPORTED_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component not supported");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component cannot be downgraded");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Incomplete component image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component version is identical to running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_VER_STR_LOWER_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component version is lower than the running image");
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Received unexpected response code from firmware");
+		break;
+	}
+
+	return -ECANCELED;
+}
+
+/**
+ * ixgbe_send_component_table - Send PLDM component table to firmware
+ * @context: PLDM fw update structure
+ * @component: the component to process
+ * @transfer_flag: relative transfer order of this component
+ *
+ * Read relevant data from the component and forward it to the device
+ * firmware. Check the response to determine if the firmware indicates that
+ * the update can proceed.
+ *
+ * This function sends ACI commands related to the NVM, and assumes that
+ * the NVM resource has been acquired.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_send_component_table(struct pldmfw *context,
+				      struct pldmfw_component *component,
+				      u8 transfer_flag)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct netlink_ext_ack *extack = priv->extack;
+	struct ixgbe_aci_cmd_nvm_comp_tbl *comp_tbl;
+	u8 comp_response, comp_response_code;
+	struct ixgbe_hw *hw = &adapter->hw;
+	size_t length;
+	int err;
+
+	switch (component->identifier) {
+	case NVM_COMP_ID_OROM:
+	case NVM_COMP_ID_NVM:
+	case NVM_COMP_ID_NETLIST:
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to update due to unknown firmware component");
+		return -EOPNOTSUPP;
+	}
+
+	length = struct_size(comp_tbl, cvs, component->version_len);
+	comp_tbl = kzalloc(length, GFP_KERNEL);
+	if (!comp_tbl)
+		return -ENOMEM;
+
+	comp_tbl->comp_class = cpu_to_le16(component->classification);
+	comp_tbl->comp_id = cpu_to_le16(component->identifier);
+	comp_tbl->comp_class_idx = FWU_COMP_CLASS_IDX_NOT_USE;
+	comp_tbl->comp_cmp_stamp = cpu_to_le32(component->comparison_stamp);
+	comp_tbl->cvs_type = component->version_type;
+	comp_tbl->cvs_len = component->version_len;
+
+	memcpy(comp_tbl->cvs, component->version_string,
+	       component->version_len);
+
+	err = ixgbe_nvm_pass_component_tbl(hw, (u8 *)comp_tbl, length,
+					   transfer_flag, &comp_response,
+					   &comp_response_code);
+
+	kfree(comp_tbl);
+
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to transfer component table to firmware");
+		return -EIO;
+	}
+
+	return ixgbe_check_component_response(adapter,
+					      comp_response,
+					      comp_response_code, extack);
+}
+
+/**
+ * ixgbe_write_one_nvm_block - Write an NVM block and await completion response
+ * @adapter: the PF data structure
+ * @module: the module to write to
+ * @offset: offset in bytes
+ * @block_size: size of the block to write, up to 4k
+ * @block: pointer to block of data to write
+ * @last_cmd: whether this is the last command
+ * @extack: netlink extended ACK structure
+ *
+ * Write a block of data to a flash module, and await for the completion
+ * response message from firmware.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * On successful return, reset level indicates the device reset required to
+ * complete the update.
+ *
+ *   0 - IXGBE_ACI_NVM_POR_FLAG - A full power on is required
+ *   1 - IXGBE_ACI_NVM_PERST_FLAG - A cold PCIe reset is required
+ *   2 - IXGBE_ACI_NVM_EMPR_FLAG - An EMP reset is required
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_write_one_nvm_block(struct ixgbe_adapter *adapter,
+				     u16 module, u32 offset,
+				     u16 block_size, u8 *block, bool last_cmd,
+				     struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	return ixgbe_aci_update_nvm(hw, module, offset, block_size, block,
+				    last_cmd, 0);
+}
+
+/**
+ * ixgbe_write_nvm_module - Write data to an NVM module
+ * @adapter: the PF driver structure
+ * @module: the module id to program
+ * @component: the name of the component being updated
+ * @image: buffer of image data to write to the NVM
+ * @length: length of the buffer
+ * @extack: netlink extended ACK structure
+ *
+ * Loop over the data for a given NVM module and program it in 4 Kb
+ * blocks. Notify devlink core of progress after each block is programmed.
+ * Loops over a block of data and programs the NVM in 4k block chunks.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_write_nvm_module(struct ixgbe_adapter *adapter, u16 module,
+				  const char *component, const u8 *image,
+				  u32 length,
+				  struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	u32 offset = 0;
+	bool last_cmd;
+	u8 *block;
+	int err;
+
+	devlink_flash_update_status_notify(devlink, "Flashing",
+					   component, 0, length);
+
+	block = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!block)
+		return -ENOMEM;
+
+	do {
+		u32 block_size;
+
+		block_size = min_t(u32, IXGBE_ACI_MAX_BUFFER_SIZE,
+				   length - offset);
+		last_cmd = !(offset + block_size < length);
+
+		memcpy(block, image + offset, block_size);
+
+		err = ixgbe_write_one_nvm_block(adapter, module, offset,
+						block_size, block, last_cmd,
+						extack);
+		if (err)
+			break;
+
+		offset += block_size;
+
+		devlink_flash_update_status_notify(devlink, "Flashing",
+						   component, offset, length);
+	} while (!last_cmd);
+
+	if (err)
+		devlink_flash_update_status_notify(devlink, "Flashing failed",
+						   component, length, length);
+	else
+		devlink_flash_update_status_notify(devlink, "Flashing done",
+						   component, length, length);
+
+	kfree(block);
+
+	return err;
+}
+
+/* Length in seconds to wait before timing out when erasing a flash module.
+ * Yes, erasing really can take minutes to complete.
+ */
+#define IXGBE_FW_ERASE_TIMEOUT 300
+
+/**
+ * ixgbe_erase_nvm_module - Erase an NVM module and await firmware completion
+ * @adapter: the PF data structure
+ * @module: the module to erase
+ * @component: name of the component being updated
+ * @extack: netlink extended ACK structure
+ *
+ * Erase the inactive NVM bank associated with this module, and await for
+ * a completion response message from firmware.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_erase_nvm_module(struct ixgbe_adapter *adapter, u16 module,
+				  const char *component,
+				  struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	devlink_flash_update_timeout_notify(devlink, "Erasing", component,
+					    IXGBE_FW_ERASE_TIMEOUT);
+
+	err = ixgbe_aci_erase_nvm(hw, module);
+	if (err)
+		devlink_flash_update_status_notify(devlink, "Erasing failed",
+						   component, 0, 0);
+	else
+		devlink_flash_update_status_notify(devlink, "Erasing done",
+						   component, 0, 0);
+
+	return err;
+}
+
+/**
+ * ixgbe_switch_flash_banks - Tell firmware to switch NVM banks
+ * @adapter: Pointer to the PF data structure
+ * @activate_flags: flags used for the activation command
+ * @emp_reset_available: on return, indicates if EMP reset is available
+ * @extack: netlink extended ACK structure
+ *
+ * Notify firmware to activate the newly written flash banks, and wait for the
+ * firmware response.
+ *
+ * Return: 0 on success or an error code on failure.
+ */
+static int ixgbe_switch_flash_banks(struct ixgbe_adapter *adapter,
+				    u8 activate_flags,
+				    bool *emp_reset_available,
+				    struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 response_flags;
+	int err;
+
+	err = ixgbe_nvm_write_activate(hw, activate_flags, &response_flags);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to switch active flash banks");
+		return err;
+	}
+
+	if (emp_reset_available) {
+		if (hw->dev_caps.common_cap.reset_restrict_support)
+			*emp_reset_available =
+				response_flags & IXGBE_ACI_NVM_EMPR_ENA;
+		else
+			*emp_reset_available = true;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_flash_component - Flash a component of the NVM
+ * @context: PLDM fw update structure
+ * @component: the component table to program
+ *
+ * Program the flash contents for a given component. First, determine the
+ * module id. Then, erase the secondary bank for this module. Finally, write
+ * the contents of the component to the NVM.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_flash_component(struct pldmfw *context,
+				 struct pldmfw_component *component)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct netlink_ext_ack *extack = priv->extack;
+	struct ixgbe_adapter *adapter = priv->adapter;
+	const char *name;
+	u16 module;
+	int err;
+	u8 flag;
+
+	switch (component->identifier) {
+	case NVM_COMP_ID_OROM:
+		module = IXGBE_E610_SR_1ST_OROM_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+		name = "fw.undi";
+		break;
+	case NVM_COMP_ID_NVM:
+		module = IXGBE_E610_SR_1ST_NVM_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+		name = "fw.mgmt";
+		break;
+	case NVM_COMP_ID_NETLIST:
+		module = IXGBE_E610_SR_NETLIST_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+		name = "fw.netlist";
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Mark this component for activating at the end. */
+	priv->activate_flags |= flag;
+
+	err = ixgbe_erase_nvm_module(adapter, module, name, extack);
+	if (err)
+		return err;
+
+	return ixgbe_write_nvm_module(adapter, module, name,
+				      component->component_data,
+				      component->component_size, extack);
+}
+
+/**
+ * ixgbe_finalize_update - Perform last steps to complete device update
+ * @context: PLDM fw update structure
+ *
+ * Called as the last step of the update process. Complete the update by
+ * telling the firmware to switch active banks, and perform a reset of
+ * configured.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
+static int ixgbe_finalize_update(struct pldmfw *context)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct netlink_ext_ack *extack = priv->extack;
+	struct devlink *devlink = adapter->devlink;
+	int err;
+
+	/* Finally, notify firmware to activate the written NVM banks */
+	err = ixgbe_switch_flash_banks(adapter, priv->activate_flags,
+				       &priv->emp_reset_available, extack);
+	if (err)
+		return err;
+
+	adapter->fw_emp_reset_disabled = !priv->emp_reset_available;
+
+	if (!adapter->fw_emp_reset_disabled)
+		devlink_flash_update_status_notify(devlink,
+						   "Suggested is to activate new firmware by devlink reload, if it doesn't work then a power cycle is required",
+						   NULL, 0, 0);
+
+	return 0;
+}
+
+static const struct pldmfw_ops ixgbe_fwu_ops_e610 = {
+	.match_record = &pldmfw_op_pci_match_record,
+	.send_package_data = &ixgbe_send_package_data,
+	.send_component_table = &ixgbe_send_component_table,
+	.flash_component = &ixgbe_flash_component,
+	.finalize_update = &ixgbe_finalize_update,
+};
+
+/**
+ * ixgbe_get_pending_updates - Check if the component has a pending update
+ * @adapter: the PF driver structure
+ * @pending: on return, bitmap of updates pending
+ * @extack: Netlink extended ACK
+ *
+ * Check if the device has any pending updates on any flash components.
+ *
+ * Return: 0 on success, or a negative error code on failure. Update
+ * pending with the bitmap of pending updates.
+ */
+int ixgbe_get_pending_updates(struct ixgbe_adapter *adapter, u8 *pending,
+			      struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw_dev_caps *dev_caps;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	dev_caps = kzalloc(sizeof(*dev_caps), GFP_KERNEL);
+	if (!dev_caps)
+		return -ENOMEM;
+
+	err = ixgbe_discover_dev_caps(hw, dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to read device capabilities");
+		kfree(dev_caps);
+		return -EIO;
+	}
+
+	*pending = 0;
+
+	if (dev_caps->common_cap.nvm_update_pending_nvm)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+
+	if (dev_caps->common_cap.nvm_update_pending_orom)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+
+	if (dev_caps->common_cap.nvm_update_pending_netlist)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+
+	kfree(dev_caps);
+
+	return 0;
+}
+
+/**
+ * ixgbe_cancel_pending_update - Cancel any pending update for a component
+ * @adapter: the PF driver structure
+ * @component: if not NULL, the name of the component being updated
+ * @extack: Netlink extended ACK structure
+ *
+ * Cancel any pending update for the specified component. If component is
+ * NULL, all device updates will be canceled.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_cancel_pending_update(struct ixgbe_adapter *adapter,
+				       const char *component,
+				       struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 pending;
+	int err;
+
+	err = ixgbe_get_pending_updates(adapter, &pending, extack);
+	if (err)
+		return err;
+
+	/* If the flash_update request is for a specific component, ignore all
+	 * of the other components.
+	 */
+	if (component) {
+		if (strcmp(component, "fw.mgmt") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+		else if (strcmp(component, "fw.undi") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+		else if (strcmp(component, "fw.netlist") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+		else
+			return -EINVAL;
+	}
+
+	/* There is no previous pending update, so this request may continue */
+	if (!pending)
+		return 0;
+
+	/* In order to allow overwriting a previous pending update, notify
+	 * firmware to cancel that update by issuing the appropriate command.
+	 */
+	devlink_flash_update_status_notify(devlink,
+					   "Canceling previous pending update",
+					   component, 0, 0);
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_WRITE);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to acquire device flash lock");
+		return -EIO;
+	}
+
+	pending |= IXGBE_ACI_NVM_REVERT_LAST_ACTIV;
+	err = ixgbe_switch_flash_banks(adapter, pending, NULL, extack);
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_flash_pldm_image - Write a PLDM-formatted firmware image to the device
+ * @devlink: pointer to devlink associated with the device to update
+ * @params: devlink flash update parameters
+ * @extack: netlink extended ACK structure
+ *
+ * Parse the data for a given firmware file, verifying that it is a valid PLDM
+ * formatted image that matches this device.
+ *
+ * Extract the device record Package Data and Component Tables and send them
+ * to the firmware. Extract and write the flash data for each of the three
+ * main flash components, "fw.mgmt", "fw.undi", and "fw.netlist". Notify
+ * firmware once the data is written to the inactive banks.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int ixgbe_flash_pldm_image(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct device *dev = &adapter->pdev->dev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_fwu_priv priv;
+	u8 preservation;
+	int err;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return -EOPNOTSUPP;
+
+	switch (params->overwrite_mask) {
+	case 0:
+		/* preserve all settings and identifiers */
+		preservation = IXGBE_ACI_NVM_PRESERVE_ALL;
+		break;
+	case DEVLINK_FLASH_OVERWRITE_SETTINGS:
+		/* Overwrite settings, but preserve vital information such as
+		 * device identifiers.
+		 */
+		preservation = IXGBE_ACI_NVM_PRESERVE_SELECTED;
+		break;
+	case (DEVLINK_FLASH_OVERWRITE_SETTINGS |
+	      DEVLINK_FLASH_OVERWRITE_IDENTIFIERS):
+		/* overwrite both settings and identifiers, preserve nothing */
+		preservation = IXGBE_ACI_NVM_NO_PRESERVATION;
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Requested overwrite mask is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	/* Cannot get caps in recovery mode, so lack of nvm_unified_update bit
+	 * cannot lead to error
+	 */
+	if (!hw->dev_caps.common_cap.nvm_unified_update &&
+	    (hw->mac.ops.fw_recovery_mode &&
+	     !hw->mac.ops.fw_recovery_mode(hw))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Current firmware does not support unified update");
+		return -EOPNOTSUPP;
+	}
+
+	memset(&priv, 0, sizeof(priv));
+
+	priv.context.ops = &ixgbe_fwu_ops_e610;
+	priv.context.dev = dev;
+	priv.extack = extack;
+	priv.adapter = adapter;
+	priv.activate_flags = preservation;
+
+	devlink_flash_update_status_notify(devlink,
+					   "Preparing to flash", NULL, 0, 0);
+
+	err = ixgbe_cancel_pending_update(adapter, NULL, extack);
+	if (err)
+		return err;
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_WRITE);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to acquire device flash lock");
+		return -EIO;
+	}
+
+	err = pldmfw_flash_image(&priv.context, params->fw);
+	if (err == -ENOENT) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware image has no record matching this device");
+	} else if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to flash PLDM image");
+	}
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h
new file mode 100644
index 000000000000..abdd708c93df
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2025 Intel Corporation. */
+
+#ifndef _IXGBE_FW_UPDATE_H_
+#define _IXGBE_FW_UPDATE_H_
+
+int ixgbe_flash_pldm_image(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack);
+int ixgbe_get_pending_updates(struct ixgbe_adapter *adapter, u8 *pending,
+			      struct netlink_ext_ack *extack);
+#endif
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 866024f2b9ee..d1f4073b36f9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -9,7 +9,7 @@
 #define IXGBE_IPSEC_KEY_BITS  160
 static const char aes_gcm_name[] = "rfc4106(gcm(aes))";
 
-static void ixgbe_ipsec_del_sa(struct xfrm_state *xs);
+static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs);
 
 /**
  * ixgbe_ipsec_set_tx_sa - set the Tx SA registers
@@ -321,7 +321,7 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter)
 
 		if (r->used) {
 			if (r->mode & IXGBE_RXTXMOD_VF)
-				ixgbe_ipsec_del_sa(r->xs);
+				ixgbe_ipsec_del_sa(adapter->netdev, r->xs);
 			else
 				ixgbe_ipsec_set_rx_sa(hw, i, r->xs->id.spi,
 						      r->key, r->salt,
@@ -330,7 +330,7 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter)
 
 		if (t->used) {
 			if (t->mode & IXGBE_RXTXMOD_VF)
-				ixgbe_ipsec_del_sa(t->xs);
+				ixgbe_ipsec_del_sa(adapter->netdev, t->xs);
 			else
 				ixgbe_ipsec_set_tx_sa(hw, i, t->key, t->salt);
 		}
@@ -417,6 +417,7 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec,
 
 /**
  * ixgbe_ipsec_parse_proto_keys - find the key and salt based on the protocol
+ * @dev: pointer to net device
  * @xs: pointer to xfrm_state struct
  * @mykey: pointer to key array to populate
  * @mysalt: pointer to salt value to populate
@@ -424,10 +425,10 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec,
  * This copies the protocol keys and salt to our own data tables.  The
  * 82599 family only supports the one algorithm.
  **/
-static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs,
+static int ixgbe_ipsec_parse_proto_keys(struct net_device *dev,
+					struct xfrm_state *xs,
 					u32 *mykey, u32 *mysalt)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	unsigned char *key_data;
 	char *alg_name = NULL;
 	int key_len;
@@ -473,12 +474,13 @@ static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs,
 
 /**
  * ixgbe_ipsec_check_mgmt_ip - make sure there is no clash with mgmt IP filters
+ * @dev: pointer to net device
  * @xs: pointer to transformer state struct
  **/
-static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
+static int ixgbe_ipsec_check_mgmt_ip(struct net_device *dev,
+				     struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 mfval, manc, reg;
 	int num_filters = 4;
@@ -556,14 +558,15 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
 
 /**
  * ixgbe_ipsec_add_sa - program device with a security association
+ * @dev: pointer to device to program
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
  **/
-static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
+static int ixgbe_ipsec_add_sa(struct net_device *dev,
+			      struct xfrm_state *xs,
 			      struct netlink_ext_ack *extack)
 {
-	struct net_device *dev = xs->xso.real_dev;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
 	int checked, match, first;
@@ -581,7 +584,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 		return -EINVAL;
 	}
 
-	if (ixgbe_ipsec_check_mgmt_ip(xs)) {
+	if (ixgbe_ipsec_check_mgmt_ip(dev, xs)) {
 		NL_SET_ERR_MSG_MOD(extack, "IPsec IP addr clash with mgmt filters");
 		return -EINVAL;
 	}
@@ -615,7 +618,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 			rsa.decrypt = xs->ealg || xs->aead;
 
 		/* get the key and salt */
-		ret = ixgbe_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt);
+		ret = ixgbe_ipsec_parse_proto_keys(dev, xs, rsa.key, &rsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Rx SA table");
 			return ret;
@@ -724,7 +727,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 		if (xs->id.proto & IPPROTO_ESP)
 			tsa.encrypt = xs->ealg || xs->aead;
 
-		ret = ixgbe_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt);
+		ret = ixgbe_ipsec_parse_proto_keys(dev, xs, tsa.key, &tsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Tx SA table");
 			memset(&tsa, 0, sizeof(tsa));
@@ -752,12 +755,12 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 
 /**
  * ixgbe_ipsec_del_sa - clear out this specific SA
+ * @dev: pointer to device to program
  * @xs: pointer to transformer state struct
  **/
-static void ixgbe_ipsec_del_sa(struct xfrm_state *xs)
+static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 zerobuf[4] = {0, 0, 0, 0};
@@ -817,30 +820,9 @@ static void ixgbe_ipsec_del_sa(struct xfrm_state *xs)
 	}
 }
 
-/**
- * ixgbe_ipsec_offload_ok - can this packet use the xfrm hw offload
- * @skb: current data packet
- * @xs: pointer to transformer state struct
- **/
-static bool ixgbe_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
-{
-	if (xs->props.family == AF_INET) {
-		/* Offload with IPv4 options is not supported yet */
-		if (ip_hdr(skb)->ihl != 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-
-	return true;
-}
-
 static const struct xfrmdev_ops ixgbe_xfrmdev_ops = {
 	.xdo_dev_state_add = ixgbe_ipsec_add_sa,
 	.xdo_dev_state_delete = ixgbe_ipsec_del_sa,
-	.xdo_dev_offload_ok = ixgbe_ipsec_offload_ok,
 };
 
 /**
@@ -862,7 +844,8 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
 			continue;
 		if (ipsec->rx_tbl[i].mode & IXGBE_RXTXMOD_VF &&
 		    ipsec->rx_tbl[i].vf == vf)
-			ixgbe_ipsec_del_sa(ipsec->rx_tbl[i].xs);
+			ixgbe_ipsec_del_sa(adapter->netdev,
+					   ipsec->rx_tbl[i].xs);
 	}
 
 	/* search tx sa table */
@@ -871,7 +854,8 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
 			continue;
 		if (ipsec->tx_tbl[i].mode & IXGBE_RXTXMOD_VF &&
 		    ipsec->tx_tbl[i].vf == vf)
-			ixgbe_ipsec_del_sa(ipsec->tx_tbl[i].xs);
+			ixgbe_ipsec_del_sa(adapter->netdev,
+					   ipsec->tx_tbl[i].xs);
 	}
 }
 
@@ -951,7 +935,7 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 	memcpy(xs->aead->alg_name, aes_gcm_name, sizeof(aes_gcm_name));
 
 	/* set up the HW offload */
-	err = ixgbe_ipsec_add_sa(xs, NULL);
+	err = ixgbe_ipsec_add_sa(adapter->netdev, xs, NULL);
 	if (err)
 		goto err_aead;
 
@@ -1055,7 +1039,7 @@ int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 		xs = ipsec->tx_tbl[sa_idx].xs;
 	}
 
-	ixgbe_ipsec_del_sa(xs);
+	ixgbe_ipsec_del_sa(adapter->netdev, xs);
 
 	/* remove the xs that was made-up in the add request */
 	kfree_sensitive(xs);
@@ -1073,7 +1057,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 		   struct ixgbe_tx_buffer *first,
 		   struct ixgbe_ipsec_tx_data *itd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(tx_ring->netdev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct xfrm_state *xs;
 	struct sec_path *sp;
@@ -1163,7 +1147,7 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
 		    union ixgbe_adv_rx_desc *rx_desc,
 		    struct sk_buff *skb)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(rx_ring->netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(rx_ring->netdev);
 	__le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
 	__le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH |
 					     IXGBE_RXDADV_PKTTYPE_IPSEC_ESP);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 16fa621ce0ff..336d47ffb95a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include "ixgbe.h"
 #include "ixgbe_sriov.h"
@@ -107,6 +107,7 @@ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (num_tcs > 4) {
 			/*
 			 * TCs    : TC0/1 TC2/3 TC4-7
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2e38e8f6fac1..cba860f0e1f1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/types.h>
 #include <linux/module.h>
@@ -42,12 +42,14 @@
 
 #include "ixgbe.h"
 #include "ixgbe_common.h"
+#include "ixgbe_e610.h"
 #include "ixgbe_dcb_82599.h"
 #include "ixgbe_mbx.h"
 #include "ixgbe_phy.h"
 #include "ixgbe_sriov.h"
 #include "ixgbe_model.h"
 #include "ixgbe_txrx_common.h"
+#include "devlink/devlink.h"
 
 char ixgbe_driver_name[] = "ixgbe";
 static const char ixgbe_driver_string[] =
@@ -73,6 +75,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = {
 	[board_x550em_x_fw]	= &ixgbe_x550em_x_fw_info,
 	[board_x550em_a]	= &ixgbe_x550em_a_info,
 	[board_x550em_a_fw]	= &ixgbe_x550em_a_fw_info,
+	[board_e610]		= &ixgbe_e610_info,
 };
 
 /* ixgbe_pci_tbl - PCI Device ID Table
@@ -131,6 +134,11 @@ static const struct pci_device_id ixgbe_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw },
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_BACKPLANE), board_e610},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SFP), board_e610},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_10G_T), board_e610},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_2_5G_T), board_e610},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SGMII), board_e610},
 	/* required last entry */
 	{0, }
 };
@@ -173,6 +181,8 @@ static struct workqueue_struct *ixgbe_wq;
 
 static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev);
 static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *);
+static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *);
+static void ixgbe_watchdog_update_link(struct ixgbe_adapter *);
 
 static const struct net_device_ops ixgbe_netdev_ops;
 
@@ -236,8 +246,11 @@ static int ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter)
  * bandwidth details should be gathered from the parent bus instead of from the
  * device. Used to ensure that various locations all have the correct device ID
  * checks.
+ *
+ * Return: true if information should be collected from the parent bus, false
+ *         otherwise
  */
-static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw)
+static bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw)
 {
 	switch (hw->device_id) {
 	case IXGBE_DEV_ID_82599_SFP_SF_QP:
@@ -876,6 +889,7 @@ static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (direction == -1) {
 			/* other causes */
 			msix_vector |= IXGBE_IVAR_ALLOC_VAL;
@@ -915,6 +929,7 @@ void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		mask = (qmask & 0xFFFFFFFF);
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask);
 		mask = (qmask >> 32);
@@ -1025,7 +1040,7 @@ static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
 	return ((head <= tail) ? tail : tail + ring->count) - head;
 }
 
-static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
+static bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
 {
 	u32 tx_done = ixgbe_get_tx_completed(tx_ring);
 	u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
@@ -1081,7 +1096,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
 static int ixgbe_tx_maxrate(struct net_device *netdev,
 			    int queue_index, u32 maxrate)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 bcnrc_val = ixgbe_link_mbps(adapter);
 
@@ -1909,10 +1924,6 @@ bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
 {
 	struct net_device *netdev = rx_ring->netdev;
 
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	/* Verify netdev is present, and that packet does not have any
 	 * errors that would be unacceptable to the netdev.
 	 */
@@ -2095,7 +2106,7 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring,
 		/* hand second half of page back to the ring */
 		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
-		if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) {
+		if (skb && IXGBE_CB(skb)->dma == rx_buffer->dma) {
 			/* the page has been released from the ring */
 			IXGBE_CB(skb)->page_released = true;
 		} else {
@@ -2220,9 +2231,9 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	return skb;
 }
 
-static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
-				     struct ixgbe_ring *rx_ring,
-				     struct xdp_buff *xdp)
+static int ixgbe_run_xdp(struct ixgbe_adapter *adapter,
+			 struct ixgbe_ring *rx_ring,
+			 struct xdp_buff *xdp)
 {
 	int err, result = IXGBE_XDP_PASS;
 	struct bpf_prog *xdp_prog;
@@ -2272,7 +2283,7 @@ out_failure:
 		break;
 	}
 xdp_out:
-	return ERR_PTR(-result);
+	return result;
 }
 
 static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring,
@@ -2330,6 +2341,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int offset = rx_ring->rx_offset;
 	unsigned int xdp_xmit = 0;
 	struct xdp_buff xdp;
+	int xdp_res = 0;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)
@@ -2375,12 +2387,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
 			xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size);
 #endif
-			skb = ixgbe_run_xdp(adapter, rx_ring, &xdp);
+			xdp_res = ixgbe_run_xdp(adapter, rx_ring, &xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			unsigned int xdp_res = -PTR_ERR(skb);
-
+		if (xdp_res) {
 			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
 				xdp_xmit |= xdp_res;
 				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
@@ -2400,7 +2410,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		}
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
 			rx_buffer->pagecnt_bias++;
 			break;
@@ -2414,7 +2424,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			continue;
 
 		/* verify the packet layout is correct */
-		if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb))
+		if (xdp_res || ixgbe_cleanup_headers(rx_ring, rx_desc, skb))
 			continue;
 
 		/* probably a little skewed due to removing CRC */
@@ -2515,6 +2525,7 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		ixgbe_set_ivar(adapter, -1, 1, v_idx);
 		break;
 	default:
@@ -2528,6 +2539,9 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
 		  IXGBE_EIMS_MAILBOX |
 		  IXGBE_EIMS_LSC);
 
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		mask &= ~IXGBE_EIMS_FW_EVENT;
+
 	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask);
 }
 
@@ -2744,6 +2758,7 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/*
 		 * set the WDIS bit to not clear the timer bits and cause an
 		 * immediate assertion of the interrupt
@@ -2966,6 +2981,222 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
 	}
 }
 
+/**
+ * ixgbe_check_phy_fw_load - check if PHY FW load failed
+ * @adapter: pointer to adapter structure
+ * @link_cfg_err: bitmap from the link info structure
+ *
+ * Check if external PHY FW load failed and print an error message if it did.
+ */
+static void ixgbe_check_phy_fw_load(struct ixgbe_adapter *adapter,
+				    u8 link_cfg_err)
+{
+	if (!(link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE)) {
+		adapter->flags2 &= ~IXGBE_FLAG2_PHY_FW_LOAD_FAILED;
+		return;
+	}
+
+	if (adapter->flags2 & IXGBE_FLAG2_PHY_FW_LOAD_FAILED)
+		return;
+
+	if (link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE) {
+		netdev_err(adapter->netdev, "Device failed to load the FW for the external PHY. Please download and install the latest NVM for your device and try again\n");
+		adapter->flags2 |= IXGBE_FLAG2_PHY_FW_LOAD_FAILED;
+	}
+}
+
+/**
+ * ixgbe_check_module_power - check module power level
+ * @adapter: pointer to adapter structure
+ * @link_cfg_err: bitmap from the link info structure
+ *
+ * Check module power level returned by a previous call to aci_get_link_info
+ * and print error messages if module power level is not supported.
+ */
+static void ixgbe_check_module_power(struct ixgbe_adapter *adapter,
+				     u8 link_cfg_err)
+{
+	/* If module power level is supported, clear the flag. */
+	if (!(link_cfg_err & (IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT |
+			      IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED))) {
+		adapter->flags2 &= ~IXGBE_FLAG2_MOD_POWER_UNSUPPORTED;
+		return;
+	}
+
+	/* If IXGBE_FLAG2_MOD_POWER_UNSUPPORTED was previously set and the
+	 * above block didn't clear this bit, there's nothing to do.
+	 */
+	if (adapter->flags2 & IXGBE_FLAG2_MOD_POWER_UNSUPPORTED)
+		return;
+
+	if (link_cfg_err & IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT) {
+		netdev_err(adapter->netdev, "The installed module is incompatible with the device's NVM image. Cannot start link.\n");
+		adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED;
+	} else if (link_cfg_err & IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED) {
+		netdev_err(adapter->netdev, "The module's power requirements exceed the device's power supply. Cannot start link.\n");
+		adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED;
+	}
+}
+
+/**
+ * ixgbe_check_link_cfg_err - check if link configuration failed
+ * @adapter: pointer to adapter structure
+ * @link_cfg_err: bitmap from the link info structure
+ *
+ * Print if any link configuration failure happens due to the value in the
+ * link_cfg_err parameter in the link info structure.
+ */
+static void ixgbe_check_link_cfg_err(struct ixgbe_adapter *adapter,
+				     u8 link_cfg_err)
+{
+	ixgbe_check_module_power(adapter, link_cfg_err);
+	ixgbe_check_phy_fw_load(adapter, link_cfg_err);
+}
+
+/**
+ * ixgbe_process_link_status_event - process the link event
+ * @adapter: pointer to adapter structure
+ * @link_up: true if the physical link is up and false if it is down
+ * @link_speed: current link speed received from the link event
+ *
+ * Return: 0 on success or negative value on failure.
+ */
+static int
+ixgbe_process_link_status_event(struct ixgbe_adapter *adapter, bool link_up,
+				u16 link_speed)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int status;
+
+	/* Update the link info structures and re-enable link events,
+	 * don't bail on failure due to other book keeping needed.
+	 */
+	status = ixgbe_update_link_info(hw);
+	if (status)
+		e_dev_err("Failed to update link status, err %d aq_err %d\n",
+			  status, hw->aci.last_status);
+
+	ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err);
+
+	/* Check if the link state is up after updating link info, and treat
+	 * this event as an UP event since the link is actually UP now.
+	 */
+	if (hw->link.link_info.link_info & IXGBE_ACI_LINK_UP)
+		link_up = true;
+
+	/* Turn off PHY if media was removed. */
+	if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA) &&
+	    !(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE))
+		adapter->flags2 |= IXGBE_FLAG2_NO_MEDIA;
+
+	if (link_up == adapter->link_up &&
+	    link_up == netif_carrier_ok(adapter->netdev) &&
+	    link_speed == adapter->link_speed)
+		return 0;
+
+	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
+	adapter->link_check_timeout = jiffies;
+	ixgbe_watchdog_update_link(adapter);
+
+	if (link_up)
+		ixgbe_watchdog_link_is_up(adapter);
+	else
+		ixgbe_watchdog_link_is_down(adapter);
+
+	return 0;
+}
+
+/**
+ * ixgbe_handle_link_status_event - handle link status event via ACI
+ * @adapter: pointer to adapter structure
+ * @e: event structure containing link status info
+ */
+static void
+ixgbe_handle_link_status_event(struct ixgbe_adapter *adapter,
+			       struct ixgbe_aci_event *e)
+{
+	struct ixgbe_aci_cmd_get_link_status_data *link_data;
+	u16 link_speed;
+	bool link_up;
+
+	link_data = (struct ixgbe_aci_cmd_get_link_status_data *)e->msg_buf;
+
+	link_up = !!(link_data->link_info & IXGBE_ACI_LINK_UP);
+	link_speed = le16_to_cpu(link_data->link_speed);
+
+	if (ixgbe_process_link_status_event(adapter, link_up, link_speed))
+		e_dev_warn("Could not process link status event");
+}
+
+/**
+ * ixgbe_schedule_fw_event - schedule Firmware event
+ * @adapter: pointer to the adapter structure
+ *
+ * If the adapter is not in down, removing or resetting state,
+ * an event is scheduled.
+ */
+static void ixgbe_schedule_fw_event(struct ixgbe_adapter *adapter)
+{
+	if (!test_bit(__IXGBE_DOWN, &adapter->state) &&
+	    !test_bit(__IXGBE_REMOVING, &adapter->state) &&
+	    !test_bit(__IXGBE_RESETTING, &adapter->state)) {
+		adapter->flags2 |= IXGBE_FLAG2_FW_ASYNC_EVENT;
+		ixgbe_service_event_schedule(adapter);
+	}
+}
+
+/**
+ * ixgbe_aci_event_cleanup - release msg_buf memory
+ * @event: pointer to the event holding msg_buf to be released
+ *
+ * Clean memory allocated for event's msg_buf. Implements auto memory cleanup.
+ */
+static void ixgbe_aci_event_cleanup(struct ixgbe_aci_event *event)
+{
+	kfree(event->msg_buf);
+}
+
+/**
+ * ixgbe_handle_fw_event - handle Firmware event
+ * @adapter: pointer to the adapter structure
+ *
+ * Obtain an event from the ACI and then and then process it according to the
+ * type of the event and the opcode.
+ */
+static void ixgbe_handle_fw_event(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_aci_event event __cleanup(ixgbe_aci_event_cleanup);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool pending = false;
+	int err;
+
+	if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT)
+		adapter->flags2 &= ~IXGBE_FLAG2_FW_ASYNC_EVENT;
+	event.buf_len = IXGBE_ACI_MAX_BUFFER_SIZE;
+	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
+	if (!event.msg_buf)
+		return;
+
+	do {
+		err = ixgbe_aci_get_event(hw, &event, &pending);
+		if (err)
+			break;
+
+		switch (le16_to_cpu(event.desc.opcode)) {
+		case ixgbe_aci_opc_get_link_status:
+			ixgbe_handle_link_status_event(adapter, &event);
+			break;
+		case ixgbe_aci_opc_temp_tca_event:
+			e_crit(drv, "%s\n", ixgbe_overheat_msg);
+			ixgbe_down(adapter);
+			break;
+		default:
+			e_warn(hw, "unknown FW async event captured\n");
+			break;
+		}
+	} while (pending);
+}
+
 static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
 					   u64 qmask)
 {
@@ -2982,6 +3213,7 @@ static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		mask = (qmask & 0xFFFFFFFF);
 		if (mask)
 			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask);
@@ -3035,6 +3267,9 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_e610:
+		mask |= IXGBE_EIMS_FW_EVENT;
+		fallthrough;
 	case ixgbe_mac_x550em_a:
 		if (adapter->hw.device_id == IXGBE_DEV_ID_X550EM_X_SFP ||
 		    adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP ||
@@ -3091,12 +3326,16 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data)
 	if (eicr & IXGBE_EICR_MAILBOX)
 		ixgbe_msg_task(adapter);
 
+	if (eicr & IXGBE_EICR_FW_EVENT)
+		ixgbe_schedule_fw_event(adapter);
+
 	switch (hw->mac.type) {
 	case ixgbe_mac_82599EB:
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (hw->phy.type == ixgbe_phy_x550em_ext_t &&
 		    (eicr & IXGBE_EICR_GPI_SDP0_X540)) {
 			adapter->flags2 |= IXGBE_FLAG2_PHY_INTERRUPT;
@@ -3334,6 +3573,9 @@ static irqreturn_t ixgbe_intr(int irq, void *data)
 	if (eicr & IXGBE_EICR_LSC)
 		ixgbe_check_lsc(adapter);
 
+	if (eicr & IXGBE_EICR_FW_EVENT)
+		ixgbe_schedule_fw_event(adapter);
+
 	switch (hw->mac.type) {
 	case ixgbe_mac_82599EB:
 		ixgbe_check_sfp_event(adapter, eicr);
@@ -3342,6 +3584,7 @@ static irqreturn_t ixgbe_intr(int irq, void *data)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (eicr & IXGBE_EICR_ECC) {
 			e_info(link, "Received ECC Err, initiating reset\n");
 			set_bit(__IXGBE_RESET_REQUESTED, &adapter->state);
@@ -3442,6 +3685,7 @@ static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000);
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0);
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0);
@@ -4359,6 +4603,7 @@ static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		if (adapter->num_vfs)
 			rdrxctl |= IXGBE_RDRXCTL_PSP;
 		fallthrough;
@@ -4434,7 +4679,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
 static int ixgbe_vlan_rx_add_vid(struct net_device *netdev,
 				 __be16 proto, u16 vid)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* add VID to filter table */
@@ -4493,7 +4738,7 @@ void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid)
 static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev,
 				  __be16 proto, u16 vid)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* remove VID from filter table */
@@ -4526,6 +4771,7 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		for (i = 0; i < adapter->num_rx_queues; i++) {
 			struct ixgbe_ring *ring = adapter->rx_ring[i];
 
@@ -4564,6 +4810,7 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		for (i = 0; i < adapter->num_rx_queues; i++) {
 			struct ixgbe_ring *ring = adapter->rx_ring[i];
 
@@ -4716,7 +4963,7 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter)
  **/
 static int ixgbe_write_mc_addr_list(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!netif_running(netdev))
@@ -4892,7 +5139,7 @@ int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter,
 
 static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int ret;
 
 	ret = ixgbe_add_mac_filter(adapter, addr, VMDQ_P(0));
@@ -4902,7 +5149,7 @@ static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
 
 static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	ixgbe_del_mac_filter(adapter, addr, VMDQ_P(0));
 
@@ -4920,7 +5167,7 @@ static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr)
  **/
 void ixgbe_set_rx_mode(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE;
 	netdev_features_t features = netdev->features;
@@ -5022,7 +5269,7 @@ static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter)
 
 static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct udp_tunnel_info ti;
 
@@ -5148,6 +5395,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		dv_id = IXGBE_DV_X540(link, tc);
 		break;
 	default:
@@ -5208,6 +5456,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		dv_id = IXGBE_LOW_DV_X540(tc);
 		break;
 	default:
@@ -5510,6 +5759,48 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_enable_link_status_events - enable link status events
+ * @adapter: pointer to the adapter structure
+ * @mask: event mask to be set
+ *
+ * Enables link status events by invoking ixgbe_configure_lse()
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_enable_link_status_events(struct ixgbe_adapter *adapter,
+					   u16 mask)
+{
+	int err;
+
+	err = ixgbe_configure_lse(&adapter->hw, true, mask);
+	if (err)
+		return err;
+
+	adapter->lse_mask = mask;
+	return 0;
+}
+
+/**
+ * ixgbe_disable_link_status_events - disable link status events
+ * @adapter: pointer to the adapter structure
+ *
+ * Disables link status events by invoking ixgbe_configure_lse()
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_disable_link_status_events(struct ixgbe_adapter *adapter)
+{
+	int err;
+
+	err = ixgbe_configure_lse(&adapter->hw, false, adapter->lse_mask);
+	if (err)
+		return err;
+
+	adapter->lse_mask = 0;
+	return 0;
+}
+
+/**
  * ixgbe_sfp_link_config - set up SFP+ link
  * @adapter: pointer to private adapter struct
  **/
@@ -5532,13 +5823,21 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter)
  * ixgbe_non_sfp_link_config - set up non-SFP+ link
  * @hw: pointer to private hardware struct
  *
- * Returns 0 on success, negative on failure
+ * Configure non-SFP link.
+ *
+ * Return: 0 on success, negative on failure
  **/
 static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 {
-	u32 speed;
+	struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter,
+						     hw);
+	u16 mask = ~((u16)(IXGBE_ACI_LINK_EVENT_UPDOWN |
+			   IXGBE_ACI_LINK_EVENT_MEDIA_NA |
+			   IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL |
+			   IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL));
 	bool autoneg, link_up = false;
 	int ret = -EIO;
+	u32 speed;
 
 	if (hw->mac.ops.check_link)
 		ret = hw->mac.ops.check_link(hw, &speed, &link_up, false);
@@ -5561,13 +5860,53 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 	if (ret)
 		return ret;
 
-	if (hw->mac.ops.setup_link)
+	if (hw->mac.ops.setup_link) {
+		if (adapter->hw.mac.type == ixgbe_mac_e610) {
+			ret = ixgbe_enable_link_status_events(adapter, mask);
+			if (ret)
+				return ret;
+		}
 		ret = hw->mac.ops.setup_link(hw, speed, link_up);
+	}
 
 	return ret;
 }
 
 /**
+ * ixgbe_check_media_subtask - check for media
+ * @adapter: pointer to adapter structure
+ *
+ * If media is available then initialize PHY user configuration. Configure the
+ * PHY if the interface is up.
+ */
+static void ixgbe_check_media_subtask(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	/* No need to check for media if it's already present */
+	if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA))
+		return;
+
+	/* Refresh link info and check if media is present */
+	if (ixgbe_update_link_info(hw))
+		return;
+
+	ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err);
+
+	if (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE) {
+		/* PHY settings are reset on media insertion, reconfigure
+		 * PHY to preserve settings.
+		 */
+		if (!(ixgbe_non_sfp_link_config(&adapter->hw)))
+			adapter->flags2 &= ~IXGBE_FLAG2_NO_MEDIA;
+
+		/* A Link Status Event will be generated; the event handler
+		 * will complete bringing the interface up
+		 */
+	}
+}
+
+/**
  * ixgbe_clear_vf_stats_counters - Clear out VF stats after reset
  * @adapter: board private structure
  *
@@ -5630,6 +5969,7 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
 		case ixgbe_mac_X550:
 		case ixgbe_mac_X550EM_x:
 		case ixgbe_mac_x550em_a:
+		case ixgbe_mac_e610:
 		default:
 			IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF);
 			IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF);
@@ -5980,6 +6320,7 @@ dma_engine_disable:
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
 				(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
 				 ~IXGBE_DMATXCTL_TE));
@@ -6198,7 +6539,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	adapter->flags2 &= ~IXGBE_FLAG2_FDIR_REQUIRES_REINIT;
 	adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE;
 
-	del_timer_sync(&adapter->service_timer);
+	timer_delete_sync(&adapter->service_timer);
 
 	if (adapter->num_vfs) {
 		/* Clear EITR Select mapping */
@@ -6224,6 +6565,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 
 	ixgbe_clean_all_tx_rings(adapter);
 	ixgbe_clean_all_rx_rings(adapter);
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		ixgbe_disable_link_status_events(adapter);
 }
 
 /**
@@ -6258,7 +6601,7 @@ static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter)
  **/
 static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* Do the reset outside of interrupt context */
 	ixgbe_tx_timeout_reset(adapter);
@@ -6279,6 +6622,7 @@ static void ixgbe_init_dcb(struct ixgbe_adapter *adapter)
 		break;
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		adapter->dcb_cfg.num_tcs.pg_tcs = X540_TRAFFIC_CLASS;
 		adapter->dcb_cfg.num_tcs.pfc_tcs = X540_TRAFFIC_CLASS;
 		break;
@@ -6342,6 +6686,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	hw->subsystem_vendor_id = pdev->subsystem_vendor;
 	hw->subsystem_device_id = pdev->subsystem_device;
 
+	hw->mac.max_link_up_time = IXGBE_LINK_UP_TIME;
+
 	/* get_invariants needs the device IDs */
 	ii->get_invariants(hw);
 
@@ -6504,7 +6850,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK;
 
 	/* initialize eeprom parameters */
-	if (ixgbe_init_eeprom_params_generic(hw)) {
+	if (hw->eeprom.ops.init_params(hw)) {
 		e_dev_err("EEPROM initialization failed\n");
 		return -EIO;
 	}
@@ -6820,7 +7166,7 @@ static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter)
  **/
 static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (ixgbe_enabled_xdp_adapter(adapter)) {
 		int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD;
@@ -6867,7 +7213,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
  **/
 int ixgbe_open(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	int err, queues;
 
@@ -6909,6 +7255,19 @@ int ixgbe_open(struct net_device *netdev)
 	ixgbe_up_complete(adapter);
 
 	udp_tunnel_nic_reset_ntf(netdev);
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		int err = ixgbe_update_link_info(&adapter->hw);
+
+		if (err)
+			e_dev_err("Failed to update link info, err %d.\n", err);
+
+		ixgbe_check_link_cfg_err(adapter,
+					 adapter->hw.link.link_info.link_cfg_err);
+
+		err = ixgbe_non_sfp_link_config(&adapter->hw);
+		if (ixgbe_non_sfp_link_config(&adapter->hw))
+			e_dev_err("Link setup failed, err %d.\n", err);
+	}
 
 	return 0;
 
@@ -6958,7 +7317,7 @@ static void ixgbe_close_suspend(struct ixgbe_adapter *adapter)
  **/
 int ixgbe_close(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	ixgbe_ptp_stop(adapter);
 
@@ -7062,6 +7421,7 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		pci_wake_from_d3(pdev, !!wufc);
 		break;
 	default:
@@ -7209,6 +7569,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 		case ixgbe_mac_X550:
 		case ixgbe_mac_X550EM_x:
 		case ixgbe_mac_x550em_a:
+		case ixgbe_mac_e610:
 			hwstats->pxonrxc[i] +=
 				IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i));
 			break;
@@ -7221,11 +7582,12 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	for (i = 0; i < 16; i++) {
 		hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i));
 		hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i));
-		if ((hw->mac.type == ixgbe_mac_82599EB) ||
-		    (hw->mac.type == ixgbe_mac_X540) ||
-		    (hw->mac.type == ixgbe_mac_X550) ||
-		    (hw->mac.type == ixgbe_mac_X550EM_x) ||
-		    (hw->mac.type == ixgbe_mac_x550em_a)) {
+		if (hw->mac.type == ixgbe_mac_82599EB ||
+		    hw->mac.type == ixgbe_mac_X540 ||
+		    hw->mac.type == ixgbe_mac_X550 ||
+		    hw->mac.type == ixgbe_mac_X550EM_x ||
+		    hw->mac.type == ixgbe_mac_x550em_a ||
+		    hw->mac.type == ixgbe_mac_e610) {
 			hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i));
 			IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */
 			hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i));
@@ -7251,6 +7613,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* OS2BMC stats are X540 and later */
 		hwstats->o2bgptc += IXGBE_READ_REG(hw, IXGBE_O2BGPTC);
 		hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC);
@@ -7551,6 +7914,7 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 	case ixgbe_mac_82599EB: {
 		u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN);
 		u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG);
@@ -7946,7 +8310,8 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter)
  **/
 static void ixgbe_service_timer(struct timer_list *t)
 {
-	struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer);
+	struct ixgbe_adapter *adapter = timer_container_of(adapter, t,
+							   service_timer);
 	unsigned long next_event_offset;
 
 	/* poll faster when waiting for link */
@@ -8001,6 +8366,34 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter)
 	rtnl_unlock();
 }
 
+static int ixgbe_check_fw_api_mismatch(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return 0;
+
+	if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw))
+		return 0;
+
+	if (hw->api_maj_ver > IXGBE_FW_API_VER_MAJOR) {
+		e_dev_err("The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
+
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+		return -EOPNOTSUPP;
+	} else if (hw->api_maj_ver == IXGBE_FW_API_VER_MAJOR &&
+		   hw->api_min_ver > IXGBE_FW_API_VER_MINOR + IXGBE_FW_API_VER_DIFF_ALLOWED) {
+		e_dev_info("The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+	} else if (hw->api_maj_ver < IXGBE_FW_API_VER_MAJOR ||
+		   hw->api_min_ver < IXGBE_FW_API_VER_MINOR - IXGBE_FW_API_VER_DIFF_ALLOWED) {
+		e_dev_info("The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+	}
+
+	return 0;
+}
+
 /**
  * ixgbe_check_fw_error - Check firmware for errors
  * @adapter: the adapter private structure
@@ -8011,12 +8404,14 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 fwsm;
+	int err;
 
 	/* read fwsm.ext_err_ind register and log errors */
 	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
 
+	/* skip if E610's FW is reloading, warning in that case may be misleading */
 	if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK ||
-	    !(fwsm & IXGBE_FWSM_FW_VAL_BIT))
+	    (!(fwsm & IXGBE_FWSM_FW_VAL_BIT) && !(hw->mac.type == ixgbe_mac_e610)))
 		e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n",
 			   fwsm);
 
@@ -8024,10 +8419,53 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
 		e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
 		return true;
 	}
+	if (!(adapter->flags2 & IXGBE_FLAG2_API_MISMATCH)) {
+		err = ixgbe_check_fw_api_mismatch(adapter);
+		if (err)
+			return true;
+	}
+
+	/* return here if FW rollback mode has been already detected */
+	if (adapter->flags2 & IXGBE_FLAG2_FW_ROLLBACK)
+		return false;
+
+	if (hw->mac.ops.fw_rollback_mode && hw->mac.ops.fw_rollback_mode(hw)) {
+		struct ixgbe_nvm_info *nvm_info = &adapter->hw.flash.nvm;
+		char ver_buff[64] = "";
+
+		if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw))
+			goto no_version;
+
+		if (hw->mac.ops.get_nvm_ver &&
+		    hw->mac.ops.get_nvm_ver(hw, nvm_info))
+			goto no_version;
+
+		snprintf(ver_buff, sizeof(ver_buff),
+			 "Current version is NVM:%x.%x.%x, FW:%d.%d. ",
+			 nvm_info->major, nvm_info->minor, nvm_info->eetrack,
+			 hw->fw_maj_ver, hw->fw_maj_ver);
+no_version:
+		e_dev_warn("Firmware rollback mode detected. %sDevice may exhibit limited functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware rollback mode.",
+			   ver_buff);
+
+		adapter->flags2 |= IXGBE_FLAG2_FW_ROLLBACK;
+	}
 
 	return false;
 }
 
+static void ixgbe_recovery_service_task(struct work_struct *work)
+{
+	struct ixgbe_adapter *adapter = container_of(work,
+						     struct ixgbe_adapter,
+						     service_task);
+
+	ixgbe_handle_fw_event(adapter);
+	ixgbe_service_event_complete(adapter);
+
+	mod_timer(&adapter->service_timer, jiffies + msecs_to_jiffies(100));
+}
+
 /**
  * ixgbe_service_task - manages and runs subtasks
  * @work: pointer to work_struct containing our data
@@ -8047,11 +8485,21 @@ static void ixgbe_service_task(struct work_struct *work)
 		return;
 	}
 	if (ixgbe_check_fw_error(adapter)) {
-		if (!test_bit(__IXGBE_DOWN, &adapter->state))
+		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
+			if (adapter->mii_bus) {
+				mdiobus_unregister(adapter->mii_bus);
+				adapter->mii_bus = NULL;
+			}
 			unregister_netdev(adapter->netdev);
+		}
 		ixgbe_service_event_complete(adapter);
 		return;
 	}
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT)
+			ixgbe_handle_fw_event(adapter);
+		ixgbe_check_media_subtask(adapter);
+	}
 	ixgbe_reset_subtask(adapter);
 	ixgbe_phy_interrupt_subtask(adapter);
 	ixgbe_sfp_detection_subtask(adapter);
@@ -8633,7 +9081,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 	switch (vlan_get_protocol(skb)) {
 	case htons(ETH_P_FCOE):
 	case htons(ETH_P_FIP):
-		adapter = netdev_priv(dev);
+		adapter = ixgbe_from_netdev(dev);
 
 		if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
 			break;
@@ -8892,7 +9340,7 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb,
 				      struct net_device *netdev,
 				      struct ixgbe_ring *ring)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *tx_ring;
 
 	/*
@@ -8924,7 +9372,7 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb,
  **/
 static int ixgbe_set_mac(struct net_device *netdev, void *p)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct sockaddr *addr = p;
 
@@ -8942,7 +9390,7 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p)
 static int
 ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 value;
 	int rc;
@@ -8968,7 +9416,7 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
 static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
 			    u16 addr, u16 value)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (adapter->mii_bus) {
@@ -8988,7 +9436,7 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
 
 static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	switch (cmd) {
 	case SIOCSHWTSTAMP:
@@ -9014,7 +9462,7 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
 static int ixgbe_add_sanmac_netdev(struct net_device *dev)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (is_valid_ether_addr(hw->mac.san_addr)) {
@@ -9038,7 +9486,7 @@ static int ixgbe_add_sanmac_netdev(struct net_device *dev)
 static int ixgbe_del_sanmac_netdev(struct net_device *dev)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_mac_info *mac = &adapter->hw.mac;
 
 	if (is_valid_ether_addr(mac->san_addr)) {
@@ -9069,7 +9517,7 @@ static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats,
 static void ixgbe_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i;
 
 	rcu_read_lock();
@@ -9112,7 +9560,7 @@ static void ixgbe_get_stats64(struct net_device *netdev,
 static int ixgbe_ndo_get_vf_stats(struct net_device *netdev, int vf,
 				  struct ifla_vf_stats *vf_stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (vf < 0 || vf >= adapter->num_vfs)
 		return -EINVAL;
@@ -9229,7 +9677,7 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev,
 
 static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct netdev_nested_priv priv = {
 		.data = (void *)adapter,
 	};
@@ -9250,7 +9698,7 @@ static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
  */
 int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* Hardware supports up to 8 traffic classes */
@@ -9808,7 +10256,7 @@ static LIST_HEAD(ixgbe_block_cb_list);
 static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			    void *type_data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
@@ -9836,7 +10284,7 @@ void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter)
 #endif
 void ixgbe_do_reset(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (netif_running(netdev))
 		ixgbe_reinit_locked(adapter);
@@ -9847,7 +10295,7 @@ void ixgbe_do_reset(struct net_device *netdev)
 static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
 					    netdev_features_t features)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* If Rx checksum is disabled, then RSC/LRO should also be disabled */
 	if (!(features & NETIF_F_RXCSUM))
@@ -9884,7 +10332,7 @@ static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter)
 static int ixgbe_set_features(struct net_device *netdev,
 			      netdev_features_t features)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	netdev_features_t changed = netdev->features ^ features;
 	bool need_reset = false;
 
@@ -9960,7 +10408,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 {
 	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
-		struct ixgbe_adapter *adapter = netdev_priv(dev);
+		struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 		u16 pool = VMDQ_P(0);
 
 		if (netdev_uc_count(dev) >= ixgbe_available_rars(adapter, pool))
@@ -10048,7 +10496,7 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
 				    struct nlmsghdr *nlh, u16 flags,
 				    struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct nlattr *attr, *br_spec;
 	int rem;
 
@@ -10076,7 +10524,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 				    struct net_device *dev,
 				    u32 filter_mask, int nlflags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
 		return 0;
@@ -10088,7 +10536,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(pdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev);
 	struct ixgbe_fwd_adapter *accel;
 	int tcs = adapter->hw_tcs ? : 1;
 	int pool, err;
@@ -10185,7 +10633,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 {
 	struct ixgbe_fwd_adapter *accel = priv;
-	struct ixgbe_adapter *adapter = netdev_priv(pdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev);
 	unsigned int rxbase = accel->rx_base_queue;
 	unsigned int i;
 
@@ -10263,7 +10711,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 {
 	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct bpf_prog *old_prog;
 	bool need_reset;
 	int num_queues;
@@ -10335,7 +10783,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 
 static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -10370,7 +10818,7 @@ void ixgbe_xdp_ring_update_tail_locked(struct ixgbe_ring *ring)
 static int ixgbe_xdp_xmit(struct net_device *dev, int n,
 			  struct xdp_frame **frames, u32 flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ring *ring;
 	int nxmit = 0;
 	int i;
@@ -10771,6 +11219,24 @@ bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
 }
 
 /**
+ * ixgbe_set_fw_version_e610 - Set FW version specifically on E610 adapters
+ * @adapter: the adapter private structure
+ *
+ * This function is used by probe and ethtool to determine the FW version to
+ * format to display. The FW version is taken from the EEPROM/NVM.
+ *
+ */
+void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
+	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
+
+	snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id),
+		 "%x.%02x 0x%x %d.%d.%d", nvm->major, nvm->minor,
+		 nvm->eetrack, orom->major, orom->build, orom->patch);
+}
+
+/**
  * ixgbe_set_fw_version - Set FW version
  * @adapter: the adapter private structure
  *
@@ -10782,6 +11248,11 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_nvm_version nvm_ver;
 
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		ixgbe_set_fw_version_e610(adapter);
+		return;
+	}
+
 	ixgbe_get_oem_prod_version(hw, &nvm_ver);
 	if (nvm_ver.oem_valid) {
 		snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id),
@@ -10806,6 +11277,66 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_recovery_probe - Handle FW recovery mode during probe
+ * @adapter: the adapter private structure
+ *
+ * Perform limited driver initialization when FW error is detected.
+ *
+ * Return: 0 on successful probe for E610, -EIO if recovery mode is detected
+ * for non-E610 adapter, error status code on any other case.
+ */
+static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool disable_dev;
+	int err = -EIO;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		goto clean_up_probe;
+
+	ixgbe_get_hw_control(adapter);
+	mutex_init(&hw->aci.lock);
+	err = ixgbe_get_flash_data(&adapter->hw);
+	if (err)
+		goto shutdown_aci;
+
+	timer_setup(&adapter->service_timer, ixgbe_service_timer, 0);
+	INIT_WORK(&adapter->service_task, ixgbe_recovery_service_task);
+	set_bit(__IXGBE_SERVICE_INITED, &adapter->state);
+	clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
+
+	if (hw->mac.ops.get_bus_info)
+		hw->mac.ops.get_bus_info(hw);
+
+	pci_set_drvdata(pdev, adapter);
+	/* We are creating devlink interface so NIC can be managed,
+	 * e.g. new NVM image loaded
+	 */
+	devl_lock(adapter->devlink);
+	ixgbe_devlink_register_port(adapter);
+	SET_NETDEV_DEVLINK_PORT(adapter->netdev,
+				&adapter->devlink_port);
+	ixgbe_devlink_init_regions(adapter);
+	devl_register(adapter->devlink);
+	devl_unlock(adapter->devlink);
+
+	return 0;
+shutdown_aci:
+	mutex_destroy(&adapter->hw.aci.lock);
+	ixgbe_release_hw_control(adapter);
+	devlink_free(adapter->devlink);
+clean_up_probe:
+	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
+	free_netdev(netdev);
+	pci_release_mem_regions(pdev);
+	if (disable_dev)
+		pci_disable_device(pdev);
+	return err;
+}
+
+/**
  * ixgbe_probe - Device Initialization Routine
  * @pdev: PCI device information struct
  * @ent: entry in ixgbe_pci_tbl
@@ -10819,6 +11350,7 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
 static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *netdev;
+	struct ixgbe_netdevice_priv *netdev_priv_wrapper;
 	struct ixgbe_adapter *adapter = NULL;
 	struct ixgbe_hw *hw;
 	const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data];
@@ -10868,9 +11400,17 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 #else
 		indices = IXGBE_MAX_RSS_INDICES;
 #endif
+	} else if (ii->mac == ixgbe_mac_e610) {
+		indices = IXGBE_MAX_RSS_INDICES_X550;
 	}
 
-	netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices);
+	adapter = ixgbe_allocate_devlink(&pdev->dev);
+	if (IS_ERR(adapter)) {
+		err = PTR_ERR(adapter);
+		goto err_devlink;
+	}
+
+	netdev = alloc_etherdev_mq(sizeof(*netdev_priv_wrapper), indices);
 	if (!netdev) {
 		err = -ENOMEM;
 		goto err_alloc_etherdev;
@@ -10878,7 +11418,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 
-	adapter = netdev_priv(netdev);
+	netdev_priv_wrapper = netdev_priv(netdev);
+	netdev_priv_wrapper->adapter = adapter;
 
 	adapter->netdev = netdev;
 	adapter->pdev = pdev;
@@ -10894,11 +11435,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_ioremap;
 	}
 
-	netdev->netdev_ops = &ixgbe_netdev_ops;
-	ixgbe_set_ethtool_ops(netdev);
-	netdev->watchdog_timeo = 5 * HZ;
-	strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
-
 	/* Setup hw api */
 	hw->mac.ops   = *ii->mac_ops;
 	hw->mac.type  = ii->mac;
@@ -10928,17 +11464,40 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->phy.mdio.mdio_read = ixgbe_mdio_read;
 	hw->phy.mdio.mdio_write = ixgbe_mdio_write;
 
+	netdev->netdev_ops = &ixgbe_netdev_ops;
+	ixgbe_set_ethtool_ops(netdev);
+	netdev->watchdog_timeo = 5 * HZ;
+	strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
+
 	/* setup the private structure */
 	err = ixgbe_sw_init(adapter, ii);
 	if (err)
 		goto err_sw_init;
 
+	/* Make sure the SWFW semaphore is in a valid state */
+	if (hw->mac.ops.init_swfw_sync)
+		hw->mac.ops.init_swfw_sync(hw);
+
+	if (ixgbe_check_fw_error(adapter))
+		return ixgbe_recovery_probe(adapter);
+
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		err = ixgbe_get_caps(&adapter->hw);
+		if (err)
+			dev_err(&pdev->dev, "ixgbe_get_caps failed %d\n", err);
+
+		err = ixgbe_get_flash_data(&adapter->hw);
+		if (err)
+			goto err_sw_init;
+	}
+
 	if (adapter->hw.mac.type == ixgbe_mac_82599EB)
 		adapter->flags2 |= IXGBE_FLAG2_AUTO_DISABLE_VF;
 
 	switch (adapter->hw.mac.type) {
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_e610:
 		netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550;
 		break;
 	case ixgbe_mac_x550em_a:
@@ -10948,10 +11507,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		break;
 	}
 
-	/* Make sure the SWFW semaphore is in a valid state */
-	if (hw->mac.ops.init_swfw_sync)
-		hw->mac.ops.init_swfw_sync(hw);
-
 	/* Make it possible the adapter to be woken up via WOL */
 	switch (adapter->hw.mac.type) {
 	case ixgbe_mac_82599EB:
@@ -10959,6 +11514,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);
 		break;
 	default:
@@ -11103,11 +11659,6 @@ skip_sriov:
 	if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
 		netdev->features |= NETIF_F_LRO;
 
-	if (ixgbe_check_fw_error(adapter)) {
-		err = -EIO;
-		goto err_sw_init;
-	}
-
 	/* make sure the EEPROM is good */
 	if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) {
 		e_dev_err("The EEPROM Checksum Is Not Valid\n");
@@ -11130,6 +11681,8 @@ skip_sriov:
 	ether_addr_copy(hw->mac.addr, hw->mac.perm_addr);
 	ixgbe_mac_set_default_filter(adapter);
 
+	if (hw->mac.type == ixgbe_mac_e610)
+		mutex_init(&hw->aci.lock);
 	timer_setup(&adapter->service_timer, ixgbe_service_timer, 0);
 
 	if (ixgbe_removed(hw->hw_addr)) {
@@ -11188,7 +11741,7 @@ skip_sriov:
 	if (expected_gts > 0)
 		ixgbe_check_minimum_link(adapter, expected_gts);
 
-	err = ixgbe_read_pba_string_generic(hw, part_str, sizeof(part_str));
+	err = hw->eeprom.ops.read_pba_string(hw, part_str, sizeof(part_str));
 	if (err)
 		strscpy(part_str, "Unknown", sizeof(part_str));
 	if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present)
@@ -11214,6 +11767,11 @@ skip_sriov:
 	}
 	strcpy(netdev->name, "eth%d");
 	pci_set_drvdata(pdev, adapter);
+
+	devl_lock(adapter->devlink);
+	ixgbe_devlink_register_port(adapter);
+	SET_NETDEV_DEVLINK_PORT(adapter->netdev, &adapter->devlink_port);
+
 	err = register_netdev(netdev);
 	if (err)
 		goto err_register;
@@ -11268,13 +11826,20 @@ skip_sriov:
 	if (err)
 		goto err_netdev;
 
+	ixgbe_devlink_init_regions(adapter);
+	devl_register(adapter->devlink);
+	devl_unlock(adapter->devlink);
 	return 0;
 
 err_netdev:
 	unregister_netdev(netdev);
 err_register:
+	devl_port_unregister(&adapter->devlink_port);
+	devl_unlock(adapter->devlink);
 	ixgbe_release_hw_control(adapter);
 	ixgbe_clear_interrupt_scheme(adapter);
+	if (hw->mac.type == ixgbe_mac_e610)
+		mutex_destroy(&adapter->hw.aci.lock);
 err_sw_init:
 	ixgbe_disable_sriov(adapter);
 	adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP;
@@ -11287,7 +11852,9 @@ err_ioremap:
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
 err_alloc_etherdev:
+	devlink_free(adapter->devlink);
 	pci_release_mem_regions(pdev);
+err_devlink:
 err_pci_reg:
 err_dma:
 	if (!adapter || disable_dev)
@@ -11316,11 +11883,19 @@ static void ixgbe_remove(struct pci_dev *pdev)
 		return;
 
 	netdev  = adapter->netdev;
+	devl_lock(adapter->devlink);
+	devl_unregister(adapter->devlink);
+	ixgbe_devlink_destroy_regions(adapter);
 	ixgbe_dbg_adapter_exit(adapter);
 
 	set_bit(__IXGBE_REMOVING, &adapter->state);
 	cancel_work_sync(&adapter->service_task);
 
+	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+		ixgbe_disable_link_status_events(adapter);
+		mutex_destroy(&adapter->hw.aci.lock);
+	}
+
 	if (adapter->mii_bus)
 		mdiobus_unregister(adapter->mii_bus);
 
@@ -11346,6 +11921,10 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
+	devl_port_unregister(&adapter->devlink_port);
+	devl_unlock(adapter->devlink);
+	devlink_free(adapter->devlink);
+
 	ixgbe_stop_ipsec_offload(adapter);
 	ixgbe_clear_interrupt_scheme(adapter);
 
@@ -11452,6 +12031,9 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev,
 		case ixgbe_mac_x550em_a:
 			device_id = IXGBE_DEV_ID_X550EM_A_VF;
 			break;
+		case ixgbe_mac_e610:
+			device_id = IXGBE_DEV_ID_E610_VF;
+			break;
 		default:
 			device_id = 0;
 			break;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
index d67d77e5dacc..788b5af07c70 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -283,6 +283,7 @@ static int ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		vflre = IXGBE_READ_REG(hw, IXGBE_VFLREC(reg_offset));
 		break;
 	default:
@@ -407,6 +408,7 @@ void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw)
 	    hw->mac.type != ixgbe_mac_X550 &&
 	    hw->mac.type != ixgbe_mac_X550EM_x &&
 	    hw->mac.type != ixgbe_mac_x550em_a &&
+	    hw->mac.type != ixgbe_mac_e610 &&
 	    hw->mac.type != ixgbe_mac_X540)
 		return;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 07eaa3c3f4d3..2d54828bdfbb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -167,7 +167,7 @@ int ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
 					 u16 reg, u16 val, bool lock)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
-	int max_retry = 1;
+	int max_retry = 3;
 	int retry = 0;
 	u8 reg_high;
 	u8 csum;
@@ -1117,7 +1117,7 @@ int ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw)
 	hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG,
 			     MDIO_MMD_AN, &autoneg_reg);
 
-	if (hw->mac.type == ixgbe_mac_X550) {
+	if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_e610) {
 		/* Set or unset auto-negotiation 5G advertisement */
 		autoneg_reg &= ~IXGBE_MII_5GBASE_T_ADVERTISE;
 		if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) &&
@@ -1233,6 +1233,7 @@ static int ixgbe_get_copper_speeds_supported(struct ixgbe_hw *hw)
 
 	switch (hw->mac.type) {
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL;
 		hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL;
 		break;
@@ -2284,7 +2285,7 @@ static int ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset,
 					    u8 dev_addr, u8 data, bool lock)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
-	u32 max_retry = 1;
+	u32 max_retry = 3;
 	u32 retry = 0;
 	int status;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 14aa2ca51f70..81179c60af4e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -40,7 +40,7 @@
 #define IXGBE_SFF_1GBASESX_CAPABLE		0x1
 #define IXGBE_SFF_1GBASELX_CAPABLE		0x2
 #define IXGBE_SFF_1GBASET_CAPABLE		0x8
-#define IXGBE_SFF_BASEBX10_CAPABLE		0x64
+#define IXGBE_SFF_BASEBX10_CAPABLE		0x40
 #define IXGBE_SFF_10GBASESR_CAPABLE		0x10
 #define IXGBE_SFF_10GBASELR_CAPABLE		0x20
 #define IXGBE_SFF_SOFT_RS_SELECT_MASK		0x8
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 9339edbd9082..eef25e11d938 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -140,6 +140,7 @@
  * proper mult and shift to convert the cycles into nanoseconds of time.
  */
 #define IXGBE_X550_BASE_PERIOD 0xC80000000ULL
+#define IXGBE_E610_BASE_PERIOD 0x333333333ULL
 #define INCVALUE_MASK	0x7FFFFFFF
 #define ISGN		0x80000000
 
@@ -415,6 +416,7 @@ static void ixgbe_ptp_convert_to_hwtstamp(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* Upper 32 bits represent billions of cycles, lower 32 bits
 		 * represent cycles. However, we use timespec64_to_ns for the
 		 * correct math even though the units haven't been corrected
@@ -492,11 +494,13 @@ static int ixgbe_ptp_adjfine_X550(struct ptp_clock_info *ptp, long scaled_ppm)
 	struct ixgbe_adapter *adapter =
 			container_of(ptp, struct ixgbe_adapter, ptp_caps);
 	struct ixgbe_hw *hw = &adapter->hw;
+	u64 rate, base;
 	bool neg_adj;
-	u64 rate;
 	u32 inca;
 
-	neg_adj = diff_by_scaled_ppm(IXGBE_X550_BASE_PERIOD, scaled_ppm, &rate);
+	base = hw->mac.type == ixgbe_mac_e610 ? IXGBE_E610_BASE_PERIOD :
+						IXGBE_X550_BASE_PERIOD;
+	neg_adj = diff_by_scaled_ppm(base, scaled_ppm, &rate);
 
 	/* warn if rate is too large */
 	if (rate >= INCVALUE_MASK)
@@ -559,6 +563,7 @@ static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* Upper 32 bits represent billions of cycles, lower 32 bits
 		 * represent cycles. However, we use timespec64_to_ns for the
 		 * correct math even though the units haven't been corrected
@@ -1067,6 +1072,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* enable timestamping all packets only if at least some
 		 * packets were requested. Otherwise, play nice and disable
 		 * timestamping
@@ -1233,6 +1239,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 		fallthrough;
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		cc.read = ixgbe_ptp_read_X550;
 		break;
 	case ixgbe_mac_X540:
@@ -1280,6 +1287,7 @@ static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
 
 		/* Reset SYSTIME registers to 0 */
@@ -1407,6 +1415,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name);
 		adapter->ptp_caps.owner = THIS_MODULE;
 		adapter->ptp_caps.max_adj = 30000000;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 9631559a5aea..0dbbd2befd4d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -1048,7 +1048,7 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter,
 		break;
 	}
 
-	e_info(drv, "VF %d requested invalid api version %u\n", vf, api);
+	e_dbg(drv, "VF %d requested unsupported api version %u\n", vf, api);
 
 	return -1;
 }
@@ -1418,7 +1418,7 @@ void ixgbe_set_all_vfs(struct ixgbe_adapter *adapter)
 
 int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int retval;
 
 	if (vf >= adapter->num_vfs)
@@ -1526,7 +1526,7 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 			  u8 qos, __be16 vlan_proto)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7))
 		return -EINVAL;
@@ -1644,7 +1644,7 @@ void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
 int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
 			int max_tx_rate)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int link_speed;
 
 	/* verify VF is active */
@@ -1679,7 +1679,7 @@ int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
 
 int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (vf >= adapter->num_vfs)
@@ -1757,7 +1757,7 @@ void ixgbe_set_vf_link_state(struct ixgbe_adapter *adapter, int vf, int state)
  **/
 int ixgbe_ndo_set_vf_link_state(struct net_device *netdev, int vf, int state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int ret = 0;
 
 	if (vf < 0 || vf >= adapter->num_vfs) {
@@ -1794,7 +1794,7 @@ int ixgbe_ndo_set_vf_link_state(struct net_device *netdev, int vf, int state)
 int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf,
 				  bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* This operation is currently supported only for 82599 and x540
 	 * devices.
@@ -1813,7 +1813,7 @@ int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf,
 
 int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (vf >= adapter->num_vfs)
 		return -EINVAL;
@@ -1836,7 +1836,7 @@ int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 			    int vf, struct ifla_vf_info *ivi)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	if (vf >= adapter->num_vfs)
 		return -EINVAL;
 	ivi->vf = vf;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 9baccacd02a1..892fa6c1f879 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef _IXGBE_TYPE_H_
 #define _IXGBE_TYPE_H_
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 #include <linux/mdio.h>
 #include <linux/netdevice.h>
+#include "ixgbe_type_e610.h"
 
 /* Device IDs */
 #define IXGBE_DEV_ID_82598               0x10B6
@@ -71,12 +72,19 @@
 #define IXGBE_DEV_ID_X550EM_A_1G_T	0x15E4
 #define IXGBE_DEV_ID_X550EM_A_1G_T_L	0x15E5
 
+#define IXGBE_DEV_ID_E610_BACKPLANE	0x57AE
+#define IXGBE_DEV_ID_E610_SFP		0x57AF
+#define IXGBE_DEV_ID_E610_10G_T		0x57B0
+#define IXGBE_DEV_ID_E610_2_5G_T	0x57B1
+#define IXGBE_DEV_ID_E610_SGMII		0x57B2
+
 /* VF Device IDs */
 #define IXGBE_DEV_ID_82599_VF		0x10ED
 #define IXGBE_DEV_ID_X540_VF		0x1515
 #define IXGBE_DEV_ID_X550_VF		0x1565
 #define IXGBE_DEV_ID_X550EM_X_VF	0x15A8
 #define IXGBE_DEV_ID_X550EM_A_VF	0x15C5
+#define IXGBE_DEV_ID_E610_VF		0x57AD
 
 #define IXGBE_CAT(r, m)	IXGBE_##r##_##m
 
@@ -1600,7 +1608,7 @@ enum {
 #define IXGBE_EICR_PCI          0x00040000 /* PCI Exception */
 #define IXGBE_EICR_MAILBOX      0x00080000 /* VF to PF Mailbox Interrupt */
 #define IXGBE_EICR_LSC          0x00100000 /* Link Status Change */
-#define IXGBE_EICR_LINKSEC      0x00200000 /* PN Threshold */
+#define IXGBE_EICR_FW_EVENT	0x00200000 /* Async FW event */
 #define IXGBE_EICR_MNG          0x00400000 /* Manageability Event Interrupt */
 #define IXGBE_EICR_TS           0x00800000 /* Thermal Sensor Event */
 #define IXGBE_EICR_TIMESYNC     0x01000000 /* Timesync Event */
@@ -1636,6 +1644,7 @@ enum {
 #define IXGBE_EICS_PCI          IXGBE_EICR_PCI       /* PCI Exception */
 #define IXGBE_EICS_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
 #define IXGBE_EICS_LSC          IXGBE_EICR_LSC       /* Link Status Change */
+#define IXGBE_EICS_FW_EVENT	IXGBE_EICR_FW_EVENT  /* Async FW event */
 #define IXGBE_EICS_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EICS_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
 #define IXGBE_EICS_GPI_SDP0(_hw)	IXGBE_EICR_GPI_SDP0(_hw)
@@ -1654,6 +1663,7 @@ enum {
 #define IXGBE_EIMS_PCI          IXGBE_EICR_PCI       /* PCI Exception */
 #define IXGBE_EIMS_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
 #define IXGBE_EIMS_LSC          IXGBE_EICR_LSC       /* Link Status Change */
+#define IXGBE_EIMS_FW_EVENT	IXGBE_EICR_FW_EVENT  /* Async FW event */
 #define IXGBE_EIMS_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EIMS_TS           IXGBE_EICR_TS        /* Thermel Sensor Event */
 #define IXGBE_EIMS_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
@@ -1673,6 +1683,7 @@ enum {
 #define IXGBE_EIMC_PCI          IXGBE_EICR_PCI       /* PCI Exception */
 #define IXGBE_EIMC_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
 #define IXGBE_EIMC_LSC          IXGBE_EICR_LSC       /* Link Status Change */
+#define IXGBE_EIMC_FW_EVENT	IXGBE_EICR_FW_EVENT  /* Async FW event */
 #define IXGBE_EIMC_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EIMC_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
 #define IXGBE_EIMC_GPI_SDP0(_hw)	IXGBE_EICR_GPI_SDP0(_hw)
@@ -2068,6 +2079,7 @@ enum {
 #define IXGBE_SAN_MAC_ADDR_PTR  0x28
 #define IXGBE_DEVICE_CAPS       0x2C
 #define IXGBE_SERIAL_NUMBER_MAC_ADDR 0x11
+#define IXGBE_PCIE_MSIX_E610_CAPS	0xB2
 #define IXGBE_PCIE_MSIX_82599_CAPS  0x72
 #define IXGBE_MAX_MSIX_VECTORS_82599	0x40
 #define IXGBE_PCIE_MSIX_82598_CAPS  0x62
@@ -2168,6 +2180,7 @@ enum {
 #define IXGBE_PCI_DEVICE_STATUS   0xAA
 #define IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING   0x0020
 #define IXGBE_PCI_LINK_STATUS     0xB2
+#define IXGBE_PCI_LINK_STATUS_E610	0x82
 #define IXGBE_PCI_DEVICE_CONTROL2 0xC8
 #define IXGBE_PCI_LINK_WIDTH      0x3F0
 #define IXGBE_PCI_LINK_WIDTH_1    0x10
@@ -2288,6 +2301,7 @@ enum {
 #define IXGBE_RXMTRL_V2_MGMT_MSG		0x0D00
 
 #define IXGBE_FCTRL_SBP 0x00000002 /* Store Bad Packet */
+#define IXGBE_FCTRL_TPE 0x00000080 /* Tag Promiscuous Ena*/
 #define IXGBE_FCTRL_MPE 0x00000100 /* Multicast Promiscuous Ena*/
 #define IXGBE_FCTRL_UPE 0x00000200 /* Unicast Promiscuous Ena */
 #define IXGBE_FCTRL_BAM 0x00000400 /* Broadcast Accept Mode */
@@ -2351,6 +2365,7 @@ enum {
 /* Multiple Transmit Queue Command Register */
 #define IXGBE_MTQC_RT_ENA       0x1 /* DCB Enable */
 #define IXGBE_MTQC_VT_ENA       0x2 /* VMDQ2 Enable */
+#define IXGBE_MTQC_NUM_TC_OR_Q  0xC /* Number of TCs or TxQs per pool */
 #define IXGBE_MTQC_64Q_1PB      0x0 /* 64 queues 1 pack buffer */
 #define IXGBE_MTQC_32VF         0x8 /* 4 TX Queues per pool w/32VF's */
 #define IXGBE_MTQC_64VF         0x4 /* 2 TX Queues per pool w/64VF's */
@@ -2970,6 +2985,29 @@ typedef u32 ixgbe_link_speed;
 					IXGBE_LINK_SPEED_1GB_FULL | \
 					IXGBE_LINK_SPEED_10GB_FULL)
 
+/* Physical layer type */
+typedef u64 ixgbe_physical_layer;
+#define IXGBE_PHYSICAL_LAYER_UNKNOWN		0
+#define IXGBE_PHYSICAL_LAYER_10GBASE_T		0x00001
+#define IXGBE_PHYSICAL_LAYER_1000BASE_T		0x00002
+#define IXGBE_PHYSICAL_LAYER_100BASE_TX		0x00004
+#define IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU	0x00008
+#define IXGBE_PHYSICAL_LAYER_10GBASE_LR		0x00010
+#define IXGBE_PHYSICAL_LAYER_10GBASE_LRM	0x00020
+#define IXGBE_PHYSICAL_LAYER_10GBASE_SR		0x00040
+#define IXGBE_PHYSICAL_LAYER_10GBASE_KX4	0x00080
+#define IXGBE_PHYSICAL_LAYER_10GBASE_CX4	0x00100
+#define IXGBE_PHYSICAL_LAYER_1000BASE_KX	0x00200
+#define IXGBE_PHYSICAL_LAYER_1000BASE_BX	0x00400
+#define IXGBE_PHYSICAL_LAYER_10GBASE_KR		0x00800
+#define IXGBE_PHYSICAL_LAYER_10GBASE_XAUI	0x01000
+#define IXGBE_PHYSICAL_LAYER_SFP_ACTIVE_DA	0x02000
+#define IXGBE_PHYSICAL_LAYER_1000BASE_SX	0x04000
+#define IXGBE_PHYSICAL_LAYER_10BASE_T		0x08000
+#define IXGBE_PHYSICAL_LAYER_2500BASE_KX	0x10000
+#define IXGBE_PHYSICAL_LAYER_2500BASE_T		0x20000
+#define IXGBE_PHYSICAL_LAYER_5000BASE_T		0x40000
+
 /* Flow Control Data Sheet defined values
  * Calculation and defines taken from 802.1bb Annex O
  */
@@ -3145,6 +3183,8 @@ enum ixgbe_mac_type {
 	ixgbe_mac_X550,
 	ixgbe_mac_X550EM_x,
 	ixgbe_mac_x550em_a,
+	ixgbe_mac_e610,
+	ixgbe_mac_e610_vf,
 	ixgbe_num_macs
 };
 
@@ -3224,7 +3264,9 @@ enum ixgbe_media_type {
 	ixgbe_media_type_copper,
 	ixgbe_media_type_backplane,
 	ixgbe_media_type_cx4,
-	ixgbe_media_type_virtual
+	ixgbe_media_type_virtual,
+	ixgbe_media_type_da,
+	ixgbe_media_type_aui,
 };
 
 /* Flow Control Settings */
@@ -3233,7 +3275,8 @@ enum ixgbe_fc_mode {
 	ixgbe_fc_rx_pause,
 	ixgbe_fc_tx_pause,
 	ixgbe_fc_full,
-	ixgbe_fc_default
+	ixgbe_fc_default,
+	ixgbe_fc_pfc,
 };
 
 /* Smart Speed Settings */
@@ -3403,6 +3446,8 @@ struct ixgbe_eeprom_operations {
 	int (*validate_checksum)(struct ixgbe_hw *, u16 *);
 	int (*update_checksum)(struct ixgbe_hw *);
 	int (*calc_checksum)(struct ixgbe_hw *);
+	int (*read_pba_string)(struct ixgbe_hw *hw, u8 *pba_num,
+			       u32 pba_num_size);
 };
 
 struct ixgbe_mac_operations {
@@ -3411,6 +3456,7 @@ struct ixgbe_mac_operations {
 	int (*start_hw)(struct ixgbe_hw *);
 	int (*clear_hw_cntrs)(struct ixgbe_hw *);
 	enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *);
+	int (*get_fw_ver)(struct ixgbe_hw *hw);
 	int (*get_mac_addr)(struct ixgbe_hw *, u8 *);
 	int (*get_san_mac_addr)(struct ixgbe_hw *, u8 *);
 	int (*get_device_caps)(struct ixgbe_hw *, u16 *);
@@ -3479,6 +3525,8 @@ struct ixgbe_mac_operations {
 	int (*get_thermal_sensor_data)(struct ixgbe_hw *);
 	int (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw);
 	bool (*fw_recovery_mode)(struct ixgbe_hw *hw);
+	bool (*fw_rollback_mode)(struct ixgbe_hw *hw);
+	int (*get_nvm_ver)(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm);
 	void (*disable_rx)(struct ixgbe_hw *hw);
 	void (*enable_rx)(struct ixgbe_hw *hw);
 	void (*set_source_address_pruning)(struct ixgbe_hw *, bool,
@@ -3533,6 +3581,9 @@ struct ixgbe_link_operations {
 struct ixgbe_link_info {
 	struct ixgbe_link_operations ops;
 	u8 addr;
+	struct ixgbe_link_status link_info;
+	struct ixgbe_link_status link_info_old;
+	u8 get_link_info;
 };
 
 struct ixgbe_eeprom_info {
@@ -3575,6 +3626,7 @@ struct ixgbe_mac_info {
 	u8				san_mac_rar_index;
 	struct ixgbe_thermal_sensor_data  thermal_sensor_data;
 	bool				set_lben;
+	u32				max_link_up_time;
 	u8				led_link_act;
 };
 
@@ -3599,6 +3651,10 @@ struct ixgbe_phy_info {
 	bool                            reset_if_overtemp;
 	bool                            qsfp_shared_i2c_bus;
 	u32				nw_mng_if_sel;
+	u64				phy_type_low;
+	u64				phy_type_high;
+	u16				curr_user_speed_req;
+	struct ixgbe_aci_cmd_set_phy_cfg_data curr_user_phy_cfg;
 };
 
 struct ixgbe_mbx_stats {
@@ -3643,6 +3699,19 @@ struct ixgbe_hw {
 	bool				allow_unsupported_sfp;
 	bool				wol_enabled;
 	bool				need_crosstalk_fix;
+	u8				api_branch;
+	u8				api_maj_ver;
+	u8				api_min_ver;
+	u8				api_patch;
+	u8				fw_branch;
+	u8				fw_maj_ver;
+	u8				fw_min_ver;
+	u8				fw_patch;
+	u32				fw_build;
+	struct ixgbe_aci_info		aci;
+	struct ixgbe_flash_info		flash;
+	struct ixgbe_hw_dev_caps	dev_caps;
+	struct ixgbe_hw_func_caps	func_caps;
 };
 
 struct ixgbe_info {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
new file mode 100644
index 000000000000..09df67f03cf4
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
@@ -0,0 +1,1250 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IXGBE_TYPE_E610_H_
+#define _IXGBE_TYPE_E610_H_
+
+#define BYTES_PER_DWORD	4
+
+/* General E610 defines */
+#define IXGBE_MAX_VSI			768
+
+/* Checksum and Shadow RAM pointers */
+#define IXGBE_E610_SR_NVM_CTRL_WORD		0x00
+#define IXGBE_E610_SR_PBA_BLOCK_PTR		0x16
+#define IXGBE_E610_SR_PBA_BLOCK_MASK		GENMASK(15, 8)
+#define IXGBE_E610_SR_NVM_DEV_STARTER_VER	0x18
+#define IXGBE_E610_SR_NVM_EETRACK_LO		0x2D
+#define IXGBE_E610_SR_NVM_EETRACK_HI		0x2E
+#define IXGBE_E610_NVM_VER_LO_MASK		GENMASK(7, 0)
+#define IXGBE_E610_NVM_VER_HI_MASK		GENMASK(15, 12)
+#define IXGBE_E610_SR_SW_CHECKSUM_WORD		0x3F
+#define IXGBE_E610_SR_PFA_PTR			0x40
+#define IXGBE_E610_SR_1ST_NVM_BANK_PTR		0x42
+#define IXGBE_E610_SR_NVM_BANK_SIZE		0x43
+#define IXGBE_E610_SR_1ST_OROM_BANK_PTR		0x44
+#define IXGBE_E610_SR_OROM_BANK_SIZE		0x45
+#define IXGBE_E610_SR_NETLIST_BANK_PTR		0x46
+#define IXGBE_E610_SR_NETLIST_BANK_SIZE		0x47
+
+/* The OROM version topology */
+#define IXGBE_OROM_VER_PATCH_MASK		GENMASK_ULL(7, 0)
+#define IXGBE_OROM_VER_BUILD_MASK		GENMASK_ULL(23, 8)
+#define IXGBE_OROM_VER_MASK			GENMASK_ULL(31, 24)
+
+/* CSS Header words */
+#define IXGBE_NVM_CSS_HDR_LEN_L			0x02
+#define IXGBE_NVM_CSS_HDR_LEN_H			0x03
+#define IXGBE_NVM_CSS_SREV_L			0x14
+#define IXGBE_NVM_CSS_SREV_H			0x15
+
+#define IXGBE_HDR_LEN_ROUNDUP			32
+
+/* Length of Authentication header section in words */
+#define IXGBE_NVM_AUTH_HEADER_LEN		0x08
+
+/* Shadow RAM related */
+#define IXGBE_SR_WORDS_IN_1KB	512
+
+/* The Netlist ID Block is located after all of the Link Topology nodes. */
+#define IXGBE_NETLIST_ID_BLK_SIZE		0x30
+#define IXGBE_NETLIST_ID_BLK_OFFSET(n)		IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0004 + 2 * (n))
+
+/* netlist ID block field offsets (word offsets) */
+#define IXGBE_NETLIST_ID_BLK_MAJOR_VER_LOW	0x02
+#define IXGBE_NETLIST_ID_BLK_MAJOR_VER_HIGH	0x03
+#define IXGBE_NETLIST_ID_BLK_MINOR_VER_LOW	0x04
+#define IXGBE_NETLIST_ID_BLK_MINOR_VER_HIGH	0x05
+#define IXGBE_NETLIST_ID_BLK_TYPE_LOW		0x06
+#define IXGBE_NETLIST_ID_BLK_TYPE_HIGH		0x07
+#define IXGBE_NETLIST_ID_BLK_REV_LOW		0x08
+#define IXGBE_NETLIST_ID_BLK_REV_HIGH		0x09
+#define IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(n)	(0x0A + (n))
+#define IXGBE_NETLIST_ID_BLK_CUST_VER		0x2F
+
+/* The Link Topology Netlist section is stored as a series of words. It is
+ * stored in the NVM as a TLV, with the first two words containing the type
+ * and length.
+ */
+#define IXGBE_NETLIST_LINK_TOPO_MOD_ID		0x011B
+#define IXGBE_NETLIST_TYPE_OFFSET		0x0000
+#define IXGBE_NETLIST_LEN_OFFSET		0x0001
+
+/* The Link Topology section follows the TLV header. When reading the netlist
+ * using ixgbe_read_netlist_module, we need to account for the 2-word TLV
+ * header.
+ */
+#define IXGBE_NETLIST_LINK_TOPO_OFFSET(n)	((n) + 2)
+#define IXGBE_LINK_TOPO_MODULE_LEN	IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0000)
+#define IXGBE_LINK_TOPO_NODE_COUNT	IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0001)
+#define IXGBE_LINK_TOPO_NODE_COUNT_M		GENMASK_ULL(9, 0)
+
+/* Firmware Status Register (GL_FWSTS) */
+#define GL_FWSTS		0x00083048 /* Reset Source: POR */
+#define GL_FWSTS_EP_PF0		BIT(24)
+#define GL_FWSTS_EP_PF1		BIT(25)
+
+/* Global NVM General Status Register */
+#define GLNVM_GENS		0x000B6100 /* Reset Source: POR */
+#define GLNVM_GENS_SR_SIZE_M	GENMASK(7, 5)
+
+#define IXGBE_GL_MNG_FWSM		0x000B6134 /* Reset Source: POR */
+#define IXGBE_GL_MNG_FWSM_RECOVERY_M	BIT(1)
+#define IXGBE_GL_MNG_FWSM_ROLLBACK_M    BIT(2)
+
+/* Flash Access Register */
+#define IXGBE_GLNVM_FLA			0x000B6108 /* Reset Source: POR */
+#define IXGBE_GLNVM_FLA_LOCKED_S	6
+#define IXGBE_GLNVM_FLA_LOCKED_M	BIT(6)
+
+/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */
+#define IXGBE_SR_CTRL_WORD_1_M		GENMASK(7, 6)
+#define IXGBE_SR_CTRL_WORD_VALID	BIT(0)
+#define IXGBE_SR_CTRL_WORD_OROM_BANK	BIT(3)
+#define IXGBE_SR_CTRL_WORD_NETLIST_BANK	BIT(4)
+#define IXGBE_SR_CTRL_WORD_NVM_BANK	BIT(5)
+#define IXGBE_SR_NVM_PTR_4KB_UNITS	BIT(15)
+
+/* Admin Command Interface (ACI) registers */
+#define IXGBE_PF_HIDA(_i)			(0x00085000 + ((_i) * 4))
+#define IXGBE_PF_HIDA_2(_i)			(0x00085020 + ((_i) * 4))
+#define IXGBE_PF_HIBA(_i)			(0x00084000 + ((_i) * 4))
+#define IXGBE_PF_HICR				0x00082048
+
+#define IXGBE_PF_HICR_EN			BIT(0)
+#define IXGBE_PF_HICR_C				BIT(1)
+#define IXGBE_PF_HICR_SV			BIT(2)
+#define IXGBE_PF_HICR_EV			BIT(3)
+
+#define IXGBE_FW_API_VER_MAJOR		0x01
+#define IXGBE_FW_API_VER_MINOR		0x07
+#define IXGBE_FW_API_VER_DIFF_ALLOWED	0x02
+
+#define IXGBE_ACI_DESC_SIZE		32
+#define IXGBE_ACI_DESC_SIZE_IN_DWORDS	(IXGBE_ACI_DESC_SIZE / BYTES_PER_DWORD)
+
+#define IXGBE_ACI_MAX_BUFFER_SIZE		4096    /* Size in bytes */
+#define IXGBE_ACI_SEND_DELAY_TIME_MS		10
+#define IXGBE_ACI_SEND_MAX_EXECUTE		3
+#define IXGBE_ACI_SEND_TIMEOUT_MS		\
+		(IXGBE_ACI_SEND_MAX_EXECUTE * IXGBE_ACI_SEND_DELAY_TIME_MS)
+/* [ms] timeout of waiting for sync response */
+#define IXGBE_ACI_SYNC_RESPONSE_TIMEOUT		100000
+/* [ms] timeout of waiting for async response */
+#define IXGBE_ACI_ASYNC_RESPONSE_TIMEOUT	150000
+/* [ms] timeout of waiting for resource release */
+#define IXGBE_ACI_RELEASE_RES_TIMEOUT		10000
+
+/* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
+#define IXGBE_ACI_LG_BUF		512
+
+/* Flags sub-structure
+ * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
+ * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
+ */
+
+#define IXGBE_ACI_FLAG_DD	BIT(0) /* 0x1 */
+#define IXGBE_ACI_FLAG_CMP	BIT(1) /* 0x2 */
+#define IXGBE_ACI_FLAG_ERR	BIT(2) /* 0x4 */
+#define IXGBE_ACI_FLAG_VFE	BIT(3) /* 0x8 */
+#define IXGBE_ACI_FLAG_LB	BIT(9) /* 0x200 */
+#define IXGBE_ACI_FLAG_RD	BIT(10) /* 0x400 */
+#define IXGBE_ACI_FLAG_VFC	BIT(11) /* 0x800 */
+#define IXGBE_ACI_FLAG_BUF	BIT(12) /* 0x1000 */
+#define IXGBE_ACI_FLAG_SI	BIT(13) /* 0x2000 */
+#define IXGBE_ACI_FLAG_EI	BIT(14) /* 0x4000 */
+#define IXGBE_ACI_FLAG_FE	BIT(15) /* 0x8000 */
+
+/* Admin Command Interface (ACI) error codes */
+enum ixgbe_aci_err {
+	IXGBE_ACI_RC_OK		= 0,  /* Success */
+	IXGBE_ACI_RC_EPERM	= 1,  /* Operation not permitted */
+	IXGBE_ACI_RC_ENOENT	= 2,  /* No such element */
+	IXGBE_ACI_RC_ESRCH	= 3,  /* Bad opcode */
+	IXGBE_ACI_RC_EINTR	= 4,  /* Operation interrupted */
+	IXGBE_ACI_RC_EIO	= 5,  /* I/O error */
+	IXGBE_ACI_RC_ENXIO	= 6,  /* No such resource */
+	IXGBE_ACI_RC_E2BIG	= 7,  /* Arg too long */
+	IXGBE_ACI_RC_EAGAIN	= 8,  /* Try again */
+	IXGBE_ACI_RC_ENOMEM	= 9,  /* Out of memory */
+	IXGBE_ACI_RC_EACCES	= 10, /* Permission denied */
+	IXGBE_ACI_RC_EFAULT	= 11, /* Bad address */
+	IXGBE_ACI_RC_EBUSY	= 12, /* Device or resource busy */
+	IXGBE_ACI_RC_EEXIST	= 13, /* Object already exists */
+	IXGBE_ACI_RC_EINVAL	= 14, /* Invalid argument */
+	IXGBE_ACI_RC_ENOTTY	= 15, /* Not a typewriter */
+	IXGBE_ACI_RC_ENOSPC	= 16, /* No space left or alloc failure */
+	IXGBE_ACI_RC_ENOSYS	= 17, /* Function not implemented */
+	IXGBE_ACI_RC_ERANGE	= 18, /* Parameter out of range */
+	IXGBE_ACI_RC_EFLUSHED	= 19, /* Cmd flushed due to prev cmd error */
+	IXGBE_ACI_RC_BAD_ADDR	= 20, /* Descriptor contains a bad pointer */
+	IXGBE_ACI_RC_EMODE	= 21, /* Op not allowed in current dev mode */
+	IXGBE_ACI_RC_EFBIG	= 22, /* File too big */
+	IXGBE_ACI_RC_ESBCOMP	= 23, /* SB-IOSF completion unsuccessful */
+	IXGBE_ACI_RC_ENOSEC	= 24, /* Missing security manifest */
+	IXGBE_ACI_RC_EBADSIG	= 25, /* Bad RSA signature */
+	IXGBE_ACI_RC_ESVN	= 26, /* SVN number prohibits this package */
+	IXGBE_ACI_RC_EBADMAN	= 27, /* Manifest hash mismatch */
+	IXGBE_ACI_RC_EBADBUF	= 28, /* Buffer hash mismatches manifest */
+	IXGBE_ACI_RC_EACCES_BMCU	= 29, /* BMC Update in progress */
+};
+
+/* Admin Command Interface (ACI) opcodes */
+enum ixgbe_aci_opc {
+	ixgbe_aci_opc_get_ver				= 0x0001,
+	ixgbe_aci_opc_driver_ver			= 0x0002,
+	ixgbe_aci_opc_get_exp_err			= 0x0005,
+
+	/* resource ownership */
+	ixgbe_aci_opc_req_res				= 0x0008,
+	ixgbe_aci_opc_release_res			= 0x0009,
+
+	/* device/function capabilities */
+	ixgbe_aci_opc_list_func_caps			= 0x000A,
+	ixgbe_aci_opc_list_dev_caps			= 0x000B,
+
+	/* safe disable of RXEN */
+	ixgbe_aci_opc_disable_rxen			= 0x000C,
+
+	/* FW events */
+	ixgbe_aci_opc_get_fw_event			= 0x0014,
+
+	/* PHY commands */
+	ixgbe_aci_opc_get_phy_caps			= 0x0600,
+	ixgbe_aci_opc_set_phy_cfg			= 0x0601,
+	ixgbe_aci_opc_restart_an			= 0x0605,
+	ixgbe_aci_opc_get_link_status			= 0x0607,
+	ixgbe_aci_opc_set_event_mask			= 0x0613,
+	ixgbe_aci_opc_get_link_topo			= 0x06E0,
+	ixgbe_aci_opc_get_link_topo_pin			= 0x06E1,
+	ixgbe_aci_opc_read_i2c				= 0x06E2,
+	ixgbe_aci_opc_write_i2c				= 0x06E3,
+	ixgbe_aci_opc_read_mdio				= 0x06E4,
+	ixgbe_aci_opc_write_mdio			= 0x06E5,
+	ixgbe_aci_opc_set_gpio_by_func			= 0x06E6,
+	ixgbe_aci_opc_get_gpio_by_func			= 0x06E7,
+	ixgbe_aci_opc_set_port_id_led			= 0x06E9,
+	ixgbe_aci_opc_set_gpio				= 0x06EC,
+	ixgbe_aci_opc_get_gpio				= 0x06ED,
+	ixgbe_aci_opc_sff_eeprom			= 0x06EE,
+	ixgbe_aci_opc_prog_topo_dev_nvm			= 0x06F2,
+	ixgbe_aci_opc_read_topo_dev_nvm			= 0x06F3,
+
+	/* NVM commands */
+	ixgbe_aci_opc_nvm_read				= 0x0701,
+	ixgbe_aci_opc_nvm_erase				= 0x0702,
+	ixgbe_aci_opc_nvm_write				= 0x0703,
+	ixgbe_aci_opc_nvm_cfg_read			= 0x0704,
+	ixgbe_aci_opc_nvm_cfg_write			= 0x0705,
+	ixgbe_aci_opc_nvm_checksum			= 0x0706,
+	ixgbe_aci_opc_nvm_write_activate		= 0x0707,
+	ixgbe_aci_opc_nvm_sr_dump			= 0x0707,
+	ixgbe_aci_opc_nvm_save_factory_settings		= 0x0708,
+	ixgbe_aci_opc_nvm_update_empr			= 0x0709,
+	ixgbe_aci_opc_nvm_pkg_data			= 0x070A,
+	ixgbe_aci_opc_nvm_pass_component_tbl		= 0x070B,
+
+	/* Alternate Structure Commands */
+	ixgbe_aci_opc_write_alt_direct			= 0x0900,
+	ixgbe_aci_opc_write_alt_indirect		= 0x0901,
+	ixgbe_aci_opc_read_alt_direct			= 0x0902,
+	ixgbe_aci_opc_read_alt_indirect			= 0x0903,
+	ixgbe_aci_opc_done_alt_write			= 0x0904,
+	ixgbe_aci_opc_clear_port_alt_write		= 0x0906,
+
+	/* TCA Events */
+	ixgbe_aci_opc_temp_tca_event                    = 0x0C94,
+
+	/* debug commands */
+	ixgbe_aci_opc_debug_dump_internals		= 0xFF08,
+
+	/* SystemDiagnostic commands */
+	ixgbe_aci_opc_set_health_status_config		= 0xFF20,
+	ixgbe_aci_opc_get_supported_health_status_codes	= 0xFF21,
+	ixgbe_aci_opc_get_health_status			= 0xFF22,
+	ixgbe_aci_opc_clear_health_status		= 0xFF23,
+};
+
+/* Get version (direct 0x0001) */
+struct ixgbe_aci_cmd_get_ver {
+	__le32 rom_ver;
+	__le32 fw_build;
+	u8 fw_branch;
+	u8 fw_major;
+	u8 fw_minor;
+	u8 fw_patch;
+	u8 api_branch;
+	u8 api_major;
+	u8 api_minor;
+	u8 api_patch;
+};
+
+#define IXGBE_DRV_VER_STR_LEN_E610	32
+
+/* Send driver version (indirect 0x0002) */
+struct ixgbe_aci_cmd_driver_ver {
+	u8 major_ver;
+	u8 minor_ver;
+	u8 build_ver;
+	u8 subbuild_ver;
+	u8 reserved[4];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Get Expanded Error Code (0x0005, direct) */
+struct ixgbe_aci_cmd_get_exp_err {
+	__le32 reason;
+#define IXGBE_ACI_EXPANDED_ERROR_NOT_PROVIDED	0xFFFFFFFF
+	__le32 identifier;
+	u8 rsvd[8];
+};
+
+/* FW update timeout definitions are in milliseconds */
+#define IXGBE_NVM_TIMEOUT		180000
+
+enum ixgbe_aci_res_access_type {
+	IXGBE_RES_READ = 1,
+	IXGBE_RES_WRITE
+};
+
+enum ixgbe_aci_res_ids {
+	IXGBE_NVM_RES_ID = 1,
+	IXGBE_SPD_RES_ID,
+	IXGBE_CHANGE_LOCK_RES_ID,
+	IXGBE_GLOBAL_CFG_LOCK_RES_ID
+};
+
+/* Request resource ownership (direct 0x0008)
+ * Release resource ownership (direct 0x0009)
+ */
+struct ixgbe_aci_cmd_req_res {
+	__le16 res_id;
+	__le16 access_type;
+
+	/* Upon successful completion, FW writes this value and driver is
+	 * expected to release resource before timeout. This value is provided
+	 * in milliseconds.
+	 */
+	__le32 timeout;
+#define IXGBE_ACI_RES_NVM_READ_DFLT_TIMEOUT_MS	3000
+#define IXGBE_ACI_RES_NVM_WRITE_DFLT_TIMEOUT_MS	180000
+#define IXGBE_ACI_RES_CHNG_LOCK_DFLT_TIMEOUT_MS	1000
+#define IXGBE_ACI_RES_GLBL_LOCK_DFLT_TIMEOUT_MS	3000
+	/* For SDP: pin ID of the SDP */
+	__le32 res_number;
+	__le16 status;
+#define IXGBE_ACI_RES_GLBL_SUCCESS		0
+#define IXGBE_ACI_RES_GLBL_IN_PROG		1
+#define IXGBE_ACI_RES_GLBL_DONE			2
+	u8 reserved[2];
+};
+
+/* Get function capabilities (indirect 0x000A)
+ * Get device capabilities (indirect 0x000B)
+ */
+struct ixgbe_aci_cmd_list_caps {
+	u8 cmd_flags;
+	u8 pf_index;
+	u8 reserved[2];
+	__le32 count;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Device/Function buffer entry, repeated per reported capability */
+struct ixgbe_aci_cmd_list_caps_elem {
+	__le16 cap;
+#define IXGBE_ACI_CAPS_VALID_FUNCTIONS			0x0005
+#define IXGBE_ACI_MAX_VALID_FUNCTIONS			0x8
+#define IXGBE_ACI_CAPS_SRIOV				0x0012
+#define IXGBE_ACI_CAPS_VF				0x0013
+#define IXGBE_ACI_CAPS_VMDQ				0x0014
+#define IXGBE_ACI_CAPS_VSI				0x0017
+#define IXGBE_ACI_CAPS_DCB				0x0018
+#define IXGBE_ACI_CAPS_RSS				0x0040
+#define IXGBE_ACI_CAPS_RXQS				0x0041
+#define IXGBE_ACI_CAPS_TXQS				0x0042
+#define IXGBE_ACI_CAPS_MSIX				0x0043
+#define IXGBE_ACI_CAPS_FD				0x0045
+#define IXGBE_ACI_CAPS_1588				0x0046
+#define IXGBE_ACI_CAPS_MAX_MTU				0x0047
+#define IXGBE_ACI_CAPS_NVM_VER				0x0048
+#define IXGBE_ACI_CAPS_PENDING_NVM_VER			0x0049
+#define IXGBE_ACI_CAPS_OROM_VER				0x004A
+#define IXGBE_ACI_CAPS_PENDING_OROM_VER			0x004B
+#define IXGBE_ACI_CAPS_PENDING_NET_VER			0x004D
+#define IXGBE_ACI_CAPS_INLINE_IPSEC			0x0070
+#define IXGBE_ACI_CAPS_NUM_ENABLED_PORTS		0x0072
+#define IXGBE_ACI_CAPS_PCIE_RESET_AVOIDANCE		0x0076
+#define IXGBE_ACI_CAPS_POST_UPDATE_RESET_RESTRICT	0x0077
+#define IXGBE_ACI_CAPS_NVM_MGMT				0x0080
+#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0		0x0081
+#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG1		0x0082
+#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG2		0x0083
+#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG3		0x0084
+	u8 major_ver;
+	u8 minor_ver;
+	/* Number of resources described by this capability */
+	__le32 number;
+	/* Only meaningful for some types of resources */
+	__le32 logical_id;
+	/* Only meaningful for some types of resources */
+	__le32 phys_id;
+	__le64 rsvd1;
+	__le64 rsvd2;
+};
+
+/* Disable RXEN (direct 0x000C) */
+struct ixgbe_aci_cmd_disable_rxen {
+	u8 lport_num;
+	u8 reserved[15];
+};
+
+/* Get PHY capabilities (indirect 0x0600) */
+struct ixgbe_aci_cmd_get_phy_caps {
+	u8 lport_num;
+	u8 reserved;
+	__le16 param0;
+	/* 18.0 - Report qualified modules */
+#define IXGBE_ACI_GET_PHY_RQM		BIT(0)
+	/* 18.1 - 18.3 : Report mode
+	 * 000b - Report topology capabilities, without media
+	 * 001b - Report topology capabilities, with media
+	 * 010b - Report Active configuration
+	 * 011b - Report PHY Type and FEC mode capabilities
+	 * 100b - Report Default capabilities
+	 */
+#define IXGBE_ACI_REPORT_MODE_M			GENMASK(3, 1)
+#define IXGBE_ACI_REPORT_TOPO_CAP_NO_MEDIA	0
+#define IXGBE_ACI_REPORT_TOPO_CAP_MEDIA		BIT(1)
+#define IXGBE_ACI_REPORT_ACTIVE_CFG		BIT(2)
+#define IXGBE_ACI_REPORT_DFLT_CFG		BIT(3)
+	__le32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* This is #define of PHY type (Extended):
+ * The first set of defines is for phy_type_low.
+ */
+#define IXGBE_PHY_TYPE_LOW_100BASE_TX		BIT_ULL(0)
+#define IXGBE_PHY_TYPE_LOW_100M_SGMII		BIT_ULL(1)
+#define IXGBE_PHY_TYPE_LOW_1000BASE_T		BIT_ULL(2)
+#define IXGBE_PHY_TYPE_LOW_1000BASE_SX		BIT_ULL(3)
+#define IXGBE_PHY_TYPE_LOW_1000BASE_LX		BIT_ULL(4)
+#define IXGBE_PHY_TYPE_LOW_1000BASE_KX		BIT_ULL(5)
+#define IXGBE_PHY_TYPE_LOW_1G_SGMII		BIT_ULL(6)
+#define IXGBE_PHY_TYPE_LOW_2500BASE_T		BIT_ULL(7)
+#define IXGBE_PHY_TYPE_LOW_2500BASE_X		BIT_ULL(8)
+#define IXGBE_PHY_TYPE_LOW_2500BASE_KX		BIT_ULL(9)
+#define IXGBE_PHY_TYPE_LOW_5GBASE_T		BIT_ULL(10)
+#define IXGBE_PHY_TYPE_LOW_5GBASE_KR		BIT_ULL(11)
+#define IXGBE_PHY_TYPE_LOW_10GBASE_T		BIT_ULL(12)
+#define IXGBE_PHY_TYPE_LOW_10G_SFI_DA		BIT_ULL(13)
+#define IXGBE_PHY_TYPE_LOW_10GBASE_SR		BIT_ULL(14)
+#define IXGBE_PHY_TYPE_LOW_10GBASE_LR		BIT_ULL(15)
+#define IXGBE_PHY_TYPE_LOW_10GBASE_KR_CR1	BIT_ULL(16)
+#define IXGBE_PHY_TYPE_LOW_10G_SFI_AOC_ACC	BIT_ULL(17)
+#define IXGBE_PHY_TYPE_LOW_10G_SFI_C2C		BIT_ULL(18)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_T		BIT_ULL(19)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_CR		BIT_ULL(20)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_CR_S		BIT_ULL(21)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_CR1		BIT_ULL(22)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_SR		BIT_ULL(23)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_LR		BIT_ULL(24)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_KR		BIT_ULL(25)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_KR_S		BIT_ULL(26)
+#define IXGBE_PHY_TYPE_LOW_25GBASE_KR1		BIT_ULL(27)
+#define IXGBE_PHY_TYPE_LOW_25G_AUI_AOC_ACC	BIT_ULL(28)
+#define IXGBE_PHY_TYPE_LOW_25G_AUI_C2C		BIT_ULL(29)
+#define IXGBE_PHY_TYPE_LOW_MAX_INDEX		29
+/* The second set of defines is for phy_type_high. */
+#define IXGBE_PHY_TYPE_HIGH_10BASE_T		BIT_ULL(1)
+#define IXGBE_PHY_TYPE_HIGH_10M_SGMII		BIT_ULL(2)
+#define IXGBE_PHY_TYPE_HIGH_2500M_SGMII		BIT_ULL(56)
+#define IXGBE_PHY_TYPE_HIGH_100M_USXGMII	BIT_ULL(57)
+#define IXGBE_PHY_TYPE_HIGH_1G_USXGMII		BIT_ULL(58)
+#define IXGBE_PHY_TYPE_HIGH_2500M_USXGMII	BIT_ULL(59)
+#define IXGBE_PHY_TYPE_HIGH_5G_USXGMII		BIT_ULL(60)
+#define IXGBE_PHY_TYPE_HIGH_10G_USXGMII		BIT_ULL(61)
+#define IXGBE_PHY_TYPE_HIGH_MAX_INDEX		61
+
+struct ixgbe_aci_cmd_get_phy_caps_data {
+	__le64 phy_type_low; /* Use values from IXGBE_PHY_TYPE_LOW_* */
+	__le64 phy_type_high; /* Use values from IXGBE_PHY_TYPE_HIGH_* */
+	u8 caps;
+#define IXGBE_ACI_PHY_EN_TX_LINK_PAUSE			BIT(0)
+#define IXGBE_ACI_PHY_EN_RX_LINK_PAUSE			BIT(1)
+#define IXGBE_ACI_PHY_LOW_POWER_MODE			BIT(2)
+#define IXGBE_ACI_PHY_EN_LINK				BIT(3)
+#define IXGBE_ACI_PHY_AN_MODE				BIT(4)
+#define IXGBE_ACI_PHY_EN_MOD_QUAL			BIT(5)
+#define IXGBE_ACI_PHY_EN_LESM				BIT(6)
+#define IXGBE_ACI_PHY_EN_AUTO_FEC			BIT(7)
+#define IXGBE_ACI_PHY_CAPS_MASK				GENMASK(7, 0)
+	u8 low_power_ctrl_an;
+#define IXGBE_ACI_PHY_EN_D3COLD_LOW_POWER_AUTONEG	BIT(0)
+#define IXGBE_ACI_PHY_AN_EN_CLAUSE28			BIT(1)
+#define IXGBE_ACI_PHY_AN_EN_CLAUSE73			BIT(2)
+#define IXGBE_ACI_PHY_AN_EN_CLAUSE37			BIT(3)
+	__le16 eee_cap;
+#define IXGBE_ACI_PHY_EEE_EN_100BASE_TX			BIT(0)
+#define IXGBE_ACI_PHY_EEE_EN_1000BASE_T			BIT(1)
+#define IXGBE_ACI_PHY_EEE_EN_10GBASE_T			BIT(2)
+#define IXGBE_ACI_PHY_EEE_EN_1000BASE_KX		BIT(3)
+#define IXGBE_ACI_PHY_EEE_EN_10GBASE_KR			BIT(4)
+#define IXGBE_ACI_PHY_EEE_EN_25GBASE_KR			BIT(5)
+#define IXGBE_ACI_PHY_EEE_EN_10BASE_T			BIT(11)
+	__le16 eeer_value;
+	u8 phy_id_oui[4]; /* PHY/Module ID connected on the port */
+	u8 phy_fw_ver[8];
+	u8 link_fec_options;
+#define IXGBE_ACI_PHY_FEC_10G_KR_40G_KR4_EN		BIT(0)
+#define IXGBE_ACI_PHY_FEC_10G_KR_40G_KR4_REQ		BIT(1)
+#define IXGBE_ACI_PHY_FEC_25G_RS_528_REQ		BIT(2)
+#define IXGBE_ACI_PHY_FEC_25G_KR_REQ			BIT(3)
+#define IXGBE_ACI_PHY_FEC_25G_RS_544_REQ		BIT(4)
+#define IXGBE_ACI_PHY_FEC_25G_RS_CLAUSE91_EN		BIT(6)
+#define IXGBE_ACI_PHY_FEC_25G_KR_CLAUSE74_EN		BIT(7)
+#define IXGBE_ACI_PHY_FEC_MASK				0xdf
+	u8 module_compliance_enforcement;
+#define IXGBE_ACI_MOD_ENFORCE_STRICT_MODE		BIT(0)
+	u8 extended_compliance_code;
+#define IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE		3
+	u8 module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE];
+#define IXGBE_ACI_MOD_TYPE_BYTE0_SFP_PLUS		0xA0
+#define IXGBE_ACI_MOD_TYPE_BYTE0_QSFP_PLUS		0x80
+#define IXGBE_ACI_MOD_TYPE_IDENT			1
+#define IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_PASSIVE	BIT(0)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_SFP_PLUS_CU_ACTIVE	BIT(1)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_SR		BIT(4)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LR		BIT(5)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_LRM		BIT(6)
+#define IXGBE_ACI_MOD_TYPE_BYTE1_10G_BASE_ER		BIT(7)
+#define IXGBE_ACI_MOD_TYPE_BYTE2_SFP_PLUS		0xA0
+#define IXGBE_ACI_MOD_TYPE_BYTE2_QSFP_PLUS		0x86
+	u8 qualified_module_count;
+	u8 rsvd2[7];	/* Bytes 47:41 reserved */
+#define IXGBE_ACI_QUAL_MOD_COUNT_MAX			16
+	struct {
+		u8 v_oui[3];
+		u8 rsvd3;
+		u8 v_part[16];
+		__le32 v_rev;
+		__le64 rsvd4;
+	} qual_modules[IXGBE_ACI_QUAL_MOD_COUNT_MAX];
+};
+
+/* Set PHY capabilities (direct 0x0601)
+ * NOTE: This command must be followed by setup link and restart auto-neg
+ */
+struct ixgbe_aci_cmd_set_phy_cfg {
+	u8 lport_num;
+	u8 reserved[7];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Set PHY config command data structure */
+struct ixgbe_aci_cmd_set_phy_cfg_data {
+	__le64 phy_type_low; /* Use values from IXGBE_PHY_TYPE_LOW_* */
+	__le64 phy_type_high; /* Use values from IXGBE_PHY_TYPE_HIGH_* */
+	u8 caps;
+#define IXGBE_ACI_PHY_ENA_VALID_MASK		0xef
+#define IXGBE_ACI_PHY_ENA_TX_PAUSE_ABILITY	BIT(0)
+#define IXGBE_ACI_PHY_ENA_RX_PAUSE_ABILITY	BIT(1)
+#define IXGBE_ACI_PHY_ENA_LOW_POWER		BIT(2)
+#define IXGBE_ACI_PHY_ENA_LINK			BIT(3)
+#define IXGBE_ACI_PHY_ENA_AUTO_LINK_UPDT	BIT(5)
+#define IXGBE_ACI_PHY_ENA_LESM			BIT(6)
+#define IXGBE_ACI_PHY_ENA_AUTO_FEC		BIT(7)
+	u8 low_power_ctrl_an;
+	__le16 eee_cap; /* Value from ixgbe_aci_get_phy_caps */
+	__le16 eeer_value; /* Use defines from ixgbe_aci_get_phy_caps */
+	u8 link_fec_opt; /* Use defines from ixgbe_aci_get_phy_caps */
+	u8 module_compliance_enforcement;
+};
+
+/* Restart AN command data structure (direct 0x0605)
+ * Also used for response, with only the lport_num field present.
+ */
+struct ixgbe_aci_cmd_restart_an {
+	u8 lport_num;
+	u8 reserved;
+	u8 cmd_flags;
+#define IXGBE_ACI_RESTART_AN_LINK_RESTART	BIT(1)
+#define IXGBE_ACI_RESTART_AN_LINK_ENABLE	BIT(2)
+	u8 reserved2[13];
+};
+
+/* Get link status (indirect 0x0607), also used for Link Status Event */
+struct ixgbe_aci_cmd_get_link_status {
+	u8 lport_num;
+	u8 reserved;
+	__le16 cmd_flags;
+#define IXGBE_ACI_LSE_M				GENMASK(1, 0)
+#define IXGBE_ACI_LSE_NOP			0x0
+#define IXGBE_ACI_LSE_DIS			0x2
+#define IXGBE_ACI_LSE_ENA			0x3
+	/* only response uses this flag */
+#define IXGBE_ACI_LSE_IS_ENABLED		0x1
+	__le32 reserved2;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Get link status response data structure, also used for Link Status Event */
+struct ixgbe_aci_cmd_get_link_status_data {
+	u8 topo_media_conflict;
+#define IXGBE_ACI_LINK_TOPO_CONFLICT		BIT(0)
+#define IXGBE_ACI_LINK_MEDIA_CONFLICT		BIT(1)
+#define IXGBE_ACI_LINK_TOPO_CORRUPT		BIT(2)
+#define IXGBE_ACI_LINK_TOPO_UNREACH_PRT		BIT(4)
+#define IXGBE_ACI_LINK_TOPO_UNDRUTIL_PRT	BIT(5)
+#define IXGBE_ACI_LINK_TOPO_UNDRUTIL_MEDIA	BIT(6)
+#define IXGBE_ACI_LINK_TOPO_UNSUPP_MEDIA	BIT(7)
+	u8 link_cfg_err;
+#define IXGBE_ACI_LINK_CFG_ERR				BIT(0)
+#define IXGBE_ACI_LINK_CFG_COMPLETED			BIT(1)
+#define IXGBE_ACI_LINK_ACT_PORT_OPT_INVAL		BIT(2)
+#define IXGBE_ACI_LINK_FEAT_ID_OR_CONFIG_ID_INVAL	BIT(3)
+#define IXGBE_ACI_LINK_TOPO_CRITICAL_SDP_ERR		BIT(4)
+#define IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED		BIT(5)
+#define IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE	BIT(6)
+#define IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT		BIT(7)
+	u8 link_info;
+#define IXGBE_ACI_LINK_UP		BIT(0)	/* Link Status */
+#define IXGBE_ACI_LINK_FAULT		BIT(1)
+#define IXGBE_ACI_LINK_FAULT_TX		BIT(2)
+#define IXGBE_ACI_LINK_FAULT_RX		BIT(3)
+#define IXGBE_ACI_LINK_FAULT_REMOTE	BIT(4)
+#define IXGBE_ACI_LINK_UP_PORT		BIT(5)	/* External Port Link Status */
+#define IXGBE_ACI_MEDIA_AVAILABLE	BIT(6)
+#define IXGBE_ACI_SIGNAL_DETECT		BIT(7)
+	u8 an_info;
+#define IXGBE_ACI_AN_COMPLETED		BIT(0)
+#define IXGBE_ACI_LP_AN_ABILITY		BIT(1)
+#define IXGBE_ACI_PD_FAULT		BIT(2)	/* Parallel Detection Fault */
+#define IXGBE_ACI_FEC_EN		BIT(3)
+#define IXGBE_ACI_PHY_LOW_POWER		BIT(4)	/* Low Power State */
+#define IXGBE_ACI_LINK_PAUSE_TX		BIT(5)
+#define IXGBE_ACI_LINK_PAUSE_RX		BIT(6)
+#define IXGBE_ACI_QUALIFIED_MODULE	BIT(7)
+	u8 ext_info;
+#define IXGBE_ACI_LINK_PHY_TEMP_ALARM	BIT(0)
+#define IXGBE_ACI_LINK_EXCESSIVE_ERRORS	BIT(1)	/* Excessive Link Errors */
+	/* Port Tx Suspended */
+#define IXGBE_ACI_LINK_TX_ACTIVE	0
+#define IXGBE_ACI_LINK_TX_DRAINED	1
+#define IXGBE_ACI_LINK_TX_FLUSHED	3
+	u8 lb_status;
+#define IXGBE_ACI_LINK_LB_PHY_LCL	BIT(0)
+#define IXGBE_ACI_LINK_LB_PHY_RMT	BIT(1)
+#define IXGBE_ACI_LINK_LB_MAC_LCL	BIT(2)
+	__le16 max_frame_size;
+	u8 cfg;
+#define IXGBE_ACI_LINK_25G_KR_FEC_EN		BIT(0)
+#define IXGBE_ACI_LINK_25G_RS_528_FEC_EN	BIT(1)
+#define IXGBE_ACI_LINK_25G_RS_544_FEC_EN	BIT(2)
+#define IXGBE_ACI_FEC_MASK			GENMASK(2, 0)
+	/* Pacing Config */
+#define IXGBE_ACI_CFG_PACING_M		GENMASK(6, 3)
+#define IXGBE_ACI_CFG_PACING_TYPE_M	BIT(7)
+#define IXGBE_ACI_CFG_PACING_TYPE_AVG	0
+#define IXGBE_ACI_CFG_PACING_TYPE_FIXED	IXGBE_ACI_CFG_PACING_TYPE_M
+	/* External Device Power Ability */
+	u8 power_desc;
+#define IXGBE_ACI_PWR_CLASS_M			GENMASK(5, 0)
+#define IXGBE_ACI_LINK_PWR_BASET_LOW_HIGH	0
+#define IXGBE_ACI_LINK_PWR_BASET_HIGH		1
+#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_1		0
+#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_2		1
+#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_3		2
+#define IXGBE_ACI_LINK_PWR_QSFP_CLASS_4		3
+	__le16 link_speed;
+#define IXGBE_ACI_LINK_SPEED_M			GENMASK(10, 0)
+#define IXGBE_ACI_LINK_SPEED_10MB		BIT(0)
+#define IXGBE_ACI_LINK_SPEED_100MB		BIT(1)
+#define IXGBE_ACI_LINK_SPEED_1000MB		BIT(2)
+#define IXGBE_ACI_LINK_SPEED_2500MB		BIT(3)
+#define IXGBE_ACI_LINK_SPEED_5GB		BIT(4)
+#define IXGBE_ACI_LINK_SPEED_10GB		BIT(5)
+#define IXGBE_ACI_LINK_SPEED_20GB		BIT(6)
+#define IXGBE_ACI_LINK_SPEED_25GB		BIT(7)
+#define IXGBE_ACI_LINK_SPEED_40GB		BIT(8)
+#define IXGBE_ACI_LINK_SPEED_50GB		BIT(9)
+#define IXGBE_ACI_LINK_SPEED_100GB		BIT(10)
+#define IXGBE_ACI_LINK_SPEED_200GB		BIT(11)
+#define IXGBE_ACI_LINK_SPEED_UNKNOWN		BIT(15)
+	__le16 reserved3;
+	u8 ext_fec_status;
+#define IXGBE_ACI_LINK_RS_272_FEC_EN	BIT(0) /* RS 272 FEC enabled */
+	u8 reserved4;
+	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
+	/* Get link status version 2 link partner data */
+	__le64 lp_phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
+	__le64 lp_phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
+	u8 lp_fec_adv;
+#define IXGBE_ACI_LINK_LP_10G_KR_FEC_CAP	BIT(0)
+#define IXGBE_ACI_LINK_LP_25G_KR_FEC_CAP	BIT(1)
+#define IXGBE_ACI_LINK_LP_RS_528_FEC_CAP	BIT(2)
+#define IXGBE_ACI_LINK_LP_50G_KR_272_FEC_CAP	BIT(3)
+#define IXGBE_ACI_LINK_LP_100G_KR_272_FEC_CAP	BIT(4)
+#define IXGBE_ACI_LINK_LP_200G_KR_272_FEC_CAP	BIT(5)
+	u8 lp_fec_req;
+#define IXGBE_ACI_LINK_LP_10G_KR_FEC_REQ	BIT(0)
+#define IXGBE_ACI_LINK_LP_25G_KR_FEC_REQ	BIT(1)
+#define IXGBE_ACI_LINK_LP_RS_528_FEC_REQ	BIT(2)
+#define IXGBE_ACI_LINK_LP_KR_272_FEC_REQ	BIT(3)
+	u8 lp_flowcontrol;
+#define IXGBE_ACI_LINK_LP_PAUSE_ADV		BIT(0)
+#define IXGBE_ACI_LINK_LP_ASM_DIR_ADV		BIT(1)
+	u8 reserved5[5];
+} __packed;
+
+/* Set event mask command (direct 0x0613) */
+struct ixgbe_aci_cmd_set_event_mask {
+	u8	lport_num;
+	u8	reserved[7];
+	__le16	event_mask;
+#define IXGBE_ACI_LINK_EVENT_UPDOWN		BIT(1)
+#define IXGBE_ACI_LINK_EVENT_MEDIA_NA		BIT(2)
+#define IXGBE_ACI_LINK_EVENT_LINK_FAULT		BIT(3)
+#define IXGBE_ACI_LINK_EVENT_PHY_TEMP_ALARM	BIT(4)
+#define IXGBE_ACI_LINK_EVENT_EXCESSIVE_ERRORS	BIT(5)
+#define IXGBE_ACI_LINK_EVENT_SIGNAL_DETECT	BIT(6)
+#define IXGBE_ACI_LINK_EVENT_AN_COMPLETED	BIT(7)
+#define IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL	BIT(8)
+#define IXGBE_ACI_LINK_EVENT_PORT_TX_SUSPENDED	BIT(9)
+#define IXGBE_ACI_LINK_EVENT_TOPO_CONFLICT	BIT(10)
+#define IXGBE_ACI_LINK_EVENT_MEDIA_CONFLICT	BIT(11)
+#define IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL	BIT(12)
+	u8	reserved1[6];
+};
+
+struct ixgbe_aci_cmd_link_topo_params {
+	u8 lport_num;
+	u8 lport_num_valid;
+#define IXGBE_ACI_LINK_TOPO_PORT_NUM_VALID	BIT(0)
+	u8 node_type_ctx;
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_M		GENMASK(3, 0)
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_PHY	0
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_GPIO_CTRL	1
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_MUX_CTRL	2
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_LED_CTRL	3
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_LED	4
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_THERMAL	5
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CAGE	6
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_MEZZ	7
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_ID_EEPROM	8
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CLK_CTRL	9
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_CLK_MUX	10
+#define IXGBE_ACI_LINK_TOPO_NODE_TYPE_GPS	11
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_S		4
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_M		GENMASK(7, 4)
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_GLOBAL			0
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_BOARD			1
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_PORT			2
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE			3
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE_HANDLE		4
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_DIRECT_BUS_ACCESS		5
+#define IXGBE_ACI_LINK_TOPO_NODE_CTX_NODE_HANDLE_BUS_ADDRESS	6
+	u8 index;
+};
+
+struct ixgbe_aci_cmd_link_topo_addr {
+	struct ixgbe_aci_cmd_link_topo_params topo_params;
+	__le16 handle;
+/* Used to decode the handle field */
+#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_M		BIT(9)
+#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_LOM		BIT(9)
+#define IXGBE_ACI_LINK_TOPO_HANDLE_BRD_TYPE_MEZZ	0
+};
+
+/* Get Link Topology Handle (direct, 0x06E0) */
+struct ixgbe_aci_cmd_get_link_topo {
+	struct ixgbe_aci_cmd_link_topo_addr addr;
+	u8 node_part_num;
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_PCA9575		0x21
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_ZL30632_80032	0x24
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_SI5384		0x25
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_C827		0x31
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_GEN_CLK_MUX	0x47
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_GEN_GPS		0x48
+#define IXGBE_ACI_GET_LINK_TOPO_NODE_NR_E610_PTC	0x49
+	u8 rsvd[9];
+};
+
+/* Get Link Topology Pin (direct, 0x06E1) */
+struct ixgbe_aci_cmd_get_link_topo_pin {
+	struct ixgbe_aci_cmd_link_topo_addr addr;
+	u8 input_io_params;
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_GPIO	0
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RESET_N	1
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_INT_N	2
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_PRESENT_N	3
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_TX_DIS	4
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_MODSEL_N	5
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_LPMODE	6
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_TX_FAULT	7
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RX_LOSS	8
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RS0		9
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RS1		10
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_EEPROM_WP	11
+/* 12 repeats intentionally due to two different uses depending on context */
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_LED		12
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_RED_LED	12
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_GREEN_LED	13
+#define IXGBE_ACI_LINK_TOPO_IO_FUNC_BLUE_LED	14
+#define IXGBE_ACI_LINK_TOPO_INPUT_IO_TYPE_GPIO	3
+/* Use IXGBE_ACI_LINK_TOPO_NODE_TYPE_* for the type values */
+	u8 output_io_params;
+/* Use IXGBE_ACI_LINK_TOPO_NODE_TYPE_* for the type values */
+	u8 output_io_flags;
+#define IXGBE_ACI_LINK_TOPO_OUTPUT_POLARITY	BIT(5)
+#define IXGBE_ACI_LINK_TOPO_OUTPUT_VALUE	BIT(6)
+#define IXGBE_ACI_LINK_TOPO_OUTPUT_DRIVEN	BIT(7)
+	u8 rsvd[7];
+};
+
+/* Set Port Identification LED (direct, 0x06E9) */
+struct ixgbe_aci_cmd_set_port_id_led {
+	u8 lport_num;
+	u8 lport_num_valid;
+	u8 ident_mode;
+	u8 rsvd[13];
+};
+
+#define IXGBE_ACI_PORT_ID_PORT_NUM_VALID	BIT(0)
+#define IXGBE_ACI_PORT_IDENT_LED_ORIG		0
+#define IXGBE_ACI_PORT_IDENT_LED_BLINK		BIT(0)
+
+/* Read/Write SFF EEPROM command (indirect 0x06EE) */
+struct ixgbe_aci_cmd_sff_eeprom {
+	u8 lport_num;
+	u8 lport_num_valid;
+#define IXGBE_ACI_SFF_PORT_NUM_VALID		BIT(0)
+	__le16 i2c_bus_addr;
+#define IXGBE_ACI_SFF_I2CBUS_7BIT_M		GENMASK(6, 0)
+#define IXGBE_ACI_SFF_I2CBUS_10BIT_M		GENMASK(9, 0)
+#define IXGBE_ACI_SFF_I2CBUS_TYPE_M		BIT(10)
+#define IXGBE_ACI_SFF_I2CBUS_TYPE_7BIT		0
+#define IXGBE_ACI_SFF_I2CBUS_TYPE_10BIT		IXGBE_ACI_SFF_I2CBUS_TYPE_M
+#define IXGBE_ACI_SFF_NO_PAGE_BANK_UPDATE	0
+#define IXGBE_ACI_SFF_UPDATE_PAGE		1
+#define IXGBE_ACI_SFF_UPDATE_BANK		2
+#define IXGBE_ACI_SFF_UPDATE_PAGE_BANK		3
+#define IXGBE_ACI_SFF_IS_WRITE			BIT(15)
+	__le16 i2c_offset;
+	u8 module_bank;
+	u8 module_page;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* NVM Read command (indirect 0x0701)
+ * NVM Erase commands (direct 0x0702)
+ * NVM Write commands (indirect 0x0703)
+ * NVM Write Activate commands (direct 0x0707)
+ * NVM Shadow RAM Dump commands (direct 0x0707)
+ */
+struct ixgbe_aci_cmd_nvm {
+#define IXGBE_ACI_NVM_MAX_OFFSET	0xFFFFFF
+	__le16 offset_low;
+	u8 offset_high; /* For Write Activate offset_high is used as flags2 */
+#define IXGBE_ACI_NVM_OFFSET_HI_A_MASK  GENMASK(15, 8)
+#define IXGBE_ACI_NVM_OFFSET_HI_U_MASK	GENMASK(23, 16)
+	u8 cmd_flags;
+#define IXGBE_ACI_NVM_LAST_CMD		BIT(0)
+#define IXGBE_ACI_NVM_PCIR_REQ		BIT(0) /* Used by NVM Write reply */
+#define IXGBE_ACI_NVM_PRESERVE_ALL	BIT(1)
+#define IXGBE_ACI_NVM_ACTIV_SEL_NVM	BIT(3) /* Write Activate/SR Dump only */
+#define IXGBE_ACI_NVM_ACTIV_SEL_OROM	BIT(4)
+#define IXGBE_ACI_NVM_ACTIV_SEL_NETLIST	BIT(5)
+#define IXGBE_ACI_NVM_SPECIAL_UPDATE	BIT(6)
+#define IXGBE_ACI_NVM_REVERT_LAST_ACTIV	BIT(6) /* Write Activate only */
+#define IXGBE_ACI_NVM_FLASH_ONLY	BIT(7)
+#define IXGBE_ACI_NVM_RESET_LVL_M	GENMASK(1, 0) /* Write reply only */
+#define IXGBE_ACI_NVM_POR_FLAG		0
+#define IXGBE_ACI_NVM_PERST_FLAG	1
+#define IXGBE_ACI_NVM_EMPR_FLAG		2
+#define IXGBE_ACI_NVM_EMPR_ENA		BIT(0) /* Write Activate reply only */
+#define IXGBE_ACI_NVM_NO_PRESERVATION	0x0
+#define IXGBE_ACI_NVM_PRESERVE_SELECTED	0x6
+
+	/* For Write Activate, several flags are sent as part of a separate
+	 * flags2 field using a separate byte. For simplicity of the software
+	 * interface, we pass the flags as a 16 bit value so these flags are
+	 * all offset by 8 bits
+	 */
+#define IXGBE_ACI_NVM_ACTIV_REQ_EMPR	BIT(8) /* NVM Write Activate only */
+	__le16 module_typeid;
+	__le16 length;
+#define IXGBE_ACI_NVM_ERASE_LEN	0xFFFF
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* NVM Module_Type ID, needed offset and read_len for
+ * struct ixgbe_aci_cmd_nvm.
+ */
+#define IXGBE_ACI_NVM_START_POINT		0
+
+/* NVM Checksum Command (direct, 0x0706) */
+struct ixgbe_aci_cmd_nvm_checksum {
+	u8 flags;
+#define IXGBE_ACI_NVM_CHECKSUM_VERIFY	BIT(0)
+#define IXGBE_ACI_NVM_CHECKSUM_RECALC	BIT(1)
+	u8 rsvd;
+	__le16 checksum; /* Used only by response */
+#define IXGBE_ACI_NVM_CHECKSUM_CORRECT	0xBABA
+	u8 rsvd2[12];
+};
+
+/* Used for NVM Set Package Data command - 0x070A */
+struct ixgbe_aci_cmd_nvm_pkg_data {
+	u8 reserved[3];
+	u8 cmd_flags;
+#define IXGBE_ACI_NVM_PKG_DELETE	BIT(0) /* used for command call */
+
+	u32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Used for Pass Component Table command - 0x070B */
+struct ixgbe_aci_cmd_nvm_pass_comp_tbl {
+	u8 component_response; /* Response only */
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED		0x0
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE	0x1
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_NOT_BE_UPDATED	0x2
+#define IXGBE_ACI_NVM_PASS_COMP_PARTIAL_CHECK		0x3
+	u8 component_response_code; /* Response only */
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED_CODE	0x0
+#define IXGBE_ACI_NVM_PASS_COMP_STAMP_IDENTICAL_CODE	0x1
+#define IXGBE_ACI_NVM_PASS_COMP_STAMP_LOWER		0x2
+#define IXGBE_ACI_NVM_PASS_COMP_INVALID_STAMP_CODE	0x3
+#define IXGBE_ACI_NVM_PASS_COMP_CONFLICT_CODE		0x4
+#define IXGBE_ACI_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE	0x5
+#define IXGBE_ACI_NVM_PASS_COMP_NOT_SUPPORTED_CODE	0x6
+#define IXGBE_ACI_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE	0x7
+#define IXGBE_ACI_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE	0x8
+#define IXGBE_ACI_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE	0xA
+#define IXGBE_ACI_NVM_PASS_COMP_VER_STR_LOWER_CODE	0xB
+	u8 reserved;
+	u8 transfer_flag;
+	__le32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+struct ixgbe_aci_cmd_nvm_comp_tbl {
+	__le16 comp_class;
+#define NVM_COMP_CLASS_ALL_FW		0x000A
+
+	__le16 comp_id;
+#define NVM_COMP_ID_OROM		0x5
+#define NVM_COMP_ID_NVM			0x6
+#define NVM_COMP_ID_NETLIST		0x8
+
+	u8 comp_class_idx;
+#define FWU_COMP_CLASS_IDX_NOT_USE	0x0
+
+	__le32 comp_cmp_stamp;
+	u8 cvs_type;
+#define NVM_CVS_TYPE_ASCII		0x1
+
+	u8 cvs_len;
+	u8 cvs[]; /* Component Version String */
+} __packed;
+
+/**
+ * struct ixgbe_aci_desc - Admin Command (AC) descriptor
+ * @flags: IXGBE_ACI_FLAG_* flags
+ * @opcode: Admin command opcode
+ * @datalen: length in bytes of indirect/external data buffer
+ * @retval: return value from firmware
+ * @cookie_high: opaque data high-half
+ * @cookie_low: opaque data low-half
+ * @params: command-specific parameters
+ *
+ * Descriptor format for commands the driver posts via the
+ * Admin Command Interface (ACI).
+ * The firmware writes back onto the command descriptor and returns
+ * the result of the command. Asynchronous events that are not an immediate
+ * result of the command are written to the Admin Command Interface (ACI) using
+ * the same descriptor format. Descriptors are in little-endian notation with
+ * 32-bit words.
+ */
+struct ixgbe_aci_desc {
+	__le16 flags;
+	__le16 opcode;
+	__le16 datalen;
+	__le16 retval;
+	__le32 cookie_high;
+	__le32 cookie_low;
+	union {
+		u8 raw[16];
+		struct ixgbe_aci_cmd_get_ver get_ver;
+		struct ixgbe_aci_cmd_driver_ver driver_ver;
+		struct ixgbe_aci_cmd_get_exp_err exp_err;
+		struct ixgbe_aci_cmd_req_res res_owner;
+		struct ixgbe_aci_cmd_list_caps get_cap;
+		struct ixgbe_aci_cmd_disable_rxen disable_rxen;
+		struct ixgbe_aci_cmd_get_phy_caps get_phy;
+		struct ixgbe_aci_cmd_set_phy_cfg set_phy;
+		struct ixgbe_aci_cmd_restart_an restart_an;
+		struct ixgbe_aci_cmd_get_link_status get_link_status;
+		struct ixgbe_aci_cmd_set_event_mask set_event_mask;
+		struct ixgbe_aci_cmd_set_port_id_led set_port_id_led;
+		struct ixgbe_aci_cmd_get_link_topo get_link_topo;
+		struct ixgbe_aci_cmd_get_link_topo_pin get_link_topo_pin;
+		struct ixgbe_aci_cmd_sff_eeprom read_write_sff_param;
+		struct ixgbe_aci_cmd_nvm nvm;
+		struct ixgbe_aci_cmd_nvm_checksum nvm_checksum;
+		struct ixgbe_aci_cmd_nvm_pkg_data pkg_data;
+		struct ixgbe_aci_cmd_nvm_pass_comp_tbl pass_comp_tbl;
+	} params;
+};
+
+/* E610-specific adapter context structures */
+
+struct ixgbe_link_status {
+	/* Refer to ixgbe_aci_phy_type for bits definition */
+	u64 phy_type_low;
+	u64 phy_type_high;
+	u16 max_frame_size;
+	u16 link_speed;
+	u16 req_speeds;
+	u8 topo_media_conflict;
+	u8 link_cfg_err;
+	u8 lse_ena;	/* Link Status Event notification */
+	u8 link_info;
+	u8 an_info;
+	u8 ext_info;
+	u8 fec_info;
+	u8 pacing;
+	/* Refer to #define from module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE]
+	 * of ixgbe_aci_get_phy_caps structure
+	 */
+	u8 module_type[IXGBE_ACI_MODULE_TYPE_TOTAL_BYTE];
+};
+
+/* Common HW capabilities for SW use */
+struct ixgbe_hw_caps {
+	/* Write CSR protection */
+	u64 wr_csr_prot;
+	u32 switching_mode;
+	/* switching mode supported - EVB switching (including cloud) */
+#define IXGBE_NVM_IMAGE_TYPE_EVB		0x0
+
+	/* Manageability mode & supported protocols over MCTP */
+	u32 mgmt_mode;
+#define IXGBE_MGMT_MODE_PASS_THRU_MODE_M	GENMASK(3, 0)
+#define IXGBE_MGMT_MODE_CTL_INTERFACE_M		GENMASK(7, 4)
+#define IXGBE_MGMT_MODE_REDIR_SB_INTERFACE_M	GENMASK(11, 8)
+
+	u32 mgmt_protocols_mctp;
+#define IXGBE_MGMT_MODE_PROTO_RSVD	BIT(0)
+#define IXGBE_MGMT_MODE_PROTO_PLDM	BIT(1)
+#define IXGBE_MGMT_MODE_PROTO_OEM	BIT(2)
+#define IXGBE_MGMT_MODE_PROTO_NC_SI	BIT(3)
+
+	u32 os2bmc;
+	u32 valid_functions;
+	/* DCB capabilities */
+	u32 active_tc_bitmap;
+	u32 maxtc;
+
+	/* RSS related capabilities */
+	u32 rss_table_size;		/* 512 for PFs and 64 for VFs */
+	u32 rss_table_entry_width;	/* RSS Entry width in bits */
+
+	/* Tx/Rx queues */
+	u32 num_rxq;			/* Number/Total Rx queues */
+	u32 rxq_first_id;		/* First queue ID for Rx queues */
+	u32 num_txq;			/* Number/Total Tx queues */
+	u32 txq_first_id;		/* First queue ID for Tx queues */
+
+	/* MSI-X vectors */
+	u32 num_msix_vectors;
+	u32 msix_vector_first_id;
+
+	/* Max MTU for function or device */
+	u32 max_mtu;
+
+	/* WOL related */
+	u32 num_wol_proxy_fltr;
+	u32 wol_proxy_vsi_seid;
+
+	/* LED/SDP pin count */
+	u32 led_pin_num;
+	u32 sdp_pin_num;
+
+	/* LED/SDP - Supports up to 12 LED pins and 8 SDP signals */
+#define IXGBE_MAX_SUPPORTED_GPIO_LED	12
+#define IXGBE_MAX_SUPPORTED_GPIO_SDP	8
+	u8 led[IXGBE_MAX_SUPPORTED_GPIO_LED];
+	u8 sdp[IXGBE_MAX_SUPPORTED_GPIO_SDP];
+	/* SR-IOV virtualization */
+	u8 sr_iov_1_1;			/* SR-IOV enabled */
+	/* VMDQ */
+	u8 vmdq;			/* VMDQ supported */
+
+	/* EVB capabilities */
+	u8 evb_802_1_qbg;		/* Edge Virtual Bridging */
+	u8 evb_802_1_qbh;		/* Bridge Port Extension */
+
+	u8 dcb;
+	u8 iscsi;
+	u8 ieee_1588;
+	u8 mgmt_cem;
+
+	/* WoL and APM support */
+#define IXGBE_WOL_SUPPORT_M		BIT(0)
+#define IXGBE_ACPI_PROG_MTHD_M		BIT(1)
+#define IXGBE_PROXY_SUPPORT_M		BIT(2)
+	u8 apm_wol_support;
+	u8 acpi_prog_mthd;
+	u8 proxy_support;
+	bool nvm_update_pending_nvm;
+	bool nvm_update_pending_orom;
+	bool nvm_update_pending_netlist;
+#define IXGBE_NVM_PENDING_NVM_IMAGE		BIT(0)
+#define IXGBE_NVM_PENDING_OROM			BIT(1)
+#define IXGBE_NVM_PENDING_NETLIST		BIT(2)
+	bool sec_rev_disabled;
+	bool update_disabled;
+	bool nvm_unified_update;
+	bool netlist_auth;
+#define IXGBE_NVM_MGMT_SEC_REV_DISABLED		BIT(0)
+#define IXGBE_NVM_MGMT_UPDATE_DISABLED		BIT(1)
+#define IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT	BIT(3)
+#define IXGBE_NVM_MGMT_NETLIST_AUTH_SUPPORT	BIT(5)
+	bool no_drop_policy_support;
+	/* PCIe reset avoidance */
+	bool pcie_reset_avoidance; /* false: not supported, true: supported */
+	/* Post update reset restriction */
+	bool reset_restrict_support; /* false: not supported, true: supported */
+
+	/* External topology device images within the NVM */
+#define IXGBE_EXT_TOPO_DEV_IMG_COUNT	4
+	u32 ext_topo_dev_img_ver_high[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+	u32 ext_topo_dev_img_ver_low[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+	u8 ext_topo_dev_img_part_num[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+#define IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_S	8
+#define IXGBE_EXT_TOPO_DEV_IMG_PART_NUM_M	GENMASK(15, 8)
+	bool ext_topo_dev_img_load_en[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+#define IXGBE_EXT_TOPO_DEV_IMG_LOAD_EN	BIT(0)
+	bool ext_topo_dev_img_prog_en[IXGBE_EXT_TOPO_DEV_IMG_COUNT];
+#define IXGBE_EXT_TOPO_DEV_IMG_PROG_EN	BIT(1)
+} __packed;
+
+#define IXGBE_OROM_CIV_SIGNATURE	"$CIV"
+
+struct ixgbe_orom_civd_info {
+	u8 signature[4];	/* Must match ASCII '$CIV' characters */
+	u8 checksum;		/* Simple modulo 256 sum of all structure bytes must equal 0 */
+	__le32 combo_ver;	/* Combo Image Version number */
+	u8 combo_name_len;	/* Length of the unicode combo image version string, max of 32 */
+	__le16 combo_name[32];	/* Unicode string representing the Combo Image version */
+};
+
+/* Function specific capabilities */
+struct ixgbe_hw_func_caps {
+	u32 num_allocd_vfs;		/* Number of allocated VFs */
+	u32 vf_base_id;			/* Logical ID of the first VF */
+	u32 guar_num_vsi;
+	struct ixgbe_hw_caps common_cap;
+	bool no_drop_policy_ena;
+};
+
+/* Device wide capabilities */
+struct ixgbe_hw_dev_caps {
+	struct ixgbe_hw_caps common_cap;
+	u32 num_vfs_exposed;		/* Total number of VFs exposed */
+	u32 num_vsi_allocd_to_host;	/* Excluding EMP VSI */
+	u32 num_flow_director_fltr;	/* Number of FD filters available */
+	u32 num_funcs;
+};
+
+/* ACI event information */
+struct ixgbe_aci_event {
+	struct ixgbe_aci_desc desc;
+	u8 *msg_buf;
+	u16 msg_len;
+	u16 buf_len;
+};
+
+struct ixgbe_aci_info {
+	struct mutex lock;		/* admin command interface lock */
+	enum ixgbe_aci_err last_status;	/* last status of sent admin command */
+};
+
+enum ixgbe_bank_select {
+	IXGBE_ACTIVE_FLASH_BANK,
+	IXGBE_INACTIVE_FLASH_BANK,
+};
+
+/* Option ROM version information */
+struct ixgbe_orom_info {
+	u8 major;			/* Major version of OROM */
+	u8 patch;			/* Patch version of OROM */
+	u16 build;			/* Build version of OROM */
+	u32 srev;			/* Security revision */
+};
+
+/* NVM version information */
+struct ixgbe_nvm_info {
+	u32 eetrack;
+	u32 srev;
+	u8 major;
+	u8 minor;
+} __packed;
+
+/* netlist version information */
+struct ixgbe_netlist_info {
+	u32 major;			/* major high/low */
+	u32 minor;			/* minor high/low */
+	u32 type;			/* type high/low */
+	u32 rev;			/* revision high/low */
+	u32 hash;			/* SHA-1 hash word */
+	u16 cust_ver;			/* customer version */
+} __packed;
+
+/* Enumeration of possible flash banks for the NVM, OROM, and Netlist modules
+ * of the flash image.
+ */
+enum ixgbe_flash_bank {
+	IXGBE_INVALID_FLASH_BANK,
+	IXGBE_1ST_FLASH_BANK,
+	IXGBE_2ND_FLASH_BANK,
+};
+
+/* information for accessing NVM, OROM, and Netlist flash banks */
+struct ixgbe_bank_info {
+	u32 nvm_ptr;				/* Pointer to 1st NVM bank */
+	u32 nvm_size;				/* Size of NVM bank */
+	u32 orom_ptr;				/* Pointer to 1st OROM bank */
+	u32 orom_size;				/* Size of OROM bank */
+	u32 netlist_ptr;			/* Ptr to 1st Netlist bank */
+	u32 netlist_size;			/* Size of Netlist bank */
+	enum ixgbe_flash_bank nvm_bank;		/* Active NVM bank */
+	enum ixgbe_flash_bank orom_bank;	/* Active OROM bank */
+	enum ixgbe_flash_bank netlist_bank;	/* Active Netlist bank */
+};
+
+/* Flash Chip Information */
+struct ixgbe_flash_info {
+	struct ixgbe_orom_info orom;	/* Option ROM version info */
+	u32 flash_size;			/* Available flash size in bytes */
+	struct ixgbe_nvm_info nvm;	/* NVM version information */
+	struct ixgbe_netlist_info netlist;	/* Netlist version info */
+	struct ixgbe_bank_info banks;	/* Flash Bank information */
+	u16 sr_words;			/* Shadow RAM size in words */
+	u8 blank_nvm_mode;		/* is NVM empty (no FW present) */
+};
+
+#endif /* _IXGBE_TYPE_E610_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index 81e1df83f136..f1ab95aa8c83 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -66,7 +66,9 @@ int ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw, ixgbe_link_speed speed,
  *  Resets the hardware by resetting the transmit and receive units, masks
  *  and clears all interrupts, perform a PHY reset, and perform a link (MAC)
  *  reset.
- **/
+ *
+ *  Return: 0 on success or negative value on failure
+ */
 int ixgbe_reset_hw_X540(struct ixgbe_hw *hw)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
@@ -133,10 +135,14 @@ mac_reset_top:
 	hw->mac.num_rar_entries = IXGBE_X540_MAX_TX_QUEUES;
 	hw->mac.ops.init_rx_addrs(hw);
 
+	/* The following is not supported by E610. */
+	if (hw->mac.type == ixgbe_mac_e610)
+		return status;
+
 	/* Store the permanent SAN mac address */
 	hw->mac.ops.get_san_mac_addr(hw, hw->mac.san_addr);
 
-	/* Add the SAN MAC address to the RAR only if it's a valid address */
+	/* Add the SAN MAC address to RAR if it's a valid address */
 	if (is_valid_ether_addr(hw->mac.san_addr)) {
 		/* Save the SAN MAC RAR index */
 		hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1;
@@ -888,6 +894,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_X540 = {
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_X540,
 	.validate_checksum      = &ixgbe_validate_eeprom_checksum_X540,
 	.update_checksum        = &ixgbe_update_eeprom_checksum_X540,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_X540 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h
index b69a680d3ab5..6ed360c5b605 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h
@@ -1,5 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
+
+#ifndef _IXGBE_X540_H_
+#define _IXGBE_X540_H_
 
 #include "ixgbe_type.h"
 
@@ -17,3 +20,5 @@ int ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask);
 void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask);
 void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw);
 int ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw);
+
+#endif /* _IXGBE_X540_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index d9a8cf018d3b..1d2acdb64f45 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include "ixgbe_x540.h"
+#include "ixgbe_x550.h"
 #include "ixgbe_type.h"
 #include "ixgbe_common.h"
 #include "ixgbe_mbx.h"
@@ -2770,9 +2771,9 @@ static int ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx)
  *  semaphore, -EIO when command fails or -ENIVAL when incorrect
  *  params passed.
  **/
-static int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
-				     u8 build, u8 sub, u16 len,
-				     const char *driver_ver)
+int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
+			      u8 build, u8 sub, u16 len,
+			      const char *driver_ver)
 {
 	struct ixgbe_hic_drv_info2 fw_cmd;
 	int ret_val;
@@ -3505,14 +3506,14 @@ mac_reset_top:
 	return status;
 }
 
-/** ixgbe_set_ethertype_anti_spoofing_X550 - Enable/Disable Ethertype
+/** ixgbe_set_ethertype_anti_spoofing_x550 - Enable/Disable Ethertype
  *	anti-spoofing
  *  @hw:  pointer to hardware structure
  *  @enable: enable or disable switch for Ethertype anti-spoofing
  *  @vf: Virtual Function pool - VF Pool to set for Ethertype anti-spoofing
  **/
-static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw,
-						   bool enable, int vf)
+void ixgbe_set_ethertype_anti_spoofing_x550(struct ixgbe_hw *hw,
+					    bool enable, int vf)
 {
 	int vf_target_reg = vf >> 3;
 	int vf_target_shift = vf % 8 + IXGBE_SPOOF_ETHERTYPEAS_SHIFT;
@@ -3527,14 +3528,14 @@ static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw,
 	IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), pfvfspoof);
 }
 
-/** ixgbe_set_source_address_pruning_X550 - Enable/Disbale src address pruning
+/** ixgbe_set_source_address_pruning_x550 - Enable/Disable src address pruning
  *  @hw: pointer to hardware structure
  *  @enable: enable or disable source address pruning
  *  @pool: Rx pool to set source address pruning for
  **/
-static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw,
-						  bool enable,
-						  unsigned int pool)
+void ixgbe_set_source_address_pruning_x550(struct ixgbe_hw *hw,
+					   bool enable,
+					   unsigned int pool)
 {
 	u64 pfflp;
 
@@ -3831,9 +3832,9 @@ static int ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr,
 	.set_mac_anti_spoofing		= &ixgbe_set_mac_anti_spoofing, \
 	.set_vlan_anti_spoofing		= &ixgbe_set_vlan_anti_spoofing, \
 	.set_source_address_pruning	= \
-				&ixgbe_set_source_address_pruning_X550, \
+				&ixgbe_set_source_address_pruning_x550, \
 	.set_ethertype_anti_spoofing	= \
-				&ixgbe_set_ethertype_anti_spoofing_X550, \
+				&ixgbe_set_ethertype_anti_spoofing_x550, \
 	.disable_rx_buff		= &ixgbe_disable_rx_buff_generic, \
 	.enable_rx_buff			= &ixgbe_enable_rx_buff_generic, \
 	.get_thermal_sensor_data	= NULL, \
@@ -3958,6 +3959,7 @@ static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = {
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_X550, \
 	.update_checksum	= &ixgbe_update_eeprom_checksum_X550, \
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_X550, \
+	.read_pba_string        = &ixgbe_read_pba_string_generic, \
 
 static const struct ixgbe_eeprom_operations eeprom_ops_X550 = {
 	X550_COMMON_EEP
@@ -4047,7 +4049,7 @@ static const u32 ixgbe_mvals_X550EM_x[IXGBE_MVALS_IDX_LIMIT] = {
 	IXGBE_MVALS_INIT(X550EM_x)
 };
 
-static const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = {
+const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = {
 	IXGBE_MVALS_INIT(X550EM_a)
 };
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h
new file mode 100644
index 000000000000..3e4092f8da3e
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IXGBE_X550_H_
+#define _IXGBE_X550_H_
+
+#include "ixgbe_type.h"
+
+extern const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT];
+
+int ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min,
+			      u8 build, u8 sub, u16 len,
+			      const char *driver_ver);
+void ixgbe_set_source_address_pruning_x550(struct ixgbe_hw *hw,
+					   bool enable,
+					   unsigned int pool);
+void ixgbe_set_ethertype_anti_spoofing_x550(struct ixgbe_hw *hw,
+					    bool enable, int vf);
+
+#endif /* _IXGBE_X550_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 3e3b471e53f0..ac58964b2f08 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -508,7 +508,7 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 
 int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ring *ring;
 
 	if (test_bit(__IXGBE_DOWN, &adapter->state))
diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h
index 5f08779c0e4e..a9bc96f6399d 100644
--- a/drivers/net/ethernet/intel/ixgbevf/defines.h
+++ b/drivers/net/ethernet/intel/ixgbevf/defines.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef _IXGBEVF_DEFINES_H_
 #define _IXGBEVF_DEFINES_H_
@@ -16,6 +16,9 @@
 #define IXGBE_DEV_ID_X550_VF_HV		0x1564
 #define IXGBE_DEV_ID_X550EM_X_VF_HV	0x15A9
 
+#define IXGBE_DEV_ID_E610_VF		0x57AD
+#define IXGBE_SUBDEV_ID_E610_VF_HV	0x00FF
+
 #define IXGBE_VF_IRQ_CLEAR_MASK		7
 #define IXGBE_VF_MAX_TX_QUEUES		8
 #define IXGBE_VF_MAX_RX_QUEUES		8
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
index 66cf17f19408..65580b9cb06f 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -201,6 +201,7 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec,
 
 /**
  * ixgbevf_ipsec_parse_proto_keys - find the key and salt based on the protocol
+ * @dev: pointer to net device to program
  * @xs: pointer to xfrm_state struct
  * @mykey: pointer to key array to populate
  * @mysalt: pointer to salt value to populate
@@ -208,10 +209,10 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec,
  * This copies the protocol keys and salt to our own data tables.  The
  * 82599 family only supports the one algorithm.
  **/
-static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
+static int ixgbevf_ipsec_parse_proto_keys(struct net_device *dev,
+					  struct xfrm_state *xs,
 					  u32 *mykey, u32 *mysalt)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	unsigned char *key_data;
 	char *alg_name = NULL;
 	int key_len;
@@ -256,13 +257,14 @@ static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
 
 /**
  * ixgbevf_ipsec_add_sa - program device with a security association
+ * @dev: pointer to net device to program
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
  **/
-static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
+static int ixgbevf_ipsec_add_sa(struct net_device *dev,
+				struct xfrm_state *xs,
 				struct netlink_ext_ack *extack)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbevf_adapter *adapter;
 	struct ixgbevf_ipsec *ipsec;
 	u16 sa_idx;
@@ -310,7 +312,8 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 			rsa.decrypt = xs->ealg || xs->aead;
 
 		/* get the key and salt */
-		ret = ixgbevf_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt);
+		ret = ixgbevf_ipsec_parse_proto_keys(dev, xs, rsa.key,
+						     &rsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Rx SA table");
 			return ret;
@@ -363,7 +366,8 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 		if (xs->id.proto & IPPROTO_ESP)
 			tsa.encrypt = xs->ealg || xs->aead;
 
-		ret = ixgbevf_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt);
+		ret = ixgbevf_ipsec_parse_proto_keys(dev, xs, tsa.key,
+						     &tsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Tx SA table");
 			memset(&tsa, 0, sizeof(tsa));
@@ -388,11 +392,12 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 
 /**
  * ixgbevf_ipsec_del_sa - clear out this specific SA
+ * @dev: pointer to net device to program
  * @xs: pointer to transformer state struct
  **/
-static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
+static void ixgbevf_ipsec_del_sa(struct net_device *dev,
+				 struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbevf_adapter *adapter;
 	struct ixgbevf_ipsec *ipsec;
 	u16 sa_idx;
@@ -428,30 +433,9 @@ static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
 	}
 }
 
-/**
- * ixgbevf_ipsec_offload_ok - can this packet use the xfrm hw offload
- * @skb: current data packet
- * @xs: pointer to transformer state struct
- **/
-static bool ixgbevf_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
-{
-	if (xs->props.family == AF_INET) {
-		/* Offload with IPv4 options is not supported yet */
-		if (ip_hdr(skb)->ihl != 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-
-	return true;
-}
-
 static const struct xfrmdev_ops ixgbevf_xfrmdev_ops = {
 	.xdo_dev_state_add = ixgbevf_ipsec_add_sa,
 	.xdo_dev_state_delete = ixgbevf_ipsec_del_sa,
-	.xdo_dev_offload_ok = ixgbevf_ipsec_offload_ok,
 };
 
 /**
@@ -629,7 +613,6 @@ void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter)
 
 	switch (adapter->hw.api_version) {
 	case ixgbe_mbox_api_14:
-	case ixgbe_mbox_api_15:
 		break;
 	default:
 		return;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 130cb868774c..4384e892f967 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef _IXGBEVF_H_
 #define _IXGBEVF_H_
@@ -418,6 +418,8 @@ enum ixgbevf_boards {
 	board_X550EM_x_vf,
 	board_X550EM_x_vf_hv,
 	board_x550em_a_vf,
+	board_e610_vf,
+	board_e610_vf_hv,
 };
 
 enum ixgbevf_xcast_modes {
@@ -434,12 +436,13 @@ extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_info;
 extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops;
 extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops_legacy;
 extern const struct ixgbevf_info ixgbevf_x550em_a_vf_info;
+extern const struct ixgbevf_info ixgbevf_e610_vf_info;
 
 extern const struct ixgbevf_info ixgbevf_82599_vf_hv_info;
 extern const struct ixgbevf_info ixgbevf_X540_vf_hv_info;
 extern const struct ixgbevf_info ixgbevf_X550_vf_hv_info;
 extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_hv_info;
-extern const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops;
+extern const struct ixgbevf_info ixgbevf_e610_vf_hv_info;
 
 /* needed by ethtool.c */
 extern const char ixgbevf_driver_name[];
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 149911e3002a..535d0f71f521 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 /******************************************************************************
  Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code
@@ -39,7 +39,7 @@ static const char ixgbevf_driver_string[] =
 	"Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver";
 
 static char ixgbevf_copyright[] =
-	"Copyright (c) 2009 - 2018 Intel Corporation.";
+	"Copyright (c) 2009 - 2024 Intel Corporation.";
 
 static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
 	[board_82599_vf]	= &ixgbevf_82599_vf_info,
@@ -51,6 +51,8 @@ static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
 	[board_X550EM_x_vf]	= &ixgbevf_X550EM_x_vf_info,
 	[board_X550EM_x_vf_hv]	= &ixgbevf_X550EM_x_vf_hv_info,
 	[board_x550em_a_vf]	= &ixgbevf_x550em_a_vf_info,
+	[board_e610_vf]         = &ixgbevf_e610_vf_info,
+	[board_e610_vf_hv]      = &ixgbevf_e610_vf_hv_info,
 };
 
 /* ixgbevf_pci_tbl - PCI Device ID Table
@@ -71,6 +73,9 @@ static const struct pci_device_id ixgbevf_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF), board_X550EM_x_vf },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF_HV), board_X550EM_x_vf_hv},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_VF), board_x550em_a_vf },
+	{PCI_VDEVICE_SUB(INTEL, IXGBE_DEV_ID_E610_VF, PCI_ANY_ID,
+			 IXGBE_SUBDEV_ID_E610_VF_HV), board_e610_vf_hv},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_VF), board_e610_vf},
 	/* required last entry */
 	{0, }
 };
@@ -732,10 +737,6 @@ static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring,
 				    union ixgbe_adv_rx_desc *rx_desc,
 				    struct sk_buff *skb)
 {
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	/* verify that the packet does not have any known errors */
 	if (unlikely(ixgbevf_test_staterr(rx_desc,
 					  IXGBE_RXDADV_ERR_FRAME_ERR_MASK))) {
@@ -1044,9 +1045,9 @@ static int ixgbevf_xmit_xdp_ring(struct ixgbevf_ring *ring,
 	return IXGBEVF_XDP_TX;
 }
 
-static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
-				       struct ixgbevf_ring  *rx_ring,
-				       struct xdp_buff *xdp)
+static int ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
+			   struct ixgbevf_ring *rx_ring,
+			   struct xdp_buff *xdp)
 {
 	int result = IXGBEVF_XDP_PASS;
 	struct ixgbevf_ring *xdp_ring;
@@ -1080,7 +1081,7 @@ out_failure:
 		break;
 	}
 xdp_out:
-	return ERR_PTR(-result);
+	return result;
 }
 
 static unsigned int ixgbevf_rx_frame_truesize(struct ixgbevf_ring *rx_ring,
@@ -1122,6 +1123,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 	struct sk_buff *skb = rx_ring->skb;
 	bool xdp_xmit = false;
 	struct xdp_buff xdp;
+	int xdp_res = 0;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)
@@ -1165,11 +1167,11 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 			/* At larger PAGE_SIZE, frame_sz depend on len size */
 			xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, size);
 #endif
-			skb = ixgbevf_run_xdp(adapter, rx_ring, &xdp);
+			xdp_res = ixgbevf_run_xdp(adapter, rx_ring, &xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -IXGBEVF_XDP_TX) {
+		if (xdp_res) {
+			if (xdp_res == IXGBEVF_XDP_TX) {
 				xdp_xmit = true;
 				ixgbevf_rx_buffer_flip(rx_ring, rx_buffer,
 						       size);
@@ -1189,7 +1191,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		}
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
 			rx_buffer->pagecnt_bias++;
 			break;
@@ -1203,7 +1205,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 			continue;
 
 		/* verify the packet layout is correct */
-		if (ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) {
+		if (xdp_res || ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) {
 			skb = NULL;
 			continue;
 		}
@@ -2512,7 +2514,7 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter)
 
 	ixgbevf_napi_disable_all(adapter);
 
-	del_timer_sync(&adapter->service_timer);
+	timer_delete_sync(&adapter->service_timer);
 
 	/* disable transmits in the hardware now that interrupts are off */
 	for (i = 0; i < adapter->num_tx_queues; i++) {
@@ -3174,8 +3176,8 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter)
  **/
 static void ixgbevf_service_timer(struct timer_list *t)
 {
-	struct ixgbevf_adapter *adapter = from_timer(adapter, t,
-						     service_timer);
+	struct ixgbevf_adapter *adapter = timer_container_of(adapter, t,
+							     service_timer);
 
 	/* Reset the timer */
 	mod_timer(&adapter->service_timer, (HZ * 2) + jiffies);
@@ -4693,6 +4695,9 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	case ixgbe_mac_X540_vf:
 		dev_info(&pdev->dev, "Intel(R) X540 Virtual Function\n");
 		break;
+	case ixgbe_mac_e610_vf:
+		dev_info(&pdev->dev, "Intel(R) E610 Virtual Function\n");
+		break;
 	case ixgbe_mac_82599_vf:
 	default:
 		dev_info(&pdev->dev, "Intel(R) 82599 Virtual Function\n");
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c
index a55dd978f7ca..24d0237e7a99 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.c
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c
@@ -505,15 +505,3 @@ const struct ixgbe_mbx_operations ixgbevf_mbx_ops_legacy = {
 	.check_for_ack	= ixgbevf_check_for_ack_vf,
 	.check_for_rst	= ixgbevf_check_for_rst_vf,
 };
-
-/* Mailbox operations when running on Hyper-V.
- * On Hyper-V, PF/VF communication is not through the
- * hardware mailbox; this communication is through
- * a software mediated path.
- * Most mail box operations are noop while running on
- * Hyper-V.
- */
-const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops = {
-	.init_params	= ixgbevf_init_mbx_params_vf,
-	.check_for_rst	= ixgbevf_check_for_rst_vf,
-};
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index 1641d00d8ed3..da7a72ecce7a 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #include "vf.h"
 #include "ixgbevf.h"
@@ -1076,3 +1076,13 @@ const struct ixgbevf_info ixgbevf_x550em_a_vf_info = {
 	.mac = ixgbe_mac_x550em_a_vf,
 	.mac_ops = &ixgbevf_mac_ops,
 };
+
+const struct ixgbevf_info ixgbevf_e610_vf_info = {
+	.mac                    = ixgbe_mac_e610_vf,
+	.mac_ops                = &ixgbevf_mac_ops,
+};
+
+const struct ixgbevf_info ixgbevf_e610_vf_hv_info = {
+	.mac            = ixgbe_mac_e610_vf,
+	.mac_ops        = &ixgbevf_hv_mac_ops,
+};
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h
index b4eef5b6c172..2d791bc26ae4 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 1999 - 2018 Intel Corporation. */
+/* Copyright(c) 1999 - 2024 Intel Corporation. */
 
 #ifndef __IXGBE_VF_H__
 #define __IXGBE_VF_H__
@@ -54,6 +54,8 @@ enum ixgbe_mac_type {
 	ixgbe_mac_X550_vf,
 	ixgbe_mac_X550EM_x_vf,
 	ixgbe_mac_x550em_a_vf,
+	ixgbe_mac_e610,
+	ixgbe_mac_e610_vf,
 	ixgbe_num_macs
 };
 
diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c
index f20926669318..66d1d23b8ad2 100644
--- a/drivers/net/ethernet/intel/libeth/rx.c
+++ b/drivers/net/ethernet/intel/libeth/rx.c
@@ -186,7 +186,7 @@ err_buf:
 
 	return -ENOMEM;
 }
-EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, LIBETH);
+EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, "LIBETH");
 
 /**
  * libeth_rx_fq_destroy - destroy a &page_pool created by libeth
@@ -197,7 +197,7 @@ void libeth_rx_fq_destroy(struct libeth_fq *fq)
 	kvfree(fq->fqes);
 	page_pool_destroy(fq->pp);
 }
-EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_destroy, LIBETH);
+EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_destroy, "LIBETH");
 
 /**
  * libeth_rx_recycle_slow - recycle a libeth page from the NAPI context
@@ -209,7 +209,7 @@ void libeth_rx_recycle_slow(struct page *page)
 {
 	page_pool_recycle_direct(page->pp, page);
 }
-EXPORT_SYMBOL_NS_GPL(libeth_rx_recycle_slow, LIBETH);
+EXPORT_SYMBOL_NS_GPL(libeth_rx_recycle_slow, "LIBETH");
 
 /* Converting abstract packet type numbers into a software structure with
  * the packet parameters to do O(1) lookup on Rx.
@@ -251,7 +251,7 @@ void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt)
 	pt->hash_type |= libeth_rx_pt_xdp_iprot[pt->inner_prot];
 	pt->hash_type |= libeth_rx_pt_xdp_pl[pt->payload_layer];
 }
-EXPORT_SYMBOL_NS_GPL(libeth_rx_pt_gen_hash_type, LIBETH);
+EXPORT_SYMBOL_NS_GPL(libeth_rx_pt_gen_hash_type, "LIBETH");
 
 /* Module */
 
diff --git a/drivers/net/ethernet/intel/libie/rx.c b/drivers/net/ethernet/intel/libie/rx.c
index aceb8d8813c4..66a9825fe11f 100644
--- a/drivers/net/ethernet/intel/libie/rx.c
+++ b/drivers/net/ethernet/intel/libie/rx.c
@@ -116,8 +116,8 @@ const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM] = {
 	LIBIE_RX_PT_IP(4),
 	LIBIE_RX_PT_IP(6),
 };
-EXPORT_SYMBOL_NS_GPL(libie_rx_pt_lut, LIBIE);
+EXPORT_SYMBOL_NS_GPL(libie_rx_pt_lut, "LIBIE");
 
 MODULE_DESCRIPTION("Intel(R) Ethernet common library");
-MODULE_IMPORT_NS(LIBETH);
+MODULE_IMPORT_NS("LIBETH");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index 87c7e6251a4f..891a94d89f4b 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -900,7 +900,8 @@ static void korina_check_media(struct net_device *dev, unsigned int init_media)
 
 static void korina_poll_media(struct timer_list *t)
 {
-	struct korina_private *lp = from_timer(lp, t, media_check_timer);
+	struct korina_private *lp = timer_container_of(lp, t,
+						       media_check_timer);
 	struct net_device *dev = lp->dev;
 
 	korina_check_media(dev, 0);
@@ -1239,7 +1240,7 @@ static int korina_close(struct net_device *dev)
 	struct korina_private *lp = netdev_priv(dev);
 	u32 tmp;
 
-	del_timer(&lp->media_check_timer);
+	timer_delete(&lp->media_check_timer);
 
 	/* Disable interrupts */
 	disable_irq(lp->rx_irq);
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 660dff5426e7..83ce3bfefa5c 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -90,7 +90,6 @@ struct ltq_etop_priv {
 	struct net_device *netdev;
 	struct platform_device *pdev;
 	struct ltq_eth_data *pldata;
-	struct resource *res;
 
 	struct mii_bus *mii_bus;
 
@@ -643,31 +642,14 @@ ltq_etop_probe(struct platform_device *pdev)
 {
 	struct net_device *dev;
 	struct ltq_etop_priv *priv;
-	struct resource *res;
 	int err;
 	int i;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "failed to get etop resource\n");
-		err = -ENOENT;
-		goto err_out;
-	}
-
-	res = devm_request_mem_region(&pdev->dev, res->start,
-				      resource_size(res), dev_name(&pdev->dev));
-	if (!res) {
-		dev_err(&pdev->dev, "failed to request etop resource\n");
-		err = -EBUSY;
-		goto err_out;
-	}
-
-	ltq_etop_membase = devm_ioremap(&pdev->dev, res->start,
-					resource_size(res));
-	if (!ltq_etop_membase) {
+	ltq_etop_membase = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ltq_etop_membase)) {
 		dev_err(&pdev->dev, "failed to remap etop engine %d\n",
 			pdev->id);
-		err = -ENOMEM;
+		err = PTR_ERR(ltq_etop_membase);
 		goto err_out;
 	}
 
@@ -679,7 +661,6 @@ ltq_etop_probe(struct platform_device *pdev)
 	dev->netdev_ops = &ltq_eth_netdev_ops;
 	dev->ethtool_ops = &ltq_etop_ethtool_ops;
 	priv = netdev_priv(dev);
-	priv->res = res;
 	priv->pdev = pdev;
 	priv->pldata = dev_get_platdata(&pdev->dev);
 	priv->netdev = dev;
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 837295fecd17..50f7c59e8a04 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -34,7 +34,6 @@ config MV643XX_ETH
 config MVMDIO
 	tristate "Marvell MDIO interface support"
 	depends on HAS_IOMEM
-	select MDIO_DEVRES
 	select PHYLIB
 	help
 	  This driver supports the MDIO interface found in the network
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index a06048719e84..0ab52c57c648 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1333,7 +1333,8 @@ static void mib_counters_update(struct mv643xx_eth_private *mp)
 
 static void mib_counters_timer_wrapper(struct timer_list *t)
 {
-	struct mv643xx_eth_private *mp = from_timer(mp, t, mib_counters_timer);
+	struct mv643xx_eth_private *mp = timer_container_of(mp, t,
+							    mib_counters_timer);
 	mib_counters_update(mp);
 	mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ);
 }
@@ -2247,7 +2248,7 @@ static int mv643xx_eth_poll(struct napi_struct *napi, int budget)
 
 	if (unlikely(mp->oom)) {
 		mp->oom = 0;
-		del_timer(&mp->rx_oom);
+		timer_delete(&mp->rx_oom);
 	}
 
 	work_done = 0;
@@ -2306,7 +2307,7 @@ static int mv643xx_eth_poll(struct napi_struct *napi, int budget)
 
 static inline void oom_timer_wrapper(struct timer_list *t)
 {
-	struct mv643xx_eth_private *mp = from_timer(mp, t, rx_oom);
+	struct mv643xx_eth_private *mp = timer_container_of(mp, t, rx_oom);
 
 	napi_schedule(&mp->napi);
 }
@@ -2521,7 +2522,7 @@ static int mv643xx_eth_stop(struct net_device *dev)
 
 	napi_disable(&mp->napi);
 
-	del_timer_sync(&mp->rx_oom);
+	timer_delete_sync(&mp->rx_oom);
 
 	netif_carrier_off(dev);
 	if (dev->phydev)
@@ -2531,7 +2532,7 @@ static int mv643xx_eth_stop(struct net_device *dev)
 	port_reset(mp);
 	mv643xx_eth_get_stats(dev);
 	mib_counters_update(mp);
-	del_timer_sync(&mp->mib_counters_timer);
+	timer_delete_sync(&mp->mib_counters_timer);
 
 	for (i = 0; i < mp->rxq_count; i++)
 		rxq_deinit(mp->rxq + i);
@@ -2704,9 +2705,15 @@ static struct platform_device *port_platdev[3];
 
 static void mv643xx_eth_shared_of_remove(void)
 {
+	struct mv643xx_eth_platform_data *pd;
 	int n;
 
 	for (n = 0; n < 3; n++) {
+		if (!port_platdev[n])
+			continue;
+		pd = dev_get_platdata(&port_platdev[n]->dev);
+		if (pd)
+			of_node_put(pd->phy_node);
 		platform_device_del(port_platdev[n]);
 		port_platdev[n] = NULL;
 	}
@@ -2769,8 +2776,10 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
 	}
 
 	ppdev = platform_device_alloc(MV643XX_ETH_NAME, dev_num);
-	if (!ppdev)
-		return -ENOMEM;
+	if (!ppdev) {
+		ret = -ENOMEM;
+		goto put_err;
+	}
 	ppdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
 	ppdev->dev.of_node = pnp;
 
@@ -2792,6 +2801,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
 
 port_err:
 	platform_device_put(ppdev);
+put_err:
+	of_node_put(ppd.phy_node);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 1fb285fa0bdb..147571fdada3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -284,8 +284,12 @@
 					  MVNETA_TXQ_BUCKET_REFILL_PERIOD))
 
 #define MVNETA_LPI_CTRL_0                        0x2cc0
+#define      MVNETA_LPI_CTRL_0_TS                (0xff << 8)
 #define MVNETA_LPI_CTRL_1                        0x2cc4
-#define      MVNETA_LPI_REQUEST_ENABLE           BIT(0)
+#define      MVNETA_LPI_CTRL_1_REQUEST_ENABLE    BIT(0)
+#define      MVNETA_LPI_CTRL_1_REQUEST_FORCE     BIT(1)
+#define      MVNETA_LPI_CTRL_1_MANUAL_MODE       BIT(2)
+#define      MVNETA_LPI_CTRL_1_TW                (0xfff << 4)
 #define MVNETA_LPI_CTRL_2                        0x2cc8
 #define MVNETA_LPI_STATUS                        0x2ccc
 
@@ -541,10 +545,6 @@ struct mvneta_port {
 	struct mvneta_bm_pool *pool_short;
 	int bm_win_id;
 
-	bool eee_enabled;
-	bool eee_active;
-	bool tx_lpi_enabled;
-
 	u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)];
 
 	u32 indir[MVNETA_RSS_LU_TABLE_SIZE];
@@ -2342,7 +2342,7 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 	prefetch(data);
 	xdp_buff_clear_frags_flag(xdp);
 	xdp_prepare_buff(xdp, data, pp->rx_offset_correction + MVNETA_MH_SIZE,
-			 data_len, false);
+			 data_len, true);
 }
 
 static void
@@ -2396,6 +2396,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 		      struct xdp_buff *xdp, u32 desc_status)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	u32 metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
 	u8 num_frags;
 
@@ -2410,6 +2411,8 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb->ip_summed = mvneta_rx_csum(pp, desc_status);
 
 	if (unlikely(xdp_buff_has_frags(xdp)))
@@ -3960,23 +3963,30 @@ static struct mvneta_port *mvneta_pcs_to_port(struct phylink_pcs *pcs)
 	return container_of(pcs, struct mvneta_port, phylink_pcs);
 }
 
-static int mvneta_pcs_validate(struct phylink_pcs *pcs,
-			       unsigned long *supported,
-			       const struct phylink_link_state *state)
+static unsigned int mvneta_pcs_inband_caps(struct phylink_pcs *pcs,
+					   phy_interface_t interface)
 {
-	/* We only support QSGMII, SGMII, 802.3z and RGMII modes.
-	 * When in 802.3z mode, we must have AN enabled:
+	/* When operating in an 802.3z mode, we must have AN enabled:
 	 * "Bit 2 Field InBandAnEn In-band Auto-Negotiation enable. ...
 	 * When <PortType> = 1 (1000BASE-X) this field must be set to 1."
+	 * Therefore, inband is "required".
 	 */
-	if (phy_interface_mode_is_8023z(state->interface) &&
-	    !phylink_test(state->advertising, Autoneg))
-		return -EINVAL;
+	if (phy_interface_mode_is_8023z(interface))
+		return LINK_INBAND_ENABLE;
 
-	return 0;
+	/* QSGMII, SGMII and RGMII can be configured to use inband
+	 * signalling of the AN result. Indicate these as "possible".
+	 */
+	if (interface == PHY_INTERFACE_MODE_SGMII ||
+	    interface == PHY_INTERFACE_MODE_QSGMII ||
+	    phy_interface_mode_is_rgmii(interface))
+		return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE;
+
+	/* For any other modes, indicate that inband is not supported. */
+	return LINK_INBAND_DISABLE;
 }
 
-static void mvneta_pcs_get_state(struct phylink_pcs *pcs,
+static void mvneta_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 				 struct phylink_link_state *state)
 {
 	struct mvneta_port *pp = mvneta_pcs_to_port(pcs);
@@ -4071,7 +4081,7 @@ static void mvneta_pcs_an_restart(struct phylink_pcs *pcs)
 }
 
 static const struct phylink_pcs_ops mvneta_phylink_pcs_ops = {
-	.pcs_validate = mvneta_pcs_validate,
+	.pcs_inband_caps = mvneta_pcs_inband_caps,
 	.pcs_get_state = mvneta_pcs_get_state,
 	.pcs_config = mvneta_pcs_config,
 	.pcs_an_restart = mvneta_pcs_an_restart,
@@ -4206,18 +4216,6 @@ static int mvneta_mac_finish(struct phylink_config *config, unsigned int mode,
 	return 0;
 }
 
-static void mvneta_set_eee(struct mvneta_port *pp, bool enable)
-{
-	u32 lpi_ctl1;
-
-	lpi_ctl1 = mvreg_read(pp, MVNETA_LPI_CTRL_1);
-	if (enable)
-		lpi_ctl1 |= MVNETA_LPI_REQUEST_ENABLE;
-	else
-		lpi_ctl1 &= ~MVNETA_LPI_REQUEST_ENABLE;
-	mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi_ctl1);
-}
-
 static void mvneta_mac_link_down(struct phylink_config *config,
 				 unsigned int mode, phy_interface_t interface)
 {
@@ -4233,9 +4231,6 @@ static void mvneta_mac_link_down(struct phylink_config *config,
 		val |= MVNETA_GMAC_FORCE_LINK_DOWN;
 		mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
 	}
-
-	pp->eee_active = false;
-	mvneta_set_eee(pp, false);
 }
 
 static void mvneta_mac_link_up(struct phylink_config *config,
@@ -4284,11 +4279,56 @@ static void mvneta_mac_link_up(struct phylink_config *config,
 	}
 
 	mvneta_port_up(pp);
+}
+
+static void mvneta_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct mvneta_port *pp = netdev_priv(to_net_dev(config->dev));
+	u32 lpi1;
+
+	lpi1 = mvreg_read(pp, MVNETA_LPI_CTRL_1);
+	lpi1 &= ~(MVNETA_LPI_CTRL_1_REQUEST_ENABLE |
+		  MVNETA_LPI_CTRL_1_REQUEST_FORCE |
+		  MVNETA_LPI_CTRL_1_MANUAL_MODE);
+	mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi1);
+}
+
+static int mvneta_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				    bool tx_clk_stop)
+{
+	struct mvneta_port *pp = netdev_priv(to_net_dev(config->dev));
+	u32 ts, tw, lpi0, lpi1, status;
 
-	if (phy && pp->eee_enabled) {
-		pp->eee_active = phy_init_eee(phy, false) >= 0;
-		mvneta_set_eee(pp, pp->eee_active && pp->tx_lpi_enabled);
+	status = mvreg_read(pp, MVNETA_GMAC_STATUS);
+	if (status & MVNETA_GMAC_SPEED_1000) {
+		/* At 1G speeds, the timer resolution are 1us, and
+		 * 802.3 says tw is 16.5us. Round up to 17us.
+		 */
+		tw = 17;
+		ts = timer;
+	} else {
+		/* At 100M speeds, the timer resolutions are 10us, and
+		 * 802.3 says tw is 30us.
+		 */
+		tw = 3;
+		ts = DIV_ROUND_UP(timer, 10);
 	}
+
+	if (ts > 255)
+		ts = 255;
+
+	/* Configure ts */
+	lpi0 = mvreg_read(pp, MVNETA_LPI_CTRL_0);
+	lpi0 = u32_replace_bits(lpi0, ts, MVNETA_LPI_CTRL_0_TS);
+	mvreg_write(pp, MVNETA_LPI_CTRL_0, lpi0);
+
+	/* Configure tw and enable LPI generation */
+	lpi1 = mvreg_read(pp, MVNETA_LPI_CTRL_1);
+	lpi1 = u32_replace_bits(lpi1, tw, MVNETA_LPI_CTRL_1_TW);
+	lpi1 |= MVNETA_LPI_CTRL_1_REQUEST_ENABLE;
+	mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi1);
+
+	return 0;
 }
 
 static const struct phylink_mac_ops mvneta_phylink_ops = {
@@ -4298,6 +4338,8 @@ static const struct phylink_mac_ops mvneta_phylink_ops = {
 	.mac_finish = mvneta_mac_finish,
 	.mac_link_down = mvneta_mac_link_down,
 	.mac_link_up = mvneta_mac_link_up,
+	.mac_disable_tx_lpi = mvneta_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = mvneta_mac_enable_tx_lpi,
 };
 
 static int mvneta_mdio_probe(struct mvneta_port *pp)
@@ -4385,6 +4427,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 	if (pp->neta_armada3700)
 		return 0;
 
+	netdev_lock(port->napi.dev);
 	spin_lock(&pp->lock);
 	/*
 	 * Configuring the driver for a new CPU while the driver is
@@ -4392,6 +4435,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 	 */
 	if (pp->is_stopped) {
 		spin_unlock(&pp->lock);
+		netdev_unlock(port->napi.dev);
 		return 0;
 	}
 	netif_tx_stop_all_queues(pp->dev);
@@ -4411,7 +4455,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 	/* Mask all ethernet port interrupts */
 	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
-	napi_enable(&port->napi);
+	napi_enable_locked(&port->napi);
 
 	/*
 	 * Enable per-CPU interrupts on the CPU that is
@@ -4432,6 +4476,8 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 		    MVNETA_CAUSE_LINK_CHANGE);
 	netif_tx_start_all_queues(pp->dev);
 	spin_unlock(&pp->lock);
+	netdev_unlock(port->napi.dev);
+
 	return 0;
 }
 
@@ -5099,14 +5145,6 @@ static int mvneta_ethtool_get_eee(struct net_device *dev,
 				  struct ethtool_keee *eee)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	u32 lpi_ctl0;
-
-	lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0);
-
-	eee->eee_enabled = pp->eee_enabled;
-	eee->eee_active = pp->eee_active;
-	eee->tx_lpi_enabled = pp->tx_lpi_enabled;
-	eee->tx_lpi_timer = (lpi_ctl0) >> 8; // * scale;
 
 	return phylink_ethtool_get_eee(pp->phylink, eee);
 }
@@ -5115,7 +5153,6 @@ static int mvneta_ethtool_set_eee(struct net_device *dev,
 				  struct ethtool_keee *eee)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	u32 lpi_ctl0;
 
 	/* The Armada 37x documents do not give limits for this other than
 	 * it being an 8-bit register.
@@ -5123,16 +5160,6 @@ static int mvneta_ethtool_set_eee(struct net_device *dev,
 	if (eee->tx_lpi_enabled && eee->tx_lpi_timer > 255)
 		return -EINVAL;
 
-	lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0);
-	lpi_ctl0 &= ~(0xff << 8);
-	lpi_ctl0 |= eee->tx_lpi_timer << 8;
-	mvreg_write(pp, MVNETA_LPI_CTRL_0, lpi_ctl0);
-
-	pp->eee_enabled = eee->eee_enabled;
-	pp->tx_lpi_enabled = eee->tx_lpi_enabled;
-
-	mvneta_set_eee(pp, eee->tx_lpi_enabled && eee->eee_enabled);
-
 	return phylink_ethtool_set_eee(pp->phylink, eee);
 }
 
@@ -5446,6 +5473,9 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	    !phy_interface_mode_is_rgmii(phy_mode))
 		return -EINVAL;
 
+	/* Ensure LPI is disabled */
+	mvneta_mac_disable_tx_lpi(&pp->phylink_config);
+
 	return 0;
 }
 
@@ -5530,13 +5560,19 @@ static int mvneta_probe(struct platform_device *pdev)
 		clk_prepare_enable(pp->clk_bus);
 
 	pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops;
-	pp->phylink_pcs.neg_mode = true;
 
 	pp->phylink_config.dev = &dev->dev;
 	pp->phylink_config.type = PHYLINK_NETDEV;
 	pp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_10 |
 		MAC_100 | MAC_1000FD | MAC_2500FD;
 
+	/* Setup EEE. Choose 250us idle. Only supported in SGMII modes. */
+	__set_bit(PHY_INTERFACE_MODE_QSGMII, pp->phylink_config.lpi_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_SGMII, pp->phylink_config.lpi_interfaces);
+	pp->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD;
+	pp->phylink_config.lpi_timer_default = 250;
+	pp->phylink_config.eee_enabled_default = true;
+
 	phy_interface_set_rgmii(pp->phylink_config.supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_QSGMII,
 		  pp->phylink_config.supported_interfaces);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 9e02e4367bec..061fcd444d50 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -481,6 +481,11 @@
 #define MVPP22_GMAC_INT_SUM_MASK		0xa4
 #define     MVPP22_GMAC_INT_SUM_MASK_LINK_STAT	BIT(1)
 #define	    MVPP22_GMAC_INT_SUM_MASK_PTP	BIT(2)
+#define MVPP2_GMAC_LPI_CTRL0			0xc0
+#define     MVPP2_GMAC_LPI_CTRL0_TS_MASK	GENMASK(15, 8)
+#define MVPP2_GMAC_LPI_CTRL1			0xc4
+#define     MVPP2_GMAC_LPI_CTRL1_REQ_EN		BIT(0)
+#define     MVPP2_GMAC_LPI_CTRL1_TW_MASK	GENMASK(15, 4)
 
 /* Per-port XGMAC registers. PPv2.2 and PPv2.3, only for GOP port 0,
  * relative to port->base.
@@ -1108,6 +1113,9 @@ struct mvpp2 {
 
 	/* Spinlocks for CM3 shared memory configuration */
 	spinlock_t mss_spinlock;
+
+	/* Spinlock for shared PRS parser memory and shadow table */
+	spinlock_t prs_spinlock;
 };
 
 struct mvpp2_pcpu_stats {
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 1641791a2d5b..8ed83fb98862 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -324,7 +324,7 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = {
 		       MVPP2_PRS_RI_VLAN_MASK),
 	/* Non IP flow, with vlan tag */
 	MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG,
-		       MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP22_CLS_HEK_TAGGED,
 		       0, 0),
 };
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 571631a30320..a7872d14a49d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3915,13 +3915,13 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 
 	while (rx_done < rx_todo) {
 		struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq);
+		u32 rx_status, timestamp, metasize = 0;
 		struct mvpp2_bm_pool *bm_pool;
 		struct page_pool *pp = NULL;
 		struct sk_buff *skb;
 		unsigned int frag_size;
 		dma_addr_t dma_addr;
 		phys_addr_t phys_addr;
-		u32 rx_status, timestamp;
 		int pool, rx_bytes, err, ret;
 		struct page *page;
 		void *data;
@@ -3983,7 +3983,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 			xdp_init_buff(&xdp, PAGE_SIZE, xdp_rxq);
 			xdp_prepare_buff(&xdp, data,
 					 MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM,
-					 rx_bytes, false);
+					 rx_bytes, true);
 
 			ret = mvpp2_run_xdp(port, xdp_prog, &xdp, pp, &ps);
 
@@ -3999,6 +3999,8 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 				ps.rx_bytes += rx_bytes;
 				continue;
 			}
+
+			metasize = xdp.data - xdp.data_meta;
 		}
 
 		if (frag_size)
@@ -4038,6 +4040,8 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 
 		skb_reserve(skb, MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM);
 		skb_put(skb, rx_bytes);
+		if (metasize)
+			skb_metadata_set(skb, metasize);
 		skb->ip_summed = mvpp2_rx_csum(port, rx_status);
 		skb->protocol = eth_type_trans(skb, dev);
 
@@ -5169,38 +5173,40 @@ mvpp2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
-static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
+static int mvpp2_hwtstamp_set(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
+	struct mvpp2_port *port = netdev_priv(dev);
 	void __iomem *ptp;
 	u32 gcr, int_mask;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	if (!port->hwtstamp)
+		return -EOPNOTSUPP;
 
-	if (config.tx_type != HWTSTAMP_TX_OFF &&
-	    config.tx_type != HWTSTAMP_TX_ON)
+	if (config->tx_type != HWTSTAMP_TX_OFF &&
+	    config->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
 	ptp = port->priv->iface_base + MVPP22_PTP_BASE(port->gop_id);
 
 	int_mask = gcr = 0;
-	if (config.tx_type != HWTSTAMP_TX_OFF) {
+	if (config->tx_type != HWTSTAMP_TX_OFF) {
 		gcr |= MVPP22_PTP_GCR_TSU_ENABLE | MVPP22_PTP_GCR_TX_RESET;
 		int_mask |= MVPP22_PTP_INT_MASK_QUEUE1 |
 			    MVPP22_PTP_INT_MASK_QUEUE0;
 	}
 
 	/* It seems we must also release the TX reset when enabling the TSU */
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE)
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE)
 		gcr |= MVPP22_PTP_GCR_TSU_ENABLE | MVPP22_PTP_GCR_RX_RESET |
 		       MVPP22_PTP_GCR_TX_RESET;
 
 	if (gcr & MVPP22_PTP_GCR_TSU_ENABLE)
 		mvpp22_tai_start(port->priv->tai);
 
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE) {
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE) {
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		mvpp2_modify(ptp + MVPP22_PTP_GCR,
 			     MVPP22_PTP_GCR_RX_RESET |
 			     MVPP22_PTP_GCR_TX_RESET |
@@ -5221,26 +5227,22 @@ static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
 	if (!(gcr & MVPP22_PTP_GCR_TSU_ENABLE))
 		mvpp22_tai_stop(port->priv->tai);
 
-	port->tx_hwtstamp_type = config.tx_type;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	port->tx_hwtstamp_type = config->tx_type;
 
 	return 0;
 }
 
-static int mvpp2_get_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
+static int mvpp2_hwtstamp_get(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
-
-	memset(&config, 0, sizeof(config));
+	struct mvpp2_port *port = netdev_priv(dev);
 
-	config.tx_type = port->tx_hwtstamp_type;
-	config.rx_filter = port->rx_hwtstamp ?
-		HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+	if (!port->hwtstamp)
+		return -EOPNOTSUPP;
 
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	config->tx_type = port->tx_hwtstamp_type;
+	config->rx_filter = port->rx_hwtstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
 	return 0;
 }
@@ -5270,18 +5272,6 @@ static int mvpp2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		if (port->hwtstamp)
-			return mvpp2_set_ts_config(port, ifr);
-		break;
-
-	case SIOCGHWTSTAMP:
-		if (port->hwtstamp)
-			return mvpp2_get_ts_config(port, ifr);
-		break;
-	}
-
 	if (!port->phylink)
 		return -ENOTSUPP;
 
@@ -5757,6 +5747,28 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev,
 	return mvpp2_modify_rxfh_context(dev, NULL, rxfh, extack);
 }
 
+static int mvpp2_ethtool_get_eee(struct net_device *dev,
+				 struct ethtool_keee *eee)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!port->phylink)
+		return -EOPNOTSUPP;
+
+	return phylink_ethtool_get_eee(port->phylink, eee);
+}
+
+static int mvpp2_ethtool_set_eee(struct net_device *dev,
+				 struct ethtool_keee *eee)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!port->phylink)
+		return -EOPNOTSUPP;
+
+	return phylink_ethtool_set_eee(port->phylink, eee);
+}
+
 /* Device ops */
 
 static const struct net_device_ops mvpp2_netdev_ops = {
@@ -5773,6 +5785,8 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 	.ndo_set_features	= mvpp2_set_features,
 	.ndo_bpf		= mvpp2_xdp,
 	.ndo_xdp_xmit		= mvpp2_xdp_xmit,
+	.ndo_hwtstamp_get	= mvpp2_hwtstamp_get,
+	.ndo_hwtstamp_set	= mvpp2_hwtstamp_set,
 };
 
 static const struct ethtool_ops mvpp2_eth_tool_ops = {
@@ -5802,6 +5816,8 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.create_rxfh_context	= mvpp2_create_rxfh_context,
 	.modify_rxfh_context	= mvpp2_modify_rxfh_context,
 	.remove_rxfh_context	= mvpp2_remove_rxfh_context,
+	.get_eee		= mvpp2_ethtool_get_eee,
+	.set_eee		= mvpp2_ethtool_set_eee,
 };
 
 /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
@@ -6188,6 +6204,7 @@ static struct mvpp2_port *mvpp2_pcs_gmac_to_port(struct phylink_pcs *pcs)
 }
 
 static void mvpp2_xlg_pcs_get_state(struct phylink_pcs *pcs,
+				    unsigned int neg_mode,
 				    struct phylink_link_state *state)
 {
 	struct mvpp2_port *port = mvpp2_pcs_xlg_to_port(pcs);
@@ -6224,22 +6241,30 @@ static const struct phylink_pcs_ops mvpp2_phylink_xlg_pcs_ops = {
 	.pcs_config = mvpp2_xlg_pcs_config,
 };
 
-static int mvpp2_gmac_pcs_validate(struct phylink_pcs *pcs,
-				   unsigned long *supported,
-				   const struct phylink_link_state *state)
+static unsigned int mvpp2_gmac_pcs_inband_caps(struct phylink_pcs *pcs,
+					       phy_interface_t interface)
 {
-	/* When in 802.3z mode, we must have AN enabled:
+	/* When operating in an 802.3z mode, we must have AN enabled:
 	 * Bit 2 Field InBandAnEn In-band Auto-Negotiation enable. ...
 	 * When <PortType> = 1 (1000BASE-X) this field must be set to 1.
+	 * Therefore, inband is "required".
 	 */
-	if (phy_interface_mode_is_8023z(state->interface) &&
-	    !phylink_test(state->advertising, Autoneg))
-		return -EINVAL;
+	if (phy_interface_mode_is_8023z(interface))
+		return LINK_INBAND_ENABLE;
 
-	return 0;
+	/* SGMII and RGMII can be configured to use inband signalling of the
+	 * AN result. Indicate these as "possible".
+	 */
+	if (interface == PHY_INTERFACE_MODE_SGMII ||
+	    phy_interface_mode_is_rgmii(interface))
+		return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE;
+
+	/* For any other modes, indicate that inband is not supported. */
+	return LINK_INBAND_DISABLE;
 }
 
 static void mvpp2_gmac_pcs_get_state(struct phylink_pcs *pcs,
+				     unsigned int neg_mode,
 				     struct phylink_link_state *state)
 {
 	struct mvpp2_port *port = mvpp2_pcs_gmac_to_port(pcs);
@@ -6343,7 +6368,7 @@ static void mvpp2_gmac_pcs_an_restart(struct phylink_pcs *pcs)
 }
 
 static const struct phylink_pcs_ops mvpp2_phylink_gmac_pcs_ops = {
-	.pcs_validate = mvpp2_gmac_pcs_validate,
+	.pcs_inband_caps = mvpp2_gmac_pcs_inband_caps,
 	.pcs_get_state = mvpp2_gmac_pcs_get_state,
 	.pcs_config = mvpp2_gmac_pcs_config,
 	.pcs_an_restart = mvpp2_gmac_pcs_an_restart,
@@ -6665,6 +6690,55 @@ static void mvpp2_mac_link_down(struct phylink_config *config,
 	mvpp2_port_disable(port);
 }
 
+static void mvpp2_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct mvpp2_port *port = mvpp2_phylink_to_port(config);
+
+	mvpp2_modify(port->base + MVPP2_GMAC_LPI_CTRL1,
+		     MVPP2_GMAC_LPI_CTRL1_REQ_EN, 0);
+}
+
+static int mvpp2_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				   bool tx_clk_stop)
+{
+	struct mvpp2_port *port = mvpp2_phylink_to_port(config);
+	u32 ts, tw, lpi1, status;
+
+	status = readl(port->base + MVPP2_GMAC_STATUS0);
+	if (status & MVPP2_GMAC_STATUS0_GMII_SPEED) {
+		/* At 1G speeds, the timer resolution are 1us, and
+		 * 802.3 says tw is 16.5us. Round up to 17us.
+		 */
+		tw = 17;
+		ts = timer;
+	} else {
+		/* At 100M speeds, the timer resolutions are 10us, and
+		 * 802.3 says tw is 30us.
+		 */
+		tw = 3;
+		ts = DIV_ROUND_UP(timer, 10);
+	}
+
+	if (ts > 255)
+		ts = 255;
+
+	/* Configure ts */
+	mvpp2_modify(port->base + MVPP2_GMAC_LPI_CTRL0,
+		     MVPP2_GMAC_LPI_CTRL0_TS_MASK,
+		     FIELD_PREP(MVPP2_GMAC_LPI_CTRL0_TS_MASK, ts));
+
+	lpi1 = readl(port->base + MVPP2_GMAC_LPI_CTRL1);
+
+	/* Configure tw */
+	lpi1 = u32_replace_bits(lpi1, tw, MVPP2_GMAC_LPI_CTRL1_TW_MASK);
+
+	/* Enable LPI generation */
+	writel(lpi1 | MVPP2_GMAC_LPI_CTRL1_REQ_EN,
+	       port->base + MVPP2_GMAC_LPI_CTRL1);
+
+	return 0;
+}
+
 static const struct phylink_mac_ops mvpp2_phylink_ops = {
 	.mac_select_pcs = mvpp2_select_pcs,
 	.mac_prepare = mvpp2_mac_prepare,
@@ -6672,6 +6746,8 @@ static const struct phylink_mac_ops mvpp2_phylink_ops = {
 	.mac_finish = mvpp2_mac_finish,
 	.mac_link_up = mvpp2_mac_link_up,
 	.mac_link_down = mvpp2_mac_link_down,
+	.mac_enable_tx_lpi = mvpp2_mac_enable_tx_lpi,
+	.mac_disable_tx_lpi = mvpp2_mac_disable_tx_lpi,
 };
 
 /* Work-around for ACPI */
@@ -6901,9 +6977,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		for (thread = 0; thread < priv->nthreads; thread++) {
 			port_pcpu = per_cpu_ptr(port->pcpu, thread);
 
-			hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC,
-				     HRTIMER_MODE_REL_PINNED_SOFT);
-			port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb;
+			hrtimer_setup(&port_pcpu->tx_done_timer, mvpp2_hr_timer_cb, CLOCK_MONOTONIC,
+				      HRTIMER_MODE_REL_PINNED_SOFT);
 			port_pcpu->timer_scheduled = false;
 			port_pcpu->dev = dev;
 		}
@@ -6940,9 +7015,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->dev_port = port->id;
 
 	port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops;
-	port->pcs_gmac.neg_mode = true;
 	port->pcs_xlg.ops = &mvpp2_phylink_xlg_pcs_ops;
-	port->pcs_xlg.neg_mode = true;
 
 	if (!mvpp2_use_acpi_compat_mode(port_fwnode)) {
 		port->phylink_config.dev = &dev->dev;
@@ -6950,6 +7023,15 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		port->phylink_config.mac_capabilities =
 			MAC_2500FD | MAC_1000FD | MAC_100 | MAC_10;
 
+		__set_bit(PHY_INTERFACE_MODE_SGMII,
+			  port->phylink_config.lpi_interfaces);
+
+		port->phylink_config.lpi_capabilities = MAC_1000FD | MAC_100FD;
+
+		/* Setup EEE.  Choose 250us idle. */
+		port->phylink_config.lpi_timer_default = 250;
+		port->phylink_config.eee_enabled_default = true;
+
 		if (port->priv->global_tx_fc)
 			port->phylink_config.mac_capabilities |=
 				MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
@@ -7024,6 +7106,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 			goto err_free_port_pcpu;
 		}
 		port->phylink = phylink;
+
+		mvpp2_mac_disable_tx_lpi(&port->phylink_config);
 	} else {
 		dev_warn(&pdev->dev, "Use link irqs for port#%d. FW update required\n", port->id);
 		port->phylink = NULL;
@@ -7627,8 +7711,9 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (mvpp2_read(priv, MVPP2_VER_ID_REG) == MVPP2_VER_PP23)
 		priv->hw_version = MVPP23;
 
-	/* Init mss lock */
+	/* Init locks for shared packet processor resources */
 	spin_lock_init(&priv->mss_spinlock);
+	spin_lock_init(&priv->prs_spinlock);
 
 	/* Initialize network controller */
 	err = mvpp2_init(pdev, priv);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 9af22f497a40..93e978bdf303 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -23,6 +23,8 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 {
 	int i;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (pe->index > MVPP2_PRS_TCAM_SRAM_SIZE - 1)
 		return -EINVAL;
 
@@ -43,11 +45,13 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 }
 
 /* Initialize tcam entry from hw */
-int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
-			   int tid)
+static int __mvpp2_prs_init_from_hw(struct mvpp2 *priv,
+				    struct mvpp2_prs_entry *pe, int tid)
 {
 	int i;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (tid > MVPP2_PRS_TCAM_SRAM_SIZE - 1)
 		return -EINVAL;
 
@@ -73,6 +77,18 @@ int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
 	return 0;
 }
 
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+			   int tid)
+{
+	int err;
+
+	spin_lock_bh(&priv->prs_spinlock);
+	err = __mvpp2_prs_init_from_hw(priv, pe, tid);
+	spin_unlock_bh(&priv->prs_spinlock);
+
+	return err;
+}
+
 /* Invalidate tcam hw entry */
 static void mvpp2_prs_hw_inv(struct mvpp2 *priv, int index)
 {
@@ -374,7 +390,7 @@ static int mvpp2_prs_flow_find(struct mvpp2 *priv, int flow)
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_FLOWS)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		bits = mvpp2_prs_sram_ai_get(&pe);
 
 		/* Sram store classification lookup ID in AI bits [5:0] */
@@ -441,7 +457,7 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 
 	if (priv->prs_shadow[MVPP2_PE_DROP_ALL].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL);
+		__mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -469,14 +485,17 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 }
 
 /* Set port to unicast or multicast promiscuous mode */
-void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
-			       enum mvpp2_prs_l2_cast l2_cast, bool add)
+static void __mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
+					enum mvpp2_prs_l2_cast l2_cast,
+					bool add)
 {
 	struct mvpp2_prs_entry pe;
 	unsigned char cast_match;
 	unsigned int ri;
 	int tid;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (l2_cast == MVPP2_PRS_L2_UNI_CAST) {
 		cast_match = MVPP2_PRS_UCAST_VAL;
 		tid = MVPP2_PE_MAC_UC_PROMISCUOUS;
@@ -489,7 +508,7 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 
 	/* promiscuous mode - Accept unknown unicast or multicast packets */
 	if (priv->prs_shadow[tid].valid) {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
@@ -522,6 +541,14 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 	mvpp2_prs_hw_write(priv, &pe);
 }
 
+void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
+			       enum mvpp2_prs_l2_cast l2_cast, bool add)
+{
+	spin_lock_bh(&priv->prs_spinlock);
+	__mvpp2_prs_mac_promisc_set(priv, port, l2_cast, add);
+	spin_unlock_bh(&priv->prs_spinlock);
+}
+
 /* Set entry for dsa packets */
 static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add,
 				  bool tagged, bool extend)
@@ -539,7 +566,7 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add,
 
 	if (priv->prs_shadow[tid].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -610,7 +637,7 @@ static void mvpp2_prs_dsa_tag_ethertype_set(struct mvpp2 *priv, int port,
 
 	if (priv->prs_shadow[tid].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -673,7 +700,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai)
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid);
 		if (!match)
 			continue;
@@ -726,7 +753,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 			    priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN)
 				continue;
 
-			mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
+			__mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
 			ri_bits = mvpp2_prs_sram_ri_get(&pe);
 			if ((ri_bits & MVPP2_PRS_RI_VLAN_MASK) ==
 			    MVPP2_PRS_RI_VLAN_DOUBLE)
@@ -760,7 +787,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 
 		mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 	/* Update ports' mask */
 	mvpp2_prs_tcam_port_map_set(&pe, port_map);
@@ -800,7 +827,7 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1,
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 
 		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) &&
 			mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2);
@@ -849,7 +876,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 			    priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN)
 				continue;
 
-			mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
+			__mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
 			ri_bits = mvpp2_prs_sram_ri_get(&pe);
 			ri_bits &= MVPP2_PRS_RI_VLAN_MASK;
 			if (ri_bits == MVPP2_PRS_RI_VLAN_SINGLE ||
@@ -880,7 +907,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 
 		mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	/* Update ports' mask */
@@ -1213,8 +1240,8 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv)
 	/* Create dummy entries for drop all and promiscuous modes */
 	mvpp2_prs_drop_fc(priv);
 	mvpp2_prs_mac_drop_all_set(priv, 0, false);
-	mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false);
-	mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false);
+	__mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false);
+	__mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false);
 }
 
 /* Set default entries for various types of dsa packets */
@@ -1533,12 +1560,6 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv)
 	struct mvpp2_prs_entry pe;
 	int err;
 
-	priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool),
-					      MVPP2_PRS_DBL_VLANS_MAX,
-					      GFP_KERNEL);
-	if (!priv->prs_double_vlans)
-		return -ENOMEM;
-
 	/* Double VLAN: 0x88A8, 0x8100 */
 	err = mvpp2_prs_double_vlan_add(priv, ETH_P_8021AD, ETH_P_8021Q,
 					MVPP2_PRS_PORT_MASK);
@@ -1941,7 +1962,7 @@ static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask)
 		    port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
 			continue;
 
-		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 
 		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
 		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
@@ -1970,6 +1991,8 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
 	tid = mvpp2_prs_vid_range_find(port, vid, mask);
 
@@ -1988,8 +2011,10 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 						MVPP2_PRS_VLAN_FILT_MAX_ENTRY);
 
 		/* There isn't room for a new VID filter */
-		if (tid < 0)
+		if (tid < 0) {
+			spin_unlock_bh(&priv->prs_spinlock);
 			return tid;
+		}
 
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID);
 		pe.index = tid;
@@ -1997,7 +2022,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 		/* Mask all ports */
 		mvpp2_prs_tcam_port_map_set(&pe, 0);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	/* Enable the current port */
@@ -2019,6 +2044,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID);
 	mvpp2_prs_hw_write(priv, &pe);
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return 0;
 }
 
@@ -2028,15 +2054,16 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid)
 	struct mvpp2 *priv = port->priv;
 	int tid;
 
-	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
+	spin_lock_bh(&priv->prs_spinlock);
 
-	/* No such entry */
-	if (tid < 0)
-		return;
+	/* Invalidate TCAM entry with this <vid,port>, if it exists */
+	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
+	if (tid >= 0) {
+		mvpp2_prs_hw_inv(priv, tid);
+		priv->prs_shadow[tid].valid = false;
+	}
 
-	mvpp2_prs_hw_inv(priv, tid);
-	priv->prs_shadow[tid].valid = false;
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Remove all existing VID filters on this port */
@@ -2045,6 +2072,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 	struct mvpp2 *priv = port->priv;
 	int tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
 	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
 		if (priv->prs_shadow[tid].valid) {
@@ -2052,6 +2081,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 			priv->prs_shadow[tid].valid = false;
 		}
 	}
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Remove VID filering entry for this port */
@@ -2060,10 +2091,14 @@ void mvpp2_prs_vid_disable_filtering(struct mvpp2_port *port)
 	unsigned int tid = MVPP2_PRS_VID_PORT_DFLT(port->id);
 	struct mvpp2 *priv = port->priv;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Invalidate the guard entry */
 	mvpp2_prs_hw_inv(priv, tid);
 
 	priv->prs_shadow[tid].valid = false;
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Add guard entry that drops packets when no VID is matched on this port */
@@ -2079,6 +2114,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	pe.index = tid;
 
 	reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id));
@@ -2111,6 +2148,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port)
 	/* Update shadow table */
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID);
 	mvpp2_prs_hw_write(priv, &pe);
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Parser default initialization */
@@ -2118,6 +2157,20 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 {
 	int err, index, i;
 
+	priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE,
+					sizeof(*priv->prs_shadow),
+					GFP_KERNEL);
+	if (!priv->prs_shadow)
+		return -ENOMEM;
+
+	priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool),
+					      MVPP2_PRS_DBL_VLANS_MAX,
+					      GFP_KERNEL);
+	if (!priv->prs_double_vlans)
+		return -ENOMEM;
+
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Enable tcam table */
 	mvpp2_write(priv, MVPP2_PRS_TCAM_CTRL_REG, MVPP2_PRS_TCAM_EN_MASK);
 
@@ -2136,12 +2189,6 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 	for (index = 0; index < MVPP2_PRS_TCAM_SRAM_SIZE; index++)
 		mvpp2_prs_hw_inv(priv, index);
 
-	priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE,
-					sizeof(*priv->prs_shadow),
-					GFP_KERNEL);
-	if (!priv->prs_shadow)
-		return -ENOMEM;
-
 	/* Always start from lookup = 0 */
 	for (index = 0; index < MVPP2_MAX_PORTS; index++)
 		mvpp2_prs_hw_port_init(priv, index, MVPP2_PRS_LU_MH,
@@ -2158,26 +2205,13 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 	mvpp2_prs_vid_init(priv);
 
 	err = mvpp2_prs_etype_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_vlan_init(pdev, priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_pppoe_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_ip6_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_ip4_init(priv);
-	if (err)
-		return err;
+	err = err ? : mvpp2_prs_vlan_init(pdev, priv);
+	err = err ? : mvpp2_prs_pppoe_init(priv);
+	err = err ? : mvpp2_prs_ip6_init(priv);
+	err = err ? : mvpp2_prs_ip4_init(priv);
 
-	return 0;
+	spin_unlock_bh(&priv->prs_spinlock);
+	return err;
 }
 
 /* Compare MAC DA with tcam entry data */
@@ -2217,7 +2251,7 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da,
 		    (priv->prs_shadow[tid].udf != udf_type))
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		entry_pmap = mvpp2_prs_tcam_port_map_get(&pe);
 
 		if (mvpp2_prs_mac_range_equals(&pe, da, mask) &&
@@ -2229,7 +2263,8 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da,
 }
 
 /* Update parser's mac da entry */
-int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
+static int __mvpp2_prs_mac_da_accept(struct mvpp2_port *port,
+				     const u8 *da, bool add)
 {
 	unsigned char mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 	struct mvpp2 *priv = port->priv;
@@ -2261,7 +2296,7 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
 		/* Mask all ports */
 		mvpp2_prs_tcam_port_map_set(&pe, 0);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
@@ -2317,6 +2352,17 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
 	return 0;
 }
 
+int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
+{
+	int err;
+
+	spin_lock_bh(&port->priv->prs_spinlock);
+	err = __mvpp2_prs_mac_da_accept(port, da, add);
+	spin_unlock_bh(&port->priv->prs_spinlock);
+
+	return err;
+}
+
 int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
@@ -2345,6 +2391,8 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 	unsigned long pmap;
 	int index, tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	for (tid = MVPP2_PE_MAC_RANGE_START;
 	     tid <= MVPP2_PE_MAC_RANGE_END; tid++) {
 		unsigned char da[ETH_ALEN], da_mask[ETH_ALEN];
@@ -2354,7 +2402,7 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 		    (priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF))
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 
 		pmap = mvpp2_prs_tcam_port_map_get(&pe);
 
@@ -2375,14 +2423,17 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 			continue;
 
 		/* Remove entry from TCAM */
-		mvpp2_prs_mac_da_accept(port, da, false);
+		__mvpp2_prs_mac_da_accept(port, da, false);
 	}
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 {
 	switch (type) {
 	case MVPP2_TAG_TYPE_EDSA:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Add port to EDSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, true,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
@@ -2393,9 +2444,11 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_DSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	case MVPP2_TAG_TYPE_DSA:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Add port to DSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, true,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
@@ -2406,10 +2459,12 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	case MVPP2_TAG_TYPE_MH:
 	case MVPP2_TAG_TYPE_NONE:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Remove port form EDSA and DSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
@@ -2419,6 +2474,7 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	default:
@@ -2437,11 +2493,15 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	tid = mvpp2_prs_tcam_first_free(priv,
 					MVPP2_PE_LAST_FREE_TID,
 					MVPP2_PE_FIRST_FREE_TID);
-	if (tid < 0)
+	if (tid < 0) {
+		spin_unlock_bh(&priv->prs_spinlock);
 		return tid;
+	}
 
 	pe.index = tid;
 
@@ -2461,6 +2521,7 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
 	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
 	mvpp2_prs_hw_write(priv, &pe);
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return 0;
 }
 
@@ -2472,6 +2533,8 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&port->priv->prs_spinlock);
+
 	tid = mvpp2_prs_flow_find(port->priv, port->id);
 
 	/* Such entry not exist */
@@ -2480,8 +2543,10 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 		tid = mvpp2_prs_tcam_first_free(port->priv,
 						MVPP2_PE_LAST_FREE_TID,
 					       MVPP2_PE_FIRST_FREE_TID);
-		if (tid < 0)
+		if (tid < 0) {
+			spin_unlock_bh(&port->priv->prs_spinlock);
 			return tid;
+		}
 
 		pe.index = tid;
 
@@ -2492,13 +2557,14 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 		/* Update shadow table */
 		mvpp2_prs_shadow_set(port->priv, pe.index, MVPP2_PRS_LU_FLOWS);
 	} else {
-		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 	}
 
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
 	mvpp2_prs_tcam_port_map_set(&pe, (1 << port->id));
 	mvpp2_prs_hw_write(port->priv, &pe);
 
+	spin_unlock_bh(&port->priv->prs_spinlock);
 	return 0;
 }
 
@@ -2509,11 +2575,14 @@ int mvpp2_prs_hits(struct mvpp2 *priv, int index)
 	if (index > MVPP2_PRS_TCAM_SRAM_SIZE)
 		return -EINVAL;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index);
 
 	val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG);
 
 	val &= MVPP2_PRS_TCAM_HIT_CNT_MASK;
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return val;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
index 4f4d58189118..a88c006ea65b 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
@@ -150,17 +150,14 @@ octep_get_ethtool_stats(struct net_device *netdev,
 				    iface_rx_stats,
 				    iface_tx_stats);
 
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-		struct octep_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		tx_busy_errors += iq->stats.tx_busy;
-
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
-		rx_alloc_errors += oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		tx_busy_errors += oct->stats_iq[q].tx_busy;
+
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
+		rx_alloc_errors += oct->stats_oq[q].alloc_failures;
 	}
 	i = 0;
 	data[i++] = rx_packets;
@@ -198,22 +195,18 @@ octep_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = iface_rx_stats->err_pkts;
 
 	/* Per Tx Queue stats */
-	for (q = 0; q < oct->num_iqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-
-		data[i++] = iq->stats.instr_posted;
-		data[i++] = iq->stats.instr_completed;
-		data[i++] = iq->stats.bytes_sent;
-		data[i++] = iq->stats.tx_busy;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_iq[q].instr_posted;
+		data[i++] = oct->stats_iq[q].instr_completed;
+		data[i++] = oct->stats_iq[q].bytes_sent;
+		data[i++] = oct->stats_iq[q].tx_busy;
 	}
 
 	/* Per Rx Queue stats */
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_oq *oq = oct->oq[q];
-
-		data[i++] = oq->stats.packets;
-		data[i++] = oq->stats.bytes;
-		data[i++] = oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_oq[q].packets;
+		data[i++] = oct->stats_oq[q].bytes;
+		data[i++] = oct->stats_oq[q].alloc_failures;
 	}
 }
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 549436efc204..24499bb36c00 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -822,7 +822,7 @@ static inline int octep_iq_full_check(struct octep_iq *iq)
 	if (unlikely(IQ_INSTR_SPACE(iq) >
 		     OCTEP_WAKE_QUEUE_THRESHOLD)) {
 		netif_start_subqueue(iq->netdev, iq->q_no);
-		iq->stats.restart_cnt++;
+		iq->stats->restart_cnt++;
 		return 0;
 	}
 
@@ -960,7 +960,7 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 	wmb();
 	/* Ring Doorbell to notify the NIC of new packets */
 	writel(iq->fill_cnt, iq->doorbell_reg);
-	iq->stats.instr_posted += iq->fill_cnt;
+	iq->stats->instr_posted += iq->fill_cnt;
 	iq->fill_cnt = 0;
 	return NETDEV_TX_OK;
 
@@ -991,37 +991,24 @@ dma_map_err:
 static void octep_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
 {
-	u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
 	struct octep_device *oct = netdev_priv(netdev);
+	u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
 	int q;
 
-	if (netif_running(netdev))
-		octep_ctrl_net_get_if_stats(oct,
-					    OCTEP_CTRL_NET_INVALID_VFID,
-					    &oct->iface_rx_stats,
-					    &oct->iface_tx_stats);
-
 	tx_packets = 0;
 	tx_bytes = 0;
 	rx_packets = 0;
 	rx_bytes = 0;
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-		struct octep_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
 	}
 	stats->tx_packets = tx_packets;
 	stats->tx_bytes = tx_bytes;
 	stats->rx_packets = rx_packets;
 	stats->rx_bytes = rx_bytes;
-	stats->multicast = oct->iface_rx_stats.mcast_pkts;
-	stats->rx_errors = oct->iface_rx_stats.err_pkts;
-	stats->collisions = oct->iface_tx_stats.xscol;
-	stats->tx_fifo_errors = oct->iface_tx_stats.undflw;
 }
 
 /**
@@ -1137,6 +1124,43 @@ static int octep_set_features(struct net_device *dev, netdev_features_t features
 	return err;
 }
 
+static int octep_get_vf_config(struct net_device *dev, int vf,
+			       struct ifla_vf_info *ivi)
+{
+	struct octep_device *oct = netdev_priv(dev);
+
+	ivi->vf = vf;
+	ether_addr_copy(ivi->mac, oct->vf_info[vf].mac_addr);
+	ivi->spoofchk = true;
+	ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE;
+	ivi->trusted = false;
+
+	return 0;
+}
+
+static int octep_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
+{
+	struct octep_device *oct = netdev_priv(dev);
+	int err;
+
+	if (!is_valid_ether_addr(mac)) {
+		dev_err(&oct->pdev->dev, "Invalid  MAC Address %pM\n", mac);
+		return -EADDRNOTAVAIL;
+	}
+
+	dev_dbg(&oct->pdev->dev, "set vf-%d mac to %pM\n", vf, mac);
+	ether_addr_copy(oct->vf_info[vf].mac_addr, mac);
+	oct->vf_info[vf].flags |= OCTEON_PFVF_FLAG_MAC_SET_BY_PF;
+
+	err = octep_ctrl_net_set_mac_addr(oct, vf, mac, true);
+	if (err)
+		dev_err(&oct->pdev->dev,
+			"Set VF%d MAC address failed via host control Mbox\n",
+			vf);
+
+	return err;
+}
+
 static const struct net_device_ops octep_netdev_ops = {
 	.ndo_open                = octep_open,
 	.ndo_stop                = octep_stop,
@@ -1146,6 +1170,8 @@ static const struct net_device_ops octep_netdev_ops = {
 	.ndo_set_mac_address     = octep_set_mac,
 	.ndo_change_mtu          = octep_change_mtu,
 	.ndo_set_features        = octep_set_features,
+	.ndo_get_vf_config       = octep_get_vf_config,
+	.ndo_set_vf_mac          = octep_set_vf_mac
 };
 
 /**
@@ -1197,7 +1223,7 @@ static void octep_hb_timeout_task(struct work_struct *work)
 		miss_cnt);
 	rtnl_lock();
 	if (netif_running(oct->netdev))
-		octep_stop(oct->netdev);
+		dev_close(oct->netdev);
 	rtnl_unlock();
 }
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
index fee59e0e0138..81ac4267811c 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
@@ -220,6 +220,7 @@ struct octep_iface_link_info {
 /* The Octeon VF device specific info data structure.*/
 struct octep_pfvf_info {
 	u8 mac_addr[ETH_ALEN];
+	u32 flags;
 	u32 mbox_version;
 };
 
@@ -257,11 +258,17 @@ struct octep_device {
 	/* Pointers to Octeon Tx queues */
 	struct octep_iq *iq[OCTEP_MAX_IQ];
 
+	/* Per iq stats */
+	struct octep_iq_stats stats_iq[OCTEP_MAX_IQ];
+
 	/* Rx queues (OQ: Output Queue) */
 	u16 num_oqs;
 	/* Pointers to Octeon Rx queues */
 	struct octep_oq *oq[OCTEP_MAX_OQ];
 
+	/* Per oq stats */
+	struct octep_oq_stats stats_oq[OCTEP_MAX_OQ];
+
 	/* Hardware port number of the PCIe interface */
 	u16 pcie_port;
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c
index e6eb98d70f3c..ebecdd29f3bd 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c
@@ -156,12 +156,23 @@ static void octep_pfvf_set_mac_addr(struct octep_device *oct,  u32 vf_id,
 {
 	int err;
 
+	if (oct->vf_info[vf_id].flags & OCTEON_PFVF_FLAG_MAC_SET_BY_PF) {
+		dev_err(&oct->pdev->dev,
+			"VF%d attempted to override administrative set MAC address\n",
+			vf_id);
+		rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
+		return;
+	}
+
 	err = octep_ctrl_net_set_mac_addr(oct, vf_id, cmd.s_set_mac.mac_addr, true);
 	if (err) {
 		rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
-		dev_err(&oct->pdev->dev, "Set VF MAC address failed via host control Mbox\n");
+		dev_err(&oct->pdev->dev, "Set VF%d MAC address failed via host control Mbox\n",
+			vf_id);
 		return;
 	}
+
+	ether_addr_copy(oct->vf_info[vf_id].mac_addr, cmd.s_set_mac.mac_addr);
 	rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
 }
 
@@ -171,10 +182,18 @@ static void octep_pfvf_get_mac_addr(struct octep_device *oct,  u32 vf_id,
 {
 	int err;
 
+	if (oct->vf_info[vf_id].flags & OCTEON_PFVF_FLAG_MAC_SET_BY_PF) {
+		dev_dbg(&oct->pdev->dev, "VF%d MAC address set by PF\n", vf_id);
+		ether_addr_copy(rsp->s_set_mac.mac_addr,
+				oct->vf_info[vf_id].mac_addr);
+		rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
+		return;
+	}
 	err = octep_ctrl_net_get_mac_addr(oct, vf_id, rsp->s_set_mac.mac_addr);
 	if (err) {
 		rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK;
-		dev_err(&oct->pdev->dev, "Get VF MAC address failed via host control Mbox\n");
+		dev_err(&oct->pdev->dev, "Get VF%d MAC address failed via host control Mbox\n",
+			vf_id);
 		return;
 	}
 	rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK;
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h
index 0dc6eead292a..386a095a99bc 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h
@@ -8,8 +8,6 @@
 #ifndef _OCTEP_PFVF_MBOX_H_
 #define _OCTEP_PFVF_MBOX_H_
 
-/* VF flags */
-#define OCTEON_PFVF_FLAG_MAC_SET_BY_PF  BIT_ULL(0) /* PF has set VF MAC address */
 #define OCTEON_SDP_16K_HW_FRS  16380UL
 #define OCTEON_SDP_64K_HW_FRS  65531UL
 
@@ -23,6 +21,10 @@ enum octep_pfvf_mbox_version {
 
 #define OCTEP_PFVF_MBOX_VERSION_CURRENT	OCTEP_PFVF_MBOX_VERSION_V2
 
+/* VF flags */
+/* PF has set VF MAC address */
+#define OCTEON_PFVF_FLAG_MAC_SET_BY_PF  BIT(0)
+
 enum octep_pfvf_mbox_opcode {
 	OCTEP_PFVF_MBOX_CMD_VERSION,
 	OCTEP_PFVF_MBOX_CMD_SET_MTU,
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
index 8af75cb37c3e..82b6b19e76b4 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
@@ -87,7 +87,7 @@ static int octep_oq_refill(struct octep_device *oct, struct octep_oq *oq)
 		page = dev_alloc_page();
 		if (unlikely(!page)) {
 			dev_err(oq->dev, "refill: rx buffer alloc failed\n");
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 
@@ -98,7 +98,7 @@ static int octep_oq_refill(struct octep_device *oct, struct octep_oq *oq)
 				"OQ-%d buffer refill: DMA mapping error!\n",
 				oq->q_no);
 			put_page(page);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 		oq->buff_info[refill_idx].page = page;
@@ -134,6 +134,7 @@ static int octep_setup_oq(struct octep_device *oct, int q_no)
 	oq->netdev = oct->netdev;
 	oq->dev = &oct->pdev->dev;
 	oq->q_no = q_no;
+	oq->stats = &oct->stats_oq[q_no];
 	oq->max_count = CFG_GET_OQ_NUM_DESC(oct->conf);
 	oq->ring_size_mask = oq->max_count - 1;
 	oq->buffer_size = CFG_GET_OQ_BUF_SIZE(oct->conf);
@@ -443,7 +444,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 		if (!skb) {
 			octep_oq_drop_rx(oq, buff_info,
 					 &read_idx, &desc_used);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			continue;
 		}
 		skb_reserve(skb, data_offset);
@@ -494,8 +495,8 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 
 	oq->host_read_idx = read_idx;
 	oq->refill_count += desc_used;
-	oq->stats.packets += pkt;
-	oq->stats.bytes += rx_bytes;
+	oq->stats->packets += pkt;
+	oq->stats->bytes += rx_bytes;
 
 	return pkt;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
index 3b08e2d560dc..b4696c93d0e6 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
@@ -186,8 +186,8 @@ struct octep_oq {
 	 */
 	u8 __iomem *pkts_sent_reg;
 
-	/* Statistics for this OQ. */
-	struct octep_oq_stats stats;
+	/* Pointer to statistics for this OQ. */
+	struct octep_oq_stats *stats;
 
 	/* Packets pending to be processed */
 	u32 pkts_pending;
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
index 06851b78aa28..08ee90013fef 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
@@ -81,9 +81,9 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget)
 	}
 
 	iq->pkts_processed += compl_pkts;
-	iq->stats.instr_completed += compl_pkts;
-	iq->stats.bytes_sent += compl_bytes;
-	iq->stats.sgentry_sent += compl_sg;
+	iq->stats->instr_completed += compl_pkts;
+	iq->stats->bytes_sent += compl_bytes;
+	iq->stats->sgentry_sent += compl_sg;
 	iq->flush_index = fi;
 
 	netdev_tx_completed_queue(iq->netdev_q, compl_pkts, compl_bytes);
@@ -187,6 +187,7 @@ static int octep_setup_iq(struct octep_device *oct, int q_no)
 	iq->netdev = oct->netdev;
 	iq->dev = &oct->pdev->dev;
 	iq->q_no = q_no;
+	iq->stats = &oct->stats_iq[q_no];
 	iq->max_count = CFG_GET_IQ_NUM_DESC(oct->conf);
 	iq->ring_size_mask = iq->max_count - 1;
 	iq->fill_threshold = CFG_GET_IQ_DB_MIN(oct->conf);
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
index 875a2c34091f..58fb39dda977 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
@@ -170,8 +170,8 @@ struct octep_iq {
 	 */
 	u16 flush_index;
 
-	/* Statistics for this input queue. */
-	struct octep_iq_stats stats;
+	/* Pointer to statistics for this input queue. */
+	struct octep_iq_stats *stats;
 
 	/* Pointer to the Virtual Base addr of the input ring. */
 	struct octep_tx_desc_hw *desc_ring;
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
index 7b21439a315f..d60441928ba9 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
@@ -114,12 +114,9 @@ static void octep_vf_get_ethtool_stats(struct net_device *netdev,
 	iface_tx_stats = &oct->iface_tx_stats;
 	iface_rx_stats = &oct->iface_rx_stats;
 
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		tx_busy_errors += iq->stats.tx_busy;
-		rx_alloc_errors += oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		tx_busy_errors += oct->stats_iq[q].tx_busy;
+		rx_alloc_errors += oct->stats_oq[q].alloc_failures;
 	}
 	i = 0;
 	data[i++] = rx_alloc_errors;
@@ -134,22 +131,18 @@ static void octep_vf_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = iface_rx_stats->dropped_octets_fifo_full;
 
 	/* Per Tx Queue stats */
-	for (q = 0; q < oct->num_iqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-
-		data[i++] = iq->stats.instr_posted;
-		data[i++] = iq->stats.instr_completed;
-		data[i++] = iq->stats.bytes_sent;
-		data[i++] = iq->stats.tx_busy;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_iq[q].instr_posted;
+		data[i++] = oct->stats_iq[q].instr_completed;
+		data[i++] = oct->stats_iq[q].bytes_sent;
+		data[i++] = oct->stats_iq[q].tx_busy;
 	}
 
 	/* Per Rx Queue stats */
 	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		data[i++] = oq->stats.packets;
-		data[i++] = oq->stats.bytes;
-		data[i++] = oq->stats.alloc_failures;
+		data[i++] = oct->stats_oq[q].packets;
+		data[i++] = oct->stats_oq[q].bytes;
+		data[i++] = oct->stats_oq[q].alloc_failures;
 	}
 }
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 7e6771c9cdbb..420c3f4cf741 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -18,8 +18,6 @@
 #include "octep_vf_config.h"
 #include "octep_vf_main.h"
 
-struct workqueue_struct *octep_vf_wq;
-
 /* Supported Devices */
 static const struct pci_device_id octep_vf_pci_id_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN93_VF)},
@@ -574,7 +572,7 @@ static int octep_vf_iq_full_check(struct octep_vf_iq *iq)
 		  * caused queues to get re-enabled after
 		  * being stopped
 		  */
-		iq->stats.restart_cnt++;
+		iq->stats->restart_cnt++;
 		fallthrough;
 	case 1: /* Queue left enabled, since IQ is not yet full*/
 		return 0;
@@ -731,7 +729,7 @@ ring_dbell:
 	/* Flush the hw descriptors before writing to doorbell */
 	smp_wmb();
 	writel(iq->fill_cnt, iq->doorbell_reg);
-	iq->stats.instr_posted += iq->fill_cnt;
+	iq->stats->instr_posted += iq->fill_cnt;
 	iq->fill_cnt = 0;
 	return NETDEV_TX_OK;
 }
@@ -786,27 +784,16 @@ static void octep_vf_get_stats64(struct net_device *netdev,
 	tx_bytes = 0;
 	rx_packets = 0;
 	rx_bytes = 0;
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
 	}
 	stats->tx_packets = tx_packets;
 	stats->tx_bytes = tx_bytes;
 	stats->rx_packets = rx_packets;
 	stats->rx_bytes = rx_bytes;
-	if (!octep_vf_get_if_stats(oct)) {
-		stats->multicast = oct->iface_rx_stats.mcast_pkts;
-		stats->rx_errors = oct->iface_rx_stats.err_pkts;
-		stats->rx_dropped = oct->iface_rx_stats.dropped_pkts_fifo_full +
-				    oct->iface_rx_stats.err_pkts;
-		stats->rx_missed_errors = oct->iface_rx_stats.dropped_pkts_fifo_full;
-		stats->tx_dropped = oct->iface_tx_stats.dropped;
-	}
 }
 
 /**
@@ -846,7 +833,9 @@ static void octep_vf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	struct octep_vf_device *oct = netdev_priv(netdev);
 
 	netdev_hold(netdev, NULL, GFP_ATOMIC);
-	schedule_work(&oct->tx_timeout_task);
+	if (!schedule_work(&oct->tx_timeout_task))
+		netdev_put(netdev, NULL);
+
 }
 
 static int octep_vf_set_mac(struct net_device *netdev, void *p)
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
index 5769f62545cd..b9f13506f462 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
@@ -246,11 +246,17 @@ struct octep_vf_device {
 	/* Pointers to Octeon Tx queues */
 	struct octep_vf_iq *iq[OCTEP_VF_MAX_IQ];
 
+	/* Per iq stats */
+	struct octep_vf_iq_stats stats_iq[OCTEP_VF_MAX_IQ];
+
 	/* Rx queues (OQ: Output Queue) */
 	u16 num_oqs;
 	/* Pointers to Octeon Rx queues */
 	struct octep_vf_oq *oq[OCTEP_VF_MAX_OQ];
 
+	/* Per oq stats */
+	struct octep_vf_oq_stats stats_oq[OCTEP_VF_MAX_OQ];
+
 	/* Hardware port number of the PCIe interface */
 	u16 pcie_port;
 
@@ -314,8 +320,6 @@ static inline u16 OCTEP_VF_MINOR_REV(struct octep_vf_device *oct)
 #define octep_vf_read_csr64(octep_vf_dev, reg_off)         \
 	readq((octep_vf_dev)->mmio.hw_addr + (reg_off))
 
-extern struct workqueue_struct *octep_vf_wq;
-
 int octep_vf_device_setup(struct octep_vf_device *oct);
 int octep_vf_setup_iqs(struct octep_vf_device *oct);
 void octep_vf_free_iqs(struct octep_vf_device *oct);
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
index 82821bc28634..d70c8be3cfc4 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
@@ -87,7 +87,7 @@ static int octep_vf_oq_refill(struct octep_vf_device *oct, struct octep_vf_oq *o
 		page = dev_alloc_page();
 		if (unlikely(!page)) {
 			dev_err(oq->dev, "refill: rx buffer alloc failed\n");
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 
@@ -98,7 +98,7 @@ static int octep_vf_oq_refill(struct octep_vf_device *oct, struct octep_vf_oq *o
 				"OQ-%d buffer refill: DMA mapping error!\n",
 				oq->q_no);
 			put_page(page);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 		oq->buff_info[refill_idx].page = page;
@@ -134,6 +134,7 @@ static int octep_vf_setup_oq(struct octep_vf_device *oct, int q_no)
 	oq->netdev = oct->netdev;
 	oq->dev = &oct->pdev->dev;
 	oq->q_no = q_no;
+	oq->stats = &oct->stats_oq[q_no];
 	oq->max_count = CFG_GET_OQ_NUM_DESC(oct->conf);
 	oq->ring_size_mask = oq->max_count - 1;
 	oq->buffer_size = CFG_GET_OQ_BUF_SIZE(oct->conf);
@@ -458,8 +459,8 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 
 	oq->host_read_idx = read_idx;
 	oq->refill_count += desc_used;
-	oq->stats.packets += pkt;
-	oq->stats.bytes += rx_bytes;
+	oq->stats->packets += pkt;
+	oq->stats->bytes += rx_bytes;
 
 	return pkt;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
index fe46838b5200..9e296b7d7e34 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
@@ -187,7 +187,7 @@ struct octep_vf_oq {
 	u8 __iomem *pkts_sent_reg;
 
 	/* Statistics for this OQ. */
-	struct octep_vf_oq_stats stats;
+	struct octep_vf_oq_stats *stats;
 
 	/* Packets pending to be processed */
 	u32 pkts_pending;
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
index 47a5c054fdb6..8180e5ce3d7e 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
@@ -82,9 +82,9 @@ int octep_vf_iq_process_completions(struct octep_vf_iq *iq, u16 budget)
 	}
 
 	iq->pkts_processed += compl_pkts;
-	iq->stats.instr_completed += compl_pkts;
-	iq->stats.bytes_sent += compl_bytes;
-	iq->stats.sgentry_sent += compl_sg;
+	iq->stats->instr_completed += compl_pkts;
+	iq->stats->bytes_sent += compl_bytes;
+	iq->stats->sgentry_sent += compl_sg;
 	iq->flush_index = fi;
 
 	netif_subqueue_completed_wake(iq->netdev, iq->q_no, compl_pkts,
@@ -186,6 +186,7 @@ static int octep_vf_setup_iq(struct octep_vf_device *oct, int q_no)
 	iq->netdev = oct->netdev;
 	iq->dev = &oct->pdev->dev;
 	iq->q_no = q_no;
+	iq->stats = &oct->stats_iq[q_no];
 	iq->max_count = CFG_GET_IQ_NUM_DESC(oct->conf);
 	iq->ring_size_mask = iq->max_count - 1;
 	iq->fill_threshold = CFG_GET_IQ_DB_MIN(oct->conf);
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
index f338b975103c..1cede90e3a5f 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
@@ -129,7 +129,7 @@ struct octep_vf_iq {
 	u16 flush_index;
 
 	/* Statistics for this input queue. */
-	struct octep_vf_iq_stats stats;
+	struct octep_vf_iq_stats *stats;
 
 	/* Pointer to the Virtual Base addr of the input ring. */
 	struct octep_vf_tx_desc_hw *desc_ring;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 8216f843a7cd..971993586fb4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -66,8 +66,18 @@ static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool en);
 /* Supported devices */
 static const struct pci_device_id cgx_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_CGX) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN10K_A) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF10K_A) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF10K_B) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN10K_B) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN20KA) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF20KA) },
 	{ 0, }  /* end of table */
 };
 
@@ -707,6 +717,11 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat)
 
 	if (!is_lmac_valid(cgx, lmac_id))
 		return -ENODEV;
+
+	/* pass lmac as 0 for CGX_CMR_RX_STAT9-12 */
+	if (idx >= CGX_RX_STAT_GLOBAL_INDEX)
+		lmac_id = 0;
+
 	*rx_stat =  cgx_read(cgx, lmac_id, CGXX_CMRX_RX_STAT0 + (idx * 8));
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index 5d84386ed22d..406c59100a35 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -159,6 +159,7 @@ enum nix_scheduler {
 #define	SDP_HW_MIN_FRS			16
 #define CN10K_LMAC_LINK_MAX_FRS		16380 /* 16k - FCS */
 #define CN10K_LBK_LINK_MAX_FRS		65535 /* 64k */
+#define SDP_LINK_CREDIT			0x320202
 
 /* NIX RX action operation*/
 #define NIX_RX_ACTIONOP_DROP		(0x0ull)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 1e5aa5397504..7d21905deed8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -188,14 +188,13 @@ int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid)
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies(MBOX_RSP_TIMEOUT);
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
-	struct device *sender = &mbox->pdev->dev;
 
 	while (!time_after(jiffies, timeout)) {
 		if (mdev->num_msgs == mdev->msgs_acked)
 			return 0;
 		usleep_range(800, 1000);
 	}
-	dev_dbg(sender, "timed out while waiting for rsp\n");
+	trace_otx2_msg_wait_rsp(mbox->pdev);
 	return -EIO;
 }
 EXPORT_SYMBOL(otx2_mbox_wait_for_rsp);
@@ -219,6 +218,7 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	struct mbox_hdr *tx_hdr, *rx_hdr;
 	void *hw_mbase = mdev->hwbase;
+	struct mbox_msghdr *msg;
 	u64 intr_val;
 
 	tx_hdr = hw_mbase + mbox->tx_start;
@@ -251,7 +251,10 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 	tx_hdr->num_msgs = mdev->num_msgs;
 	rx_hdr->num_msgs = 0;
 
-	trace_otx2_msg_send(mbox->pdev, tx_hdr->num_msgs, tx_hdr->msg_size);
+	msg = (struct mbox_msghdr *)(hw_mbase + mbox->tx_start + msgs_offset);
+
+	trace_otx2_msg_send(mbox->pdev, tx_hdr->num_msgs, tx_hdr->msg_size,
+			    msg->id, msg->pcifunc);
 
 	spin_unlock(&mdev->mbox_lock);
 
@@ -445,6 +448,14 @@ const char *otx2_mbox_id2name(u16 id)
 #define M(_name, _id, _1, _2, _3) case _id: return # _name;
 	MBOX_MESSAGES
 #undef M
+
+#define M(_name, _id, _1, _2, _3) case _id: return # _name;
+	MBOX_UP_CGX_MESSAGES
+#undef M
+
+#define M(_name, _id, _1, _2, _3) case _id: return # _name;
+	MBOX_UP_CPT_MESSAGES
+#undef M
 	default:
 		return "INVALID ID";
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 62c07407eb94..a213b2663583 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -313,6 +313,10 @@ M(NIX_BANDPROF_FREE,	0x801e, nix_bandprof_free, nix_bandprof_free_req,   \
 				msg_rsp)				    \
 M(NIX_BANDPROF_GET_HWINFO, 0x801f, nix_bandprof_get_hwinfo, msg_req,		\
 				nix_bandprof_get_hwinfo_rsp)		    \
+M(NIX_CPT_BP_ENABLE,    0x8020, nix_cpt_bp_enable, nix_bp_cfg_req,	    \
+				nix_bp_cfg_rsp)				    \
+M(NIX_CPT_BP_DISABLE,   0x8021, nix_cpt_bp_disable, nix_bp_cfg_req,	    \
+				msg_rsp)				\
 M(NIX_READ_INLINE_IPSEC_CFG, 0x8023, nix_read_inline_ipsec_cfg,		\
 				msg_req, nix_inline_ipsec_cfg)		\
 M(NIX_MCAST_GRP_CREATE,	0x802b, nix_mcast_grp_create, nix_mcast_grp_create_req,	\
@@ -520,6 +524,8 @@ struct get_hw_cap_rsp {
 	u8 nix_fixed_txschq_mapping; /* Schq mapping fixed or flexible */
 	u8 nix_shaping;		     /* Is shaping and coloring supported */
 	u8 npc_hash_extract;	/* Is hash extract supported */
+#define HW_CAP_MACSEC		BIT_ULL(1)
+	u64 hw_caps;
 };
 
 /* CGX mbox message formats */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
index d39d86e694cc..0277d226293e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
@@ -143,6 +143,8 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu)
 
 	otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf);
 
+	otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pf);
+
 	mutex_unlock(&rvu->mbox_lock);
 
 	return 0;
@@ -925,7 +927,6 @@ void rvu_mcs_exit(struct rvu *rvu)
 	if (!rvu->mcs_intr_wq)
 		return;
 
-	flush_workqueue(rvu->mcs_intr_wq);
 	destroy_workqueue(rvu->mcs_intr_wq);
 	rvu->mcs_intr_wq = NULL;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
index bcc96eed2481..66749b3649c1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
@@ -545,8 +545,7 @@ static int ptp_probe(struct pci_dev *pdev,
 	spin_lock_init(&ptp->ptp_lock);
 	if (cn10k_ptp_errata(ptp)) {
 		ptp->read_ptp_tstmp = &read_ptp_tstmp_sec_nsec;
-		hrtimer_init(&ptp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		ptp->hrtimer.function = ptp_reset_thresh;
+		hrtimer_setup(&ptp->hrtimer, ptp_reset_thresh, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	} else {
 		ptp->read_ptp_tstmp = &read_ptp_tstmp_nsec;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index cd0d7b7774f1..a8025f0486c9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1393,8 +1393,6 @@ static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype)
 	if (blkaddr < 0)
 		return;
 
-	if (blktype == BLKTYPE_NIX)
-		rvu_nix_reset_mac(pfvf, pcifunc);
 
 	block = &hw->block[blkaddr];
 
@@ -1407,6 +1405,10 @@ static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype)
 		if (lf < 0) /* This should never happen */
 			continue;
 
+		if (blktype == BLKTYPE_NIX) {
+			rvu_nix_reset_mac(pfvf, pcifunc);
+			rvu_npc_clear_ucast_entry(rvu, pcifunc, lf);
+		}
 		/* Disable the LF */
 		rvu_write64(rvu, blkaddr, block->lfcfg_reg |
 			    (lf << block->lfshift), 0x00ULL);
@@ -2031,6 +2033,9 @@ int rvu_mbox_handler_get_hw_cap(struct rvu *rvu, struct msg_req *req,
 	rsp->nix_shaping = hw->cap.nix_shaping;
 	rsp->npc_hash_extract = hw->cap.npc_hash_extract;
 
+	if (rvu->mcs_blk_cnt)
+		rsp->hw_caps = HW_CAP_MACSEC;
+
 	return 0;
 }
 
@@ -2173,7 +2178,7 @@ static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid,
 		if (rsp && err)						\
 			rsp->hdr.rc = err;				\
 									\
-		trace_otx2_msg_process(mbox->pdev, _id, err);		\
+		trace_otx2_msg_process(mbox->pdev, _id, err, req->pcifunc); \
 		return rsp ? err : -ENOMEM;				\
 	}
 MBOX_MESSAGES
@@ -2634,7 +2639,7 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
 		rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), intr);
 
 		rvu_queue_work(&rvu->afvf_wq_info, 64, vfs, intr);
-		vfs -= 64;
+		vfs = 64;
 	}
 
 	intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(0));
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index a383b5ef5b2d..48f66292ad5c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -30,6 +30,8 @@
 #define PCI_SUBSYS_DEVID_CNF10K_A	       0xBA00
 #define PCI_SUBSYS_DEVID_CNF10K_B              0xBC00
 #define PCI_SUBSYS_DEVID_CN10K_B               0xBD00
+#define PCI_SUBSYS_DEVID_CN20KA                0xC220
+#define PCI_SUBSYS_DEVID_CNF20KA               0xC320
 
 /* PCI BAR nos */
 #define	PCI_AF_REG_BAR_NUM			0
@@ -967,8 +969,6 @@ void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				  bool enable);
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, u64 chan);
-void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
-				bool enable);
 void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    u64 chan);
 void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
@@ -994,6 +994,8 @@ void rvu_npc_get_mcam_entry_alloc_info(struct rvu *rvu, u16 pcifunc,
 void rvu_npc_get_mcam_counter_alloc_info(struct rvu *rvu, u16 pcifunc,
 					 int blkaddr, int *alloc_cnt,
 					 int *enable_cnt);
+void rvu_npc_clear_ucast_entry(struct rvu *rvu, int pcifunc, int nixlf);
+
 bool is_npc_intf_tx(u8 intf);
 bool is_npc_intf_rx(u8 intf);
 bool is_npc_interface_valid(struct rvu *rvu, u8 intf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 992fa0b82e8d..d0331b0e0bfd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -34,7 +34,7 @@ static struct _req_type __maybe_unused					\
 		return NULL;						\
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;				\
 	req->hdr.id = _id;						\
-	trace_otx2_msg_alloc(rvu->pdev, _id, sizeof(*req));		\
+	trace_otx2_msg_alloc(rvu->pdev, _id, sizeof(*req), 0);		\
 	return req;							\
 }
 
@@ -272,6 +272,8 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu)
 
 		otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pfid);
 
+		otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pfid);
+
 		mutex_unlock(&rvu->mbox_lock);
 	} while (pfmap);
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 7fa98aeb3663..4a3370a40dd8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -13,19 +13,26 @@
 /* RVU LMTST */
 #define LMT_TBL_OP_READ		0
 #define LMT_TBL_OP_WRITE	1
-#define LMT_MAP_TABLE_SIZE	(128 * 1024)
 #define LMT_MAPTBL_ENTRY_SIZE	16
+#define LMT_MAX_VFS		256
+
+#define LMT_MAP_ENTRY_ENA      BIT_ULL(20)
+#define LMT_MAP_ENTRY_LINES    GENMASK_ULL(18, 16)
 
 /* Function to perform operations (read/write) on lmtst map table */
 static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 			       int lmt_tbl_op)
 {
 	void __iomem *lmt_map_base;
-	u64 tbl_base;
+	u64 tbl_base, cfg;
+	int pfs, vfs;
 
 	tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+	cfg  = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	vfs = 1 << (cfg & 0xF);
+	pfs = 1 << ((cfg >> 4) & 0x7);
 
-	lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE);
+	lmt_map_base = ioremap_wc(tbl_base, pfs * vfs * LMT_MAPTBL_ENTRY_SIZE);
 	if (!lmt_map_base) {
 		dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
 		return -ENOMEM;
@@ -35,6 +42,13 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 		*val = readq(lmt_map_base + index);
 	} else {
 		writeq((*val), (lmt_map_base + index));
+
+		cfg = FIELD_PREP(LMT_MAP_ENTRY_ENA, 0x1);
+		/* 2048 LMTLINES */
+		cfg |= FIELD_PREP(LMT_MAP_ENTRY_LINES, 0x6);
+
+		writeq(cfg, (lmt_map_base + (index + 8)));
+
 		/* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S
 		 * changes effective. Write 1 for flush and read is being used as a
 		 * barrier and sets up a data dependency. Write to 0 after a write
@@ -52,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 #define LMT_MAP_TBL_W1_OFF  8
 static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc)
 {
-	return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) +
+	return ((rvu_get_pf(pcifunc) * LMT_MAX_VFS) +
 		(pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE;
 }
 
@@ -69,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
 
 	mutex_lock(&rvu->rsrc_lock);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova);
-	pf = rvu_get_pf(pcifunc) & 0x1F;
+	pf = rvu_get_pf(pcifunc) & RVU_PFVF_PF_MASK;
 	val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 |
 	      ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 148144f5b61d..c827da626471 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -553,6 +553,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 	u64 lmt_addr, val, tbl_base;
 	int pf, vf, num_vfs, hw_vfs;
 	void __iomem *lmt_map_base;
+	int apr_pfs, apr_vfs;
 	int buf_size = 10240;
 	size_t off = 0;
 	int index = 0;
@@ -568,8 +569,12 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		return -ENOMEM;
 
 	tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+	val  = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	apr_vfs = 1 << (val & 0xF);
+	apr_pfs = 1 << ((val >> 4) & 0x7);
 
-	lmt_map_base = ioremap_wc(tbl_base, 128 * 1024);
+	lmt_map_base = ioremap_wc(tbl_base, apr_pfs * apr_vfs *
+				  LMT_MAPTBL_ENTRY_SIZE);
 	if (!lmt_map_base) {
 		dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
 		kfree(buf);
@@ -591,7 +596,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d  \t\t\t",
 				    pf);
 
-		index = pf * rvu->hw->total_vfs * LMT_MAPTBL_ENTRY_SIZE;
+		index = pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE;
 		off += scnprintf(&buf[off], buf_size - 1 - off, " 0x%llx\t\t",
 				 (tbl_base + index));
 		lmt_addr = readq(lmt_map_base + index);
@@ -604,7 +609,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		/* Reading num of VFs per PF */
 		rvu_get_pf_numvfs(rvu, pf, &num_vfs, &hw_vfs);
 		for (vf = 0; vf < num_vfs; vf++) {
-			index = (pf * rvu->hw->total_vfs * 16) +
+			index = (pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE) +
 				((vf + 1)  * LMT_MAPTBL_ENTRY_SIZE);
 			off += scnprintf(&buf[off], buf_size - 1 - off,
 					    "PF%d:VF%d  \t\t", pf, vf);
@@ -917,19 +922,18 @@ static void print_npa_qsize(struct seq_file *m, struct rvu_pfvf *pfvf)
 /* The 'qsize' entry dumps current Aura/Pool context Qsize
  * and each context's current enable/disable status in a bitmap.
  */
-static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused,
+static int rvu_dbg_qsize_display(struct seq_file *s, void *unsused,
 				 int blktype)
 {
-	void (*print_qsize)(struct seq_file *filp,
+	void (*print_qsize)(struct seq_file *s,
 			    struct rvu_pfvf *pfvf) = NULL;
-	struct dentry *current_dir;
 	struct rvu_pfvf *pfvf;
 	struct rvu *rvu;
 	int qsize_id;
 	u16 pcifunc;
 	int blkaddr;
 
-	rvu = filp->private;
+	rvu = s->private;
 	switch (blktype) {
 	case BLKTYPE_NPA:
 		qsize_id = rvu->rvu_dbg.npa_qsize_id;
@@ -945,32 +949,28 @@ static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused,
 		return -EINVAL;
 	}
 
-	if (blktype == BLKTYPE_NPA) {
+	if (blktype == BLKTYPE_NPA)
 		blkaddr = BLKADDR_NPA;
-	} else {
-		current_dir = filp->file->f_path.dentry->d_parent;
-		blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ?
-				   BLKADDR_NIX1 : BLKADDR_NIX0);
-	}
+	else
+		blkaddr = debugfs_get_aux_num(s->file);
 
 	if (!rvu_dbg_is_valid_lf(rvu, blkaddr, qsize_id, &pcifunc))
 		return -EINVAL;
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
-	print_qsize(filp, pfvf);
+	print_qsize(s, pfvf);
 
 	return 0;
 }
 
-static ssize_t rvu_dbg_qsize_write(struct file *filp,
+static ssize_t rvu_dbg_qsize_write(struct file *file,
 				   const char __user *buffer, size_t count,
 				   loff_t *ppos, int blktype)
 {
 	char *blk_string = (blktype == BLKTYPE_NPA) ? "npa" : "nix";
-	struct seq_file *seqfile = filp->private_data;
+	struct seq_file *seqfile = file->private_data;
 	char *cmd_buf, *cmd_buf_tmp, *subtoken;
 	struct rvu *rvu = seqfile->private;
-	struct dentry *current_dir;
 	int blkaddr;
 	u16 pcifunc;
 	int ret, lf;
@@ -996,13 +996,10 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp,
 		goto qsize_write_done;
 	}
 
-	if (blktype == BLKTYPE_NPA) {
+	if (blktype == BLKTYPE_NPA)
 		blkaddr = BLKADDR_NPA;
-	} else {
-		current_dir = filp->f_path.dentry->d_parent;
-		blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ?
-				   BLKADDR_NIX1 : BLKADDR_NIX0);
-	}
+	else
+		blkaddr = debugfs_get_aux_num(file);
 
 	if (!rvu_dbg_is_valid_lf(rvu, blkaddr, lf, &pcifunc)) {
 		ret = -EINVAL;
@@ -2704,8 +2701,8 @@ static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr)
 			    &rvu_dbg_nix_ndc_tx_hits_miss_fops);
 	debugfs_create_file("ndc_rx_hits_miss", 0600, rvu->rvu_dbg.nix, nix_hw,
 			    &rvu_dbg_nix_ndc_rx_hits_miss_fops);
-	debugfs_create_file("qsize", 0600, rvu->rvu_dbg.nix, rvu,
-			    &rvu_dbg_nix_qsize_fops);
+	debugfs_create_file_aux_num("qsize", 0600, rvu->rvu_dbg.nix, rvu,
+			    blkaddr, &rvu_dbg_nix_qsize_fops);
 	debugfs_create_file("ingress_policer_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
 			    &rvu_dbg_nix_band_prof_ctx_fops);
 	debugfs_create_file("ingress_policer_rsrc", 0600, rvu->rvu_dbg.nix, nix_hw,
@@ -2854,28 +2851,14 @@ static int cgx_print_stats(struct seq_file *s, int lmac_id)
 	return err;
 }
 
-static int rvu_dbg_derive_lmacid(struct seq_file *filp, int *lmac_id)
+static int rvu_dbg_derive_lmacid(struct seq_file *s)
 {
-	struct dentry *current_dir;
-	char *buf;
-
-	current_dir = filp->file->f_path.dentry->d_parent;
-	buf = strrchr(current_dir->d_name.name, 'c');
-	if (!buf)
-		return -EINVAL;
-
-	return kstrtoint(buf + 1, 10, lmac_id);
+	return debugfs_get_aux_num(s->file);
 }
 
-static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused)
+static int rvu_dbg_cgx_stat_display(struct seq_file *s, void *unused)
 {
-	int lmac_id, err;
-
-	err = rvu_dbg_derive_lmacid(filp, &lmac_id);
-	if (!err)
-		return cgx_print_stats(filp, lmac_id);
-
-	return err;
+	return cgx_print_stats(s, rvu_dbg_derive_lmacid(s));
 }
 
 RVU_DEBUG_SEQ_FOPS(cgx_stat, cgx_stat_display, NULL);
@@ -2933,15 +2916,9 @@ static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id)
 	return 0;
 }
 
-static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *filp, void *unused)
+static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *s, void *unused)
 {
-	int err, lmac_id;
-
-	err = rvu_dbg_derive_lmacid(filp, &lmac_id);
-	if (!err)
-		return cgx_print_dmac_flt(filp, lmac_id);
-
-	return err;
+	return cgx_print_dmac_flt(s, rvu_dbg_derive_lmacid(s));
 }
 
 RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL);
@@ -2980,10 +2957,10 @@ static void rvu_dbg_cgx_init(struct rvu *rvu)
 			rvu->rvu_dbg.lmac =
 				debugfs_create_dir(dname, rvu->rvu_dbg.cgx);
 
-			debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac,
-					    cgx, &rvu_dbg_cgx_stat_fops);
-			debugfs_create_file("mac_filter", 0600,
-					    rvu->rvu_dbg.lmac, cgx,
+			debugfs_create_file_aux_num("stats", 0600, rvu->rvu_dbg.lmac,
+					    cgx, lmac_id, &rvu_dbg_cgx_stat_fops);
+			debugfs_create_file_aux_num("mac_filter", 0600,
+					    rvu->rvu_dbg.lmac, cgx, lmac_id,
 					    &rvu_dbg_cgx_dmac_flt_fops);
 		}
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index dab4deca893f..27c3a2daaaa9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -207,7 +207,7 @@ static void rvu_nix_unregister_interrupts(struct rvu *rvu)
 		rvu->irq_allocated[offs + NIX_AF_INT_VEC_RVU] = false;
 	}
 
-	for (i = NIX_AF_INT_VEC_AF_ERR; i < NIX_AF_INT_VEC_CNT; i++)
+	for (i = NIX_AF_INT_VEC_GEN; i < NIX_AF_INT_VEC_CNT; i++)
 		if (rvu->irq_allocated[offs + i]) {
 			free_irq(pci_irq_vector(rvu->pdev, offs + i), rvu_dl);
 			rvu->irq_allocated[offs + i] = false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 5d5a01dbbca1..613655fcd34f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -569,9 +569,17 @@ void rvu_nix_flr_free_bpids(struct rvu *rvu, u16 pcifunc)
 	mutex_unlock(&rvu->rsrc_lock);
 }
 
-int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
-				    struct nix_bp_cfg_req *req,
-				    struct msg_rsp *rsp)
+static u16 nix_get_channel(u16 chan, bool cpt_link)
+{
+	/* CPT channel for a given link channel is always
+	 * assumed to be BIT(11) set in link channel.
+	 */
+	return cpt_link ? chan | BIT(11) : chan;
+}
+
+static int nix_bp_disable(struct rvu *rvu,
+			  struct nix_bp_cfg_req *req,
+			  struct msg_rsp *rsp, bool cpt_link)
 {
 	u16 pcifunc = req->hdr.pcifunc;
 	int blkaddr, pf, type, err;
@@ -579,6 +587,7 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
 	struct rvu_pfvf *pfvf;
 	struct nix_hw *nix_hw;
 	struct nix_bp *bp;
+	u16 chan_v;
 	u64 cfg;
 
 	pf = rvu_get_pf(pcifunc);
@@ -589,6 +598,9 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
 	if (is_sdp_pfvf(pcifunc))
 		type = NIX_INTF_TYPE_SDP;
 
+	if (cpt_link && !rvu->hw->cpt_links)
+		return 0;
+
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr);
 	if (err)
@@ -597,8 +609,9 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
 	bp = &nix_hw->bp;
 	chan_base = pfvf->rx_chan_base + req->chan_base;
 	for (chan = chan_base; chan < (chan_base + req->chan_cnt); chan++) {
-		cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan));
-		rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan),
+		chan_v = nix_get_channel(chan, cpt_link);
+		cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan_v));
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan_v),
 			    cfg & ~BIT_ULL(16));
 
 		if (type == NIX_INTF_TYPE_LBK) {
@@ -617,6 +630,20 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
 	return 0;
 }
 
+int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
+				    struct nix_bp_cfg_req *req,
+				    struct msg_rsp *rsp)
+{
+	return nix_bp_disable(rvu, req, rsp, false);
+}
+
+int rvu_mbox_handler_nix_cpt_bp_disable(struct rvu *rvu,
+					struct nix_bp_cfg_req *req,
+					struct msg_rsp *rsp)
+{
+	return nix_bp_disable(rvu, req, rsp, true);
+}
+
 static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
 			    int type, int chan_id)
 {
@@ -696,15 +723,17 @@ static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
 	return bpid;
 }
 
-int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu,
-				   struct nix_bp_cfg_req *req,
-				   struct nix_bp_cfg_rsp *rsp)
+static int nix_bp_enable(struct rvu *rvu,
+			 struct nix_bp_cfg_req *req,
+			 struct nix_bp_cfg_rsp *rsp,
+			 bool cpt_link)
 {
 	int blkaddr, pf, type, chan_id = 0;
 	u16 pcifunc = req->hdr.pcifunc;
 	struct rvu_pfvf *pfvf;
 	u16 chan_base, chan;
 	s16 bpid, bpid_base;
+	u16 chan_v;
 	u64 cfg;
 
 	pf = rvu_get_pf(pcifunc);
@@ -717,6 +746,9 @@ int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu,
 	    type != NIX_INTF_TYPE_SDP)
 		return 0;
 
+	if (cpt_link && !rvu->hw->cpt_links)
+		return 0;
+
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 
@@ -730,9 +762,11 @@ int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu,
 			return -EINVAL;
 		}
 
-		cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan));
+		chan_v = nix_get_channel(chan, cpt_link);
+
+		cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan_v));
 		cfg &= ~GENMASK_ULL(8, 0);
-		rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan),
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_CHANX_CFG(chan_v),
 			    cfg | (bpid & GENMASK_ULL(8, 0)) | BIT_ULL(16));
 		chan_id++;
 		bpid = rvu_nix_get_bpid(rvu, req, type, chan_id);
@@ -750,6 +784,20 @@ int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu,
 	return 0;
 }
 
+int rvu_mbox_handler_nix_bp_enable(struct rvu *rvu,
+				   struct nix_bp_cfg_req *req,
+				   struct nix_bp_cfg_rsp *rsp)
+{
+	return nix_bp_enable(rvu, req, rsp, false);
+}
+
+int rvu_mbox_handler_nix_cpt_bp_enable(struct rvu *rvu,
+				       struct nix_bp_cfg_req *req,
+				       struct nix_bp_cfg_rsp *rsp)
+{
+	return nix_bp_enable(rvu, req, rsp, true);
+}
+
 static void nix_setup_lso_tso_l3(struct rvu *rvu, int blkaddr,
 				 u64 format, bool v4, u64 *fidx)
 {
@@ -4672,6 +4720,9 @@ static void nix_link_config(struct rvu *rvu, int blkaddr,
 	rvu_get_lbk_link_max_frs(rvu, &lbk_max_frs);
 	rvu_get_lmac_link_max_frs(rvu, &lmac_max_frs);
 
+	/* Set SDP link credit */
+	rvu_write64(rvu, blkaddr, NIX_AF_SDP_LINK_CREDIT, SDP_LINK_CREDIT);
+
 	/* Set default min/max packet lengths allowed on NIX Rx links.
 	 *
 	 * With HW reset minlen value of 60byte, HW will treat ARP pkts
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 821fe242f821..da15bb451178 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -820,24 +820,6 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
 
-void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
-				bool enable)
-{
-	struct npc_mcam *mcam = &rvu->hw->mcam;
-	int blkaddr, index;
-
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
-	if (blkaddr < 0)
-		return;
-
-	/* Get 'pcifunc' of PF device */
-	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
-
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf,
-					 NIXLF_BCAST_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
-}
-
 void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    u64 chan)
 {
@@ -1125,6 +1107,7 @@ void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
 static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, bool enable)
 {
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	int index, blkaddr;
 
@@ -1133,9 +1116,12 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 		return;
 
 	/* Ucast MCAM match entry of this PF/VF */
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-					 nixlf, NIXLF_UCAST_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+	if (npc_is_feature_supported(rvu, BIT_ULL(NPC_DMAC),
+				     pfvf->nix_rx_intf)) {
+		index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+						 nixlf, NIXLF_UCAST_ENTRY);
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+	}
 
 	/* Nothing to do for VFs, on platforms where pkt replication
 	 * is not supported
@@ -3588,3 +3574,33 @@ int rvu_mbox_handler_npc_mcam_entry_stats(struct rvu *rvu,
 
 	return 0;
 }
+
+void rvu_npc_clear_ucast_entry(struct rvu *rvu, int pcifunc, int nixlf)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_npc_mcam_rule *rule;
+	int ucast_idx, blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					     nixlf, NIXLF_UCAST_ENTRY);
+
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, ucast_idx, false);
+
+	npc_set_mcam_action(rvu, mcam, blkaddr, ucast_idx, 0);
+
+	npc_clear_mcam_entry(rvu, mcam, blkaddr, ucast_idx);
+
+	mutex_lock(&mcam->lock);
+	list_for_each_entry(rule, &mcam->mcam_rules, list) {
+		if (rule->entry == ucast_idx) {
+			list_del(&rule->list);
+			kfree(rule);
+			break;
+		}
+	}
+	mutex_unlock(&mcam->lock);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index da69e454662a..1b765045aa63 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -1452,23 +1452,21 @@ process_flow:
 	 * hence modify pcifunc accordingly.
 	 */
 
-	/* AF installing for a PF/VF */
-	if (!req->hdr.pcifunc)
+	if (!req->hdr.pcifunc) {
+		/* AF installing for a PF/VF */
 		target = req->vf;
-
-	/* PF installing for its VF */
-	if (!from_vf && req->vf && !from_rep_dev) {
+	} else if (!from_vf && req->vf && !from_rep_dev) {
+		/* PF installing for its VF */
 		target = (req->hdr.pcifunc & ~RVU_PFVF_FUNC_MASK) | req->vf;
 		pf_set_vfs_mac = req->default_rule &&
 				(req->features & BIT_ULL(NPC_DMAC));
-	}
-
-	/* Representor device installing for a representee */
-	if (from_rep_dev && req->vf)
+	} else if (from_rep_dev && req->vf) {
+		/* Representor device installing for a representee */
 		target = req->vf;
-	else
+	} else {
 		/* msg received from PF/VF */
 		target = req->hdr.pcifunc;
+	}
 
 	/* ignore chan_mask in case pf func is not AF, revisit later */
 	if (!is_pffunc_af(req->hdr.pcifunc))
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
index 052ae5923e3a..32953cca108c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
@@ -60,6 +60,8 @@ static int rvu_rep_up_notify(struct rvu *rvu, struct rep_event *event)
 
 	otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf);
 
+	otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pf);
+
 	mutex_unlock(&rvu->mbox_lock);
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
index 775fd4c35794..19e0d16b12f6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
@@ -11,3 +11,5 @@
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_alloc);
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_interrupt);
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_process);
+EXPORT_TRACEPOINT_SYMBOL(otx2_msg_status);
+EXPORT_TRACEPOINT_SYMBOL(otx2_parse_dump);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
index 5704520f9b02..4cd0fc4b0d20 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
@@ -18,33 +18,42 @@
 #include "mbox.h"
 
 TRACE_EVENT(otx2_msg_alloc,
-	    TP_PROTO(const struct pci_dev *pdev, u16 id, u64 size),
-	    TP_ARGS(pdev, id, size),
+	    TP_PROTO(const struct pci_dev *pdev, u16 id, u64 size, u16 pcifunc),
+	    TP_ARGS(pdev, id, size, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, id)
 			     __field(u64, size)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->id = id;
 			   __entry->size = size;
+			   __entry->pcifunc = pcifunc;
 	    ),
-	    TP_printk("[%s] msg:(%s) size:%lld\n", __get_str(dev),
-		      otx2_mbox_id2name(__entry->id), __entry->size)
+	    TP_printk("[%s] msg:(%s) size:%lld pcifunc:0x%x\n", __get_str(dev),
+		      otx2_mbox_id2name(__entry->id), __entry->size,
+		      __entry->pcifunc)
 );
 
 TRACE_EVENT(otx2_msg_send,
-	    TP_PROTO(const struct pci_dev *pdev, u16 num_msgs, u64 msg_size),
-	    TP_ARGS(pdev, num_msgs, msg_size),
+	    TP_PROTO(const struct pci_dev *pdev, u16 num_msgs, u64 msg_size,
+		     u16 id, u16 pcifunc),
+	    TP_ARGS(pdev, num_msgs, msg_size, id, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, num_msgs)
 			     __field(u64, msg_size)
+			     __field(u16, id)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->num_msgs = num_msgs;
 			   __entry->msg_size = msg_size;
+			   __entry->id = id;
+			   __entry->pcifunc = pcifunc;
 	    ),
-	    TP_printk("[%s] sent %d msg(s) of size:%lld\n", __get_str(dev),
-		      __entry->num_msgs, __entry->msg_size)
+	    TP_printk("[%s] sent %d msg(s) of size:%lld msg:(%s) pcifunc:0x%x\n",
+		      __get_str(dev), __entry->num_msgs, __entry->msg_size,
+		      otx2_mbox_id2name(__entry->id), __entry->pcifunc)
 );
 
 TRACE_EVENT(otx2_msg_check,
@@ -81,18 +90,73 @@ TRACE_EVENT(otx2_msg_interrupt,
 );
 
 TRACE_EVENT(otx2_msg_process,
-	    TP_PROTO(const struct pci_dev *pdev, u16 id, int err),
-	    TP_ARGS(pdev, id, err),
+	    TP_PROTO(const struct pci_dev *pdev, u16 id, int err, u16 pcifunc),
+	    TP_ARGS(pdev, id, err, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, id)
 			     __field(int, err)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->id = id;
 			   __entry->err = err;
+			   __entry->pcifunc = pcifunc;
+	    ),
+	    TP_printk("[%s] msg:(%s) error:%d pcifunc:0x%x\n", __get_str(dev),
+		      otx2_mbox_id2name(__entry->id),
+		      __entry->err, __entry->pcifunc)
+);
+
+TRACE_EVENT(otx2_msg_wait_rsp,
+	    TP_PROTO(const struct pci_dev *pdev),
+	    TP_ARGS(pdev),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+	    ),
+	    TP_fast_assign(__assign_str(dev)
+	    ),
+	    TP_printk("[%s] timed out while waiting for response\n",
+		      __get_str(dev))
+);
+
+TRACE_EVENT(otx2_msg_status,
+	    TP_PROTO(const struct pci_dev *pdev, const char *msg, u16 num_msgs),
+	    TP_ARGS(pdev, msg, num_msgs),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __string(str, msg)
+			     __field(u16, num_msgs)
+	    ),
+	    TP_fast_assign(__assign_str(dev);
+			   __assign_str(str);
+			   __entry->num_msgs = num_msgs;
+	    ),
+	    TP_printk("[%s] %s num_msgs:%d\n", __get_str(dev),
+		      __get_str(str), __entry->num_msgs)
+);
+
+TRACE_EVENT(otx2_parse_dump,
+	    TP_PROTO(const struct pci_dev *pdev, char *msg, u64 *word),
+	    TP_ARGS(pdev, msg, word),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __string(str, msg)
+			     __field(u64, w0)
+			     __field(u64, w1)
+			     __field(u64, w2)
+			     __field(u64, w3)
+			     __field(u64, w4)
+			     __field(u64, w5)
+	    ),
+	    TP_fast_assign(__assign_str(dev);
+			   __assign_str(str);
+			   __entry->w0 = *(word + 0);
+			   __entry->w1 = *(word + 1);
+			   __entry->w2 = *(word + 2);
+			   __entry->w3 = *(word + 3);
+			   __entry->w4 = *(word + 4);
+			   __entry->w5 = *(word + 5);
 	    ),
-	    TP_printk("[%s] msg:(%s) error:%d\n", __get_str(dev),
-		      otx2_mbox_id2name(__entry->id), __entry->err)
+	    TP_printk("[%s] nix parse %s W0:%#llx W1:%#llx W2:%#llx W3:%#llx W4:%#llx W5:%#llx\n",
+		      __get_str(dev), __get_str(str), __entry->w0, __entry->w1, __entry->w2,
+		      __entry->w3, __entry->w4, __entry->w5)
 );
 
 #endif /* __RVU_TRACE_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
index dbc971266865..69e0778f9ac1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
@@ -9,11 +9,12 @@ obj-$(CONFIG_RVU_ESWITCH) += rvu_rep.o
 
 rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
                otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \
-               otx2_devlink.o qos_sq.o qos.o
+               otx2_devlink.o qos_sq.o qos.o otx2_xsk.o
 rvu_nicvf-y := otx2_vf.o
 rvu_rep-y := rep.o
 
 rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o
 rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o
+rvu_nicpf-$(CONFIG_XFRM_OFFLOAD) += cn10k_ipsec.o
 
 ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index a15cc86635d6..7f6a435ac680 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -112,9 +112,12 @@ int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 	struct otx2_nic *pfvf = dev;
 	int cnt = cq->pool_ptrs;
 	u64 ptrs[NPA_MAX_BURST];
+	struct otx2_pool *pool;
 	dma_addr_t bufptr;
 	int num_ptrs = 1;
 
+	pool = &pfvf->qset.pool[cq->cq_idx];
+
 	/* Refill pool with new buffers */
 	while (cq->pool_ptrs) {
 		if (otx2_alloc_buffer(pfvf, cq, &bufptr)) {
@@ -124,7 +127,9 @@ int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 			break;
 		}
 		cq->pool_ptrs--;
-		ptrs[num_ptrs] = (u64)bufptr + OTX2_HEAD_ROOM;
+		ptrs[num_ptrs] = pool->xsk_pool ?
+				 (u64)bufptr : (u64)bufptr + OTX2_HEAD_ROOM;
+
 		num_ptrs++;
 		if (num_ptrs == NPA_MAX_BURST || cq->pool_ptrs == 0) {
 			__cn10k_aura_freeptr(pfvf, cq->cq_idx, ptrs,
@@ -352,9 +357,12 @@ int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf)
 	mutex_lock(&pfvf->mbox.lock);
 
 	/* Remove RQ's policer mapping */
-	for (qidx = 0; qidx < hw->rx_queues; qidx++)
-		cn10k_map_unmap_rq_policer(pfvf, qidx,
-					   hw->matchall_ipolicer, false);
+	for (qidx = 0; qidx < hw->rx_queues; qidx++) {
+		rc = cn10k_map_unmap_rq_policer(pfvf, qidx, hw->matchall_ipolicer, false);
+		if (rc)
+			dev_warn(pfvf->dev, "Failed to unmap RQ %d's policer (error %d).",
+				 qidx, rc);
+	}
 
 	rc = cn10k_free_leaf_profile(pfvf, hw->matchall_ipolicer);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
new file mode 100644
index 000000000000..a6500e3673f2
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
@@ -0,0 +1,1041 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell IPSEC offload driver
+ *
+ * Copyright (C) 2024 Marvell.
+ */
+
+#include <net/xfrm.h>
+#include <linux/netdevice.h>
+#include <linux/bitfield.h>
+#include <crypto/aead.h>
+#include <crypto/gcm.h>
+
+#include "otx2_common.h"
+#include "otx2_struct.h"
+#include "cn10k_ipsec.h"
+
+static bool is_dev_support_ipsec_offload(struct pci_dev *pdev)
+{
+	return is_dev_cn10ka_b0(pdev) || is_dev_cn10kb(pdev);
+}
+
+static bool cn10k_cpt_device_set_inuse(struct otx2_nic *pf)
+{
+	enum cn10k_cpt_hw_state_e state;
+
+	while (true) {
+		state = atomic_cmpxchg(&pf->ipsec.cpt_state,
+				       CN10K_CPT_HW_AVAILABLE,
+				       CN10K_CPT_HW_IN_USE);
+		if (state == CN10K_CPT_HW_AVAILABLE)
+			return true;
+		if (state == CN10K_CPT_HW_UNAVAILABLE)
+			return false;
+
+		mdelay(1);
+	}
+}
+
+static void cn10k_cpt_device_set_available(struct otx2_nic *pf)
+{
+	atomic_set(&pf->ipsec.cpt_state, CN10K_CPT_HW_AVAILABLE);
+}
+
+static void  cn10k_cpt_device_set_unavailable(struct otx2_nic *pf)
+{
+	atomic_set(&pf->ipsec.cpt_state, CN10K_CPT_HW_UNAVAILABLE);
+}
+
+static int cn10k_outb_cptlf_attach(struct otx2_nic *pf)
+{
+	struct rsrc_attach *attach;
+	int ret = -ENOMEM;
+
+	mutex_lock(&pf->mbox.lock);
+	/* Get memory to put this msg */
+	attach = otx2_mbox_alloc_msg_attach_resources(&pf->mbox);
+	if (!attach)
+		goto unlock;
+
+	attach->cptlfs = true;
+	attach->modify = true;
+
+	/* Send attach request to AF */
+	ret = otx2_sync_mbox_msg(&pf->mbox);
+
+unlock:
+	mutex_unlock(&pf->mbox.lock);
+	return ret;
+}
+
+static int cn10k_outb_cptlf_detach(struct otx2_nic *pf)
+{
+	struct rsrc_detach *detach;
+	int ret = -ENOMEM;
+
+	mutex_lock(&pf->mbox.lock);
+	detach = otx2_mbox_alloc_msg_detach_resources(&pf->mbox);
+	if (!detach)
+		goto unlock;
+
+	detach->partial = true;
+	detach->cptlfs = true;
+
+	/* Send detach request to AF */
+	ret = otx2_sync_mbox_msg(&pf->mbox);
+
+unlock:
+	mutex_unlock(&pf->mbox.lock);
+	return ret;
+}
+
+static int cn10k_outb_cptlf_alloc(struct otx2_nic *pf)
+{
+	struct cpt_lf_alloc_req_msg *req;
+	int ret = -ENOMEM;
+
+	mutex_lock(&pf->mbox.lock);
+	req = otx2_mbox_alloc_msg_cpt_lf_alloc(&pf->mbox);
+	if (!req)
+		goto unlock;
+
+	/* PF function */
+	req->nix_pf_func = pf->pcifunc;
+	/* Enable SE-IE Engine Group */
+	req->eng_grpmsk = 1 << CN10K_DEF_CPT_IPSEC_EGRP;
+
+	ret = otx2_sync_mbox_msg(&pf->mbox);
+
+unlock:
+	mutex_unlock(&pf->mbox.lock);
+	return ret;
+}
+
+static void cn10k_outb_cptlf_free(struct otx2_nic *pf)
+{
+	mutex_lock(&pf->mbox.lock);
+	otx2_mbox_alloc_msg_cpt_lf_free(&pf->mbox);
+	otx2_sync_mbox_msg(&pf->mbox);
+	mutex_unlock(&pf->mbox.lock);
+}
+
+static int cn10k_outb_cptlf_config(struct otx2_nic *pf)
+{
+	struct cpt_inline_ipsec_cfg_msg *req;
+	int ret = -ENOMEM;
+
+	mutex_lock(&pf->mbox.lock);
+	req = otx2_mbox_alloc_msg_cpt_inline_ipsec_cfg(&pf->mbox);
+	if (!req)
+		goto unlock;
+
+	req->dir = CPT_INLINE_OUTBOUND;
+	req->enable = 1;
+	req->nix_pf_func = pf->pcifunc;
+	ret = otx2_sync_mbox_msg(&pf->mbox);
+unlock:
+	mutex_unlock(&pf->mbox.lock);
+	return ret;
+}
+
+static void cn10k_outb_cptlf_iq_enable(struct otx2_nic *pf)
+{
+	u64 reg_val;
+
+	/* Set Execution Enable of instruction queue */
+	reg_val = otx2_read64(pf, CN10K_CPT_LF_INPROG);
+	reg_val |= BIT_ULL(16);
+	otx2_write64(pf, CN10K_CPT_LF_INPROG, reg_val);
+
+	/* Set iqueue's enqueuing */
+	reg_val = otx2_read64(pf, CN10K_CPT_LF_CTL);
+	reg_val |= BIT_ULL(0);
+	otx2_write64(pf, CN10K_CPT_LF_CTL, reg_val);
+}
+
+static void cn10k_outb_cptlf_iq_disable(struct otx2_nic *pf)
+{
+	u32 inflight, grb_cnt, gwb_cnt;
+	u32 nq_ptr, dq_ptr;
+	int timeout = 20;
+	u64 reg_val;
+	int cnt;
+
+	/* Disable instructions enqueuing */
+	otx2_write64(pf, CN10K_CPT_LF_CTL, 0ull);
+
+	/* Wait for instruction queue to become empty.
+	 * CPT_LF_INPROG.INFLIGHT count is zero
+	 */
+	do {
+		reg_val = otx2_read64(pf, CN10K_CPT_LF_INPROG);
+		inflight = FIELD_GET(CPT_LF_INPROG_INFLIGHT, reg_val);
+		if (!inflight)
+			break;
+
+		usleep_range(10000, 20000);
+		if (timeout-- < 0) {
+			netdev_err(pf->netdev, "Timeout to cleanup CPT IQ\n");
+			break;
+		}
+	} while (1);
+
+	/* Disable executions in the LF's queue,
+	 * the queue should be empty at this point
+	 */
+	reg_val &= ~BIT_ULL(16);
+	otx2_write64(pf, CN10K_CPT_LF_INPROG, reg_val);
+
+	/* Wait for instruction queue to become empty */
+	cnt = 0;
+	do {
+		reg_val = otx2_read64(pf, CN10K_CPT_LF_INPROG);
+		if (reg_val & BIT_ULL(31))
+			cnt = 0;
+		else
+			cnt++;
+		reg_val = otx2_read64(pf, CN10K_CPT_LF_Q_GRP_PTR);
+		nq_ptr = FIELD_GET(CPT_LF_Q_GRP_PTR_DQ_PTR, reg_val);
+		dq_ptr = FIELD_GET(CPT_LF_Q_GRP_PTR_DQ_PTR, reg_val);
+	} while ((cnt < 10) && (nq_ptr != dq_ptr));
+
+	cnt = 0;
+	do {
+		reg_val = otx2_read64(pf, CN10K_CPT_LF_INPROG);
+		inflight = FIELD_GET(CPT_LF_INPROG_INFLIGHT, reg_val);
+		grb_cnt = FIELD_GET(CPT_LF_INPROG_GRB_CNT, reg_val);
+		gwb_cnt = FIELD_GET(CPT_LF_INPROG_GWB_CNT, reg_val);
+		if (inflight == 0 && gwb_cnt < 40 &&
+		    (grb_cnt == 0 || grb_cnt == 40))
+			cnt++;
+		else
+			cnt = 0;
+	} while (cnt < 10);
+}
+
+/* Allocate memory for CPT outbound Instruction queue.
+ * Instruction queue memory format is:
+ *      -----------------------------
+ *     | Instruction Group memory    |
+ *     |  (CPT_LF_Q_SIZE[SIZE_DIV40] |
+ *     |   x 16 Bytes)               |
+ *     |                             |
+ *      ----------------------------- <-- CPT_LF_Q_BASE[ADDR]
+ *     | Flow Control (128 Bytes)    |
+ *     |                             |
+ *      -----------------------------
+ *     |  Instruction Memory         |
+ *     |  (CPT_LF_Q_SIZE[SIZE_DIV40] |
+ *     |   × 40 × 64 bytes)          |
+ *     |                             |
+ *      -----------------------------
+ */
+static int cn10k_outb_cptlf_iq_alloc(struct otx2_nic *pf)
+{
+	struct cn10k_cpt_inst_queue *iq = &pf->ipsec.iq;
+
+	iq->size = CN10K_CPT_INST_QLEN_BYTES + CN10K_CPT_Q_FC_LEN +
+		    CN10K_CPT_INST_GRP_QLEN_BYTES + OTX2_ALIGN;
+
+	iq->real_vaddr = dma_alloc_coherent(pf->dev, iq->size,
+					    &iq->real_dma_addr, GFP_KERNEL);
+	if (!iq->real_vaddr)
+		return -ENOMEM;
+
+	/* iq->vaddr/dma_addr points to Flow Control location */
+	iq->vaddr = iq->real_vaddr + CN10K_CPT_INST_GRP_QLEN_BYTES;
+	iq->dma_addr = iq->real_dma_addr + CN10K_CPT_INST_GRP_QLEN_BYTES;
+
+	/* Align pointers */
+	iq->vaddr = PTR_ALIGN(iq->vaddr, OTX2_ALIGN);
+	iq->dma_addr = PTR_ALIGN(iq->dma_addr, OTX2_ALIGN);
+	return 0;
+}
+
+static void cn10k_outb_cptlf_iq_free(struct otx2_nic *pf)
+{
+	struct cn10k_cpt_inst_queue *iq = &pf->ipsec.iq;
+
+	if (iq->real_vaddr)
+		dma_free_coherent(pf->dev, iq->size, iq->real_vaddr,
+				  iq->real_dma_addr);
+
+	iq->real_vaddr = NULL;
+	iq->vaddr = NULL;
+}
+
+static int cn10k_outb_cptlf_iq_init(struct otx2_nic *pf)
+{
+	u64 reg_val;
+	int ret;
+
+	/* Allocate Memory for CPT IQ */
+	ret = cn10k_outb_cptlf_iq_alloc(pf);
+	if (ret)
+		return ret;
+
+	/* Disable IQ */
+	cn10k_outb_cptlf_iq_disable(pf);
+
+	/* Set IQ base address */
+	otx2_write64(pf, CN10K_CPT_LF_Q_BASE, pf->ipsec.iq.dma_addr);
+
+	/* Set IQ size */
+	reg_val = FIELD_PREP(CPT_LF_Q_SIZE_DIV40, CN10K_CPT_SIZE_DIV40 +
+			     CN10K_CPT_EXTRA_SIZE_DIV40);
+	otx2_write64(pf, CN10K_CPT_LF_Q_SIZE, reg_val);
+
+	return 0;
+}
+
+static int cn10k_outb_cptlf_init(struct otx2_nic *pf)
+{
+	int ret;
+
+	/* Initialize CPTLF Instruction Queue (IQ) */
+	ret = cn10k_outb_cptlf_iq_init(pf);
+	if (ret)
+		return ret;
+
+	/* Configure CPTLF for outbound ipsec offload */
+	ret = cn10k_outb_cptlf_config(pf);
+	if (ret)
+		goto iq_clean;
+
+	/* Enable CPTLF IQ */
+	cn10k_outb_cptlf_iq_enable(pf);
+	return 0;
+iq_clean:
+	cn10k_outb_cptlf_iq_free(pf);
+	return ret;
+}
+
+static int cn10k_outb_cpt_init(struct net_device *netdev)
+{
+	struct otx2_nic *pf = netdev_priv(netdev);
+	int ret;
+
+	/* Attach a CPT LF for outbound ipsec offload */
+	ret = cn10k_outb_cptlf_attach(pf);
+	if (ret)
+		return ret;
+
+	/* Allocate a CPT LF for outbound ipsec offload */
+	ret = cn10k_outb_cptlf_alloc(pf);
+	if (ret)
+		goto detach;
+
+	/* Initialize the CPTLF for outbound ipsec offload */
+	ret = cn10k_outb_cptlf_init(pf);
+	if (ret)
+		goto lf_free;
+
+	pf->ipsec.io_addr = (__force u64)otx2_get_regaddr(pf,
+						CN10K_CPT_LF_NQX(0));
+
+	/* Set ipsec offload enabled for this device */
+	pf->flags |= OTX2_FLAG_IPSEC_OFFLOAD_ENABLED;
+
+	cn10k_cpt_device_set_available(pf);
+	return 0;
+
+lf_free:
+	cn10k_outb_cptlf_free(pf);
+detach:
+	cn10k_outb_cptlf_detach(pf);
+	return ret;
+}
+
+static int cn10k_outb_cpt_clean(struct otx2_nic *pf)
+{
+	int ret;
+
+	if (!cn10k_cpt_device_set_inuse(pf)) {
+		netdev_err(pf->netdev, "CPT LF device unavailable\n");
+		return -ENODEV;
+	}
+
+	/* Set ipsec offload disabled for this device */
+	pf->flags &= ~OTX2_FLAG_IPSEC_OFFLOAD_ENABLED;
+
+	/* Disable CPTLF Instruction Queue (IQ) */
+	cn10k_outb_cptlf_iq_disable(pf);
+
+	/* Set IQ base address and size to 0 */
+	otx2_write64(pf, CN10K_CPT_LF_Q_BASE, 0);
+	otx2_write64(pf, CN10K_CPT_LF_Q_SIZE, 0);
+
+	/* Free CPTLF IQ */
+	cn10k_outb_cptlf_iq_free(pf);
+
+	/* Free and detach CPT LF */
+	cn10k_outb_cptlf_free(pf);
+	ret = cn10k_outb_cptlf_detach(pf);
+	if (ret)
+		netdev_err(pf->netdev, "Failed to detach CPT LF\n");
+
+	cn10k_cpt_device_set_unavailable(pf);
+	return ret;
+}
+
+static void cn10k_cpt_inst_flush(struct otx2_nic *pf, struct cpt_inst_s *inst,
+				 u64 size)
+{
+	struct otx2_lmt_info *lmt_info;
+	u64 val = 0, tar_addr = 0;
+
+	lmt_info = per_cpu_ptr(pf->hw.lmt_info, smp_processor_id());
+	/* FIXME: val[0:10] LMT_ID.
+	 * [12:15] no of LMTST - 1 in the burst.
+	 * [19:63] data size of each LMTST in the burst except first.
+	 */
+	val = (lmt_info->lmt_id & 0x7FF);
+	/* Target address for LMTST flush tells HW how many 128bit
+	 * words are present.
+	 * tar_addr[6:4] size of first LMTST - 1 in units of 128b.
+	 */
+	tar_addr |= pf->ipsec.io_addr | (((size / 16) - 1) & 0x7) << 4;
+	dma_wmb();
+	memcpy((u64 *)lmt_info->lmt_addr, inst, size);
+	cn10k_lmt_flush(val, tar_addr);
+}
+
+static int cn10k_wait_for_cpt_respose(struct otx2_nic *pf,
+				      struct cpt_res_s *res)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(100);
+	u64 *completion_ptr = (u64 *)res;
+
+	do {
+		if (time_after(jiffies, timeout)) {
+			netdev_err(pf->netdev, "CPT response timeout\n");
+			return -EBUSY;
+		}
+	} while ((READ_ONCE(*completion_ptr) & CN10K_CPT_COMP_E_MASK) ==
+		 CN10K_CPT_COMP_E_NOTDONE);
+
+	if (!(res->compcode == CN10K_CPT_COMP_E_GOOD ||
+	      res->compcode == CN10K_CPT_COMP_E_WARN) || res->uc_compcode) {
+		netdev_err(pf->netdev, "compcode=%x doneint=%x\n",
+			   res->compcode, res->doneint);
+		netdev_err(pf->netdev, "uc_compcode=%x uc_info=%llx esn=%llx\n",
+			   res->uc_compcode, (u64)res->uc_info, res->esn);
+	}
+	return 0;
+}
+
+static int cn10k_outb_write_sa(struct otx2_nic *pf, struct qmem *sa_info)
+{
+	dma_addr_t res_iova, dptr_iova, sa_iova;
+	struct cn10k_tx_sa_s *sa_dptr;
+	struct cpt_inst_s inst = {};
+	struct cpt_res_s *res;
+	u32 sa_size, off;
+	u64 *sptr, *dptr;
+	u64 reg_val;
+	int ret;
+
+	sa_iova = sa_info->iova;
+	if (!sa_iova)
+		return -EINVAL;
+
+	res = dma_alloc_coherent(pf->dev, sizeof(struct cpt_res_s),
+				 &res_iova, GFP_ATOMIC);
+	if (!res)
+		return -ENOMEM;
+
+	sa_size = sizeof(struct cn10k_tx_sa_s);
+	sa_dptr = dma_alloc_coherent(pf->dev, sa_size, &dptr_iova, GFP_ATOMIC);
+	if (!sa_dptr) {
+		dma_free_coherent(pf->dev, sizeof(struct cpt_res_s), res,
+				  res_iova);
+		return -ENOMEM;
+	}
+
+	sptr = (__force u64 *)sa_info->base;
+	dptr =  (__force u64 *)sa_dptr;
+	for (off = 0; off < (sa_size / 8); off++)
+		*(dptr + off) = (__force u64)cpu_to_be64(*(sptr + off));
+
+	res->compcode = CN10K_CPT_COMP_E_NOTDONE;
+	inst.res_addr = res_iova;
+	inst.dptr = (u64)dptr_iova;
+	inst.param2 = sa_size >> 3;
+	inst.dlen = sa_size;
+	inst.opcode_major = CN10K_IPSEC_MAJOR_OP_WRITE_SA;
+	inst.opcode_minor = CN10K_IPSEC_MINOR_OP_WRITE_SA;
+	inst.cptr = sa_iova;
+	inst.ctx_val = 1;
+	inst.egrp = CN10K_DEF_CPT_IPSEC_EGRP;
+
+	/* Check if CPT-LF available */
+	if (!cn10k_cpt_device_set_inuse(pf)) {
+		ret = -ENODEV;
+		goto free_mem;
+	}
+
+	cn10k_cpt_inst_flush(pf, &inst, sizeof(struct cpt_inst_s));
+	dma_wmb();
+	ret = cn10k_wait_for_cpt_respose(pf, res);
+	if (ret)
+		goto set_available;
+
+	/* Trigger CTX flush to write dirty data back to DRAM */
+	reg_val = FIELD_PREP(CPT_LF_CTX_FLUSH, sa_iova >> 7);
+	otx2_write64(pf, CN10K_CPT_LF_CTX_FLUSH, reg_val);
+
+set_available:
+	cn10k_cpt_device_set_available(pf);
+free_mem:
+	dma_free_coherent(pf->dev, sa_size, sa_dptr, dptr_iova);
+	dma_free_coherent(pf->dev, sizeof(struct cpt_res_s), res, res_iova);
+	return ret;
+}
+
+static int cn10k_ipsec_get_hw_ctx_offset(void)
+{
+	/* Offset on Hardware-context offset in word */
+	return (offsetof(struct cn10k_tx_sa_s, hw_ctx) / sizeof(u64)) & 0x7F;
+}
+
+static int cn10k_ipsec_get_ctx_push_size(void)
+{
+	/* Context push size is round up and in multiple of 8 Byte */
+	return (roundup(offsetof(struct cn10k_tx_sa_s, hw_ctx), 8) / 8) & 0x7F;
+}
+
+static int cn10k_ipsec_get_aes_key_len(int key_len)
+{
+	/* key_len is aes key length in bytes */
+	switch (key_len) {
+	case 16:
+		return CN10K_IPSEC_SA_AES_KEY_LEN_128;
+	case 24:
+		return CN10K_IPSEC_SA_AES_KEY_LEN_192;
+	default:
+		return CN10K_IPSEC_SA_AES_KEY_LEN_256;
+	}
+}
+
+static void cn10k_outb_prepare_sa(struct xfrm_state *x,
+				  struct cn10k_tx_sa_s *sa_entry)
+{
+	int key_len = (x->aead->alg_key_len + 7) / 8;
+	struct net_device *netdev = x->xso.dev;
+	u8 *key = x->aead->alg_key;
+	struct otx2_nic *pf;
+	u32 *tmp_salt;
+	u64 *tmp_key;
+	int idx;
+
+	memset(sa_entry, 0, sizeof(struct cn10k_tx_sa_s));
+
+	/* context size, 128 Byte aligned up */
+	pf = netdev_priv(netdev);
+	sa_entry->ctx_size = (pf->ipsec.sa_size / OTX2_ALIGN)  & 0xF;
+	sa_entry->hw_ctx_off = cn10k_ipsec_get_hw_ctx_offset();
+	sa_entry->ctx_push_size = cn10k_ipsec_get_ctx_push_size();
+
+	/* Ucode to skip two words of CPT_CTX_HW_S */
+	sa_entry->ctx_hdr_size = 1;
+
+	/* Allow Atomic operation (AOP) */
+	sa_entry->aop_valid = 1;
+
+	/* Outbound, ESP TRANSPORT/TUNNEL Mode, AES-GCM with */
+	sa_entry->sa_dir = CN10K_IPSEC_SA_DIR_OUTB;
+	sa_entry->ipsec_protocol = CN10K_IPSEC_SA_IPSEC_PROTO_ESP;
+	sa_entry->enc_type = CN10K_IPSEC_SA_ENCAP_TYPE_AES_GCM;
+	sa_entry->iv_src = CN10K_IPSEC_SA_IV_SRC_PACKET;
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		sa_entry->ipsec_mode = CN10K_IPSEC_SA_IPSEC_MODE_TUNNEL;
+	else
+		sa_entry->ipsec_mode = CN10K_IPSEC_SA_IPSEC_MODE_TRANSPORT;
+
+	/* Last 4 bytes are salt */
+	key_len -= 4;
+	sa_entry->aes_key_len = cn10k_ipsec_get_aes_key_len(key_len);
+	memcpy(sa_entry->cipher_key, key, key_len);
+	tmp_key = (u64 *)sa_entry->cipher_key;
+
+	for (idx = 0; idx < key_len / 8; idx++)
+		tmp_key[idx] = (__force u64)cpu_to_be64(tmp_key[idx]);
+
+	memcpy(&sa_entry->iv_gcm_salt, key + key_len, 4);
+	tmp_salt = (u32 *)&sa_entry->iv_gcm_salt;
+	*tmp_salt = (__force u32)cpu_to_be32(*tmp_salt);
+
+	/* Write SA context data to memory before enabling */
+	wmb();
+
+	/* Enable SA */
+	sa_entry->sa_valid = 1;
+}
+
+static int cn10k_ipsec_validate_state(struct xfrm_state *x,
+				      struct netlink_ext_ack *extack)
+{
+	if (x->props.aalgo != SADB_AALG_NONE) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload authenticated xfrm states");
+		return -EINVAL;
+	}
+	if (x->props.ealgo != SADB_X_EALG_AES_GCM_ICV16) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only AES-GCM-ICV16 xfrm state may be offloaded");
+		return -EINVAL;
+	}
+	if (x->props.calgo != SADB_X_CALG_NONE) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload compressed xfrm states");
+		return -EINVAL;
+	}
+	if (x->props.flags & XFRM_STATE_ESN) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot offload ESN xfrm states");
+		return -EINVAL;
+	}
+	if (x->props.family != AF_INET && x->props.family != AF_INET6) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only IPv4/v6 xfrm states may be offloaded");
+		return -EINVAL;
+	}
+	if (x->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload other than crypto-mode");
+		return -EINVAL;
+	}
+	if (x->props.mode != XFRM_MODE_TRANSPORT &&
+	    x->props.mode != XFRM_MODE_TUNNEL) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only tunnel/transport xfrm states may be offloaded");
+		return -EINVAL;
+	}
+	if (x->id.proto != IPPROTO_ESP) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only ESP xfrm state may be offloaded");
+		return -EINVAL;
+	}
+	if (x->encap) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Encapsulated xfrm state may not be offloaded");
+		return -EINVAL;
+	}
+	if (!x->aead) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload xfrm states without aead");
+		return -EINVAL;
+	}
+
+	if (x->aead->alg_icv_len != 128) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload xfrm states with AEAD ICV length other than 128bit");
+		return -EINVAL;
+	}
+	if (x->aead->alg_key_len != 128 + 32 &&
+	    x->aead->alg_key_len != 192 + 32 &&
+	    x->aead->alg_key_len != 256 + 32) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload xfrm states with AEAD key length other than 128/192/256bit");
+		return -EINVAL;
+	}
+	if (x->tfcpad) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload xfrm states with tfc padding");
+		return -EINVAL;
+	}
+	if (!x->geniv) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload xfrm states without geniv");
+		return -EINVAL;
+	}
+	if (strcmp(x->geniv, "seqiv")) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot offload xfrm states with geniv other than seqiv");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int cn10k_ipsec_inb_add_state(struct xfrm_state *x,
+				     struct netlink_ext_ack *extack)
+{
+	NL_SET_ERR_MSG_MOD(extack, "xfrm inbound offload not supported");
+	return -EOPNOTSUPP;
+}
+
+static int cn10k_ipsec_outb_add_state(struct net_device *dev,
+				      struct xfrm_state *x,
+				      struct netlink_ext_ack *extack)
+{
+	struct cn10k_tx_sa_s *sa_entry;
+	struct qmem *sa_info;
+	struct otx2_nic *pf;
+	int err;
+
+	err = cn10k_ipsec_validate_state(x, extack);
+	if (err)
+		return err;
+
+	pf = netdev_priv(dev);
+
+	err = qmem_alloc(pf->dev, &sa_info, pf->ipsec.sa_size, OTX2_ALIGN);
+	if (err)
+		return err;
+
+	sa_entry = (struct cn10k_tx_sa_s *)sa_info->base;
+	cn10k_outb_prepare_sa(x, sa_entry);
+
+	err = cn10k_outb_write_sa(pf, sa_info);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Error writing outbound SA");
+		qmem_free(pf->dev, sa_info);
+		return err;
+	}
+
+	x->xso.offload_handle = (unsigned long)sa_info;
+	/* Enable static branch when first SA setup */
+	if (!pf->ipsec.outb_sa_count)
+		static_branch_enable(&cn10k_ipsec_sa_enabled);
+	pf->ipsec.outb_sa_count++;
+	return 0;
+}
+
+static int cn10k_ipsec_add_state(struct net_device *dev,
+				 struct xfrm_state *x,
+				 struct netlink_ext_ack *extack)
+{
+	if (x->xso.dir == XFRM_DEV_OFFLOAD_IN)
+		return cn10k_ipsec_inb_add_state(x, extack);
+	else
+		return cn10k_ipsec_outb_add_state(dev, x, extack);
+}
+
+static void cn10k_ipsec_del_state(struct net_device *dev, struct xfrm_state *x)
+{
+	struct cn10k_tx_sa_s *sa_entry;
+	struct qmem *sa_info;
+	struct otx2_nic *pf;
+	int err;
+
+	if (x->xso.dir == XFRM_DEV_OFFLOAD_IN)
+		return;
+
+	pf = netdev_priv(dev);
+
+	sa_info = (struct qmem *)x->xso.offload_handle;
+	sa_entry = (struct cn10k_tx_sa_s *)sa_info->base;
+	memset(sa_entry, 0, sizeof(struct cn10k_tx_sa_s));
+	/* Disable SA in CPT h/w */
+	sa_entry->ctx_push_size = cn10k_ipsec_get_ctx_push_size();
+	sa_entry->ctx_size = (pf->ipsec.sa_size / OTX2_ALIGN)  & 0xF;
+	sa_entry->aop_valid = 1;
+
+	err = cn10k_outb_write_sa(pf, sa_info);
+	if (err)
+		netdev_err(dev, "Error (%d) deleting SA\n", err);
+
+	x->xso.offload_handle = 0;
+	qmem_free(pf->dev, sa_info);
+
+	/* If no more SA's then update netdev feature for potential change
+	 * in NETIF_F_HW_ESP.
+	 */
+	if (!--pf->ipsec.outb_sa_count)
+		queue_work(pf->ipsec.sa_workq, &pf->ipsec.sa_work);
+}
+
+static const struct xfrmdev_ops cn10k_ipsec_xfrmdev_ops = {
+	.xdo_dev_state_add	= cn10k_ipsec_add_state,
+	.xdo_dev_state_delete	= cn10k_ipsec_del_state,
+};
+
+static void cn10k_ipsec_sa_wq_handler(struct work_struct *work)
+{
+	struct cn10k_ipsec *ipsec = container_of(work, struct cn10k_ipsec,
+						 sa_work);
+	struct otx2_nic *pf = container_of(ipsec, struct otx2_nic, ipsec);
+
+	/* Disable static branch when no more SA enabled */
+	static_branch_disable(&cn10k_ipsec_sa_enabled);
+	rtnl_lock();
+	netdev_update_features(pf->netdev);
+	rtnl_unlock();
+}
+
+int cn10k_ipsec_ethtool_init(struct net_device *netdev, bool enable)
+{
+	struct otx2_nic *pf = netdev_priv(netdev);
+
+	/* IPsec offload supported on cn10k */
+	if (!is_dev_support_ipsec_offload(pf->pdev))
+		return -EOPNOTSUPP;
+
+	/* Initialize CPT for outbound ipsec offload */
+	if (enable)
+		return cn10k_outb_cpt_init(netdev);
+
+	/* Don't do CPT cleanup if SA installed */
+	if (pf->ipsec.outb_sa_count) {
+		netdev_err(pf->netdev, "SA installed on this device\n");
+		return -EBUSY;
+	}
+
+	return cn10k_outb_cpt_clean(pf);
+}
+
+int cn10k_ipsec_init(struct net_device *netdev)
+{
+	struct otx2_nic *pf = netdev_priv(netdev);
+	u32 sa_size;
+
+	if (!is_dev_support_ipsec_offload(pf->pdev))
+		return 0;
+
+	/* Each SA entry size is 128 Byte round up in size */
+	sa_size = sizeof(struct cn10k_tx_sa_s) % OTX2_ALIGN ?
+			 (sizeof(struct cn10k_tx_sa_s) / OTX2_ALIGN + 1) *
+			 OTX2_ALIGN : sizeof(struct cn10k_tx_sa_s);
+	pf->ipsec.sa_size = sa_size;
+
+	INIT_WORK(&pf->ipsec.sa_work, cn10k_ipsec_sa_wq_handler);
+	pf->ipsec.sa_workq = alloc_workqueue("cn10k_ipsec_sa_workq", 0, 0);
+	if (!pf->ipsec.sa_workq) {
+		netdev_err(pf->netdev, "SA alloc workqueue failed\n");
+		return -ENOMEM;
+	}
+
+	/* Set xfrm device ops */
+	netdev->xfrmdev_ops = &cn10k_ipsec_xfrmdev_ops;
+	netdev->hw_features |= NETIF_F_HW_ESP;
+	netdev->hw_enc_features |= NETIF_F_HW_ESP;
+
+	cn10k_cpt_device_set_unavailable(pf);
+	return 0;
+}
+EXPORT_SYMBOL(cn10k_ipsec_init);
+
+void cn10k_ipsec_clean(struct otx2_nic *pf)
+{
+	if (!is_dev_support_ipsec_offload(pf->pdev))
+		return;
+
+	if (!(pf->flags & OTX2_FLAG_IPSEC_OFFLOAD_ENABLED))
+		return;
+
+	if (pf->ipsec.sa_workq) {
+		destroy_workqueue(pf->ipsec.sa_workq);
+		pf->ipsec.sa_workq = NULL;
+	}
+
+	cn10k_outb_cpt_clean(pf);
+}
+EXPORT_SYMBOL(cn10k_ipsec_clean);
+
+static u16 cn10k_ipsec_get_ip_data_len(struct xfrm_state *x,
+				       struct sk_buff *skb)
+{
+	struct ipv6hdr *ipv6h;
+	struct iphdr *iph;
+	u8 *src;
+
+	src = (u8 *)skb->data + ETH_HLEN;
+
+	if (x->props.family == AF_INET) {
+		iph = (struct iphdr *)src;
+		return ntohs(iph->tot_len);
+	}
+
+	ipv6h = (struct ipv6hdr *)src;
+	return ntohs(ipv6h->payload_len) + sizeof(struct ipv6hdr);
+}
+
+/* Prepare CPT and NIX SQE scatter/gather subdescriptor structure.
+ * SG of NIX and CPT are same in size.
+ * Layout of a NIX SQE and CPT SG entry:
+ *      -----------------------------
+ *     |     CPT Scatter Gather      |
+ *     |       (SQE SIZE)            |
+ *     |                             |
+ *      -----------------------------
+ *     |       NIX SQE               |
+ *     |       (SQE SIZE)            |
+ *     |                             |
+ *      -----------------------------
+ */
+bool otx2_sqe_add_sg_ipsec(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
+			   struct sk_buff *skb, int num_segs, int *offset)
+{
+	struct cpt_sg_s *cpt_sg = NULL;
+	struct nix_sqe_sg_s *sg = NULL;
+	u64 dma_addr, *iova = NULL;
+	u64 *cpt_iova = NULL;
+	u16 *sg_lens = NULL;
+	int seg, len;
+
+	sq->sg[sq->head].num_segs = 0;
+	cpt_sg = (struct cpt_sg_s *)(sq->sqe_base - sq->sqe_size);
+
+	for (seg = 0; seg < num_segs; seg++) {
+		if ((seg % MAX_SEGS_PER_SG) == 0) {
+			sg = (struct nix_sqe_sg_s *)(sq->sqe_base + *offset);
+			sg->ld_type = NIX_SEND_LDTYPE_LDD;
+			sg->subdc = NIX_SUBDC_SG;
+			sg->segs = 0;
+			sg_lens = (void *)sg;
+			iova = (void *)sg + sizeof(*sg);
+			/* Next subdc always starts at a 16byte boundary.
+			 * So if sg->segs is whether 2 or 3, offset += 16bytes.
+			 */
+			if ((num_segs - seg) >= (MAX_SEGS_PER_SG - 1))
+				*offset += sizeof(*sg) + (3 * sizeof(u64));
+			else
+				*offset += sizeof(*sg) + sizeof(u64);
+
+			cpt_sg += (seg / MAX_SEGS_PER_SG) * 4;
+			cpt_iova = (void *)cpt_sg + sizeof(*cpt_sg);
+		}
+		dma_addr = otx2_dma_map_skb_frag(pfvf, skb, seg, &len);
+		if (dma_mapping_error(pfvf->dev, dma_addr))
+			return false;
+
+		sg_lens[seg % MAX_SEGS_PER_SG] = len;
+		sg->segs++;
+		*iova++ = dma_addr;
+		*cpt_iova++ = dma_addr;
+
+		/* Save DMA mapping info for later unmapping */
+		sq->sg[sq->head].dma_addr[seg] = dma_addr;
+		sq->sg[sq->head].size[seg] = len;
+		sq->sg[sq->head].num_segs++;
+
+		*cpt_sg = *(struct cpt_sg_s *)sg;
+		cpt_sg->rsvd_63_50 = 0;
+	}
+
+	sq->sg[sq->head].skb = (u64)skb;
+	return true;
+}
+
+static u16 cn10k_ipsec_get_param1(u8 iv_offset)
+{
+	u16 param1_val;
+
+	/* Set Crypto mode, disable L3/L4 checksum */
+	param1_val = CN10K_IPSEC_INST_PARAM1_DIS_L4_CSUM |
+		      CN10K_IPSEC_INST_PARAM1_DIS_L3_CSUM;
+	param1_val |= (u16)iv_offset << CN10K_IPSEC_INST_PARAM1_IV_OFFSET_SHIFT;
+	return param1_val;
+}
+
+bool cn10k_ipsec_transmit(struct otx2_nic *pf, struct netdev_queue *txq,
+			  struct otx2_snd_queue *sq, struct sk_buff *skb,
+			  int num_segs, int size)
+{
+	struct cpt_inst_s inst;
+	struct cpt_res_s *res;
+	struct xfrm_state *x;
+	struct qmem *sa_info;
+	dma_addr_t dptr_iova;
+	struct sec_path *sp;
+	u8 encap_offset;
+	u8 auth_offset;
+	u8 gthr_size;
+	u8 iv_offset;
+	u16 dlen;
+
+	/* Check for IPSEC offload enabled */
+	if (!(pf->flags & OTX2_FLAG_IPSEC_OFFLOAD_ENABLED))
+		goto drop;
+
+	sp = skb_sec_path(skb);
+	if (unlikely(!sp->len))
+		goto drop;
+
+	x = xfrm_input_state(skb);
+	if (unlikely(!x))
+		goto drop;
+
+	if (x->props.mode != XFRM_MODE_TRANSPORT &&
+	    x->props.mode != XFRM_MODE_TUNNEL)
+		goto drop;
+
+	dlen = cn10k_ipsec_get_ip_data_len(x, skb);
+	if (dlen == 0 && netif_msg_tx_err(pf)) {
+		netdev_err(pf->netdev, "Invalid IP header, ip-length zero\n");
+		goto drop;
+	}
+
+	/* Check for valid SA context */
+	sa_info = (struct qmem *)x->xso.offload_handle;
+	if (!sa_info)
+		goto drop;
+
+	memset(&inst, 0, sizeof(struct cpt_inst_s));
+
+	/* Get authentication offset */
+	if (x->props.family == AF_INET)
+		auth_offset = sizeof(struct iphdr);
+	else
+		auth_offset = sizeof(struct ipv6hdr);
+
+	/* IV offset is after ESP header */
+	iv_offset = auth_offset + sizeof(struct ip_esp_hdr);
+	/* Encap will start after IV */
+	encap_offset = iv_offset + GCM_RFC4106_IV_SIZE;
+
+	/* CPT Instruction word-1 */
+	res = (struct cpt_res_s *)(sq->cpt_resp->base + (64 * sq->head));
+	res->compcode = 0;
+	inst.res_addr = sq->cpt_resp->iova + (64 * sq->head);
+
+	/* CPT Instruction word-2 */
+	inst.rvu_pf_func = pf->pcifunc;
+
+	/* CPT Instruction word-3:
+	 * Set QORD to force CPT_RES_S write completion
+	 */
+	inst.qord = 1;
+
+	/* CPT Instruction word-4 */
+	/* inst.dlen should not include ICV length */
+	inst.dlen = dlen + ETH_HLEN - (x->aead->alg_icv_len / 8);
+	inst.opcode_major = CN10K_IPSEC_MAJOR_OP_OUTB_IPSEC;
+	inst.param1 = cn10k_ipsec_get_param1(iv_offset);
+
+	inst.param2 = encap_offset <<
+		       CN10K_IPSEC_INST_PARAM2_ENC_DATA_OFFSET_SHIFT;
+	inst.param2 |= (u16)auth_offset <<
+			CN10K_IPSEC_INST_PARAM2_AUTH_DATA_OFFSET_SHIFT;
+
+	/* CPT Instruction word-5 */
+	gthr_size = num_segs / MAX_SEGS_PER_SG;
+	gthr_size = (num_segs % MAX_SEGS_PER_SG) ? gthr_size + 1 : gthr_size;
+
+	gthr_size &= 0xF;
+	dptr_iova = (sq->sqe_ring->iova + (sq->head * (sq->sqe_size * 2)));
+	inst.dptr = dptr_iova | ((u64)gthr_size << 60);
+
+	/* CPT Instruction word-6 */
+	inst.rptr = inst.dptr;
+
+	/* CPT Instruction word-7 */
+	inst.cptr = sa_info->iova;
+	inst.ctx_val = 1;
+	inst.egrp = CN10K_DEF_CPT_IPSEC_EGRP;
+
+	/* CPT Instruction word-0 */
+	inst.nixtxl = (size / 16) - 1;
+	inst.dat_offset = ETH_HLEN;
+	inst.nixtx_offset = sq->sqe_size;
+
+	netdev_tx_sent_queue(txq, skb->len);
+
+	/* Finally Flush the CPT instruction */
+	sq->head++;
+	sq->head &= (sq->sqe_cnt - 1);
+	cn10k_cpt_inst_flush(pf, &inst, sizeof(struct cpt_inst_s));
+	return true;
+drop:
+	dev_kfree_skb_any(skb);
+	return false;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h
new file mode 100644
index 000000000000..9965df0faa3e
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h
@@ -0,0 +1,265 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell IPSEC offload driver
+ *
+ * Copyright (C) 2024 Marvell.
+ */
+
+#ifndef CN10K_IPSEC_H
+#define CN10K_IPSEC_H
+
+#include <linux/types.h>
+
+DECLARE_STATIC_KEY_FALSE(cn10k_ipsec_sa_enabled);
+
+/* CPT instruction size in bytes */
+#define CN10K_CPT_INST_SIZE	64
+
+/* CPT instruction (CPT_INST_S) queue length */
+#define CN10K_CPT_INST_QLEN	8200
+
+/* CPT instruction queue size passed to HW is in units of
+ * 40*CPT_INST_S messages.
+ */
+#define CN10K_CPT_SIZE_DIV40 (CN10K_CPT_INST_QLEN / 40)
+
+/* CPT needs 320 free entries */
+#define CN10K_CPT_INST_QLEN_EXTRA_BYTES	(320 * CN10K_CPT_INST_SIZE)
+#define CN10K_CPT_EXTRA_SIZE_DIV40	(320 / 40)
+
+/* CPT instruction queue length in bytes */
+#define CN10K_CPT_INST_QLEN_BYTES					\
+		((CN10K_CPT_SIZE_DIV40 * 40 * CN10K_CPT_INST_SIZE) +	\
+		CN10K_CPT_INST_QLEN_EXTRA_BYTES)
+
+/* CPT instruction group queue length in bytes */
+#define CN10K_CPT_INST_GRP_QLEN_BYTES					\
+		((CN10K_CPT_SIZE_DIV40 + CN10K_CPT_EXTRA_SIZE_DIV40) * 16)
+
+/* CPT FC length in bytes */
+#define CN10K_CPT_Q_FC_LEN 128
+
+/* Default CPT engine group for ipsec offload */
+#define CN10K_DEF_CPT_IPSEC_EGRP 1
+
+/* CN10K CPT LF registers */
+#define CPT_LFBASE			(BLKTYPE_CPT << RVU_FUNC_BLKADDR_SHIFT)
+#define CN10K_CPT_LF_CTL		(CPT_LFBASE | 0x10)
+#define CN10K_CPT_LF_INPROG		(CPT_LFBASE | 0x40)
+#define CN10K_CPT_LF_Q_BASE		(CPT_LFBASE | 0xf0)
+#define CN10K_CPT_LF_Q_SIZE		(CPT_LFBASE | 0x100)
+#define CN10K_CPT_LF_Q_INST_PTR		(CPT_LFBASE | 0x110)
+#define CN10K_CPT_LF_Q_GRP_PTR		(CPT_LFBASE | 0x120)
+#define CN10K_CPT_LF_NQX(a)		(CPT_LFBASE | 0x400 | (a) << 3)
+#define CN10K_CPT_LF_CTX_FLUSH		(CPT_LFBASE | 0x510)
+
+/* IPSEC Instruction opcodes */
+#define CN10K_IPSEC_MAJOR_OP_WRITE_SA 0x01UL
+#define CN10K_IPSEC_MINOR_OP_WRITE_SA 0x09UL
+#define CN10K_IPSEC_MAJOR_OP_OUTB_IPSEC 0x2AUL
+
+enum cn10k_cpt_comp_e {
+	CN10K_CPT_COMP_E_NOTDONE = 0x00,
+	CN10K_CPT_COMP_E_GOOD = 0x01,
+	CN10K_CPT_COMP_E_FAULT = 0x02,
+	CN10K_CPT_COMP_E_HWERR = 0x04,
+	CN10K_CPT_COMP_E_INSTERR = 0x05,
+	CN10K_CPT_COMP_E_WARN = 0x06,
+	CN10K_CPT_COMP_E_MASK = 0x3F
+};
+
+struct cn10k_cpt_inst_queue {
+	u8 *vaddr;
+	u8 *real_vaddr;
+	dma_addr_t dma_addr;
+	dma_addr_t real_dma_addr;
+	u32 size;
+};
+
+enum cn10k_cpt_hw_state_e {
+	CN10K_CPT_HW_UNAVAILABLE,
+	CN10K_CPT_HW_AVAILABLE,
+	CN10K_CPT_HW_IN_USE
+};
+
+struct cn10k_ipsec {
+	/* Outbound CPT */
+	u64 io_addr;
+	atomic_t cpt_state;
+	struct cn10k_cpt_inst_queue iq;
+
+	/* SA info */
+	u32 sa_size;
+	u32 outb_sa_count;
+	struct work_struct sa_work;
+	struct workqueue_struct *sa_workq;
+};
+
+/* CN10K IPSEC Security Association (SA) */
+/* SA direction */
+#define CN10K_IPSEC_SA_DIR_INB			0
+#define CN10K_IPSEC_SA_DIR_OUTB			1
+/* SA protocol */
+#define CN10K_IPSEC_SA_IPSEC_PROTO_AH		0
+#define CN10K_IPSEC_SA_IPSEC_PROTO_ESP		1
+/* SA Encryption Type */
+#define CN10K_IPSEC_SA_ENCAP_TYPE_AES_GCM	5
+/* SA IPSEC mode Transport/Tunnel */
+#define CN10K_IPSEC_SA_IPSEC_MODE_TRANSPORT	0
+#define CN10K_IPSEC_SA_IPSEC_MODE_TUNNEL	1
+/* SA AES Key Length */
+#define CN10K_IPSEC_SA_AES_KEY_LEN_128		1
+#define CN10K_IPSEC_SA_AES_KEY_LEN_192		2
+#define CN10K_IPSEC_SA_AES_KEY_LEN_256		3
+/* IV Source */
+#define CN10K_IPSEC_SA_IV_SRC_COUNTER		0
+#define CN10K_IPSEC_SA_IV_SRC_PACKET		3
+
+struct cn10k_tx_sa_s {
+	u64 esn_en		: 1; /* W0 */
+	u64 rsvd_w0_1_8		: 8;
+	u64 hw_ctx_off		: 7;
+	u64 ctx_id		: 16;
+	u64 rsvd_w0_32_47	: 16;
+	u64 ctx_push_size	: 7;
+	u64 rsvd_w0_55		: 1;
+	u64 ctx_hdr_size	: 2;
+	u64 aop_valid		: 1;
+	u64 rsvd_w0_59		: 1;
+	u64 ctx_size		: 4;
+	u64 w1;			/* W1 */
+	u64 sa_valid		: 1; /* W2 */
+	u64 sa_dir		: 1;
+	u64 rsvd_w2_2_3		: 2;
+	u64 ipsec_mode		: 1;
+	u64 ipsec_protocol	: 1;
+	u64 aes_key_len		: 2;
+	u64 enc_type		: 3;
+	u64 rsvd_w2_11_19	: 9;
+	u64 iv_src		: 2;
+	u64 rsvd_w2_22_31	: 10;
+	u64 rsvd_w2_32_63	: 32;
+	u64 w3;			/* W3 */
+	u8 cipher_key[32];	/* W4 - W7 */
+	u32 rsvd_w8_0_31;	/* W8 : IV */
+	u32 iv_gcm_salt;
+	u64 rsvd_w9_w30[22];	/* W9 - W30 */
+	u64 hw_ctx[6];		/* W31 - W36 */
+};
+
+/* CPT instruction parameter-1 */
+#define CN10K_IPSEC_INST_PARAM1_DIS_L4_CSUM		0x1
+#define CN10K_IPSEC_INST_PARAM1_DIS_L3_CSUM		0x2
+#define CN10K_IPSEC_INST_PARAM1_CRYPTO_MODE		0x20
+#define CN10K_IPSEC_INST_PARAM1_IV_OFFSET_SHIFT		8
+
+/* CPT instruction parameter-2 */
+#define CN10K_IPSEC_INST_PARAM2_ENC_DATA_OFFSET_SHIFT	0
+#define CN10K_IPSEC_INST_PARAM2_AUTH_DATA_OFFSET_SHIFT	8
+
+/* CPT Instruction Structure */
+struct cpt_inst_s {
+	u64 nixtxl		: 3; /* W0 */
+	u64 doneint		: 1;
+	u64 rsvd_w0_4_15	: 12;
+	u64 dat_offset		: 8;
+	u64 ext_param1		: 8;
+	u64 nixtx_offset	: 20;
+	u64 rsvd_w0_52_63	: 12;
+	u64 res_addr;		/* W1 */
+	u64 tag			: 32; /* W2 */
+	u64 tt			: 2;
+	u64 grp			: 10;
+	u64 rsvd_w2_44_47	: 4;
+	u64 rvu_pf_func		: 16;
+	u64 qord		: 1; /* W3 */
+	u64 rsvd_w3_1_2		: 2;
+	u64 wqe_ptr		: 61;
+	u64 dlen		: 16; /* W4 */
+	u64 param2		: 16;
+	u64 param1		: 16;
+	u64 opcode_major	: 8;
+	u64 opcode_minor	: 8;
+	u64 dptr;		/* W5 */
+	u64 rptr;		/* W6 */
+	u64 cptr		: 60; /* W7 */
+	u64 ctx_val		: 1;
+	u64 egrp		: 3;
+};
+
+/* CPT Instruction Result Structure */
+struct cpt_res_s {
+	u64 compcode		: 7; /* W0 */
+	u64 doneint		: 1;
+	u64 uc_compcode		: 8;
+	u64 uc_info		: 48;
+	u64 esn;		/* W1 */
+};
+
+/* CPT SG structure */
+struct cpt_sg_s {
+	u64 seg1_size	: 16;
+	u64 seg2_size	: 16;
+	u64 seg3_size	: 16;
+	u64 segs	: 2;
+	u64 rsvd_63_50	: 14;
+};
+
+/* CPT LF_INPROG Register */
+#define CPT_LF_INPROG_INFLIGHT	GENMASK_ULL(8, 0)
+#define CPT_LF_INPROG_GRB_CNT	GENMASK_ULL(39, 32)
+#define CPT_LF_INPROG_GWB_CNT	GENMASK_ULL(47, 40)
+
+/* CPT LF_Q_GRP_PTR Register */
+#define CPT_LF_Q_GRP_PTR_DQ_PTR	GENMASK_ULL(14, 0)
+#define CPT_LF_Q_GRP_PTR_NQ_PTR	GENMASK_ULL(46, 32)
+
+/* CPT LF_Q_SIZE Register */
+#define CPT_LF_Q_BASE_ADDR GENMASK_ULL(52, 7)
+
+/* CPT LF_Q_SIZE Register */
+#define CPT_LF_Q_SIZE_DIV40 GENMASK_ULL(14, 0)
+
+/* CPT LF CTX Flush Register */
+#define CPT_LF_CTX_FLUSH GENMASK_ULL(45, 0)
+
+#ifdef CONFIG_XFRM_OFFLOAD
+int cn10k_ipsec_init(struct net_device *netdev);
+void cn10k_ipsec_clean(struct otx2_nic *pf);
+int cn10k_ipsec_ethtool_init(struct net_device *netdev, bool enable);
+bool otx2_sqe_add_sg_ipsec(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
+			   struct sk_buff *skb, int num_segs, int *offset);
+bool cn10k_ipsec_transmit(struct otx2_nic *pf, struct netdev_queue *txq,
+			  struct otx2_snd_queue *sq, struct sk_buff *skb,
+			  int num_segs, int size);
+#else
+static inline __maybe_unused int cn10k_ipsec_init(struct net_device *netdev)
+{
+	return 0;
+}
+
+static inline __maybe_unused void cn10k_ipsec_clean(struct otx2_nic *pf)
+{
+}
+
+static inline __maybe_unused
+int cn10k_ipsec_ethtool_init(struct net_device *netdev, bool enable)
+{
+	return 0;
+}
+
+static inline bool __maybe_unused
+otx2_sqe_add_sg_ipsec(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
+		      struct sk_buff *skb, int num_segs, int *offset)
+{
+	return true;
+}
+
+static inline bool __maybe_unused
+cn10k_ipsec_transmit(struct otx2_nic *pf, struct netdev_queue *txq,
+		     struct otx2_snd_queue *sq, struct sk_buff *skb,
+		     int num_segs, int size)
+{
+	return true;
+}
+#endif
+#endif // CN10K_IPSEC_H
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
index 6cc7a78968fc..4c7e0f345cb5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
@@ -133,9 +133,7 @@ static const char *rsrc_name(enum mcs_rsrc_type rsrc_type)
 		return "SA";
 	default:
 		return "Unknown";
-	};
-
-	return "Unknown";
+	}
 }
 
 static int cn10k_mcs_alloc_rsrc(struct otx2_nic *pfvf, enum mcs_direction dir,
@@ -533,7 +531,8 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf,
 	if (sw_tx_sc->encrypt)
 		sectag_tci |= (MCS_TCI_E | MCS_TCI_C);
 
-	policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, secy->netdev->mtu);
+	policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU,
+			    pfvf->netdev->mtu + OTX2_ETH_HLEN);
 	/* Write SecTag excluding AN bits(1..0) */
 	policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_TCI, sectag_tci >> 2);
 	policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_OFFSET, tag_offset);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 523ecb798a7a..6b5c9536d26d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -10,11 +10,19 @@
 #include <net/page_pool/helpers.h>
 #include <net/tso.h>
 #include <linux/bitfield.h>
+#include <linux/dcbnl.h>
+#include <net/xfrm.h>
 
 #include "otx2_reg.h"
 #include "otx2_common.h"
 #include "otx2_struct.h"
 #include "cn10k.h"
+#include "otx2_xsk.h"
+
+static bool otx2_is_pfc_enabled(struct otx2_nic *pfvf)
+{
+	return IS_ENABLED(CONFIG_DCB) && !!pfvf->pfc_en;
+}
 
 static void otx2_nix_rq_op_stats(struct queue_stats *stats,
 				 struct otx2_nic *pfvf, int qidx)
@@ -323,6 +331,10 @@ int otx2_set_rss_table(struct otx2_nic *pfvf, int ctx_id)
 	rss_ctx = rss->rss_ctx[ctx_id];
 	/* Get memory to put this msg */
 	for (idx = 0; idx < rss->rss_size; idx++) {
+		/* Ignore the queue if AF_XDP zero copy is enabled */
+		if (test_bit(rss_ctx->ind_tbl[idx], pfvf->af_xdp_zc_qidx))
+			continue;
+
 		aq = otx2_mbox_alloc_msg_nix_aq_enq(mbox);
 		if (!aq) {
 			/* The shared memory buffer can be full.
@@ -542,10 +554,13 @@ static int otx2_alloc_pool_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 }
 
 static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-			     dma_addr_t *dma)
+			     dma_addr_t *dma, int qidx, int idx)
 {
 	u8 *buf;
 
+	if (pool->xsk_pool)
+		return otx2_xsk_pool_alloc_buf(pfvf, pool, dma, idx);
+
 	if (pool->page_pool)
 		return otx2_alloc_pool_buf(pfvf, pool, dma);
 
@@ -564,12 +579,12 @@ static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 }
 
 int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-		    dma_addr_t *dma)
+		    dma_addr_t *dma, int qidx, int idx)
 {
 	int ret;
 
 	local_bh_disable();
-	ret = __otx2_alloc_rbuf(pfvf, pool, dma);
+	ret = __otx2_alloc_rbuf(pfvf, pool, dma, qidx, idx);
 	local_bh_enable();
 	return ret;
 }
@@ -577,7 +592,8 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq,
 		      dma_addr_t *dma)
 {
-	if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma)))
+	if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma,
+				       cq->cq_idx, cq->pool_ptrs - 1)))
 		return -ENOMEM;
 	return 0;
 }
@@ -877,7 +893,7 @@ void otx2_sqb_flush(struct otx2_nic *pfvf)
 #define RQ_PASS_LVL_AURA (255 - ((95 * 256) / 100)) /* RED when 95% is full */
 #define RQ_DROP_LVL_AURA (255 - ((99 * 256) / 100)) /* Drop when 99% is full */
 
-static int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura)
+int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura)
 {
 	struct otx2_qset *qset = &pfvf->qset;
 	struct nix_aq_enq_req *aq;
@@ -964,6 +980,29 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 	if (err)
 		return err;
 
+	/* Allocate memory for NIX SQE (which includes NIX SG) and CPT SG.
+	 * SG of NIX and CPT are same in size. Allocate memory for CPT SG
+	 * same as NIX SQE for base address alignment.
+	 * Layout of a NIX SQE and CPT SG entry:
+	 *      -----------------------------
+	 *     |     CPT Scatter Gather      |
+	 *     |       (SQE SIZE)            |
+	 *     |                             |
+	 *      -----------------------------
+	 *     |       NIX SQE               |
+	 *     |       (SQE SIZE)            |
+	 *     |                             |
+	 *      -----------------------------
+	 */
+	err = qmem_alloc(pfvf->dev, &sq->sqe_ring, qset->sqe_cnt,
+			 sq->sqe_size * 2);
+	if (err)
+		return err;
+
+	err = qmem_alloc(pfvf->dev, &sq->cpt_resp, qset->sqe_cnt, 64);
+	if (err)
+		return err;
+
 	if (qidx < pfvf->hw.tx_queues) {
 		err = qmem_alloc(pfvf->dev, &sq->tso_hdrs, qset->sqe_cnt,
 				 TSO_HEADER_SIZE);
@@ -998,6 +1037,10 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 
 	sq->stats.bytes = 0;
 	sq->stats.pkts = 0;
+	/* Attach XSK_BUFF_POOL to XDP queue */
+	if (qidx > pfvf->hw.xdp_queues)
+		otx2_attach_xsk_buff(pfvf, sq, (qidx - pfvf->hw.xdp_queues));
+
 
 	chan_offset = qidx % pfvf->hw.tx_chan_cnt;
 	err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, chan_offset, sqb_aura);
@@ -1011,12 +1054,13 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 
 }
 
-static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
+int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 {
 	struct otx2_qset *qset = &pfvf->qset;
 	int err, pool_id, non_xdp_queues;
 	struct nix_aq_enq_req *aq;
 	struct otx2_cq_queue *cq;
+	struct otx2_pool *pool;
 
 	cq = &qset->cq[qidx];
 	cq->cq_idx = qidx;
@@ -1025,8 +1069,20 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 		cq->cq_type = CQ_RX;
 		cq->cint_idx = qidx;
 		cq->cqe_cnt = qset->rqe_cnt;
-		if (pfvf->xdp_prog)
+		if (pfvf->xdp_prog) {
 			xdp_rxq_info_reg(&cq->xdp_rxq, pfvf->netdev, qidx, 0);
+			pool = &qset->pool[qidx];
+			if (pool->xsk_pool) {
+				xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
+							   MEM_TYPE_XSK_BUFF_POOL,
+							   NULL);
+				xsk_pool_set_rxq_info(pool->xsk_pool, &cq->xdp_rxq);
+			} else if (pool->page_pool) {
+				xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
+							   MEM_TYPE_PAGE_POOL,
+							   pool->page_pool);
+			}
+		}
 	} else if (qidx < non_xdp_queues) {
 		cq->cq_type = CQ_TX;
 		cq->cint_idx = qidx - pfvf->hw.rx_queues;
@@ -1245,9 +1301,10 @@ void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool,
 
 	pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
 	page = virt_to_head_page(phys_to_virt(pa));
-
 	if (pool->page_pool) {
 		page_pool_put_full_page(pool->page_pool, page, true);
+	} else if (pool->xsk_pool) {
+		/* Note: No way of identifying xdp_buff */
 	} else {
 		dma_unmap_page_attrs(pfvf->dev, iova, size,
 				     DMA_FROM_DEVICE,
@@ -1262,6 +1319,7 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type)
 	int pool_id, pool_start = 0, pool_end = 0, size = 0;
 	struct otx2_pool *pool;
 	u64 iova;
+	int idx;
 
 	if (type == AURA_NIX_SQ) {
 		pool_start = otx2_get_pool_idx(pfvf, type, 0);
@@ -1276,16 +1334,21 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type)
 
 	/* Free SQB and RQB pointers from the aura pool */
 	for (pool_id = pool_start; pool_id < pool_end; pool_id++) {
-		iova = otx2_aura_allocptr(pfvf, pool_id);
 		pool = &pfvf->qset.pool[pool_id];
+		iova = otx2_aura_allocptr(pfvf, pool_id);
 		while (iova) {
 			if (type == AURA_NIX_RQ)
 				iova -= OTX2_HEAD_ROOM;
-
 			otx2_free_bufs(pfvf, pool, iova, size);
-
 			iova = otx2_aura_allocptr(pfvf, pool_id);
 		}
+
+		for (idx = 0 ; idx < pool->xdp_cnt; idx++) {
+			if (!pool->xdp[idx])
+				continue;
+
+			xsk_buff_free(pool->xdp[idx]);
+		}
 	}
 }
 
@@ -1302,7 +1365,8 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf)
 		qmem_free(pfvf->dev, pool->stack);
 		qmem_free(pfvf->dev, pool->fc_addr);
 		page_pool_destroy(pool->page_pool);
-		pool->page_pool = NULL;
+		devm_kfree(pfvf->dev, pool->xdp);
+		pool->xsk_pool = NULL;
 	}
 	devm_kfree(pfvf->dev, pfvf->qset.pool);
 	pfvf->qset.pool = NULL;
@@ -1389,6 +1453,7 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
 		   int stack_pages, int numptrs, int buf_size, int type)
 {
 	struct page_pool_params pp_params = { 0 };
+	struct xsk_buff_pool *xsk_pool;
 	struct npa_aq_enq_req *aq;
 	struct otx2_pool *pool;
 	int err;
@@ -1432,21 +1497,35 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
 	aq->ctype = NPA_AQ_CTYPE_POOL;
 	aq->op = NPA_AQ_INSTOP_INIT;
 
-	if (type != AURA_NIX_RQ) {
-		pool->page_pool = NULL;
+	if (type != AURA_NIX_RQ)
+		return 0;
+
+	if (!test_bit(pool_id, pfvf->af_xdp_zc_qidx)) {
+		pp_params.order = get_order(buf_size);
+		pp_params.flags = PP_FLAG_DMA_MAP;
+		pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs);
+		pp_params.nid = NUMA_NO_NODE;
+		pp_params.dev = pfvf->dev;
+		pp_params.dma_dir = DMA_FROM_DEVICE;
+		pool->page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(pool->page_pool)) {
+			netdev_err(pfvf->netdev, "Creation of page pool failed\n");
+			return PTR_ERR(pool->page_pool);
+		}
 		return 0;
 	}
 
-	pp_params.order = get_order(buf_size);
-	pp_params.flags = PP_FLAG_DMA_MAP;
-	pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs);
-	pp_params.nid = NUMA_NO_NODE;
-	pp_params.dev = pfvf->dev;
-	pp_params.dma_dir = DMA_FROM_DEVICE;
-	pool->page_pool = page_pool_create(&pp_params);
-	if (IS_ERR(pool->page_pool)) {
-		netdev_err(pfvf->netdev, "Creation of page pool failed\n");
-		return PTR_ERR(pool->page_pool);
+	/* Set XSK pool to support AF_XDP zero-copy */
+	xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, pool_id);
+	if (xsk_pool) {
+		pool->xsk_pool = xsk_pool;
+		pool->xdp_cnt = numptrs;
+		pool->xdp = devm_kcalloc(pfvf->dev,
+					 numptrs, sizeof(struct xdp_buff *), GFP_KERNEL);
+		if (IS_ERR(pool->xdp)) {
+			netdev_err(pfvf->netdev, "Creation of xsk pool failed\n");
+			return PTR_ERR(pool->xdp);
+		}
 	}
 
 	return 0;
@@ -1507,9 +1586,18 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
 		}
 
 		for (ptr = 0; ptr < num_sqbs; ptr++) {
-			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
-			if (err)
+			err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
+			if (err) {
+				if (pool->xsk_pool) {
+					ptr--;
+					while (ptr >= 0) {
+						xsk_buff_free(pool->xdp[ptr]);
+						ptr--;
+					}
+				}
 				goto err_mem;
+			}
+
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
 			sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
 		}
@@ -1559,11 +1647,19 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf)
 	/* Allocate pointers and free them to aura/pool */
 	for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
 		pool = &pfvf->qset.pool[pool_id];
+
 		for (ptr = 0; ptr < num_ptrs; ptr++) {
-			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
-			if (err)
+			err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
+			if (err) {
+				if (pool->xsk_pool) {
+					while (ptr)
+						xsk_buff_free(pool->xdp[--ptr]);
+				}
 				return -ENOMEM;
+			}
+
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
+						   pool->xsk_pool ? bufptr :
 						   bufptr + OTX2_HEAD_ROOM);
 		}
 	}
@@ -1722,18 +1818,43 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable)
 		return -ENOMEM;
 
 	req->chan_base = 0;
-#ifdef CONFIG_DCB
-	req->chan_cnt = pfvf->pfc_en ? IEEE_8021QAZ_MAX_TCS : 1;
-	req->bpid_per_chan = pfvf->pfc_en ? 1 : 0;
-#else
-	req->chan_cnt =  1;
-	req->bpid_per_chan = 0;
-#endif
+	if (otx2_is_pfc_enabled(pfvf)) {
+		req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
+		req->bpid_per_chan = 1;
+	} else {
+		req->chan_cnt = pfvf->hw.rx_chan_cnt;
+		req->bpid_per_chan = 0;
+	}
 
 	return otx2_sync_mbox_msg(&pfvf->mbox);
 }
 EXPORT_SYMBOL(otx2_nix_config_bp);
 
+int otx2_nix_cpt_config_bp(struct otx2_nic *pfvf, bool enable)
+{
+	struct nix_bp_cfg_req *req;
+
+	if (enable)
+		req = otx2_mbox_alloc_msg_nix_cpt_bp_enable(&pfvf->mbox);
+	else
+		req = otx2_mbox_alloc_msg_nix_cpt_bp_disable(&pfvf->mbox);
+
+	if (!req)
+		return -ENOMEM;
+
+	req->chan_base = 0;
+	if (otx2_is_pfc_enabled(pfvf)) {
+		req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
+		req->bpid_per_chan = 1;
+	} else {
+		req->chan_cnt = pfvf->hw.rx_chan_cnt;
+		req->bpid_per_chan = 0;
+	}
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+}
+EXPORT_SYMBOL(otx2_nix_cpt_config_bp);
+
 /* Mbox message handlers */
 void mbox_handler_cgx_stats(struct otx2_nic *pfvf,
 			    struct cgx_stats_rsp *rsp)
@@ -1934,6 +2055,43 @@ int otx2_handle_ntuple_tc_features(struct net_device *netdev, netdev_features_t
 }
 EXPORT_SYMBOL(otx2_handle_ntuple_tc_features);
 
+int otx2_set_hw_capabilities(struct otx2_nic *pfvf)
+{
+	struct mbox *mbox = &pfvf->mbox;
+	struct otx2_hw *hw = &pfvf->hw;
+	struct get_hw_cap_rsp *rsp;
+	struct msg_req *req;
+	int ret = -ENOMEM;
+
+	mutex_lock(&mbox->lock);
+
+	req = otx2_mbox_alloc_msg_get_hw_cap(mbox);
+	if (!req)
+		goto fail;
+
+	ret = otx2_sync_mbox_msg(mbox);
+	if (ret)
+		goto fail;
+
+	rsp = (struct get_hw_cap_rsp *)otx2_mbox_get_rsp(&pfvf->mbox.mbox,
+							 0, &req->hdr);
+	if (IS_ERR(rsp)) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (rsp->hw_caps & HW_CAP_MACSEC)
+		__set_bit(CN10K_HW_MACSEC, &hw->cap_flag);
+
+	mutex_unlock(&mbox->lock);
+
+	return 0;
+fail:
+	dev_err(pfvf->dev, "Cannot get MACSEC capability from AF\n");
+	mutex_unlock(&mbox->lock);
+	return ret;
+}
+
 #define M(_name, _id, _fn_name, _req_type, _rsp_type)			\
 int __weak								\
 otx2_mbox_up_handler_ ## _fn_name(struct otx2_nic *pfvf,		\
@@ -1947,3 +2105,48 @@ EXPORT_SYMBOL(otx2_mbox_up_handler_ ## _fn_name);
 MBOX_UP_CGX_MESSAGES
 MBOX_UP_MCS_MESSAGES
 #undef M
+
+dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf,
+				 struct sk_buff *skb, int seg, int *len)
+{
+	enum dma_data_direction dir = DMA_TO_DEVICE;
+	const skb_frag_t *frag;
+	struct page *page;
+	int offset;
+
+	/* Crypto hardware need write permission for ipsec crypto offload */
+	if (unlikely(xfrm_offload(skb))) {
+		dir = DMA_BIDIRECTIONAL;
+		skb = skb_unshare(skb, GFP_ATOMIC);
+	}
+
+	/* First segment is always skb->data */
+	if (!seg) {
+		page = virt_to_page(skb->data);
+		offset = offset_in_page(skb->data);
+		*len = skb_headlen(skb);
+	} else {
+		frag = &skb_shinfo(skb)->frags[seg - 1];
+		page = skb_frag_page(frag);
+		offset = skb_frag_off(frag);
+		*len = skb_frag_size(frag);
+	}
+	return otx2_dma_map_page(pfvf, page, offset, *len, dir);
+}
+
+void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg)
+{
+	enum dma_data_direction dir = DMA_TO_DEVICE;
+	struct sk_buff *skb = NULL;
+	int seg;
+
+	skb = (struct sk_buff *)sg->skb;
+	if (unlikely(xfrm_offload(skb)))
+		dir = DMA_BIDIRECTIONAL;
+
+	for (seg = 0; seg < sg->num_segs; seg++) {
+		otx2_dma_unmap_page(pfvf, sg->dma_addr[seg],
+				    sg->size[seg], dir);
+	}
+	sg->num_segs = 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 566848663fea..ca0e6ab12ceb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -21,6 +21,7 @@
 #include <linux/time64.h>
 #include <linux/dim.h>
 #include <uapi/linux/if_macsec.h>
+#include <net/page_pool/helpers.h>
 
 #include <mbox.h>
 #include <npc.h>
@@ -30,6 +31,7 @@
 #include <rvu_trace.h>
 #include "qos.h"
 #include "rep.h"
+#include "cn10k_ipsec.h"
 
 /* IPv4 flag more fragment bit */
 #define IPV4_FLAG_MORE				0x20
@@ -40,6 +42,7 @@
 #define PCI_DEVID_OCTEONTX2_RVU_AFVF		0xA0F8
 
 #define PCI_SUBSYS_DEVID_96XX_RVU_PFVF		0xB200
+#define PCI_SUBSYS_DEVID_CN10K_A_RVU_PFVF	0xB900
 #define PCI_SUBSYS_DEVID_CN10K_B_RVU_PFVF	0xBD00
 
 #define PCI_DEVID_OCTEONTX2_SDP_REP		0xA0F7
@@ -55,6 +58,9 @@
 #define NIX_PF_PFC_PRIO_MAX			8
 #endif
 
+/* Number of segments per SG structure */
+#define MAX_SEGS_PER_SG 3
+
 enum arua_mapped_qtypes {
 	AURA_NIX_RQ,
 	AURA_NIX_SQ,
@@ -123,6 +129,12 @@ enum otx2_errcodes_re {
 	ERRCODE_IL4_CSUM = 0x22,
 };
 
+enum otx2_xdp_action {
+	OTX2_XDP_TX	  = BIT(0),
+	OTX2_XDP_REDIRECT = BIT(1),
+	OTX2_AF_XDP_FRAME = BIT(2),
+};
+
 struct otx2_dev_stats {
 	u64 rx_bytes;
 	u64 rx_frames;
@@ -344,6 +356,7 @@ struct otx2_flow_config {
 	struct list_head	flow_list_tc;
 	u8			ucast_flt_cnt;
 	bool			ntuple;
+	u16			ntuple_cnt;
 };
 
 struct dev_hw_ops {
@@ -448,6 +461,7 @@ struct otx2_nic {
 #define OTX2_FLAG_TC_MARK_ENABLED		BIT_ULL(17)
 #define OTX2_FLAG_REP_MODE_ENABLED		 BIT_ULL(18)
 #define OTX2_FLAG_PORT_UP			BIT_ULL(19)
+#define OTX2_FLAG_IPSEC_OFFLOAD_ENABLED		BIT_ULL(20)
 	u64			flags;
 	u64			*cq_op_addr;
 
@@ -499,9 +513,9 @@ struct otx2_nic {
 
 	/* Devlink */
 	struct otx2_devlink	*dl;
-#ifdef CONFIG_DCB
 	/* PFC */
 	u8			pfc_en;
+#ifdef CONFIG_DCB
 	u8			*queue_to_pfc_map;
 	u16			pfc_schq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
 	bool			pfc_alloc_status[NIX_PF_PFC_PRIO_MAX];
@@ -522,6 +536,11 @@ struct otx2_nic {
 	u16			rep_pf_map[RVU_MAX_REP];
 	u16			esw_mode;
 #endif
+
+	/* Inline ipsec */
+	struct cn10k_ipsec	ipsec;
+	/* af_xdp zero-copy */
+	unsigned long		*af_xdp_zc_qidx;
 };
 
 static inline bool is_otx2_lbkvf(struct pci_dev *pdev)
@@ -572,6 +591,15 @@ static inline bool is_dev_cn10kb(struct pci_dev *pdev)
 	return pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_B_RVU_PFVF;
 }
 
+static inline bool is_dev_cn10ka_b0(struct pci_dev *pdev)
+{
+	if (pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_A_RVU_PFVF &&
+	    (pdev->revision & 0xFF) == 0x54)
+		return true;
+
+	return false;
+}
+
 static inline void otx2_setup_dev_hw_settings(struct otx2_nic *pfvf)
 {
 	struct otx2_hw *hw = &pfvf->hw;
@@ -604,9 +632,6 @@ static inline void otx2_setup_dev_hw_settings(struct otx2_nic *pfvf)
 		__set_bit(CN10K_PTP_ONESTEP, &hw->cap_flag);
 		__set_bit(QOS_CIR_PIR_SUPPORT, &hw->cap_flag);
 	}
-
-	if (is_dev_cn10kb(pfvf->pdev))
-		__set_bit(CN10K_HW_MACSEC, &hw->cap_flag);
 }
 
 /* Register read/write APIs */
@@ -621,6 +646,9 @@ static inline void __iomem *otx2_get_regaddr(struct otx2_nic *nic, u64 offset)
 	case BLKTYPE_NPA:
 		blkaddr = BLKADDR_NPA;
 		break;
+	case BLKTYPE_CPT:
+		blkaddr = BLKADDR_CPT0;
+		break;
 	default:
 		blkaddr = BLKADDR_RVUM;
 		break;
@@ -841,6 +869,7 @@ static struct _req_type __maybe_unused					\
 *otx2_mbox_alloc_msg_ ## _fn_name(struct mbox *mbox)                    \
 {									\
 	struct _req_type *req;						\
+	u16 pcifunc = mbox->pfvf->pcifunc;				\
 									\
 	req = (struct _req_type *)otx2_mbox_alloc_msg_rsp(		\
 		&mbox->mbox, 0, sizeof(struct _req_type),		\
@@ -849,7 +878,8 @@ static struct _req_type __maybe_unused					\
 		return NULL;						\
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;				\
 	req->hdr.id = _id;						\
-	trace_otx2_msg_alloc(mbox->mbox.pdev, _id, sizeof(*req));	\
+	req->hdr.pcifunc = pcifunc;					\
+	trace_otx2_msg_alloc(mbox->mbox.pdev, _id, sizeof(*req), pcifunc); \
 	return req;							\
 }
 
@@ -981,10 +1011,11 @@ void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq);
 void otx2_free_pending_sqe(struct otx2_nic *pfvf);
 void otx2_sqb_flush(struct otx2_nic *pfvf);
 int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-		    dma_addr_t *dma);
+		    dma_addr_t *dma, int qidx, int idx);
 int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable);
 void otx2_ctx_disable(struct mbox *mbox, int type, bool npa);
 int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable);
+int otx2_nix_cpt_config_bp(struct otx2_nic *pfvf, bool enable);
 void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int qidx);
 void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq);
 int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura);
@@ -1010,6 +1041,9 @@ void otx2_pfaf_mbox_destroy(struct otx2_nic *pf);
 void otx2_disable_mbox_intr(struct otx2_nic *pf);
 void otx2_disable_napi(struct otx2_nic *pf);
 irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq);
+int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura);
+int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx);
+int otx2_set_hw_capabilities(struct otx2_nic *pfvf);
 
 /* RSS configuration APIs*/
 int otx2_rss_init(struct otx2_nic *pfvf);
@@ -1072,7 +1106,10 @@ int otx2_del_macfilter(struct net_device *netdev, const u8 *mac);
 int otx2_add_macfilter(struct net_device *netdev, const u8 *mac);
 int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable);
 int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf);
-bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx);
+bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
+			    u64 iova, int len, u16 qidx, u16 flags);
+void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, struct xdp_frame *xdpf,
+			 u64 dma_addr, int len, int *offset, u16 flags);
 u16 otx2_get_max_mtu(struct otx2_nic *pfvf);
 int otx2_handle_ntuple_tc_features(struct net_device *netdev,
 				   netdev_features_t features);
@@ -1149,4 +1186,9 @@ static inline int mcam_entry_cmp(const void *a, const void *b)
 {
 	return *(u16 *)a - *(u16 *)b;
 }
+
+dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf,
+				 struct sk_buff *skb, int seg, int *len);
+void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg);
+int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx);
 #endif /* OTX2_COMMON_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
index 294fba58b670..f110dfa42360 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
@@ -435,6 +435,9 @@ process_pfc:
 		return err;
 	}
 
+	/* Default disable backpressure on NIX-CPT */
+	otx2_nix_cpt_config_bp(pfvf, false);
+
 	/* Request Per channel Bpids */
 	if (pfc->pfc_en)
 		otx2_nix_config_bp(pfvf, true);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 33ec9a7f7c03..e13ae5484c19 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -41,6 +41,7 @@ static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
 	if (!pfvf->flow_cfg)
 		return 0;
 
+	pfvf->flow_cfg->ntuple_cnt = ctx->val.vu16;
 	otx2_alloc_mcam_entries(pfvf, ctx->val.vu16);
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 2d53dc77ef1e..45b8c9230184 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -315,7 +315,7 @@ static void otx2_get_pauseparam(struct net_device *netdev,
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 	struct cgx_pause_frm_cfg *req, *rsp;
 
-	if (is_otx2_lbkvf(pfvf->pdev))
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return;
 
 	mutex_lock(&pfvf->mbox.lock);
@@ -347,7 +347,7 @@ static int otx2_set_pauseparam(struct net_device *netdev,
 	if (pause->autoneg)
 		return -EOPNOTSUPP;
 
-	if (is_otx2_lbkvf(pfvf->pdev))
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return -EOPNOTSUPP;
 
 	if (pause->rx_pause)
@@ -910,8 +910,12 @@ static int otx2_get_rxfh(struct net_device *dev,
 		return -ENOENT;
 
 	if (indir) {
-		for (idx = 0; idx < rss->rss_size; idx++)
+		for (idx = 0; idx < rss->rss_size; idx++) {
+			/* Ignore if the rx queue is AF_XDP zero copy enabled */
+			if (test_bit(rss_ctx->ind_tbl[idx], pfvf->af_xdp_zc_qidx))
+				continue;
 			indir[idx] = rss_ctx->ind_tbl[idx];
+		}
 	}
 	if (rxfh->key)
 		memcpy(rxfh->key, rss->key, sizeof(rss->key));
@@ -937,8 +941,8 @@ static u32 otx2_get_link(struct net_device *netdev)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 
-	/* LBK link is internal and always UP */
-	if (is_otx2_lbkvf(pfvf->pdev))
+	/* LBK and SDP links are internal and always UP */
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return 1;
 	return pfvf->linfo.link_up;
 }
@@ -1409,7 +1413,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 
-	if (is_otx2_lbkvf(pfvf->pdev)) {
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) {
 		cmd->base.duplex = DUPLEX_FULL;
 		cmd->base.speed = SPEED_100000;
 	} else {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 47bfd1fb37d4..64c6d9162ef6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -247,7 +247,7 @@ int otx2_mcam_entry_init(struct otx2_nic *pfvf)
 	mutex_unlock(&pfvf->mbox.lock);
 
 	/* Allocate entries for Ntuple filters */
-	count = otx2_alloc_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT);
+	count = otx2_alloc_mcam_entries(pfvf, flow_cfg->ntuple_cnt);
 	if (count <= 0) {
 		otx2_clear_ntuple_flow_info(pfvf, flow_cfg);
 		return 0;
@@ -307,6 +307,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf)
 	INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc);
 
 	pf->flow_cfg->ucast_flt_cnt = OTX2_DEFAULT_UNICAST_FLOWS;
+	pf->flow_cfg->ntuple_cnt = OTX2_DEFAULT_FLOWCOUNT;
 
 	/* Allocate bare minimum number of MCAM entries needed for
 	 * unicast and ntuple filters.
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index e310f99b1736..db7c466fdc39 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -26,6 +26,8 @@
 #include "cn10k.h"
 #include "qos.h"
 #include <rvu_trace.h>
+#include "cn10k_ipsec.h"
+#include "otx2_xsk.h"
 
 #define DRV_NAME	"rvu_nicpf"
 #define DRV_STRING	"Marvell RVU NIC Physical Function Driver"
@@ -463,6 +465,9 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work)
 
 	offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-VF down queue handler(forwarding)",
+			      vf_mbox->num_msgs);
+
 	for (id = 0; id < vf_mbox->num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + mbox->rx_start +
 					     offset);
@@ -471,7 +476,7 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work)
 			goto inval_msg;
 
 		/* Set VF's number in each of the msg */
-		msg->pcifunc &= RVU_PFVF_FUNC_MASK;
+		msg->pcifunc &= ~RVU_PFVF_FUNC_MASK;
 		msg->pcifunc |= (vf_idx + 1) & RVU_PFVF_FUNC_MASK;
 		offset = msg->next_msgoff;
 	}
@@ -501,6 +506,9 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work)
 
 	offset = mbox->rx_start + ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-VF up queue handler(response)",
+			      vf_mbox->up_num_msgs);
+
 	for (id = 0; id < vf_mbox->up_num_msgs; id++) {
 		msg = mdev->mbase + offset;
 
@@ -817,6 +825,9 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work)
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 	pf = af_mbox->pfvf;
 
+	trace_otx2_msg_status(pf->pdev, "PF-AF down queue handler(response)",
+			      num_msgs);
+
 	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 		otx2_process_pfaf_mbox_msg(pf, msg);
@@ -972,6 +983,9 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-AF up queue handler(notification)",
+			      num_msgs);
+
 	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 
@@ -1021,6 +1035,9 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 
 		trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF",
 					 BIT_ULL(0));
+
+		trace_otx2_msg_status(pf->pdev, "PF-AF up work queued(interrupt)",
+				      hdr->num_msgs);
 	}
 
 	if (mbox_data & MBOX_DOWN_MSG) {
@@ -1037,6 +1054,9 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 
 		trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF",
 					 BIT_ULL(0));
+
+		trace_otx2_msg_status(pf->pdev, "PF-AF down work queued(interrupt)",
+				      hdr->num_msgs);
 	}
 
 	return IRQ_HANDLED;
@@ -1484,6 +1504,8 @@ static void otx2_free_sq_res(struct otx2_nic *pf)
 		if (!sq->sqe)
 			continue;
 		qmem_free(pf->dev, sq->sqe);
+		qmem_free(pf->dev, sq->sqe_ring);
+		qmem_free(pf->dev, sq->cpt_resp);
 		qmem_free(pf->dev, sq->tso_hdrs);
 		kfree(sq->sg);
 		kfree(sq->sqb_ptrs);
@@ -1551,6 +1573,9 @@ int otx2_init_hw_resources(struct otx2_nic *pf)
 	if (err)
 		goto err_free_npa_lf;
 
+	/* Default disable backpressure on NIX-CPT */
+	otx2_nix_cpt_config_bp(pf, false);
+
 	/* Enable backpressure for CGX mapped PF/VFs */
 	if (!is_otx2_lbkvf(pf->pdev))
 		otx2_nix_config_bp(pf, true);
@@ -1656,9 +1681,7 @@ void otx2_free_hw_resources(struct otx2_nic *pf)
 	struct nix_lf_free_req *free_req;
 	struct mbox *mbox = &pf->mbox;
 	struct otx2_cq_queue *cq;
-	struct otx2_pool *pool;
 	struct msg_req *req;
-	int pool_id;
 	int qidx;
 
 	/* Ensure all SQE are processed */
@@ -1699,13 +1722,6 @@ void otx2_free_hw_resources(struct otx2_nic *pf)
 	/* Free RQ buffer pointers*/
 	otx2_free_aura_ptr(pf, AURA_NIX_RQ);
 
-	for (qidx = 0; qidx < pf->hw.rx_queues; qidx++) {
-		pool_id = otx2_get_pool_idx(pf, AURA_NIX_RQ, qidx);
-		pool = &pf->qset.pool[pool_id];
-		page_pool_destroy(pool->page_pool);
-		pool->page_pool = NULL;
-	}
-
 	otx2_free_cq_res(pf);
 
 	/* Free all ingress bandwidth profiles allocated */
@@ -2273,6 +2289,10 @@ static int otx2_set_features(struct net_device *netdev,
 		return otx2_enable_rxvlan(pf,
 					  features & NETIF_F_HW_VLAN_CTAG_RX);
 
+	if (changed & NETIF_F_HW_ESP)
+		return cn10k_ipsec_ethtool_init(netdev,
+						features & NETIF_F_HW_ESP);
+
 	return otx2_handle_ntuple_tc_features(netdev, features);
 }
 
@@ -2681,7 +2701,6 @@ static int otx2_get_vf_config(struct net_device *netdev, int vf,
 static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf,
 			    int qidx)
 {
-	struct page *page;
 	u64 dma_addr;
 	int err = 0;
 
@@ -2691,11 +2710,11 @@ static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf,
 	if (dma_mapping_error(pf->dev, dma_addr))
 		return -ENOMEM;
 
-	err = otx2_xdp_sq_append_pkt(pf, dma_addr, xdpf->len, qidx);
+	err = otx2_xdp_sq_append_pkt(pf, xdpf, dma_addr, xdpf->len,
+				     qidx, OTX2_XDP_REDIRECT);
 	if (!err) {
 		otx2_dma_unmap_page(pf, dma_addr, xdpf->len, DMA_TO_DEVICE);
-		page = virt_to_page(xdpf->data);
-		put_page(page);
+		xdp_return_frame(xdpf);
 		return -ENOMEM;
 	}
 	return 0;
@@ -2779,6 +2798,8 @@ static int otx2_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return otx2_xdp_setup(pf, xdp->prog);
+	case XDP_SETUP_XSK_POOL:
+		return otx2_xsk_pool_setup(pf, xdp->xsk.pool, xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
@@ -2856,6 +2877,7 @@ static const struct net_device_ops otx2_netdev_ops = {
 	.ndo_set_vf_vlan	= otx2_set_vf_vlan,
 	.ndo_get_vf_config	= otx2_get_vf_config,
 	.ndo_bpf		= otx2_xdp,
+	.ndo_xsk_wakeup		= otx2_xsk_wakeup,
 	.ndo_xdp_xmit           = otx2_xdp_xmit,
 	.ndo_setup_tc		= otx2_setup_tc,
 	.ndo_set_vf_trust	= otx2_ndo_set_vf_trust,
@@ -3044,7 +3066,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -3053,7 +3075,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		return err;
 	}
 
 	pci_set_master(pdev);
@@ -3063,10 +3085,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);
 
 	netdev = alloc_etherdev_mqs(sizeof(*pf), qcount + qos_txqs, qcount);
-	if (!netdev) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
+	if (!netdev)
+		return -ENOMEM;
 
 	pci_set_drvdata(pdev, netdev);
 	SET_NETDEV_DEV(netdev, &pdev->dev);
@@ -3124,6 +3144,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_ptp_destroy;
 
+	otx2_set_hw_capabilities(pf);
+
 	err = cn10k_mcs_init(pf);
 	if (err)
 		goto err_del_mcam_entries;
@@ -3162,10 +3184,14 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* reset CGX/RPM MAC stats */
 	otx2_reset_mac_stats(pf);
 
+	err = cn10k_ipsec_init(netdev);
+	if (err)
+		goto err_mcs_free;
+
 	err = register_netdev(netdev);
 	if (err) {
 		dev_err(dev, "Failed to register netdevice\n");
-		goto err_mcs_free;
+		goto err_ipsec_clean;
 	}
 
 	err = otx2_wq_init(pf);
@@ -3190,22 +3216,36 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* Enable link notifications */
 	otx2_cgx_config_linkevents(pf, true);
 
+	pf->af_xdp_zc_qidx = bitmap_zalloc(qcount, GFP_KERNEL);
+	if (!pf->af_xdp_zc_qidx) {
+		err = -ENOMEM;
+		goto err_sriov_cleannup;
+	}
+
 #ifdef CONFIG_DCB
 	err = otx2_dcbnl_set_ops(netdev);
 	if (err)
-		goto err_pf_sriov_init;
+		goto err_free_zc_bmap;
 #endif
 
 	otx2_qos_init(pf, qos_txqs);
 
 	return 0;
 
+#ifdef CONFIG_DCB
+err_free_zc_bmap:
+	bitmap_free(pf->af_xdp_zc_qidx);
+#endif
+err_sriov_cleannup:
+	otx2_sriov_vfcfg_cleanup(pf);
 err_pf_sriov_init:
 	otx2_shutdown_tc(pf);
 err_mcam_flow_del:
 	otx2_mcam_flow_del(pf);
 err_unreg_netdev:
 	unregister_netdev(netdev);
+err_ipsec_clean:
+	cn10k_ipsec_clean(pf);
 err_mcs_free:
 	cn10k_mcs_free(pf);
 err_del_mcam_entries:
@@ -3224,8 +3264,6 @@ err_detach_rsrc:
 err_free_netdev:
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-err_release_regions:
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -3267,6 +3305,7 @@ static void otx2_vf_link_event_task(struct work_struct *work)
 	req = (struct cgx_link_info_msg *)msghdr;
 	req->hdr.id = MBOX_MSG_CGX_LINK_EVENT;
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = pf->pcifunc;
 	memcpy(&req->link_info, &pf->linfo, sizeof(req->link_info));
 
 	otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx);
@@ -3403,6 +3442,7 @@ static void otx2_remove(struct pci_dev *pdev)
 
 	otx2_unregister_dl(pf);
 	unregister_netdev(netdev);
+	cn10k_ipsec_clean(pf);
 	cn10k_mcs_free(pf);
 	otx2_sriov_disable(pf->pdev);
 	otx2_sriov_vfcfg_cleanup(pf);
@@ -3424,8 +3464,6 @@ static void otx2_remove(struct pci_dev *pdev)
 	pci_free_irq_vectors(pf->pdev);
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver otx2_pf_driver = {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 04bc06a80e23..99ace381cc78 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -11,6 +11,8 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <net/ip6_checksum.h>
+#include <net/xfrm.h>
+#include <net/xdp.h>
 
 #include "otx2_reg.h"
 #include "otx2_common.h"
@@ -18,6 +20,7 @@
 #include "otx2_txrx.h"
 #include "otx2_ptp.h"
 #include "cn10k.h"
+#include "otx2_xsk.h"
 
 #define CQE_ADDR(CQ, idx) ((CQ)->cqe_base + ((CQ)->cqe_size * (idx)))
 #define PTP_PORT	        0x13F
@@ -26,11 +29,30 @@
  */
 #define PTP_SYNC_SEC_OFFSET	34
 
+DEFINE_STATIC_KEY_FALSE(cn10k_ipsec_sa_enabled);
+
+static int otx2_get_free_sqe(struct otx2_snd_queue *sq)
+{
+	return (sq->cons_head - sq->head - 1 + sq->sqe_cnt)
+		& (sq->sqe_cnt - 1);
+}
+
 static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
 				     struct otx2_cq_queue *cq,
-				     bool *need_xdp_flush);
+				     u32 *metasize, bool *need_xdp_flush);
+
+static void otx2_sq_set_sqe_base(struct otx2_snd_queue *sq,
+				 struct sk_buff *skb)
+{
+	if (static_branch_unlikely(&cn10k_ipsec_sa_enabled) &&
+	    (xfrm_offload(skb)))
+		sq->sqe_base = sq->sqe_ring->base + sq->sqe_size +
+				(sq->head * (sq->sqe_size * 2));
+	else
+		sq->sqe_base = sq->sqe->base;
+}
 
 static int otx2_nix_cq_op_status(struct otx2_nic *pfvf,
 				 struct otx2_cq_queue *cq)
@@ -80,54 +102,24 @@ static unsigned int frag_num(unsigned int i)
 #endif
 }
 
-static dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf,
-					struct sk_buff *skb, int seg, int *len)
-{
-	const skb_frag_t *frag;
-	struct page *page;
-	int offset;
-
-	/* First segment is always skb->data */
-	if (!seg) {
-		page = virt_to_page(skb->data);
-		offset = offset_in_page(skb->data);
-		*len = skb_headlen(skb);
-	} else {
-		frag = &skb_shinfo(skb)->frags[seg - 1];
-		page = skb_frag_page(frag);
-		offset = skb_frag_off(frag);
-		*len = skb_frag_size(frag);
-	}
-	return otx2_dma_map_page(pfvf, page, offset, *len, DMA_TO_DEVICE);
-}
-
-static void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg)
-{
-	int seg;
-
-	for (seg = 0; seg < sg->num_segs; seg++) {
-		otx2_dma_unmap_page(pfvf, sg->dma_addr[seg],
-				    sg->size[seg], DMA_TO_DEVICE);
-	}
-	sg->num_segs = 0;
-}
-
 static void otx2_xdp_snd_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_snd_queue *sq,
-				 struct nix_cqe_tx_s *cqe)
+				     struct nix_cqe_tx_s *cqe,
+				     int *xsk_frames)
 {
 	struct nix_send_comp_s *snd_comp = &cqe->comp;
 	struct sg_list *sg;
-	struct page *page;
-	u64 pa;
 
 	sg = &sq->sg[snd_comp->sqe_id];
+	if (sg->flags & OTX2_AF_XDP_FRAME) {
+		(*xsk_frames)++;
+		return;
+	}
 
-	pa = otx2_iova_to_phys(pfvf->iommu_domain, sg->dma_addr[0]);
-	otx2_dma_unmap_page(pfvf, sg->dma_addr[0],
-			    sg->size[0], DMA_TO_DEVICE);
-	page = virt_to_page(phys_to_virt(pa));
-	put_page(page);
+	if (sg->flags & OTX2_XDP_REDIRECT)
+		otx2_dma_unmap_page(pfvf, sg->dma_addr[0], sg->size[0], DMA_TO_DEVICE);
+	xdp_return_frame((struct xdp_frame *)sg->skb);
+	sg->skb = (u64)NULL;
 }
 
 static void otx2_snd_pkt_handler(struct otx2_nic *pfvf,
@@ -343,18 +335,24 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 	struct nix_rx_parse_s *parse = &cqe->parse;
 	struct nix_rx_sg_s *sg = &cqe->sg;
 	struct sk_buff *skb = NULL;
+	u64 *word = (u64 *)parse;
 	void *end, *start;
+	u32 metasize = 0;
 	u64 *seg_addr;
 	u16 *seg_size;
 	int seg;
 
 	if (unlikely(parse->errlev || parse->errcode)) {
-		if (otx2_check_rcv_errors(pfvf, cqe, cq->cq_idx))
+		if (otx2_check_rcv_errors(pfvf, cqe, cq->cq_idx)) {
+			trace_otx2_parse_dump(pfvf->pdev, "Err:", word);
 			return;
+		}
 	}
+	trace_otx2_parse_dump(pfvf->pdev, "", word);
 
 	if (pfvf->xdp_prog)
-		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq, need_xdp_flush))
+		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq,
+					     &metasize, need_xdp_flush))
 			return;
 
 	skb = napi_get_frags(napi);
@@ -386,6 +384,8 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 		skb->mark = parse->match_id;
 
 	skb_mark_for_recycle(skb);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 
 	napi_gro_frags(napi);
 }
@@ -449,6 +449,18 @@ int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 	return cnt - cq->pool_ptrs;
 }
 
+static void otx2_zc_submit_pkts(struct otx2_nic *pfvf, struct xsk_buff_pool *xsk_pool,
+				int *xsk_frames, int qidx, int budget)
+{
+	if (*xsk_frames)
+		xsk_tx_completed(xsk_pool, *xsk_frames);
+
+	if (xsk_uses_need_wakeup(xsk_pool))
+		xsk_set_tx_need_wakeup(xsk_pool);
+
+	otx2_zc_napi_handler(pfvf, xsk_pool, qidx, budget);
+}
+
 static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 				struct otx2_cq_queue *cq, int budget)
 {
@@ -457,16 +469,22 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 	struct nix_cqe_tx_s *cqe;
 	struct net_device *ndev;
 	int processed_cqe = 0;
+	int xsk_frames = 0;
+
+	qidx = cq->cq_idx - pfvf->hw.rx_queues;
+	sq = &pfvf->qset.sq[qidx];
 
 	if (cq->pend_cqe >= budget)
 		goto process_cqe;
 
-	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe)
+	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) {
+		if (sq->xsk_pool)
+			otx2_zc_submit_pkts(pfvf, sq->xsk_pool, &xsk_frames,
+					    qidx, budget);
 		return 0;
+	}
 
 process_cqe:
-	qidx = cq->cq_idx - pfvf->hw.rx_queues;
-	sq = &pfvf->qset.sq[qidx];
 
 	while (likely(processed_cqe < budget) && cq->pend_cqe) {
 		cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq);
@@ -476,10 +494,8 @@ process_cqe:
 			break;
 		}
 
-		qidx = cq->cq_idx - pfvf->hw.rx_queues;
-
 		if (cq->cq_type == CQ_XDP)
-			otx2_xdp_snd_pkt_handler(pfvf, sq, cqe);
+			otx2_xdp_snd_pkt_handler(pfvf, sq, cqe, &xsk_frames);
 		else
 			otx2_snd_pkt_handler(pfvf, cq, &pfvf->qset.sq[qidx],
 					     cqe, budget, &tx_pkts, &tx_bytes);
@@ -520,6 +536,10 @@ process_cqe:
 		    netif_carrier_ok(ndev))
 			netif_tx_wake_queue(txq);
 	}
+
+	if (sq->xsk_pool)
+		otx2_zc_submit_pkts(pfvf, sq->xsk_pool, &xsk_frames, qidx, budget);
+
 	return 0;
 }
 
@@ -545,9 +565,10 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p
 int otx2_napi_handler(struct napi_struct *napi, int budget)
 {
 	struct otx2_cq_queue *rx_cq = NULL;
+	struct otx2_cq_queue *cq = NULL;
+	struct otx2_pool *pool = NULL;
 	struct otx2_cq_poll *cq_poll;
 	int workdone = 0, cq_idx, i;
-	struct otx2_cq_queue *cq;
 	struct otx2_qset *qset;
 	struct otx2_nic *pfvf;
 	int filled_cnt = -1;
@@ -572,6 +593,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 
 	if (rx_cq && rx_cq->pool_ptrs)
 		filled_cnt = pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
+
 	/* Clear the IRQ */
 	otx2_write64(pfvf, NIX_LF_CINTX_INT(cq_poll->cint_idx), BIT_ULL(0));
 
@@ -584,20 +606,31 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 		if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED)
 			otx2_adjust_adaptive_coalese(pfvf, cq_poll);
 
+		if (likely(cq))
+			pool = &pfvf->qset.pool[cq->cq_idx];
+
 		if (unlikely(!filled_cnt)) {
 			struct refill_work *work;
 			struct delayed_work *dwork;
 
-			work = &pfvf->refill_wrk[cq->cq_idx];
-			dwork = &work->pool_refill_work;
-			/* Schedule a task if no other task is running */
-			if (!cq->refill_task_sched) {
-				work->napi = napi;
-				cq->refill_task_sched = true;
-				schedule_delayed_work(dwork,
-						      msecs_to_jiffies(100));
+			if (likely(cq)) {
+				work = &pfvf->refill_wrk[cq->cq_idx];
+				dwork = &work->pool_refill_work;
+				/* Schedule a task if no other task is running */
+				if (!cq->refill_task_sched) {
+					work->napi = napi;
+					cq->refill_task_sched = true;
+					schedule_delayed_work(dwork,
+							      msecs_to_jiffies(100));
+				}
+				/* Call wake-up for not able to fill buffers */
+				if (pool->xsk_pool)
+					xsk_set_rx_need_wakeup(pool->xsk_pool);
 			}
 		} else {
+			/* Clear wake-up, since buffers are filled successfully */
+			if (pool && pool->xsk_pool)
+				xsk_clear_rx_need_wakeup(pool->xsk_pool);
 			/* Re-enable interrupts */
 			otx2_write64(pfvf,
 				     NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
@@ -625,7 +658,6 @@ void otx2_sqe_flush(void *dev, struct otx2_snd_queue *sq,
 	sq->head &= (sq->sqe_cnt - 1);
 }
 
-#define MAX_SEGS_PER_SG	3
 /* Add SQE scatter/gather subdescriptor structure */
 static bool otx2_sqe_add_sg(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
 			    struct sk_buff *skb, int num_segs, int *offset)
@@ -1161,11 +1193,12 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq,
 	int offset, num_segs, free_desc;
 	struct nix_sqe_hdr_s *sqe_hdr;
 	struct otx2_nic *pfvf = dev;
+	bool ret;
 
 	/* Check if there is enough room between producer
 	 * and consumer index.
 	 */
-	free_desc = (sq->cons_head - sq->head - 1 + sq->sqe_cnt) & (sq->sqe_cnt - 1);
+	free_desc = otx2_get_free_sqe(sq);
 	if (free_desc < sq->sqe_thresh)
 		return false;
 
@@ -1177,6 +1210,7 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq,
 	/* If SKB doesn't fit in a single SQE, linearize it.
 	 * TODO: Consider adding JUMP descriptor instead.
 	 */
+
 	if (unlikely(num_segs > OTX2_MAX_FRAGS_IN_SQE)) {
 		if (__skb_linearize(skb)) {
 			dev_kfree_skb_any(skb);
@@ -1196,6 +1230,9 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq,
 		return true;
 	}
 
+	/* Set sqe base address */
+	otx2_sq_set_sqe_base(sq, skb);
+
 	/* Set SQE's SEND_HDR.
 	 * Do not clear the first 64bit as it contains constant info.
 	 */
@@ -1208,7 +1245,13 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq,
 	otx2_sqe_add_ext(pfvf, sq, skb, &offset);
 
 	/* Add SG subdesc with data frags */
-	if (!otx2_sqe_add_sg(pfvf, sq, skb, num_segs, &offset)) {
+	if (static_branch_unlikely(&cn10k_ipsec_sa_enabled) &&
+	    (xfrm_offload(skb)))
+		ret = otx2_sqe_add_sg_ipsec(pfvf, sq, skb, num_segs, &offset);
+	else
+		ret = otx2_sqe_add_sg(pfvf, sq, skb, num_segs, &offset);
+
+	if (!ret) {
 		otx2_dma_unmap_skb_frags(pfvf, &sq->sg[sq->head]);
 		return false;
 	}
@@ -1217,11 +1260,15 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq,
 
 	sqe_hdr->sizem1 = (offset / 16) - 1;
 
+	if (static_branch_unlikely(&cn10k_ipsec_sa_enabled) &&
+	    (xfrm_offload(skb)))
+		return cn10k_ipsec_transmit(pfvf, txq, sq, skb, num_segs,
+					    offset);
+
 	netdev_tx_sent_queue(txq, skb->len);
 
 	/* Flush SQE to HW */
 	pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx);
-
 	return true;
 }
 EXPORT_SYMBOL(otx2_sq_append_skb);
@@ -1234,15 +1281,19 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int q
 	u16 pool_id;
 	u64 iova;
 
-	if (pfvf->xdp_prog)
+	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx);
+	pool = &pfvf->qset.pool[pool_id];
+
+	if (pfvf->xdp_prog) {
+		if (pool->page_pool)
+			xdp_rxq_info_unreg_mem_model(&cq->xdp_rxq);
+
 		xdp_rxq_info_unreg(&cq->xdp_rxq);
+	}
 
 	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe)
 		return;
 
-	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx);
-	pool = &pfvf->qset.pool[pool_id];
-
 	while (cq->pend_cqe) {
 		cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq);
 		processed_cqe++;
@@ -1363,8 +1414,8 @@ void otx2_free_pending_sqe(struct otx2_nic *pfvf)
 	}
 }
 
-static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
-				int len, int *offset)
+void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, struct xdp_frame *xdpf,
+			 u64 dma_addr, int len, int *offset, u16 flags)
 {
 	struct nix_sqe_sg_s *sg = NULL;
 	u64 *iova = NULL;
@@ -1381,16 +1432,34 @@ static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
 	sq->sg[sq->head].dma_addr[0] = dma_addr;
 	sq->sg[sq->head].size[0] = len;
 	sq->sg[sq->head].num_segs = 1;
+	sq->sg[sq->head].flags = flags;
+	sq->sg[sq->head].skb = (u64)xdpf;
+}
+
+int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx)
+{
+	struct otx2_snd_queue *sq;
+	int free_sqe;
+
+	sq = &pfvf->qset.sq[qidx];
+	free_sqe = otx2_get_free_sqe(sq);
+	if (free_sqe < sq->sqe_thresh) {
+		netdev_warn(pfvf->netdev, "No free sqe for Send queue%d\n", qidx);
+		return 0;
+	}
+
+	return free_sqe - sq->sqe_thresh;
 }
 
-bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx)
+bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
+			    u64 iova, int len, u16 qidx, u16 flags)
 {
 	struct nix_sqe_hdr_s *sqe_hdr;
 	struct otx2_snd_queue *sq;
 	int offset, free_sqe;
 
 	sq = &pfvf->qset.sq[qidx];
-	free_sqe = (sq->num_sqbs - *sq->aura_fc_addr) * sq->sqe_per_sqb;
+	free_sqe = otx2_get_free_sqe(sq);
 	if (free_sqe < sq->sqe_thresh)
 		return false;
 
@@ -1409,7 +1478,7 @@ bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx)
 
 	offset = sizeof(*sqe_hdr);
 
-	otx2_xdp_sqe_add_sg(sq, iova, len, &offset);
+	otx2_xdp_sqe_add_sg(sq, xdpf, iova, len, &offset, flags);
 	sqe_hdr->sizem1 = (offset / 16) - 1;
 	pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx);
 
@@ -1420,16 +1489,30 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
 				     struct otx2_cq_queue *cq,
-				     bool *need_xdp_flush)
+				     u32 *metasize, bool *need_xdp_flush)
 {
+	struct xdp_buff xdp, *xsk_buff = NULL;
 	unsigned char *hard_start;
+	struct otx2_pool *pool;
+	struct xdp_frame *xdpf;
 	int qidx = cq->cq_idx;
-	struct xdp_buff xdp;
 	struct page *page;
 	u64 iova, pa;
 	u32 act;
 	int err;
 
+	pool = &pfvf->qset.pool[qidx];
+
+	if (pool->xsk_pool) {
+		xsk_buff = pool->xdp[--cq->rbpool->xdp_top];
+		if (!xsk_buff)
+			return false;
+
+		xsk_buff->data_end = xsk_buff->data + cqe->sg.seg_size;
+		act = bpf_prog_run_xdp(prog, xsk_buff);
+		goto handle_xdp_verdict;
+	}
+
 	iova = cqe->sg.seg_addr - OTX2_HEAD_ROOM;
 	pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
 	page = virt_to_page(phys_to_virt(pa));
@@ -1438,41 +1521,63 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 	hard_start = (unsigned char *)phys_to_virt(pa);
 	xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM,
-			 cqe->sg.seg_size, false);
+			 cqe->sg.seg_size, true);
 
 	act = bpf_prog_run_xdp(prog, &xdp);
 
+handle_xdp_verdict:
 	switch (act) {
 	case XDP_PASS:
+		*metasize = xdp.data - xdp.data_meta;
 		break;
 	case XDP_TX:
 		qidx += pfvf->hw.tx_queues;
 		cq->pool_ptrs++;
-		return otx2_xdp_sq_append_pkt(pfvf, iova,
-					      cqe->sg.seg_size, qidx);
+		xdpf = xdp_convert_buff_to_frame(&xdp);
+		return otx2_xdp_sq_append_pkt(pfvf, xdpf,
+					      cqe->sg.seg_addr,
+					      cqe->sg.seg_size,
+					      qidx, OTX2_XDP_TX);
 	case XDP_REDIRECT:
 		cq->pool_ptrs++;
-		err = xdp_do_redirect(pfvf->netdev, &xdp, prog);
+		if (xsk_buff) {
+			err = xdp_do_redirect(pfvf->netdev, xsk_buff, prog);
+			if (!err) {
+				*need_xdp_flush = true;
+				return true;
+			}
+			return false;
+		}
 
-		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
-				    DMA_FROM_DEVICE);
+		err = xdp_do_redirect(pfvf->netdev, &xdp, prog);
 		if (!err) {
 			*need_xdp_flush = true;
 			return true;
 		}
-		put_page(page);
+
+		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
+				    DMA_FROM_DEVICE);
+		xdpf = xdp_convert_buff_to_frame(&xdp);
+		xdp_return_frame(xdpf);
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(pfvf->netdev, prog, act);
-		break;
+		fallthrough;
 	case XDP_ABORTED:
-		trace_xdp_exception(pfvf->netdev, prog, act);
-		break;
+		if (act == XDP_ABORTED)
+			trace_xdp_exception(pfvf->netdev, prog, act);
+		fallthrough;
 	case XDP_DROP:
-		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
-				    DMA_FROM_DEVICE);
-		put_page(page);
 		cq->pool_ptrs++;
+		if (xsk_buff) {
+			xsk_buff_free(xsk_buff);
+		} else if (page->pp) {
+			page_pool_recycle_direct(pool->page_pool, page);
+		} else {
+			otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
+					    DMA_FROM_DEVICE);
+			put_page(page);
+		}
 		return true;
 	}
 	return false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index e1db5f961877..acf259d72008 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -12,6 +12,7 @@
 #include <linux/iommu.h>
 #include <linux/if_vlan.h>
 #include <net/xdp.h>
+#include <net/xdp_sock_drv.h>
 
 #define LBK_CHAN_BASE	0x000
 #define SDP_CHAN_BASE	0x700
@@ -76,6 +77,7 @@ struct otx2_rcv_queue {
 
 struct sg_list {
 	u16	num_segs;
+	u16	flags;
 	u64	skb;
 	u64	size[OTX2_MAX_FRAGS_IN_SQE];
 	u64	dma_addr[OTX2_MAX_FRAGS_IN_SQE];
@@ -101,6 +103,11 @@ struct otx2_snd_queue {
 	struct queue_stats	stats;
 	u16			sqb_count;
 	u64			*sqb_ptrs;
+	/* SQE ring and CPT response queue for Inline IPSEC */
+	struct qmem		*sqe_ring;
+	struct qmem		*cpt_resp;
+	/* Buffer pool for af_xdp zero-copy */
+	struct xsk_buff_pool    *xsk_pool;
 } ____cacheline_aligned_in_smp;
 
 enum cq_type {
@@ -124,7 +131,11 @@ struct otx2_pool {
 	struct qmem		*stack;
 	struct qmem		*fc_addr;
 	struct page_pool	*page_pool;
+	struct xsk_buff_pool	*xsk_pool;
+	struct xdp_buff		**xdp;
+	u16			xdp_cnt;
 	u16			rbsize;
+	u16			xdp_top;
 };
 
 struct otx2_cq_queue {
@@ -141,6 +152,7 @@ struct otx2_cq_queue {
 	void			*cqe_base;
 	struct qmem		*cqe;
 	struct otx2_pool	*rbpool;
+	bool			xsk_zc_en;
 	struct xdp_rxq_info xdp_rxq;
 } ____cacheline_aligned_in_smp;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 839fc77c11b2..8a8b598bd389 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -14,6 +14,7 @@
 #include "otx2_reg.h"
 #include "otx2_ptp.h"
 #include "cn10k.h"
+#include "cn10k_ipsec.h"
 
 #define DRV_NAME	"rvu_nicvf"
 #define DRV_STRING	"Marvell RVU NIC Virtual Function Driver"
@@ -135,7 +136,7 @@ static int otx2vf_process_mbox_msg_up(struct otx2_nic *vf,
 
 		rsp->hdr.id = MBOX_MSG_CGX_LINK_EVENT;
 		rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
-		rsp->hdr.pcifunc = 0;
+		rsp->hdr.pcifunc = req->pcifunc;
 		rsp->hdr.rc = 0;
 		err = otx2_mbox_up_handler_cgx_link_event(
 				vf, (struct cgx_link_info_msg *)req, rsp);
@@ -547,7 +548,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -556,7 +557,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		return err;
 	}
 
 	pci_set_master(pdev);
@@ -564,10 +565,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	qcount = num_online_cpus();
 	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);
 	netdev = alloc_etherdev_mqs(sizeof(*vf), qcount + qos_txqs, qcount);
-	if (!netdev) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
+	if (!netdev)
+		return -ENOMEM;
 
 	pci_set_drvdata(pdev, netdev);
 	SET_NETDEV_DEV(netdev, &pdev->dev);
@@ -693,10 +692,14 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 			 pdev->bus->number, n);
 	}
 
+	err = cn10k_ipsec_init(netdev);
+	if (err)
+		goto err_ptp_destroy;
+
 	err = register_netdev(netdev);
 	if (err) {
 		dev_err(dev, "Failed to register netdevice\n");
-		goto err_ptp_destroy;
+		goto err_ipsec_clean;
 	}
 
 	err = otx2_vf_wq_init(vf);
@@ -717,19 +720,36 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_shutdown_tc;
 
+	vf->af_xdp_zc_qidx = bitmap_zalloc(qcount, GFP_KERNEL);
+	if (!vf->af_xdp_zc_qidx) {
+		err = -ENOMEM;
+		goto err_unreg_devlink;
+	}
+
 #ifdef CONFIG_DCB
-	err = otx2_dcbnl_set_ops(netdev);
-	if (err)
-		goto err_shutdown_tc;
+	/* Priority flow control is not supported for LBK and SDP vf(s) */
+	if (!(is_otx2_lbkvf(vf->pdev) || is_otx2_sdp_rep(vf->pdev))) {
+		err = otx2_dcbnl_set_ops(netdev);
+		if (err)
+			goto err_free_zc_bmap;
+	}
 #endif
 	otx2_qos_init(vf, qos_txqs);
 
 	return 0;
 
+#ifdef CONFIG_DCB
+err_free_zc_bmap:
+	bitmap_free(vf->af_xdp_zc_qidx);
+#endif
+err_unreg_devlink:
+	otx2_unregister_dl(vf);
 err_shutdown_tc:
 	otx2_shutdown_tc(vf);
 err_unreg_netdev:
 	unregister_netdev(netdev);
+err_ipsec_clean:
+	cn10k_ipsec_clean(vf);
 err_ptp_destroy:
 	otx2_ptp_destroy(vf);
 err_detach_rsrc:
@@ -746,8 +766,6 @@ err_free_irq_vectors:
 err_free_netdev:
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-err_release_regions:
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -782,6 +800,7 @@ static void otx2vf_remove(struct pci_dev *pdev)
 	unregister_netdev(netdev);
 	if (vf->otx2_wq)
 		destroy_workqueue(vf->otx2_wq);
+	cn10k_ipsec_clean(vf);
 	otx2_ptp_destroy(vf);
 	otx2_mcam_flow_del(vf);
 	otx2_shutdown_tc(vf);
@@ -795,8 +814,6 @@ static void otx2vf_remove(struct pci_dev *pdev)
 	pci_free_irq_vectors(vf->pdev);
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver otx2vf_driver = {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
new file mode 100644
index 000000000000..b328aae23d73
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#include <linux/bpf_trace.h>
+#include <linux/stringify.h>
+#include <net/xdp_sock_drv.h>
+#include <net/xdp.h>
+
+#include "otx2_common.h"
+#include "otx2_struct.h"
+#include "otx2_xsk.h"
+
+int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+			    dma_addr_t *dma, int idx)
+{
+	struct xdp_buff *xdp;
+	int delta;
+
+	xdp = xsk_buff_alloc(pool->xsk_pool);
+	if (!xdp)
+		return -ENOMEM;
+
+	pool->xdp[pool->xdp_top++] = xdp;
+	*dma = OTX2_DATA_ALIGN(xsk_buff_xdp_get_dma(xdp));
+	/* Adjust xdp->data for unaligned addresses */
+	delta = *dma - xsk_buff_xdp_get_dma(xdp);
+	xdp->data += delta;
+
+	return 0;
+}
+
+static int otx2_xsk_ctx_disable(struct otx2_nic *pfvf, u16 qidx, int aura_id)
+{
+	struct nix_cn10k_aq_enq_req *cn10k_rq_aq;
+	struct npa_aq_enq_req *aura_aq;
+	struct npa_aq_enq_req *pool_aq;
+	struct nix_aq_enq_req *rq_aq;
+
+	if (test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
+		cn10k_rq_aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
+		if (!cn10k_rq_aq)
+			return -ENOMEM;
+		cn10k_rq_aq->qidx = qidx;
+		cn10k_rq_aq->rq.ena = 0;
+		cn10k_rq_aq->rq_mask.ena = 1;
+		cn10k_rq_aq->ctype = NIX_AQ_CTYPE_RQ;
+		cn10k_rq_aq->op = NIX_AQ_INSTOP_WRITE;
+	} else {
+		rq_aq = otx2_mbox_alloc_msg_nix_aq_enq(&pfvf->mbox);
+		if (!rq_aq)
+			return -ENOMEM;
+		rq_aq->qidx = qidx;
+		rq_aq->sq.ena = 0;
+		rq_aq->sq_mask.ena = 1;
+		rq_aq->ctype = NIX_AQ_CTYPE_RQ;
+		rq_aq->op = NIX_AQ_INSTOP_WRITE;
+	}
+
+	aura_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
+	if (!aura_aq)
+		goto fail;
+
+	aura_aq->aura_id = aura_id;
+	aura_aq->aura.ena = 0;
+	aura_aq->aura_mask.ena = 1;
+	aura_aq->ctype = NPA_AQ_CTYPE_AURA;
+	aura_aq->op = NPA_AQ_INSTOP_WRITE;
+
+	pool_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
+	if (!pool_aq)
+		goto fail;
+
+	pool_aq->aura_id = aura_id;
+	pool_aq->pool.ena = 0;
+	pool_aq->pool_mask.ena = 1;
+
+	pool_aq->ctype = NPA_AQ_CTYPE_POOL;
+	pool_aq->op = NPA_AQ_INSTOP_WRITE;
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+
+fail:
+	otx2_mbox_reset(&pfvf->mbox.mbox, 0);
+	return -ENOMEM;
+}
+
+static void otx2_clean_up_rq(struct otx2_nic *pfvf, int qidx)
+{
+	struct otx2_qset *qset = &pfvf->qset;
+	struct otx2_cq_queue *cq;
+	struct otx2_pool *pool;
+	u64 iova;
+
+	/* If the DOWN flag is set SQs are already freed */
+	if (pfvf->flags & OTX2_FLAG_INTF_DOWN)
+		return;
+
+	cq = &qset->cq[qidx];
+	if (cq)
+		otx2_cleanup_rx_cqes(pfvf, cq, qidx);
+
+	pool = &pfvf->qset.pool[qidx];
+	iova = otx2_aura_allocptr(pfvf, qidx);
+	while (iova) {
+		iova -= OTX2_HEAD_ROOM;
+		otx2_free_bufs(pfvf, pool, iova, pfvf->rbsize);
+		iova = otx2_aura_allocptr(pfvf, qidx);
+	}
+
+	mutex_lock(&pfvf->mbox.lock);
+	otx2_xsk_ctx_disable(pfvf, qidx, qidx);
+	mutex_unlock(&pfvf->mbox.lock);
+}
+
+int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qidx)
+{
+	u16 rx_queues = pf->hw.rx_queues;
+	u16 tx_queues = pf->hw.tx_queues;
+	int err;
+
+	if (qidx >= rx_queues || qidx >= tx_queues)
+		return -EINVAL;
+
+	err = xsk_pool_dma_map(pool, pf->dev, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+	if (err)
+		return err;
+
+	set_bit(qidx, pf->af_xdp_zc_qidx);
+	otx2_clean_up_rq(pf, qidx);
+	/* Reconfigure RSS table as 'qidx' cannot be part of RSS now */
+	otx2_set_rss_table(pf, DEFAULT_RSS_CONTEXT_GROUP);
+	/* Kick start the NAPI context so that receiving will start */
+	return otx2_xsk_wakeup(pf->netdev, qidx, XDP_WAKEUP_RX);
+}
+
+int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qidx)
+{
+	struct net_device *netdev = pf->netdev;
+	struct xsk_buff_pool *pool;
+	struct otx2_snd_queue *sq;
+
+	pool = xsk_get_pool_from_qid(netdev, qidx);
+	if (!pool)
+		return -EINVAL;
+
+	sq = &pf->qset.sq[qidx + pf->hw.tx_queues];
+	sq->xsk_pool = NULL;
+	otx2_clean_up_rq(pf, qidx);
+	clear_bit(qidx, pf->af_xdp_zc_qidx);
+	xsk_pool_dma_unmap(pool, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+	/* Reconfigure RSS table as 'qidx' now need to be part of RSS now */
+	otx2_set_rss_table(pf, DEFAULT_RSS_CONTEXT_GROUP);
+
+	return 0;
+}
+
+int otx2_xsk_pool_setup(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qidx)
+{
+	if (pool)
+		return otx2_xsk_pool_enable(pf, pool, qidx);
+
+	return otx2_xsk_pool_disable(pf, qidx);
+}
+
+int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
+{
+	struct otx2_nic *pf = netdev_priv(dev);
+	struct otx2_cq_poll *cq_poll = NULL;
+	struct otx2_qset *qset = &pf->qset;
+
+	if (pf->flags & OTX2_FLAG_INTF_DOWN)
+		return -ENETDOWN;
+
+	if (queue_id >= pf->hw.rx_queues || queue_id >= pf->hw.tx_queues)
+		return -EINVAL;
+
+	cq_poll = &qset->napi[queue_id];
+	if (!cq_poll)
+		return -EINVAL;
+
+	/* Trigger interrupt */
+	if (!napi_if_scheduled_mark_missed(&cq_poll->napi)) {
+		otx2_write64(pf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx), BIT_ULL(0));
+		otx2_write64(pf, NIX_LF_CINTX_INT_W1S(cq_poll->cint_idx), BIT_ULL(0));
+	}
+
+	return 0;
+}
+
+void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int qidx)
+{
+	if (test_bit(qidx, pfvf->af_xdp_zc_qidx))
+		sq->xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, qidx);
+}
+
+static void otx2_xsk_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len,
+				   u16 qidx)
+{
+	struct nix_sqe_hdr_s *sqe_hdr;
+	struct otx2_snd_queue *sq;
+	int offset;
+
+	sq = &pfvf->qset.sq[qidx];
+	memset(sq->sqe_base + 8, 0, sq->sqe_size - 8);
+
+	sqe_hdr = (struct nix_sqe_hdr_s *)(sq->sqe_base);
+
+	if (!sqe_hdr->total) {
+		sqe_hdr->aura = sq->aura_id;
+		sqe_hdr->df = 1;
+		sqe_hdr->sq = qidx;
+		sqe_hdr->pnc = 1;
+	}
+	sqe_hdr->total = len;
+	sqe_hdr->sqe_id = sq->head;
+
+	offset = sizeof(*sqe_hdr);
+
+	otx2_xdp_sqe_add_sg(sq, NULL, iova, len, &offset, OTX2_AF_XDP_FRAME);
+	sqe_hdr->sizem1 = (offset / 16) - 1;
+	pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx);
+}
+
+void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool,
+			  int queue, int budget)
+{
+	struct xdp_desc *xdp_desc = pool->tx_descs;
+	int  i, batch;
+
+	budget = min(budget, otx2_read_free_sqe(pfvf, queue));
+	batch = xsk_tx_peek_release_desc_batch(pool, budget);
+	if (!batch)
+		return;
+
+	for (i = 0; i < batch; i++) {
+		dma_addr_t dma_addr;
+
+		dma_addr = xsk_buff_raw_get_dma(pool, xdp_desc[i].addr);
+		otx2_xsk_sq_append_pkt(pfvf, dma_addr, xdp_desc[i].len, queue);
+	}
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
new file mode 100644
index 000000000000..8047fafee8fe
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU PF/VF Netdev Devlink
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#ifndef	OTX2_XSK_H
+#define	OTX2_XSK_H
+
+struct otx2_nic;
+struct xsk_buff_pool;
+
+int otx2_xsk_pool_setup(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qid);
+int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qid);
+int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qid);
+int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+			    dma_addr_t *dma, int idx);
+int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
+void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool,
+			  int queue, int budget);
+void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int qidx);
+
+#endif /* OTX2_XSK_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 0f844c14485a..5765bac119f0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -165,6 +165,11 @@ static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf,
 
 		otx2_config_sched_shaping(pfvf, node, cfg, &num_regs);
 	} else if (level == NIX_TXSCH_LVL_TL2) {
+		/* configure parent txschq */
+		cfg->reg[num_regs] = NIX_AF_TL2X_PARENT(node->schq);
+		cfg->regval[num_regs] = (u64)hw->tx_link << 16;
+		num_regs++;
+
 		/* configure link cfg */
 		if (level == pfvf->qos.link_cfg_lvl) {
 			cfg->reg[num_regs] = NIX_AF_TL3_TL2X_LINKX_CFG(node->schq, hw->tx_link);
@@ -1633,6 +1638,7 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 	if (!node->is_static)
 		dwrr_del_node = true;
 
+	WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER);
 	/* destroy the leaf node */
 	otx2_qos_disable_sq(pfvf, qid);
 	otx2_qos_destroy_node(pfvf, node);
@@ -1677,9 +1683,6 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 	}
 	kfree(new_cfg);
 
-	/* update tx_real_queues */
-	otx2_qos_update_tx_netdev_queues(pfvf);
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
index 9d887bfc3108..58d572ce08ef 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
@@ -82,7 +82,7 @@ static int otx2_qos_sq_aura_pool_init(struct otx2_nic *pfvf, int qidx)
 	}
 
 	for (ptr = 0; ptr < num_sqbs; ptr++) {
-		err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+		err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
 		if (err)
 			goto sqb_free;
 		pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
@@ -256,6 +256,26 @@ out:
 	return err;
 }
 
+static int otx2_qos_nix_npa_ndc_sync(struct otx2_nic *pfvf)
+{
+	struct ndc_sync_op *req;
+	int rc;
+
+	mutex_lock(&pfvf->mbox.lock);
+
+	req = otx2_mbox_alloc_msg_ndc_sync_op(&pfvf->mbox);
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
+		return -ENOMEM;
+	}
+
+	req->nix_lf_tx_sync = true;
+	req->npa_lf_sync = true;
+	rc = otx2_sync_mbox_msg(&pfvf->mbox);
+	mutex_unlock(&pfvf->mbox.lock);
+	return rc;
+}
+
 void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx)
 {
 	struct otx2_qset *qset = &pfvf->qset;
@@ -285,6 +305,8 @@ void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx)
 
 	otx2_qos_sqb_flush(pfvf, sq_idx);
 	otx2_smq_flush(pfvf, otx2_get_smq_idx(pfvf, sq_idx));
+	/* NIX/NPA NDC sync */
+	otx2_qos_nix_npa_ndc_sync(pfvf);
 	otx2_cleanup_tx_cqes(pfvf, cq);
 
 	mutex_lock(&pfvf->mbox.lock);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
index 232b10740c13..2cd3da3b6843 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
@@ -67,6 +67,8 @@ static int rvu_rep_mcam_flow_init(struct rep_dev *rep)
 
 		rsp = (struct npc_mcam_alloc_entry_rsp *)otx2_mbox_get_rsp
 			(&priv->mbox.mbox, 0, &req->hdr);
+		if (IS_ERR(rsp))
+			goto exit;
 
 		for (ent = 0; ent < rsp->count; ent++)
 			rep->flow_cfg->flow_ent[ent + allocated] = rsp->entry_list[ent];
@@ -680,14 +682,17 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack)
 		ndev->features |= ndev->hw_features;
 		eth_hw_addr_random(ndev);
 		err = rvu_rep_devlink_port_register(rep);
-		if (err)
+		if (err) {
+			free_netdev(ndev);
 			goto exit;
+		}
 
 		SET_NETDEV_DEVLINK_PORT(ndev, &rep->dl_port);
 		err = register_netdev(ndev);
 		if (err) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "PFVF representor registration failed");
+			rvu_rep_devlink_port_unregister(rep);
 			free_netdev(ndev);
 			goto exit;
 		}
@@ -760,7 +765,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -769,7 +774,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		goto err_set_drv_data;
 	}
 
 	pci_set_master(pdev);
@@ -777,7 +782,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		err = -ENOMEM;
-		goto err_release_regions;
+		goto err_set_drv_data;
 	}
 
 	pci_set_drvdata(pdev, priv);
@@ -794,7 +799,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	err = otx2_init_rsrc(pdev, priv);
 	if (err)
-		goto err_release_regions;
+		goto err_set_drv_data;
 
 	priv->iommu_domain = iommu_get_domain_for_dev(dev);
 
@@ -817,9 +822,8 @@ err_detach_rsrc:
 	otx2_disable_mbox_intr(priv);
 	otx2_pfaf_mbox_destroy(priv);
 	pci_free_irq_vectors(pdev);
-err_release_regions:
+err_set_drv_data:
 	pci_set_drvdata(pdev, NULL);
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -839,7 +843,6 @@ static void rvu_rep_remove(struct pci_dev *pdev)
 	otx2_pfaf_mbox_destroy(priv);
 	pci_free_irq_vectors(priv->pdev);
 	pci_set_drvdata(pdev, NULL);
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver rvu_rep_driver = {
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_counter.c b/drivers/net/ethernet/marvell/prestera/prestera_counter.c
index 4cd53a2dae46..634f4543c1d7 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_counter.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_counter.c
@@ -336,8 +336,7 @@ prestera_counter_block_get_by_idx(struct prestera_counter *counter, u32 idx)
 
 static void prestera_counter_stats_work(struct work_struct *work)
 {
-	struct delayed_work *dl_work =
-		container_of(work, struct delayed_work, work);
+	struct delayed_work *dl_work = to_delayed_work(work);
 	struct prestera_counter *counter =
 		container_of(dl_work, struct prestera_counter, stats_dw);
 	struct prestera_counter_block *block;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 22ca6ee9665e..71ffb55d1fc4 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -280,6 +280,7 @@ prestera_mac_select_pcs(struct phylink_config *config,
 }
 
 static void prestera_pcs_get_state(struct phylink_pcs *pcs,
+				   unsigned int neg_mode,
 				   struct phylink_link_state *state)
 {
 	struct prestera_port *port = container_of(pcs, struct prestera_port,
@@ -395,7 +396,6 @@ static int prestera_port_sfp_bind(struct prestera_port *port)
 			continue;
 
 		port->phylink_pcs.ops = &prestera_pcs_ops;
-		port->phylink_pcs.neg_mode = true;
 
 		port->phy_config.dev = &port->dev->dev;
 		port->phy_config.type = PHYLINK_NETDEV;
@@ -634,7 +634,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id)
 		goto err_dl_port_register;
 
 	dev->features |= NETIF_F_HW_TC;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 	dev->netdev_ops = &prestera_netdev_ops;
 	dev->ethtool_ops = &prestera_ethtool_ops;
 	SET_NETDEV_DEV(dev, sw->dev->dev);
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
index 35857dc19542..c45d108b2f6d 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
@@ -845,9 +845,9 @@ static int prestera_pci_probe(struct pci_dev *pdev,
 		goto err_pci_enable_device;
 	}
 
-	err = pci_request_regions(pdev, driver_name);
+	err = pcim_request_all_regions(pdev, driver_name);
 	if (err) {
-		dev_err(&pdev->dev, "pci_request_regions failed\n");
+		dev_err(&pdev->dev, "pcim_request_all_regions failed\n");
 		goto err_pci_request_regions;
 	}
 
@@ -938,7 +938,6 @@ err_pci_dev_alloc:
 err_pp_ioremap:
 err_mem_ioremap:
 err_dma_mask:
-	pci_release_regions(pdev);
 err_pci_request_regions:
 err_pci_enable_device:
 	return err;
@@ -953,7 +952,6 @@ static void prestera_pci_remove(struct pci_dev *pdev)
 	pci_free_irq_vectors(pdev);
 	destroy_workqueue(fw->wq);
 	prestera_fw_uninit(fw);
-	pci_release_regions(pdev);
 }
 
 static const struct pci_device_id prestera_pci_devices[] = {
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 2bf426cea6dd..e4cfdc8bc055 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -353,7 +353,7 @@ static void rxq_refill(struct net_device *dev)
 
 static inline void rxq_refill_timer_wrapper(struct timer_list *t)
 {
-	struct pxa168_eth_private *pep = from_timer(pep, t, timeout);
+	struct pxa168_eth_private *pep = timer_container_of(pep, t, timeout);
 	napi_schedule(&pep->napi);
 }
 
@@ -1175,7 +1175,7 @@ static int pxa168_eth_stop(struct net_device *dev)
 	/* Write to ICR to clear interrupts. */
 	wrl(pep, INT_W_CLEAR, 0);
 	napi_disable(&pep->napi);
-	del_timer_sync(&pep->timeout);
+	timer_delete_sync(&pep->timeout);
 	netif_carrier_off(dev);
 	free_irq(dev->irq, dev);
 	rxq_deinit(dev);
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 25bf6ec44289..05349a0b2db1 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -1494,7 +1494,7 @@ static int xm_check_link(struct net_device *dev)
  */
 static void xm_link_timer(struct timer_list *t)
 {
-	struct skge_port *skge = from_timer(skge, t, link_timer);
+	struct skge_port *skge = timer_container_of(skge, t, link_timer);
 	struct net_device *dev = skge->netdev;
 	struct skge_hw *hw = skge->hw;
 	int port = skge->port;
@@ -2662,7 +2662,7 @@ static int skge_down(struct net_device *dev)
 	netif_tx_disable(dev);
 
 	if (is_genesis(hw) && hw->phy_type == SK_PHY_XMAC)
-		del_timer_sync(&skge->link_timer);
+		timer_delete_sync(&skge->link_timer);
 
 	napi_disable(&skge->napi);
 	netif_carrier_off(dev);
@@ -3742,10 +3742,7 @@ static int skge_device_event(struct notifier_block *unused,
 	skge = netdev_priv(dev);
 	switch (event) {
 	case NETDEV_CHANGENAME:
-		if (skge->debugfs)
-			skge->debugfs = debugfs_rename(skge_debug,
-						       skge->debugfs,
-						       skge_debug, dev->name);
+		debugfs_change_name(skge->debugfs, "%s", dev->name);
 		break;
 
 	case NETDEV_GOING_DOWN:
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 3914cd9210d4..3831f533b9db 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -130,6 +130,7 @@ static const struct pci_device_id sky2_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436C) }, /* 88E8072 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436D) }, /* 88E8055 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4370) }, /* 88E8075 */
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4373) }, /* 88E8075 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4380) }, /* 88E8057 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4381) }, /* 88E8059 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4382) }, /* 88E8079 */
@@ -2960,7 +2961,7 @@ static int sky2_rx_hung(struct net_device *dev)
 
 static void sky2_watchdog(struct timer_list *t)
 {
-	struct sky2_hw *hw = from_timer(hw, t, watchdog_timer);
+	struct sky2_hw *hw = timer_container_of(hw, t, watchdog_timer);
 
 	/* Check for lost IRQ once a second */
 	if (sky2_read32(hw, B0_ISRC)) {
@@ -4493,10 +4494,7 @@ static int sky2_device_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_CHANGENAME:
-		if (sky2->debugfs) {
-			sky2->debugfs = debugfs_rename(sky2_debug, sky2->debugfs,
-						       sky2_debug, dev->name);
-		}
+		debugfs_change_name(sky2->debugfs, "%s", dev->name);
 		break;
 
 	case NETDEV_GOING_DOWN:
@@ -5054,7 +5052,7 @@ static int sky2_suspend(struct device *dev)
 	if (!hw)
 		return 0;
 
-	del_timer_sync(&hw->watchdog_timer);
+	timer_delete_sync(&hw->watchdog_timer);
 	cancel_work_sync(&hw->restart_work);
 
 	rtnl_lock();
diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index 95c4405b7d7b..7bfd3f230ff5 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -7,14 +7,6 @@ config NET_VENDOR_MEDIATEK
 
 if NET_VENDOR_MEDIATEK
 
-config NET_AIROHA
-	tristate "Airoha SoC Gigabit Ethernet support"
-	depends on NET_DSA || !NET_DSA
-	select PAGE_POOL
-	help
-	  This driver supports the gigabit ethernet MACs in the
-	  Airoha SoC family.
-
 config NET_MEDIATEK_SOC_WED
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	def_bool NET_MEDIATEK_SOC != n
diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile
index ddbb7f4a516c..03e008fbc859 100644
--- a/drivers/net/ethernet/mediatek/Makefile
+++ b/drivers/net/ethernet/mediatek/Makefile
@@ -11,4 +11,3 @@ mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_debugfs.o
 endif
 obj-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_ops.o
 obj-$(CONFIG_NET_MEDIATEK_STAR_EMAC) += mtk_star_emac.o
-obj-$(CONFIG_NET_AIROHA) += airoha_eth.o
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_path.c b/drivers/net/ethernet/mediatek/mtk_eth_path.c
index 7c27a19c4d8f..b4c01e2878f6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_path.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_path.c
@@ -14,7 +14,7 @@
 
 struct mtk_eth_muxc {
 	const char	*name;
-	int		cap_bit;
+	u64		cap_bit;
 	int		(*set_path)(struct mtk_eth *eth, u64 path);
 };
 
@@ -31,6 +31,8 @@ static const char *mtk_eth_path_name(u64 path)
 		return "gmac2_rgmii";
 	case MTK_ETH_PATH_GMAC2_SGMII:
 		return "gmac2_sgmii";
+	case MTK_ETH_PATH_GMAC2_2P5GPHY:
+		return "gmac2_2p5gphy";
 	case MTK_ETH_PATH_GMAC2_GEPHY:
 		return "gmac2_gephy";
 	case MTK_ETH_PATH_GDM1_ESW:
@@ -127,6 +129,29 @@ static int set_mux_u3_gmac2_to_qphy(struct mtk_eth *eth, u64 path)
 	return 0;
 }
 
+static int set_mux_gmac2_to_2p5gphy(struct mtk_eth *eth, u64 path)
+{
+	int ret;
+
+	if (path == MTK_ETH_PATH_GMAC2_2P5GPHY) {
+		ret = regmap_clear_bits(eth->ethsys, ETHSYS_SYSCFG0,
+					SYSCFG0_SGMII_GMAC2_V2);
+		if (ret)
+			return ret;
+
+		/* Setup mux to 2p5g PHY */
+		ret = regmap_clear_bits(eth->infra, TOP_MISC_NETSYS_PCS_MUX,
+					MUX_G2_USXGMII_SEL);
+		if (ret)
+			return ret;
+
+		dev_dbg(eth->dev, "path %s in %s updated\n",
+			mtk_eth_path_name(path), __func__);
+	}
+
+	return 0;
+}
+
 static int set_mux_gmac1_gmac2_to_sgmii_rgmii(struct mtk_eth *eth, u64 path)
 {
 	unsigned int val = 0;
@@ -210,6 +235,10 @@ static const struct mtk_eth_muxc mtk_eth_muxc[] = {
 		.cap_bit = MTK_ETH_MUX_U3_GMAC2_TO_QPHY,
 		.set_path = set_mux_u3_gmac2_to_qphy,
 	}, {
+		.name = "mux_gmac2_to_2p5gphy",
+		.cap_bit = MTK_ETH_MUX_GMAC2_TO_2P5GPHY,
+		.set_path = set_mux_gmac2_to_2p5gphy,
+	}, {
 		.name = "mux_gmac1_gmac2_to_sgmii_rgmii",
 		.cap_bit = MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII,
 		.set_path = set_mux_gmac1_gmac2_to_sgmii_rgmii,
@@ -260,6 +289,20 @@ int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id)
 	return mtk_eth_mux_setup(eth, path);
 }
 
+int mtk_gmac_2p5gphy_path_setup(struct mtk_eth *eth, int mac_id)
+{
+	u64 path = 0;
+
+	if (mac_id == MTK_GMAC2_ID)
+		path = MTK_ETH_PATH_GMAC2_2P5GPHY;
+
+	if (!path)
+		return -EINVAL;
+
+	/* Setup proper MUXes along the path */
+	return mtk_eth_mux_setup(eth, path);
+}
+
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id)
 {
 	u64 path = 0;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 53485142938c..b38e4f2de674 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -269,12 +269,8 @@ static const char * const mtk_clks_source_name[] = {
 	"ethwarp_wocpu2",
 	"ethwarp_wocpu1",
 	"ethwarp_wocpu0",
-	"top_usxgmii0_sel",
-	"top_usxgmii1_sel",
 	"top_sgm0_sel",
 	"top_sgm1_sel",
-	"top_xfi_phy0_xtal_sel",
-	"top_xfi_phy1_xtal_sel",
 	"top_eth_gmii_sel",
 	"top_eth_refck_50m_sel",
 	"top_eth_sys_200m_sel",
@@ -507,7 +503,7 @@ static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth,
 static void mtk_setup_bridge_switch(struct mtk_eth *eth)
 {
 	/* Force Port1 XGMAC Link Up */
-	mtk_m32(eth, 0, MTK_XGMAC_FORCE_LINK(MTK_GMAC1_ID),
+	mtk_m32(eth, 0, MTK_XGMAC_FORCE_MODE(MTK_GMAC1_ID),
 		MTK_XGMAC_STS(MTK_GMAC1_ID));
 
 	/* Adjust GSW bridge IPG to 11 */
@@ -536,6 +532,26 @@ static struct phylink_pcs *mtk_mac_select_pcs(struct phylink_config *config,
 	return NULL;
 }
 
+static int mtk_mac_prepare(struct phylink_config *config, unsigned int mode,
+			   phy_interface_t iface)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+
+	if (mtk_interface_mode_is_xgmii(eth, iface) &&
+	    mac->id != MTK_GMAC1_ID) {
+		mtk_m32(mac->hw, XMAC_MCR_TRX_DISABLE,
+			XMAC_MCR_TRX_DISABLE, MTK_XMAC_MCR(mac->id));
+
+		mtk_m32(mac->hw, MTK_XGMAC_FORCE_MODE(mac->id) |
+				 MTK_XGMAC_FORCE_LINK(mac->id),
+			MTK_XGMAC_FORCE_MODE(mac->id), MTK_XGMAC_STS(mac->id));
+	}
+
+	return 0;
+}
+
 static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 			   const struct phylink_link_state *state)
 {
@@ -577,6 +593,12 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 			}
 			break;
 		case PHY_INTERFACE_MODE_INTERNAL:
+			if (mac->id == MTK_GMAC2_ID &&
+			    MTK_HAS_CAPS(eth->soc->caps, MTK_2P5GPHY)) {
+				err = mtk_gmac_2p5gphy_path_setup(eth, mac->id);
+				if (err)
+					goto init_err;
+			}
 			break;
 		default:
 			goto err_phy;
@@ -648,12 +670,12 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 	}
 
 	/* Setup gmac */
-	if (mtk_is_netsys_v3_or_greater(eth) &&
-	    mac->interface == PHY_INTERFACE_MODE_INTERNAL) {
+	if (mtk_interface_mode_is_xgmii(eth, state->interface)) {
 		mtk_w32(mac->hw, MTK_GDMA_XGDM_SEL, MTK_GDMA_EG_CTRL(mac->id));
 		mtk_w32(mac->hw, MAC_MCR_FORCE_LINK_DOWN, MTK_MAC_MCR(mac->id));
 
-		mtk_setup_bridge_switch(eth);
+		if (mac->id == MTK_GMAC1_ID)
+			mtk_setup_bridge_switch(eth);
 	}
 
 	return;
@@ -700,10 +722,19 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode,
 {
 	struct mtk_mac *mac = container_of(config, struct mtk_mac,
 					   phylink_config);
-	u32 mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
 
-	mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK);
-	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
+	if (!mtk_interface_mode_is_xgmii(mac->hw, interface)) {
+		/* GMAC modes */
+		mtk_m32(mac->hw,
+			MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK, 0,
+			MTK_MAC_MCR(mac->id));
+	} else if (mac->id != MTK_GMAC1_ID) {
+		/* XGMAC except for built-in switch */
+		mtk_m32(mac->hw, XMAC_MCR_TRX_DISABLE, XMAC_MCR_TRX_DISABLE,
+			MTK_XMAC_MCR(mac->id));
+		mtk_m32(mac->hw, MTK_XGMAC_FORCE_LINK(mac->id), 0,
+			MTK_XGMAC_STS(mac->id));
+	}
 }
 
 static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
@@ -734,7 +765,7 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 		case SPEED_100:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 103) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3);
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
 			break;
 		case SPEED_1000:
@@ -757,13 +788,13 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 		case SPEED_100:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5);
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
 			break;
 		case SPEED_1000:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 10) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 6) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 10);
 			break;
 		default:
@@ -775,13 +806,12 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 	mtk_w32(eth, val, soc->reg_map->qdma.qtx_sch + ofs);
 }
 
-static void mtk_mac_link_up(struct phylink_config *config,
-			    struct phy_device *phy,
-			    unsigned int mode, phy_interface_t interface,
-			    int speed, int duplex, bool tx_pause, bool rx_pause)
+static void mtk_gdm_mac_link_up(struct mtk_mac *mac,
+				struct phy_device *phy,
+				unsigned int mode, phy_interface_t interface,
+				int speed, int duplex, bool tx_pause,
+				bool rx_pause)
 {
-	struct mtk_mac *mac = container_of(config, struct mtk_mac,
-					   phylink_config);
 	u32 mcr;
 
 	mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
@@ -815,32 +845,145 @@ static void mtk_mac_link_up(struct phylink_config *config,
 	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
 }
 
+static void mtk_xgdm_mac_link_up(struct mtk_mac *mac,
+				 struct phy_device *phy,
+				 unsigned int mode, phy_interface_t interface,
+				 int speed, int duplex, bool tx_pause,
+				 bool rx_pause)
+{
+	u32 mcr;
+
+	if (mac->id == MTK_GMAC1_ID)
+		return;
+
+	/* Eliminate the interference(before link-up) caused by PHY noise */
+	mtk_m32(mac->hw, XMAC_LOGIC_RST, 0, MTK_XMAC_LOGIC_RST(mac->id));
+	mdelay(20);
+	mtk_m32(mac->hw, XMAC_GLB_CNTCLR, XMAC_GLB_CNTCLR,
+		MTK_XMAC_CNT_CTRL(mac->id));
+
+	mtk_m32(mac->hw, MTK_XGMAC_FORCE_LINK(mac->id),
+		MTK_XGMAC_FORCE_LINK(mac->id), MTK_XGMAC_STS(mac->id));
+
+	mcr = mtk_r32(mac->hw, MTK_XMAC_MCR(mac->id));
+	mcr &= ~(XMAC_MCR_FORCE_TX_FC | XMAC_MCR_FORCE_RX_FC |
+		 XMAC_MCR_TRX_DISABLE);
+	/* Configure pause modes -
+	 * phylink will avoid these for half duplex
+	 */
+	if (tx_pause)
+		mcr |= XMAC_MCR_FORCE_TX_FC;
+	if (rx_pause)
+		mcr |= XMAC_MCR_FORCE_RX_FC;
+
+	mtk_w32(mac->hw, mcr, MTK_XMAC_MCR(mac->id));
+}
+
+static void mtk_mac_link_up(struct phylink_config *config,
+			    struct phy_device *phy,
+			    unsigned int mode, phy_interface_t interface,
+			    int speed, int duplex, bool tx_pause, bool rx_pause)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+
+	if (mtk_interface_mode_is_xgmii(mac->hw, interface))
+		mtk_xgdm_mac_link_up(mac, phy, mode, interface, speed, duplex,
+				     tx_pause, rx_pause);
+	else
+		mtk_gdm_mac_link_up(mac, phy, mode, interface, speed, duplex,
+				    tx_pause, rx_pause);
+}
+
+static void mtk_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+
+	mtk_m32(eth, MAC_MCR_EEE100M | MAC_MCR_EEE1G, 0, MTK_MAC_MCR(mac->id));
+}
+
+static int mtk_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				 bool tx_clk_stop)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+	u32 val;
+
+	if (mtk_interface_mode_is_xgmii(eth, mac->interface))
+		return -EOPNOTSUPP;
+
+	/* Tx idle timer in ms */
+	timer = DIV_ROUND_UP(timer, 1000);
+
+	/* If the timer is zero, then set LPI_MODE, which allows the
+	 * system to enter LPI mode immediately rather than waiting for
+	 * the LPI threshold.
+	 */
+	if (!timer)
+		val = MAC_EEE_LPI_MODE;
+	else if (FIELD_FIT(MAC_EEE_LPI_TXIDLE_THD, timer))
+		val = FIELD_PREP(MAC_EEE_LPI_TXIDLE_THD, timer);
+	else
+		val = MAC_EEE_LPI_TXIDLE_THD;
+
+	if (tx_clk_stop)
+		val |= MAC_EEE_CKG_TXIDLE;
+
+	/* PHY Wake-up time, this field does not have a reset value, so use the
+	 * reset value from MT7531 (36us for 100M and 17us for 1000M).
+	 */
+	val |= FIELD_PREP(MAC_EEE_WAKEUP_TIME_1000, 17) |
+	       FIELD_PREP(MAC_EEE_WAKEUP_TIME_100, 36);
+
+	mtk_w32(eth, val, MTK_MAC_EEECR(mac->id));
+	mtk_m32(eth, 0, MAC_MCR_EEE100M | MAC_MCR_EEE1G, MTK_MAC_MCR(mac->id));
+
+	return 0;
+}
+
 static const struct phylink_mac_ops mtk_phylink_ops = {
+	.mac_prepare = mtk_mac_prepare,
 	.mac_select_pcs = mtk_mac_select_pcs,
 	.mac_config = mtk_mac_config,
 	.mac_finish = mtk_mac_finish,
 	.mac_link_down = mtk_mac_link_down,
 	.mac_link_up = mtk_mac_link_up,
+	.mac_disable_tx_lpi = mtk_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = mtk_mac_enable_tx_lpi,
 };
 
+static void mtk_mdio_config(struct mtk_eth *eth)
+{
+	u32 val;
+
+	/* Configure MDC Divider */
+	val = FIELD_PREP(PPSC_MDC_CFG, eth->mdc_divider);
+
+	/* Configure MDC Turbo Mode */
+	if (mtk_is_netsys_v3_or_greater(eth))
+		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
+	else
+		val |= PPSC_MDC_TURBO;
+
+	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
+}
+
 static int mtk_mdio_init(struct mtk_eth *eth)
 {
-	unsigned int max_clk = 2500000, divider;
+	unsigned int max_clk = 2500000;
 	struct device_node *mii_np;
 	int ret;
 	u32 val;
 
-	mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus");
+	mii_np = of_get_available_child_by_name(eth->dev->of_node, "mdio-bus");
 	if (!mii_np) {
 		dev_err(eth->dev, "no %s child node found", "mdio-bus");
 		return -ENODEV;
 	}
 
-	if (!of_device_is_available(mii_np)) {
-		ret = -ENODEV;
-		goto err_put_node;
-	}
-
 	eth->mii_bus = devm_mdiobus_alloc(eth->dev);
 	if (!eth->mii_bus) {
 		ret = -ENOMEM;
@@ -865,20 +1008,9 @@ static int mtk_mdio_init(struct mtk_eth *eth)
 		}
 		max_clk = val;
 	}
-	divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
-
-	/* Configure MDC Turbo Mode */
-	if (mtk_is_netsys_v3_or_greater(eth))
-		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
-
-	/* Configure MDC Divider */
-	val = FIELD_PREP(PPSC_MDC_CFG, divider);
-	if (!mtk_is_netsys_v3_or_greater(eth))
-		val |= PPSC_MDC_TURBO;
-	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
-
-	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / divider);
-
+	eth->mdc_divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
+	mtk_mdio_config(eth);
+	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / eth->mdc_divider);
 	ret = of_mdiobus_register(eth->mii_bus, mii_np);
 
 err_put_node:
@@ -2079,7 +2211,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		if (ring->page_pool) {
 			struct page *page = virt_to_head_page(data);
 			struct xdp_buff xdp;
-			u32 ret;
+			u32 ret, metasize;
 
 			new_data = mtk_page_pool_get_buff(ring->page_pool,
 							  &dma_addr,
@@ -2095,7 +2227,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 
 			xdp_init_buff(&xdp, PAGE_SIZE, &ring->xdp_q);
 			xdp_prepare_buff(&xdp, data, MTK_PP_HEADROOM, pktlen,
-					 false);
+					 true);
 			xdp_buff_clear_frags_flag(&xdp);
 
 			ret = mtk_xdp_run(eth, ring, &xdp, netdev);
@@ -2115,6 +2247,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 
 			skb_reserve(skb, xdp.data - xdp.data_hard_start);
 			skb_put(skb, xdp.data_end - xdp.data);
+			metasize = xdp.data - xdp.data_meta;
+			if (metasize)
+				skb_metadata_set(skb, metasize);
 			skb_mark_for_recycle(skb);
 		} else {
 			if (ring->frag_size <= PAGE_SIZE)
@@ -2201,14 +2336,18 @@ skip_rx:
 		ring->data[idx] = new_data;
 		rxd->rxd1 = (unsigned int)dma_addr;
 release_desc:
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
+			if (unlikely(dma_addr == DMA_MAPPING_ERROR))
+				addr64 = FIELD_GET(RX_DMA_ADDR64_MASK,
+						   rxd->rxd2);
+			else
+				addr64 = RX_DMA_PREP_ADDR64(dma_addr);
+		}
+
 		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 			rxd->rxd2 = RX_DMA_LSO;
 		else
-			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
-
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA) &&
-		    likely(dma_addr != DMA_MAPPING_ERROR))
-			rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
+			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size) | addr64;
 
 		ring->calc_idx = idx;
 		done++;
@@ -3135,11 +3274,19 @@ static int mtk_dma_init(struct mtk_eth *eth)
 static void mtk_dma_free(struct mtk_eth *eth)
 {
 	const struct mtk_soc_data *soc = eth->soc;
-	int i;
+	int i, j, txqs = 1;
+
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
+		txqs = MTK_QDMA_NUM_QUEUES;
+
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
+		if (!eth->netdev[i])
+			continue;
+
+		for (j = 0; j < txqs; j++)
+			netdev_tx_reset_subqueue(eth->netdev[i], j);
+	}
 
-	for (i = 0; i < MTK_MAX_DEVS; i++)
-		if (eth->netdev[i])
-			netdev_reset_queue(eth->netdev[i]);
 	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) {
 		dma_free_coherent(eth->dma_dev,
 				  MTK_QDMA_RING_SIZE * soc->tx.desc_size,
@@ -3269,7 +3416,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
 		if (mtk_is_netsys_v2_or_greater(eth))
 			val |= MTK_MUTLI_CNT | MTK_RESV_BUF |
 			       MTK_WCOMP_EN | MTK_DMAD_WR_WDONE |
-			       MTK_CHK_DDONE_EN | MTK_LEAKY_BUCKET_EN;
+			       MTK_CHK_DDONE_EN;
 		else
 			val |= MTK_RX_BT_32DWORDS;
 		mtk_w32(eth, val, reg_map->qdma.glo_cfg);
@@ -3414,9 +3561,6 @@ static int mtk_open(struct net_device *dev)
 			}
 			mtk_gdm_config(eth, target_mac->id, gdm_config);
 		}
-		/* Reset and enable PSE */
-		mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
-		mtk_w32(eth, 0, MTK_RST_GL);
 
 		napi_enable(&eth->tx_napi);
 		napi_enable(&eth->rx_napi);
@@ -3928,6 +4072,10 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	else
 		mtk_hw_reset(eth);
 
+	/* No MT7628/88 support yet */
+	if (reset && !MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
+		mtk_mdio_config(eth);
+
 	if (mtk_is_netsys_v3_or_greater(eth)) {
 		/* Set FE to PDMAv2 if necessary */
 		val = mtk_r32(eth, MTK_FE_GLO_MISC);
@@ -3988,11 +4136,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
 	if (mtk_is_netsys_v3_or_greater(eth)) {
-		/* PSE should not drop port1, port8 and port9 packets */
-		mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+		/* PSE dummy page mechanism */
+		mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) |
+			PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ);
+
+		/* PSE free buffer drop threshold */
+		mtk_w32(eth, 0x00600009, PSE_IQ_REV(8));
+
+		/* PSE should not drop port8, port9 and port13 packets from
+		 * WDMA Tx
+		 */
+		mtk_w32(eth, 0x00002300, PSE_DROP_CFG);
+
+		/* PSE should drop packets to port8, port9 and port13 on WDMA Rx
+		 * ring full
+		 */
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2));
 
 		/* GDM and CDM Threshold */
-		mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+		mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES);
 		mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);
 
 		/* Disable GDM1 RX CRC stripping */
@@ -4009,7 +4173,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 		mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
 
 		/* PSE should drop packets to port 8/9 on WDMA Rx ring full */
-		mtk_w32(eth, 0x00000300, PSE_PPE0_DROP);
+		mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0));
 
 		/* PSE Free Queue Flow Control  */
 		mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2);
@@ -4474,6 +4638,20 @@ static int mtk_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 	return phylink_ethtool_set_pauseparam(mac->phylink, pause);
 }
 
+static int mtk_get_eee(struct net_device *dev, struct ethtool_keee *eee)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+
+	return phylink_ethtool_get_eee(mac->phylink, eee);
+}
+
+static int mtk_set_eee(struct net_device *dev, struct ethtool_keee *eee)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+
+	return phylink_ethtool_set_eee(mac->phylink, eee);
+}
+
 static u16 mtk_select_queue(struct net_device *dev, struct sk_buff *skb,
 			    struct net_device *sb_dev)
 {
@@ -4506,6 +4684,8 @@ static const struct ethtool_ops mtk_ethtool_ops = {
 	.set_pauseparam		= mtk_set_pauseparam,
 	.get_rxnfc		= mtk_get_rxnfc,
 	.set_rxnfc		= mtk_set_rxnfc,
+	.get_eee		= mtk_get_eee,
+	.set_eee		= mtk_set_eee,
 };
 
 static const struct net_device_ops mtk_netdev_ops = {
@@ -4615,6 +4795,9 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	mac->phylink_config.type = PHYLINK_NETDEV;
 	mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD;
+	mac->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD |
+		MAC_2500FD;
+	mac->phylink_config.lpi_timer_default = 1000;
 
 	/* MT7623 gmac0 is now missing its speed-specific PLL configuration
 	 * in its .mac_config method (since state->speed is not valid there.
@@ -4653,7 +4836,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	}
 
 	if (mtk_is_netsys_v3_or_greater(mac->hw) &&
-	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW_BIT) &&
+	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW) &&
 	    id == MTK_GMAC1_ID) {
 		mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
 						       MAC_SYM_PAUSE |
@@ -4673,6 +4856,11 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 
 	mac->phylink = phylink;
 
+	if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_2P5GPHY) &&
+	    id == MTK_GMAC2_ID)
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  mac->phylink_config.supported_interfaces);
+
 	SET_NETDEV_DEV(eth->netdev[id], eth->dev);
 	eth->netdev[id]->watchdog_timeo = 5 * HZ;
 	eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 0d5225f1d3ee..6f72a8c8ae1e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -151,7 +151,15 @@
 #define PSE_FQFC_CFG1		0x100
 #define PSE_FQFC_CFG2		0x104
 #define PSE_DROP_CFG		0x108
-#define PSE_PPE0_DROP		0x110
+#define PSE_PPE_DROP(x)		(0x110 + ((x) * 0x4))
+
+/* PSE Last FreeQ Page Request Control */
+#define PSE_DUMY_REQ		0x10C
+/* PSE_DUMY_REQ is not a typo but actually called like that also in
+ * MediaTek's datasheet
+ */
+#define PSE_DUMMY_WORK_GDM(x)	BIT(16 + (x))
+#define DUMMY_PAGE_THR		0x1
 
 /* PSE Input Queue Reservation Register*/
 #define PSE_IQ_REV(x)		(0x140 + (((x) - 1) << 2))
@@ -423,7 +431,8 @@
 
 /* XMAC status registers */
 #define MTK_XGMAC_STS(x)	(((x) == MTK_GMAC3_ID) ? 0x1001C : 0x1000C)
-#define MTK_XGMAC_FORCE_LINK(x)	(((x) == MTK_GMAC2_ID) ? BIT(31) : BIT(15))
+#define MTK_XGMAC_FORCE_MODE(x)	(((x) == MTK_GMAC2_ID) ? BIT(31) : BIT(15))
+#define MTK_XGMAC_FORCE_LINK(x)	(((x) == MTK_GMAC2_ID) ? BIT(27) : BIT(11))
 #define MTK_USXGMII_PCS_LINK	BIT(8)
 #define MTK_XGMAC_RX_FC		BIT(5)
 #define MTK_XGMAC_TX_FC		BIT(4)
@@ -453,6 +462,8 @@
 #define MAC_MCR_RX_FIFO_CLR_DIS	BIT(12)
 #define MAC_MCR_BACKOFF_EN	BIT(9)
 #define MAC_MCR_BACKPR_EN	BIT(8)
+#define MAC_MCR_EEE1G		BIT(7)
+#define MAC_MCR_EEE100M		BIT(6)
 #define MAC_MCR_FORCE_RX_FC	BIT(5)
 #define MAC_MCR_FORCE_TX_FC	BIT(4)
 #define MAC_MCR_SPEED_1000	BIT(3)
@@ -461,6 +472,15 @@
 #define MAC_MCR_FORCE_LINK	BIT(0)
 #define MAC_MCR_FORCE_LINK_DOWN	(MAC_MCR_FORCE_MODE)
 
+/* Mac EEE control registers */
+#define MTK_MAC_EEECR(x)		(0x10104 + (x * 0x100))
+#define MAC_EEE_WAKEUP_TIME_1000	GENMASK(31, 24)
+#define MAC_EEE_WAKEUP_TIME_100		GENMASK(23, 16)
+#define MAC_EEE_LPI_TXIDLE_THD		GENMASK(15, 8)
+#define MAC_EEE_CKG_TXIDLE		BIT(3)
+#define MAC_EEE_CKG_RXLPI		BIT(2)
+#define MAC_EEE_LPI_MODE		BIT(0)
+
 /* Mac status registers */
 #define MTK_MAC_MSR(x)		(0x10108 + (x * 0x100))
 #define MAC_MSR_EEE1G		BIT(7)
@@ -505,6 +525,21 @@
 #define INTF_MODE_RGMII_1000    (TRGMII_MODE | TRGMII_CENTRAL_ALIGNED)
 #define INTF_MODE_RGMII_10_100  0
 
+/* XFI Mac control registers */
+#define MTK_XMAC_BASE(x)	(0x12000 + (((x) - 1) * 0x1000))
+#define MTK_XMAC_MCR(x)		(MTK_XMAC_BASE(x))
+#define XMAC_MCR_TRX_DISABLE	0xf
+#define XMAC_MCR_FORCE_TX_FC	BIT(5)
+#define XMAC_MCR_FORCE_RX_FC	BIT(4)
+
+/* XFI Mac logic reset registers */
+#define MTK_XMAC_LOGIC_RST(x)	(MTK_XMAC_BASE(x) + 0x10)
+#define XMAC_LOGIC_RST		BIT(0)
+
+/* XFI Mac count global control */
+#define MTK_XMAC_CNT_CTRL(x)	(MTK_XMAC_BASE(x) + 0x100)
+#define XMAC_GLB_CNTCLR		BIT(0)
+
 /* GPIO port control registers for GMAC 2*/
 #define GPIO_OD33_CTRL8		0x4c0
 #define GPIO_BIAS_CTRL		0xed0
@@ -568,6 +603,10 @@
 #define GEPHY_MAC_SEL          BIT(1)
 
 /* Top misc registers */
+#define TOP_MISC_NETSYS_PCS_MUX	0x0
+#define NETSYS_PCS_MUX_MASK	GENMASK(1, 0)
+#define MUX_G2_USXGMII_SEL	BIT(1)
+
 #define USB_PHY_SWITCH_REG	0x218
 #define QPHY_SEL_MASK		GENMASK(1, 0)
 #define SGMII_QPHY_SEL		0x2
@@ -932,6 +971,7 @@ enum mkt_eth_capabilities {
 	MTK_RGMII_BIT = 0,
 	MTK_TRGMII_BIT,
 	MTK_SGMII_BIT,
+	MTK_2P5GPHY_BIT,
 	MTK_ESW_BIT,
 	MTK_GEPHY_BIT,
 	MTK_MUX_BIT,
@@ -952,6 +992,7 @@ enum mkt_eth_capabilities {
 	MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT,
 	MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT,
 	MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT,
+	MTK_ETH_MUX_GMAC2_TO_2P5GPHY_BIT,
 	MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT,
 	MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII_BIT,
 
@@ -961,6 +1002,7 @@ enum mkt_eth_capabilities {
 	MTK_ETH_PATH_GMAC1_SGMII_BIT,
 	MTK_ETH_PATH_GMAC2_RGMII_BIT,
 	MTK_ETH_PATH_GMAC2_SGMII_BIT,
+	MTK_ETH_PATH_GMAC2_2P5GPHY_BIT,
 	MTK_ETH_PATH_GMAC2_GEPHY_BIT,
 	MTK_ETH_PATH_GDM1_ESW_BIT,
 };
@@ -969,6 +1011,7 @@ enum mkt_eth_capabilities {
 #define MTK_RGMII		BIT_ULL(MTK_RGMII_BIT)
 #define MTK_TRGMII		BIT_ULL(MTK_TRGMII_BIT)
 #define MTK_SGMII		BIT_ULL(MTK_SGMII_BIT)
+#define MTK_2P5GPHY		BIT_ULL(MTK_2P5GPHY_BIT)
 #define MTK_ESW			BIT_ULL(MTK_ESW_BIT)
 #define MTK_GEPHY		BIT_ULL(MTK_GEPHY_BIT)
 #define MTK_MUX			BIT_ULL(MTK_MUX_BIT)
@@ -991,6 +1034,8 @@ enum mkt_eth_capabilities {
 	BIT_ULL(MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT)
 #define MTK_ETH_MUX_U3_GMAC2_TO_QPHY		\
 	BIT_ULL(MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT)
+#define MTK_ETH_MUX_GMAC2_TO_2P5GPHY		\
+	BIT_ULL(MTK_ETH_MUX_GMAC2_TO_2P5GPHY_BIT)
 #define MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII	\
 	BIT_ULL(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT)
 #define MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII	\
@@ -1002,6 +1047,7 @@ enum mkt_eth_capabilities {
 #define MTK_ETH_PATH_GMAC1_SGMII	BIT_ULL(MTK_ETH_PATH_GMAC1_SGMII_BIT)
 #define MTK_ETH_PATH_GMAC2_RGMII	BIT_ULL(MTK_ETH_PATH_GMAC2_RGMII_BIT)
 #define MTK_ETH_PATH_GMAC2_SGMII	BIT_ULL(MTK_ETH_PATH_GMAC2_SGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_2P5GPHY	BIT_ULL(MTK_ETH_PATH_GMAC2_2P5GPHY_BIT)
 #define MTK_ETH_PATH_GMAC2_GEPHY	BIT_ULL(MTK_ETH_PATH_GMAC2_GEPHY_BIT)
 #define MTK_ETH_PATH_GDM1_ESW		BIT_ULL(MTK_ETH_PATH_GDM1_ESW_BIT)
 
@@ -1011,6 +1057,7 @@ enum mkt_eth_capabilities {
 #define MTK_GMAC2_RGMII		(MTK_ETH_PATH_GMAC2_RGMII | MTK_RGMII)
 #define MTK_GMAC2_SGMII		(MTK_ETH_PATH_GMAC2_SGMII | MTK_SGMII)
 #define MTK_GMAC2_GEPHY		(MTK_ETH_PATH_GMAC2_GEPHY | MTK_GEPHY)
+#define MTK_GMAC2_2P5GPHY	(MTK_ETH_PATH_GMAC2_2P5GPHY | MTK_2P5GPHY)
 #define MTK_GDM1_ESW		(MTK_ETH_PATH_GDM1_ESW | MTK_ESW)
 
 /* MUXes present on SoCs */
@@ -1030,6 +1077,10 @@ enum mkt_eth_capabilities {
 	(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII | MTK_MUX | \
 	MTK_SHARED_SGMII)
 
+/* 2: GMAC2 -> 2P5GPHY */
+#define MTK_MUX_GMAC2_TO_2P5GPHY      \
+	(MTK_ETH_MUX_GMAC2_TO_2P5GPHY | MTK_MUX | MTK_INFRA)
+
 /* 0: GMACx -> GEPHY, 1: GMACx -> SGMII where x is 1 or 2 */
 #define MTK_MUX_GMAC12_TO_GEPHY_SGMII   \
 	(MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII | MTK_MUX)
@@ -1065,8 +1116,9 @@ enum mkt_eth_capabilities {
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
 		      MTK_RSTCTRL_PPE1 | MTK_SRAM)
 
-#define MT7988_CAPS  (MTK_36BIT_DMA | MTK_GDM1_ESW | MTK_QDMA | \
-		      MTK_RSTCTRL_PPE1 | MTK_RSTCTRL_PPE2 | MTK_SRAM)
+#define MT7988_CAPS  (MTK_36BIT_DMA | MTK_GDM1_ESW | MTK_GMAC2_2P5GPHY | \
+		      MTK_MUX_GMAC2_TO_2P5GPHY | MTK_QDMA | MTK_RSTCTRL_PPE1 | \
+		      MTK_RSTCTRL_PPE2 | MTK_SRAM)
 
 struct mtk_tx_dma_desc_info {
 	dma_addr_t	addr;
@@ -1126,7 +1178,7 @@ struct mtk_reg_map {
 };
 
 /* struct mtk_eth_data -	This is the structure holding all differences
- *				among various plaforms
+ *				among various platforms
  * @reg_map			Soc register map.
  * @ana_rgc3:                   The offset for register ANA_RGC3 related to
  *				sgmiisys syscon
@@ -1226,7 +1278,7 @@ struct mtk_soc_data {
  * @mii_bus:		If there is a bus we need to create an instance for it
  * @pending_work:	The workqueue used to reset the dma ring
  * @state:		Initialization and runtime state of the device
- * @soc:		Holding specific data among vaious SoCs
+ * @soc:		Holding specific data among various SoCs
  */
 
 struct mtk_eth {
@@ -1260,6 +1312,7 @@ struct mtk_eth {
 	struct clk			*clks[MTK_CLK_MAX];
 
 	struct mii_bus			*mii_bus;
+	unsigned int			mdc_divider;
 	struct work_struct		pending_work;
 	unsigned long			state;
 
@@ -1417,6 +1470,23 @@ static inline u32 mtk_get_ib2_multicast_mask(struct mtk_eth *eth)
 	return MTK_FOE_IB2_MULTICAST;
 }
 
+static inline bool mtk_interface_mode_is_xgmii(struct mtk_eth *eth,
+					       phy_interface_t interface)
+{
+	if (!mtk_is_netsys_v3_or_greater(eth))
+		return false;
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_INTERNAL:
+	case PHY_INTERFACE_MODE_USXGMII:
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_5GBASER:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* read the hardware status register */
 void mtk_stats_update_mac(struct mtk_mac *mac);
 
@@ -1425,6 +1495,7 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg);
 u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned int reg);
 
 int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id);
+int mtk_gmac_2p5gphy_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id);
 
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index f20bb390df3a..c855fb799ce1 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -34,8 +34,10 @@ struct mtk_flow_data {
 	u16 vlan_in;
 
 	struct {
-		u16 id;
-		__be16 proto;
+		struct {
+			u16 id;
+			__be16 proto;
+		} vlans[2];
 		u8 num;
 	} vlan;
 	struct {
@@ -349,18 +351,19 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 		case FLOW_ACTION_CSUM:
 			break;
 		case FLOW_ACTION_VLAN_PUSH:
-			if (data.vlan.num == 1 ||
+			if (data.vlan.num + data.pppoe.num == 2 ||
 			    act->vlan.proto != htons(ETH_P_8021Q))
 				return -EOPNOTSUPP;
 
-			data.vlan.id = act->vlan.vid;
-			data.vlan.proto = act->vlan.proto;
+			data.vlan.vlans[data.vlan.num].id = act->vlan.vid;
+			data.vlan.vlans[data.vlan.num].proto = act->vlan.proto;
 			data.vlan.num++;
 			break;
 		case FLOW_ACTION_VLAN_POP:
 			break;
 		case FLOW_ACTION_PPPOE_PUSH:
-			if (data.pppoe.num == 1)
+			if (data.pppoe.num == 1 ||
+			    data.vlan.num == 2)
 				return -EOPNOTSUPP;
 
 			data.pppoe.sid = act->pppoe.sid;
@@ -450,12 +453,9 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 	if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE)
 		foe.bridge.vlan = data.vlan_in;
 
-	if (data.vlan.num == 1) {
-		if (data.vlan.proto != htons(ETH_P_8021Q))
-			return -EOPNOTSUPP;
+	for (i = 0; i < data.vlan.num; i++)
+		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.vlans[i].id);
 
-		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.id);
-	}
 	if (data.pppoe.num == 1)
 		mtk_foe_entry_set_pppoe(eth, &foe, data.pppoe.sid);
 
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 25989c79c92e..b83886a41121 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1163,6 +1163,7 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 	struct net_device *ndev = priv->ndev;
 	unsigned int head = ring->head;
 	unsigned int entry = ring->tail;
+	unsigned long flags;
 
 	while (entry != head && count < (MTK_STAR_RING_NUM_DESCS - 1)) {
 		ret = mtk_star_tx_complete_one(priv);
@@ -1182,9 +1183,9 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 		netif_wake_queue(ndev);
 
 	if (napi_complete(napi)) {
-		spin_lock(&priv->lock);
+		spin_lock_irqsave(&priv->lock, flags);
 		mtk_star_enable_dma_irq(priv, false, true);
-		spin_unlock(&priv->lock);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
 	return 0;
@@ -1341,16 +1342,16 @@ push_new_skb:
 static int mtk_star_rx_poll(struct napi_struct *napi, int budget)
 {
 	struct mtk_star_priv *priv;
+	unsigned long flags;
 	int work_done = 0;
 
 	priv = container_of(napi, struct mtk_star_priv, rx_napi);
 
 	work_done = mtk_star_rx(priv, budget);
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
-		spin_lock(&priv->lock);
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		spin_lock_irqsave(&priv->lock, flags);
 		mtk_star_enable_dma_irq(priv, true, false);
-		spin_unlock(&priv->lock);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
 	return work_done;
@@ -1427,15 +1428,10 @@ static int mtk_star_mdio_init(struct net_device *ndev)
 
 	of_node = dev->of_node;
 
-	mdio_node = of_get_child_by_name(of_node, "mdio");
+	mdio_node = of_get_available_child_by_name(of_node, "mdio");
 	if (!mdio_node)
 		return -ENODEV;
 
-	if (!of_device_is_available(mdio_node)) {
-		ret = -ENODEV;
-		goto out_put_node;
-	}
-
 	priv->mii = devm_mdiobus_alloc(dev);
 	if (!priv->mii) {
 		ret = -ENOMEM;
@@ -1467,6 +1463,8 @@ static __maybe_unused int mtk_star_suspend(struct device *dev)
 	if (netif_running(ndev))
 		mtk_star_disable(ndev);
 
+	netif_device_detach(ndev);
+
 	clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 
 	return 0;
@@ -1491,6 +1489,8 @@ static __maybe_unused int mtk_star_resume(struct device *dev)
 			clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 	}
 
+	netif_device_attach(ndev);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index e212a4ba9275..351dd152f4f3 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -2000,7 +2000,7 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask)
 		if (mtk_wed_is_v3_or_greater(dev->hw))
 			wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_TX_TKID_ALI_EN);
 
-		/* initail tx interrupt trigger */
+		/* initial tx interrupt trigger */
 		wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX,
 			MTK_WED_WPDMA_INT_CTRL_TX0_DONE_EN |
 			MTK_WED_WPDMA_INT_CTRL_TX0_DONE_CLR |
@@ -2011,7 +2011,7 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask)
 			FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_TX1_DONE_TRIG,
 				   dev->wlan.tx_tbit[1]));
 
-		/* initail txfree interrupt trigger */
+		/* initial txfree interrupt trigger */
 		wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX_FREE,
 			MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_EN |
 			MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_CLR |
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 825e05fb8607..0b1cb340206f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -7,6 +7,7 @@ config MLX4_EN
 	tristate "Mellanox Technologies 1/10/40Gbit Ethernet support"
 	depends on PCI && NETDEVICES && ETHERNET && INET
 	depends on PTP_1588_CLOCK_OPTIONAL
+	select PAGE_POOL
 	select MLX4_CORE
 	help
 	  This driver supports Mellanox Technologies ConnectX Ethernet
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index b330020dc0d6..07b061a97a6e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -526,28 +526,6 @@ out:
 	return res;
 }
 
-u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones, u32 uid, u32 obj, u32 count)
-{
-	struct mlx4_zone_entry *zone;
-	int res = 0;
-
-	spin_lock(&zones->lock);
-
-	zone = __mlx4_find_zone_by_uid(zones, uid);
-
-	if (NULL == zone) {
-		res = -1;
-		goto out;
-	}
-
-	__mlx4_free_from_zone(zone, obj, count);
-
-out:
-	spin_unlock(&zones->lock);
-
-	return res;
-}
-
 u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count)
 {
 	struct mlx4_zone_entry *zone;
@@ -682,9 +660,9 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
 }
 
 static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir,
-				    struct mlx4_db *db, int order)
+				    struct mlx4_db *db, unsigned int order)
 {
-	int o;
+	unsigned int o;
 	int i;
 
 	for (o = order; o <= 1; ++o) {
@@ -712,7 +690,7 @@ found:
 	return 0;
 }
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_db_pgdir *pgdir;
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 0d8a362c2673..edcc6f662618 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -236,7 +236,7 @@ static void dump_err_buf(struct mlx4_dev *dev)
 
 static void poll_catas(struct timer_list *t)
 {
-	struct mlx4_priv *priv = from_timer(priv, t, catas_err.timer);
+	struct mlx4_priv *priv = timer_container_of(priv, t, catas_err.timer);
 	struct mlx4_dev *dev = &priv->dev;
 	u32 slave_read;
 
@@ -305,7 +305,7 @@ void mlx4_stop_catas_poll(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
-	del_timer_sync(&priv->catas_err.timer);
+	timer_delete_sync(&priv->catas_err.timer);
 
 	if (priv->catas_err.map) {
 		iounmap(priv->catas_err.map);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index cd754cd76bde..d73a2044dc26 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -249,7 +249,7 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 static u32 freq_to_shift(u16 freq)
 {
 	u32 freq_khz = freq * 1000;
-	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles = freq_khz * 1000ULL * MLX4_EN_WRAP_AROUND_SEC;
 	u64 max_val_cycles_rounded = 1ULL << fls64(max_val_cycles - 1);
 	/* calculate max possible multiplier in order to fit in 64bit */
 	u64 max_mul = div64_u64(ULLONG_MAX, max_val_cycles_rounded);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index cd17a3f4faf8..a68cd3f0304c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1897,6 +1897,7 @@ static int mlx4_en_get_ts_info(struct net_device *dev,
 	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) {
 		info->so_timestamping |=
 			SOF_TIMESTAMPING_TX_HARDWARE |
+			SOF_TIMESTAMPING_TX_SOFTWARE |
 			SOF_TIMESTAMPING_RX_HARDWARE |
 			SOF_TIMESTAMPING_RAW_HARDWARE;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 15c57e9517e9..b33285d755b9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -48,60 +48,43 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ip6_checksum.h>
 #endif
+#include <net/page_pool/helpers.h>
 
 #include "mlx4_en.h"
 
-static int mlx4_alloc_page(struct mlx4_en_priv *priv,
-			   struct mlx4_en_rx_alloc *frag,
-			   gfp_t gfp)
-{
-	struct page *page;
-	dma_addr_t dma;
-
-	page = alloc_page(gfp);
-	if (unlikely(!page))
-		return -ENOMEM;
-	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir);
-	if (unlikely(dma_mapping_error(priv->ddev, dma))) {
-		__free_page(page);
-		return -ENOMEM;
-	}
-	frag->page = page;
-	frag->dma = dma;
-	frag->page_offset = priv->rx_headroom;
-	return 0;
-}
-
 static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
 			       struct mlx4_en_rx_ring *ring,
 			       struct mlx4_en_rx_desc *rx_desc,
 			       struct mlx4_en_rx_alloc *frags,
 			       gfp_t gfp)
 {
+	dma_addr_t dma;
 	int i;
 
 	for (i = 0; i < priv->num_frags; i++, frags++) {
 		if (!frags->page) {
-			if (mlx4_alloc_page(priv, frags, gfp)) {
+			frags->page = page_pool_alloc_pages(ring->pp, gfp);
+			if (!frags->page) {
 				ring->alloc_fail++;
 				return -ENOMEM;
 			}
+			page_pool_fragment_page(frags->page, 1);
+			frags->page_offset = priv->rx_headroom;
+
 			ring->rx_alloc_pages++;
 		}
-		rx_desc->data[i].addr = cpu_to_be64(frags->dma +
-						    frags->page_offset);
+		dma = page_pool_get_dma_addr(frags->page);
+		rx_desc->data[i].addr = cpu_to_be64(dma + frags->page_offset);
 	}
 	return 0;
 }
 
 static void mlx4_en_free_frag(const struct mlx4_en_priv *priv,
+			      struct mlx4_en_rx_ring *ring,
 			      struct mlx4_en_rx_alloc *frag)
 {
-	if (frag->page) {
-		dma_unmap_page(priv->ddev, frag->dma,
-			       PAGE_SIZE, priv->dma_dir);
-		__free_page(frag->page);
-	}
+	if (frag->page)
+		page_pool_put_full_page(ring->pp, frag->page, false);
 	/* We need to clear all fields, otherwise a change of priv->log_rx_info
 	 * could lead to see garbage later in frag->page.
 	 */
@@ -141,18 +124,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 		(index << ring->log_stride);
 	struct mlx4_en_rx_alloc *frags = ring->rx_info +
 					(index << priv->log_rx_info);
-	if (likely(ring->page_cache.index > 0)) {
-		/* XDP uses a single page per frame */
-		if (!frags->page) {
-			ring->page_cache.index--;
-			frags->page = ring->page_cache.buf[ring->page_cache.index].page;
-			frags->dma  = ring->page_cache.buf[ring->page_cache.index].dma;
-		}
-		frags->page_offset = XDP_PACKET_HEADROOM;
-		rx_desc->data[0].addr = cpu_to_be64(frags->dma +
-						    XDP_PACKET_HEADROOM);
-		return 0;
-	}
 
 	return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp);
 }
@@ -178,7 +149,7 @@ static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv,
 	frags = ring->rx_info + (index << priv->log_rx_info);
 	for (nr = 0; nr < priv->num_frags; nr++) {
 		en_dbg(DRV, priv, "Freeing fragment:%d\n", nr);
-		mlx4_en_free_frag(priv, frags + nr);
+		mlx4_en_free_frag(priv, ring, frags + nr);
 	}
 }
 
@@ -268,6 +239,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   u32 size, u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct page_pool_params pp = {};
 	struct mlx4_en_rx_ring *ring;
 	int err = -ENOMEM;
 	int tmp;
@@ -286,9 +258,26 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->log_stride = ffs(ring->stride) - 1;
 	ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
 
-	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
+	pp.flags = PP_FLAG_DMA_MAP;
+	pp.pool_size = size * DIV_ROUND_UP(priv->rx_skb_size, PAGE_SIZE);
+	pp.nid = node;
+	pp.napi = &priv->rx_cq[queue_index]->napi;
+	pp.netdev = priv->dev;
+	pp.dev = &mdev->dev->persist->pdev->dev;
+	pp.dma_dir = priv->dma_dir;
+
+	ring->pp = page_pool_create(&pp);
+	if (!ring->pp)
 		goto err_ring;
 
+	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
+		goto err_pp;
+
+	err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_POOL,
+					 ring->pp);
+	if (err)
+		goto err_xdp_info;
+
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
 					sizeof(struct mlx4_en_rx_alloc));
 	ring->rx_info = kvzalloc_node(tmp, GFP_KERNEL, node);
@@ -319,6 +308,8 @@ err_info:
 	ring->rx_info = NULL;
 err_xdp_info:
 	xdp_rxq_info_unreg(&ring->xdp_rxq);
+err_pp:
+	page_pool_destroy(ring->pp);
 err_ring:
 	kfree(ring);
 	*pring = NULL;
@@ -409,26 +400,6 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 	}
 }
 
-/* When the rx ring is running in page-per-packet mode, a released frame can go
- * directly into a small cache, to avoid unmapping or touching the page
- * allocator. In bpf prog performance scenarios, buffers are either forwarded
- * or dropped, never converted to skbs, so every page can come directly from
- * this cache when it is sized to be a multiple of the napi budget.
- */
-bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
-			struct mlx4_en_rx_alloc *frame)
-{
-	struct mlx4_en_page_cache *cache = &ring->page_cache;
-
-	if (cache->index >= MLX4_EN_CACHE_SIZE)
-		return false;
-
-	cache->buf[cache->index].page = frame->page;
-	cache->buf[cache->index].dma = frame->dma;
-	cache->index++;
-	return true;
-}
-
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
@@ -445,6 +416,7 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 	xdp_rxq_info_unreg(&ring->xdp_rxq);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
 	kvfree(ring->rx_info);
+	page_pool_destroy(ring->pp);
 	ring->rx_info = NULL;
 	kfree(ring);
 	*pring = NULL;
@@ -453,14 +425,6 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_rx_ring *ring)
 {
-	int i;
-
-	for (i = 0; i < ring->page_cache.index; i++) {
-		dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma,
-			       PAGE_SIZE, priv->dma_dir);
-		put_page(ring->page_cache.buf[i].page);
-	}
-	ring->page_cache.index = 0;
 	mlx4_en_free_rx_buf(priv, ring);
 	if (ring->stride <= TXBB_SIZE)
 		ring->buf -= TXBB_SIZE;
@@ -487,7 +451,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 		if (unlikely(!page))
 			goto fail;
 
-		dma = frags->dma;
+		dma = page_pool_get_dma_addr(page);
 		dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset,
 					      frag_size, priv->dma_dir);
 
@@ -498,6 +462,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 		if (frag_info->frag_stride == PAGE_SIZE / 2) {
 			frags->page_offset ^= PAGE_SIZE / 2;
 			release = page_count(page) != 1 ||
+				  atomic_long_read(&page->pp_ref_count) != 1 ||
 				  page_is_pfmemalloc(page) ||
 				  page_to_nid(page) != numa_mem_id();
 		} else if (!priv->rx_headroom) {
@@ -511,10 +476,9 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 			release = frags->page_offset + frag_info->frag_size > PAGE_SIZE;
 		}
 		if (release) {
-			dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir);
 			frags->page = NULL;
 		} else {
-			page_ref_inc(page);
+			page_pool_ref_page(page);
 		}
 
 		nr++;
@@ -784,7 +748,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			/* Get pointer to first fragment since we haven't
 			 * skb yet and cast it to ethhdr struct
 			 */
-			dma = frags[0].dma + frags[0].page_offset;
+			dma = page_pool_get_dma_addr(frags[0].page);
+			dma += frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
 						DMA_FROM_DEVICE);
 
@@ -823,7 +788,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			void *orig_data;
 			u32 act;
 
-			dma = frags[0].dma + frags[0].page_offset;
+			dma = page_pool_get_dma_addr(frags[0].page);
+			dma += frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma,
 						priv->frag_info[0].frag_size,
 						DMA_FROM_DEVICE);
@@ -886,6 +852,7 @@ xdp_drop_no_cnt:
 		skb = napi_get_frags(&cq->napi);
 		if (unlikely(!skb))
 			goto next;
+		skb_mark_for_recycle(skb);
 
 		if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) {
 			u64 timestamp = mlx4_en_get_cqe_ts(cqe);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 1ddb11cb25f9..87f35bcbeff8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -44,6 +44,7 @@
 #include <linux/ipv6.h>
 #include <linux/indirect_call_wrapper.h>
 #include <net/ipv6.h>
+#include <net/page_pool/helpers.h>
 
 #include "mlx4_en.h"
 
@@ -350,16 +351,10 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    int napi_mode)
 {
 	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
-	struct mlx4_en_rx_alloc frame = {
-		.page = tx_info->page,
-		.dma = tx_info->map0_dma,
-	};
-
-	if (!napi_mode || !mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
-		dma_unmap_page(priv->ddev, tx_info->map0_dma,
-			       PAGE_SIZE, priv->dma_dir);
-		put_page(tx_info->page);
-	}
+	struct page_pool *pool = ring->recycle_ring->pp;
+
+	/* Note that napi_mode = 0 means ndo_close() path, not budget = 0 */
+	page_pool_put_full_page(pool, tx_info->page, !!napi_mode);
 
 	return tx_info->nr_txbb;
 }
@@ -450,6 +445,8 @@ int mlx4_en_process_tx_cq(struct net_device *dev,
 
 	if (unlikely(!priv->port_up))
 		return 0;
+	if (unlikely(!napi_budget) && cq->type == TX_XDP)
+		return 0;
 
 	netdev_txq_bql_complete_prefetchw(ring->tx_queue);
 
@@ -1194,7 +1191,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 	tx_desc = ring->buf + (index << LOG_TXBB_SIZE);
 	data = &tx_desc->data;
 
-	dma = frame->dma;
+	dma = page_pool_get_dma_addr(frame->page);
 
 	tx_info->page = frame->page;
 	frame->page = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index d7d856d1758a..b213094ea30f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1478,12 +1478,6 @@ void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc);
 u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
 			    int align, u32 skip_mask, u32 *puid);
 
-/* Free <count> objects, start from <obj> of the uid <uid> from zone_allocator
- * <zones>.
- */
-u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones,
-			   u32 uid, u32 obj, u32 count);
-
 /* If <zones> was allocated with MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP, instead of
  * specifying the uid when freeing an object, zone allocator could figure it by
  * itself. Other parameters are similar to mlx4_zone_free.
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 28b70dcc652e..ad0d91a75184 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -247,20 +247,11 @@ struct mlx4_en_tx_desc {
 
 struct mlx4_en_rx_alloc {
 	struct page	*page;
-	dma_addr_t	dma;
 	u32		page_offset;
 };
 
 #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
 
-struct mlx4_en_page_cache {
-	u32 index;
-	struct {
-		struct page	*page;
-		dma_addr_t	dma;
-	} buf[MLX4_EN_CACHE_SIZE];
-};
-
 enum {
 	MLX4_EN_TX_RING_STATE_RECOVERING,
 };
@@ -335,14 +326,14 @@ struct mlx4_en_rx_ring {
 	u16 stride;
 	u16 log_stride;
 	u16 cqn;	/* index of port CQ associated with this ring */
+	u8  fcs_del;
 	u32 prod;
 	u32 cons;
 	u32 buf_size;
-	u8  fcs_del;
+	struct page_pool *pp;
 	void *buf;
 	void *rx_info;
 	struct bpf_prog __rcu *xdp_prog;
-	struct mlx4_en_page_cache page_cache;
 	unsigned long bytes;
 	unsigned long packets;
 	unsigned long csum_ok;
@@ -707,8 +698,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_priv *priv, unsigned int length,
 			       int tx_ind, bool *doorbell_pending);
 void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
-bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
-			struct mlx4_en_rx_alloc *frame);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index d7444782bfdd..698a5d1f0d7e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -106,7 +106,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 	buddy->max_order = max_order;
 	spin_lock_init(&buddy->lock);
 
-	buddy->bits = kcalloc(buddy->max_order + 1, sizeof(long *),
+	buddy->bits = kcalloc(buddy->max_order + 1, sizeof(*buddy->bits),
 			      GFP_KERNEL);
 	buddy->num_free = kcalloc(buddy->max_order + 1, sizeof(*buddy->num_free),
 				  GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 4e43f4a7d246..e3d0b13c1610 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -147,26 +147,6 @@ static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
 	return err;
 }
 
-int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx)
-{
-	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	struct mlx4_mac_table *table = &info->mac_table;
-	int i;
-
-	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
-		if (!table->refs[i])
-			continue;
-
-		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
-			*idx = i;
-			return 0;
-		}
-	}
-
-	return -ENOENT;
-}
-EXPORT_SYMBOL_GPL(mlx4_find_cached_mac);
-
 static bool mlx4_need_mf_bond(struct mlx4_dev *dev)
 {
 	int i, num_eth_ports = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index ea6070180c96..6ec7d6e0181d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -31,6 +31,7 @@ config MLX5_CORE_EN
 	bool "Mellanox 5th generation network adapters (ConnectX series) Ethernet support"
 	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	select PAGE_POOL
+	select PAGE_POOL_STATS
 	select DIMLIB
 	help
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
@@ -80,8 +81,8 @@ config MLX5_BRIDGE
 	default y
 	help
 	  mlx5 ConnectX offloads support for Ethernet Bridging (BRIDGE).
-	  Enable adding representors of mlx5 uplink and VF ports to Bridge and
-	  offloading rules for traffic between such ports. Supports VLANs (trunk and
+	  Enable offloading FDB rules from a bridge device containing
+	  representors of mlx5 uplink and VF ports. Supports VLANs (trunk and
 	  access modes).
 
 config MLX5_CLS_ACT
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index be3d0876c521..d292e6a9e22c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -17,7 +17,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		fs_counters.o fs_ft_pool.o rl.o lag/debugfs.o lag/lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
 		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o diag/reporter_vnic.o \
-		fw_reset.o qos.o lib/tout.o lib/aso.o wc.o
+		fw_reset.o qos.o lib/tout.o lib/aso.o wc.o fs_pool.o
 
 #
 # Netdev basic
@@ -60,6 +60,7 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en/tc/act/act.o en/tc/act/drop.o en/tc/a
 ifneq ($(CONFIG_MLX5_TC_CT),)
 	mlx5_core-y			     += en/tc_ct.o en/tc/ct_fs_dmfs.o
 	mlx5_core-$(CONFIG_MLX5_SW_STEERING) += en/tc/ct_fs_smfs.o
+	mlx5_core-$(CONFIG_MLX5_HW_STEERING) += en/tc/ct_fs_hmfs.o
 endif
 
 mlx5_core-$(CONFIG_MLX5_TC_SAMPLE)   += en/tc/sample.o
@@ -123,6 +124,7 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/sws/dr_domain.o \
 					steering/sws/dr_ste_v0.o \
 					steering/sws/dr_ste_v1.o \
 					steering/sws/dr_ste_v2.o \
+					steering/sws/dr_ste_v3.o \
 					steering/sws/dr_cmd.o \
 					steering/sws/dr_fw.o \
 					steering/sws/dr_action.o \
@@ -150,8 +152,10 @@ mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/cmd.o \
 					steering/hws/bwc.o \
 					steering/hws/debug.o \
 					steering/hws/vport.o \
-					steering/hws/bwc_complex.o
-
+					steering/hws/bwc_complex.o \
+					steering/hws/fs_hws_pools.o \
+					steering/hws/fs_hws.o \
+					steering/hws/action_ste_pool.o
 
 #
 # SF device
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 6bd8a18e3af3..b1aeea7c4a91 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -94,6 +94,11 @@ static u16 in_to_opcode(void *in)
 	return MLX5_GET(mbox_in, in, opcode);
 }
 
+static u16 in_to_uid(void *in)
+{
+	return MLX5_GET(mbox_in, in, uid);
+}
+
 /* Returns true for opcodes that might be triggered very frequently and throttle
  * the command interface. Limit their command slots usage.
  */
@@ -823,7 +828,7 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 
 	opcode = in_to_opcode(in);
 	op_mod = MLX5_GET(mbox_in, in, op_mod);
-	uid    = MLX5_GET(mbox_in, in, uid);
+	uid    = in_to_uid(in);
 	status = MLX5_GET(mbox_out, out, status);
 
 	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY &&
@@ -922,8 +927,7 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 
 static void cb_timeout_handler(struct work_struct *work)
 {
-	struct delayed_work *dwork = container_of(work, struct delayed_work,
-						  work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5_cmd_work_ent *ent = container_of(dwork,
 						     struct mlx5_cmd_work_ent,
 						     cb_timeout_work);
@@ -1013,6 +1017,7 @@ static void cmd_work_handler(struct work_struct *work)
 				complete(&ent->done);
 			}
 			up(&cmd->vars.sem);
+			complete(&ent->slotted);
 			return;
 		}
 	} else {
@@ -1870,6 +1875,17 @@ static int is_manage_pages(void *in)
 	return in_to_opcode(in) == MLX5_CMD_OP_MANAGE_PAGES;
 }
 
+static bool mlx5_has_privileged_uid(struct mlx5_core_dev *dev)
+{
+	return !xa_empty(&dev->cmd.vars.privileged_uids);
+}
+
+static bool mlx5_cmd_is_privileged_uid(struct mlx5_core_dev *dev,
+				       u16 uid)
+{
+	return !!xa_load(&dev->cmd.vars.privileged_uids, uid);
+}
+
 /*  Notes:
  *    1. Callback functions may not sleep
  *    2. Page queue commands do not support asynchrous completion
@@ -1880,7 +1896,9 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 {
 	struct mlx5_cmd_msg *inb, *outb;
 	u16 opcode = in_to_opcode(in);
-	bool throttle_op;
+	bool throttle_locked = false;
+	bool unpriv_locked = false;
+	u16 uid = in_to_uid(in);
 	int pages_queue;
 	gfp_t gfp;
 	u8 token;
@@ -1889,12 +1907,17 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode))
 		return -ENXIO;
 
-	throttle_op = mlx5_cmd_is_throttle_opcode(opcode);
-	if (throttle_op) {
-		if (callback) {
-			if (down_trylock(&dev->cmd.vars.throttle_sem))
-				return -EBUSY;
-		} else {
+	if (!callback) {
+		/* The semaphore is already held for callback commands. It was
+		 * acquired in mlx5_cmd_exec_cb()
+		 */
+		if (uid && mlx5_has_privileged_uid(dev)) {
+			if (!mlx5_cmd_is_privileged_uid(dev, uid)) {
+				unpriv_locked = true;
+				down(&dev->cmd.vars.unprivileged_sem);
+			}
+		} else if (mlx5_cmd_is_throttle_opcode(opcode)) {
+			throttle_locked = true;
 			down(&dev->cmd.vars.throttle_sem);
 		}
 	}
@@ -1940,8 +1963,11 @@ out_out:
 out_in:
 	free_msg(dev, inb);
 out_up:
-	if (throttle_op)
+	if (throttle_locked)
 		up(&dev->cmd.vars.throttle_sem);
+	if (unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
+
 	return err;
 }
 
@@ -2103,18 +2129,22 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 	struct mlx5_async_work *work = _work;
 	struct mlx5_async_ctx *ctx;
 	struct mlx5_core_dev *dev;
-	u16 opcode;
+	bool throttle_locked;
+	bool unpriv_locked;
 
 	ctx = work->ctx;
 	dev = ctx->dev;
-	opcode = work->opcode;
+	throttle_locked = work->throttle_locked;
+	unpriv_locked = work->unpriv_locked;
 	status = cmd_status_err(dev, status, work->opcode, work->op_mod, work->out);
 	work->user_callback(status, work);
 	/* Can't access "work" from this point on. It could have been freed in
 	 * the callback.
 	 */
-	if (mlx5_cmd_is_throttle_opcode(opcode))
+	if (throttle_locked)
 		up(&dev->cmd.vars.throttle_sem);
+	if (unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
 	if (atomic_dec_and_test(&ctx->num_inflight))
 		complete(&ctx->inflight_done);
 }
@@ -2123,6 +2153,8 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 		     void *out, int out_size, mlx5_async_cbk_t callback,
 		     struct mlx5_async_work *work)
 {
+	struct mlx5_core_dev *dev = ctx->dev;
+	u16 uid;
 	int ret;
 
 	work->ctx = ctx;
@@ -2130,11 +2162,43 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 	work->opcode = in_to_opcode(in);
 	work->op_mod = MLX5_GET(mbox_in, in, op_mod);
 	work->out = out;
+	work->throttle_locked = false;
+	work->unpriv_locked = false;
+	uid = in_to_uid(in);
+
 	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
 		return -EIO;
-	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
+
+	if (uid && mlx5_has_privileged_uid(dev)) {
+		if (!mlx5_cmd_is_privileged_uid(dev, uid)) {
+			if (down_trylock(&dev->cmd.vars.unprivileged_sem)) {
+				ret = -EBUSY;
+				goto dec_num_inflight;
+			}
+			work->unpriv_locked = true;
+		}
+	} else if (mlx5_cmd_is_throttle_opcode(in_to_opcode(in))) {
+		if (down_trylock(&dev->cmd.vars.throttle_sem)) {
+			ret = -EBUSY;
+			goto dec_num_inflight;
+		}
+		work->throttle_locked = true;
+	}
+
+	ret = cmd_exec(dev, in, in_size, out, out_size,
 		       mlx5_cmd_exec_cb_handler, work, false);
-	if (ret && atomic_dec_and_test(&ctx->num_inflight))
+	if (ret)
+		goto sem_up;
+
+	return 0;
+
+sem_up:
+	if (work->throttle_locked)
+		up(&dev->cmd.vars.throttle_sem);
+	if (work->unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
+dec_num_inflight:
+	if (atomic_dec_and_test(&ctx->num_inflight))
 		complete(&ctx->inflight_done);
 
 	return ret;
@@ -2370,10 +2434,16 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 	sema_init(&cmd->vars.sem, cmd->vars.max_reg_cmds);
 	sema_init(&cmd->vars.pages_sem, 1);
 	sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
+	sema_init(&cmd->vars.unprivileged_sem,
+		  DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
+
+	xa_init(&cmd->vars.privileged_uids);
 
 	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
-	if (!cmd->pool)
-		return -ENOMEM;
+	if (!cmd->pool) {
+		err = -ENOMEM;
+		goto err_destroy_xa;
+	}
 
 	err = alloc_cmd_page(dev, cmd);
 	if (err)
@@ -2407,6 +2477,8 @@ err_cmd_page:
 	free_cmd_page(dev, cmd);
 err_free_pool:
 	dma_pool_destroy(cmd->pool);
+err_destroy_xa:
+	xa_destroy(&dev->cmd.vars.privileged_uids);
 	return err;
 }
 
@@ -2419,6 +2491,7 @@ void mlx5_cmd_disable(struct mlx5_core_dev *dev)
 	destroy_msg_cache(dev);
 	free_cmd_page(dev, cmd);
 	dma_pool_destroy(cmd->pool);
+	xa_destroy(&dev->cmd.vars.privileged_uids);
 }
 
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
@@ -2426,3 +2499,18 @@ void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
 {
 	dev->cmd.state = cmdif_state;
 }
+
+int mlx5_cmd_add_privileged_uid(struct mlx5_core_dev *dev, u16 uid)
+{
+	return xa_insert(&dev->cmd.vars.privileged_uids, uid,
+			 xa_mk_value(uid), GFP_KERNEL);
+}
+EXPORT_SYMBOL(mlx5_cmd_add_privileged_uid);
+
+void mlx5_cmd_remove_privileged_uid(struct mlx5_core_dev *dev, u16 uid)
+{
+	void *data = xa_erase(&dev->cmd.vars.privileged_uids, uid);
+
+	WARN(!data, "Privileged UID %u does not exist\n", uid);
+}
+EXPORT_SYMBOL(mlx5_cmd_remove_privileged_uid);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 9a79674d27f1..891bbbbfbbf1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -228,8 +228,15 @@ enum {
 	MLX5_INTERFACE_PROTOCOL_VNET,
 
 	MLX5_INTERFACE_PROTOCOL_DPLL,
+	MLX5_INTERFACE_PROTOCOL_FWCTL,
 };
 
+static bool is_fwctl_supported(struct mlx5_core_dev *dev)
+{
+	/* fwctl is most useful on PFs, prevent fwctl on SFs for now */
+	return MLX5_CAP_GEN(dev, uctx_cap) && !mlx5_core_is_sf(dev);
+}
+
 static const struct mlx5_adev_device {
 	const char *suffix;
 	bool (*is_supported)(struct mlx5_core_dev *dev);
@@ -252,6 +259,8 @@ static const struct mlx5_adev_device {
 					   .is_supported = &is_mp_supported },
 	[MLX5_INTERFACE_PROTOCOL_DPLL] = { .suffix = "dpll",
 					   .is_supported = &is_dpll_supported },
+	[MLX5_INTERFACE_PROTOCOL_FWCTL] = { .suffix = "fwctl",
+					    .is_supported = &is_fwctl_supported },
 };
 
 int mlx5_adev_idx_alloc(void)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 98d4306929f3..73cd74644378 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -46,6 +46,9 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	u32 running_fw, stored_fw;
 	int err;
 
+	if (!mlx5_core_is_pf(dev))
+		return 0;
+
 	err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id);
 	if (err)
 		return err;
@@ -324,7 +327,8 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.rate_node_tx_max_set = mlx5_esw_devlink_rate_node_tx_max_set,
 	.rate_node_new = mlx5_esw_devlink_rate_node_new,
 	.rate_node_del = mlx5_esw_devlink_rate_node_del,
-	.rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set,
+	.rate_leaf_parent_set = mlx5_esw_devlink_rate_leaf_parent_set,
+	.rate_node_parent_set = mlx5_esw_devlink_rate_node_parent_set,
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
 	.port_new = mlx5_devlink_sf_port_new,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index 9aed29fa4900..d6e736c1fb24 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -292,7 +292,7 @@ TRACE_EVENT(mlx5_fs_add_rule,
 			   if (rule->dest_attr.type &
 			       MLX5_FLOW_DESTINATION_TYPE_COUNTER)
 				__entry->counter_id =
-					rule->dest_attr.counter_id;
+					mlx5_fc_id(rule->dest_attr.counter);
 	    ),
 	    TP_printk("rule=%p fte=%p index=%u sw_action=<%s> [dst] %s\n",
 		      __entry->rule, __entry->fte, __entry->index,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
index c7216e84ef8c..86253a89c24c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
@@ -13,6 +13,50 @@ struct mlx5_vnic_diag_stats {
 	__be64 query_vnic_env_out[MLX5_ST_SZ_QW(query_vnic_env_out)];
 };
 
+static void mlx5_reporter_vnic_diagnose_counter_icm(struct mlx5_core_dev *dev,
+						    struct devlink_fmsg *fmsg,
+						    u16 vport_num, bool other_vport)
+{
+	u32 out_icm_reg[MLX5_ST_SZ_DW(vhca_icm_ctrl_reg)] = {};
+	u32 in_icm_reg[MLX5_ST_SZ_DW(vhca_icm_ctrl_reg)] = {};
+	u32 out_reg[MLX5_ST_SZ_DW(nic_cap_reg)] = {};
+	u32 in_reg[MLX5_ST_SZ_DW(nic_cap_reg)] = {};
+	u32 cur_alloc_icm;
+	int vhca_icm_ctrl;
+	u16 vhca_id;
+	int err;
+
+	err = mlx5_core_access_reg(dev, in_reg, sizeof(in_reg), out_reg,
+				   sizeof(out_reg), MLX5_REG_NIC_CAP, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "Reading nic_cap_reg failed. err = %d\n", err);
+		return;
+	}
+	vhca_icm_ctrl = MLX5_GET(nic_cap_reg, out_reg, vhca_icm_ctrl);
+	if (!vhca_icm_ctrl)
+		return;
+
+	MLX5_SET(vhca_icm_ctrl_reg, in_icm_reg, vhca_id_valid, other_vport);
+	if (other_vport) {
+		err = mlx5_vport_get_vhca_id(dev, vport_num, &vhca_id);
+		if (err) {
+			mlx5_core_warn(dev, "vport to vhca_id failed. vport_num = %d, err = %d\n",
+				       vport_num, err);
+			return;
+		}
+		MLX5_SET(vhca_icm_ctrl_reg, in_icm_reg, vhca_id, vhca_id);
+	}
+	err = mlx5_core_access_reg(dev, in_icm_reg, sizeof(in_icm_reg),
+				   out_icm_reg, sizeof(out_icm_reg),
+				   MLX5_REG_VHCA_ICM_CTRL, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "Reading vhca_icm_ctrl failed. err = %d\n", err);
+		return;
+	}
+	cur_alloc_icm = MLX5_GET(vhca_icm_ctrl_reg, out_icm_reg, cur_alloc_icm);
+	devlink_fmsg_u32_pair_put(fmsg, "icm_consumption", cur_alloc_icm);
+}
+
 void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 					  struct devlink_fmsg *fmsg,
 					  u16 vport_num, bool other_vport)
@@ -59,6 +103,8 @@ void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 		devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail",
 					  VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail));
 	}
+	if (MLX5_CAP_GEN(dev, nic_cap_reg))
+		mlx5_reporter_vnic_diagnose_counter_icm(dev, fmsg, vport_num, other_vport);
 
 	devlink_fmsg_obj_nest_end(fmsg);
 	devlink_fmsg_pair_nest_end(fmsg);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
index 31142f6cc372..1e5522a19483 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
@@ -242,7 +242,7 @@ static int mlx5_dpll_clock_quality_level_get(const struct dpll_device *dpll,
 		return 0;
 	}
 errout:
-	NL_SET_ERR_MSG_MOD(extack, "Invalid clock quality level obtained from firmware\n");
+	NL_SET_ERR_MSG_MOD(extack, "Invalid clock quality level obtained from firmware");
 	return -EINVAL;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 979fc56205e1..5b0d03b3efe8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -95,8 +95,6 @@ struct page_pool;
 #define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) \
 	MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, order_base_2(MLX5E_RX_MAX_HEAD))
 
-#define MLX5_MPWRQ_MAX_LOG_WQE_SZ 18
-
 /* Keep in sync with mlx5e_mpwrq_log_wqe_sz.
  * These are theoretical maximums, which can be further restricted by
  * capabilities. These values are used for static resource allocations and
@@ -232,16 +230,22 @@ struct mlx5e_rx_wqe_cyc {
 	DECLARE_FLEX_ARRAY(struct mlx5_wqe_data_seg, data);
 };
 
-struct mlx5e_umr_wqe {
+struct mlx5e_umr_wqe_hdr {
 	struct mlx5_wqe_ctrl_seg       ctrl;
 	struct mlx5_wqe_umr_ctrl_seg   uctrl;
 	struct mlx5_mkey_seg           mkc;
+};
+
+struct mlx5e_umr_wqe {
+	struct mlx5e_umr_wqe_hdr hdr;
 	union {
 		DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts);
 		DECLARE_FLEX_ARRAY(struct mlx5_klm, inline_klms);
 		DECLARE_FLEX_ARRAY(struct mlx5_ksm, inline_ksms);
 	};
 };
+static_assert(offsetof(struct mlx5e_umr_wqe, inline_mtts) == sizeof(struct mlx5e_umr_wqe_hdr),
+	      "struct members should be included in struct mlx5e_umr_wqe_hdr, not in struct mlx5e_umr_wqe");
 
 enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_CQE_BASED_MODER,
@@ -386,7 +390,6 @@ enum {
 	MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
 	MLX5E_SQ_STATE_PENDING_XSK_TX,
 	MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC,
-	MLX5E_SQ_STATE_XDP_MULTIBUF,
 	MLX5E_NUM_SQ_STATES, /* Must be kept last */
 };
 
@@ -395,6 +398,7 @@ struct mlx5e_tx_mpwqe {
 	struct mlx5e_tx_wqe *wqe;
 	u32 bytes_count;
 	u8 ds_count;
+	u8 ds_count_max;
 	u8 pkt_count;
 	u8 inline_on;
 };
@@ -516,6 +520,12 @@ struct mlx5e_xdpsq {
 	struct mlx5e_channel      *channel;
 } ____cacheline_aligned_in_smp;
 
+struct mlx5e_xdp_buff {
+	struct xdp_buff xdp;
+	struct mlx5_cqe64 *cqe;
+	struct mlx5e_rq *rq;
+};
+
 struct mlx5e_ktls_resync_resp;
 
 struct mlx5e_icosq {
@@ -660,7 +670,7 @@ struct mlx5e_rq {
 		} wqe;
 		struct {
 			struct mlx5_wq_ll      wq;
-			struct mlx5e_umr_wqe   umr_wqe;
+			struct mlx5e_umr_wqe_hdr umr_wqe;
 			struct mlx5e_mpw_info *info;
 			mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
 			__be32                 umr_mkey_be;
@@ -712,6 +722,7 @@ struct mlx5e_rq {
 	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
+	struct mlx5e_xdp_buff mxbuf;
 
 	/* AF_XDP zero-copy */
 	struct xsk_buff_pool  *xsk_pool;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 1e8b7d330701..b5c3a2a9d2a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -84,9 +84,9 @@ enum {
 	MLX5E_ARFS_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 #endif
 #ifdef CONFIG_MLX5_EN_IPSEC
-	MLX5E_ACCEL_FS_POL_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
-	MLX5E_ACCEL_FS_ESP_FT_LEVEL,
+	MLX5E_ACCEL_FS_ESP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 	MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL,
+	MLX5E_ACCEL_FS_POL_FT_LEVEL,
 	MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
 #endif
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 81523825faa2..cb972b2d46e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -114,6 +114,7 @@ int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
 	int err = 0;
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	mutex_lock(&priv->state_lock);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
@@ -123,6 +124,7 @@ int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
 
 out:
 	mutex_unlock(&priv->state_lock);
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 64b62ed17b07..58ec5e44aa7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -10,6 +10,9 @@
 #include <net/page_pool/types.h>
 #include <net/xdp_sock_drv.h>
 
+#define MLX5_MPWRQ_MAX_LOG_WQE_SZ 18
+#define MLX5_REP_MPWRQ_MAX_LOG_WQE_SZ 17
+
 static u8 mlx5e_mpwrq_min_page_shift(struct mlx5_core_dev *mdev)
 {
 	u8 min_page_shift = MLX5_CAP_GEN_2(mdev, log_min_mkey_entity_size);
@@ -103,18 +106,22 @@ u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
 			  enum mlx5e_mpwrq_umr_mode umr_mode)
 {
 	u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode);
-	u8 max_pages_per_wqe, max_log_mpwqe_size;
+	u8 max_pages_per_wqe, max_log_wqe_size_calc;
+	u8 max_log_wqe_size_cap;
 	u16 max_wqe_size;
 
 	/* Keep in sync with MLX5_MPWRQ_MAX_PAGES_PER_WQE. */
 	max_wqe_size = mlx5e_get_max_sq_aligned_wqebbs(mdev) * MLX5_SEND_WQE_BB;
 	max_pages_per_wqe = ALIGN_DOWN(max_wqe_size - sizeof(struct mlx5e_umr_wqe),
 				       MLX5_UMR_FLEX_ALIGNMENT) / umr_entry_size;
-	max_log_mpwqe_size = ilog2(max_pages_per_wqe) + page_shift;
+	max_log_wqe_size_calc = ilog2(max_pages_per_wqe) + page_shift;
+
+	WARN_ON_ONCE(max_log_wqe_size_calc < MLX5E_ORDER2_MAX_PACKET_MTU);
 
-	WARN_ON_ONCE(max_log_mpwqe_size < MLX5E_ORDER2_MAX_PACKET_MTU);
+	max_log_wqe_size_cap = mlx5_core_is_ecpf(mdev) ?
+			   MLX5_REP_MPWRQ_MAX_LOG_WQE_SZ : MLX5_MPWRQ_MAX_LOG_WQE_SZ;
 
-	return min_t(u8, max_log_mpwqe_size, MLX5_MPWRQ_MAX_LOG_WQE_SZ);
+	return min_t(u8, max_log_wqe_size_calc, max_log_wqe_size_cap);
 }
 
 u8 mlx5e_mpwrq_pages_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift,
@@ -423,7 +430,7 @@ u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5_core_dev *mdev,
 				     struct mlx5e_params *params)
 {
 	u32 resrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) *
-			 PAGE_SIZE;
+			 MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE;
 
 	return order_base_2(DIV_ROUND_UP(resrv_size, params->sw_mtu));
 }
@@ -827,7 +834,8 @@ static u32 mlx5e_shampo_get_log_cq_size(struct mlx5_core_dev *mdev,
 					struct mlx5e_params *params,
 					struct mlx5e_xsk_param *xsk)
 {
-	int rsrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * PAGE_SIZE;
+	int rsrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) *
+		MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE;
 	u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
 	int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
 	u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
@@ -1036,7 +1044,8 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
 			    struct mlx5e_rq_param *rq_param)
 {
-	int resv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * PAGE_SIZE;
+	int resv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) *
+		MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE;
 	u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, NULL));
 	int pkt_per_resv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
 	u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL);
@@ -1240,7 +1249,6 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
-	param->is_xdp_mb = !mlx5e_rx_is_linear_skb(mdev, params, xsk);
 	mlx5e_build_tx_cq_param(mdev, params, &param->cqp);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 3f8986f9d862..bd5877acc5b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -33,7 +33,6 @@ struct mlx5e_sq_param {
 	struct mlx5_wq_param       wq;
 	bool                       is_mpw;
 	bool                       is_tls;
-	bool                       is_xdp_mb;
 	u16                        stop_room;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 5f6a0605e4ae..6049ccf475bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -80,6 +80,7 @@ int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
 	struct mlx5_port_eth_proto eproto;
+	const struct mlx5_link_info *info;
 	bool force_legacy = false;
 	bool ext;
 	int err;
@@ -94,9 +95,13 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 		if (err)
 			goto out;
 	}
-	*speed = mlx5_port_ptys2speed(mdev, eproto.oper, force_legacy);
-	if (!(*speed))
+	info = mlx5_port_ptys2info(mdev, eproto.oper, force_legacy);
+	if (!info) {
+		*speed = SPEED_UNKNOWN;
 		err = -EINVAL;
+		goto out;
+	}
+	*speed = info->speed;
 
 out:
 	return err;
@@ -296,11 +301,16 @@ enum mlx5e_fec_supported_link_mode {
 	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_2X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_4X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X,
 	MLX5E_MAX_FEC_SUPPORTED_LINK_MODE,
 };
 
 #define MLX5E_FEC_FIRST_50G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X
 #define MLX5E_FEC_FIRST_100G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_100G_1X
+#define MLX5E_FEC_FIRST_200G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X
 
 #define MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, policy, write, link)			\
 	do {										\
@@ -320,8 +330,10 @@ static bool mlx5e_is_fec_supported_link_mode(struct mlx5_core_dev *dev,
 	return link_mode < MLX5E_FEC_FIRST_50G_PER_LANE_MODE ||
 	       (link_mode < MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
 		MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm)) ||
-	       (link_mode >= MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
-		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm));
+	       (link_mode < MLX5E_FEC_FIRST_200G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm)) ||
+	       (link_mode >= MLX5E_FEC_FIRST_200G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_200G_per_lane_in_pplm));
 }
 
 /* get/set FEC admin field for a given speed */
@@ -368,6 +380,18 @@ static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
 		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 200g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 1600g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -421,6 +445,18 @@ static int mlx5e_get_fec_cap_field(u32 *pplm, u16 *fec_cap,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
 		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 200g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 400g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 1600g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -494,6 +530,26 @@ out:
 	return 0;
 }
 
+static u16 mlx5e_remap_fec_conf_mode(enum mlx5e_fec_supported_link_mode link_mode,
+				     u16 conf_fec)
+{
+	/* RS fec in ethtool is originally mapped to MLX5E_FEC_RS_528_514.
+	 * For link modes up to 25G per lane, the value is kept.
+	 * For 50G or 100G per lane, it's remapped to MLX5E_FEC_RS_544_514.
+	 * For 200G per lane, remapped to MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD.
+	 */
+	if (conf_fec != BIT(MLX5E_FEC_RS_528_514))
+		return conf_fec;
+
+	if (link_mode >= MLX5E_FEC_FIRST_200G_PER_LANE_MODE)
+		return BIT(MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD);
+
+	if (link_mode >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
+		return BIT(MLX5E_FEC_RS_544_514);
+
+	return conf_fec;
+}
+
 int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 {
 	bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm);
@@ -530,14 +586,7 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 		if (!mlx5e_is_fec_supported_link_mode(dev, i))
 			break;
 
-		/* RS fec in ethtool is mapped to MLX5E_FEC_RS_528_514
-		 * to link modes up to 25G per lane and to
-		 * MLX5E_FEC_RS_544_514 in the new link modes based on
-		 * 50G or 100G per lane
-		 */
-		if (conf_fec == (1 << MLX5E_FEC_RS_528_514) &&
-		    i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
-			conf_fec = (1 << MLX5E_FEC_RS_544_514);
+		conf_fec = mlx5e_remap_fec_conf_mode(i, conf_fec);
 
 		mlx5e_get_fec_cap_field(out, &fec_caps, i);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index d1da225f35da..fa2283dd383b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -61,6 +61,7 @@ enum {
 	MLX5E_FEC_NOFEC,
 	MLX5E_FEC_FIRECODE,
 	MLX5E_FEC_RS_528_514,
+	MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD = 4,
 	MLX5E_FEC_RS_544_514 = 7,
 	MLX5E_FEC_LLRS_272_257_1 = 9,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index afd654583b6b..5d0014129a7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -8,6 +8,7 @@
 #include "en/fs_tt_redirect.h"
 #include <linux/list.h>
 #include <linux/spinlock.h>
+#include <net/netdev_lock.h>
 
 struct mlx5e_ptp_fs {
 	struct mlx5_flow_handle *l2_rule;
@@ -326,7 +327,7 @@ static int mlx5e_ptp_alloc_txqsq(struct mlx5e_ptp *c, int txq_ix,
 	int node;
 
 	sq->pdev      = c->pdev;
-	sq->clock     = &mdev->clock;
+	sq->clock     = mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->priv      = c->priv;
@@ -449,8 +450,22 @@ static void mlx5e_ptpsq_unhealthy_work(struct work_struct *work)
 {
 	struct mlx5e_ptpsq *ptpsq =
 		container_of(work, struct mlx5e_ptpsq, report_unhealthy_work);
+	struct mlx5e_txqsq *sq = &ptpsq->txqsq;
+
+	/* Recovering the PTP SQ means re-enabling NAPI, which requires the
+	 * netdev instance lock. However, SQ closing has to wait for this work
+	 * task to finish while also holding the same lock. So either get the
+	 * lock or find that the SQ is no longer enabled and thus this work is
+	 * not relevant anymore.
+	 */
+	while (!netdev_trylock(sq->netdev)) {
+		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))
+			return;
+		msleep(20);
+	}
 
 	mlx5e_reporter_tx_ptpsq_unhealthy(ptpsq);
+	netdev_unlock(sq->netdev);
 }
 
 static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
@@ -696,7 +711,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
 	rq->pdev         = c->pdev;
 	rq->netdev       = priv->netdev;
 	rq->priv         = priv;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->tstamp       = &priv->tstamp;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
@@ -892,7 +907,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	if (err)
 		goto err_free;
 
-	netif_napi_add(netdev, &c->napi, mlx5e_ptp_napi_poll);
+	netif_napi_add_locked(netdev, &c->napi, mlx5e_ptp_napi_poll);
 
 	mlx5e_ptp_build_params(c, cparams, params);
 
@@ -910,7 +925,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	return 0;
 
 err_napi_del:
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 err_free:
 	kvfree(cparams);
 	kvfree(c);
@@ -920,7 +935,7 @@ err_free:
 void mlx5e_ptp_close(struct mlx5e_ptp *c)
 {
 	mlx5e_ptp_close_queues(c);
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
 	kvfree(c);
 }
@@ -929,7 +944,7 @@ void mlx5e_ptp_activate_channel(struct mlx5e_ptp *c)
 {
 	int tc;
 
-	napi_enable(&c->napi);
+	napi_enable_locked(&c->napi);
 
 	if (test_bit(MLX5E_PTP_STATE_TX, c->state)) {
 		for (tc = 0; tc < c->num_tc; tc++)
@@ -957,7 +972,7 @@ void mlx5e_ptp_deactivate_channel(struct mlx5e_ptp *c)
 			mlx5e_deactivate_txqsq(&c->ptpsq[tc].txqsq);
 	}
 
-	napi_disable(&c->napi);
+	napi_disable_locked(&c->napi);
 }
 
 int mlx5e_ptp_get_rqn(struct mlx5e_ptp *c, u32 *rqn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index 5d128c5b4529..0f5d7ea8956f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -48,15 +48,10 @@ mlx5_esw_bridge_lag_rep_get(struct net_device *dev, struct mlx5_eswitch *esw)
 	struct list_head *iter;
 
 	netdev_for_each_lower_dev(dev, lower, iter) {
-		struct mlx5_core_dev *mdev;
-		struct mlx5e_priv *priv;
-
 		if (!mlx5e_eswitch_rep(lower))
 			continue;
 
-		priv = netdev_priv(lower);
-		mdev = priv->mdev;
-		if (mlx5_lag_is_shared_fdb(mdev) && mlx5_esw_bridge_dev_same_esw(lower, esw))
+		if (mlx5_esw_bridge_dev_same_esw(lower, esw))
 			return lower;
 	}
 
@@ -125,7 +120,7 @@ static bool mlx5_esw_bridge_is_local(struct net_device *dev, struct net_device *
 	priv = netdev_priv(rep);
 	mdev = priv->mdev;
 	if (netif_is_lag_master(dev))
-		return mlx5_lag_is_shared_fdb(mdev) && mlx5_lag_is_master(mdev);
+		return mlx5_lag_is_master(mdev);
 	return true;
 }
 
@@ -455,6 +450,9 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 	if (!rep)
 		return NOTIFY_DONE;
 
+	if (netif_is_lag_master(dev) && !mlx5_lag_is_shared_fdb(esw->dev))
+		return NOTIFY_DONE;
+
 	switch (event) {
 	case SWITCHDEV_FDB_ADD_TO_BRIDGE:
 		fdb_info = container_of(info,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 25d751eba99b..e75759533ae0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -317,10 +317,8 @@ mlx5e_rx_reporter_diagnose_common_ptp_config(struct mlx5e_priv *priv, struct mlx
 }
 
 static void
-mlx5e_rx_reporter_diagnose_common_config(struct devlink_health_reporter *reporter,
-					 struct devlink_fmsg *fmsg)
+mlx5e_rx_reporter_diagnose_common_config(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg)
 {
-	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
 	struct mlx5e_rq *generic_rq = &priv->channels.c[0]->rq;
 	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
 
@@ -340,20 +338,100 @@ static void mlx5e_rx_reporter_build_diagnose_output_ptp_rq(struct mlx5e_rq *rq,
 	devlink_fmsg_obj_nest_end(fmsg);
 }
 
-static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
-				      struct devlink_fmsg *fmsg,
-				      struct netlink_ext_ack *extack)
+static void mlx5e_rx_reporter_diagnose_rx_res_dir_tirns(struct mlx5e_rx_res *rx_res,
+							struct devlink_fmsg *fmsg)
 {
-	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
-	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
+	unsigned int max_nch = mlx5e_rx_res_get_max_nch(rx_res);
 	int i;
 
-	mutex_lock(&priv->state_lock);
+	devlink_fmsg_arr_pair_nest_start(fmsg, "Direct TIRs");
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto unlock;
+	for (i = 0; i < max_nch; i++) {
+		devlink_fmsg_obj_nest_start(fmsg);
+
+		devlink_fmsg_u32_pair_put(fmsg, "ix", i);
+		devlink_fmsg_u32_pair_put(fmsg, "tirn", mlx5e_rx_res_get_tirn_direct(rx_res, i));
+		devlink_fmsg_u32_pair_put(fmsg, "rqtn", mlx5e_rx_res_get_rqtn_direct(rx_res, i));
+
+		devlink_fmsg_obj_nest_end(fmsg);
+	}
+
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(struct mlx5e_rss *rss, bool inner,
+						       struct devlink_fmsg *fmsg)
+{
+	bool found_valid_tir = false;
+	int tt;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		if (!mlx5e_rss_valid_tir(rss, tt, inner))
+			continue;
+
+		if (!found_valid_tir) {
+			char *tir_msg = inner ? "Inner TIRs Numbers" : "TIRs Numbers";
+
+			found_valid_tir = true;
+			devlink_fmsg_arr_pair_nest_start(fmsg, tir_msg);
+		}
+
+		devlink_fmsg_obj_nest_start(fmsg);
+		devlink_fmsg_string_pair_put(fmsg, "tt", mlx5_ttc_get_name(tt));
+		devlink_fmsg_u32_pair_put(fmsg, "tirn", mlx5e_rss_get_tirn(rss, tt, inner));
+		devlink_fmsg_obj_nest_end(fmsg);
+	}
+
+	if (found_valid_tir)
+		devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res_rss_ix(struct mlx5e_rx_res *rx_res, u32 rss_idx,
+						     struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_rss *rss = mlx5e_rx_res_rss_get(rx_res, rss_idx);
+
+	if (!rss)
+		return;
+
+	devlink_fmsg_obj_nest_start(fmsg);
+
+	devlink_fmsg_u32_pair_put(fmsg, "Index", rss_idx);
+	devlink_fmsg_u32_pair_put(fmsg, "rqtn", mlx5e_rss_get_rqtn(rss));
+	mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(rss, false, fmsg);
+	if (mlx5e_rss_get_inner_ft_support(rss))
+		mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(rss, true, fmsg);
+
+	devlink_fmsg_obj_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res_rss(struct mlx5e_rx_res *rx_res,
+						  struct devlink_fmsg *fmsg)
+{
+	int rss_ix;
+
+	devlink_fmsg_arr_pair_nest_start(fmsg, "RSS");
+	for (rss_ix = 0; rss_ix < MLX5E_MAX_NUM_RSS; rss_ix++)
+		mlx5e_rx_reporter_diagnose_rx_res_rss_ix(rx_res, rss_ix, fmsg);
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res(struct mlx5e_priv *priv,
+					      struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_rx_res *rx_res = priv->rx_res;
+
+	mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RX resources");
+	mlx5e_rx_reporter_diagnose_rx_res_dir_tirns(rx_res, fmsg);
+	mlx5e_rx_reporter_diagnose_rx_res_rss(rx_res, fmsg);
+	mlx5e_health_fmsg_named_obj_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rqs(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
+	int i;
 
-	mlx5e_rx_reporter_diagnose_common_config(reporter, fmsg);
 	devlink_fmsg_arr_pair_nest_start(fmsg, "RQs");
 
 	for (i = 0; i < priv->channels.num; i++) {
@@ -367,7 +445,24 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
 	}
 	if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state))
 		mlx5e_rx_reporter_build_diagnose_output_ptp_rq(&ptp_ch->rq, fmsg);
+
 	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
+				      struct devlink_fmsg *fmsg,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	mlx5e_rx_reporter_diagnose_common_config(priv, fmsg);
+	mlx5e_rx_reporter_diagnose_rqs(priv, fmsg);
+	mlx5e_rx_reporter_diagnose_rx_res(priv, fmsg);
 unlock:
 	mutex_unlock(&priv->state_lock);
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 09433b91be17..c3bda4612fa9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -16,7 +16,6 @@ static const char * const sq_sw_state_type_name[] = {
 	[MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE] = "vlan_need_l2_inline",
 	[MLX5E_SQ_STATE_PENDING_XSK_TX] = "pending_xsk_tx",
 	[MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC] = "pending_tls_rx_resync",
-	[MLX5E_SQ_STATE_XDP_MULTIBUF] = "xdp_multibuf",
 };
 
 static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
@@ -108,9 +107,7 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 	mlx5e_reset_txqsq_cc_pc(sq);
 	sq->stats->recover++;
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
-	rtnl_lock();
 	mlx5e_activate_txqsq(sq);
-	rtnl_unlock();
 
 	if (sq->channel)
 		mlx5e_trigger_napi_icosq(sq->channel);
@@ -184,16 +181,12 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
 	carrier_ok = netif_carrier_ok(netdev);
 	netif_carrier_off(netdev);
 
-	rtnl_lock();
 	mlx5e_deactivate_priv_channels(priv);
-	rtnl_unlock();
 
 	mlx5e_ptp_close(chs->ptp);
 	err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
 
-	rtnl_lock();
 	mlx5e_activate_priv_channels(priv);
-	rtnl_unlock();
 
 	/* return carrier back if needed */
 	if (carrier_ok)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
index 5f742f896600..74cd111ee320 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
@@ -81,6 +81,11 @@ struct mlx5e_rss {
 	refcount_t refcnt;
 };
 
+bool mlx5e_rss_get_inner_ft_support(struct mlx5e_rss *rss)
+{
+	return rss->inner_ft_support;
+}
+
 void mlx5e_rss_params_indir_modify_actual_size(struct mlx5e_rss *rss, u32 num_channels)
 {
 	rss->indir.actual_table_size = mlx5e_rqt_size(rss->mdev, num_channels);
@@ -156,6 +161,7 @@ static void mlx5e_rss_params_init(struct mlx5e_rss *rss)
 {
 	enum mlx5_traffic_types tt;
 
+	rss->hash.symmetric = true;
 	rss->hash.hfunc = ETH_RSS_HASH_TOP;
 	netdev_rss_key_fill(rss->hash.toeplitz_hash_key,
 			    sizeof(rss->hash.toeplitz_hash_key));
@@ -449,6 +455,16 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 	return mlx5e_tir_get_tirn(tir);
 }
 
+u32 mlx5e_rss_get_rqtn(struct mlx5e_rss *rss)
+{
+	return mlx5e_rqt_get_rqtn(&rss->rqt);
+}
+
+bool mlx5e_rss_valid_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, bool inner)
+{
+	return !!rss_get_tir(rss, tt, inner);
+}
+
 /* Fill the "tirn" output parameter.
  * Create the requested TIR if it's its first usage.
  */
@@ -551,7 +567,7 @@ inner_tir:
 	return final_err;
 }
 
-int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc)
+int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc, bool *symmetric)
 {
 	if (indir)
 		memcpy(indir, rss->indir.table,
@@ -564,11 +580,14 @@ int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc)
 	if (hfunc)
 		*hfunc = rss->hash.hfunc;
 
+	if (symmetric)
+		*symmetric = rss->hash.symmetric;
+
 	return 0;
 }
 
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
-		       const u8 *key, const u8 *hfunc,
+		       const u8 *key, const u8 *hfunc, const bool *symmetric,
 		       u32 *rqns, u32 *vhca_ids, unsigned int num_rqns)
 {
 	bool changed_indir = false;
@@ -608,6 +627,11 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
 		       rss->indir.actual_table_size * sizeof(*rss->indir.table));
 	}
 
+	if (symmetric) {
+		rss->hash.symmetric = *symmetric;
+		changed_hash = true;
+	}
+
 	if (changed_indir && rss->enabled) {
 		err = mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns);
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
index d0df98963c8d..8ac902190010 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
@@ -32,8 +32,11 @@ void mlx5e_rss_refcnt_inc(struct mlx5e_rss *rss);
 void mlx5e_rss_refcnt_dec(struct mlx5e_rss *rss);
 unsigned int mlx5e_rss_refcnt_read(struct mlx5e_rss *rss);
 
+bool mlx5e_rss_get_inner_ft_support(struct mlx5e_rss *rss);
 u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 		       bool inner);
+bool mlx5e_rss_valid_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, bool inner);
+u32 mlx5e_rss_get_rqtn(struct mlx5e_rss *rss);
 int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 			  enum mlx5_traffic_types tt,
 			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
@@ -44,9 +47,9 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss);
 
 int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
 				     struct mlx5e_packet_merge_param *pkt_merge_param);
-int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc);
+int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc, bool *symmetric);
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
-		       const u8 *key, const u8 *hfunc,
+		       const u8 *key, const u8 *hfunc, const bool *symmetric,
 		       u32 *rqns, u32 *vhca_ids, unsigned int num_rqns);
 struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss);
 u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index a86eade9a9e0..5fcbe47337b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -5,8 +5,6 @@
 #include "channels.h"
 #include "params.h"
 
-#define MLX5E_MAX_NUM_RSS 16
-
 struct mlx5e_rx_res {
 	struct mlx5_core_dev *mdev; /* primary */
 	enum mlx5e_rx_res_features features;
@@ -196,7 +194,7 @@ void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int n
 }
 
 int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      u32 *indir, u8 *key, u8 *hfunc)
+			      u32 *indir, u8 *key, u8 *hfunc, bool *symmetric)
 {
 	struct mlx5e_rss *rss;
 
@@ -207,11 +205,12 @@ int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 	if (!rss)
 		return -ENOENT;
 
-	return mlx5e_rss_get_rxfh(rss, indir, key, hfunc);
+	return mlx5e_rss_get_rxfh(rss, indir, key, hfunc, symmetric);
 }
 
 int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      const u32 *indir, const u8 *key, const u8 *hfunc)
+			      const u32 *indir, const u8 *key, const u8 *hfunc,
+			      const bool *symmetric)
 {
 	u32 *vhca_ids = get_vhca_ids(res, 0);
 	struct mlx5e_rss *rss;
@@ -223,8 +222,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 	if (!rss)
 		return -ENOENT;
 
-	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, vhca_ids,
-				  res->rss_nch);
+	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, symmetric,
+				  res->rss_rqns, vhca_ids, res->rss_nch);
 }
 
 int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
@@ -497,6 +496,11 @@ void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res)
 	mlx5e_rx_res_free(res);
 }
 
+unsigned int mlx5e_rx_res_get_max_nch(struct mlx5e_rx_res *res)
+{
+	return res->max_nch;
+}
+
 u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 {
 	return mlx5e_tir_get_tirn(&res->channels[ix].direct_tir);
@@ -522,7 +526,7 @@ u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res)
 	return mlx5e_tir_get_tirn(&res->ptp.tir);
 }
 
-static u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
+u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 {
 	return mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 7b1a9f0f1874..3e09d91281af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -10,6 +10,8 @@
 #include "fs.h"
 #include "rss.h"
 
+#define MLX5E_MAX_NUM_RSS 16
+
 struct mlx5e_rx_res;
 
 struct mlx5e_channels;
@@ -34,6 +36,9 @@ u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix);
 u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res);
+u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix);
+unsigned int mlx5e_rx_res_get_max_nch(struct mlx5e_rx_res *res);
+bool mlx5_rx_res_rss_inner_ft_support(struct mlx5e_rx_res *res);
 
 /* Activate/deactivate API */
 void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs);
@@ -44,9 +49,10 @@ void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *ch
 /* Configuration API */
 void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int nch);
 int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      u32 *indir, u8 *key, u8 *hfunc);
+			      u32 *indir, u8 *key, u8 *hfunc, bool *symmetric);
 int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      const u32 *indir, const u8 *key, const u8 *hfunc);
+			      const u32 *indir, const u8 *key, const u8 *hfunc,
+			      const bool *symmetric);
 
 int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
 				     enum mlx5_traffic_types tt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
index d6c12d0ea55b..2e528b2c34d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
@@ -73,11 +73,6 @@ struct mlx5e_tc_act {
 	bool is_terminating_action;
 };
 
-struct mlx5e_tc_flow_action {
-	unsigned int num_entries;
-	struct flow_action_entry **entries;
-};
-
 extern struct mlx5e_tc_act mlx5e_tc_act_drop;
 extern struct mlx5e_tc_act mlx5e_tc_act_trap;
 extern struct mlx5e_tc_act mlx5e_tc_act_accept;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
index feeb41693c17..b6cabe829f19 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
@@ -5,6 +5,16 @@
 #include "en/tc_priv.h"
 #include "en/tc_ct.h"
 
+static bool
+tc_act_can_offload_ct(struct mlx5e_tc_act_parse_state *parse_state,
+		      const struct flow_action_entry *act,
+		      int act_index,
+		      struct mlx5_flow_attr *attr)
+{
+	return !((act->ct.action & TCA_CT_ACT_COMMIT) &&
+		 flow_action_is_last_entry(parse_state->flow_action, act));
+}
+
 static int
 tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state,
 		const struct flow_action_entry *act,
@@ -56,6 +66,7 @@ tc_act_is_missable_ct(const struct flow_action_entry *act)
 }
 
 struct mlx5e_tc_act mlx5e_tc_act_ct = {
+	.can_offload = tc_act_can_offload_ct,
 	.parse_action = tc_act_parse_ct,
 	.post_parse = tc_act_post_parse_ct,
 	.is_multi_table_act = tc_act_is_multi_table_act_ct,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
index 62b3f7ff5562..e5b30801314b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
@@ -48,4 +48,14 @@ mlx5_ct_fs_smfs_ops_get(void)
 }
 #endif /* IS_ENABLED(CONFIG_MLX5_SW_STEERING) */
 
+#if IS_ENABLED(CONFIG_MLX5_HW_STEERING)
+struct mlx5_ct_fs_ops *mlx5_ct_fs_hmfs_ops_get(void);
+#else
+static inline struct mlx5_ct_fs_ops *
+mlx5_ct_fs_hmfs_ops_get(void)
+{
+	return NULL;
+}
+#endif /* IS_ENABLED(CONFIG_MLX5_SW_STEERING) */
+
 #endif /* __MLX5_EN_TC_CT_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c
new file mode 100644
index 000000000000..a4263137fef5
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. */
+
+#include "en_tc.h"
+#include "en/tc_ct.h"
+#include "en/tc_priv.h"
+#include "en/tc/ct_fs.h"
+#include "fs_core.h"
+#include "steering/hws/fs_hws_pools.h"
+#include "steering/hws/mlx5hws.h"
+#include "steering/hws/table.h"
+
+struct mlx5_ct_fs_hmfs_matcher {
+	struct mlx5hws_bwc_matcher *hws_bwc_matcher;
+	refcount_t ref;
+};
+
+/* We need {ipv4, ipv6} x {tcp, udp, gre}  matchers. */
+#define NUM_MATCHERS (2 * 3)
+
+struct mlx5_ct_fs_hmfs {
+	struct mlx5hws_table *ct_tbl;
+	struct mlx5hws_table *ct_nat_tbl;
+	struct mlx5_flow_table *ct_nat;
+	struct mlx5hws_action *fwd_action;
+	struct mlx5hws_action *last_action;
+	struct mlx5hws_context *ctx;
+	struct mutex lock;   /* Guards matchers */
+	struct mlx5_ct_fs_hmfs_matcher matchers[NUM_MATCHERS];
+	struct mlx5_ct_fs_hmfs_matcher matchers_nat[NUM_MATCHERS];
+};
+
+struct mlx5_ct_fs_hmfs_rule {
+	struct mlx5_ct_fs_rule fs_rule;
+	struct mlx5hws_bwc_rule *hws_bwc_rule;
+	struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher;
+	struct mlx5_fc *counter;
+};
+
+static u32 get_matcher_idx(bool ipv4, bool tcp, bool gre)
+{
+	return ipv4 * 3 + tcp * 2 + gre;
+}
+
+static int mlx5_ct_fs_hmfs_init(struct mlx5_ct_fs *fs, struct mlx5_flow_table *ct,
+				struct mlx5_flow_table *ct_nat, struct mlx5_flow_table *post_ct)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5hws_table *ct_tbl, *ct_nat_tbl, *post_ct_tbl;
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+
+	ct_tbl = ct->fs_hws_table.hws_table;
+	ct_nat_tbl = ct_nat->fs_hws_table.hws_table;
+	post_ct_tbl = post_ct->fs_hws_table.hws_table;
+	fs_hmfs->ct_nat = ct_nat;
+
+	if (!ct_tbl || !ct_nat_tbl || !post_ct_tbl) {
+		netdev_warn(fs->netdev, "ct_fs_hmfs: failed to init, missing backing hws tables");
+		return -EOPNOTSUPP;
+	}
+
+	netdev_dbg(fs->netdev, "using hmfs steering");
+
+	fs_hmfs->ct_tbl = ct_tbl;
+	fs_hmfs->ct_nat_tbl = ct_nat_tbl;
+	fs_hmfs->ctx = ct_tbl->ctx;
+	mutex_init(&fs_hmfs->lock);
+
+	fs_hmfs->fwd_action = mlx5hws_action_create_dest_table(ct_tbl->ctx, post_ct_tbl, flags);
+	if (!fs_hmfs->fwd_action) {
+		netdev_warn(fs->netdev, "ct_fs_hmfs: failed to create fwd action\n");
+		return -EINVAL;
+	}
+	fs_hmfs->last_action = mlx5hws_action_create_last(ct_tbl->ctx, flags);
+	if (!fs_hmfs->last_action) {
+		netdev_warn(fs->netdev, "ct_fs_hmfs: failed to create last action\n");
+		mlx5hws_action_destroy(fs_hmfs->fwd_action);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void mlx5_ct_fs_hmfs_destroy(struct mlx5_ct_fs *fs)
+{
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+
+	mlx5hws_action_destroy(fs_hmfs->last_action);
+	mlx5hws_action_destroy(fs_hmfs->fwd_action);
+}
+
+static struct mlx5hws_bwc_matcher *
+mlx5_ct_fs_hmfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5hws_table *tbl,
+			       struct mlx5_flow_spec *spec, bool ipv4, bool tcp, bool gre)
+{
+	u8 match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2 | MLX5_MATCH_OUTER_HEADERS;
+	struct mlx5hws_match_parameters mask = {
+		.match_buf = spec->match_criteria,
+		.match_sz = sizeof(spec->match_criteria),
+	};
+	u32 priority = get_matcher_idx(ipv4, tcp, gre);  /* Static priority based on params. */
+	struct mlx5hws_bwc_matcher *hws_bwc_matcher;
+
+	hws_bwc_matcher = mlx5hws_bwc_matcher_create(tbl, priority, match_criteria_enable, &mask);
+	if (!hws_bwc_matcher)
+		return ERR_PTR(-EINVAL);
+
+	return hws_bwc_matcher;
+}
+
+static struct mlx5_ct_fs_hmfs_matcher *
+mlx5_ct_fs_hmfs_matcher_get(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec,
+			    bool nat, bool ipv4, bool tcp, bool gre)
+{
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+	u32 matcher_idx = get_matcher_idx(ipv4, tcp, gre);
+	struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher;
+	struct mlx5hws_bwc_matcher *hws_bwc_matcher;
+	struct mlx5hws_table *tbl;
+
+	hmfs_matcher = nat ?
+		(fs_hmfs->matchers_nat + matcher_idx) :
+		(fs_hmfs->matchers + matcher_idx);
+
+	if (refcount_inc_not_zero(&hmfs_matcher->ref))
+		return hmfs_matcher;
+
+	mutex_lock(&fs_hmfs->lock);
+
+	/* Retry with lock, as the matcher might be already created by another cpu. */
+	if (refcount_inc_not_zero(&hmfs_matcher->ref))
+		goto out_unlock;
+
+	tbl = nat ? fs_hmfs->ct_nat_tbl : fs_hmfs->ct_tbl;
+
+	hws_bwc_matcher = mlx5_ct_fs_hmfs_matcher_create(fs, tbl, spec, ipv4, tcp, gre);
+	if (IS_ERR(hws_bwc_matcher)) {
+		netdev_warn(fs->netdev,
+			    "ct_fs_hmfs: failed to create bwc matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %ld\n",
+			    nat, ipv4, tcp, gre, PTR_ERR(hws_bwc_matcher));
+
+		hmfs_matcher = ERR_CAST(hws_bwc_matcher);
+		goto out_unlock;
+	}
+
+	hmfs_matcher->hws_bwc_matcher = hws_bwc_matcher;
+	refcount_set(&hmfs_matcher->ref, 1);
+
+out_unlock:
+	mutex_unlock(&fs_hmfs->lock);
+	return hmfs_matcher;
+}
+
+static void
+mlx5_ct_fs_hmfs_matcher_put(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher)
+{
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+
+	if (!refcount_dec_and_mutex_lock(&hmfs_matcher->ref, &fs_hmfs->lock))
+		return;
+
+	mlx5hws_bwc_matcher_destroy(hmfs_matcher->hws_bwc_matcher);
+	mutex_unlock(&fs_hmfs->lock);
+}
+
+#define NUM_CT_HMFS_RULES 4
+
+static void mlx5_ct_fs_hmfs_fill_rule_actions(struct mlx5_ct_fs_hmfs *fs_hmfs,
+					      struct mlx5_flow_attr *attr,
+					      struct mlx5hws_rule_action *rule_actions)
+{
+	struct mlx5_fs_hws_action *mh_action = &attr->modify_hdr->fs_hws_action;
+
+	memset(rule_actions, 0, NUM_CT_HMFS_RULES * sizeof(*rule_actions));
+	rule_actions[0].action = mlx5_fc_get_hws_action(fs_hmfs->ctx, attr->counter);
+	/* Modify header is special, it may require extra arguments outside the action itself. */
+	if (mh_action->mh_data) {
+		rule_actions[1].modify_header.offset = mh_action->mh_data->offset;
+		rule_actions[1].modify_header.data = mh_action->mh_data->data;
+	}
+	rule_actions[1].action = mh_action->hws_action;
+	rule_actions[2].action = fs_hmfs->fwd_action;
+	rule_actions[3].action = fs_hmfs->last_action;
+}
+
+static struct mlx5_ct_fs_rule *
+mlx5_ct_fs_hmfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec,
+			    struct mlx5_flow_attr *attr, struct flow_rule *flow_rule)
+{
+	struct mlx5hws_rule_action rule_actions[NUM_CT_HMFS_RULES];
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+	struct mlx5hws_match_parameters match_params = {
+		.match_buf = spec->match_value,
+		.match_sz = ARRAY_SIZE(spec->match_value),
+	};
+	struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher;
+	struct mlx5_ct_fs_hmfs_rule *hmfs_rule;
+	bool nat, tcp, ipv4, gre;
+	int err;
+
+	if (!mlx5e_tc_ct_is_valid_flow_rule(fs->netdev, flow_rule))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	hmfs_rule = kzalloc(sizeof(*hmfs_rule), GFP_KERNEL);
+	if (!hmfs_rule)
+		return ERR_PTR(-ENOMEM);
+
+	nat = (attr->ft == fs_hmfs->ct_nat);
+	ipv4 = mlx5e_tc_get_ip_version(spec, true) == 4;
+	tcp = MLX5_GET(fte_match_param, spec->match_value,
+		       outer_headers.ip_protocol) == IPPROTO_TCP;
+	gre = MLX5_GET(fte_match_param, spec->match_value,
+		       outer_headers.ip_protocol) == IPPROTO_GRE;
+
+	hmfs_matcher = mlx5_ct_fs_hmfs_matcher_get(fs, spec, nat, ipv4, tcp, gre);
+	if (IS_ERR(hmfs_matcher)) {
+		err = PTR_ERR(hmfs_matcher);
+		goto err_free_rule;
+	}
+	hmfs_rule->hmfs_matcher = hmfs_matcher;
+
+	mlx5_ct_fs_hmfs_fill_rule_actions(fs_hmfs, attr, rule_actions);
+	hmfs_rule->counter = attr->counter;
+
+	hmfs_rule->hws_bwc_rule =
+		mlx5hws_bwc_rule_create(hmfs_matcher->hws_bwc_matcher, &match_params,
+					spec->flow_context.flow_source, rule_actions);
+	if (!hmfs_rule->hws_bwc_rule) {
+		err = -EINVAL;
+		goto err_put_matcher;
+	}
+
+	return &hmfs_rule->fs_rule;
+
+err_put_matcher:
+	mlx5_fc_put_hws_action(hmfs_rule->counter);
+	mlx5_ct_fs_hmfs_matcher_put(fs, hmfs_matcher);
+err_free_rule:
+	kfree(hmfs_rule);
+	return ERR_PTR(err);
+}
+
+static void mlx5_ct_fs_hmfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule)
+{
+	struct mlx5_ct_fs_hmfs_rule *hmfs_rule = container_of(fs_rule,
+							      struct mlx5_ct_fs_hmfs_rule,
+							      fs_rule);
+	mlx5hws_bwc_rule_destroy(hmfs_rule->hws_bwc_rule);
+	mlx5_fc_put_hws_action(hmfs_rule->counter);
+	mlx5_ct_fs_hmfs_matcher_put(fs, hmfs_rule->hmfs_matcher);
+	kfree(hmfs_rule);
+}
+
+static int mlx5_ct_fs_hmfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule,
+					  struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr)
+{
+	struct mlx5_ct_fs_hmfs_rule *hmfs_rule = container_of(fs_rule,
+							      struct mlx5_ct_fs_hmfs_rule,
+							      fs_rule);
+	struct mlx5hws_rule_action rule_actions[NUM_CT_HMFS_RULES];
+	struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs);
+	int err;
+
+	mlx5_ct_fs_hmfs_fill_rule_actions(fs_hmfs, attr, rule_actions);
+
+	err = mlx5hws_bwc_rule_action_update(hmfs_rule->hws_bwc_rule, rule_actions);
+	if (err) {
+		mlx5_fc_put_hws_action(attr->counter);
+		return err;
+	}
+
+	mlx5_fc_put_hws_action(hmfs_rule->counter);
+	hmfs_rule->counter = attr->counter;
+
+	return 0;
+}
+
+static struct mlx5_ct_fs_ops hmfs_ops = {
+	.ct_rule_add = mlx5_ct_fs_hmfs_ct_rule_add,
+	.ct_rule_del = mlx5_ct_fs_hmfs_ct_rule_del,
+	.ct_rule_update = mlx5_ct_fs_hmfs_ct_rule_update,
+
+	.init = mlx5_ct_fs_hmfs_init,
+	.destroy = mlx5_ct_fs_hmfs_destroy,
+
+	.priv_size = sizeof(struct mlx5_ct_fs_hmfs),
+};
+
+struct mlx5_ct_fs_ops *mlx5_ct_fs_hmfs_ops_get(void)
+{
+	return &hmfs_ops;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
index 45737d039252..0c97c5899904 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
@@ -13,7 +13,6 @@
 #define INIT_ERR_PREFIX "ct_fs_smfs init failed"
 #define ct_dbg(fmt, args...)\
 	netdev_dbg(fs->netdev, "ct_fs_smfs debug: " fmt "\n", ##args)
-#define MLX5_CT_TCP_FLAGS_MASK cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16)
 
 struct mlx5_ct_fs_smfs_matcher {
 	struct mlx5dr_matcher *dr_matcher;
@@ -220,78 +219,6 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs)
 	mlx5_smfs_action_destroy(fs_smfs->fwd_action);
 }
 
-static inline bool
-mlx5_tc_ct_valid_used_dissector_keys(const u64 used_keys)
-{
-#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name)
-	const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) |
-				DISS_BIT(META);
-	const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) |
-				DISS_BIT(PORTS) | DISS_BIT(TCP);
-	const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) |
-				DISS_BIT(PORTS) | DISS_BIT(TCP);
-	const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) |
-				DISS_BIT(PORTS);
-	const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) |
-				 DISS_BIT(PORTS);
-	const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS);
-	const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS);
-
-	return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp ||
-		used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre);
-}
-
-static bool
-mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *flow_rule)
-{
-	struct flow_match_ipv4_addrs ipv4_addrs;
-	struct flow_match_ipv6_addrs ipv6_addrs;
-	struct flow_match_control control;
-	struct flow_match_basic basic;
-	struct flow_match_ports ports;
-	struct flow_match_tcp tcp;
-
-	if (!mlx5_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) {
-		ct_dbg("rule uses unexpected dissectors (0x%016llx)",
-		       flow_rule->match.dissector->used_keys);
-		return false;
-	}
-
-	flow_rule_match_basic(flow_rule, &basic);
-	flow_rule_match_control(flow_rule, &control);
-	flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs);
-	flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs);
-	if (basic.key->ip_proto != IPPROTO_GRE)
-		flow_rule_match_ports(flow_rule, &ports);
-	if (basic.key->ip_proto == IPPROTO_TCP)
-		flow_rule_match_tcp(flow_rule, &tcp);
-
-	if (basic.mask->n_proto != htons(0xFFFF) ||
-	    (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) ||
-	    basic.mask->ip_proto != 0xFF ||
-	    (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP &&
-	     basic.key->ip_proto != IPPROTO_GRE)) {
-		ct_dbg("rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)",
-		       ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto),
-		       basic.key->ip_proto, basic.mask->ip_proto);
-		return false;
-	}
-
-	if (basic.key->ip_proto != IPPROTO_GRE &&
-	    (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) {
-		ct_dbg("rule uses ports match (src 0x%04x, dst 0x%04x)",
-		       ports.mask->src, ports.mask->dst);
-		return false;
-	}
-
-	if (basic.key->ip_proto == IPPROTO_TCP && tcp.mask->flags != MLX5_CT_TCP_FLAGS_MASK) {
-		ct_dbg("rule uses unexpected tcp match (flags 0x%02x)", tcp.mask->flags);
-		return false;
-	}
-
-	return true;
-}
-
 static struct mlx5_ct_fs_rule *
 mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec,
 			    struct mlx5_flow_attr *attr, struct flow_rule *flow_rule)
@@ -304,7 +231,7 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec,
 	int num_actions = 0, err;
 	bool nat, tcp, ipv4, gre;
 
-	if (!mlx5_ct_fs_smfs_ct_validate_flow_rule(fs, flow_rule))
+	if (!mlx5e_tc_ct_is_valid_flow_rule(fs->netdev, flow_rule))
 		return ERR_PTR(-EOPNOTSUPP);
 
 	smfs_rule = kzalloc(sizeof(*smfs_rule), GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
index 8218c892b161..7819fb297280 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
@@ -593,3 +593,8 @@ mlx5e_tc_meter_get_stats(struct mlx5e_flow_meter_handle *meter,
 	*drops = packets2;
 	*lastuse = max_t(u64, lastuse1, lastuse2);
 }
+
+int mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter)
+{
+	return meter->meters_obj->base_id;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
index 9b795cd106bb..d6afb6556875 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
@@ -72,4 +72,17 @@ void
 mlx5e_tc_meter_get_stats(struct mlx5e_flow_meter_handle *meter,
 			 u64 *bytes, u64 *packets, u64 *drops, u64 *lastuse);
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
+int mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter);
+
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static inline int
+mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter)
+{
+	return 0;
+}
+#endif /* CONFIG_MLX5_CLS_ACT */
+
 #endif /* __MLX5_EN_FLOW_METER_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index a84ebac2f011..81332cd4a582 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -1349,6 +1349,32 @@ mlx5_tc_ct_block_flow_offload_stats(struct mlx5_ct_ft *ft,
 	return 0;
 }
 
+static bool
+mlx5_tc_ct_filter_legacy_non_nic_flows(struct mlx5_ct_ft *ft,
+				       struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
+	struct flow_match_meta match;
+	struct net_device *netdev;
+	bool same_dev = false;
+
+	if (!is_mdev_legacy_mode(ct_priv->dev) ||
+	    !flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META))
+		return true;
+
+	flow_rule_match_meta(rule, &match);
+
+	if (!(match.key->ingress_ifindex & match.mask->ingress_ifindex))
+		return true;
+
+	netdev = dev_get_by_index(&init_net, match.key->ingress_ifindex);
+	same_dev = ct_priv->netdev == netdev;
+	dev_put(netdev);
+
+	return same_dev;
+}
+
 static int
 mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data,
 			      void *cb_priv)
@@ -1361,6 +1387,9 @@ mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data,
 
 	switch (f->command) {
 	case FLOW_CLS_REPLACE:
+		if (!mlx5_tc_ct_filter_legacy_non_nic_flows(ft, f))
+			return -EOPNOTSUPP;
+
 		return mlx5_tc_ct_block_flow_offload_add(ft, f);
 	case FLOW_CLS_DESTROY:
 		return mlx5_tc_ct_block_flow_offload_del(ft, f);
@@ -2065,10 +2094,19 @@ mlx5_tc_ct_fs_init(struct mlx5_tc_ct_priv *ct_priv)
 	struct mlx5_ct_fs_ops *fs_ops = mlx5_ct_fs_dmfs_ops_get();
 	int err;
 
-	if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB &&
-	    ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) {
-		ct_dbg("Using SMFS ct flow steering provider");
-		fs_ops = mlx5_ct_fs_smfs_ops_get();
+	if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB) {
+		if (ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_HMFS) {
+			ct_dbg("Using HMFS ct flow steering provider");
+			fs_ops = mlx5_ct_fs_hmfs_ops_get();
+		} else if (ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) {
+			ct_dbg("Using SMFS ct flow steering provider");
+			fs_ops = mlx5_ct_fs_smfs_ops_get();
+		}
+
+		if (!fs_ops) {
+			ct_dbg("Requested flow steering mode is not enabled.");
+			return -EOPNOTSUPP;
+		}
 	}
 
 	ct_priv->fs = kzalloc(sizeof(*ct_priv->fs) + fs_ops->priv_size, GFP_KERNEL);
@@ -2421,3 +2459,74 @@ out_inc_drop:
 	atomic_inc(&ct_priv->debugfs.stats.rx_dropped);
 	return false;
 }
+
+static bool mlx5e_tc_ct_valid_used_dissector_keys(const u64 used_keys)
+{
+#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name)
+	const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) |
+				DISS_BIT(META);
+	const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) |
+				DISS_BIT(PORTS) | DISS_BIT(TCP);
+	const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) |
+				DISS_BIT(PORTS) | DISS_BIT(TCP);
+	const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) |
+				DISS_BIT(PORTS);
+	const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) |
+				 DISS_BIT(PORTS);
+	const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS);
+	const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS);
+
+	return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp ||
+		used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre);
+}
+
+bool mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, struct flow_rule *flow_rule)
+{
+	struct flow_match_ipv4_addrs ipv4_addrs;
+	struct flow_match_ipv6_addrs ipv6_addrs;
+	struct flow_match_control control;
+	struct flow_match_basic basic;
+	struct flow_match_ports ports;
+	struct flow_match_tcp tcp;
+
+	if (!mlx5e_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) {
+		netdev_dbg(dev, "ct_debug: rule uses unexpected dissectors (0x%016llx)",
+			   flow_rule->match.dissector->used_keys);
+		return false;
+	}
+
+	flow_rule_match_basic(flow_rule, &basic);
+	flow_rule_match_control(flow_rule, &control);
+	flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs);
+	flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs);
+	if (basic.key->ip_proto != IPPROTO_GRE)
+		flow_rule_match_ports(flow_rule, &ports);
+	if (basic.key->ip_proto == IPPROTO_TCP)
+		flow_rule_match_tcp(flow_rule, &tcp);
+
+	if (basic.mask->n_proto != htons(0xFFFF) ||
+	    (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) ||
+	    basic.mask->ip_proto != 0xFF ||
+	    (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP &&
+	     basic.key->ip_proto != IPPROTO_GRE)) {
+		netdev_dbg(dev, "ct_debug: rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)",
+			   ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto),
+			   basic.key->ip_proto, basic.mask->ip_proto);
+		return false;
+	}
+
+	if (basic.key->ip_proto != IPPROTO_GRE &&
+	    (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) {
+		netdev_dbg(dev, "ct_debug: rule uses ports match (src 0x%04x, dst 0x%04x)",
+			   ports.mask->src, ports.mask->dst);
+		return false;
+	}
+
+	if (basic.key->ip_proto == IPPROTO_TCP && tcp.mask->flags != MLX5_CT_TCP_FLAGS_MASK) {
+		netdev_dbg(dev, "ct_debug: rule uses unexpected tcp match (flags 0x%02x)",
+			   tcp.mask->flags);
+		return false;
+	}
+
+	return true;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index b66c5f98067f..5e9dbdd4a5e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -128,6 +128,9 @@ bool
 mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 			 struct sk_buff *skb, u8 zone_restore_id);
 
+#define MLX5_CT_TCP_FLAGS_MASK cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16)
+bool mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, struct flow_rule *flow_rule);
+
 #else /* CONFIG_MLX5_TC_CT */
 
 static inline struct mlx5_tc_ct_priv *
@@ -202,5 +205,12 @@ mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 	return false;
 }
 
+static inline bool
+mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev,
+			       struct flow_rule *flow_rule)
+{
+	return false;
+}
+
 #endif /* !IS_ENABLED(CONFIG_MLX5_TC_CT) */
 #endif /* __MLX5_EN_TC_CT_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 721f35e59757..2162d776fe35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -31,8 +31,7 @@ static void mlx5e_tc_tun_route_attr_cleanup(struct mlx5e_tc_tun_route_attr *attr
 {
 	if (attr->n)
 		neigh_release(attr->n);
-	if (attr->route_dev)
-		dev_put(attr->route_dev);
+	dev_put(attr->route_dev);
 }
 
 struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev)
@@ -68,16 +67,14 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 	 * while holding rcu read lock. Take the net_device for correctness
 	 * sake.
 	 */
-	if (uplink_upper)
-		dev_hold(uplink_upper);
+	dev_hold(uplink_upper);
 	rcu_read_unlock();
 
 	dst_is_lag_dev = (uplink_upper &&
 			  netif_is_lag_master(uplink_upper) &&
 			  real_dev == uplink_upper &&
 			  mlx5_lag_is_sriov(priv->mdev));
-	if (uplink_upper)
-		dev_put(uplink_upper);
+	dev_put(uplink_upper);
 
 	/* if the egress device isn't on the same HW e-switch or
 	 * it's a LAG device, use the uplink
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 878cbdbf5ec8..a0fc76a1bc08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -5,6 +5,7 @@
 #include <net/nexthop.h>
 #include <net/ip_tunnels.h>
 #include "tc_tun_encap.h"
+#include "fs_core.h"
 #include "en_tc.h"
 #include "tc_tun.h"
 #include "rep/tc.h"
@@ -24,17 +25,24 @@ static int mlx5e_set_int_port_tunnel(struct mlx5e_priv *priv,
 
 	route_dev = dev_get_by_index(dev_net(e->out_dev), e->route_dev_ifindex);
 
-	if (!route_dev || !netif_is_ovs_master(route_dev) ||
-	    attr->parse_attr->filter_dev == e->out_dev)
+	if (!route_dev || !netif_is_ovs_master(route_dev))
 		goto out;
 
+	if (priv->mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS &&
+	    mlx5e_eswitch_uplink_rep(attr->parse_attr->filter_dev) &&
+	    (attr->esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) {
+		mlx5_core_warn(priv->mdev,
+			       "Matching on external port with encap + fwd to table actions is not allowed for firmware steering\n");
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = mlx5e_set_fwd_to_int_port_actions(priv, attr, e->route_dev_ifindex,
 						MLX5E_TC_INT_PORT_EGRESS,
 						&attr->action, out_index);
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 
 	return err;
 }
@@ -744,8 +752,7 @@ static int mlx5e_set_vf_tunnel(struct mlx5_eswitch *esw,
 	}
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 	return err;
 }
 
@@ -779,8 +786,7 @@ static int mlx5e_update_vf_tunnel(struct mlx5_eswitch *esw,
 	mlx5e_tc_match_to_reg_mod_hdr_change(esw->dev, mod_hdr_acts, VPORT_TO_REG, act_id, data);
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index e4e487c8431b..7a18a469961d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -140,7 +140,7 @@ static int mlx5e_tc_tun_parse_vxlan_gbp_option(struct mlx5e_priv *priv,
 	gbp_mask = (u32 *)&enc_opts.mask->data[0];
 
 	if (*gbp_mask & ~VXLAN_GBP_MASK) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "Wrong VxLAN GBP mask(0x%08X)\n", *gbp_mask);
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Wrong VxLAN GBP mask(0x%08X)", *gbp_mask);
 		return -EINVAL;
 	}
 
@@ -165,9 +165,6 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 	struct flow_match_enc_keyid enc_keyid;
 	void *misc_c, *misc_v;
 
-	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
 		return 0;
 
@@ -182,6 +179,30 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 		err = mlx5e_tc_tun_parse_vxlan_gbp_option(priv, spec, f);
 		if (err)
 			return err;
+
+		/* We can't mix custom tunnel headers with symbolic ones and we
+		 * don't have a symbolic field name for GBP, so we use custom
+		 * tunnel headers in this case. We need hardware support to
+		 * match on custom tunnel headers, but we already know it's
+		 * supported because the previous call successfully checked for
+		 * that.
+		 */
+		misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				      misc_parameters_5);
+		misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				      misc_parameters_5);
+
+		/* Shift by 8 to account for the reserved bits in the vxlan
+		 * header after the VNI.
+		 */
+		MLX5_SET(fte_match_set_misc5, misc_c, tunnel_header_1,
+			 be32_to_cpu(enc_keyid.mask->keyid) << 8);
+		MLX5_SET(fte_match_set_misc5, misc_v, tunnel_header_1,
+			 be32_to_cpu(enc_keyid.key->keyid) << 8);
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_5;
+
+		return 0;
 	}
 
 	/* match on VNI is required */
@@ -195,6 +216,11 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
+	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			      misc_parameters);
+	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			      misc_parameters);
+
 	MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
 		 be32_to_cpu(enc_keyid.mask->keyid));
 	MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
index 11f724ad90db..19499072f67f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
@@ -124,7 +124,7 @@ void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
 		const size_t len = MLX5_FLD_SZ_BYTES(tirc, rx_hash_toeplitz_key);
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc, rx_hash_toeplitz_key);
 
-		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
+		MLX5_SET(tirc, tirc, rx_hash_symmetric, rss_hash->symmetric);
 		memcpy(rss_key, rss_hash->toeplitz_hash_key, len);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
index 857a84bcd53a..e8df3aaf6562 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
@@ -9,6 +9,7 @@
 struct mlx5e_rss_params_hash {
 	u8 hfunc;
 	u8 toeplitz_hash_key[40];
+	bool symmetric;
 };
 
 struct mlx5e_rss_params_traffic_type {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 53ca16cb9c41..b5c19396e096 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -46,7 +46,7 @@ static void mlx5e_init_trap_rq(struct mlx5e_trap *t, struct mlx5e_params *params
 	rq->pdev         = t->pdev;
 	rq->netdev       = priv->netdev;
 	rq->priv         = priv;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->tstamp       = &priv->tstamp;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
@@ -149,7 +149,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 	t->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	t->stats    = &priv->trap_stats.ch;
 
-	netif_napi_add(netdev, &t->napi, mlx5e_trap_napi_poll);
+	netif_napi_add_locked(netdev, &t->napi, mlx5e_trap_napi_poll);
 
 	err = mlx5e_open_trap_rq(priv, t);
 	if (unlikely(err))
@@ -164,7 +164,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 err_close_trap_rq:
 	mlx5e_close_trap_rq(&t->rq);
 err_napi_del:
-	netif_napi_del(&t->napi);
+	netif_napi_del_locked(&t->napi);
 	kvfree(t);
 	return ERR_PTR(err);
 }
@@ -173,13 +173,13 @@ void mlx5e_close_trap(struct mlx5e_trap *trap)
 {
 	mlx5e_tir_destroy(&trap->tir);
 	mlx5e_close_trap_rq(&trap->rq);
-	netif_napi_del(&trap->napi);
+	netif_napi_del_locked(&trap->napi);
 	kvfree(trap);
 }
 
 static void mlx5e_activate_trap(struct mlx5e_trap *trap)
 {
-	napi_enable(&trap->napi);
+	napi_enable_locked(&trap->napi);
 	mlx5e_activate_rq(&trap->rq);
 	mlx5e_trigger_napi_sched(&trap->napi);
 }
@@ -189,7 +189,7 @@ void mlx5e_deactivate_trap(struct mlx5e_priv *priv)
 	struct mlx5e_trap *trap = priv->en_trap;
 
 	mlx5e_deactivate_rq(&trap->rq);
-	napi_disable(&trap->napi);
+	napi_disable_locked(&trap->napi);
 }
 
 static struct mlx5e_trap *mlx5e_add_trap_queue(struct mlx5e_priv *priv)
@@ -285,6 +285,7 @@ int mlx5e_handle_trap_event(struct mlx5e_priv *priv, struct mlx5_trap_ctx *trap_
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		return 0;
 
+	netdev_lock(priv->netdev);
 	switch (trap_ctx->action) {
 	case DEVLINK_TRAP_ACTION_TRAP:
 		err = mlx5e_handle_action_trap(priv, trap_ctx->id);
@@ -297,6 +298,7 @@ int mlx5e_handle_trap_event(struct mlx5e_priv *priv, struct mlx5_trap_ctx *trap_
 			    trap_ctx->action);
 		err = -EINVAL;
 	}
+	netdev_unlock(priv->netdev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 5ec468268d1a..e837c21d3d21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -214,6 +214,19 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
 	return pi;
 }
 
+static inline u16 mlx5e_txqsq_get_next_pi_anysize(struct mlx5e_txqsq *sq,
+						  u16 *size)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 pi, contig_wqebbs;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	*size = min_t(u16, contig_wqebbs, sq->max_sq_mpw_wqebbs);
+
+	return pi;
+}
+
 void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq);
 
 static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
@@ -358,9 +371,9 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 
 void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq);
 
-static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs)
+static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session)
 {
-	return session->ds_count == max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS;
+	return session->ds_count == session->ds_count_max;
 }
 
 static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 94b291662087..5ce1b463b7a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -289,9 +289,9 @@ static u64 mlx5e_xsk_fill_timestamp(void *_priv)
 	ts = get_cqe_ts(priv->cqe);
 
 	if (mlx5_is_real_time_rq(priv->cq->mdev) || mlx5_is_real_time_sq(priv->cq->mdev))
-		return mlx5_real_time_cyc2time(&priv->cq->mdev->clock, ts);
+		return mlx5_real_time_cyc2time(priv->cq->mdev->clock, ts);
 
-	return  mlx5_timecounter_cyc2time(&priv->cq->mdev->clock, ts);
+	return  mlx5_timecounter_cyc2time(priv->cq->mdev->clock, ts);
 }
 
 static void mlx5e_xsk_request_checksum(u16 csum_start, u16 csum_offset, void *priv)
@@ -390,6 +390,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 		.wqe = wqe,
 		.bytes_count = 0,
 		.ds_count = MLX5E_TX_WQE_EMPTY_DS_COUNT,
+		.ds_count_max = sq->max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS,
 		.pkt_count = 0,
 		.inline_on = mlx5e_xdp_get_inline_state(sq, session->inline_on),
 	};
@@ -501,7 +502,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, p, stats);
 
-	if (unlikely(mlx5e_xdp_mpwqe_is_full(session, sq->max_sq_mpw_wqebbs)))
+	if (unlikely(mlx5e_xdp_mpwqe_is_full(session)))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	stats->xmit++;
@@ -546,6 +547,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 	bool inline_ok;
 	bool linear;
 	u16 pi;
+	int i;
 
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
@@ -612,41 +614,33 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
 
-	if (test_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state)) {
-		int i;
-
-		memset(&cseg->trailer, 0, sizeof(cseg->trailer));
-		memset(eseg, 0, sizeof(*eseg) - sizeof(eseg->trailer));
-
-		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+	memset(&cseg->trailer, 0, sizeof(cseg->trailer));
+	memset(eseg, 0, sizeof(*eseg) - sizeof(eseg->trailer));
 
-		for (i = 0; i < num_frags; i++) {
-			skb_frag_t *frag = &xdptxdf->sinfo->frags[i];
-			dma_addr_t addr;
+	eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
 
-			addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[i] :
-				page_pool_get_dma_addr(skb_frag_page(frag)) +
-				skb_frag_off(frag);
+	for (i = 0; i < num_frags; i++) {
+		skb_frag_t *frag = &xdptxdf->sinfo->frags[i];
+		dma_addr_t addr;
 
-			dseg->addr = cpu_to_be64(addr);
-			dseg->byte_count = cpu_to_be32(skb_frag_size(frag));
-			dseg->lkey = sq->mkey_be;
-			dseg++;
-		}
+		addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[i] :
+			page_pool_get_dma_addr(skb_frag_page(frag)) +
+			skb_frag_off(frag);
 
-		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+		dseg->addr = cpu_to_be64(addr);
+		dseg->byte_count = cpu_to_be32(skb_frag_size(frag));
+		dseg->lkey = sq->mkey_be;
+		dseg++;
+	}
 
-		sq->db.wqe_info[pi] = (struct mlx5e_xdp_wqe_info) {
-			.num_wqebbs = num_wqebbs,
-			.num_pkts = 1,
-		};
+	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-		sq->pc += num_wqebbs;
-	} else {
-		cseg->fm_ce_se = 0;
+	sq->db.wqe_info[pi] = (struct mlx5e_xdp_wqe_info) {
+		.num_wqebbs = num_wqebbs,
+		.num_pkts = 1,
+	};
 
-		sq->pc++;
-	}
+	sq->pc += num_wqebbs;
 
 	xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg);
 
@@ -713,8 +707,8 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
 				page = xdpi.page.page;
 
-				/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-				 * as we know this is a page_pool page.
+				/* No need to check page_pool_page_is_pp() as we
+				 * know this is a page_pool page.
 				 */
 				page_pool_recycle_direct(page->pp, page);
 			} while (++n < num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index e054db1e10f8..46ab0a9e8cdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -45,12 +45,6 @@
 	(MLX5E_XDP_INLINE_WQE_MAX_DS_CNT * MLX5_SEND_WQE_DS - \
 	 sizeof(struct mlx5_wqe_inline_seg))
 
-struct mlx5e_xdp_buff {
-	struct xdp_buff xdp;
-	struct mlx5_cqe64 *cqe;
-	struct mlx5e_rq *rq;
-};
-
 /* XDP packets can be transmitted in different ways. On completion, we need to
  * distinguish between them to clean up things in a proper way.
  */
@@ -182,13 +176,13 @@ static inline bool mlx5e_xdp_get_inline_state(struct mlx5e_xdpsq *sq, bool cur)
 	return cur;
 }
 
-static inline bool mlx5e_xdp_mpwqe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs)
+static inline bool mlx5e_xdp_mpwqe_is_full(struct mlx5e_tx_mpwqe *session)
 {
 	if (session->inline_on)
 		return session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT >
-		       max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS;
+		       session->ds_count_max;
 
-	return mlx5e_tx_mpwqe_is_full(session, max_sq_mpw_wqebbs);
+	return mlx5e_tx_mpwqe_is_full(session);
 }
 
 struct mlx5e_xdp_wqe_info {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index 1b7132fa70de..2b05536d564a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -123,7 +123,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	bitmap_zero(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	wi->consumed_strides = 0;
 
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((icosq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR);
 
 	/* Optimized for speed: keep in sync with mlx5e_mpwrq_umr_entry_size. */
@@ -134,7 +134,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		offset = offset * sizeof(struct mlx5_klm) * 2 / MLX5_OCTWORD;
 	else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_TRIPLE))
 		offset = offset * sizeof(struct mlx5_ksm) * 4 / MLX5_OCTWORD;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
 
 	icosq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type = MLX5E_ICOSQ_WQE_UMR_RX,
@@ -144,7 +144,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	icosq->pc += rq->mpwqe.umr_wqebbs;
 
-	icosq->doorbell_cseg = &umr_wqe->ctrl;
+	icosq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 9240cfe25d10..d743e823362a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -72,7 +72,7 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c,
 	rq->netdev       = c->netdev;
 	rq->priv         = c->priv;
 	rq->tstamp       = c->tstamp;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
 	rq->channel      = c;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index ca92e518be76..77f61cd28a79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -94,25 +94,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 	u32 esn, esn_msb;
 	u8 overlap;
 
-	switch (x->xso.type) {
-	case XFRM_DEV_OFFLOAD_PACKET:
-		switch (x->xso.dir) {
-		case XFRM_DEV_OFFLOAD_IN:
-			esn = x->replay_esn->seq;
-			esn_msb = x->replay_esn->seq_hi;
-			break;
-		case XFRM_DEV_OFFLOAD_OUT:
-			esn = x->replay_esn->oseq;
-			esn_msb = x->replay_esn->oseq_hi;
-			break;
-		default:
-			WARN_ON(true);
-			return false;
-		}
-		break;
-	case XFRM_DEV_OFFLOAD_CRYPTO:
-		/* Already parsed by XFRM core */
+	switch (x->xso.dir) {
+	case XFRM_DEV_OFFLOAD_IN:
 		esn = x->replay_esn->seq;
+		esn_msb = x->replay_esn->seq_hi;
+		break;
+	case XFRM_DEV_OFFLOAD_OUT:
+		esn = x->replay_esn->oseq;
+		esn_msb = x->replay_esn->oseq_hi;
 		break;
 	default:
 		WARN_ON(true);
@@ -121,11 +110,15 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	overlap = sa_entry->esn_state.overlap;
 
-	if (esn >= x->replay_esn->replay_window)
-		seq_bottom = esn - x->replay_esn->replay_window + 1;
+	if (!x->replay_esn->replay_window) {
+		seq_bottom = esn;
+	} else {
+		if (esn >= x->replay_esn->replay_window)
+			seq_bottom = esn - x->replay_esn->replay_window + 1;
 
-	if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO)
-		esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom));
+		if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO)
+			esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom));
+	}
 
 	if (sa_entry->esn_state.esn_msb)
 		sa_entry->esn_state.esn = esn;
@@ -266,8 +259,7 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry);
-	struct xfrm_state *x = sa_entry->x;
-	struct net_device *netdev;
+	struct net_device *netdev = sa_entry->dev;
 	struct neighbour *n;
 	u8 addr[ETH_ALEN];
 	const void *pkey;
@@ -277,19 +269,17 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	    attrs->type != XFRM_DEV_OFFLOAD_PACKET)
 		return;
 
-	netdev = x->xso.real_dev;
-
 	mlx5_query_mac_address(mdev, addr);
 	switch (attrs->dir) {
 	case XFRM_DEV_OFFLOAD_IN:
 		src = attrs->dmac;
 		dst = attrs->smac;
-		pkey = &attrs->saddr.a4;
+		pkey = &attrs->addrs.saddr.a4;
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		src = attrs->smac;
 		dst = attrs->dmac;
-		pkey = &attrs->daddr.a4;
+		pkey = &attrs->addrs.daddr.a4;
 		break;
 	default:
 		return;
@@ -310,6 +300,16 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	neigh_release(n);
 }
 
+static void mlx5e_ipsec_state_mask(struct mlx5e_ipsec_addr *addrs)
+{
+	/*
+	 * State doesn't have subnet prefixes in outer headers.
+	 * The match is performed for exaxt source/destination addresses.
+	 */
+	memset(addrs->smask.m6, 0xFF, sizeof(__be32) * 4);
+	memset(addrs->dmask.m6, 0xFF, sizeof(__be32) * 4);
+}
+
 void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 					struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
@@ -381,9 +381,11 @@ skip_replay_window:
 	attrs->spi = be32_to_cpu(x->id.spi);
 
 	/* source , destination ips */
-	memcpy(&attrs->saddr, x->props.saddr.a6, sizeof(attrs->saddr));
-	memcpy(&attrs->daddr, x->id.daddr.a6, sizeof(attrs->daddr));
-	attrs->family = x->props.family;
+	memcpy(&attrs->addrs.saddr, x->props.saddr.a6,
+	       sizeof(attrs->addrs.saddr));
+	memcpy(&attrs->addrs.daddr, x->id.daddr.a6, sizeof(attrs->addrs.daddr));
+	attrs->addrs.family = x->props.family;
+	mlx5e_ipsec_state_mask(&attrs->addrs);
 	attrs->type = x->xso.type;
 	attrs->reqid = x->props.reqid;
 	attrs->upspec.dport = ntohs(x->sel.dport);
@@ -435,7 +437,8 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
 	}
 	if (x->encap) {
 		if (!(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ESPINUDP)) {
-			NL_SET_ERR_MSG_MOD(extack, "Encapsulation is not supported");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Encapsulation is not supported");
 			return -EINVAL;
 		}
 
@@ -686,17 +689,17 @@ static int mlx5e_ipsec_create_dwork(struct mlx5e_ipsec_sa_entry *sa_entry)
 	return 0;
 }
 
-static int mlx5e_xfrm_add_state(struct xfrm_state *x,
+static int mlx5e_xfrm_add_state(struct net_device *dev,
+				struct xfrm_state *x,
 				struct netlink_ext_ack *extack)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = NULL;
-	struct net_device *netdev = x->xso.real_dev;
 	struct mlx5e_ipsec *ipsec;
 	struct mlx5e_priv *priv;
 	gfp_t gfp;
 	int err;
 
-	priv = netdev_priv(netdev);
+	priv = netdev_priv(dev);
 	if (!priv->ipsec)
 		return -EOPNOTSUPP;
 
@@ -707,6 +710,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 		return -ENOMEM;
 
 	sa_entry->x = x;
+	sa_entry->dev = dev;
 	sa_entry->ipsec = ipsec;
 	/* Check if this SA is originated from acquire flow temporary SA */
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
@@ -724,6 +728,12 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 	/* check esn */
 	if (x->props.flags & XFRM_STATE_ESN)
 		mlx5e_ipsec_update_esn_state(sa_entry);
+	else
+		/* According to RFC4303, section "3.3.3. Sequence Number Generation",
+		 * the first packet sent using a given SA will contain a sequence
+		 * number of 1.
+		 */
+		sa_entry->esn_state.esn = 1;
 
 	mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &sa_entry->attrs);
 
@@ -768,9 +778,12 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 				   MLX5_IPSEC_RESCHED);
 
 	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET &&
-	    x->props.mode == XFRM_MODE_TUNNEL)
-		xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id,
-			    MLX5E_IPSEC_TUNNEL_SA);
+	    x->props.mode == XFRM_MODE_TUNNEL) {
+		xa_lock_bh(&ipsec->sadb);
+		__xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id,
+			      MLX5E_IPSEC_TUNNEL_SA);
+		xa_unlock_bh(&ipsec->sadb);
+	}
 
 out:
 	x->xso.offload_handle = (unsigned long)sa_entry;
@@ -794,10 +807,9 @@ err_xfrm:
 	return err;
 }
 
-static void mlx5e_xfrm_del_state(struct xfrm_state *x)
+static void mlx5e_xfrm_del_state(struct net_device *dev, struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
-	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 	struct mlx5e_ipsec_sa_entry *old;
 
@@ -806,15 +818,9 @@ static void mlx5e_xfrm_del_state(struct xfrm_state *x)
 
 	old = xa_erase_bh(&ipsec->sadb, sa_entry->ipsec_obj_id);
 	WARN_ON(old != sa_entry);
-
-	if (attrs->mode == XFRM_MODE_TUNNEL &&
-	    attrs->type == XFRM_DEV_OFFLOAD_PACKET)
-		/* Make sure that no ARP requests are running in parallel */
-		flush_workqueue(ipsec->wq);
-
 }
 
-static void mlx5e_xfrm_free_state(struct xfrm_state *x)
+static void mlx5e_xfrm_free_state(struct net_device *dev, struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
@@ -847,8 +853,6 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 	struct mlx5e_ipsec_sa_entry *sa_entry;
 	struct mlx5e_ipsec *ipsec;
 	struct neighbour *n = ptr;
-	struct net_device *netdev;
-	struct xfrm_state *x;
 	unsigned long idx;
 
 	if (event != NETEVENT_NEIGH_UPDATE || !(n->nud_state & NUD_VALID))
@@ -858,21 +862,19 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 	xa_for_each_marked(&ipsec->sadb, idx, sa_entry, MLX5E_IPSEC_TUNNEL_SA) {
 		attrs = &sa_entry->attrs;
 
-		if (attrs->family == AF_INET) {
-			if (!neigh_key_eq32(n, &attrs->saddr.a4) &&
-			    !neigh_key_eq32(n, &attrs->daddr.a4))
+		if (attrs->addrs.family == AF_INET) {
+			if (!neigh_key_eq32(n, &attrs->addrs.saddr.a4) &&
+			    !neigh_key_eq32(n, &attrs->addrs.daddr.a4))
 				continue;
 		} else {
-			if (!neigh_key_eq128(n, &attrs->saddr.a4) &&
-			    !neigh_key_eq128(n, &attrs->daddr.a4))
+			if (!neigh_key_eq128(n, &attrs->addrs.saddr.a4) &&
+			    !neigh_key_eq128(n, &attrs->addrs.daddr.a4))
 				continue;
 		}
 
-		x = sa_entry->x;
-		netdev = x->xso.real_dev;
 		data = sa_entry->work->data;
 
-		neigh_ha_snapshot(data->addr, n, netdev);
+		neigh_ha_snapshot(data->addr, n, sa_entry->dev);
 		queue_work(ipsec->wq, &sa_entry->work->work);
 	}
 
@@ -958,21 +960,6 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv)
 	priv->ipsec = NULL;
 }
 
-static bool mlx5e_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
-{
-	if (x->props.family == AF_INET) {
-		/* Offload with IPv4 options is not supported yet */
-		if (ip_hdr(skb)->ihl > 5)
-			return false;
-	} else {
-		/* Offload with IPv6 extension headers is not support yet */
-		if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
-			return false;
-	}
-
-	return true;
-}
-
 static void mlx5e_xfrm_advance_esn_state(struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
@@ -1003,8 +990,8 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	size_t headers;
 
 	lockdep_assert(lockdep_is_held(&x->lock) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_state_lock));
+		       lockdep_is_held(&net->xfrm.xfrm_cfg_mutex) ||
+		       lockdep_is_held(&net->xfrm.xfrm_state_lock));
 
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
 		return;
@@ -1040,7 +1027,7 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	 * by removing always available headers.
 	 */
 	headers = sizeof(struct ethhdr);
-	if (sa_entry->attrs.family == AF_INET)
+	if (sa_entry->attrs.addrs.family == AF_INET)
 		headers += sizeof(struct iphdr);
 	else
 		headers += sizeof(struct ipv6hdr);
@@ -1049,6 +1036,43 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	x->curlft.bytes += success_bytes - headers * success_packets;
 }
 
+static __be32 word_to_mask(int prefix)
+{
+	if (prefix < 0)
+		return 0;
+
+	if (!prefix || prefix > 31)
+		return cpu_to_be32(0xFFFFFFFF);
+
+	return cpu_to_be32(((1U << prefix) - 1) << (32 - prefix));
+}
+
+static void mlx5e_ipsec_policy_mask(struct mlx5e_ipsec_addr *addrs,
+				    struct xfrm_selector *sel)
+{
+	int i;
+
+	if (addrs->family == AF_INET) {
+		addrs->smask.m4 = word_to_mask(sel->prefixlen_s);
+		addrs->saddr.a4 &= addrs->smask.m4;
+		addrs->dmask.m4 = word_to_mask(sel->prefixlen_d);
+		addrs->daddr.a4 &= addrs->dmask.m4;
+		return;
+	}
+
+	for (i = 0; i < 4; i++) {
+		if (sel->prefixlen_s != 32 * i)
+			addrs->smask.m6[i] =
+				word_to_mask(sel->prefixlen_s - 32 * i);
+		addrs->saddr.a6[i] &= addrs->smask.m6[i];
+
+		if (sel->prefixlen_d != 32 * i)
+			addrs->dmask.m6[i] =
+				word_to_mask(sel->prefixlen_d - 32 * i);
+		addrs->daddr.a6[i] &= addrs->dmask.m6[i];
+	}
+}
+
 static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
 				      struct xfrm_policy *x,
 				      struct netlink_ext_ack *extack)
@@ -1121,9 +1145,10 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry,
 	sel = &x->selector;
 	memset(attrs, 0, sizeof(*attrs));
 
-	memcpy(&attrs->saddr, sel->saddr.a6, sizeof(attrs->saddr));
-	memcpy(&attrs->daddr, sel->daddr.a6, sizeof(attrs->daddr));
-	attrs->family = sel->family;
+	memcpy(&attrs->addrs.saddr, sel->saddr.a6, sizeof(attrs->addrs.saddr));
+	memcpy(&attrs->addrs.daddr, sel->daddr.a6, sizeof(attrs->addrs.daddr));
+	attrs->addrs.family = sel->family;
+	mlx5e_ipsec_policy_mask(&attrs->addrs, sel);
 	attrs->dir = x->xdo.dir;
 	attrs->action = x->action;
 	attrs->type = XFRM_DEV_OFFLOAD_PACKET;
@@ -1139,7 +1164,7 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry,
 static int mlx5e_xfrm_add_policy(struct xfrm_policy *x,
 				 struct netlink_ext_ack *extack)
 {
-	struct net_device *netdev = x->xdo.real_dev;
+	struct net_device *netdev = x->xdo.dev;
 	struct mlx5e_ipsec_pol_entry *pol_entry;
 	struct mlx5e_priv *priv;
 	int err;
@@ -1201,7 +1226,6 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_add	= mlx5e_xfrm_add_state,
 	.xdo_dev_state_delete	= mlx5e_xfrm_del_state,
 	.xdo_dev_state_free	= mlx5e_xfrm_free_state,
-	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
 
 	.xdo_dev_state_update_stats = mlx5e_xfrm_update_stats,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 7d943e93cf6d..ffcd0cdeb775 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -76,27 +76,36 @@ struct mlx5_replay_esn {
 	u8 trigger : 1;
 };
 
-struct mlx5_accel_esp_xfrm_attrs {
-	u32   spi;
-	u32   mode;
-	struct aes_gcm_keymat aes_gcm;
-
+struct mlx5e_ipsec_addr {
 	union {
 		__be32 a4;
 		__be32 a6[4];
 	} saddr;
-
+	union {
+		__be32 m4;
+		__be32 m6[4];
+	} smask;
 	union {
 		__be32 a4;
 		__be32 a6[4];
 	} daddr;
+	union {
+		__be32 m4;
+		__be32 m6[4];
+	} dmask;
+	u8 family;
+};
 
+struct mlx5_accel_esp_xfrm_attrs {
+	u32   spi;
+	u32   mode;
+	struct aes_gcm_keymat aes_gcm;
+	struct mlx5e_ipsec_addr addrs;
 	struct upspec upspec;
 	u8 dir : 2;
 	u8 type : 2;
 	u8 drop : 1;
 	u8 encap : 1;
-	u8 family;
 	struct mlx5_replay_esn replay_esn;
 	u32 authsize;
 	u32 reqid;
@@ -128,6 +137,7 @@ struct mlx5e_ipsec_hw_stats {
 	u64 ipsec_rx_bytes;
 	u64 ipsec_rx_drop_pkts;
 	u64 ipsec_rx_drop_bytes;
+	u64 ipsec_rx_drop_mismatch_sa_sel;
 	u64 ipsec_tx_pkts;
 	u64 ipsec_tx_bytes;
 	u64 ipsec_tx_drop_pkts;
@@ -184,6 +194,7 @@ struct mlx5e_ipsec_ft {
 	struct mutex mutex; /* Protect changes to this struct */
 	struct mlx5_flow_table *pol;
 	struct mlx5_flow_table *sa;
+	struct mlx5_flow_table *sa_sel;
 	struct mlx5_flow_table *status;
 	u32 refcnt;
 };
@@ -195,6 +206,8 @@ struct mlx5e_ipsec_drop {
 
 struct mlx5e_ipsec_rule {
 	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_handle *status_pass;
+	struct mlx5_flow_handle *sa_sel;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_pkt_reformat *pkt_reformat;
 	struct mlx5_fc *fc;
@@ -206,6 +219,7 @@ struct mlx5e_ipsec_rule {
 struct mlx5e_ipsec_miss {
 	struct mlx5_flow_group *group;
 	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *fc;
 };
 
 struct mlx5e_ipsec_tx_create_attr {
@@ -260,6 +274,7 @@ struct mlx5e_ipsec_limits {
 struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_esn_state esn_state;
 	struct xfrm_state *x;
+	struct net_device *dev;
 	struct mlx5e_ipsec *ipsec;
 	struct mlx5_accel_esp_xfrm_attrs attrs;
 	void (*set_iv_op)(struct sk_buff *skb, struct xfrm_state *x,
@@ -274,18 +289,8 @@ struct mlx5e_ipsec_sa_entry {
 };
 
 struct mlx5_accel_pol_xfrm_attrs {
-	union {
-		__be32 a4;
-		__be32 a6[4];
-	} saddr;
-
-	union {
-		__be32 a4;
-		__be32 a6[4];
-	} daddr;
-
+	struct mlx5e_ipsec_addr addrs;
 	struct upspec upspec;
-	u8 family;
 	u8 action;
 	u8 type : 2;
 	u8 dir : 2;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index e51b03d4c717..98b6a3a623f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -16,6 +16,16 @@
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16
 #define IPSEC_TUNNEL_DEFAULT_TTL 0x40
 
+#define MLX5_IPSEC_FS_SA_SELECTOR_MAX_NUM_GROUPS 16
+
+enum {
+	MLX5_IPSEC_ASO_OK,
+	MLX5_IPSEC_ASO_BAD_REPLY,
+
+	/* For crypto offload, set by driver */
+	MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD = 0xAA,
+};
+
 struct mlx5e_ipsec_fc {
 	struct mlx5_fc *cnt;
 	struct mlx5_fc *drop;
@@ -33,6 +43,9 @@ struct mlx5e_ipsec_tx {
 };
 
 struct mlx5e_ipsec_status_checks {
+	struct mlx5_flow_group *pass_group;
+	struct mlx5_flow_handle *packet_offload_pass_rule;
+	struct mlx5_flow_handle *crypto_offload_pass_rule;
 	struct mlx5_flow_group *drop_all_group;
 	struct mlx5e_ipsec_drop all;
 };
@@ -41,10 +54,12 @@ struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
 	struct mlx5e_ipsec_miss sa;
-	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_status_checks status_drops;
+	struct mlx5e_ipsec_miss sa_sel;
+	struct mlx5e_ipsec_status_checks status_checks;
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
+	struct mlx5_flow_table *pol_miss_ft;
+	struct mlx5_flow_handle *pol_miss_rule;
 	u8 allow_tunnel_mode : 1;
 };
 
@@ -130,11 +145,12 @@ static void ipsec_chains_put_table(struct mlx5_fs_chains *chains, u32 prio)
 
 static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 					       int level, int prio,
+					       int num_reserved_entries,
 					       int max_num_groups, u32 flags)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 
-	ft_attr.autogroup.num_reserved_entries = 1;
+	ft_attr.autogroup.num_reserved_entries = num_reserved_entries;
 	ft_attr.autogroup.max_num_groups = max_num_groups;
 	ft_attr.max_fte = NUM_IPSEC_FTE;
 	ft_attr.level = level;
@@ -147,22 +163,35 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
-	mlx5_del_flow_rules(rx->status_drops.all.rule);
-	mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc);
-	mlx5_destroy_flow_group(rx->status_drops.drop_all_group);
+	mlx5_del_flow_rules(rx->status_checks.all.rule);
+	mlx5_fc_destroy(ipsec->mdev, rx->status_checks.all.fc);
+	mlx5_destroy_flow_group(rx->status_checks.drop_all_group);
 }
 
 static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
-	mlx5_del_flow_rules(rx->status.rule);
+	mlx5_del_flow_rules(rx->status_checks.packet_offload_pass_rule);
+	mlx5_del_flow_rules(rx->status_checks.crypto_offload_pass_rule);
+}
 
-	if (rx != ipsec->rx_esw)
-		return;
+static void ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					struct mlx5e_ipsec_rx *rx,
+					struct mlx5_flow_spec *spec)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 
-#ifdef CONFIG_MLX5_ESWITCH
-	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
-#endif
+	if (rx == ipsec->rx_esw) {
+		mlx5_esw_ipsec_rx_rule_add_match_obj(sa_entry, spec);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters_2.metadata_reg_c_2);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters_2.metadata_reg_c_2,
+			 sa_entry->ipsec_obj_id | BIT(31));
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+	}
 }
 
 static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
@@ -194,17 +223,14 @@ static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	flow_act.flags = FLOW_ACT_NO_APPEND;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(flow_counter);
+	dest.counter = flow_counter;
 	if (rx == ipsec->rx_esw)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
-	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_2,
-		 sa_entry->ipsec_obj_id | BIT(31));
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -223,7 +249,7 @@ static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
 	}
 	sa_entry->ipsec_rule.trailer.fc = flow_counter;
 
-	dest.counter_id = mlx5_fc_id(flow_counter);
+	dest.counter = flow_counter;
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
@@ -275,16 +301,14 @@ static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	flow_act.flags = FLOW_ACT_NO_APPEND;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(flow_counter);
+	dest.counter = flow_counter;
 	if (rx == ipsec->rx_esw)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
-	MLX5_SET(fte_match_param, spec->match_value,  misc_parameters_2.metadata_reg_c_2,
-		 sa_entry->ipsec_obj_id | BIT(31));
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -348,7 +372,7 @@ static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(flow_counter);
+	dest.counter = flow_counter;
 	if (rx == ipsec->rx_esw)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
@@ -359,9 +383,9 @@ static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
 		goto err_rule;
 	}
 
-	rx->status_drops.drop_all_group = g;
-	rx->status_drops.all.rule = rule;
-	rx->status_drops.all.fc = flow_counter;
+	rx->status_checks.drop_all_group = g;
+	rx->status_checks.all.rule = rule;
+	rx->status_checks.all.fc = flow_counter;
 
 	kvfree(flow_group_in);
 	kvfree(spec);
@@ -377,9 +401,52 @@ err_out:
 	return err;
 }
 
-static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
-				       struct mlx5e_ipsec_rx *rx,
-				       struct mlx5_flow_destination *dest)
+static int ipsec_rx_status_pass_group_create(struct mlx5e_ipsec *ipsec,
+					     struct mlx5e_ipsec_rx *rx)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_flow_group *fg;
+	void *match_criteria;
+	u32 *flow_group_in;
+	int err = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS_2);
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
+
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 start_flow_index, ft->max_fte - 3);
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 end_flow_index, ft->max_fte - 2);
+
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_warn(ipsec->mdev,
+			       "Failed to create rx status pass flow group, err=%d\n",
+			       err);
+	}
+	rx->status_checks.pass_group = fg;
+
+	kvfree(flow_group_in);
+	return err;
+}
+
+static struct mlx5_flow_handle *
+ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
+			    struct mlx5e_ipsec_rx *rx,
+			    struct mlx5_flow_destination *dest,
+			    u8 aso_ok)
 {
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
@@ -388,7 +455,7 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 			 misc_parameters_2.ipsec_syndrome);
@@ -397,11 +464,11 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 	MLX5_SET(fte_match_param, spec->match_value,
 		 misc_parameters_2.ipsec_syndrome, 0);
 	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_4, 0);
+		 misc_parameters_2.metadata_reg_c_4, aso_ok);
 	if (rx == ipsec->rx_esw)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
-	flow_act.flags = FLOW_ACT_NO_APPEND;
+	flow_act.flags = FLOW_ACT_NO_APPEND | FLOW_ACT_IGNORE_FLOW_LEVEL;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
@@ -412,19 +479,19 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 		goto err_rule;
 	}
 
-	rx->status.rule = rule;
 	kvfree(spec);
-	return 0;
+	return rule;
 
 err_rule:
 	kvfree(spec);
-	return err;
+	return ERR_PTR(err);
 }
 
 static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
 	ipsec_rx_status_pass_destroy(ipsec, rx);
+	mlx5_destroy_flow_group(rx->status_checks.pass_group);
 	ipsec_rx_status_drop_destroy(ipsec, rx);
 }
 
@@ -432,19 +499,44 @@ static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx *rx,
 				       struct mlx5_flow_destination *dest)
 {
+	struct mlx5_flow_destination pol_dest[2];
+	struct mlx5_flow_handle *rule;
 	int err;
 
 	err = ipsec_rx_status_drop_all_create(ipsec, rx);
 	if (err)
 		return err;
 
-	err = ipsec_rx_status_pass_create(ipsec, rx, dest);
+	err = ipsec_rx_status_pass_group_create(ipsec, rx);
 	if (err)
-		goto err_pass_create;
+		goto err_pass_group_create;
+
+	rule = ipsec_rx_status_pass_create(ipsec, rx, dest,
+					   MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_crypto_offload_pass_create;
+	}
+	rx->status_checks.crypto_offload_pass_rule = rule;
+
+	pol_dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	pol_dest[0].ft = rx->ft.pol;
+	pol_dest[1] = dest[1];
+	rule = ipsec_rx_status_pass_create(ipsec, rx, pol_dest,
+					   MLX5_IPSEC_ASO_OK);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_packet_offload_pass_create;
+	}
+	rx->status_checks.packet_offload_pass_rule = rule;
 
 	return 0;
 
-err_pass_create:
+err_packet_offload_pass_create:
+	mlx5_del_flow_rules(rx->status_checks.crypto_offload_pass_rule);
+err_crypto_offload_pass_create:
+	mlx5_destroy_flow_group(rx->status_checks.pass_group);
+err_pass_group_create:
 	ipsec_rx_status_drop_destroy(ipsec, rx);
 	return err;
 }
@@ -493,6 +585,15 @@ out:
 	return err;
 }
 
+static void ipsec_rx_update_default_dest(struct mlx5e_ipsec_rx *rx,
+					 struct mlx5_flow_destination *old_dest,
+					 struct mlx5_flow_destination *new_dest)
+{
+	mlx5_modify_rule_destination(rx->pol_miss_rule, new_dest, old_dest);
+	mlx5_modify_rule_destination(rx->status_checks.crypto_offload_pass_rule,
+				     new_dest, old_dest);
+}
+
 static void handle_ipsec_rx_bringup(struct mlx5e_ipsec *ipsec, u32 family)
 {
 	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family, XFRM_DEV_OFFLOAD_PACKET);
@@ -507,8 +608,7 @@ static void handle_ipsec_rx_bringup(struct mlx5e_ipsec *ipsec, u32 family)
 
 	new_dest.ft = mlx5_ipsec_fs_roce_ft_get(ipsec->roce, family);
 	new_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	mlx5_modify_rule_destination(rx->status.rule, &new_dest, &old_dest);
-	mlx5_modify_rule_destination(rx->sa.rule, &new_dest, &old_dest);
+	ipsec_rx_update_default_dest(rx, &old_dest, &new_dest);
 }
 
 static void handle_ipsec_rx_cleanup(struct mlx5e_ipsec *ipsec, u32 family)
@@ -520,8 +620,7 @@ static void handle_ipsec_rx_cleanup(struct mlx5e_ipsec *ipsec, u32 family)
 	old_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	new_dest = mlx5_ttc_get_default_dest(mlx5e_fs_get_ttc(ipsec->fs, false),
 					     family2tt(family));
-	mlx5_modify_rule_destination(rx->sa.rule, &new_dest, &old_dest);
-	mlx5_modify_rule_destination(rx->status.rule, &new_dest, &old_dest);
+	ipsec_rx_update_default_dest(rx, &old_dest, &new_dest);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, ipsec->mdev);
 }
@@ -577,13 +676,8 @@ static void ipsec_rx_ft_disconnect(struct mlx5e_ipsec *ipsec, u32 family)
 	mlx5_ttc_fwd_default_dest(ttc, family2tt(family));
 }
 
-static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
-		       struct mlx5e_ipsec_rx *rx, u32 family)
+static void ipsec_rx_policy_destroy(struct mlx5e_ipsec_rx *rx)
 {
-	/* disconnect */
-	if (rx != ipsec->rx_esw)
-		ipsec_rx_ft_disconnect(ipsec, family);
-
 	if (rx->chains) {
 		ipsec_chains_destroy(rx->chains);
 	} else {
@@ -592,6 +686,29 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		mlx5_destroy_flow_table(rx->ft.pol);
 	}
 
+	if (rx->pol_miss_rule) {
+		mlx5_del_flow_rules(rx->pol_miss_rule);
+		mlx5_destroy_flow_table(rx->pol_miss_ft);
+	}
+}
+
+static void ipsec_rx_sa_selector_destroy(struct mlx5_core_dev *mdev,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	mlx5_del_flow_rules(rx->sa_sel.rule);
+	mlx5_fc_destroy(mdev, rx->sa_sel.fc);
+	rx->sa_sel.fc = NULL;
+	mlx5_destroy_flow_group(rx->sa_sel.group);
+	mlx5_destroy_flow_table(rx->ft.sa_sel);
+}
+
+static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
+		       struct mlx5e_ipsec_rx *rx, u32 family)
+{
+	/* disconnect */
+	if (rx != ipsec->rx_esw)
+		ipsec_rx_ft_disconnect(ipsec, family);
+
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 	mlx5_destroy_flow_table(rx->ft.sa);
@@ -600,7 +717,17 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 	mlx5_destroy_flow_table(rx->ft.status);
 
+	ipsec_rx_sa_selector_destroy(mdev, rx);
+
+	ipsec_rx_policy_destroy(rx);
+
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
+
+#ifdef CONFIG_MLX5_ESWITCH
+	if (rx == ipsec->rx_esw)
+		mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch),
+				      0, 1, 0);
+#endif
 }
 
 static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
@@ -652,6 +779,28 @@ static int ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 	return 0;
 }
 
+static void ipsec_rx_sa_miss_dest_get(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx,
+				      struct mlx5e_ipsec_rx_create_attr *attr,
+				      struct mlx5_flow_destination *dest,
+				      struct mlx5_flow_destination *miss_dest)
+{
+	if (rx == ipsec->rx_esw)
+		*miss_dest = *dest;
+	else
+		*miss_dest =
+			mlx5_ttc_get_default_dest(attr->ttc,
+						  family2tt(attr->family));
+}
+
+static void ipsec_rx_default_dest_get(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx,
+				      struct mlx5_flow_destination *dest)
+{
+	dest->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest->ft = rx->pol_miss_ft;
+}
+
 static void ipsec_rx_ft_connect(struct mlx5e_ipsec *ipsec,
 				struct mlx5e_ipsec_rx *rx,
 				struct mlx5e_ipsec_rx_create_attr *attr)
@@ -659,15 +808,219 @@ static void ipsec_rx_ft_connect(struct mlx5e_ipsec *ipsec,
 	struct mlx5_flow_destination dest = {};
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft = rx->ft.pol;
+	dest.ft = rx->ft.sa;
 	mlx5_ttc_fwd_dest(attr->ttc, family2tt(attr->family), &dest);
 }
 
+static int ipsec_rx_chains_create_miss(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5e_ipsec_rx_create_attr *attr,
+				       struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	if (rx == ipsec->rx_esw) {
+		/* No need to create miss table for switchdev mode,
+		 * just set it to the root chain table.
+		 */
+		rx->pol_miss_ft = dest->ft;
+		return 0;
+	}
+
+	ft_attr.max_fte = 1;
+	ft_attr.autogroup.max_num_groups = 1;
+	ft_attr.level = attr->pol_level;
+	ft_attr.prio = attr->prio;
+
+	ft = mlx5_create_auto_grouped_flow_table(attr->ns, &ft_attr);
+	if (IS_ERR(ft))
+		return PTR_ERR(ft);
+
+	rule = mlx5_add_flow_rules(ft, NULL, &flow_act, dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_rule;
+	}
+
+	rx->pol_miss_ft = ft;
+	rx->pol_miss_rule = rule;
+
+	return 0;
+
+err_rule:
+	mlx5_destroy_flow_table(ft);
+	return err;
+}
+
+static int ipsec_rx_policy_create(struct mlx5e_ipsec *ipsec,
+				  struct mlx5e_ipsec_rx *rx,
+				  struct mlx5e_ipsec_rx_create_attr *attr,
+				  struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_destination default_dest;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	err = ipsec_rx_chains_create_miss(ipsec, rx, attr, dest);
+	if (err)
+		return err;
+
+	ipsec_rx_default_dest_get(ipsec, rx, &default_dest);
+
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
+		rx->chains = ipsec_chains_create(mdev,
+						 default_dest.ft,
+						 attr->chains_ns,
+						 attr->prio,
+						 attr->sa_level,
+						 &rx->ft.pol);
+		if (IS_ERR(rx->chains))
+			err = PTR_ERR(rx->chains);
+	} else {
+		ft = ipsec_ft_create(attr->ns, attr->pol_level,
+				     attr->prio, 1, 2, 0);
+		if (IS_ERR(ft)) {
+			err = PTR_ERR(ft);
+			goto err_out;
+		}
+		rx->ft.pol = ft;
+
+		err = ipsec_miss_create(mdev, rx->ft.pol, &rx->pol,
+					&default_dest);
+		if (err)
+			mlx5_destroy_flow_table(rx->ft.pol);
+	}
+
+	if (!err)
+		return 0;
+
+err_out:
+	if (rx->pol_miss_rule) {
+		mlx5_del_flow_rules(rx->pol_miss_rule);
+		mlx5_destroy_flow_table(rx->pol_miss_ft);
+	}
+	return err;
+}
+
+static int ipsec_rx_sa_selector_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5e_ipsec_rx_create_attr *attr)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_destination dest;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	u32 *flow_group_in;
+	struct mlx5_fc *fc;
+	int err;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	ft = ipsec_ft_create(attr->ns, attr->status_level, attr->prio, 1,
+			     MLX5_IPSEC_FS_SA_SELECTOR_MAX_NUM_GROUPS, 0);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "Failed to create RX SA selector flow table, err=%d\n",
+			      err);
+		goto err_ft;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index,
+		 ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ft->max_fte - 1);
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_err(mdev, "Failed to create RX SA selector miss group, err=%d\n",
+			      err);
+		goto err_fg;
+	}
+
+	fc = mlx5_fc_create(mdev, false);
+	if (IS_ERR(fc)) {
+		err = PTR_ERR(fc);
+		mlx5_core_err(mdev,
+			      "Failed to create ipsec RX SA selector miss rule counter, err=%d\n",
+			      err);
+		goto err_cnt;
+	}
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter = fc;
+	flow_act.action =
+		MLX5_FLOW_CONTEXT_ACTION_COUNT | MLX5_FLOW_CONTEXT_ACTION_DROP;
+
+	rule = mlx5_add_flow_rules(ft, NULL, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Failed to create RX SA selector miss drop rule, err=%d\n",
+			      err);
+		goto err_rule;
+	}
+
+	rx->ft.sa_sel = ft;
+	rx->sa_sel.group = fg;
+	rx->sa_sel.fc = fc;
+	rx->sa_sel.rule = rule;
+
+	kvfree(flow_group_in);
+
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, fc);
+err_cnt:
+	mlx5_destroy_flow_group(fg);
+err_fg:
+	mlx5_destroy_flow_table(ft);
+err_ft:
+	kvfree(flow_group_in);
+	return err;
+}
+
+/* The decryption processing is as follows:
+ *
+ *   +----------+                         +-------------+
+ *   |          |                         |             |
+ *   |  Kernel  <--------------+----------+ policy miss <------------+
+ *   |          |              ^          |             |            ^
+ *   +----^-----+              |          +-------------+            |
+ *        |                  crypto                                  |
+ *      miss                offload ok                         allow/default
+ *        ^                    ^                                     ^
+ *        |                    |                  packet             |
+ *   +----+---------+     +----+-------------+   offload ok   +------+---+
+ *   |              |     |                  |   (no UPSPEC)  |          |
+ *   | SA (decrypt) +----->      status      +--->------->----+  policy  |
+ *   |              |     |                  |                |          |
+ *   +--------------+     ++---------+-------+                +-^----+---+
+ *                         |         |                          |    |
+ *                         v        packet             +-->->---+    v
+ *                         |       offload ok        match           |
+ *                       fails    (with UPSPEC)        |           block
+ *                         |         |   +-------------+-+           |
+ *                         v         v   |               |  miss     v
+ *                        drop       +--->    SA sel     +--------->drop
+ *                                       |               |
+ *                                       +---------------+
+ */
+
 static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		     struct mlx5e_ipsec_rx *rx, u32 family)
 {
+	struct mlx5_flow_destination dest[2], miss_dest;
 	struct mlx5e_ipsec_rx_create_attr attr;
-	struct mlx5_flow_destination dest[2];
 	struct mlx5_flow_table *ft;
 	u32 flags = 0;
 	int err;
@@ -678,80 +1031,61 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 4, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;
 	}
 	rx->ft.status = ft;
 
-	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
-	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
+	err = ipsec_rx_sa_selector_create(ipsec, rx, &attr);
 	if (err)
-		goto err_add;
+		goto err_fs_ft_sa_sel;
 
 	/* Create FT */
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
 		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (rx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 2, flags);
+	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 1, 2, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft;
 	}
 	rx->ft.sa = ft;
 
-	err = ipsec_miss_create(mdev, rx->ft.sa, &rx->sa, dest);
+	ipsec_rx_sa_miss_dest_get(ipsec, rx, &attr, &dest[0], &miss_dest);
+	err = ipsec_miss_create(mdev, rx->ft.sa, &rx->sa, &miss_dest);
 	if (err)
 		goto err_fs;
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
-		rx->chains = ipsec_chains_create(mdev, rx->ft.sa,
-						 attr.chains_ns,
-						 attr.prio,
-						 attr.pol_level,
-						 &rx->ft.pol);
-		if (IS_ERR(rx->chains)) {
-			err = PTR_ERR(rx->chains);
-			goto err_pol_ft;
-		}
-
-		goto connect;
-	}
+	err = ipsec_rx_policy_create(ipsec, rx, &attr, &dest[0]);
+	if (err)
+		goto err_policy;
 
-	ft = ipsec_ft_create(attr.ns, attr.pol_level, attr.prio, 2, 0);
-	if (IS_ERR(ft)) {
-		err = PTR_ERR(ft);
-		goto err_pol_ft;
-	}
-	rx->ft.pol = ft;
-	memset(dest, 0x00, 2 * sizeof(*dest));
-	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[0].ft = rx->ft.sa;
-	err = ipsec_miss_create(mdev, rx->ft.pol, &rx->pol, dest);
+	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[1].counter = rx->fc->cnt;
+	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
 	if (err)
-		goto err_pol_miss;
+		goto err_add;
 
-connect:
 	/* connect */
 	if (rx != ipsec->rx_esw)
 		ipsec_rx_ft_connect(ipsec, rx, &attr);
 	return 0;
 
-err_pol_miss:
-	mlx5_destroy_flow_table(rx->ft.pol);
-err_pol_ft:
+err_add:
+	ipsec_rx_policy_destroy(rx);
+err_policy:
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 err_fs:
 	mlx5_destroy_flow_table(rx->ft.sa);
-err_fs_ft:
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	mlx5_ipsec_rx_status_destroy(ipsec, rx);
-err_add:
+err_fs_ft:
+	ipsec_rx_sa_selector_destroy(mdev, rx);
+err_fs_ft_sa_sel:
 	mlx5_destroy_flow_table(rx->ft.status);
 err_fs_ft_status:
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
@@ -873,7 +1207,7 @@ static int ipsec_counter_rule_tx(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW |
 			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(tx->fc->cnt);
+	dest.counter = tx->fc->cnt;
 	fte = mlx5_add_flow_rules(tx->ft.status, spec, &flow_act, &dest, 1);
 	if (IS_ERR(fte)) {
 		err = PTR_ERR(fte);
@@ -941,7 +1275,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	int err;
 
 	ipsec_tx_create_attr_set(ipsec, tx, &attr);
-	ft = ipsec_ft_create(tx->ns, attr.cnt_level, attr.prio, 1, 0);
+	ft = ipsec_ft_create(tx->ns, attr.cnt_level, attr.prio, 1, 1, 0);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 	tx->ft.status = ft;
@@ -954,7 +1288,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (tx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 4, flags);
+	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 1, 4, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_sa_ft;
@@ -982,7 +1316,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		goto connect_roce;
 	}
 
-	ft = ipsec_ft_create(tx->ns, attr.pol_level, attr.prio, 2, 0);
+	ft = ipsec_ft_create(tx->ns, attr.pol_level, attr.prio, 1, 2, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_pol_ft;
@@ -1150,9 +1484,14 @@ static void tx_ft_put_policy(struct mlx5e_ipsec *ipsec, u32 prio, int type)
 	mutex_unlock(&tx->ft.mutex);
 }
 
-static void setup_fte_addr4(struct mlx5_flow_spec *spec, __be32 *saddr,
-			    __be32 *daddr)
+static void setup_fte_addr4(struct mlx5_flow_spec *spec,
+			    struct mlx5e_ipsec_addr *addrs)
 {
+	__be32 *saddr = &addrs->saddr.a4;
+	__be32 *smask = &addrs->smask.m4;
+	__be32 *daddr = &addrs->daddr.a4;
+	__be32 *dmask = &addrs->dmask.m4;
+
 	if (!*saddr && !*daddr)
 		return;
 
@@ -1164,21 +1503,26 @@ static void setup_fte_addr4(struct mlx5_flow_spec *spec, __be32 *saddr,
 	if (*saddr) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), saddr, 4);
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-				 outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), smask, 4);
 	}
 
 	if (*daddr) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), daddr, 4);
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-				 outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), dmask, 4);
 	}
 }
 
-static void setup_fte_addr6(struct mlx5_flow_spec *spec, __be32 *saddr,
-			    __be32 *daddr)
+static void setup_fte_addr6(struct mlx5_flow_spec *spec,
+			    struct mlx5e_ipsec_addr *addrs)
 {
+	__be32 *saddr = addrs->saddr.a6;
+	__be32 *smask = addrs->smask.m6;
+	__be32 *daddr = addrs->daddr.a6;
+	__be32 *dmask = addrs->dmask.m6;
+
 	if (addr6_all_zero(saddr) && addr6_all_zero(daddr))
 		return;
 
@@ -1190,15 +1534,15 @@ static void setup_fte_addr6(struct mlx5_flow_spec *spec, __be32 *saddr,
 	if (!addr6_all_zero(saddr)) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), saddr, 16);
-		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), 0xff, 16);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), dmask, 16);
 	}
 
 	if (!addr6_all_zero(daddr)) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), daddr, 16);
-		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), 0xff, 16);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), smask, 16);
 	}
 }
 
@@ -1340,7 +1684,8 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 				 MLX5_ACTION_TYPE_SET);
 			MLX5_SET(set_action_in, action[2], field,
 				 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
-			MLX5_SET(set_action_in, action[2], data, 0);
+			MLX5_SET(set_action_in, action[2], data,
+				 MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD);
 			MLX5_SET(set_action_in, action[2], offset, 0);
 			MLX5_SET(set_action_in, action[2], length, 32);
 		}
@@ -1387,7 +1732,7 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) {
 		bfflen += sizeof(*esp_hdr) + 8;
 
-		switch (attrs->family) {
+		switch (attrs->addrs.family) {
 		case AF_INET:
 			bfflen += sizeof(*iphdr);
 			break;
@@ -1404,7 +1749,7 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 		return -ENOMEM;
 
 	eth_hdr = (struct ethhdr *)reformatbf;
-	switch (attrs->family) {
+	switch (attrs->addrs.family) {
 	case AF_INET:
 		eth_hdr->h_proto = htons(ETH_P_IP);
 		break;
@@ -1427,11 +1772,11 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 		reformat_params->param_0 = attrs->authsize;
 
 		hdr = reformatbf + sizeof(*eth_hdr);
-		switch (attrs->family) {
+		switch (attrs->addrs.family) {
 		case AF_INET:
 			iphdr = (struct iphdr *)hdr;
-			memcpy(&iphdr->saddr, &attrs->saddr.a4, 4);
-			memcpy(&iphdr->daddr, &attrs->daddr.a4, 4);
+			memcpy(&iphdr->saddr, &attrs->addrs.saddr.a4, 4);
+			memcpy(&iphdr->daddr, &attrs->addrs.daddr.a4, 4);
 			iphdr->version = 4;
 			iphdr->ihl = 5;
 			iphdr->ttl = IPSEC_TUNNEL_DEFAULT_TTL;
@@ -1440,8 +1785,8 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 			break;
 		case AF_INET6:
 			ipv6hdr = (struct ipv6hdr *)hdr;
-			memcpy(&ipv6hdr->saddr, &attrs->saddr.a6, 16);
-			memcpy(&ipv6hdr->daddr, &attrs->daddr.a6, 16);
+			memcpy(&ipv6hdr->saddr, &attrs->addrs.saddr.a6, 16);
+			memcpy(&ipv6hdr->daddr, &attrs->addrs.daddr.a6, 16);
 			ipv6hdr->nexthdr = IPPROTO_ESP;
 			ipv6hdr->version = 6;
 			ipv6hdr->hop_limit = IPSEC_TUNNEL_DEFAULT_TTL;
@@ -1475,7 +1820,7 @@ static int get_reformat_type(struct mlx5_accel_esp_xfrm_attrs *attrs)
 			return MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP;
 		return MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT;
 	case XFRM_DEV_OFFLOAD_OUT:
-		if (attrs->family == AF_INET) {
+		if (attrs->addrs.family == AF_INET) {
 			if (attrs->encap)
 				return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV4;
 			return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4;
@@ -1576,6 +1921,85 @@ static int setup_pkt_reformat(struct mlx5e_ipsec *ipsec,
 	return 0;
 }
 
+static int rx_add_rule_sa_selector(struct mlx5e_ipsec_sa_entry *sa_entry,
+				   struct mlx5e_ipsec_rx *rx,
+				   struct upspec *upspec)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest[2];
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_4, 0);
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest[0].ft = rx->ft.sa_sel;
+	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[1].counter = rx->fc->cnt;
+
+	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx pass rule, err=%d\n",
+			      err);
+		goto err_add_status_pass_rule;
+	}
+
+	sa_entry->ipsec_rule.status_pass = rule;
+
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_4, 0);
+
+	setup_fte_upper_proto_match(spec, upspec);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest[0].ft = rx->ft.pol;
+
+	rule = mlx5_add_flow_rules(rx->ft.sa_sel, spec, &flow_act, &dest[0], 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx sa selector rule, err=%d\n",
+			      err);
+		goto err_add_sa_sel_rule;
+	}
+
+	sa_entry->ipsec_rule.sa_sel = rule;
+
+	kvfree(spec);
+	return 0;
+
+err_add_sa_sel_rule:
+	mlx5_del_flow_rules(sa_entry->ipsec_rule.status_pass);
+err_add_status_pass_rule:
+	kvfree(spec);
+	return err;
+}
+
 static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
@@ -1589,7 +2013,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5_fc *counter;
 	int err = 0;
 
-	rx = rx_ft_get(mdev, ipsec, attrs->family, attrs->type);
+	rx = rx_ft_get(mdev, ipsec, attrs->addrs.family, attrs->type);
 	if (IS_ERR(rx))
 		return PTR_ERR(rx);
 
@@ -1599,16 +2023,15 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_spi(spec, attrs->spi, attrs->encap);
 	if (!attrs->encap)
 		setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
-	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
 	if (!attrs->drop) {
 		if (rx != ipsec->rx_esw)
@@ -1649,13 +2072,20 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[0].ft = rx->ft.status;
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[1].counter_id = mlx5_fc_id(counter);
+	dest[1].counter = counter;
 	rule = mlx5_add_flow_rules(rx->ft.sa, spec, &flow_act, dest, 2);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err);
 		goto err_add_flow;
 	}
+
+	if (attrs->upspec.proto && attrs->type == XFRM_DEV_OFFLOAD_PACKET) {
+		err = rx_add_rule_sa_selector(sa_entry, rx, &attrs->upspec);
+		if (err)
+			goto err_add_sa_sel;
+	}
+
 	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
 		err = rx_add_rule_drop_replay(sa_entry, rx);
 	if (err)
@@ -1679,6 +2109,11 @@ err_drop_reason:
 		mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc);
 	}
 err_add_replay:
+	if (sa_entry->ipsec_rule.sa_sel) {
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.sa_sel);
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.status_pass);
+	}
+err_add_sa_sel:
 	mlx5_del_flow_rules(rule);
 err_add_flow:
 	mlx5_fc_destroy(mdev, counter);
@@ -1691,7 +2126,7 @@ err_pkt_reformat:
 err_mod_header:
 	kvfree(spec);
 err_alloc:
-	rx_ft_put(ipsec, attrs->family, attrs->type);
+	rx_ft_put(ipsec, attrs->addrs.family, attrs->type);
 	return err;
 }
 
@@ -1718,23 +2153,21 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
-	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
-
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_CRYPTO:
+		if (attrs->addrs.family == AF_INET)
+			setup_fte_addr4(spec, &attrs->addrs);
+		else
+			setup_fte_addr6(spec, &attrs->addrs);
 		setup_fte_spi(spec, attrs->spi, false);
 		setup_fte_esp(spec);
 		setup_fte_reg_a(spec);
 		break;
 	case XFRM_DEV_OFFLOAD_PACKET:
-		if (attrs->reqid)
-			setup_fte_reg_c4(spec, attrs->reqid);
+		setup_fte_reg_c4(spec, attrs->reqid);
 		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;
@@ -1762,7 +2195,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	dest[0].ft = tx->ft.status;
 	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[1].counter_id = mlx5_fc_id(counter);
+	dest[1].counter = counter;
 	rule = mlx5_add_flow_rules(tx->ft.sa, spec, &flow_act, dest, 2);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -1812,10 +2245,10 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	}
 
 	tx = ipsec_tx(ipsec, attrs->type);
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
@@ -1835,7 +2268,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
 				   MLX5_FLOW_CONTEXT_ACTION_COUNT;
 		dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		dest[dstn].counter_id = mlx5_fc_id(tx->fc->drop);
+		dest[dstn].counter = tx->fc->drop;
 		dstn++;
 		break;
 	default:
@@ -1885,12 +2318,12 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	struct mlx5e_ipsec_rx *rx;
 	int err, dstn = 0;
 
-	ft = rx_ft_get_policy(mdev, pol_entry->ipsec, attrs->family, attrs->prio,
-			      attrs->type);
+	ft = rx_ft_get_policy(mdev, pol_entry->ipsec, attrs->addrs.family,
+			      attrs->prio, attrs->type);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 
-	rx = ipsec_rx(pol_entry->ipsec, attrs->family, attrs->type);
+	rx = ipsec_rx(pol_entry->ipsec, attrs->addrs.family, attrs->type);
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec) {
@@ -1898,10 +2331,10 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
@@ -1913,7 +2346,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	case XFRM_POLICY_BLOCK:
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
 		dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		dest[dstn].counter_id = mlx5_fc_id(rx->fc->drop);
+		dest[dstn].counter = rx->fc->drop;
 		dstn++;
 		break;
 	default:
@@ -1925,8 +2358,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
 	if (rx == ipsec->rx_esw && rx->chains)
 		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
-	dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[dstn].ft = rx->ft.sa;
+	ipsec_rx_default_dest_get(ipsec, rx, &dest[dstn]);
 	dstn++;
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, dstn);
 	if (IS_ERR(rule)) {
@@ -1942,7 +2374,8 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 err_action:
 	kvfree(spec);
 err_alloc:
-	rx_ft_put_policy(pol_entry->ipsec, attrs->family, attrs->prio, attrs->type);
+	rx_ft_put_policy(pol_entry->ipsec, attrs->addrs.family, attrs->prio,
+			 attrs->type);
 	return err;
 }
 
@@ -2063,6 +2496,7 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	stats->ipsec_rx_bytes = 0;
 	stats->ipsec_rx_drop_pkts = 0;
 	stats->ipsec_rx_drop_bytes = 0;
+	stats->ipsec_rx_drop_mismatch_sa_sel = 0;
 	stats->ipsec_tx_pkts = 0;
 	stats->ipsec_tx_bytes = 0;
 	stats->ipsec_tx_drop_pkts = 0;
@@ -2072,6 +2506,9 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_rx_pkts, &stats->ipsec_rx_bytes);
 	mlx5_fc_query(mdev, fc->drop, &stats->ipsec_rx_drop_pkts,
 		      &stats->ipsec_rx_drop_bytes);
+	if (ipsec->rx_ipv4->sa_sel.fc)
+		mlx5_fc_query(mdev, ipsec->rx_ipv4->sa_sel.fc,
+			      &stats->ipsec_rx_drop_mismatch_sa_sel, &bytes);
 
 	fc = ipsec->tx->fc;
 	mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_tx_pkts, &stats->ipsec_tx_bytes);
@@ -2100,6 +2537,11 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 			stats->ipsec_tx_drop_pkts += packets;
 			stats->ipsec_tx_drop_bytes += bytes;
 		}
+
+		if (ipsec->rx_esw->sa_sel.fc &&
+		    !mlx5_fc_query(mdev, ipsec->rx_esw->sa_sel.fc,
+				   &packets, &bytes))
+			stats->ipsec_rx_drop_mismatch_sa_sel += packets;
 	}
 }
 
@@ -2197,12 +2639,18 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	mlx5_del_flow_rules(ipsec_rule->auth.rule);
 	mlx5_fc_destroy(mdev, ipsec_rule->auth.fc);
 
+	if (ipsec_rule->sa_sel) {
+		mlx5_del_flow_rules(ipsec_rule->sa_sel);
+		mlx5_del_flow_rules(ipsec_rule->status_pass);
+	}
+
 	if (ipsec_rule->replay.rule) {
 		mlx5_del_flow_rules(ipsec_rule->replay.rule);
 		mlx5_fc_destroy(mdev, ipsec_rule->replay.fc);
 	}
 	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
-	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
+	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.addrs.family,
+		  sa_entry->attrs.type);
 }
 
 int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
@@ -2238,7 +2686,8 @@ void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
 	mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev);
 
 	if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) {
-		rx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.family,
+		rx_ft_put_policy(pol_entry->ipsec,
+				 pol_entry->attrs.addrs.family,
 				 pol_entry->attrs.prio, pol_entry->attrs.type);
 		return;
 	}
@@ -2378,7 +2827,7 @@ bool mlx5e_ipsec_fs_tunnel_enabled(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5e_ipsec_rx *rx;
 	struct mlx5e_ipsec_tx *tx;
 
-	rx = ipsec_rx(sa_entry->ipsec, attrs->family, attrs->type);
+	rx = ipsec_rx(sa_entry->ipsec, attrs->addrs.family, attrs->type);
 	tx = ipsec_tx(sa_entry->ipsec, attrs->type);
 	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT)
 		return tx->allow_tunnel_mode;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 53cfa39188cb..820debf3fbbf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -91,8 +91,9 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 EXPORT_SYMBOL_GPL(mlx5_ipsec_device_caps);
 
 static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
-				     struct mlx5_accel_esp_xfrm_attrs *attrs)
+				     struct mlx5e_ipsec_sa_entry *sa_entry)
 {
+	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
 	void *aso_ctx;
 
 	aso_ctx = MLX5_ADDR_OF(ipsec_obj, obj, ipsec_aso);
@@ -120,8 +121,12 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
 	 * active.
 	 */
 	MLX5_SET(ipsec_obj, obj, aso_return_reg, MLX5_IPSEC_ASO_REG_C_4_5);
-	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT)
+	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) {
 		MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_INC_SN);
+		if (!attrs->replay_esn.trigger)
+			MLX5_SET(ipsec_aso, aso_ctx, mode_parameter,
+				 sa_entry->esn_state.esn);
+	}
 
 	if (attrs->lft.hard_packet_limit != XFRM_INF) {
 		MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt,
@@ -175,7 +180,7 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	res = &mdev->mlx5e_res.hw_objs;
 	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
-		mlx5e_ipsec_packet_setup(obj, res->pdn, attrs);
+		mlx5e_ipsec_packet_setup(obj, res->pdn, sa_entry);
 
 	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (!err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
index 92bf3fa44a3b..93be388068f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
@@ -42,6 +42,7 @@ static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_pkts) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_mismatch_sa_sel) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_pkts) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_drop_pkts) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index cc9bcc420032..6ab02f3fc291 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -339,9 +339,13 @@ static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx,
 {
 	struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev);
 	struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs;
+	const struct macsec_tx_sc *tx_sc = &ctx->secy->tx_sc;
 	struct mlx5_macsec_rule_attrs rule_attrs;
 	union mlx5_macsec_rule *macsec_rule;
 
+	if (is_tx && tx_sc->encoding_sa != sa->assoc_num)
+		return 0;
+
 	rule_attrs.macsec_obj_id = sa->macsec_obj_id;
 	rule_attrs.sci = sa->sci;
 	rule_attrs.assoc_num = sa->assoc_num;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 8705cffc747f..5fe016e477b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1147,6 +1147,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 	bool reset = true;
 	int err;
 
+	netdev_lock(priv->netdev);
 	mutex_lock(&priv->state_lock);
 
 	new_params = priv->channels.params;
@@ -1162,6 +1163,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 				       &trust_state, reset);
 
 	mutex_unlock(&priv->state_lock);
+	netdev_unlock(priv->netdev);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index cae39198b4db..3cb8d3bf9044 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -42,6 +42,8 @@
 #include "lib/clock.h"
 #include "en/fs_ethtool.h"
 
+#define LANES_UNKNOWN		 0
+
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
 {
@@ -237,14 +239,33 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT,
 				       ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT,
 				       ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT);
-}
-
-static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_1_200GBASE_CR1_KR1, ext,
+				       ETHTOOL_LINK_MODE_200000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseVR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_2_400GBASE_CR2_KR2, ext,
+				       ETHTOOL_LINK_MODE_400000baseCR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR2_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseSR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseVR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_800GAUI_4_800GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_800000baseCR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT);
+}
+
+static void mlx5e_ethtool_get_speed_arr(bool ext,
 					struct ptys2ethtool_config **arr,
 					u32 *size)
 {
-	bool ext = mlx5_ptys_ext_supported(mdev);
-
 	*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
 	*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
 		      ARRAY_SIZE(ptys2legacy_ethtool_table);
@@ -891,37 +912,19 @@ int mlx5e_set_per_queue_coalesce(struct net_device *dev, u32 queue,
 	return mlx5e_ethtool_set_per_queue_coalesce(priv, queue, coal);
 }
 
-static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev,
-					unsigned long *supported_modes,
-					u32 eth_proto_cap)
+static void ptys2ethtool_process_link(u32 eth_eproto, bool ext, bool advertised,
+				      unsigned long *modes)
 {
-	unsigned long proto_cap = eth_proto_cap;
+	unsigned long eproto = eth_eproto;
 	struct ptys2ethtool_config *table;
 	u32 max_size;
 	int proto;
 
-	mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size);
-	for_each_set_bit(proto, &proto_cap, max_size)
-		bitmap_or(supported_modes, supported_modes,
-			  table[proto].supported,
-			  __ETHTOOL_LINK_MODE_MASK_NBITS);
-}
-
-static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
-				    u32 eth_proto_cap, bool ext)
-{
-	unsigned long proto_cap = eth_proto_cap;
-	struct ptys2ethtool_config *table;
-	u32 max_size;
-	int proto;
-
-	table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
-	max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
-			 ARRAY_SIZE(ptys2legacy_ethtool_table);
-
-	for_each_set_bit(proto, &proto_cap, max_size)
-		bitmap_or(advertising_modes, advertising_modes,
-			  table[proto].advertised,
+	mlx5e_ethtool_get_speed_arr(ext, &table, &max_size);
+	for_each_set_bit(proto, &eproto, max_size)
+		bitmap_or(modes, modes,
+			  advertised ?
+			  table[proto].advertised : table[proto].supported,
 			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
@@ -931,6 +934,7 @@ static const u32 pplm_fec_2_ethtool[] = {
 	[MLX5E_FEC_RS_528_514] = ETHTOOL_FEC_RS,
 	[MLX5E_FEC_RS_544_514] = ETHTOOL_FEC_RS,
 	[MLX5E_FEC_LLRS_272_257_1] = ETHTOOL_FEC_LLRS,
+	[MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD] = ETHTOOL_FEC_RS,
 };
 
 static u32 pplm2ethtool_fec(u_long fec_mode, unsigned long size)
@@ -1074,50 +1078,51 @@ static void ptys2ethtool_supported_advertised_port(struct mlx5_core_dev *mdev,
 	}
 }
 
-static void get_speed_duplex(struct net_device *netdev,
-			     u32 eth_proto_oper, bool force_legacy,
-			     u16 data_rate_oper,
-			     struct ethtool_link_ksettings *link_ksettings)
+static void get_link_properties(struct net_device *netdev,
+				u32 eth_proto_oper, bool force_legacy,
+				u16 data_rate_oper,
+				struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	u32 speed = SPEED_UNKNOWN;
+	const struct mlx5_link_info *info;
 	u8 duplex = DUPLEX_UNKNOWN;
+	u32 speed = SPEED_UNKNOWN;
+	u32 lanes = LANES_UNKNOWN;
 
 	if (!netif_carrier_ok(netdev))
 		goto out;
 
-	speed = mlx5_port_ptys2speed(priv->mdev, eth_proto_oper, force_legacy);
-	if (!speed) {
-		if (data_rate_oper)
-			speed = 100 * data_rate_oper;
-		else
-			speed = SPEED_UNKNOWN;
-		goto out;
-	}
-
-	duplex = DUPLEX_FULL;
+	info = mlx5_port_ptys2info(priv->mdev, eth_proto_oper, force_legacy);
+	if (info) {
+		speed = info->speed;
+		lanes = info->lanes;
+		duplex = DUPLEX_FULL;
+	} else if (data_rate_oper)
+		speed = 100 * data_rate_oper;
 
 out:
-	link_ksettings->base.speed = speed;
 	link_ksettings->base.duplex = duplex;
+	link_ksettings->base.speed = speed;
+	link_ksettings->lanes = lanes;
 }
 
 static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
 			  struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *supported = link_ksettings->link_modes.supported;
-	ptys2ethtool_supported_link(mdev, supported, eth_proto_cap);
+	bool ext = mlx5_ptys_ext_supported(mdev);
+
+	ptys2ethtool_process_link(eth_proto_cap, ext, false, supported);
 
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
 }
 
-static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause,
+static void get_advertising(u32 eth_proto_admin, u8 tx_pause, u8 rx_pause,
 			    struct ethtool_link_ksettings *link_ksettings,
 			    bool ext)
 {
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
-	ptys2ethtool_adver_link(advertising, eth_proto_cap, ext);
-
+	ptys2ethtool_process_link(eth_proto_admin, ext, true, advertising);
 	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)
@@ -1173,7 +1178,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
 	bool ext = mlx5_ptys_ext_supported(mdev);
 
-	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
+	ptys2ethtool_process_link(eth_proto_lp, ext, true, lp_advertising);
 }
 
 static int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
@@ -1235,8 +1240,8 @@ static int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	get_supported(mdev, eth_proto_cap, link_ksettings);
 	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
 			admin_ext);
-	get_speed_duplex(priv->netdev, eth_proto_oper, !admin_ext,
-			 data_rate_oper, link_ksettings);
+	get_link_properties(priv->netdev, eth_proto_oper, !admin_ext,
+			    data_rate_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 	connector_type = connector_type < MLX5E_CONNECTOR_TYPE_NUMBER ?
@@ -1341,28 +1346,22 @@ static bool ext_link_mode_requested(const unsigned long *adver)
 	return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static bool ext_requested(u8 autoneg, const unsigned long *adver, bool ext_supported)
-{
-	bool ext_link_mode = ext_link_mode_requested(adver);
-
-	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_supported;
-}
-
 static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 					    const struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_port_eth_proto eproto;
+	struct mlx5_link_info info = {};
 	const unsigned long *adver;
 	bool an_changes = false;
 	u8 an_disable_admin;
 	bool ext_supported;
+	bool ext_requested;
 	u8 an_disable_cap;
 	bool an_disable;
 	u32 link_modes;
 	u8 an_status;
 	u8 autoneg;
-	u32 speed;
 	bool ext;
 	int err;
 
@@ -1370,13 +1369,15 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 
 	adver = link_ksettings->link_modes.advertising;
 	autoneg = link_ksettings->base.autoneg;
-	speed = link_ksettings->base.speed;
+	info.speed = link_ksettings->base.speed;
+	info.lanes = link_ksettings->lanes;
 
 	ext_supported = mlx5_ptys_ext_supported(mdev);
-	ext = ext_requested(autoneg, adver, ext_supported);
-	if (!ext_supported && ext)
+	ext_requested = ext_link_mode_requested(adver);
+	if (!ext_supported && ext_requested)
 		return -EOPNOTSUPP;
 
+	ext = autoneg == AUTONEG_ENABLE ? ext_requested : ext_supported;
 	ethtool2ptys_adver_func = ext ? mlx5e_ethtool2ptys_ext_adver_link :
 				  mlx5e_ethtool2ptys_adver_link;
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
@@ -1386,7 +1387,7 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 		goto out;
 	}
 	link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
-		mlx5_port_speed2linkmodes(mdev, speed, !ext);
+		mlx5_port_info2linkmodes(mdev, &info, !ext);
 
 	err = mlx5e_speed_validate(priv->netdev, ext, link_modes, autoneg);
 	if (err)
@@ -1458,18 +1459,27 @@ static int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u32 rss_context = rxfh->rss_context;
+	bool symmetric;
 	int err;
 
 	mutex_lock(&priv->state_lock);
 	err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context,
-					rxfh->indir, rxfh->key, &rxfh->hfunc);
+					rxfh->indir, rxfh->key, &rxfh->hfunc, &symmetric);
 	mutex_unlock(&priv->state_lock);
-	return err;
+
+	if (err)
+		return err;
+
+	if (symmetric)
+		rxfh->input_xfrm = RXH_XFRM_SYM_OR_XOR;
+
+	return 0;
 }
 
 static int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
 			  struct netlink_ext_ack *extack)
 {
+	bool symmetric = rxfh->input_xfrm == RXH_XFRM_SYM_OR_XOR;
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	u32 *rss_context = &rxfh->rss_context;
 	u8 hfunc = rxfh->hfunc;
@@ -1504,7 +1514,8 @@ static int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxf
 
 	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context,
 					rxfh->indir, rxfh->key,
-					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
+					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc,
+					rxfh->input_xfrm == RXH_XFRM_NO_CHANGE ? NULL : &symmetric);
 
 unlock:
 	mutex_unlock(&priv->state_lock);
@@ -1675,6 +1686,7 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 		return 0;
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_TX_SOFTWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
 
@@ -2018,7 +2030,7 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev,
 		if (size_read < 0) {
 			NL_SET_ERR_MSG_FMT_MOD(
 				extack,
-				"Query module eeprom by page failed, read %u bytes, err %d\n",
+				"Query module eeprom by page failed, read %u bytes, err %d",
 				i, size_read);
 			return i;
 		}
@@ -2045,14 +2057,9 @@ int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	dev_hold(dev);
-	rtnl_unlock();
-
 	err = mlx5_firmware_flash(mdev, fw, NULL);
 	release_firmware(fw);
 
-	rtnl_lock();
-	dev_put(dev);
 	return err;
 }
 
@@ -2607,12 +2614,14 @@ static void mlx5e_get_ts_stats(struct net_device *netdev,
 }
 
 const struct ethtool_ops mlx5e_ethtool_ops = {
+	.cap_link_lanes_supported = true,
 	.cap_rss_ctx_supported	= true,
 	.rxfh_per_ctx_key	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_USE_CQE,
+	.supported_input_xfrm = RXH_XFRM_SYM_OR_XOR,
 	.get_drvinfo       = mlx5e_get_drvinfo,
 	.get_link          = ethtool_op_get_link,
 	.get_link_ext_state  = mlx5e_get_link_ext_state,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 05058710d2c7..04a969128161 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -484,7 +484,9 @@ static int mlx5e_vlan_rx_add_svid(struct mlx5e_flow_steering *fs,
 	}
 
 	/* Need to fix some features.. */
+	netdev_lock(netdev);
 	netdev_update_features(netdev);
+	netdev_unlock(netdev);
 	return err;
 }
 
@@ -521,7 +523,9 @@ int mlx5e_fs_vlan_rx_kill_vid(struct mlx5e_flow_steering *fs,
 	} else if (be16_to_cpu(proto) == ETH_P_8021AD) {
 		clear_bit(vid, fs->vlan->active_svlans);
 		mlx5e_fs_del_vlan_rule(fs, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, vid);
+		netdev_lock(netdev);
 		netdev_update_features(netdev);
+		netdev_unlock(netdev);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 773624bb2c5d..d68230a7b9f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -884,8 +884,10 @@ static int flow_type_to_traffic_type(u32 flow_type)
 	case ESP_V6_FLOW:
 		return MLX5_TT_IPV6_IPSEC_ESP;
 	case IPV4_FLOW:
+	case IP_USER_FLOW:
 		return MLX5_TT_IPV4;
 	case IPV6_FLOW:
+	case IPV6_USER_FLOW:
 		return MLX5_TT_IPV6;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d0b80b520397..ea822c69d137 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,6 +39,7 @@
 #include <linux/debugfs.h>
 #include <linux/if_bridge.h>
 #include <linux/filter.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
 #include <net/page_pool/types.h>
 #include <net/pkt_sched.h>
@@ -311,8 +312,8 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 				       struct mlx5e_icosq *sq,
 				       struct mlx5e_umr_wqe *wqe)
 {
-	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->ctrl;
-	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
+	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->hdr.ctrl;
+	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->hdr.uctrl;
 	u16 octowords;
 	u8 ds_cnt;
 
@@ -359,7 +360,7 @@ static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, int node)
 	return 0;
 
 err_nomem:
-	kvfree(shampo->bitmap);
+	bitmap_free(shampo->bitmap);
 	kvfree(shampo->pages);
 
 	return -ENOMEM;
@@ -367,7 +368,7 @@ err_nomem:
 
 static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq)
 {
-	kvfree(rq->mpwqe.shampo->bitmap);
+	bitmap_free(rq->mpwqe.shampo->bitmap);
 	kvfree(rq->mpwqe.shampo->pages);
 }
 
@@ -393,7 +394,9 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node)
 		bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	}
 
-	mlx5e_build_umr_wqe(rq, rq->icosq, &rq->mpwqe.umr_wqe);
+	mlx5e_build_umr_wqe(rq, rq->icosq,
+			    container_of(&rq->mpwqe.umr_wqe,
+					 struct mlx5e_umr_wqe, hdr));
 
 	return 0;
 }
@@ -737,7 +740,7 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 	rq->netdev       = c->netdev;
 	rq->priv         = c->priv;
 	rq->tstamp       = c->tstamp;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
 	rq->channel      = c;
@@ -1614,7 +1617,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	int err;
 
 	sq->pdev      = c->pdev;
-	sq->clock     = &mdev->clock;
+	sq->clock     = mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->mdev      = c->mdev;
@@ -1901,7 +1904,20 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
 					      recover_work);
 
+	/* Recovering queues means re-enabling NAPI, which requires the netdev
+	 * instance lock. However, SQ closing flows have to wait for work tasks
+	 * to finish while also holding the netdev instance lock. So either get
+	 * the lock or find that the SQ is no longer enabled and thus this work
+	 * is not relevant anymore.
+	 */
+	while (!netdev_trylock(sq->netdev)) {
+		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))
+			return;
+		msleep(20);
+	}
+
 	mlx5e_reporter_tx_err_cqe(sq);
+	netdev_unlock(sq->netdev);
 }
 
 static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
@@ -2023,41 +2039,12 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 	csp.min_inline_mode = sq->min_inline_mode;
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 
-	if (param->is_xdp_mb)
-		set_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state);
-
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
 	if (err)
 		goto err_free_xdpsq;
 
 	mlx5e_set_xmit_fp(sq, param->is_mpw);
 
-	if (!param->is_mpw && !test_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state)) {
-		unsigned int ds_cnt = MLX5E_TX_WQE_EMPTY_DS_COUNT + 1;
-		unsigned int inline_hdr_sz = 0;
-		int i;
-
-		if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-			inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
-			ds_cnt++;
-		}
-
-		/* Pre initialize fixed WQE fields */
-		for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
-			struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
-			struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-			struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-
-			sq->db.wqe_info[i] = (struct mlx5e_xdp_wqe_info) {
-				.num_wqebbs = 1,
-				.num_pkts   = 1,
-			};
-
-			cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
-			eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
-		}
-	}
-
 	return 0;
 
 err_free_xdpsq:
@@ -2087,7 +2074,7 @@ static struct mlx5e_xdpsq *mlx5e_open_xdpredirect_sq(struct mlx5e_channel *c,
 	struct mlx5e_xdpsq *xdpsq;
 	int err;
 
-	xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, c->cpu);
+	xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!xdpsq)
 		return ERR_PTR(-ENOMEM);
 
@@ -2680,11 +2667,11 @@ void mlx5e_trigger_napi_sched(struct napi_struct *napi)
 
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_params *params,
-			      struct mlx5e_channel_param *cparam,
 			      struct xsk_buff_pool *xsk_pool,
 			      struct mlx5e_channel **cp)
 {
 	struct net_device *netdev = priv->netdev;
+	struct mlx5e_channel_param *cparam;
 	struct mlx5_core_dev *mdev;
 	struct mlx5e_xsk_param xsk;
 	struct mlx5e_channel *c;
@@ -2706,8 +2693,15 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 		return err;
 
 	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
-	if (!c)
-		return -ENOMEM;
+	cparam = kvzalloc(sizeof(*cparam), GFP_KERNEL);
+	if (!c || !cparam) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	err = mlx5e_build_channel_param(mdev, params, cparam);
+	if (err)
+		goto err_free;
 
 	c->priv     = priv;
 	c->mdev     = mdev;
@@ -2725,8 +2719,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->aff_mask = irq_get_effective_affinity_mask(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(mdev, ix);
 
-	netif_napi_add_config(netdev, &c->napi, mlx5e_napi_poll, ix);
-	netif_napi_set_irq(&c->napi, irq);
+	netif_napi_add_config_locked(netdev, &c->napi, mlx5e_napi_poll, ix);
+	netif_napi_set_irq_locked(&c->napi, irq);
 
 	err = mlx5e_open_queues(c, params, cparam);
 	if (unlikely(err))
@@ -2741,14 +2735,17 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 
 	*cp = c;
 
+	kvfree(cparam);
 	return 0;
 
 err_close_queues:
 	mlx5e_close_queues(c);
 
 err_napi_del:
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
+err_free:
+	kvfree(cparam);
 	kvfree(c);
 
 	return err;
@@ -2758,7 +2755,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 {
 	int tc;
 
-	napi_enable(&c->napi);
+	napi_enable_locked(&c->napi);
 
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
@@ -2790,7 +2787,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 		mlx5e_deactivate_txqsq(&c->sq[tc]);
 	mlx5e_qos_deactivate_queues(c);
 
-	napi_disable(&c->napi);
+	napi_disable_locked(&c->napi);
 }
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
@@ -2799,7 +2796,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 		mlx5e_close_xsk(c);
 	mlx5e_close_queues(c);
 	mlx5e_qos_close_queues(c);
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
 	kvfree(c);
 }
@@ -2807,20 +2804,14 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 int mlx5e_open_channels(struct mlx5e_priv *priv,
 			struct mlx5e_channels *chs)
 {
-	struct mlx5e_channel_param *cparam;
 	int err = -ENOMEM;
 	int i;
 
 	chs->num = chs->params.num_channels;
 
 	chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
-	cparam = kvzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
-	if (!chs->c || !cparam)
-		goto err_free;
-
-	err = mlx5e_build_channel_param(priv->mdev, &chs->params, cparam);
-	if (err)
-		goto err_free;
+	if (!chs->c)
+		goto err_out;
 
 	for (i = 0; i < chs->num; i++) {
 		struct xsk_buff_pool *xsk_pool = NULL;
@@ -2828,7 +2819,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 		if (chs->params.xdp_prog)
 			xsk_pool = mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, i);
 
-		err = mlx5e_open_channel(priv, i, &chs->params, cparam, xsk_pool, &chs->c[i]);
+		err = mlx5e_open_channel(priv, i, &chs->params, xsk_pool, &chs->c[i]);
 		if (err)
 			goto err_close_channels;
 	}
@@ -2846,7 +2837,6 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 	}
 
 	mlx5e_health_channels_update(priv);
-	kvfree(cparam);
 	return 0;
 
 err_close_ptp:
@@ -2857,9 +2847,8 @@ err_close_channels:
 	for (i--; i >= 0; i--)
 		mlx5e_close_channel(chs->c[i]);
 
-err_free:
 	kfree(chs->c);
-	kvfree(cparam);
+err_out:
 	chs->num = 0;
 	return err;
 }
@@ -3814,8 +3803,11 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 	/* MQPRIO is another toplevel qdisc that can't be attached
 	 * simultaneously with the offloaded HTB.
 	 */
-	if (WARN_ON(mlx5e_selq_is_htb_enabled(&priv->selq)))
-		return -EINVAL;
+	if (mlx5e_selq_is_htb_enabled(&priv->selq)) {
+		NL_SET_ERR_MSG_MOD(mqprio->extack,
+				   "MQPRIO cannot be configured when HTB offload is enabled.");
+		return -EOPNOTSUPP;
+	}
 
 	switch (mqprio->mode) {
 	case TC_MQPRIO_MODE_DCB:
@@ -3944,6 +3936,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	}
 
 	stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer;
+	stats->rx_dropped = PPORT_2863_GET(pstats, if_in_discards);
 
 	stats->rx_length_errors =
 		PPORT_802_3_GET(pstats, a_in_range_length_errors) +
@@ -4297,7 +4290,7 @@ void mlx5e_set_xdp_feature(struct net_device *netdev)
 
 	if (!netdev->netdev_ops->ndo_bpf ||
 	    params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
-		xdp_clear_features_flag(netdev);
+		xdp_set_features_flag_locked(netdev, 0);
 		return;
 	}
 
@@ -4306,7 +4299,7 @@ void mlx5e_set_xdp_feature(struct net_device *netdev)
 	      NETDEV_XDP_ACT_RX_SG |
 	      NETDEV_XDP_ACT_NDO_XMIT |
 	      NETDEV_XDP_ACT_NDO_XMIT_SG;
-	xdp_set_features_flag(netdev, val);
+	xdp_set_features_flag_locked(netdev, val);
 }
 
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
@@ -4370,6 +4363,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev
 	if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
 		netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n");
 
+	features &= ~NETIF_F_HW_MACSEC;
+	if (netdev->features & NETIF_F_HW_MACSEC)
+		netdev_warn(netdev, "Disabling HW MACsec offload, not supported in switchdev mode\n");
+
 	return features;
 }
 
@@ -4444,9 +4441,9 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 
 	if (mlx5e_is_uplink_rep(priv)) {
 		features = mlx5e_fix_uplink_rep_features(netdev, features);
-		netdev->netns_local = true;
+		netdev->netns_immutable = true;
 	} else {
-		netdev->netns_local = false;
+		netdev->netns_immutable = false;
 	}
 
 	mutex_unlock(&priv->state_lock);
@@ -4985,21 +4982,19 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	struct net_device *netdev = priv->netdev;
 	int i;
 
-	/* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues
-	 * through this flow. However, channel closing flows have to wait for
-	 * this work to finish while holding rtnl lock too. So either get the
-	 * lock or find that channels are being closed for other reason and
-	 * this work is not relevant anymore.
+	/* Recovering the TX queues implies re-enabling NAPI, which requires
+	 * the netdev instance lock.
+	 * However, channel closing flows have to wait for this work to finish
+	 * while holding the same lock. So either get the lock or find that
+	 * channels are being closed for other reason and this work is not
+	 * relevant anymore.
 	 */
-	while (!rtnl_trylock()) {
+	while (!netdev_trylock(netdev)) {
 		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
 			return;
 		msleep(20);
 	}
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto unlock;
-
 	for (i = 0; i < netdev->real_num_tx_queues; i++) {
 		struct netdev_queue *dev_queue =
 			netdev_get_tx_queue(netdev, i);
@@ -5013,8 +5008,7 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 			break;
 	}
 
-unlock:
-	rtnl_unlock();
+	netdev_unlock(netdev);
 }
 
 static void mlx5e_tx_timeout(struct net_device *dev, unsigned int txqueue)
@@ -5129,11 +5123,9 @@ static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 mode, setting;
-	int err;
 
-	err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting);
-	if (err)
-		return err;
+	if (mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting))
+		return -EOPNOTSUPP;
 	mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB;
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
 				       mode,
@@ -5340,7 +5332,6 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i,
 	struct mlx5e_rq_stats *xskrq_stats;
 	struct mlx5e_rq_stats *rq_stats;
 
-	ASSERT_RTNL();
 	if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch)
 		return;
 
@@ -5360,7 +5351,6 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_sq_stats *sq_stats;
 
-	ASSERT_RTNL();
 	if (!priv->stats_nch)
 		return;
 
@@ -5381,7 +5371,6 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 	struct mlx5e_ptp *ptp_channel;
 	int i, tc;
 
-	ASSERT_RTNL();
 	if (!mlx5e_is_uplink_rep(priv)) {
 		rx->packets = 0;
 		rx->bytes = 0;
@@ -5477,6 +5466,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->netdev_ops = &mlx5e_netdev_ops;
 	netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
 	netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 
 	mlx5e_dcbnl_build_netdev(netdev);
 
@@ -5858,9 +5849,11 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	mlx5e_nic_set_rx_mode(priv);
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (netif_running(netdev))
 		mlx5e_open(netdev);
 	udp_tunnel_nic_reset_ntf(priv->netdev);
+	netdev_unlock(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
 }
@@ -5873,9 +5866,16 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 		mlx5e_dcbnl_delete_app(priv);
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	if (netif_running(priv->netdev))
 		mlx5e_close(priv->netdev);
 	netif_device_detach(priv->netdev);
+	if (priv->en_trap) {
+		mlx5e_deactivate_trap(priv);
+		mlx5e_close_trap(priv->en_trap);
+		priv->en_trap = NULL;
+	}
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	mlx5e_nic_set_rx_mode(priv);
@@ -5885,11 +5885,6 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 		mlx5e_monitor_counter_cleanup(priv);
 
 	mlx5e_disable_blocking_events(priv);
-	if (priv->en_trap) {
-		mlx5e_deactivate_trap(priv);
-		mlx5e_close_trap(priv->en_trap);
-		priv->en_trap = NULL;
-	}
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove_netdev(mdev, priv->netdev);
 	mlx5_vxlan_reset_to_default(mdev->vxlan);
@@ -6144,7 +6139,9 @@ static void mlx5e_update_features(struct net_device *netdev)
 		return; /* features will be updated on netdev registration */
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	netdev_update_features(netdev);
+	netdev_unlock(netdev);
 	rtnl_unlock();
 }
 
@@ -6155,7 +6152,7 @@ static void mlx5e_reset_channels(struct net_device *netdev)
 
 int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 {
-	const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED;
+	const bool need_lock = priv->netdev->reg_state == NETREG_REGISTERED;
 	const struct mlx5e_profile *profile = priv->profile;
 	int max_nch;
 	int err;
@@ -6197,15 +6194,19 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	 * 2. Set our default XPS cpumask.
 	 * 3. Build the RQT.
 	 *
-	 * rtnl_lock is required by netif_set_real_num_*_queues in case the
+	 * Locking is required by netif_set_real_num_*_queues in case the
 	 * netdev has been registered by this point (if this function was called
 	 * in the reload or resume flow).
 	 */
-	if (take_rtnl)
+	if (need_lock) {
 		rtnl_lock();
+		netdev_lock(priv->netdev);
+	}
 	err = mlx5e_num_channels_changed(priv);
-	if (take_rtnl)
+	if (need_lock) {
+		netdev_unlock(priv->netdev);
 		rtnl_unlock();
+	}
 	if (err)
 		goto out;
 
@@ -6540,8 +6541,23 @@ static void _mlx5e_remove(struct auxiliary_device *adev)
 
 	mlx5_core_uplink_netdev_set(mdev, NULL);
 	mlx5e_dcbnl_delete_app(priv);
-	unregister_netdev(priv->netdev);
-	_mlx5e_suspend(adev, false);
+	/* When unload driver, the netdev is in registered state
+	 * if it's from legacy mode. If from switchdev mode, it
+	 * is already unregistered before changing to NIC profile.
+	 */
+	if (priv->netdev->reg_state == NETREG_REGISTERED) {
+		unregister_netdev(priv->netdev);
+		_mlx5e_suspend(adev, false);
+	} else {
+		struct mlx5_core_dev *pos;
+		int i;
+
+		if (test_bit(MLX5E_STATE_DESTROYING, &priv->state))
+			mlx5_sd_for_each_dev(i, mdev, pos)
+				mlx5e_destroy_mdev_resources(pos);
+		else
+			_mlx5e_suspend(adev, true);
+	}
 	/* Avoid cleanup if profile rollback failed. */
 	if (priv->profile)
 		priv->profile->cleanup(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 554f9cb5b53f..63a7a788fb0d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -33,6 +33,7 @@
 #include <linux/dim.h>
 #include <linux/debugfs.h>
 #include <linux/mlx5/fs.h>
+#include <net/netdev_lock.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
 #include <net/act_api.h>
@@ -65,6 +66,7 @@
 #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \
 	max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
 #define MLX5E_REP_PARAMS_DEF_NUM_CHANNELS 1
+#define MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE 0x8
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
@@ -802,6 +804,7 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_stop                = mlx5e_rep_close,
 	.ndo_start_xmit          = mlx5e_xmit,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
+	.ndo_set_mac_address	 = eth_mac_addr,
 	.ndo_get_stats64         = mlx5e_rep_get_stats,
 	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
@@ -855,6 +858,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
+	if (!mlx5e_is_uplink_rep(priv) && mlx5_core_is_ecpf(mdev))
+		params->log_rq_mtu_frames = MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE;
 
 	/* If netdev is already registered (e.g. move from nic profile to uplink,
 	 * RTNL lock must be held before triggering netdev notifiers.
@@ -882,10 +887,14 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 {
 	SET_NETDEV_DEV(netdev, mdev->device);
 	netdev->netdev_ops = &mlx5e_netdev_ops_rep;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 	eth_hw_addr_random(netdev);
 	netdev->ethtool_ops = &mlx5e_rep_ethtool_ops;
 
 	netdev->watchdog_timeo    = 15 * HZ;
+	if (mlx5_core_is_ecpf(mdev))
+		netdev->tx_queue_len = 1 << MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 	netdev->hw_features    |= NETIF_F_HW_TC;
@@ -900,7 +909,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 
 	netdev->features |= netdev->hw_features;
 
-	netdev->netns_local = true;
+	netdev->netns_immutable = true;
 }
 
 static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
@@ -1339,9 +1348,11 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	netdev->wanted_features |= NETIF_F_HW_TC;
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (netif_running(netdev))
 		mlx5e_open(netdev);
 	udp_tunnel_nic_reset_ntf(priv->netdev);
+	netdev_unlock(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
 }
@@ -1351,9 +1362,11 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	if (netif_running(priv->netdev))
 		mlx5e_close(priv->netdev);
 	netif_device_detach(priv->netdev);
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	mlx5e_rep_bridge_cleanup(priv);
@@ -1509,6 +1522,21 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv)
 
 	priv = netdev_priv(netdev);
 
+	/* This bit is set when using devlink to change eswitch mode from
+	 * switchdev to legacy. As need to keep uplink netdev ifindex, we
+	 * detach uplink representor profile and attach NIC profile only.
+	 * The netdev will be unregistered later when unload NIC auxiliary
+	 * driver for this case.
+	 * We explicitly block devlink eswitch mode change if any IPSec rules
+	 * offloaded, but can't block other cases, such as driver unload
+	 * and devlink reload. We have to unregister netdev before profile
+	 * change for those cases. This is to avoid resource leak because
+	 * the offloaded rules don't have the chance to be unoffloaded before
+	 * cleanup which is triggered by detach uplink representor profile.
+	 */
+	if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_SWITCH_LEGACY))
+		unregister_netdev(netdev);
+
 	mlx5e_netdev_attach_nic_profile(priv);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1963bc5adb18..84b1ab8233b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -631,16 +631,16 @@ static void build_ksm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe,
 			  __be32 key, u16 offset, u16 ksm_len)
 {
 	memset(umr_wqe, 0, offsetof(struct mlx5e_umr_wqe, inline_ksms));
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			     MLX5_OPCODE_UMR);
-	umr_wqe->ctrl.umr_mkey = key;
-	umr_wqe->ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT)
+	umr_wqe->hdr.ctrl.umr_mkey = key;
+	umr_wqe->hdr.ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT)
 					    | MLX5E_KSM_UMR_DS_CNT(ksm_len));
-	umr_wqe->uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
-	umr_wqe->uctrl.xlt_octowords = cpu_to_be16(ksm_len);
-	umr_wqe->uctrl.mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
+	umr_wqe->hdr.uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_octowords = cpu_to_be16(ksm_len);
+	umr_wqe->hdr.uctrl.mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
 static struct mlx5e_frag_page *mlx5e_shampo_hd_to_frag_page(struct mlx5e_rq *rq, int header_index)
@@ -704,7 +704,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 
 	shampo->pi = (shampo->pi + ksm_entries) & (shampo->hd_per_wq - 1);
 	sq->pc += wqe_bbs;
-	sq->doorbell_cseg = &umr_wqe->ctrl;
+	sq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 
@@ -814,12 +814,12 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	bitmap_zero(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	wi->consumed_strides = 0;
 
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
 
 	offset = (ix * rq->mpwqe.mtts_per_wqe) * sizeof(struct mlx5_mtt) / MLX5_OCTWORD;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type   = MLX5E_ICOSQ_WQE_UMR_RX,
@@ -829,7 +829,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	sq->pc += rq->mpwqe.umr_wqebbs;
 
-	sq->doorbell_cseg = &umr_wqe->ctrl;
+	sq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 
@@ -1684,17 +1684,17 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog) {
-		struct mlx5e_xdp_buff mxbuf;
+		struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 
 		net_prefetchw(va); /* xdp_frame data area */
 		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-				 cqe_bcnt, &mxbuf);
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf))
+				 cqe_bcnt, mxbuf);
+		if (mlx5e_xdp_handle(rq, prog, mxbuf))
 			return NULL; /* page/packet was consumed by XDP */
 
-		rx_headroom = mxbuf.xdp.data - mxbuf.xdp.data_hard_start;
-		metasize = mxbuf.xdp.data - mxbuf.xdp.data_meta;
-		cqe_bcnt = mxbuf.xdp.data_end - mxbuf.xdp.data;
+		rx_headroom = mxbuf->xdp.data - mxbuf->xdp.data_hard_start;
+		metasize = mxbuf->xdp.data - mxbuf->xdp.data_meta;
+		cqe_bcnt = mxbuf->xdp.data_end - mxbuf->xdp.data;
 	}
 	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt, metasize);
@@ -1713,11 +1713,11 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 			     struct mlx5_cqe64 *cqe, u32 cqe_bcnt)
 {
 	struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+	struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 	struct mlx5e_wqe_frag_info *head_wi = wi;
 	u16 rx_headroom = rq->buff.headroom;
 	struct mlx5e_frag_page *frag_page;
 	struct skb_shared_info *sinfo;
-	struct mlx5e_xdp_buff mxbuf;
 	u32 frag_consumed_bytes;
 	struct bpf_prog *prog;
 	struct sk_buff *skb;
@@ -1737,8 +1737,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	net_prefetch(va + rx_headroom);
 
 	mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-			 frag_consumed_bytes, &mxbuf);
-	sinfo = xdp_get_shared_info_from_buff(&mxbuf.xdp);
+			 frag_consumed_bytes, mxbuf);
+	sinfo = xdp_get_shared_info_from_buff(&mxbuf->xdp);
 	truesize = 0;
 
 	cqe_bcnt -= frag_consumed_bytes;
@@ -1750,8 +1750,9 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 		frag_consumed_bytes = min_t(u32, frag_info->frag_size, cqe_bcnt);
 
-		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf.xdp, frag_page,
-					       wi->offset, frag_consumed_bytes);
+		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf->xdp,
+					       frag_page, wi->offset,
+					       frag_consumed_bytes);
 		truesize += frag_info->frag_stride;
 
 		cqe_bcnt -= frag_consumed_bytes;
@@ -1760,7 +1761,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	}
 
 	prog = rcu_dereference(rq->xdp_prog);
-	if (prog && mlx5e_xdp_handle(rq, prog, &mxbuf)) {
+	if (prog && mlx5e_xdp_handle(rq, prog, mxbuf)) {
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 			struct mlx5e_wqe_frag_info *pwi;
 
@@ -1770,21 +1771,23 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 		return NULL; /* page/packet was consumed by XDP */
 	}
 
-	skb = mlx5e_build_linear_skb(rq, mxbuf.xdp.data_hard_start, rq->buff.frame0_sz,
-				     mxbuf.xdp.data - mxbuf.xdp.data_hard_start,
-				     mxbuf.xdp.data_end - mxbuf.xdp.data,
-				     mxbuf.xdp.data - mxbuf.xdp.data_meta);
+	skb = mlx5e_build_linear_skb(
+		rq, mxbuf->xdp.data_hard_start, rq->buff.frame0_sz,
+		mxbuf->xdp.data - mxbuf->xdp.data_hard_start,
+		mxbuf->xdp.data_end - mxbuf->xdp.data,
+		mxbuf->xdp.data - mxbuf->xdp.data_meta);
 	if (unlikely(!skb))
 		return NULL;
 
 	skb_mark_for_recycle(skb);
 	head_wi->frag_page->frags++;
 
-	if (xdp_buff_has_frags(&mxbuf.xdp)) {
+	if (xdp_buff_has_frags(&mxbuf->xdp)) {
 		/* sinfo->nr_frags is reset by build_skb, calculate again. */
 		xdp_update_skb_shared_info(skb, wi - head_wi - 1,
 					   sinfo->xdp_frags_size, truesize,
-					   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+					   xdp_buff_is_frag_pfmemalloc(
+						&mxbuf->xdp));
 
 		for (struct mlx5e_wqe_frag_info *pwi = head_wi + 1; pwi < wi; pwi++)
 			pwi->frag_page->frags++;
@@ -1984,10 +1987,10 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	struct mlx5e_frag_page *frag_page = &wi->alloc_units.frag_pages[page_idx];
 	u16 headlen = min_t(u16, MLX5E_RX_MAX_HEAD, cqe_bcnt);
 	struct mlx5e_frag_page *head_page = frag_page;
+	struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 	u32 frag_offset    = head_offset;
 	u32 byte_cnt       = cqe_bcnt;
 	struct skb_shared_info *sinfo;
-	struct mlx5e_xdp_buff mxbuf;
 	unsigned int truesize = 0;
 	struct bpf_prog *prog;
 	struct sk_buff *skb;
@@ -2033,9 +2036,10 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		}
 	}
 
-	mlx5e_fill_mxbuf(rq, cqe, va, linear_hr, linear_frame_sz, linear_data_len, &mxbuf);
+	mlx5e_fill_mxbuf(rq, cqe, va, linear_hr, linear_frame_sz,
+			 linear_data_len, mxbuf);
 
-	sinfo = xdp_get_shared_info_from_buff(&mxbuf.xdp);
+	sinfo = xdp_get_shared_info_from_buff(&mxbuf->xdp);
 
 	while (byte_cnt) {
 		/* Non-linear mode, hence non-XSK, which always uses PAGE_SIZE. */
@@ -2046,7 +2050,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		else
 			truesize += ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz));
 
-		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf.xdp, frag_page, frag_offset,
+		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf->xdp,
+					       frag_page, frag_offset,
 					       pg_consumed_bytes);
 		byte_cnt -= pg_consumed_bytes;
 		frag_offset = 0;
@@ -2054,7 +2059,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	}
 
 	if (prog) {
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
+		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 				struct mlx5e_frag_page *pfp;
 
@@ -2067,10 +2072,10 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
-		skb = mlx5e_build_linear_skb(rq, mxbuf.xdp.data_hard_start,
-					     linear_frame_sz,
-					     mxbuf.xdp.data - mxbuf.xdp.data_hard_start, 0,
-					     mxbuf.xdp.data - mxbuf.xdp.data_meta);
+		skb = mlx5e_build_linear_skb(
+			rq, mxbuf->xdp.data_hard_start, linear_frame_sz,
+			mxbuf->xdp.data - mxbuf->xdp.data_hard_start, 0,
+			mxbuf->xdp.data - mxbuf->xdp.data_meta);
 		if (unlikely(!skb)) {
 			mlx5e_page_release_fragmented(rq, &wi->linear_page);
 			return NULL;
@@ -2080,13 +2085,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		wi->linear_page.frags++;
 		mlx5e_page_release_fragmented(rq, &wi->linear_page);
 
-		if (xdp_buff_has_frags(&mxbuf.xdp)) {
+		if (xdp_buff_has_frags(&mxbuf->xdp)) {
 			struct mlx5e_frag_page *pagep;
 
 			/* sinfo->nr_frags is reset by build_skb, calculate again. */
 			xdp_update_skb_shared_info(skb, frag_page - head_page,
 						   sinfo->xdp_frags_size, truesize,
-						   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+						   xdp_buff_is_frag_pfmemalloc(
+							&mxbuf->xdp));
 
 			pagep = head_page;
 			do
@@ -2097,12 +2103,13 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	} else {
 		dma_addr_t addr;
 
-		if (xdp_buff_has_frags(&mxbuf.xdp)) {
+		if (xdp_buff_has_frags(&mxbuf->xdp)) {
 			struct mlx5e_frag_page *pagep;
 
 			xdp_update_skb_shared_info(skb, sinfo->nr_frags,
 						   sinfo->xdp_frags_size, truesize,
-						   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+						   xdp_buff_is_frag_pfmemalloc(
+							&mxbuf->xdp));
 
 			pagep = frag_page - sinfo->nr_frags;
 			do
@@ -2152,20 +2159,20 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog) {
-		struct mlx5e_xdp_buff mxbuf;
+		struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 
 		net_prefetchw(va); /* xdp_frame data area */
 		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-				 cqe_bcnt, &mxbuf);
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
+				 cqe_bcnt, mxbuf);
+		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
 				frag_page->frags++;
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
-		rx_headroom = mxbuf.xdp.data - mxbuf.xdp.data_hard_start;
-		metasize = mxbuf.xdp.data - mxbuf.xdp.data_meta;
-		cqe_bcnt = mxbuf.xdp.data_end - mxbuf.xdp.data;
+		rx_headroom = mxbuf->xdp.data - mxbuf->xdp.data_hard_start;
+		metasize =  mxbuf->xdp.data -  mxbuf->xdp.data_meta;
+		cqe_bcnt =  mxbuf->xdp.data_end -  mxbuf->xdp.data;
 	}
 	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt, metasize);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 1d60465cc2ca..2f7a543feca6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -166,6 +166,9 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
 	struct udphdr *udph;
 	struct iphdr *iph;
 
+	if (skb_linearize(skb))
+		goto out;
+
 	/* We are only going to peek, no need to clone the SKB */
 	if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb))
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 611ec4b6f370..19664fa7f217 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -37,9 +37,7 @@
 #include "en/ptp.h"
 #include "en/port.h"
 
-#ifdef CONFIG_PAGE_POOL_STATS
 #include <net/page_pool/helpers.h>
-#endif
 
 void mlx5e_ethtool_put_stat(u64 **data, u64 val)
 {
@@ -196,7 +194,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) },
 #endif
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) },
-#ifdef CONFIG_PAGE_POOL_STATS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_fast) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_slow) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_slow_high_order) },
@@ -208,7 +205,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_ring) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_ring_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_released_ref) },
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_bytes) },
@@ -377,7 +373,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_arfs_err                += rq_stats->arfs_err;
 #endif
 	s->rx_recover                 += rq_stats->recover;
-#ifdef CONFIG_PAGE_POOL_STATS
 	s->rx_pp_alloc_fast          += rq_stats->pp_alloc_fast;
 	s->rx_pp_alloc_slow          += rq_stats->pp_alloc_slow;
 	s->rx_pp_alloc_empty         += rq_stats->pp_alloc_empty;
@@ -389,7 +384,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_pp_recycle_ring			+= rq_stats->pp_recycle_ring;
 	s->rx_pp_recycle_ring_full		+= rq_stats->pp_recycle_ring_full;
 	s->rx_pp_recycle_released_ref		+= rq_stats->pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	s->rx_tls_decrypted_packets   += rq_stats->tls_decrypted_packets;
 	s->rx_tls_decrypted_bytes     += rq_stats->tls_decrypted_bytes;
@@ -496,7 +490,6 @@ static void mlx5e_stats_grp_sw_update_stats_qos(struct mlx5e_priv *priv,
 	}
 }
 
-#ifdef CONFIG_PAGE_POOL_STATS
 static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
 {
 	struct mlx5e_rq_stats *rq_stats = c->rq.stats;
@@ -519,11 +512,6 @@ static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
 	rq_stats->pp_recycle_ring_full = stats.recycle_stats.ring_full;
 	rq_stats->pp_recycle_released_ref = stats.recycle_stats.released_refcnt;
 }
-#else
-static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
-{
-}
-#endif
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 {
@@ -1227,6 +1215,13 @@ out:
 	mutex_unlock(&priv->state_lock);
 }
 
+#define PPORT_PHY_LAYER_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.phys_layer_cntrs.c)
+static const struct counter_desc pport_phy_layer_cntrs_stats_desc[] = {
+	{ "link_down_events_phy", PPORT_PHY_LAYER_OFF(link_down_events) }
+};
+
 #define PPORT_PHY_STATISTICAL_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.phys_layer_statistical_cntrs.c##_high)
@@ -1243,25 +1238,45 @@ pport_phy_statistical_err_lanes_stats_desc[] = {
 	{ "rx_err_lane_3_phy", PPORT_PHY_STATISTICAL_OFF(phy_corrected_bits_lane3) },
 };
 
+#define PPORT_PHY_RECOVERY_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, counter_set.phys_layer_recovery_cntrs.c)
+static const struct counter_desc
+pport_phy_recovery_cntrs_stats_desc[] = {
+	{ "total_success_recovery_phy",
+	  PPORT_PHY_RECOVERY_OFF(total_successful_recovery_events) }
+};
+
+#define NUM_PPORT_PHY_LAYER_COUNTERS \
+	ARRAY_SIZE(pport_phy_layer_cntrs_stats_desc)
 #define NUM_PPORT_PHY_STATISTICAL_COUNTERS \
 	ARRAY_SIZE(pport_phy_statistical_stats_desc)
 #define NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS \
 	ARRAY_SIZE(pport_phy_statistical_err_lanes_stats_desc)
+#define NUM_PPORT_PHY_RECOVERY_COUNTERS \
+	ARRAY_SIZE(pport_phy_recovery_cntrs_stats_desc)
+
+#define NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, ppcnt_statistical_group) ? \
+	NUM_PPORT_PHY_STATISTICAL_COUNTERS : 0)
+#define NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, per_lane_error_counters) ? \
+	NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS : 0)
+#define NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, ppcnt_recovery_counters) ? \
+	NUM_PPORT_PHY_RECOVERY_COUNTERS : 0)
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(phy)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int num_stats;
 
-	/* "1" for link_down_events special counter */
-	num_stats = 1;
+	num_stats = NUM_PPORT_PHY_LAYER_COUNTERS;
 
-	num_stats += MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group) ?
-		     NUM_PPORT_PHY_STATISTICAL_COUNTERS : 0;
+	num_stats += NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev);
 
-	num_stats += MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters) ?
-		     NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS : 0;
+	num_stats += NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
 
+	num_stats += NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev);
 	return num_stats;
 }
 
@@ -1270,18 +1285,22 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(phy)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int i;
 
-	ethtool_puts(data, "link_down_events_phy");
-
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
+	for (i = 0; i < NUM_PPORT_PHY_LAYER_COUNTERS; i++)
+		ethtool_puts(data, pport_phy_layer_cntrs_stats_desc[i].format);
 
-	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
+	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev); i++)
 		ethtool_puts(data, pport_phy_statistical_stats_desc[i].format);
 
-	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
-		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
-			ethtool_puts(data,
-				     pport_phy_statistical_err_lanes_stats_desc[i].format);
+	for (i = 0;
+	     i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
+	     i++)
+		ethtool_puts(data,
+			     pport_phy_statistical_err_lanes_stats_desc[i]
+			     .format);
+
+	for (i = 0; i < NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev); i++)
+		ethtool_puts(data,
+			     pport_phy_recovery_cntrs_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
@@ -1289,30 +1308,35 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int i;
 
-	/* link_down_events_phy has special handling since it is not stored in __be64 format */
-	mlx5e_ethtool_put_stat(
-		data, MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters,
-			       counter_set.phys_layer_cntrs.link_down_events));
-
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
+	for (i = 0; i < NUM_PPORT_PHY_LAYER_COUNTERS; i++)
+		mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR32_BE(&priv->stats.pport
+					.phy_counters,
+					pport_phy_layer_cntrs_stats_desc, i));
 
-	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
+	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev); i++)
 		mlx5e_ethtool_put_stat(
 			data,
 			MLX5E_READ_CTR64_BE(
 				&priv->stats.pport.phy_statistical_counters,
 				pport_phy_statistical_stats_desc, i));
 
-	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
-		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
-			mlx5e_ethtool_put_stat(
-				data,
-				MLX5E_READ_CTR64_BE(
-					&priv->stats.pport
-						 .phy_statistical_counters,
-					pport_phy_statistical_err_lanes_stats_desc,
-					i));
+	for (i = 0;
+	     i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
+	     i++)
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_BE(
+				&priv->stats.pport.phy_statistical_counters,
+				pport_phy_statistical_err_lanes_stats_desc, i));
+
+	for (i = 0; i < NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev); i++)
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR32_BE(
+				&priv->stats.pport.phy_recovery_counters,
+				pport_phy_recovery_cntrs_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)
@@ -1328,12 +1352,21 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP);
 	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
 
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group)) {
+		out = pstats->phy_statistical_counters;
+		MLX5_SET(ppcnt_reg, in, grp,
+			 MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP);
+		mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0,
+				     0);
+	}
 
-	out = pstats->phy_statistical_counters;
-	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_recovery_counters)) {
+		out = pstats->phy_recovery_counters;
+		MLX5_SET(ppcnt_reg, in, grp,
+			 MLX5_PHYSICAL_LAYER_RECOVERY_GROUP);
+		mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0,
+				     0);
+	}
 }
 
 void mlx5e_get_link_ext_stats(struct net_device *dev,
@@ -2086,7 +2119,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) },
 #endif
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) },
-#ifdef CONFIG_PAGE_POOL_STATS
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_fast) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_slow) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_slow_high_order) },
@@ -2098,7 +2130,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_ring) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_ring_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_released_ref) },
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_bytes) },
@@ -2393,8 +2424,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ptp)
 	}
 	if (priv->rx_ptp_opened) {
 		for (i = 0; i < NUM_PTP_RQ_STATS; i++)
-			ethtool_sprintf(data, ptp_rq_stats_desc[i].format,
-					MLX5E_PTP_CHANNEL_IX);
+			ethtool_puts(data, ptp_rq_stats_desc[i].format);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 5961c569cfe0..def5dea1463d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -54,7 +54,7 @@
 #define MLX5E_DECLARE_PTP_TX_STAT(type, fld) "ptp_tx%d_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_PTP_CH_STAT(type, fld) "ptp_ch_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_PTP_CQ_STAT(type, fld) "ptp_cq%d_"#fld, offsetof(type, fld)
-#define MLX5E_DECLARE_PTP_RQ_STAT(type, fld) "ptp_rq%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_PTP_RQ_STAT(type, fld) "ptp_rq0_"#fld, offsetof(type, fld)
 
 #define MLX5E_DECLARE_QOS_TX_STAT(type, fld) "qos_tx%d_"#fld, offsetof(type, fld)
 
@@ -215,7 +215,6 @@ struct mlx5e_sw_stats {
 	u64 ch_aff_change;
 	u64 ch_force_irq;
 	u64 ch_eq_rearm;
-#ifdef CONFIG_PAGE_POOL_STATS
 	u64 rx_pp_alloc_fast;
 	u64 rx_pp_alloc_slow;
 	u64 rx_pp_alloc_slow_high_order;
@@ -227,7 +226,6 @@ struct mlx5e_sw_stats {
 	u64 rx_pp_recycle_ring;
 	u64 rx_pp_recycle_ring_full;
 	u64 rx_pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tx_tls_encrypted_packets;
 	u64 tx_tls_encrypted_bytes;
@@ -309,6 +307,9 @@ struct mlx5e_vport_stats {
 #define PPORT_PHY_STATISTICAL_GET(pstats, c) \
 	MLX5_GET64(ppcnt_reg, (pstats)->phy_statistical_counters, \
 		   counter_set.phys_layer_statistical_cntrs.c##_high)
+#define PPORT_PHY_RECOVERY_GET(pstats, c) \
+	MLX5_GET64(ppcnt_reg, (pstats)->phy_recovery_counters, \
+		   counter_set.phys_layer_recovery_cntrs.c)
 #define PPORT_PER_PRIO_GET(pstats, prio, c) \
 	MLX5_GET64(ppcnt_reg, pstats->per_prio_counters[prio], \
 		   counter_set.eth_per_prio_grp_data_layout.c##_high)
@@ -324,6 +325,7 @@ struct mlx5e_pport_stats {
 	__be64 per_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 phy_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 phy_statistical_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
+	__be64 phy_recovery_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 eth_ext_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 per_tc_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 per_tc_congest_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];
@@ -381,7 +383,6 @@ struct mlx5e_rq_stats {
 	u64 arfs_err;
 #endif
 	u64 recover;
-#ifdef CONFIG_PAGE_POOL_STATS
 	u64 pp_alloc_fast;
 	u64 pp_alloc_slow;
 	u64 pp_alloc_slow_high_order;
@@ -393,7 +394,6 @@ struct mlx5e_rq_stats {
 	u64 pp_recycle_ring;
 	u64 pp_recycle_ring_full;
 	u64 pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_decrypted_packets;
 	u64 tls_decrypted_bytes;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 6b3b1afe8312..fef418e1ed1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1282,7 +1282,7 @@ mlx5e_add_offloaded_nic_rule(struct mlx5e_priv *priv,
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		dest[dest_ix].counter_id = mlx5_fc_id(attr->counter);
+		dest[dest_ix].counter = attr->counter;
 		dest_ix++;
 	}
 
@@ -1750,9 +1750,6 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	    !list_is_first(&attr->list, &flow->attrs))
 		return 0;
 
-	if (flow_flag_test(flow, SLOW))
-		return 0;
-
 	esw_attr = attr->esw_attr;
 	if (!esw_attr->split_count ||
 	    esw_attr->split_count == esw_attr->out_count - 1)
@@ -1766,7 +1763,7 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
 		/* external dest with encap is considered as internal by firmware */
 		if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK &&
-		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID))
+		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
 			ext_dest = true;
 		else
 			int_dest = true;
@@ -2031,9 +2028,8 @@ err_out:
 	return err;
 }
 
-static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
+static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
 {
-	struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
 	void *headers_v = MLX5_ADDR_OF(fte_match_param,
 				       spec->match_value,
 				       misc_parameters_3);
@@ -2072,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	}
 	complete_all(&flow->del_hw_done);
 
-	if (mlx5_flow_has_geneve_opt(flow))
+	if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
 		mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 
 	if (flow->decap_route)
@@ -2577,12 +2573,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 
 		err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
 		if (err) {
-			kvfree(tmp_spec);
 			NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
 			netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
-			return err;
+		} else {
+			err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
 		}
-		err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
+		if (mlx5_flow_has_geneve_opt(tmp_spec))
+			mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 		kvfree(tmp_spec);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f8c7912abe0e..55a8629f0792 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -337,10 +337,11 @@ static void mlx5e_sq_calc_wqe_attr(struct sk_buff *skb, const struct mlx5e_tx_at
 	};
 }
 
-static void mlx5e_tx_skb_update_hwts_flags(struct sk_buff *skb)
+static void mlx5e_tx_skb_update_ts_flags(struct sk_buff *skb)
 {
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+	skb_tx_timestamp(skb);
 }
 
 static void mlx5e_tx_check_stop(struct mlx5e_txqsq *sq)
@@ -392,7 +393,7 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | attr->opcode);
 	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | wqe_attr->ds_cnt);
 
-	mlx5e_tx_skb_update_hwts_flags(skb);
+	mlx5e_tx_skb_update_ts_flags(skb);
 
 	sq->pc += wi->num_wqebbs;
 
@@ -525,9 +526,9 @@ static void mlx5e_tx_mpwqe_session_start(struct mlx5e_txqsq *sq,
 {
 	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_tx_wqe *wqe;
-	u16 pi;
+	u16 pi, num_wqebbs;
 
-	pi = mlx5e_txqsq_get_next_pi(sq, sq->max_sq_mpw_wqebbs);
+	pi = mlx5e_txqsq_get_next_pi_anysize(sq, &num_wqebbs);
 	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 	net_prefetchw(wqe->data);
 
@@ -535,6 +536,7 @@ static void mlx5e_tx_mpwqe_session_start(struct mlx5e_txqsq *sq,
 		.wqe = wqe,
 		.bytes_count = 0,
 		.ds_count = MLX5E_TX_WQE_EMPTY_DS_COUNT,
+		.ds_count_max = num_wqebbs * MLX5_SEND_WQEBB_NUM_DS,
 		.pkt_count = 0,
 		.inline_on = 0,
 	};
@@ -624,9 +626,9 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE);
 	mlx5e_skb_fifo_push(&sq->db.skb_fifo, skb);
 	mlx5e_tx_mpwqe_add_dseg(sq, &txd);
-	mlx5e_tx_skb_update_hwts_flags(skb);
+	mlx5e_tx_skb_update_ts_flags(skb);
 
-	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe, sq->max_sq_mpw_wqebbs))) {
+	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe))) {
 		/* Might stop the queue and affect the retval of __netdev_tx_sent_queue. */
 		cseg = mlx5e_tx_mpwqe_session_complete(sq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 2b229b6226c6..dfb079e59d85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -871,8 +871,8 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 
 static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
+	struct mlx5_irq_pool *pool = mlx5_irq_table_get_comp_irq_pool(dev);
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
 	struct irq_affinity_desc af_desc = {};
 	struct mlx5_irq *irq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
index 6b4c9ffad95b..7dd1dc3f77c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
@@ -135,7 +135,7 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 	if (drop_counter) {
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
 		drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		drop_ctr_dst.counter_id = mlx5_fc_id(drop_counter);
+		drop_ctr_dst.counter = drop_counter;
 		dst = &drop_ctr_dst;
 		dest_num++;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
index d599e50af346..3ce455c2535c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
@@ -27,7 +27,7 @@ esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns,
 	esw_debug(dev, "Create vport[%d] %s ACL table\n", vport_num,
 		  ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress");
 
-	root_ns = mlx5_get_flow_vport_acl_namespace(dev, ns, vport->index);
+	root_ns = mlx5_get_flow_vport_namespace(dev, ns, vport->index);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch root namespace for vport (%d)\n",
 			 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
index 093ed86a0acd..1c37098e09ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
@@ -260,7 +260,7 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 	if (counter) {
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
 		drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		drop_ctr_dst.counter_id = mlx5_fc_id(counter);
+		drop_ctr_dst.counter = counter;
 		dst = &drop_ctr_dst;
 		dest_num++;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index c5ea1d1d2b03..76e35c827da0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -570,7 +570,8 @@ mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge)
 
 static struct mlx5_flow_handle *
 mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char *addr,
-					     struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+					     struct mlx5_esw_bridge_vlan *vlan,
+					     struct mlx5_fc *counter,
 					     struct mlx5_esw_bridge *bridge,
 					     struct mlx5_eswitch *esw)
 {
@@ -628,7 +629,7 @@ mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char
 	dests[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dests[0].ft = bridge->egress_ft;
 	dests[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dests[1].counter_id = counter_id;
+	dests[1].counter = counter;
 
 	handle = mlx5_add_flow_rules(br_offloads->ingress_ft, rule_spec, &flow_act, dests,
 				     ARRAY_SIZE(dests));
@@ -639,17 +640,19 @@ mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char
 
 static struct mlx5_flow_handle *
 mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
-				    struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+				    struct mlx5_esw_bridge_vlan *vlan,
+				    struct mlx5_fc *counter,
 				    struct mlx5_esw_bridge *bridge)
 {
-	return mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
+	return mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter,
 							    bridge, bridge->br_offloads->esw);
 }
 
 static struct mlx5_flow_handle *
 mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, u16 esw_owner_vhca_id,
 					 const unsigned char *addr,
-					 struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+					 struct mlx5_esw_bridge_vlan *vlan,
+					 struct mlx5_fc *counter,
 					 struct mlx5_esw_bridge *bridge)
 {
 	struct mlx5_devcom_comp_dev *devcom = bridge->br_offloads->esw->devcom, *pos;
@@ -671,7 +674,7 @@ mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, u16 esw_owner_vhca_id,
 		goto out;
 	}
 
-	handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
+	handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter,
 							      bridge, peer_esw);
 
 out:
@@ -1385,10 +1388,9 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow
 
 	handle = peer ?
 		mlx5_esw_bridge_ingress_flow_peer_create(vport_num, esw_owner_vhca_id,
-							 addr, vlan, mlx5_fc_id(counter),
-							 bridge) :
+							 addr, vlan, counter, bridge) :
 		mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan,
-						    mlx5_fc_id(counter), bridge);
+						    counter, bridge);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
 		esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d,peer=%d)\n",
@@ -1861,7 +1863,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 			 "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)\n",
 			 addr, vport_num);
 		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)\n",
+				       "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)",
 				       addr, vport_num);
 		return -EINVAL;
 	}
@@ -1874,7 +1876,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 				 "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n",
 				 addr, vid, vport_num);
 			NL_SET_ERR_MSG_FMT_MOD(extack,
-					       "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)\n",
+					       "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)",
 					       addr, vid, vport_num);
 			return -EINVAL;
 		}
@@ -1882,7 +1884,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 
 	err = mlx5_esw_bridge_port_mdb_attach(dev, port, addr, vid);
 	if (err) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to add MDB (MAC=%pM,vid=%u,vport=%u)\n",
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to add MDB (MAC=%pM,vid=%u,vport=%u)",
 				       addr, vid, vport_num);
 		return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 982fe3714683..b7102e14d23d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -32,7 +32,7 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 	u16 pfnum;
 
 	mlx5_esw_get_port_parent_id(dev, &ppid);
-	pfnum = mlx5_get_dev_index(dev);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 	external = mlx5_core_is_ecpf_esw_manager(dev);
 	if (external)
 		controller_num = dev->priv.eswitch->offloads.host_number + 1;
@@ -110,7 +110,7 @@ static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw
 	struct netdev_phys_item_id ppid = {};
 	u16 pfnum;
 
-	pfnum = mlx5_get_dev_index(dev);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 	mlx5_esw_get_port_parent_id(dev, &ppid);
 	memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 	dl_port->attrs.switch_id.id_len = ppid.id_len;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 5a0047bdcb51..3cfe743610d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -10,9 +10,9 @@
 #endif
 
 enum {
-	MLX5_ESW_IPSEC_RX_POL_FT_LEVEL,
 	MLX5_ESW_IPSEC_RX_ESP_FT_LEVEL,
 	MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL,
+	MLX5_ESW_IPSEC_RX_POL_FT_LEVEL,
 };
 
 enum {
@@ -85,6 +85,19 @@ err_header_alloc:
 	return err;
 }
 
+void mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_spec *spec)
+{
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_1,
+		 ESW_IPSEC_RX_MAPPED_ID_MATCH_MASK);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_1,
+		 sa_entry->rx_mapped_id << ESW_ZONE_ID_BITS);
+
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+}
+
 void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
@@ -150,11 +163,11 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
 	unsigned long i;
 	int err;
 
-	xa_for_each(&esw->offloads.vport_reps, i, rep) {
-		rpriv = rep->rep_data[REP_ETH].priv;
-		if (!rpriv || !rpriv->netdev)
+	mlx5_esw_for_each_rep(esw, i, rep) {
+		if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
 			continue;
 
+		rpriv = rep->rep_data[REP_ETH].priv;
 		rhashtable_walk_enter(&rpriv->tc_ht, &iter);
 		rhashtable_walk_start(&iter);
 		while ((flow = rhashtable_walk_next(&iter)) != NULL) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index ac9c65b89166..514c15258b1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -20,6 +20,8 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
 void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
+void mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_spec *spec);
 #else
 static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_rx_create_attr *attr) {}
@@ -48,5 +50,8 @@ static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_tx_create_attr *attr) {}
 
 static inline void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) {}
+static inline void
+mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+				     struct mlx5_flow_spec *spec) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 45183de424f3..76382626ad41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -96,7 +96,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	if (!flow_group_in)
 		return -ENOMEM;
 
-	ft_attr.max_fte = POOL_NEXT_SIZE;
+	ft_attr.max_fte = MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 8b7c843446e1..b6ae384396b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -90,15 +90,30 @@ struct mlx5_esw_sched_node {
 	struct list_head children;
 	/* Valid only if this node is associated with a vport. */
 	struct mlx5_vport *vport;
+	/* Level in the hierarchy. The root node level is 1. */
+	u8 level;
 };
 
+static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node)
+{
+	if (!node->parent) {
+		/* Root children are assigned a depth level of 2. */
+		node->level = 2;
+		list_add_tail(&node->entry, &node->esw->qos.domain->nodes);
+	} else {
+		node->level = node->parent->level + 1;
+		list_add_tail(&node->entry, &node->parent->children);
+	}
+}
+
 static void
 esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent)
 {
 	list_del_init(&node->entry);
 	node->parent = parent;
-	list_add_tail(&node->entry, &parent->children);
-	node->esw = parent->esw;
+	if (parent)
+		node->esw = parent->esw;
+	esw_qos_node_attach_to_parent(node);
 }
 
 void mlx5_esw_qos_vport_qos_free(struct mlx5_vport *vport)
@@ -305,8 +320,9 @@ static int esw_qos_set_node_min_rate(struct mlx5_esw_sched_node *node,
 	return 0;
 }
 
-static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id,
-					  u32 *tsar_ix)
+static int
+esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id,
+			       u32 max_rate, u32 bw_share, u32 *tsar_ix)
 {
 	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	void *attr;
@@ -323,6 +339,8 @@ static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
 	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
 		 parent_element_id);
+	MLX5_SET(scheduling_context, tsar_ctx, max_average_bw, max_rate);
+	MLX5_SET(scheduling_context, tsar_ctx, bw_share, bw_share);
 	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
 	MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_DWRR);
 
@@ -358,7 +376,6 @@ static struct mlx5_esw_sched_node *
 __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type type,
 		     struct mlx5_esw_sched_node *parent)
 {
-	struct list_head *parent_children;
 	struct mlx5_esw_sched_node *node;
 
 	node = kzalloc(sizeof(*node), GFP_KERNEL);
@@ -370,8 +387,7 @@ __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type
 	node->type = type;
 	node->parent = parent;
 	INIT_LIST_HEAD(&node->children);
-	parent_children = parent ? &parent->children : &esw->qos.domain->nodes;
-	list_add_tail(&node->entry, parent_children);
+	esw_qos_node_attach_to_parent(node);
 
 	return node;
 }
@@ -396,7 +412,8 @@ __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sch
 	u32 tsar_ix;
 	int err;
 
-	err = esw_qos_create_node_sched_elem(esw->dev, esw->qos.root_tsar_ix, &tsar_ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, esw->qos.root_tsar_ix, 0,
+					     0, &tsar_ix);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "E-Switch create TSAR for node failed");
 		return ERR_PTR(err);
@@ -463,7 +480,8 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
 	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
 		return -EOPNOTSUPP;
 
-	err = esw_qos_create_node_sched_elem(esw->dev, 0, &esw->qos.root_tsar_ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, 0, 0, 0,
+					     &esw->qos.root_tsar_ix);
 	if (err) {
 		esw_warn(dev, "E-Switch create root TSAR failed (%d)\n", err);
 		return err;
@@ -564,6 +582,9 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_
 		return err;
 
 	esw_qos_normalize_min_rate(parent->esw, parent, extack);
+	trace_mlx5_esw_vport_qos_create(vport->dev, vport,
+					vport->qos.sched_node->max_rate,
+					vport->qos.sched_node->bw_share);
 
 	return 0;
 }
@@ -591,8 +612,11 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	sched_node->vport = vport;
 	vport->qos.sched_node = sched_node;
 	err = esw_qos_vport_enable(vport, parent, extack);
-	if (err)
+	if (err) {
+		__esw_qos_free_node(sched_node);
 		esw_qos_put(esw);
+		vport->qos.sched_node = NULL;
+	}
 
 	return err;
 }
@@ -980,10 +1004,10 @@ int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_s
 	return err;
 }
 
-int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
-				     struct devlink_rate *parent,
-				     void *priv, void *parent_priv,
-				     struct netlink_ext_ack *extack)
+int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *node;
 	struct mlx5_vport *vport = priv;
@@ -994,3 +1018,105 @@ int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
 	node = parent_priv;
 	return mlx5_esw_qos_vport_update_parent(vport, node, extack);
 }
+
+static int
+mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node,
+				      struct mlx5_esw_sched_node *parent,
+				      struct netlink_ext_ack *extack)
+{
+	u8 new_level, max_level;
+
+	if (parent && parent->esw != node->esw) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot assign node to another E-Switch");
+		return -EOPNOTSUPP;
+	}
+
+	if (!list_empty(&node->children)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot reassign a node that contains rate objects");
+		return -EOPNOTSUPP;
+	}
+
+	new_level = parent ? parent->level + 1 : 2;
+	max_level = 1 << MLX5_CAP_QOS(node->esw->dev, log_esw_max_sched_depth);
+	if (new_level > max_level) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Node hierarchy depth exceeds the maximum supported level");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node,
+					     struct mlx5_esw_sched_node *parent,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_parent = node->parent;
+	struct mlx5_eswitch *esw = node->esw;
+	u32 parent_ix;
+	int err;
+
+	parent_ix = parent ? parent->ix : node->esw->qos.root_tsar_ix;
+	mlx5_destroy_scheduling_element_cmd(esw->dev,
+					    SCHEDULING_HIERARCHY_E_SWITCH,
+					    node->ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, parent_ix,
+					     node->max_rate, 0, &node->ix);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to create a node under the new hierarchy.");
+		if (esw_qos_create_node_sched_elem(esw->dev, curr_parent->ix,
+						   node->max_rate,
+						   node->bw_share,
+						   &node->ix))
+			esw_warn(esw->dev, "Node restore QoS failed\n");
+
+		return err;
+	}
+	esw_qos_node_set_parent(node, parent);
+
+	return 0;
+}
+
+static int mlx5_esw_qos_node_update_parent(struct mlx5_esw_sched_node *node,
+					   struct mlx5_esw_sched_node *parent,
+					   struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_parent;
+	struct mlx5_eswitch *esw = node->esw;
+	int err;
+
+	err = mlx5_esw_qos_node_validate_set_parent(node, parent, extack);
+	if (err)
+		return err;
+
+	esw_qos_lock(esw);
+	curr_parent = node->parent;
+	err = esw_qos_vports_node_update_parent(node, parent, extack);
+	if (err)
+		goto out;
+
+	esw_qos_normalize_min_rate(esw, curr_parent, extack);
+	esw_qos_normalize_min_rate(esw, parent, extack);
+
+out:
+	esw_qos_unlock(esw);
+
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *node = priv, *parent_node;
+
+	if (!parent)
+		return mlx5_esw_qos_node_update_parent(node, NULL, extack);
+
+	parent_node = parent_priv;
+	return mlx5_esw_qos_node_update_parent(node, parent_node, extack);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
index 6eb8f6a648c8..ed40ec8f027e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
@@ -29,10 +29,14 @@ int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv,
 				   struct netlink_ext_ack *extack);
 int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv,
 				   struct netlink_ext_ack *extack);
-int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
-				     struct devlink_rate *parent,
-				     void *priv, void *parent_priv,
-				     struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack);
 #endif
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 7fb8a3381f84..4917d185d0c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1295,12 +1295,15 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 		ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events);
 		if (ret)
 			goto ecpf_err;
-		if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-			ret = mlx5_eswitch_load_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs,
-							     enabled_events);
-			if (ret)
-				goto ec_vf_err;
-		}
+	}
+
+	/* Enable ECVF vports */
+	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
+		ret = mlx5_eswitch_load_ec_vf_vports(esw,
+						     esw->esw_funcs.num_ec_vfs,
+						     enabled_events);
+		if (ret)
+			goto ec_vf_err;
 	}
 
 	/* Enable VF vports */
@@ -1331,9 +1334,11 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
 {
 	mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
 
+	if (mlx5_core_ec_sriov_enabled(esw->dev))
+		mlx5_eswitch_unload_ec_vf_vports(esw,
+						 esw->esw_funcs.num_ec_vfs);
+
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		if (mlx5_core_ec_sriov_enabled(esw->dev))
-			mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs);
 		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index a83d41121db6..8573d36785f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -714,6 +714,9 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
 			  MLX5_CAP_GEN_2((esw->dev), ec_vf_vport_base) +\
 			  (last) - 1)
 
+#define mlx5_esw_for_each_rep(esw, i, rep) \
+	xa_for_each(&((esw)->offloads.vport_reps), i, rep)
+
 struct mlx5_eswitch *__must_check
 mlx5_devlink_eswitch_get(struct devlink *devlink);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d6ff2dc4c19e..0e3a977d5332 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -53,9 +53,6 @@
 #include "lag/lag.h"
 #include "en/tc/post_meter.h"
 
-#define mlx5_esw_for_each_rep(esw, i, rep) \
-	xa_for_each(&((esw)->offloads.vport_reps), i, rep)
-
 /* There are two match-all miss flows, one for unicast dst mac and
  * one for multicast.
  */
@@ -651,6 +648,7 @@ esw_setup_meter(struct mlx5_flow_attr *attr, struct mlx5_flow_act *flow_act)
 	meter = attr->meter_attr.meter;
 	flow_act->exe_aso.type = attr->exe_aso_type;
 	flow_act->exe_aso.object_id = meter->obj_id;
+	flow_act->exe_aso.base_id = mlx5e_flow_meter_get_base_id(meter);
 	flow_act->exe_aso.flow_meter.meter_idx = meter->idx;
 	flow_act->exe_aso.flow_meter.init_color = MLX5_FLOW_METER_COLOR_GREEN;
 	/* use metadata reg 5 for packet color */
@@ -724,7 +722,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		dest[i].counter_id = mlx5_fc_id(attr->counter);
+		dest[i].counter = attr->counter;
 		i++;
 	}
 
@@ -2335,9 +2333,10 @@ out_free:
 static void esw_mode_change(struct mlx5_eswitch *esw, u16 mode)
 {
 	mlx5_devcom_comp_lock(esw->dev->priv.hca_devcom_comp);
-
-	if (esw->dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) {
+	if (esw->dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV ||
+	    mlx5_core_mp_enabled(esw->dev)) {
 		esw->mode = mode;
+		mlx5_rescan_drivers_locked(esw->dev);
 		mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp);
 		return;
 	}
@@ -2830,9 +2829,9 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master,
 	if (IS_ERR(vport))
 		return PTR_ERR(vport);
 
-	egress_ns = mlx5_get_flow_vport_acl_namespace(master,
-						      MLX5_FLOW_NAMESPACE_ESW_EGRESS,
-						      vport->index);
+	egress_ns = mlx5_get_flow_vport_namespace(master,
+						  MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+						  vport->index);
 	if (!egress_ns)
 		return -EINVAL;
 
@@ -3534,7 +3533,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	int err;
 
 	mutex_init(&esw->offloads.termtbl_mutex);
-	mlx5_rdma_enable_roce(esw->dev);
+	err = mlx5_rdma_enable_roce(esw->dev);
+	if (err)
+		goto err_roce;
 
 	err = mlx5_esw_host_number_init(esw);
 	if (err)
@@ -3595,6 +3596,7 @@ err_vport_metadata:
 	esw_offloads_metadata_uninit(esw);
 err_metadata:
 	mlx5_rdma_disable_roce(esw->dev);
+err_roce:
 	mutex_destroy(&esw->offloads.termtbl_mutex);
 	return err;
 }
@@ -3779,6 +3781,8 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	esw->eswitch_operation_in_progress = true;
 	up_write(&esw->mode_lock);
 
+	if (mode == DEVLINK_ESWITCH_MODE_LEGACY)
+		esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY;
 	mlx5_eswitch_disable_locked(esw);
 	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
 		if (mlx5_devlink_trap_get_num_active(esw->dev)) {
@@ -4157,37 +4161,12 @@ u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw,
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
 
-static int mlx5_esw_query_vport_vhca_id(struct mlx5_eswitch *esw, u16 vport_num, u16 *vhca_id)
-{
-	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	void *query_ctx;
-	void *hca_caps;
-	int err;
-
-	*vhca_id = 0;
-
-	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
-	if (!query_ctx)
-		return -ENOMEM;
-
-	err = mlx5_vport_get_other_func_general_cap(esw->dev, vport_num, query_ctx);
-	if (err)
-		goto out_free;
-
-	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
-	*vhca_id = MLX5_GET(cmd_hca_cap, hca_caps, vhca_id);
-
-out_free:
-	kfree(query_ctx);
-	return err;
-}
-
 int mlx5_esw_vport_vhca_id_set(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	u16 *old_entry, *vhca_map_entry, vhca_id;
 	int err;
 
-	err = mlx5_esw_query_vport_vhca_id(esw, vport_num, &vhca_id);
+	err = mlx5_vport_get_vhca_id(esw->dev, vport_num, &vhca_id);
 	if (err) {
 		esw_warn(esw->dev, "Getting vhca_id for vport failed (vport=%u,err=%d)\n",
 			 vport_num, err);
@@ -4213,7 +4192,7 @@ void mlx5_esw_vport_vhca_id_clear(struct mlx5_eswitch *esw, u16 vport_num)
 	u16 *vhca_map_entry, vhca_id;
 	int err;
 
-	err = mlx5_esw_query_vport_vhca_id(esw, vport_num, &vhca_id);
+	err = mlx5_vport_get_vhca_id(esw->dev, vport_num, &vhca_id);
 	if (err)
 		esw_warn(esw->dev, "Getting vhca_id for vport failed (vport=%hu,err=%d)\n",
 			 vport_num, err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index d91ea53eb394..01c5f5990f9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -6,6 +6,7 @@
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "lib/events.h"
+#include "hwmon.h"
 
 struct mlx5_event_nb {
 	struct mlx5_nb  nb;
@@ -153,21 +154,50 @@ static int any_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+#if IS_ENABLED(CONFIG_HWMON)
+static void print_sensor_names_in_bit_set(struct mlx5_core_dev *dev, struct mlx5_hwmon *hwmon,
+					  u64 bit_set, int bit_set_offset)
+{
+	unsigned long *bit_set_ptr = (unsigned long *)&bit_set;
+	int num_bits = sizeof(bit_set) * BITS_PER_BYTE;
+	int i;
+
+	for_each_set_bit(i, bit_set_ptr, num_bits) {
+		const char *sensor_name = hwmon_get_sensor_name(hwmon, i + bit_set_offset);
+
+		mlx5_core_warn(dev, "Sensor name[%d]: %s\n", i + bit_set_offset, sensor_name);
+	}
+}
+#endif /* CONFIG_HWMON */
+
 /* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */
 static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 {
 	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
 	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_core_dev *dev      = events->dev;
 	struct mlx5_eqe      *eqe      = data;
 	u64 value_lsb;
 	u64 value_msb;
 
 	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
+	/* bit 1-63 are not supported for NICs,
+	 * hence read only bit 0 (asic) from lsb.
+	 */
+	value_lsb &= 0x1;
 	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
 
-	mlx5_core_warn(events->dev,
-		       "High temperature on sensors with bit set %llx %llx",
-		       value_msb, value_lsb);
+	if (net_ratelimit()) {
+		mlx5_core_warn(dev, "High temperature on sensors with bit set %#llx %#llx.\n",
+			       value_msb, value_lsb);
+#if IS_ENABLED(CONFIG_HWMON)
+		if (dev->hwmon) {
+			print_sensor_names_in_bit_set(dev, dev->hwmon, value_lsb, 0);
+			print_sensor_names_in_bit_set(dev, dev->hwmon, value_msb,
+						      sizeof(value_lsb) * BITS_PER_BYTE);
+		}
+#endif
+	}
 
 	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 676005854dad..1af76da8b132 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -217,7 +217,8 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 	int err;
 
 	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
-	    underlay_qpn == 0)
+	    underlay_qpn == 0 &&
+	    (ft->type != FS_FT_RDMA_RX && ft->type != FS_FT_RDMA_TX))
 		return 0;
 
 	if (ft->type == FS_FT_FDB &&
@@ -526,7 +527,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	struct mlx5_flow_rule *dst;
 	void *in_flow_context, *vlan;
 	void *in_match_value;
-	int reformat_id = 0;
+	u32 reformat_id = 0;
 	unsigned int inlen;
 	int dst_cnt_size;
 	u32 *in, action;
@@ -579,23 +580,21 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(flow_context, in_flow_context, action, action);
 
 	if (!extended_dest && fte->act_dests.action.pkt_reformat) {
-		struct mlx5_pkt_reformat *pkt_reformat = fte->act_dests.action.pkt_reformat;
-
-		if (pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
-			reformat_id = mlx5_fs_dr_action_get_pkt_reformat_id(pkt_reformat);
-			if (reformat_id < 0) {
-				mlx5_core_err(dev,
-					      "Unsupported SW-owned pkt_reformat type (%d) in FW-owned table\n",
-					      pkt_reformat->reformat_type);
-				err = reformat_id;
-				goto err_out;
-			}
-		} else {
-			reformat_id = fte->act_dests.action.pkt_reformat->id;
+		struct mlx5_pkt_reformat *pkt_reformat =
+			fte->act_dests.action.pkt_reformat;
+
+		err = mlx5_fs_get_packet_reformat_id(pkt_reformat,
+						     &reformat_id);
+		if (err) {
+			mlx5_core_err(dev,
+				      "Unsupported pkt_reformat type (%d)\n",
+				      pkt_reformat->reformat_type);
+			goto err_out;
 		}
 	}
 
-	MLX5_SET(flow_context, in_flow_context, packet_reformat_id, (u32)reformat_id);
+	MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
+		 reformat_id);
 
 	if (fte->act_dests.action.modify_hdr) {
 		if (fte->act_dests.action.modify_hdr->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
@@ -718,7 +717,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				continue;
 
 			MLX5_SET(flow_counter_list, in_dests, flow_counter_id,
-				 dst->dest_attr.counter_id);
+				 mlx5_fc_id(dst->dest_attr.counter));
 			in_dests += dst_cnt_size;
 			list_size++;
 		}
@@ -1141,6 +1140,8 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ
 	case FS_FT_RDMA_RX:
 	case FS_FT_RDMA_TX:
 	case FS_FT_PORT_SEL:
+	case FS_FT_RDMA_TRANSPORT_RX:
+	case FS_FT_RDMA_TRANSPORT_TX:
 		return mlx5_fs_cmd_get_fw_cmds();
 	default:
 		return mlx5_fs_cmd_get_stub_cmds();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 2eabfcc247c6..a8046200d376 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -658,6 +658,7 @@ static void del_sw_hw_rule(struct fs_node *node)
 			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
 			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
 		fte->act_dests.action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
+		mlx5_fc_local_destroy(rule->dest_attr.counter);
 		goto out;
 	}
 
@@ -820,11 +821,17 @@ static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte)
 		return index;
 
 	fte->index = index + fg->start_index;
+retry_insert:
 	ret = rhashtable_insert_fast(&fg->ftes_hash,
 				     &fte->hash,
 				     rhash_fte);
-	if (ret)
+	if (ret) {
+		if (ret == -EBUSY) {
+			cond_resched();
+			goto retry_insert;
+		}
 		goto err_ida_remove;
+	}
 
 	tree_add_node(&fte->node, &fg->node);
 	list_add_tail(&fte->node.list, &fg->node.children);
@@ -1449,7 +1456,7 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 	struct mlx5_flow_table *ft;
 	int autogroups_max_fte;
 
-	ft = mlx5_create_flow_table(ns, ft_attr);
+	ft = mlx5_create_vport_flow_table(ns, ft_attr, ft_attr->vport);
 	if (IS_ERR(ft))
 		return ft;
 
@@ -1823,14 +1830,35 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft,
 	return err;
 }
 
+int mlx5_fs_get_packet_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				   u32 *id)
+{
+	switch (pkt_reformat->owner) {
+	case MLX5_FLOW_RESOURCE_OWNER_FW:
+		*id = pkt_reformat->id;
+		return 0;
+	case MLX5_FLOW_RESOURCE_OWNER_SW:
+		return mlx5_fs_dr_action_get_pkt_reformat_id(pkt_reformat, id);
+	case MLX5_FLOW_RESOURCE_OWNER_HWS:
+		return mlx5_fs_hws_action_get_pkt_reformat_id(pkt_reformat, id);
+	default:
+		return -EINVAL;
+	}
+}
+
 static bool mlx5_pkt_reformat_cmp(struct mlx5_pkt_reformat *p1,
 				  struct mlx5_pkt_reformat *p2)
 {
-	return p1->owner == p2->owner &&
-		(p1->owner == MLX5_FLOW_RESOURCE_OWNER_FW ?
-		 p1->id == p2->id :
-		 mlx5_fs_dr_action_get_pkt_reformat_id(p1) ==
-		 mlx5_fs_dr_action_get_pkt_reformat_id(p2));
+	int err1, err2;
+	u32 id1, id2;
+
+	if (p1->owner != p2->owner)
+		return false;
+
+	err1 = mlx5_fs_get_packet_reformat_id(p1, &id1);
+	err2 = mlx5_fs_get_packet_reformat_id(p2, &id2);
+
+	return !err1 && !err2 && id1 == id2;
 }
 
 static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
@@ -2200,6 +2228,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	struct mlx5_flow_handle *rule;
 	struct match_list *iter;
 	bool take_write = false;
+	bool try_again = false;
 	struct fs_fte *fte;
 	u64  version = 0;
 	int err;
@@ -2264,6 +2293,7 @@ skip_search:
 		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
 
 		if (!g->node.active) {
+			try_again = true;
 			up_write_ref_node(&g->node, false);
 			continue;
 		}
@@ -2285,7 +2315,8 @@ skip_search:
 			tree_put_node(&fte->node, false);
 		return rule;
 	}
-	rule = ERR_PTR(-ENOENT);
+	err = try_again ? -EAGAIN : -ENOENT;
+	rule = ERR_PTR(err);
 out:
 	kmem_cache_free(steering->ftes_cache, fte);
 	return rule;
@@ -2709,6 +2740,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_TX:
 		root_ns = steering->rdma_tx_root_ns;
+		prio = RDMA_TX_BYPASS_PRIO;
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS:
 		root_ns = steering->rdma_rx_root_ns;
@@ -2756,9 +2788,9 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL(mlx5_get_flow_namespace);
 
-struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev,
-							      enum mlx5_flow_namespace_type type,
-							      int vport)
+struct mlx5_flow_namespace *
+mlx5_get_flow_vport_namespace(struct mlx5_core_dev *dev,
+			      enum mlx5_flow_namespace_type type, int vport_idx)
 {
 	struct mlx5_flow_steering *steering = dev->priv.steering;
 
@@ -2767,25 +2799,43 @@ struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_d
 
 	switch (type) {
 	case MLX5_FLOW_NAMESPACE_ESW_EGRESS:
-		if (vport >= steering->esw_egress_acl_vports)
+		if (vport_idx >= steering->esw_egress_acl_vports)
 			return NULL;
 		if (steering->esw_egress_root_ns &&
-		    steering->esw_egress_root_ns[vport])
-			return &steering->esw_egress_root_ns[vport]->ns;
+		    steering->esw_egress_root_ns[vport_idx])
+			return &steering->esw_egress_root_ns[vport_idx]->ns;
 		else
 			return NULL;
 	case MLX5_FLOW_NAMESPACE_ESW_INGRESS:
-		if (vport >= steering->esw_ingress_acl_vports)
+		if (vport_idx >= steering->esw_ingress_acl_vports)
 			return NULL;
 		if (steering->esw_ingress_root_ns &&
-		    steering->esw_ingress_root_ns[vport])
-			return &steering->esw_ingress_root_ns[vport]->ns;
+		    steering->esw_ingress_root_ns[vport_idx])
+			return &steering->esw_ingress_root_ns[vport_idx]->ns;
+		else
+			return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX:
+		if (vport_idx >= steering->rdma_transport_rx_vports)
+			return NULL;
+		if (steering->rdma_transport_rx_root_ns &&
+		    steering->rdma_transport_rx_root_ns[vport_idx])
+			return &steering->rdma_transport_rx_root_ns[vport_idx]->ns;
+		else
+			return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX:
+		if (vport_idx >= steering->rdma_transport_tx_vports)
+			return NULL;
+
+		if (steering->rdma_transport_tx_root_ns &&
+		    steering->rdma_transport_tx_root_ns[vport_idx])
+			return &steering->rdma_transport_tx_root_ns[vport_idx]->ns;
 		else
 			return NULL;
 	default:
 		return NULL;
 	}
 }
+EXPORT_SYMBOL(mlx5_get_flow_vport_namespace);
 
 static struct fs_prio *_fs_create_prio(struct mlx5_flow_namespace *ns,
 				       unsigned int prio,
@@ -3191,6 +3241,127 @@ out_err:
 	return err;
 }
 
+static int
+init_rdma_transport_rx_root_ns_one(struct mlx5_flow_steering *steering,
+				   int vport_idx)
+{
+	struct fs_prio *prio;
+
+	steering->rdma_transport_rx_root_ns[vport_idx] =
+		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_RX);
+	if (!steering->rdma_transport_rx_root_ns[vport_idx])
+		return -ENOMEM;
+
+	/* create 1 prio*/
+	prio = fs_create_prio(&steering->rdma_transport_rx_root_ns[vport_idx]->ns,
+			      MLX5_RDMA_TRANSPORT_BYPASS_PRIO, 1);
+	return PTR_ERR_OR_ZERO(prio);
+}
+
+static int
+init_rdma_transport_tx_root_ns_one(struct mlx5_flow_steering *steering,
+				   int vport_idx)
+{
+	struct fs_prio *prio;
+
+	steering->rdma_transport_tx_root_ns[vport_idx] =
+		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_TX);
+	if (!steering->rdma_transport_tx_root_ns[vport_idx])
+		return -ENOMEM;
+
+	/* create 1 prio*/
+	prio = fs_create_prio(&steering->rdma_transport_tx_root_ns[vport_idx]->ns,
+			      MLX5_RDMA_TRANSPORT_BYPASS_PRIO, 1);
+	return PTR_ERR_OR_ZERO(prio);
+}
+
+static int init_rdma_transport_rx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct mlx5_core_dev *dev = steering->dev;
+	int total_vports;
+	int err;
+	int i;
+
+	/* In case eswitch not supported and working in legacy mode */
+	total_vports = mlx5_eswitch_get_total_vports(dev) ?: 1;
+
+	steering->rdma_transport_rx_root_ns =
+			kcalloc(total_vports,
+				sizeof(*steering->rdma_transport_rx_root_ns),
+				GFP_KERNEL);
+	if (!steering->rdma_transport_rx_root_ns)
+		return -ENOMEM;
+
+	for (i = 0; i < total_vports; i++) {
+		err = init_rdma_transport_rx_root_ns_one(steering, i);
+		if (err)
+			goto cleanup_root_ns;
+	}
+	steering->rdma_transport_rx_vports = total_vports;
+	return 0;
+
+cleanup_root_ns:
+	while (i--)
+		cleanup_root_ns(steering->rdma_transport_rx_root_ns[i]);
+	kfree(steering->rdma_transport_rx_root_ns);
+	steering->rdma_transport_rx_root_ns = NULL;
+	return err;
+}
+
+static int init_rdma_transport_tx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct mlx5_core_dev *dev = steering->dev;
+	int total_vports;
+	int err;
+	int i;
+
+	/* In case eswitch not supported and working in legacy mode */
+	total_vports = mlx5_eswitch_get_total_vports(dev) ?: 1;
+
+	steering->rdma_transport_tx_root_ns =
+			kcalloc(total_vports,
+				sizeof(*steering->rdma_transport_tx_root_ns),
+				GFP_KERNEL);
+	if (!steering->rdma_transport_tx_root_ns)
+		return -ENOMEM;
+
+	for (i = 0; i < total_vports; i++) {
+		err = init_rdma_transport_tx_root_ns_one(steering, i);
+		if (err)
+			goto cleanup_root_ns;
+	}
+	steering->rdma_transport_tx_vports = total_vports;
+	return 0;
+
+cleanup_root_ns:
+	while (i--)
+		cleanup_root_ns(steering->rdma_transport_tx_root_ns[i]);
+	kfree(steering->rdma_transport_tx_root_ns);
+	steering->rdma_transport_tx_root_ns = NULL;
+	return err;
+}
+
+static void cleanup_rdma_transport_roots_ns(struct mlx5_flow_steering *steering)
+{
+	int i;
+
+	if (steering->rdma_transport_rx_root_ns) {
+		for (i = 0; i < steering->rdma_transport_rx_vports; i++)
+			cleanup_root_ns(steering->rdma_transport_rx_root_ns[i]);
+
+		kfree(steering->rdma_transport_rx_root_ns);
+		steering->rdma_transport_rx_root_ns = NULL;
+	}
+
+	if (steering->rdma_transport_tx_root_ns) {
+		for (i = 0; i < steering->rdma_transport_tx_vports; i++)
+			cleanup_root_ns(steering->rdma_transport_tx_root_ns[i]);
+
+		kfree(steering->rdma_transport_tx_root_ns);
+		steering->rdma_transport_tx_root_ns = NULL;
+	}
+}
+
 /* FT and tc chains are stored in the same array so we can re-use the
  * mlx5_get_fdb_sub_ns() and tc api for FT chains.
  * When creating a new ns for each chain store it in the first available slot.
@@ -3528,35 +3699,42 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	char *value = val.vstr;
-	int err = 0;
+	u8 eswitch_mode;
 
-	if (!strcmp(value, "dmfs")) {
+	if (!strcmp(value, "dmfs"))
 		return 0;
-	} else if (!strcmp(value, "smfs")) {
-		u8 eswitch_mode;
-		bool smfs_cap;
 
-		eswitch_mode = mlx5_eswitch_mode(dev);
-		smfs_cap = mlx5_fs_dr_is_supported(dev);
+	if (!strcmp(value, "smfs")) {
+		bool smfs_cap = mlx5_fs_dr_is_supported(dev);
 
 		if (!smfs_cap) {
-			err = -EOPNOTSUPP;
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Software managed steering is not supported by current device");
+			return -EOPNOTSUPP;
 		}
+	} else if (!strcmp(value, "hmfs")) {
+		bool hmfs_cap = mlx5_fs_hws_is_supported(dev);
 
-		else if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+		if (!hmfs_cap) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Software managed steering is not supported when eswitch offloads enabled.");
-			err = -EOPNOTSUPP;
+					   "Hardware steering is not supported by current device");
+			return -EOPNOTSUPP;
 		}
 	} else {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Bad parameter: supported values are [\"dmfs\", \"smfs\"]");
-		err = -EINVAL;
+				   "Bad parameter: supported values are [\"dmfs\", \"smfs\", \"hmfs\"]");
+		return -EINVAL;
 	}
 
-	return err;
+	eswitch_mode = mlx5_eswitch_mode(dev);
+	if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Moving to %s is not supported when eswitch offloads enabled.",
+				       value);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
 }
 
 static int mlx5_fs_mode_set(struct devlink *devlink, u32 id,
@@ -3568,6 +3746,8 @@ static int mlx5_fs_mode_set(struct devlink *devlink, u32 id,
 
 	if (!strcmp(ctx->val.vstr, "smfs"))
 		mode = MLX5_FLOW_STEERING_MODE_SMFS;
+	else if (!strcmp(ctx->val.vstr, "hmfs"))
+		mode = MLX5_FLOW_STEERING_MODE_HMFS;
 	else
 		mode = MLX5_FLOW_STEERING_MODE_DMFS;
 	dev->priv.steering->mode = mode;
@@ -3580,10 +3760,17 @@ static int mlx5_fs_mode_get(struct devlink *devlink, u32 id,
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 
-	if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS)
+	switch (dev->priv.steering->mode) {
+	case MLX5_FLOW_STEERING_MODE_SMFS:
 		strscpy(ctx->val.vstr, "smfs", sizeof(ctx->val.vstr));
-	else
+		break;
+	case MLX5_FLOW_STEERING_MODE_HMFS:
+		strscpy(ctx->val.vstr, "hmfs", sizeof(ctx->val.vstr));
+		break;
+	default:
 		strscpy(ctx->val.vstr, "dmfs", sizeof(ctx->val.vstr));
+	}
+
 	return 0;
 }
 
@@ -3607,6 +3794,7 @@ void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev)
 	cleanup_root_ns(steering->rdma_rx_root_ns);
 	cleanup_root_ns(steering->rdma_tx_root_ns);
 	cleanup_root_ns(steering->egress_root_ns);
+	cleanup_rdma_transport_roots_ns(steering);
 
 	devl_params_unregister(priv_to_devlink(dev), mlx5_fs_params,
 			       ARRAY_SIZE(mlx5_fs_params));
@@ -3658,8 +3846,7 @@ int mlx5_fs_core_init(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
-	    MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) {
+	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support)) {
 		err = init_rdma_rx_root_ns(steering);
 		if (err)
 			goto err;
@@ -3677,6 +3864,18 @@ int mlx5_fs_core_init(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
+	if (MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(dev, ft_support)) {
+		err = init_rdma_transport_rx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
+	if (MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(dev, ft_support)) {
+		err = init_rdma_transport_tx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
 	return 0;
 
 err:
@@ -3827,8 +4026,10 @@ mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type
 	struct mlx5_flow_namespace *ns;
 
 	if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS ||
-	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS)
-		ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0);
+	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS ||
+	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX ||
+	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX)
+		ns = mlx5_get_flow_vport_namespace(dev, ns_type, 0);
 	else
 		ns = mlx5_get_flow_namespace(dev, ns_type);
 	if (!ns)
@@ -4003,6 +4204,8 @@ int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns,
 
 	if (mode == MLX5_FLOW_STEERING_MODE_SMFS)
 		cmds = mlx5_fs_cmd_get_dr_cmds();
+	else if (mode == MLX5_FLOW_STEERING_MODE_HMFS)
+		cmds = mlx5_fs_cmd_get_hws_cmds();
 	else
 		cmds = mlx5_fs_cmd_get_fw_cmds();
 	if (!cmds)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index bad2df0715ec..500826229b0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -38,6 +38,7 @@
 #include <linux/rhashtable.h>
 #include <linux/llist.h>
 #include <steering/sws/fs_dr.h>
+#include <steering/hws/fs_hws.h>
 
 #define FDB_TC_MAX_CHAIN 3
 #define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1)
@@ -57,6 +58,7 @@ struct mlx5_flow_definer {
 enum mlx5_flow_resource_owner {
 	MLX5_FLOW_RESOURCE_OWNER_FW,
 	MLX5_FLOW_RESOURCE_OWNER_SW,
+	MLX5_FLOW_RESOURCE_OWNER_HWS,
 };
 
 struct mlx5_modify_hdr {
@@ -64,6 +66,7 @@ struct mlx5_modify_hdr {
 	enum mlx5_flow_resource_owner owner;
 	union {
 		struct mlx5_fs_dr_action fs_dr_action;
+		struct mlx5_fs_hws_action fs_hws_action;
 		u32 id;
 	};
 };
@@ -74,6 +77,7 @@ struct mlx5_pkt_reformat {
 	enum mlx5_flow_resource_owner owner;
 	union {
 		struct mlx5_fs_dr_action fs_dr_action;
+		struct mlx5_fs_hws_action fs_hws_action;
 		u32 id;
 	};
 };
@@ -112,7 +116,9 @@ enum fs_flow_table_type {
 	FS_FT_PORT_SEL		= 0X9,
 	FS_FT_FDB_RX		= 0xa,
 	FS_FT_FDB_TX		= 0xb,
-	FS_FT_MAX_TYPE = FS_FT_FDB_TX,
+	FS_FT_RDMA_TRANSPORT_RX	= 0xd,
+	FS_FT_RDMA_TRANSPORT_TX	= 0xe,
+	FS_FT_MAX_TYPE = FS_FT_RDMA_TRANSPORT_TX,
 };
 
 enum fs_flow_table_op_mod {
@@ -126,7 +132,8 @@ enum fs_fte_status {
 
 enum mlx5_flow_steering_mode {
 	MLX5_FLOW_STEERING_MODE_DMFS,
-	MLX5_FLOW_STEERING_MODE_SMFS
+	MLX5_FLOW_STEERING_MODE_SMFS,
+	MLX5_FLOW_STEERING_MODE_HMFS,
 };
 
 enum mlx5_flow_steering_capabilty {
@@ -154,6 +161,10 @@ struct mlx5_flow_steering {
 	struct mlx5_flow_root_namespace	*port_sel_root_ns;
 	int esw_egress_acl_vports;
 	int esw_ingress_acl_vports;
+	struct mlx5_flow_root_namespace **rdma_transport_rx_root_ns;
+	struct mlx5_flow_root_namespace **rdma_transport_tx_root_ns;
+	int rdma_transport_rx_vports;
+	int rdma_transport_tx_vports;
 };
 
 struct fs_node {
@@ -190,7 +201,10 @@ struct mlx5_flow_handle {
 /* Type of children is mlx5_flow_group */
 struct mlx5_flow_table {
 	struct fs_node			node;
-	struct mlx5_fs_dr_table		fs_dr_table;
+	union {
+		struct mlx5_fs_dr_table		fs_dr_table;
+		struct mlx5_fs_hws_table	fs_hws_table;
+	};
 	u32				id;
 	u16				vport;
 	unsigned int			max_fte;
@@ -247,7 +261,10 @@ struct fs_fte_dup {
 /* Type of children is mlx5_flow_rule */
 struct fs_fte {
 	struct fs_node			node;
-	struct mlx5_fs_dr_rule		fs_dr_rule;
+	union {
+		struct mlx5_fs_dr_rule		fs_dr_rule;
+		struct mlx5_fs_hws_rule		fs_hws_rule;
+	};
 	u32				val[MLX5_ST_SZ_DW_MATCH_PARAM];
 	struct fs_fte_action		act_dests;
 	struct fs_fte_dup		*dup;
@@ -280,7 +297,10 @@ struct mlx5_flow_group_mask {
 /* Type of children is fs_fte */
 struct mlx5_flow_group {
 	struct fs_node			node;
-	struct mlx5_fs_dr_matcher	fs_dr_matcher;
+	union {
+		struct mlx5_fs_dr_matcher	fs_dr_matcher;
+		struct mlx5_fs_hws_matcher	fs_hws_matcher;
+	};
 	struct mlx5_flow_group_mask	mask;
 	u32				start_index;
 	u32				max_ftes;
@@ -293,7 +313,10 @@ struct mlx5_flow_group {
 struct mlx5_flow_root_namespace {
 	struct mlx5_flow_namespace	ns;
 	enum   mlx5_flow_steering_mode	mode;
-	struct mlx5_fs_dr_domain	fs_dr_domain;
+	union {
+		struct mlx5_fs_dr_domain	fs_dr_domain;
+		struct mlx5_fs_hws_context	fs_hws_context;
+	};
 	enum   fs_flow_table_type	table_type;
 	struct mlx5_core_dev		*dev;
 	struct mlx5_flow_table		*root_ft;
@@ -303,6 +326,36 @@ struct mlx5_flow_root_namespace {
 	const struct mlx5_flow_cmds	*cmds;
 };
 
+enum mlx5_fc_type {
+	MLX5_FC_TYPE_ACQUIRED = 0,
+	MLX5_FC_TYPE_LOCAL,
+};
+
+struct mlx5_fc_cache {
+	u64 packets;
+	u64 bytes;
+	u64 lastuse;
+};
+
+struct mlx5_fc {
+	u32 id;
+	bool aging;
+	enum mlx5_fc_type type;
+	struct mlx5_fc_bulk *bulk;
+	struct mlx5_fc_cache cache;
+	/* last{packets,bytes} are used for calculating deltas since last reading. */
+	u64 lastpackets;
+	u64 lastbytes;
+};
+
+struct mlx5_fc_bulk {
+	struct mlx5_fs_bulk fs_bulk;
+	u32 base_id;
+	struct mlx5_fs_hws_data hws_data;
+	struct mlx5_fc fcs[];
+};
+
+u32 mlx5_fc_get_base_id(struct mlx5_fc *counter);
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev);
 void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev);
 void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev,
@@ -334,6 +387,9 @@ u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace
 
 struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
 
+int mlx5_fs_get_packet_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				   u32 *id);
+
 #define fs_get_obj(v, _node)  {v = container_of((_node), typeof(*v), node); }
 
 #define fs_list_for_each_entry(pos, root)		\
@@ -382,7 +438,9 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
 	(type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) :      \
 	(type == FS_FT_FDB_RX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \
 	(type == FS_FT_FDB_TX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \
-	(BUILD_BUG_ON_ZERO(FS_FT_FDB_TX != FS_FT_MAX_TYPE))\
+	(type == FS_FT_RDMA_TRANSPORT_RX) ? MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(mdev, cap) :      \
+	(type == FS_FT_RDMA_TRANSPORT_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(mdev, cap) :      \
+	(BUILD_BUG_ON_ZERO(FS_FT_RDMA_TRANSPORT_TX != FS_FT_MAX_TYPE))\
 	)
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 62d0c689796b..492775d3d193 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -34,6 +34,7 @@
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
 #include "fs_core.h"
+#include "fs_pool.h"
 #include "fs_cmd.h"
 
 #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000)
@@ -43,33 +44,6 @@
 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18)
 #define MLX5_FC_POOL_USED_BUFF_RATIO 10
 
-struct mlx5_fc_cache {
-	u64 packets;
-	u64 bytes;
-	u64 lastuse;
-};
-
-struct mlx5_fc {
-	u32 id;
-	bool aging;
-	struct mlx5_fc_bulk *bulk;
-	struct mlx5_fc_cache cache;
-	/* last{packets,bytes} are used for calculating deltas since last reading. */
-	u64 lastpackets;
-	u64 lastbytes;
-};
-
-struct mlx5_fc_pool {
-	struct mlx5_core_dev *dev;
-	struct mutex pool_lock; /* protects pool lists */
-	struct list_head fully_used;
-	struct list_head partially_used;
-	struct list_head unused;
-	int available_fcs;
-	int used_fcs;
-	int threshold;
-};
-
 struct mlx5_fc_stats {
 	struct xarray counters;
 
@@ -80,13 +54,13 @@ struct mlx5_fc_stats {
 	int bulk_query_len;
 	bool bulk_query_alloc_failed;
 	unsigned long next_bulk_query_alloc;
-	struct mlx5_fc_pool fc_pool;
+	struct mlx5_fs_pool fc_pool;
 };
 
-static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev);
-static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool);
-static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool);
-static void mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc);
+static void mlx5_fc_pool_init(struct mlx5_fs_pool *fc_pool, struct mlx5_core_dev *dev);
+static void mlx5_fc_pool_cleanup(struct mlx5_fs_pool *fc_pool);
+static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fs_pool *fc_pool);
+static void mlx5_fc_pool_release_counter(struct mlx5_fs_pool *fc_pool, struct mlx5_fc *fc);
 
 static int get_init_bulk_query_len(struct mlx5_core_dev *dev)
 {
@@ -186,6 +160,9 @@ static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter)
 {
 	struct mlx5_fc_stats *fc_stats = dev->priv.fc_stats;
 
+	if (WARN_ON(counter->type == MLX5_FC_TYPE_LOCAL))
+		return;
+
 	if (counter->bulk)
 		mlx5_fc_pool_release_counter(&fc_stats->fc_pool, counter);
 	else
@@ -435,15 +412,7 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev,
 					    fc_stats->sampling_interval);
 }
 
-/* Flow counter bluks */
-
-struct mlx5_fc_bulk {
-	struct list_head pool_list;
-	u32 base_id;
-	int bulk_len;
-	unsigned long *bitmask;
-	struct mlx5_fc fcs[] __counted_by(bulk_len);
-};
+/* Flow counter bulks */
 
 static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk,
 			 u32 id)
@@ -452,16 +421,16 @@ static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk,
 	counter->id = id;
 }
 
-static int mlx5_fc_bulk_get_free_fcs_amount(struct mlx5_fc_bulk *bulk)
+u32 mlx5_fc_get_base_id(struct mlx5_fc *counter)
 {
-	return bitmap_weight(bulk->bitmask, bulk->bulk_len);
+	return counter->bulk->base_id;
 }
 
-static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev)
+static struct mlx5_fs_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev,
+						void *pool_ctx)
 {
 	enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask;
-	struct mlx5_fc_bulk *bulk;
-	int err = -ENOMEM;
+	struct mlx5_fc_bulk *fc_bulk;
 	int bulk_len;
 	u32 base_id;
 	int i;
@@ -469,207 +438,141 @@ static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev)
 	alloc_bitmask = MLX5_CAP_GEN(dev, flow_counter_bulk_alloc);
 	bulk_len = alloc_bitmask > 0 ? MLX5_FC_BULK_NUM_FCS(alloc_bitmask) : 1;
 
-	bulk = kvzalloc(struct_size(bulk, fcs, bulk_len), GFP_KERNEL);
-	if (!bulk)
-		goto err_alloc_bulk;
-
-	bulk->bitmask = kvcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long),
-				 GFP_KERNEL);
-	if (!bulk->bitmask)
-		goto err_alloc_bitmask;
+	fc_bulk = kvzalloc(struct_size(fc_bulk, fcs, bulk_len), GFP_KERNEL);
+	if (!fc_bulk)
+		return NULL;
 
-	err = mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id);
-	if (err)
-		goto err_mlx5_cmd_bulk_alloc;
+	if (mlx5_fs_bulk_init(dev, &fc_bulk->fs_bulk, bulk_len))
+		goto fc_bulk_free;
 
-	bulk->base_id = base_id;
-	bulk->bulk_len = bulk_len;
-	for (i = 0; i < bulk_len; i++) {
-		mlx5_fc_init(&bulk->fcs[i], bulk, base_id + i);
-		set_bit(i, bulk->bitmask);
-	}
+	if (mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id))
+		goto fs_bulk_cleanup;
+	fc_bulk->base_id = base_id;
+	for (i = 0; i < bulk_len; i++)
+		mlx5_fc_init(&fc_bulk->fcs[i], fc_bulk, base_id + i);
 
-	return bulk;
+	refcount_set(&fc_bulk->hws_data.hws_action_refcount, 0);
+	mutex_init(&fc_bulk->hws_data.lock);
+	return &fc_bulk->fs_bulk;
 
-err_mlx5_cmd_bulk_alloc:
-	kvfree(bulk->bitmask);
-err_alloc_bitmask:
-	kvfree(bulk);
-err_alloc_bulk:
-	return ERR_PTR(err);
+fs_bulk_cleanup:
+	mlx5_fs_bulk_cleanup(&fc_bulk->fs_bulk);
+fc_bulk_free:
+	kvfree(fc_bulk);
+	return NULL;
 }
 
 static int
-mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk)
+mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk)
 {
-	if (mlx5_fc_bulk_get_free_fcs_amount(bulk) < bulk->bulk_len) {
+	struct mlx5_fc_bulk *fc_bulk = container_of(fs_bulk,
+						    struct mlx5_fc_bulk,
+						    fs_bulk);
+
+	if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) {
 		mlx5_core_err(dev, "Freeing bulk before all counters were released\n");
 		return -EBUSY;
 	}
 
-	mlx5_cmd_fc_free(dev, bulk->base_id);
-	kvfree(bulk->bitmask);
-	kvfree(bulk);
+	mlx5_cmd_fc_free(dev, fc_bulk->base_id);
+	mlx5_fs_bulk_cleanup(fs_bulk);
+	kvfree(fc_bulk);
 
 	return 0;
 }
 
-static struct mlx5_fc *mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk)
+static void mlx5_fc_pool_update_threshold(struct mlx5_fs_pool *fc_pool)
 {
-	int free_fc_index = find_first_bit(bulk->bitmask, bulk->bulk_len);
-
-	if (free_fc_index >= bulk->bulk_len)
-		return ERR_PTR(-ENOSPC);
-
-	clear_bit(free_fc_index, bulk->bitmask);
-	return &bulk->fcs[free_fc_index];
-}
-
-static int mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc)
-{
-	int fc_index = fc->id - bulk->base_id;
-
-	if (test_bit(fc_index, bulk->bitmask))
-		return -EINVAL;
-
-	set_bit(fc_index, bulk->bitmask);
-	return 0;
+	fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD,
+				   fc_pool->used_units / MLX5_FC_POOL_USED_BUFF_RATIO);
 }
 
 /* Flow counters pool API */
 
-static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev)
-{
-	fc_pool->dev = dev;
-	mutex_init(&fc_pool->pool_lock);
-	INIT_LIST_HEAD(&fc_pool->fully_used);
-	INIT_LIST_HEAD(&fc_pool->partially_used);
-	INIT_LIST_HEAD(&fc_pool->unused);
-	fc_pool->available_fcs = 0;
-	fc_pool->used_fcs = 0;
-	fc_pool->threshold = 0;
-}
+static const struct mlx5_fs_pool_ops mlx5_fc_pool_ops = {
+	.bulk_destroy = mlx5_fc_bulk_destroy,
+	.bulk_create = mlx5_fc_bulk_create,
+	.update_threshold = mlx5_fc_pool_update_threshold,
+};
 
-static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool)
+static void
+mlx5_fc_pool_init(struct mlx5_fs_pool *fc_pool, struct mlx5_core_dev *dev)
 {
-	struct mlx5_core_dev *dev = fc_pool->dev;
-	struct mlx5_fc_bulk *bulk;
-	struct mlx5_fc_bulk *tmp;
-
-	list_for_each_entry_safe(bulk, tmp, &fc_pool->fully_used, pool_list)
-		mlx5_fc_bulk_destroy(dev, bulk);
-	list_for_each_entry_safe(bulk, tmp, &fc_pool->partially_used, pool_list)
-		mlx5_fc_bulk_destroy(dev, bulk);
-	list_for_each_entry_safe(bulk, tmp, &fc_pool->unused, pool_list)
-		mlx5_fc_bulk_destroy(dev, bulk);
+	mlx5_fs_pool_init(fc_pool, dev, &mlx5_fc_pool_ops, NULL);
 }
 
-static void mlx5_fc_pool_update_threshold(struct mlx5_fc_pool *fc_pool)
+static void mlx5_fc_pool_cleanup(struct mlx5_fs_pool *fc_pool)
 {
-	fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD,
-				   fc_pool->used_fcs / MLX5_FC_POOL_USED_BUFF_RATIO);
+	mlx5_fs_pool_cleanup(fc_pool);
 }
 
-static struct mlx5_fc_bulk *
-mlx5_fc_pool_alloc_new_bulk(struct mlx5_fc_pool *fc_pool)
+static struct mlx5_fc *
+mlx5_fc_pool_acquire_counter(struct mlx5_fs_pool *fc_pool)
 {
-	struct mlx5_core_dev *dev = fc_pool->dev;
-	struct mlx5_fc_bulk *new_bulk;
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_fc_bulk *fc_bulk;
+	int err;
 
-	new_bulk = mlx5_fc_bulk_create(dev);
-	if (!IS_ERR(new_bulk))
-		fc_pool->available_fcs += new_bulk->bulk_len;
-	mlx5_fc_pool_update_threshold(fc_pool);
-	return new_bulk;
+	err = mlx5_fs_pool_acquire_index(fc_pool, &pool_index);
+	if (err)
+		return ERR_PTR(err);
+	fc_bulk = container_of(pool_index.fs_bulk, struct mlx5_fc_bulk, fs_bulk);
+	return &fc_bulk->fcs[pool_index.index];
 }
 
 static void
-mlx5_fc_pool_free_bulk(struct mlx5_fc_pool *fc_pool, struct mlx5_fc_bulk *bulk)
+mlx5_fc_pool_release_counter(struct mlx5_fs_pool *fc_pool, struct mlx5_fc *fc)
 {
+	struct mlx5_fs_bulk *fs_bulk = &fc->bulk->fs_bulk;
+	struct mlx5_fs_pool_index pool_index = {};
 	struct mlx5_core_dev *dev = fc_pool->dev;
 
-	fc_pool->available_fcs -= bulk->bulk_len;
-	mlx5_fc_bulk_destroy(dev, bulk);
-	mlx5_fc_pool_update_threshold(fc_pool);
+	pool_index.fs_bulk = fs_bulk;
+	pool_index.index = fc->id - fc->bulk->base_id;
+	if (mlx5_fs_pool_release_index(fc_pool, &pool_index))
+		mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n");
 }
 
-static struct mlx5_fc *
-mlx5_fc_pool_acquire_from_list(struct list_head *src_list,
-			       struct list_head *next_list,
-			       bool move_non_full_bulk)
+/**
+ * mlx5_fc_local_create - Allocate mlx5_fc struct for a counter which
+ * was already acquired using its counter id and bulk data.
+ *
+ * @counter_id: counter acquired counter id
+ * @offset: counter offset from bulk base
+ * @bulk_size: counter's bulk size as was allocated
+ *
+ * Return: Pointer to mlx5_fc on success, ERR_PTR otherwise.
+ */
+struct mlx5_fc *
+mlx5_fc_local_create(u32 counter_id, u32 offset, u32 bulk_size)
 {
-	struct mlx5_fc_bulk *bulk;
-	struct mlx5_fc *fc;
-
-	if (list_empty(src_list))
-		return ERR_PTR(-ENODATA);
-
-	bulk = list_first_entry(src_list, struct mlx5_fc_bulk, pool_list);
-	fc = mlx5_fc_bulk_acquire_fc(bulk);
-	if (move_non_full_bulk || mlx5_fc_bulk_get_free_fcs_amount(bulk) == 0)
-		list_move(&bulk->pool_list, next_list);
-	return fc;
-}
+	struct mlx5_fc_bulk *fc_bulk;
+	struct mlx5_fc *counter;
 
-static struct mlx5_fc *
-mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool)
-{
-	struct mlx5_fc_bulk *new_bulk;
-	struct mlx5_fc *fc;
-
-	mutex_lock(&fc_pool->pool_lock);
-
-	fc = mlx5_fc_pool_acquire_from_list(&fc_pool->partially_used,
-					    &fc_pool->fully_used, false);
-	if (IS_ERR(fc))
-		fc = mlx5_fc_pool_acquire_from_list(&fc_pool->unused,
-						    &fc_pool->partially_used,
-						    true);
-	if (IS_ERR(fc)) {
-		new_bulk = mlx5_fc_pool_alloc_new_bulk(fc_pool);
-		if (IS_ERR(new_bulk)) {
-			fc = ERR_CAST(new_bulk);
-			goto out;
-		}
-		fc = mlx5_fc_bulk_acquire_fc(new_bulk);
-		list_add(&new_bulk->pool_list, &fc_pool->partially_used);
+	counter = kzalloc(sizeof(*counter), GFP_KERNEL);
+	if (!counter)
+		return ERR_PTR(-ENOMEM);
+	fc_bulk = kzalloc(sizeof(*fc_bulk), GFP_KERNEL);
+	if (!fc_bulk) {
+		kfree(counter);
+		return ERR_PTR(-ENOMEM);
 	}
-	fc_pool->available_fcs--;
-	fc_pool->used_fcs++;
 
-out:
-	mutex_unlock(&fc_pool->pool_lock);
-	return fc;
+	counter->type = MLX5_FC_TYPE_LOCAL;
+	counter->id = counter_id;
+	fc_bulk->base_id = counter_id - offset;
+	fc_bulk->fs_bulk.bulk_len = bulk_size;
+	counter->bulk = fc_bulk;
+	return counter;
 }
+EXPORT_SYMBOL(mlx5_fc_local_create);
 
-static void
-mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc)
+void mlx5_fc_local_destroy(struct mlx5_fc *counter)
 {
-	struct mlx5_core_dev *dev = fc_pool->dev;
-	struct mlx5_fc_bulk *bulk = fc->bulk;
-	int bulk_free_fcs_amount;
-
-	mutex_lock(&fc_pool->pool_lock);
-
-	if (mlx5_fc_bulk_release_fc(bulk, fc)) {
-		mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n");
-		goto unlock;
-	}
-
-	fc_pool->available_fcs++;
-	fc_pool->used_fcs--;
-
-	bulk_free_fcs_amount = mlx5_fc_bulk_get_free_fcs_amount(bulk);
-	if (bulk_free_fcs_amount == 1)
-		list_move_tail(&bulk->pool_list, &fc_pool->partially_used);
-	if (bulk_free_fcs_amount == bulk->bulk_len) {
-		list_del(&bulk->pool_list);
-		if (fc_pool->available_fcs > fc_pool->threshold)
-			mlx5_fc_pool_free_bulk(fc_pool, bulk);
-		else
-			list_add(&bulk->pool_list, &fc_pool->unused);
-	}
+	if (!counter || counter->type != MLX5_FC_TYPE_LOCAL)
+		return;
 
-unlock:
-	mutex_unlock(&fc_pool->pool_lock);
+	kfree(counter->bulk);
+	kfree(counter);
 }
+EXPORT_SYMBOL(mlx5_fc_local_destroy);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
index c14590acc772..f6abfd00d7e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
@@ -50,10 +50,12 @@ mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type tab
 	int i, found_i = -1;
 
 	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
-		if (dev->priv.ft_pool->ft_left[i] && FT_POOLS[i] >= desired_size &&
+		if (dev->priv.ft_pool->ft_left[i] &&
+		    (FT_POOLS[i] >= desired_size ||
+		     desired_size == MLX5_FS_MAX_POOL_SIZE) &&
 		    FT_POOLS[i] <= max_ft_size) {
 			found_i = i;
-			if (desired_size != POOL_NEXT_SIZE)
+			if (desired_size != MLX5_FS_MAX_POOL_SIZE)
 				break;
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
index 25f4274b372b..173e312db720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
@@ -7,8 +7,6 @@
 #include <linux/mlx5/driver.h>
 #include "fs_core.h"
 
-#define POOL_NEXT_SIZE 0
-
 int mlx5_ft_pool_init(struct mlx5_core_dev *dev);
 void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c
new file mode 100644
index 000000000000..f6c226664602
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include <mlx5_core.h>
+#include "fs_pool.h"
+
+int mlx5_fs_bulk_init(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk,
+		      int bulk_len)
+{
+	int i;
+
+	fs_bulk->bitmask = kvcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long),
+				    GFP_KERNEL);
+	if (!fs_bulk->bitmask)
+		return -ENOMEM;
+
+	fs_bulk->bulk_len = bulk_len;
+	for (i = 0; i < bulk_len; i++)
+		set_bit(i, fs_bulk->bitmask);
+
+	return 0;
+}
+
+void mlx5_fs_bulk_cleanup(struct mlx5_fs_bulk *fs_bulk)
+{
+	kvfree(fs_bulk->bitmask);
+}
+
+int mlx5_fs_bulk_get_free_amount(struct mlx5_fs_bulk *bulk)
+{
+	return bitmap_weight(bulk->bitmask, bulk->bulk_len);
+}
+
+static int mlx5_fs_bulk_acquire_index(struct mlx5_fs_bulk *fs_bulk,
+				      struct mlx5_fs_pool_index *pool_index)
+{
+	int free_index = find_first_bit(fs_bulk->bitmask, fs_bulk->bulk_len);
+
+	WARN_ON_ONCE(!pool_index || !fs_bulk);
+	if (free_index >= fs_bulk->bulk_len)
+		return -ENOSPC;
+
+	clear_bit(free_index, fs_bulk->bitmask);
+	pool_index->fs_bulk = fs_bulk;
+	pool_index->index = free_index;
+	return 0;
+}
+
+static int mlx5_fs_bulk_release_index(struct mlx5_fs_bulk *fs_bulk, int index)
+{
+	if (test_bit(index, fs_bulk->bitmask))
+		return -EINVAL;
+
+	set_bit(index, fs_bulk->bitmask);
+	return 0;
+}
+
+void mlx5_fs_pool_init(struct mlx5_fs_pool *pool, struct mlx5_core_dev *dev,
+		       const struct mlx5_fs_pool_ops *ops, void *pool_ctx)
+{
+	WARN_ON_ONCE(!ops || !ops->bulk_destroy || !ops->bulk_create ||
+		     !ops->update_threshold);
+	pool->dev = dev;
+	pool->pool_ctx = pool_ctx;
+	mutex_init(&pool->pool_lock);
+	INIT_LIST_HEAD(&pool->fully_used);
+	INIT_LIST_HEAD(&pool->partially_used);
+	INIT_LIST_HEAD(&pool->unused);
+	pool->available_units = 0;
+	pool->used_units = 0;
+	pool->threshold = 0;
+	pool->ops = ops;
+}
+
+void mlx5_fs_pool_cleanup(struct mlx5_fs_pool *pool)
+{
+	struct mlx5_core_dev *dev = pool->dev;
+	struct mlx5_fs_bulk *bulk;
+	struct mlx5_fs_bulk *tmp;
+
+	list_for_each_entry_safe(bulk, tmp, &pool->fully_used, pool_list)
+		pool->ops->bulk_destroy(dev, bulk);
+	list_for_each_entry_safe(bulk, tmp, &pool->partially_used, pool_list)
+		pool->ops->bulk_destroy(dev, bulk);
+	list_for_each_entry_safe(bulk, tmp, &pool->unused, pool_list)
+		pool->ops->bulk_destroy(dev, bulk);
+}
+
+static struct mlx5_fs_bulk *
+mlx5_fs_pool_alloc_new_bulk(struct mlx5_fs_pool *fs_pool)
+{
+	struct mlx5_core_dev *dev = fs_pool->dev;
+	struct mlx5_fs_bulk *new_bulk;
+
+	new_bulk = fs_pool->ops->bulk_create(dev, fs_pool->pool_ctx);
+	if (new_bulk)
+		fs_pool->available_units += new_bulk->bulk_len;
+	fs_pool->ops->update_threshold(fs_pool);
+	return new_bulk;
+}
+
+static void
+mlx5_fs_pool_free_bulk(struct mlx5_fs_pool *fs_pool, struct mlx5_fs_bulk *bulk)
+{
+	struct mlx5_core_dev *dev = fs_pool->dev;
+
+	fs_pool->available_units -= bulk->bulk_len;
+	fs_pool->ops->bulk_destroy(dev, bulk);
+	fs_pool->ops->update_threshold(fs_pool);
+}
+
+static int
+mlx5_fs_pool_acquire_from_list(struct list_head *src_list,
+			       struct list_head *next_list,
+			       bool move_non_full_bulk,
+			       struct mlx5_fs_pool_index *pool_index)
+{
+	struct mlx5_fs_bulk *fs_bulk;
+	int err;
+
+	if (list_empty(src_list))
+		return -ENODATA;
+
+	fs_bulk = list_first_entry(src_list, struct mlx5_fs_bulk, pool_list);
+	err = mlx5_fs_bulk_acquire_index(fs_bulk, pool_index);
+	if (move_non_full_bulk || mlx5_fs_bulk_get_free_amount(fs_bulk) == 0)
+		list_move(&fs_bulk->pool_list, next_list);
+	return err;
+}
+
+int mlx5_fs_pool_acquire_index(struct mlx5_fs_pool *fs_pool,
+			       struct mlx5_fs_pool_index *pool_index)
+{
+	struct mlx5_fs_bulk *new_bulk;
+	int err;
+
+	mutex_lock(&fs_pool->pool_lock);
+
+	err = mlx5_fs_pool_acquire_from_list(&fs_pool->partially_used,
+					     &fs_pool->fully_used, false,
+					     pool_index);
+	if (err)
+		err = mlx5_fs_pool_acquire_from_list(&fs_pool->unused,
+						     &fs_pool->partially_used,
+						     true, pool_index);
+	if (err) {
+		new_bulk = mlx5_fs_pool_alloc_new_bulk(fs_pool);
+		if (!new_bulk) {
+			err = -ENOENT;
+			goto out;
+		}
+		err = mlx5_fs_bulk_acquire_index(new_bulk, pool_index);
+		WARN_ON_ONCE(err);
+		list_add(&new_bulk->pool_list, &fs_pool->partially_used);
+	}
+	fs_pool->available_units--;
+	fs_pool->used_units++;
+
+out:
+	mutex_unlock(&fs_pool->pool_lock);
+	return err;
+}
+
+int mlx5_fs_pool_release_index(struct mlx5_fs_pool *fs_pool,
+			       struct mlx5_fs_pool_index *pool_index)
+{
+	struct mlx5_fs_bulk *bulk = pool_index->fs_bulk;
+	int bulk_free_amount;
+	int err;
+
+	mutex_lock(&fs_pool->pool_lock);
+
+	/* TBD would rather return void if there was no warn here in original code */
+	err = mlx5_fs_bulk_release_index(bulk, pool_index->index);
+	if (err)
+		goto unlock;
+
+	fs_pool->available_units++;
+	fs_pool->used_units--;
+
+	bulk_free_amount = mlx5_fs_bulk_get_free_amount(bulk);
+	if (bulk_free_amount == 1)
+		list_move_tail(&bulk->pool_list, &fs_pool->partially_used);
+	if (bulk_free_amount == bulk->bulk_len) {
+		list_del(&bulk->pool_list);
+		if (fs_pool->available_units > fs_pool->threshold)
+			mlx5_fs_pool_free_bulk(fs_pool, bulk);
+		else
+			list_add(&bulk->pool_list, &fs_pool->unused);
+	}
+
+unlock:
+	mutex_unlock(&fs_pool->pool_lock);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h
new file mode 100644
index 000000000000..f04ec3107498
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef __MLX5_FS_POOL_H__
+#define __MLX5_FS_POOL_H__
+
+#include <linux/mlx5/driver.h>
+
+struct mlx5_fs_bulk {
+	struct list_head pool_list;
+	int bulk_len;
+	unsigned long *bitmask;
+};
+
+struct mlx5_fs_pool_index {
+	struct mlx5_fs_bulk *fs_bulk;
+	int index;
+};
+
+struct mlx5_fs_pool;
+
+struct mlx5_fs_pool_ops {
+	int (*bulk_destroy)(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *bulk);
+	struct mlx5_fs_bulk * (*bulk_create)(struct mlx5_core_dev *dev,
+					     void *pool_ctx);
+	void (*update_threshold)(struct mlx5_fs_pool *pool);
+};
+
+struct mlx5_fs_pool {
+	struct mlx5_core_dev *dev;
+	void *pool_ctx;
+	const struct mlx5_fs_pool_ops *ops;
+	struct mutex pool_lock; /* protects pool lists */
+	struct list_head fully_used;
+	struct list_head partially_used;
+	struct list_head unused;
+	int available_units;
+	int used_units;
+	int threshold;
+};
+
+int mlx5_fs_bulk_init(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk,
+		      int bulk_len);
+void mlx5_fs_bulk_cleanup(struct mlx5_fs_bulk *fs_bulk);
+int mlx5_fs_bulk_get_free_amount(struct mlx5_fs_bulk *bulk);
+
+void mlx5_fs_pool_init(struct mlx5_fs_pool *pool, struct mlx5_core_dev *dev,
+		       const struct mlx5_fs_pool_ops *ops, void *pool_ctx);
+void mlx5_fs_pool_cleanup(struct mlx5_fs_pool *pool);
+int mlx5_fs_pool_acquire_index(struct mlx5_fs_pool *fs_pool,
+			       struct mlx5_fs_pool_index *pool_index);
+int mlx5_fs_pool_release_index(struct mlx5_fs_pool *fs_pool,
+			       struct mlx5_fs_pool_index *pool_index);
+
+#endif /* __MLX5_FS_POOL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 76ad46bf477d..57476487e31f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -281,6 +281,19 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN(dev, shampo)) {
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_SHAMPO, HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+	}
+
+	if (MLX5_CAP_GEN(dev, adv_rdma)) {
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ADV_RDMA,
+					      HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 566710d34a7b..69933addd921 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -246,7 +246,7 @@ static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
-	del_timer_sync(&fw_reset->timer);
+	timer_delete_sync(&fw_reset->timer);
 }
 
 static int mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health)
@@ -278,7 +278,8 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work)
 #define MLX5_RESET_POLL_INTERVAL	(HZ / 10)
 static void poll_sync_reset(struct timer_list *t)
 {
-	struct mlx5_fw_reset *fw_reset = from_timer(fw_reset, t, timer);
+	struct mlx5_fw_reset *fw_reset = timer_container_of(fw_reset, t,
+							    timer);
 	struct mlx5_core_dev *dev = fw_reset->dev;
 	u32 fatal_error;
 
@@ -345,15 +346,12 @@ static void mlx5_fw_live_patch_event(struct work_struct *work)
 }
 
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
-static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev)
+static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev,
+					struct pci_dev *bridge)
 {
-	struct pci_dev *bridge = dev->pdev->bus->self;
 	u16 reg16;
 	int err;
 
-	if (!bridge)
-		return -EOPNOTSUPP;
-
 	err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, &reg16);
 	if (err)
 		return err;
@@ -416,9 +414,15 @@ static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
 static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
 				      u8 reset_method)
 {
+	struct pci_dev *bridge = dev->pdev->bus->self;
 	u16 dev_id;
 	int err;
 
+	if (!bridge) {
+		mlx5_core_warn(dev, "PCI bus bridge is not accessible\n");
+		return false;
+	}
+
 	if (!MLX5_CAP_GEN(dev, fast_teardown)) {
 		mlx5_core_warn(dev, "fast teardown is not supported by firmware\n");
 		return false;
@@ -426,7 +430,7 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
 
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
 	if (reset_method != MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET) {
-		err = mlx5_check_hotplug_interrupt(dev);
+		err = mlx5_check_hotplug_interrupt(dev, bridge);
 		if (err)
 			return false;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index a6329ca2d9bf..cf7a1edd0530 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -96,6 +96,11 @@ static int mlx5_health_get_rfr(u8 rfr_severity)
 	return rfr_severity >> MLX5_RFR_BIT_OFFSET;
 }
 
+static int mlx5_health_get_crr(u8 rfr_severity)
+{
+	return (rfr_severity >> MLX5_CRR_BIT_OFFSET) & 0x01;
+}
+
 static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
@@ -375,6 +380,8 @@ static const char *hsynd_str(u8 synd)
 		return "High temperature";
 	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR:
 		return "ICM fetch PCI data poisoned error";
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_TRUST_LOCKDOWN_ERR:
+		return "Trust lockdown error";
 	default:
 		return "unrecognized error";
 	}
@@ -442,12 +449,15 @@ static void print_health_info(struct mlx5_core_dev *dev)
 	mlx5_log(dev, severity, "time %u\n", ioread32be(&h->time));
 	mlx5_log(dev, severity, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
 	mlx5_log(dev, severity, "rfr %d\n", mlx5_health_get_rfr(rfr_severity));
+	mlx5_log(dev, severity, "crr %d\n", mlx5_health_get_crr(rfr_severity));
 	mlx5_log(dev, severity, "severity %d (%s)\n", severity, mlx5_loglevel_str(severity));
 	mlx5_log(dev, severity, "irisc_index %d\n", ioread8(&h->irisc_index));
 	mlx5_log(dev, severity, "synd 0x%x: %s\n", ioread8(&h->synd),
 		 hsynd_str(ioread8(&h->synd)));
 	mlx5_log(dev, severity, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
 	mlx5_log(dev, severity, "raw fw_ver 0x%08x\n", ioread32be(&h->fw_ver));
+	if (mlx5_health_get_crr(rfr_severity))
+		mlx5_core_warn(dev, "Cold reset is required\n");
 }
 
 static int
@@ -769,7 +779,8 @@ static void mlx5_health_log_ts_update(struct work_struct *work)
 
 static void poll_health(struct timer_list *t)
 {
-	struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer);
+	struct mlx5_core_dev *dev = timer_container_of(dev, t,
+						       priv.health.timer);
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
 	u32 fatal_error;
@@ -799,14 +810,17 @@ static void poll_health(struct timer_list *t)
 	health->prev = count;
 	if (health->miss_counter == MAX_MISSES) {
 		mlx5_core_err(dev, "device's health compromised - reached miss count\n");
+		health->synd = ioread8(&h->synd);
 		print_health_info(dev);
 		queue_work(health->wq, &health->report_work);
 	}
 
 	prev_synd = health->synd;
 	health->synd = ioread8(&h->synd);
-	if (health->synd && health->synd != prev_synd)
+	if (health->synd && health->synd != prev_synd) {
+		print_health_info(dev);
 		queue_work(health->wq, &health->report_work);
+	}
 
 out:
 	mod_timer(&health->timer, get_next_poll_jiffies(dev));
@@ -834,7 +848,7 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
 	if (disable_health)
 		set_bit(MLX5_DROP_HEALTH_WORK, &health->flags);
 
-	del_timer_sync(&health->timer);
+	timer_delete_sync(&health->timer);
 }
 
 void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
index 353f81dccd1c..4ba2636d7fb6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
@@ -416,3 +416,8 @@ void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev)
 	mlx5_hwmon_free(hwmon);
 	mdev->hwmon = NULL;
 }
+
+const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel)
+{
+	return hwmon->temp_channel_desc[channel].sensor_name;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
index 999654a9b9da..f38271c22c10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
@@ -10,6 +10,7 @@
 
 int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev);
 void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev);
+const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel);
 
 #else
 static inline int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 0979d672d47f..79ae3a51a4b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -32,6 +32,7 @@
 
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/fs.h>
+#include <net/netdev_lock.h>
 #include "en.h"
 #include "en/params.h"
 #include "ipoib.h"
@@ -102,6 +103,8 @@ int mlx5i_init(struct mlx5_core_dev *mdev, struct net_device *netdev)
 
 	netdev->netdev_ops = &mlx5i_netdev_ops;
 	netdev->ethtool_ops = &mlx5i_ethtool_ops;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index 1477db7f5307..2691d88cdee1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -175,7 +175,7 @@ unlock:
 
 void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *irq)
 {
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
+	struct mlx5_irq_pool *pool = mlx5_irq_get_pool(irq);
 	int cpu;
 
 	cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
index f4b777d4e108..62b6faa4276a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
@@ -105,20 +105,20 @@ static int mapping_show(struct seq_file *file, void *priv)
 	struct mlx5_lag *ldev;
 	bool hash = false;
 	bool lag_active;
+	int i, idx = 0;
 	int num_ports;
-	int i;
 
 	ldev = mlx5_lag_dev(dev);
 	mutex_lock(&ldev->lock);
 	lag_active = __mlx5_lag_is_active(ldev);
 	if (lag_active) {
 		if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &ldev->mode_flags)) {
-			mlx5_infer_tx_enabled(&ldev->tracker, ldev->ports, ports,
+			mlx5_infer_tx_enabled(&ldev->tracker, ldev, ports,
 					      &num_ports);
 			hash = true;
 		} else {
-			for (i = 0; i < ldev->ports; i++)
-				ports[i] = ldev->v2p_map[i];
+			mlx5_ldev_for_each(i, 0, ldev)
+				ports[idx++] = ldev->v2p_map[i];
 			num_ports = ldev->ports;
 		}
 	}
@@ -144,11 +144,8 @@ static int members_show(struct seq_file *file, void *priv)
 
 	ldev = mlx5_lag_dev(dev);
 	mutex_lock(&ldev->lock);
-	for (i = 0; i < ldev->ports; i++) {
-		if (!ldev->pf[i].dev)
-			continue;
+	mlx5_ldev_for_each(i, 0, ldev)
 		seq_printf(file, "%s\n", dev_name(ldev->pf[i].dev->device));
-	}
 	mutex_unlock(&ldev->lock);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 7f68468c2e75..d058cbb4a00c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -43,10 +43,6 @@
 #include "mp.h"
 #include "mpesw.h"
 
-enum {
-	MLX5_LAG_EGRESS_PORT_1 = 1,
-	MLX5_LAG_EGRESS_PORT_2,
-};
 
 /* General purpose, use for short periods of time.
  * Beware of lock dependencies (preferably, no locks should be acquired
@@ -72,7 +68,7 @@ static u8 lag_active_port_bits(struct mlx5_lag *ldev)
 	int num_enabled;
 	int idx;
 
-	mlx5_infer_tx_enabled(&ldev->tracker, ldev->ports, enabled_ports,
+	mlx5_infer_tx_enabled(&ldev->tracker, ldev, enabled_ports,
 			      &num_enabled);
 	for (idx = 0; idx < num_enabled; idx++)
 		active_port |= BIT_MASK(enabled_ports[idx]);
@@ -80,23 +76,30 @@ static u8 lag_active_port_bits(struct mlx5_lag *ldev)
 	return active_port;
 }
 
-static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 *ports, int mode,
-			       unsigned long flags)
+static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev,
+			       int mode, unsigned long flags)
 {
 	bool fdb_sel_mode = test_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE,
 				     &flags);
 	int port_sel_mode = get_port_sel_mode(mode, flags);
 	u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {};
+	u8 *ports = ldev->v2p_map;
+	int idx0, idx1;
 	void *lag_ctx;
 
 	lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx);
 	MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG);
 	MLX5_SET(lagc, lag_ctx, fdb_selection_mode, fdb_sel_mode);
+	idx0 = mlx5_lag_get_dev_index_by_seq(ldev, 0);
+	idx1 = mlx5_lag_get_dev_index_by_seq(ldev, 1);
+
+	if (idx0 < 0 || idx1 < 0)
+		return -EINVAL;
 
 	switch (port_sel_mode) {
 	case MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY:
-		MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[0]);
-		MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[1]);
+		MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[idx0]);
+		MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[idx1]);
 		break;
 	case MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT:
 		if (!MLX5_CAP_PORT_SELECTION(dev, port_select_flow_table_bypass))
@@ -113,17 +116,23 @@ static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 *ports, int mode,
 	return mlx5_cmd_exec_in(dev, create_lag, in);
 }
 
-static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, u8 num_ports,
+static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev,
 			       u8 *ports)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_lag_in)] = {};
 	void *lag_ctx = MLX5_ADDR_OF(modify_lag_in, in, ctx);
+	int idx0, idx1;
+
+	idx0 = mlx5_lag_get_dev_index_by_seq(ldev, 0);
+	idx1 = mlx5_lag_get_dev_index_by_seq(ldev, 1);
+	if (idx0 < 0 || idx1 < 0)
+		return -EINVAL;
 
 	MLX5_SET(modify_lag_in, in, opcode, MLX5_CMD_OP_MODIFY_LAG);
 	MLX5_SET(modify_lag_in, in, field_select, 0x1);
 
-	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[0]);
-	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[1]);
+	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[idx0]);
+	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[idx1]);
 
 	return mlx5_cmd_exec_in(dev, modify_lag, in);
 }
@@ -148,33 +157,31 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag);
 
-static void mlx5_infer_tx_disabled(struct lag_tracker *tracker, u8 num_ports,
+static void mlx5_infer_tx_disabled(struct lag_tracker *tracker, struct mlx5_lag *ldev,
 				   u8 *ports, int *num_disabled)
 {
 	int i;
 
 	*num_disabled = 0;
-	for (i = 0; i < num_ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev)
 		if (!tracker->netdev_state[i].tx_enabled ||
 		    !tracker->netdev_state[i].link_up)
 			ports[(*num_disabled)++] = i;
-	}
 }
 
-void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
+void mlx5_infer_tx_enabled(struct lag_tracker *tracker, struct mlx5_lag *ldev,
 			   u8 *ports, int *num_enabled)
 {
 	int i;
 
 	*num_enabled = 0;
-	for (i = 0; i < num_ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev)
 		if (tracker->netdev_state[i].tx_enabled &&
 		    tracker->netdev_state[i].link_up)
 			ports[(*num_enabled)++] = i;
-	}
 
 	if (*num_enabled == 0)
-		mlx5_infer_tx_disabled(tracker, num_ports, ports, num_enabled);
+		mlx5_infer_tx_disabled(tracker, ldev, ports, num_enabled);
 }
 
 static void mlx5_lag_print_mapping(struct mlx5_core_dev *dev,
@@ -192,7 +199,7 @@ static void mlx5_lag_print_mapping(struct mlx5_core_dev *dev,
 	int j;
 
 	if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) {
-		mlx5_infer_tx_enabled(tracker, ldev->ports, enabled_ports,
+		mlx5_infer_tx_enabled(tracker, ldev, enabled_ports,
 				      &num_enabled);
 		for (i = 0; i < num_enabled; i++) {
 			err = scnprintf(buf + written, 4, "%d, ", enabled_ports[i] + 1);
@@ -203,7 +210,7 @@ static void mlx5_lag_print_mapping(struct mlx5_core_dev *dev,
 		buf[written - 2] = 0;
 		mlx5_core_info(dev, "lag map active ports: %s\n", buf);
 	} else {
-		for (i = 0; i < ldev->ports; i++) {
+		mlx5_ldev_for_each(i, 0, ldev) {
 			for (j  = 0; j < ldev->buckets; j++) {
 				idx = i * ldev->buckets + j;
 				err = scnprintf(buf + written, 10,
@@ -286,13 +293,55 @@ int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 {
 	int i;
 
-	for (i = 0; i < ldev->ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev)
 		if (ldev->pf[i].netdev == ndev)
 			return i;
 
 	return -ENOENT;
 }
 
+int mlx5_lag_get_dev_index_by_seq(struct mlx5_lag *ldev, int seq)
+{
+	int i, num = 0;
+
+	if (!ldev)
+		return -ENOENT;
+
+	mlx5_ldev_for_each(i, 0, ldev) {
+		if (num == seq)
+			return i;
+		num++;
+	}
+	return -ENOENT;
+}
+
+int mlx5_lag_num_devs(struct mlx5_lag *ldev)
+{
+	int i, num = 0;
+
+	if (!ldev)
+		return 0;
+
+	mlx5_ldev_for_each(i, 0, ldev) {
+		(void)i;
+		num++;
+	}
+	return num;
+}
+
+int mlx5_lag_num_netdevs(struct mlx5_lag *ldev)
+{
+	int i, num = 0;
+
+	if (!ldev)
+		return 0;
+
+	mlx5_ldev_for_each(i, 0, ldev)
+		if (ldev->pf[i].netdev)
+			num++;
+	return num;
+}
+
 static bool __mlx5_lag_is_roce(struct mlx5_lag *ldev)
 {
 	return ldev->mode == MLX5_LAG_MODE_ROCE;
@@ -310,7 +359,7 @@ static bool __mlx5_lag_is_sriov(struct mlx5_lag *ldev)
  * with mapping that points to active ports.
  */
 static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
-					   u8 num_ports,
+					   struct mlx5_lag *ldev,
 					   u8 buckets,
 					   u8 *ports)
 {
@@ -323,7 +372,7 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 	int i;
 	int j;
 
-	for (i = 0; i < num_ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		if (tracker->netdev_state[i].tx_enabled &&
 		    tracker->netdev_state[i].link_up)
 			enabled[enabled_ports_num++] = i;
@@ -334,15 +383,16 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 	/* Use native mapping by default where each port's buckets
 	 * point the native port: 1 1 1 .. 1 2 2 2 ... 2 3 3 3 ... 3 etc
 	 */
-	for (i = 0; i < num_ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev) {
 		for (j = 0; j < buckets; j++) {
 			idx = i * buckets + j;
-			ports[idx] = MLX5_LAG_EGRESS_PORT_1 + i;
+			ports[idx] = i + 1;
 		}
+	}
 
 	/* If all ports are disabled/enabled keep native mapping */
-	if (enabled_ports_num == num_ports ||
-	    disabled_ports_num == num_ports)
+	if (enabled_ports_num == ldev->ports ||
+	    disabled_ports_num == ldev->ports)
 		return;
 
 	/* Go over the disabled ports and for each assign a random active port */
@@ -358,7 +408,7 @@ static bool mlx5_lag_has_drop_rule(struct mlx5_lag *ldev)
 {
 	int i;
 
-	for (i = 0; i < ldev->ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev)
 		if (ldev->pf[i].has_drop)
 			return true;
 	return false;
@@ -368,7 +418,7 @@ static void mlx5_lag_drop_rule_cleanup(struct mlx5_lag *ldev)
 {
 	int i;
 
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		if (!ldev->pf[i].has_drop)
 			continue;
 
@@ -396,7 +446,7 @@ static void mlx5_lag_drop_rule_setup(struct mlx5_lag *ldev,
 	if (!ldev->tracker.has_inactive)
 		return;
 
-	mlx5_infer_tx_disabled(tracker, ldev->ports, disabled_ports, &num_disabled);
+	mlx5_infer_tx_disabled(tracker, ldev, disabled_ports, &num_disabled);
 
 	for (i = 0; i < num_disabled; i++) {
 		disabled_index = disabled_ports[i];
@@ -428,10 +478,15 @@ static int mlx5_cmd_modify_active_port(struct mlx5_core_dev *dev, u8 ports)
 
 static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	struct mlx5_core_dev *dev0;
 	u8 active_ports;
 	int ret;
 
+	if (idx < 0)
+		return -EINVAL;
+
+	dev0 = ldev->pf[idx].dev;
 	if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &ldev->mode_flags)) {
 		ret = mlx5_lag_port_sel_modify(ldev, ports);
 		if (ret ||
@@ -442,7 +497,7 @@ static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports)
 
 		return mlx5_cmd_modify_active_port(dev0, active_ports);
 	}
-	return mlx5_cmd_modify_lag(dev0, ldev->ports, ports);
+	return mlx5_cmd_modify_lag(dev0, ldev, ports);
 }
 
 static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev *dev)
@@ -450,7 +505,7 @@ static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev
 	struct net_device *ndev = NULL;
 	struct mlx5_lag *ldev;
 	unsigned long flags;
-	int i;
+	int i, last_idx;
 
 	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
@@ -458,14 +513,17 @@ static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev
 	if (!ldev)
 		goto unlock;
 
-	for (i = 0; i < ldev->ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev)
 		if (ldev->tracker.netdev_state[i].tx_enabled)
 			ndev = ldev->pf[i].netdev;
-	if (!ndev)
-		ndev = ldev->pf[ldev->ports - 1].netdev;
+	if (!ndev) {
+		last_idx = mlx5_lag_get_dev_index_by_seq(ldev, ldev->ports - 1);
+		if (last_idx < 0)
+			goto unlock;
+		ndev = ldev->pf[last_idx].netdev;
+	}
 
-	if (ndev)
-		dev_hold(ndev);
+	dev_hold(ndev);
 
 unlock:
 	spin_unlock_irqrestore(&lag_lock, flags);
@@ -476,16 +534,21 @@ unlock:
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker)
 {
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	u8 ports[MLX5_MAX_PORTS * MLX5_LAG_MAX_HASH_BUCKETS] = {};
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	struct mlx5_core_dev *dev0;
 	int idx;
 	int err;
 	int i;
 	int j;
 
-	mlx5_infer_tx_affinity_mapping(tracker, ldev->ports, ldev->buckets, ports);
+	if (first_idx < 0)
+		return;
 
-	for (i = 0; i < ldev->ports; i++) {
+	dev0 = ldev->pf[first_idx].dev;
+	mlx5_infer_tx_affinity_mapping(tracker, ldev, ldev->buckets, ports);
+
+	mlx5_ldev_for_each(i, 0, ldev) {
 		for (j = 0; j < ldev->buckets; j++) {
 			idx = i * ldev->buckets + j;
 			if (ports[idx] == ldev->v2p_map[idx])
@@ -520,10 +583,21 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
 	}
 }
 
-static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
-					   unsigned long *flags)
+static int mlx5_lag_set_port_sel_mode(struct mlx5_lag *ldev,
+				      enum mlx5_lag_mode mode,
+				      unsigned long *flags)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	struct mlx5_core_dev *dev0;
+
+	if (first_idx < 0)
+		return -EINVAL;
+
+	if (mode == MLX5_LAG_MODE_MPESW ||
+	    mode == MLX5_LAG_MODE_MULTIPATH)
+		return 0;
+
+	dev0 = ldev->pf[first_idx].dev;
 
 	if (!MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table)) {
 		if (ldev->ports > 2)
@@ -539,30 +613,10 @@ static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
 	return 0;
 }
 
-static void mlx5_lag_set_port_sel_mode_offloads(struct mlx5_lag *ldev,
-						struct lag_tracker *tracker,
-						enum mlx5_lag_mode mode,
-						unsigned long *flags)
-{
-	struct lag_func *dev0 = &ldev->pf[MLX5_LAG_P1];
-
-	if (mode == MLX5_LAG_MODE_MPESW)
-		return;
-
-	if (MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) &&
-	    tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH) {
-		if (ldev->ports > 2)
-			ldev->buckets = MLX5_LAG_MAX_HASH_BUCKETS;
-		set_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, flags);
-	}
-}
-
 static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 			      struct lag_tracker *tracker, bool shared_fdb,
 			      unsigned long *flags)
 {
-	bool roce_lag = mode == MLX5_LAG_MODE_ROCE;
-
 	*flags = 0;
 	if (shared_fdb) {
 		set_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, flags);
@@ -572,11 +626,7 @@ static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 	if (mode == MLX5_LAG_MODE_MPESW)
 		set_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, flags);
 
-	if (roce_lag)
-		return mlx5_lag_set_port_sel_mode_roce(ldev, flags);
-
-	mlx5_lag_set_port_sel_mode_offloads(ldev, tracker, mode, flags);
-	return 0;
+	return mlx5_lag_set_port_sel_mode(ldev, mode, flags);
 }
 
 char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags)
@@ -593,12 +643,18 @@ char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags)
 
 static int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
-	struct mlx5_eswitch *master_esw = dev0->priv.eswitch;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	struct mlx5_eswitch *master_esw;
+	struct mlx5_core_dev *dev0;
+	int i, j;
 	int err;
-	int i;
 
-	for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) {
+	if (first_idx < 0)
+		return -EINVAL;
+
+	dev0 = ldev->pf[first_idx].dev;
+	master_esw = dev0->priv.eswitch;
+	mlx5_ldev_for_each(i, first_idx + 1, ldev) {
 		struct mlx5_eswitch *slave_esw = ldev->pf[i].dev->priv.eswitch;
 
 		err = mlx5_eswitch_offloads_single_fdb_add_one(master_esw,
@@ -608,9 +664,9 @@ static int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev)
 	}
 	return 0;
 err:
-	for (; i > MLX5_LAG_P1; i--)
+	mlx5_ldev_for_each_reverse(j, i, first_idx + 1, ldev)
 		mlx5_eswitch_offloads_single_fdb_del_one(master_esw,
-							 ldev->pf[i].dev->priv.eswitch);
+							 ldev->pf[j].dev->priv.eswitch);
 	return err;
 }
 
@@ -620,16 +676,21 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 			   unsigned long flags)
 {
 	bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags);
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {};
+	struct mlx5_core_dev *dev0;
 	int err;
 
+	if (first_idx < 0)
+		return -EINVAL;
+
+	dev0 = ldev->pf[first_idx].dev;
 	if (tracker)
 		mlx5_lag_print_mapping(dev0, ldev, tracker, flags);
 	mlx5_core_info(dev0, "shared_fdb:%d mode:%s\n",
 		       shared_fdb, mlx5_get_str_port_sel_mode(mode, flags));
 
-	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map, mode, flags);
+	err = mlx5_cmd_create_lag(dev0, ldev, mode, flags);
 	if (err) {
 		mlx5_core_err(dev0,
 			      "Failed to create LAG (%d)\n",
@@ -661,17 +722,22 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 		      enum mlx5_lag_mode mode,
 		      bool shared_fdb)
 {
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	bool roce_lag = mode == MLX5_LAG_MODE_ROCE;
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	struct mlx5_core_dev *dev0;
 	unsigned long flags = 0;
 	int err;
 
+	if (first_idx < 0)
+		return -EINVAL;
+
+	dev0 = ldev->pf[first_idx].dev;
 	err = mlx5_lag_set_flags(ldev, mode, tracker, shared_fdb, &flags);
 	if (err)
 		return err;
 
 	if (mode != MLX5_LAG_MODE_MPESW) {
-		mlx5_infer_tx_affinity_mapping(tracker, ldev->ports, ldev->buckets, ldev->v2p_map);
+		mlx5_infer_tx_affinity_mapping(tracker, ldev, ldev->buckets, ldev->v2p_map);
 		if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) {
 			err = mlx5_lag_port_sel_create(ldev, tracker->hash_type,
 						       ldev->v2p_map);
@@ -709,20 +775,26 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 
 int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
-	struct mlx5_eswitch *master_esw = dev0->priv.eswitch;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {};
 	bool roce_lag = __mlx5_lag_is_roce(ldev);
 	unsigned long flags = ldev->mode_flags;
+	struct mlx5_eswitch *master_esw;
+	struct mlx5_core_dev *dev0;
 	int err;
 	int i;
 
+	if (first_idx < 0)
+		return -EINVAL;
+
+	dev0 = ldev->pf[first_idx].dev;
+	master_esw = dev0->priv.eswitch;
 	ldev->mode = MLX5_LAG_MODE_NONE;
 	ldev->mode_flags = 0;
 	mlx5_lag_mp_reset(ldev);
 
 	if (test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags)) {
-		for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++)
+		mlx5_ldev_for_each(i, first_idx + 1, ldev)
 			mlx5_eswitch_offloads_single_fdb_del_one(master_esw,
 								 ldev->pf[i].dev->priv.eswitch);
 		clear_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags);
@@ -754,6 +826,7 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 
 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 {
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 #ifdef CONFIG_MLX5_ESWITCH
 	struct mlx5_core_dev *dev;
 	u8 mode;
@@ -761,30 +834,29 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 	bool roce_support;
 	int i;
 
-	for (i = 0; i < ldev->ports; i++)
-		if (!ldev->pf[i].dev)
-			return false;
+	if (first_idx < 0 || mlx5_lag_num_devs(ldev) != ldev->ports)
+		return false;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		dev = ldev->pf[i].dev;
 		if (mlx5_eswitch_num_vfs(dev->priv.eswitch) && !is_mdev_switchdev_mode(dev))
 			return false;
 	}
 
-	dev = ldev->pf[MLX5_LAG_P1].dev;
+	dev = ldev->pf[first_idx].dev;
 	mode = mlx5_eswitch_mode(dev);
-	for (i = 0; i < ldev->ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev)
 		if (mlx5_eswitch_mode(ldev->pf[i].dev) != mode)
 			return false;
 
 #else
-	for (i = 0; i < ldev->ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev)
 		if (mlx5_sriov_is_enabled(ldev->pf[i].dev))
 			return false;
 #endif
-	roce_support = mlx5_get_roce_state(ldev->pf[MLX5_LAG_P1].dev);
-	for (i = 1; i < ldev->ports; i++)
+	roce_support = mlx5_get_roce_state(ldev->pf[first_idx].dev);
+	mlx5_ldev_for_each(i, first_idx + 1, ldev)
 		if (mlx5_get_roce_state(ldev->pf[i].dev) != roce_support)
 			return false;
 
@@ -795,10 +867,7 @@ void mlx5_lag_add_devices(struct mlx5_lag *ldev)
 {
 	int i;
 
-	for (i = 0; i < ldev->ports; i++) {
-		if (!ldev->pf[i].dev)
-			continue;
-
+	mlx5_ldev_for_each(i, 0, ldev) {
 		if (ldev->pf[i].dev->priv.flags &
 		    MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
 			continue;
@@ -812,10 +881,7 @@ void mlx5_lag_remove_devices(struct mlx5_lag *ldev)
 {
 	int i;
 
-	for (i = 0; i < ldev->ports; i++) {
-		if (!ldev->pf[i].dev)
-			continue;
-
+	mlx5_ldev_for_each(i, 0, ldev) {
 		if (ldev->pf[i].dev->priv.flags &
 		    MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
 			continue;
@@ -828,11 +894,16 @@ void mlx5_lag_remove_devices(struct mlx5_lag *ldev)
 void mlx5_disable_lag(struct mlx5_lag *ldev)
 {
 	bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	struct mlx5_core_dev *dev0;
 	bool roce_lag;
 	int err;
 	int i;
 
+	if (idx < 0)
+		return;
+
+	dev0 = ldev->pf[idx].dev;
 	roce_lag = __mlx5_lag_is_roce(ldev);
 
 	if (shared_fdb) {
@@ -842,7 +913,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
 			dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 			mlx5_rescan_drivers_locked(dev0);
 		}
-		for (i = 1; i < ldev->ports; i++)
+		mlx5_ldev_for_each(i, idx + 1, ldev)
 			mlx5_nic_vport_disable_roce(ldev->pf[i].dev);
 	}
 
@@ -854,17 +925,21 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
 		mlx5_lag_add_devices(ldev);
 
 	if (shared_fdb)
-		for (i = 0; i < ldev->ports; i++)
+		mlx5_ldev_for_each(i, 0, ldev)
 			if (!(ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV))
 				mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 }
 
-static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
 {
+	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_core_dev *dev;
 	int i;
 
-	for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) {
+	if (idx < 0)
+		return false;
+
+	mlx5_ldev_for_each(i, idx + 1, ldev) {
 		dev = ldev->pf[i].dev;
 		if (is_mdev_switchdev_mode(dev) &&
 		    mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) &&
@@ -876,7 +951,7 @@ static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
 		return false;
 	}
 
-	dev = ldev->pf[MLX5_LAG_P1].dev;
+	dev = ldev->pf[idx].dev;
 	if (is_mdev_switchdev_mode(dev) &&
 	    mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) &&
 	    mlx5_esw_offloads_devcom_is_ready(dev->priv.eswitch) &&
@@ -892,11 +967,11 @@ static bool mlx5_lag_is_roce_lag(struct mlx5_lag *ldev)
 	bool roce_lag = true;
 	int i;
 
-	for (i = 0; i < ldev->ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev)
 		roce_lag = roce_lag && !mlx5_sriov_is_enabled(ldev->pf[i].dev);
 
 #ifdef CONFIG_MLX5_ESWITCH
-	for (i = 0; i < ldev->ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev)
 		roce_lag = roce_lag && is_mdev_legacy_mode(ldev->pf[i].dev);
 #endif
 
@@ -917,13 +992,18 @@ static bool mlx5_lag_should_disable_lag(struct mlx5_lag *ldev, bool do_bond)
 
 static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct lag_tracker tracker = { };
+	struct mlx5_core_dev *dev0;
 	struct net_device *ndev;
 	bool do_bond, roce_lag;
 	int err;
 	int i;
 
+	if (idx < 0)
+		return;
+
+	dev0 = ldev->pf[idx].dev;
 	if (!mlx5_lag_is_ready(ldev)) {
 		do_bond = false;
 	} else {
@@ -937,7 +1017,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	}
 
 	if (do_bond && !__mlx5_lag_is_active(ldev)) {
-		bool shared_fdb = mlx5_shared_fdb_supported(ldev);
+		bool shared_fdb = mlx5_lag_shared_fdb_supported(ldev);
 
 		roce_lag = mlx5_lag_is_roce_lag(ldev);
 
@@ -951,12 +1031,16 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 		if (err) {
 			if (shared_fdb || roce_lag)
 				mlx5_lag_add_devices(ldev);
+			if (shared_fdb) {
+				mlx5_ldev_for_each(i, 0, ldev)
+					mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
+			}
 
 			return;
 		} else if (roce_lag) {
 			dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 			mlx5_rescan_drivers_locked(dev0);
-			for (i = 1; i < ldev->ports; i++) {
+			mlx5_ldev_for_each(i, idx + 1, ldev) {
 				if (mlx5_get_roce_state(ldev->pf[i].dev))
 					mlx5_nic_vport_enable_roce(ldev->pf[i].dev);
 			}
@@ -966,7 +1050,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 			dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 			mlx5_rescan_drivers_locked(dev0);
 
-			for (i = 0; i < ldev->ports; i++) {
+			mlx5_ldev_for_each(i, 0, ldev) {
 				err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 				if (err)
 					break;
@@ -977,7 +1061,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 				mlx5_rescan_drivers_locked(dev0);
 				mlx5_deactivate_lag(ldev);
 				mlx5_lag_add_devices(ldev);
-				for (i = 0; i < ldev->ports; i++)
+				mlx5_ldev_for_each(i, 0, ldev)
 					mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 				mlx5_core_err(dev0, "Failed to enable lag\n");
 				return;
@@ -1010,12 +1094,9 @@ struct mlx5_devcom_comp_dev *mlx5_lag_get_devcom_comp(struct mlx5_lag *ldev)
 	int i;
 
 	mutex_lock(&ldev->lock);
-	for (i = 0; i < ldev->ports; i++) {
-		if (ldev->pf[i].dev) {
-			devcom = ldev->pf[i].dev->priv.hca_devcom_comp;
-			break;
-		}
-	}
+	i = mlx5_get_next_ldev_func(ldev, 0);
+	if (i < MLX5_MAX_PORTS)
+		devcom = ldev->pf[i].dev->priv.hca_devcom_comp;
 	mutex_unlock(&ldev->lock);
 	return devcom;
 }
@@ -1068,7 +1149,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	u8 bond_status = 0;
 	int num_slaves = 0;
 	int changed = 0;
-	int idx;
+	int i, idx = -1;
 
 	if (!netif_is_lag_master(upper))
 		return 0;
@@ -1083,8 +1164,13 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	 */
 	rcu_read_lock();
 	for_each_netdev_in_bond_rcu(upper, ndev_tmp) {
-		idx = mlx5_lag_dev_get_netdev_idx(ldev, ndev_tmp);
-		if (idx >= 0) {
+		mlx5_ldev_for_each(i, 0, ldev) {
+			if (ldev->pf[i].netdev == ndev_tmp) {
+				idx++;
+				break;
+			}
+		}
+		if (i < MLX5_MAX_PORTS) {
 			slave = bond_slave_get_rcu(ndev_tmp);
 			if (slave)
 				has_inactive |= bond_is_slave_inactive(slave);
@@ -1234,15 +1320,12 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 }
 
 static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev,
-				 struct mlx5_core_dev *dev,
-				 struct net_device *netdev)
+				struct mlx5_core_dev *dev,
+				struct net_device *netdev)
 {
 	unsigned int fn = mlx5_get_dev_index(dev);
 	unsigned long flags;
 
-	if (fn >= ldev->ports)
-		return;
-
 	spin_lock_irqsave(&lag_lock, flags);
 	ldev->pf[fn].netdev = netdev;
 	ldev->tracker.netdev_state[fn].link_up = 0;
@@ -1257,7 +1340,7 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev,
 	int i;
 
 	spin_lock_irqsave(&lag_lock, flags);
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		if (ldev->pf[i].netdev == netdev) {
 			ldev->pf[i].netdev = NULL;
 			break;
@@ -1267,13 +1350,10 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev,
 }
 
 static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev,
-			       struct mlx5_core_dev *dev)
+			      struct mlx5_core_dev *dev)
 {
 	unsigned int fn = mlx5_get_dev_index(dev);
 
-	if (fn >= ldev->ports)
-		return;
-
 	ldev->pf[fn].dev = dev;
 	dev->priv.lag = ldev;
 }
@@ -1281,16 +1361,13 @@ static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev,
 static void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev,
 				  struct mlx5_core_dev *dev)
 {
-	int i;
+	int fn;
 
-	for (i = 0; i < ldev->ports; i++)
-		if (ldev->pf[i].dev == dev)
-			break;
-
-	if (i == ldev->ports)
+	fn = mlx5_get_dev_index(dev);
+	if (ldev->pf[fn].dev != dev)
 		return;
 
-	ldev->pf[i].dev = NULL;
+	ldev->pf[fn].dev = NULL;
 	dev->priv.lag = NULL;
 }
 
@@ -1398,7 +1475,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
 			 struct net_device *netdev)
 {
 	struct mlx5_lag *ldev;
-	int i;
+	int num = 0;
 
 	ldev = mlx5_lag_dev(dev);
 	if (!ldev)
@@ -1406,17 +1483,33 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
 
 	mutex_lock(&ldev->lock);
 	mlx5_ldev_add_netdev(ldev, dev, netdev);
-
-	for (i = 0; i < ldev->ports; i++)
-		if (!ldev->pf[i].netdev)
-			break;
-
-	if (i >= ldev->ports)
+	num = mlx5_lag_num_netdevs(ldev);
+	if (num >= ldev->ports)
 		set_bit(MLX5_LAG_FLAG_NDEVS_READY, &ldev->state_flags);
 	mutex_unlock(&ldev->lock);
 	mlx5_queue_bond_work(ldev, 0);
 }
 
+int mlx5_get_pre_ldev_func(struct mlx5_lag *ldev, int start_idx, int end_idx)
+{
+	int i;
+
+	for (i = start_idx; i >= end_idx; i--)
+		if (ldev->pf[i].dev)
+			return i;
+	return -1;
+}
+
+int mlx5_get_next_ldev_func(struct mlx5_lag *ldev, int start_idx)
+{
+	int i;
+
+	for (i = start_idx; i < MLX5_MAX_PORTS; i++)
+		if (ldev->pf[i].dev)
+			return i;
+	return MLX5_MAX_PORTS;
+}
+
 bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
@@ -1467,12 +1560,13 @@ bool mlx5_lag_is_master(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
 	unsigned long flags;
-	bool res;
+	bool res = false;
+	int idx;
 
 	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
-	res = ldev && __mlx5_lag_is_active(ldev) &&
-		dev == ldev->pf[MLX5_LAG_P1].dev;
+	idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	res = ldev && __mlx5_lag_is_active(ldev) && idx >= 0 && dev == ldev->pf[idx].dev;
 	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
@@ -1555,7 +1649,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
 		goto unlock;
 
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		if (ldev->pf[i].netdev == slave) {
 			port = i;
 			break;
@@ -1594,13 +1688,13 @@ struct mlx5_core_dev *mlx5_lag_get_next_peer_mdev(struct mlx5_core_dev *dev, int
 	if (!ldev)
 		goto unlock;
 
-	if (*i == ldev->ports)
+	if (*i == MLX5_MAX_PORTS)
 		goto unlock;
-	for (idx = *i; idx < ldev->ports; idx++)
+	mlx5_ldev_for_each(idx, *i, ldev)
 		if (ldev->pf[idx].dev != dev)
 			break;
 
-	if (idx == ldev->ports) {
+	if (idx == MLX5_MAX_PORTS) {
 		*i = idx;
 		goto unlock;
 	}
@@ -1621,10 +1715,10 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 {
 	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
 	struct mlx5_core_dev **mdev;
+	int ret = 0, i, j, idx = 0;
 	struct mlx5_lag *ldev;
 	unsigned long flags;
 	int num_ports;
-	int ret, i, j;
 	void *out;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
@@ -1643,8 +1737,8 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	ldev = mlx5_lag_dev(dev);
 	if (ldev && __mlx5_lag_is_active(ldev)) {
 		num_ports = ldev->ports;
-		for (i = 0; i < ldev->ports; i++)
-			mdev[i] = ldev->pf[i].dev;
+		mlx5_ldev_for_each(i, 0, ldev)
+			mdev[idx++] = ldev->pf[i].dev;
 	} else {
 		num_ports = 1;
 		mdev[MLX5_LAG_P1] = dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 50fcb1eee574..c2f256bb2bc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -92,6 +92,7 @@ mlx5_lag_is_ready(struct mlx5_lag *ldev)
 	return test_bit(MLX5_LAG_FLAG_NDEVS_READY, &ldev->state_flags);
 }
 
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev);
 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev);
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker);
@@ -103,7 +104,7 @@ int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 				struct net_device *ndev);
 
 char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags);
-void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
+void mlx5_infer_tx_enabled(struct lag_tracker *tracker, struct mlx5_lag *ldev,
 			   u8 *ports, int *num_enabled);
 
 void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev);
@@ -119,9 +120,24 @@ static inline bool mlx5_lag_is_supported(struct mlx5_core_dev *dev)
 	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(dev, lag_master) ||
 	    MLX5_CAP_GEN(dev, num_lag_ports) < 2 ||
+	    mlx5_get_dev_index(dev) >= MLX5_MAX_PORTS ||
 	    MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS)
 		return false;
 	return true;
 }
 
+#define mlx5_ldev_for_each(i, start_index, ldev) \
+	for (int tmp = start_index; tmp = mlx5_get_next_ldev_func(ldev, tmp), \
+	     i = tmp, tmp < MLX5_MAX_PORTS; tmp++)
+
+#define mlx5_ldev_for_each_reverse(i, start_index, end_index, ldev)      \
+	for (int tmp = start_index, tmp1 = end_index; \
+	     tmp = mlx5_get_pre_ldev_func(ldev, tmp, tmp1), \
+	     i = tmp, tmp >= tmp1; tmp--)
+
+int mlx5_get_pre_ldev_func(struct mlx5_lag *ldev, int start_idx, int end_idx);
+int mlx5_get_next_ldev_func(struct mlx5_lag *ldev, int start_idx);
+int mlx5_lag_get_dev_index_by_seq(struct mlx5_lag *ldev, int seq);
+int mlx5_lag_num_devs(struct mlx5_lag *ldev);
+int mlx5_lag_num_netdevs(struct mlx5_lag *ldev);
 #endif /* __MLX5_LAG_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c
index b1aa494c76ba..aee17fcf3b36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c
@@ -17,7 +17,10 @@ static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
 #define MLX5_LAG_MULTIPATH_OFFLOADS_SUPPORTED_PORTS 2
 static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev)
 {
-	if (!mlx5_lag_is_ready(ldev))
+	int idx0 = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	int idx1 = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P2);
+
+	if (idx0 < 0 || idx1 < 0 || !mlx5_lag_is_ready(ldev))
 		return false;
 
 	if (__mlx5_lag_is_active(ldev) && !__mlx5_lag_is_multipath(ldev))
@@ -26,8 +29,8 @@ static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev)
 	if (ldev->ports > MLX5_LAG_MULTIPATH_OFFLOADS_SUPPORTED_PORTS)
 		return false;
 
-	return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev,
-					 ldev->pf[MLX5_LAG_P2].dev);
+	return mlx5_esw_multipath_prereq(ldev->pf[idx0].dev,
+					 ldev->pf[idx1].dev);
 }
 
 bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev)
@@ -50,43 +53,45 @@ bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev)
 static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev,
 				       enum mlx5_lag_port_affinity port)
 {
+	int idx0 = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	int idx1 = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P2);
 	struct lag_tracker tracker = {};
 
-	if (!__mlx5_lag_is_multipath(ldev))
+	if (idx0 < 0 || idx1 < 0 || !__mlx5_lag_is_multipath(ldev))
 		return;
 
 	switch (port) {
 	case MLX5_LAG_NORMAL_AFFINITY:
-		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true;
-		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true;
-		tracker.netdev_state[MLX5_LAG_P1].link_up = true;
-		tracker.netdev_state[MLX5_LAG_P2].link_up = true;
+		tracker.netdev_state[idx0].tx_enabled = true;
+		tracker.netdev_state[idx1].tx_enabled = true;
+		tracker.netdev_state[idx0].link_up = true;
+		tracker.netdev_state[idx1].link_up = true;
 		break;
 	case MLX5_LAG_P1_AFFINITY:
-		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true;
-		tracker.netdev_state[MLX5_LAG_P1].link_up = true;
-		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = false;
-		tracker.netdev_state[MLX5_LAG_P2].link_up = false;
+		tracker.netdev_state[idx0].tx_enabled = true;
+		tracker.netdev_state[idx0].link_up = true;
+		tracker.netdev_state[idx1].tx_enabled = false;
+		tracker.netdev_state[idx1].link_up = false;
 		break;
 	case MLX5_LAG_P2_AFFINITY:
-		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = false;
-		tracker.netdev_state[MLX5_LAG_P1].link_up = false;
-		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true;
-		tracker.netdev_state[MLX5_LAG_P2].link_up = true;
+		tracker.netdev_state[idx0].tx_enabled = false;
+		tracker.netdev_state[idx0].link_up = false;
+		tracker.netdev_state[idx1].tx_enabled = true;
+		tracker.netdev_state[idx1].link_up = true;
 		break;
 	default:
-		mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev,
+		mlx5_core_warn(ldev->pf[idx0].dev,
 			       "Invalid affinity port %d", port);
 		return;
 	}
 
-	if (tracker.netdev_state[MLX5_LAG_P1].tx_enabled)
-		mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P1].dev->priv.events,
+	if (tracker.netdev_state[idx0].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[idx0].dev->priv.events,
 					 MLX5_DEV_EVENT_PORT_AFFINITY,
 					 (void *)0);
 
-	if (tracker.netdev_state[MLX5_LAG_P2].tx_enabled)
-		mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P2].dev->priv.events,
+	if (tracker.netdev_state[idx1].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[idx1].dev->priv.events,
 					 MLX5_DEV_EVENT_PORT_AFFINITY,
 					 (void *)0);
 
@@ -150,9 +155,14 @@ mlx5_lag_get_next_fib_dev(struct mlx5_lag *ldev,
 static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event,
 				     struct fib_entry_notifier_info *fen_info)
 {
+	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct net_device *nh_dev0, *nh_dev1;
 	struct fib_info *fi = fen_info->fi;
 	struct lag_mp *mp = &ldev->lag_mp;
+	int i, dev_idx = 0;
+
+	if (idx < 0)
+		return;
 
 	/* Handle delete event */
 	if (event == FIB_EVENT_ENTRY_DEL) {
@@ -179,17 +189,19 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event,
 	}
 
 	if (nh_dev0 == nh_dev1) {
-		mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev,
+		mlx5_core_warn(ldev->pf[idx].dev,
 			       "Multipath offload doesn't support routes with multiple nexthops of the same device");
 		return;
 	}
 
 	if (!nh_dev1) {
 		if (__mlx5_lag_is_active(ldev)) {
-			int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev0);
-
-			i++;
-			mlx5_lag_set_port_affinity(ldev, i);
+			mlx5_ldev_for_each(i, 0, ldev) {
+				dev_idx++;
+				if (ldev->pf[i].netdev == nh_dev0)
+					break;
+			}
+			mlx5_lag_set_port_affinity(ldev, dev_idx);
 			mlx5_lag_fib_set(mp, fi, fen_info->dst, fen_info->dst_len);
 		}
 
@@ -214,6 +226,7 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev,
 				       struct fib_info *fi)
 {
 	struct lag_mp *mp = &ldev->lag_mp;
+	int i, dev_idx = 0;
 
 	/* Check the nh event is related to the route */
 	if (!mp->fib.mfi || mp->fib.mfi != fi)
@@ -221,11 +234,15 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev,
 
 	/* nh added/removed */
 	if (event == FIB_EVENT_NH_DEL) {
-		int i = mlx5_lag_dev_get_netdev_idx(ldev, fib_nh->fib_nh_dev);
+		mlx5_ldev_for_each(i, 0, ldev) {
+			if (ldev->pf[i].netdev == fib_nh->fib_nh_dev)
+				break;
+			dev_idx++;
+		}
 
-		if (i >= 0) {
-			i = (i + 1) % 2 + 1; /* peer port */
-			mlx5_lag_set_port_affinity(ldev, i);
+		if (dev_idx >= 0) {
+			dev_idx = (dev_idx + 1) % 2 + 1; /* peer port */
+			mlx5_lag_set_port_affinity(ldev, dev_idx);
 		}
 	} else if (event == FIB_EVENT_NH_ADD &&
 		   fib_info_num_path(fi) == 2) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 571ea26edd0c..aad52d3a90e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -15,7 +15,7 @@ static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev)
 	u32 pf_metadata;
 	int i;
 
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		dev = ldev->pf[i].dev;
 		esw = dev->priv.eswitch;
 		pf_metadata = ldev->lag_mpesw.pf_metadata[i];
@@ -36,7 +36,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 	u32 pf_metadata;
 	int i, err;
 
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		dev = ldev->pf[i].dev;
 		esw = dev->priv.eswitch;
 		pf_metadata = mlx5_esw_match_metadata_alloc(esw);
@@ -52,7 +52,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 			goto err_metadata;
 	}
 
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		dev = ldev->pf[i].dev;
 		mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_MULTIPORT_ESW,
 					 (void *)0);
@@ -65,23 +65,22 @@ err_metadata:
 	return err;
 }
 
-#define MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS 4
 static int enable_mpesw(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	struct mlx5_core_dev *dev0;
 	int err;
 	int i;
 
-	if (ldev->mode != MLX5_LAG_MODE_NONE)
+	if (idx < 0 || ldev->mode != MLX5_LAG_MODE_NONE)
 		return -EINVAL;
 
-	if (ldev->ports > MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS)
-		return -EOPNOTSUPP;
-
+	dev0 = ldev->pf[idx].dev;
 	if (mlx5_eswitch_mode(dev0) != MLX5_ESWITCH_OFFLOADS ||
 	    !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table) ||
 	    !MLX5_CAP_GEN(dev0, create_lag_when_not_master_up) ||
-	    !mlx5_lag_check_prereq(ldev))
+	    !mlx5_lag_check_prereq(ldev) ||
+	    !mlx5_lag_shared_fdb_supported(ldev))
 		return -EOPNOTSUPP;
 
 	err = mlx5_mpesw_metadata_set(ldev);
@@ -98,7 +97,7 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 
 	dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 	mlx5_rescan_drivers_locked(dev0);
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 		if (err)
 			goto err_rescan_drivers;
@@ -112,7 +111,7 @@ err_rescan_drivers:
 	mlx5_deactivate_lag(ldev);
 err_add_devices:
 	mlx5_lag_add_devices(ldev);
-	for (i = 0; i < ldev->ports; i++)
+	mlx5_ldev_for_each(i, 0, ldev)
 		mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 	mlx5_mpesw_metadata_cleanup(ldev);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
index ab2717012b79..d832a12ffec0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
@@ -39,15 +39,18 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev,
 					  struct mlx5_lag_definer *lag_definer,
 					  u8 *ports)
 {
-	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_destination dest = {};
 	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_namespace *ns;
-	int err, i;
-	int idx;
-	int j;
+	struct mlx5_core_dev *dev;
+	int err, i, j, k, idx;
 
+	if (first_idx < 0)
+		return -EINVAL;
+
+	dev = ldev->pf[first_idx].dev;
 	ft_attr.max_fte = ldev->ports * ldev->buckets;
 	ft_attr.level = MLX5_LAG_FT_LEVEL_DEFINER;
 
@@ -74,7 +77,7 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev,
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_UPLINK;
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		for (j = 0; j < ldev->buckets; j++) {
 			u8 affinity;
 
@@ -88,13 +91,13 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev,
 								      &dest, 1);
 			if (IS_ERR(lag_definer->rules[idx])) {
 				err = PTR_ERR(lag_definer->rules[idx]);
-				do {
+				mlx5_ldev_for_each_reverse(k, i, 0, ldev) {
 					while (j--) {
-						idx = i * ldev->buckets + j;
+						idx = k * ldev->buckets + j;
 						mlx5_del_flow_rules(lag_definer->rules[idx]);
 					}
 					j = ldev->buckets;
-				} while (i--);
+				}
 				goto destroy_fg;
 			}
 		}
@@ -295,11 +298,16 @@ static struct mlx5_lag_definer *
 mlx5_lag_create_definer(struct mlx5_lag *ldev, enum netdev_lag_hash hash,
 			enum mlx5_traffic_types tt, bool tunnel, u8 *ports)
 {
-	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_lag_definer *lag_definer;
+	struct mlx5_core_dev *dev;
 	u32 *match_definer_mask;
 	int format_id, err;
 
+	if (first_idx < 0)
+		return ERR_PTR(-EINVAL);
+
+	dev = ldev->pf[first_idx].dev;
 	lag_definer = kzalloc(sizeof(*lag_definer), GFP_KERNEL);
 	if (!lag_definer)
 		return ERR_PTR(-ENOMEM);
@@ -341,12 +349,15 @@ free_lag_definer:
 static void mlx5_lag_destroy_definer(struct mlx5_lag *ldev,
 				     struct mlx5_lag_definer *lag_definer)
 {
-	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
-	int idx;
-	int i;
-	int j;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+	struct mlx5_core_dev *dev;
+	int idx, i, j;
 
-	for (i = 0; i < ldev->ports; i++) {
+	if (first_idx < 0)
+		return;
+
+	dev = ldev->pf[first_idx].dev;
+	mlx5_ldev_for_each(i, first_idx, ldev) {
 		for (j = 0; j < ldev->buckets; j++) {
 			idx = i * ldev->buckets + j;
 			mlx5_del_flow_rules(lag_definer->rules[idx]);
@@ -501,10 +512,15 @@ static void mlx5_lag_set_outer_ttc_params(struct mlx5_lag *ldev,
 
 static int mlx5_lag_create_ttc_table(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_lag_port_sel *port_sel = &ldev->port_sel;
 	struct ttc_params ttc_params = {};
+	struct mlx5_core_dev *dev;
+
+	if (first_idx < 0)
+		return -EINVAL;
 
+	dev = ldev->pf[first_idx].dev;
 	mlx5_lag_set_outer_ttc_params(ldev, &ttc_params);
 	port_sel->outer.ttc = mlx5_create_ttc_table(dev, &ttc_params);
 	return PTR_ERR_OR_ZERO(port_sel->outer.ttc);
@@ -512,10 +528,15 @@ static int mlx5_lag_create_ttc_table(struct mlx5_lag *ldev)
 
 static int mlx5_lag_create_inner_ttc_table(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
+	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_lag_port_sel *port_sel = &ldev->port_sel;
 	struct ttc_params ttc_params = {};
+	struct mlx5_core_dev *dev;
 
+	if (first_idx < 0)
+		return -EINVAL;
+
+	dev = ldev->pf[first_idx].dev;
 	mlx5_lag_set_inner_ttc_params(ldev, &ttc_params);
 	port_sel->inner.ttc = mlx5_create_inner_ttc_table(dev, &ttc_params);
 	return PTR_ERR_OR_ZERO(port_sel->inner.ttc);
@@ -530,7 +551,7 @@ int mlx5_lag_port_sel_create(struct mlx5_lag *ldev,
 	set_tt_map(port_sel, hash_type);
 	err = mlx5_lag_create_definers(ldev, hash_type, ports);
 	if (err)
-		return err;
+		goto clear_port_sel;
 
 	if (port_sel->tunnel) {
 		err = mlx5_lag_create_inner_ttc_table(ldev);
@@ -549,6 +570,8 @@ destroy_inner:
 		mlx5_destroy_ttc_table(port_sel->inner.ttc);
 destroy_definers:
 	mlx5_lag_destroy_definers(ldev);
+clear_port_sel:
+	memset(port_sel, 0, sizeof(*port_sel));
 	return err;
 }
 
@@ -565,7 +588,7 @@ static int __mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev,
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_UPLINK;
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 
-	for (i = 0; i < ldev->ports; i++) {
+	mlx5_ldev_for_each(i, 0, ldev) {
 		for (j = 0; j < ldev->buckets; j++) {
 			idx = i * ldev->buckets + j;
 			if (ldev->v2p_map[idx] == ports[idx])
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 4822d01123b4..cec18efadc73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -43,6 +43,8 @@
 #include <linux/cpufeature.h>
 #endif /* CONFIG_X86 */
 
+#define MLX5_RT_CLOCK_IDENTITY_SIZE MLX5_FLD_SZ_BYTES(mrtcq_reg, rt_clock_identity)
+
 enum {
 	MLX5_PIN_MODE_IN		= 0x0,
 	MLX5_PIN_MODE_OUT		= 0x1,
@@ -77,6 +79,56 @@ enum {
 	MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX = 200000,
 };
 
+struct mlx5_clock_dev_state {
+	struct mlx5_core_dev *mdev;
+	struct mlx5_devcom_comp_dev *compdev;
+	struct mlx5_nb pps_nb;
+	struct work_struct out_work;
+};
+
+struct mlx5_clock_priv {
+	struct mlx5_clock clock;
+	struct mlx5_core_dev *mdev;
+	struct mutex lock; /* protect mdev and used in PTP callbacks */
+	struct mlx5_core_dev *event_mdev;
+};
+
+static struct mlx5_clock_priv *clock_priv(struct mlx5_clock *clock)
+{
+	return container_of(clock, struct mlx5_clock_priv, clock);
+}
+
+static void mlx5_clock_lockdep_assert(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	lockdep_assert(lockdep_is_held(&clock_priv(clock)->lock));
+}
+
+static struct mlx5_core_dev *mlx5_clock_mdev_get(struct mlx5_clock *clock)
+{
+	mlx5_clock_lockdep_assert(clock);
+
+	return clock_priv(clock)->mdev;
+}
+
+static void mlx5_clock_lock(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	mutex_lock(&clock_priv(clock)->lock);
+}
+
+static void mlx5_clock_unlock(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	mutex_unlock(&clock_priv(clock)->lock);
+}
+
 static bool mlx5_real_time_mode(struct mlx5_core_dev *mdev)
 {
 	return (mlx5_is_real_time_rq(mdev) || mlx5_is_real_time_sq(mdev));
@@ -94,6 +146,22 @@ static bool mlx5_modify_mtutc_allowed(struct mlx5_core_dev *mdev)
 	return MLX5_CAP_MCAM_FEATURE(mdev, ptpcyc2realtime_modify);
 }
 
+static int mlx5_clock_identity_get(struct mlx5_core_dev *mdev,
+				   u8 identify[MLX5_RT_CLOCK_IDENTITY_SIZE])
+{
+	u32 out[MLX5_ST_SZ_DW(mrtcq_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mrtcq_reg)] = {};
+	int err;
+
+	err = mlx5_core_access_reg(mdev, in, sizeof(in),
+				   out, sizeof(out), MLX5_REG_MRTCQ, 0, 0);
+	if (!err)
+		memcpy(identify, MLX5_ADDR_OF(mrtcq_reg, out, rt_clock_identity),
+		       MLX5_RT_CLOCK_IDENTITY_SIZE);
+
+	return err;
+}
+
 static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
 {
 	/* Optimal shift constant leads to corrections above just 1 scaled ppm.
@@ -119,21 +187,30 @@ static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
 		   ilog2((U32_MAX / NSEC_PER_MSEC) * dev_freq_khz));
 }
 
+static s32 mlx5_clock_getmaxphase(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ?
+		       MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX :
+			     MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+}
+
 static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	s32 ret;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	ret = mlx5_clock_getmaxphase(mdev);
+	mlx5_clock_unlock(clock);
 
-	return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ?
-		       MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX :
-			     MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+	return ret;
 }
 
 static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta)
 {
-	s64 max = mlx5_ptp_getmaxphase(&mdev->clock.ptp_info);
+	s64 max = mlx5_clock_getmaxphase(mdev);
 
 	if (delta < -max || delta > max)
 		return false;
@@ -209,7 +286,7 @@ static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
 	if (real_time_mode)
 		*device_time = ns_to_ktime(REAL_TIME_TO_NS(device >> 32, device & U32_MAX));
 	else
-		*device_time = mlx5_timecounter_cyc2time(&mdev->clock, device);
+		*device_time = mlx5_timecounter_cyc2time(mdev->clock, device);
 
 	return 0;
 }
@@ -220,16 +297,23 @@ static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct system_time_snapshot history_begin = {0};
 	struct mlx5_core_dev *mdev;
+	int err;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
-	if (!mlx5_is_ptm_source_time_available(mdev))
-		return -EBUSY;
+	if (!mlx5_is_ptm_source_time_available(mdev)) {
+		err = -EBUSY;
+		goto unlock;
+	}
 
 	ktime_get_snapshot(&history_begin);
 
-	return get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
-					     &history_begin, cts);
+	err = get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
+					    &history_begin, cts);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 #endif /* CONFIG_X86 */
 
@@ -263,8 +347,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 {
 	struct mlx5_timer *timer = container_of(cc, struct mlx5_timer, cycles);
 	struct mlx5_clock *clock = container_of(timer, struct mlx5_clock, timer);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
 
 	return mlx5_read_time(mdev, NULL, false) & cc->mask;
 }
@@ -272,7 +355,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer;
 	u32 sign;
 
@@ -295,12 +378,10 @@ static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
 
 static void mlx5_pps_out(struct work_struct *work)
 {
-	struct mlx5_pps *pps_info = container_of(work, struct mlx5_pps,
-						 out_work);
-	struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock,
-						pps_info);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_clock_dev_state *clock_state = container_of(work, struct mlx5_clock_dev_state,
+								out_work);
+	struct mlx5_core_dev *mdev = clock_state->mdev;
+	struct mlx5_clock *clock = mdev->clock;
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	unsigned long flags;
 	int i;
@@ -322,17 +403,17 @@ static void mlx5_pps_out(struct work_struct *work)
 	}
 }
 
-static void mlx5_timestamp_overflow(struct work_struct *work)
+static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info)
 {
-	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5_core_dev *mdev;
 	struct mlx5_timer *timer;
 	struct mlx5_clock *clock;
 	unsigned long flags;
 
-	timer = container_of(dwork, struct mlx5_timer, overflow_work);
-	clock = container_of(timer, struct mlx5_clock, timer);
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	clock = container_of(ptp_info, struct mlx5_clock, ptp_info);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	timer = &clock->timer;
 
 	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto out;
@@ -343,7 +424,8 @@ static void mlx5_timestamp_overflow(struct work_struct *work)
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 out:
-	schedule_delayed_work(&timer->overflow_work, timer->overflow_period);
+	mlx5_clock_unlock(clock);
+	return timer->overflow_period;
 }
 
 static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev,
@@ -362,15 +444,12 @@ static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev,
 	return mlx5_set_mtutc(mdev, in, sizeof(in));
 }
 
-static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+static int mlx5_clock_settime(struct mlx5_core_dev *mdev, struct mlx5_clock *clock,
+			      const struct timespec64 *ts)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_timer *timer = &clock->timer;
-	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	if (mlx5_modify_mtutc_allowed(mdev)) {
 		int err = mlx5_ptp_settime_real_time(mdev, ts);
 
@@ -386,6 +465,20 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64
 	return 0;
 }
 
+static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
+	int err;
+
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	err = mlx5_clock_settime(mdev, clock, ts);
+	mlx5_clock_unlock(clock);
+
+	return err;
+}
+
 static
 struct timespec64 mlx5_ptp_gettimex_real_time(struct mlx5_core_dev *mdev,
 					      struct ptp_system_timestamp *sts)
@@ -405,7 +498,8 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	struct mlx5_core_dev *mdev;
 	u64 cycles, ns;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 	if (mlx5_real_time_mode(mdev)) {
 		*ts = mlx5_ptp_gettimex_real_time(mdev, sts);
 		goto out;
@@ -415,6 +509,7 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	ns = mlx5_timecounter_cyc2time(clock, cycles);
 	*ts = ns_to_timespec64(ns);
 out:
+	mlx5_clock_unlock(clock);
 	return 0;
 }
 
@@ -445,14 +540,16 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
+	int err = 0;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
-		int err = mlx5_ptp_adjtime_real_time(mdev, delta);
+		err = mlx5_ptp_adjtime_real_time(mdev, delta);
 
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	write_seqlock_irqsave(&clock->lock, flags);
@@ -460,17 +557,23 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
-	return 0;
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	int err;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	err = mlx5_ptp_adjtime_real_time(mdev, delta);
+	mlx5_clock_unlock(clock);
 
-	return mlx5_ptp_adjtime_real_time(mdev, delta);
+	return err;
 }
 
 static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm)
@@ -499,15 +602,17 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
+	int err = 0;
 	u32 mult;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
-		int err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
+		err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
 
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	mult = (u32)adjust_by_scaled_ppm(timer->nominal_c_mult, scaled_ppm);
@@ -517,8 +622,11 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	timer->cycles.mult = mult;
 	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
+	ptp_schedule_worker(clock->ptp, timer->overflow_period);
 
-	return 0;
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_extts_configure(struct ptp_clock_info *ptp,
@@ -527,25 +635,14 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev =
-			container_of(clock, struct mlx5_core_dev, clock);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	struct mlx5_core_dev *mdev;
 	u32 field_select = 0;
 	u8 pin_mode = 0;
 	u8 pattern = 0;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_PPS_CAP(mdev))
-		return -EOPNOTSUPP;
-
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_FALLING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	/* Reject requests to enable time stamping on both edges. */
 	if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 	    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -569,6 +666,14 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 		field_select = MLX5_MTPPS_FS_ENABLE;
 	}
 
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+
+	if (!MLX5_PPS_CAP(mdev)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
 	MLX5_SET(mtpps_reg, in, pin, pin);
 	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
 	MLX5_SET(mtpps_reg, in, pattern, pattern);
@@ -577,15 +682,23 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 
 	err = mlx5_set_mtpps(mdev, in, sizeof(in));
 	if (err)
-		return err;
+		goto unlock;
+
+	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
+	if (err)
+		goto unlock;
+
+	clock->pps_info.pin_armed[pin] = on;
+	clock_priv(clock)->event_mdev = mdev;
 
-	return mlx5_set_mtppse(mdev, pin, 0,
-			       MLX5_EVENT_MODE_REPETETIVE & on);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static u64 find_target_cycles(struct mlx5_core_dev *mdev, s64 target_ns)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	u64 cycles_now, cycles_delta;
 	u64 nsec_now, nsec_delta;
 	struct mlx5_timer *timer;
@@ -644,7 +757,7 @@ static int mlx5_perout_conf_out_pulse_duration(struct mlx5_core_dev *mdev,
 					       struct ptp_clock_request *rq,
 					       u32 *out_pulse_duration_ns)
 {
-	struct mlx5_pps *pps_info = &mdev->clock.pps_info;
+	struct mlx5_pps *pps_info = &mdev->clock->pps_info;
 	u32 out_pulse_duration;
 	struct timespec64 ts;
 
@@ -677,7 +790,7 @@ static int perout_conf_npps_real_time(struct mlx5_core_dev *mdev, struct ptp_clo
 				      u32 *field_select, u32 *out_pulse_duration_ns,
 				      u64 *period, u64 *time_stamp)
 {
-	struct mlx5_pps *pps_info = &mdev->clock.pps_info;
+	struct mlx5_pps *pps_info = &mdev->clock->pps_info;
 	struct ptp_clock_time *time = &rq->perout.start;
 	struct timespec64 ts;
 
@@ -700,38 +813,24 @@ static int perout_conf_npps_real_time(struct mlx5_core_dev *mdev, struct ptp_clo
 	return 0;
 }
 
-static bool mlx5_perout_verify_flags(struct mlx5_core_dev *mdev, unsigned int flags)
-{
-	return ((!mlx5_npps_real_time_supported(mdev) && flags) ||
-		(mlx5_npps_real_time_supported(mdev) && flags & ~PTP_PEROUT_DUTY_CYCLE));
-}
-
 static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 				 struct ptp_clock_request *rq,
 				 int on)
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev =
-			container_of(clock, struct mlx5_core_dev, clock);
-	bool rt_mode = mlx5_real_time_mode(mdev);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	u32 out_pulse_duration_ns = 0;
+	struct mlx5_core_dev *mdev;
 	u32 field_select = 0;
 	u64 npps_period = 0;
 	u64 time_stamp = 0;
 	u8 pin_mode = 0;
 	u8 pattern = 0;
+	bool rt_mode;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_PPS_CAP(mdev))
-		return -EOPNOTSUPP;
-
-	/* Reject requests with unsupported flags */
-	if (mlx5_perout_verify_flags(mdev, rq->perout.flags))
-		return -EOPNOTSUPP;
-
 	if (rq->perout.index >= clock->ptp_info.n_pins)
 		return -EINVAL;
 
@@ -740,14 +839,23 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	if (pin < 0)
 		return -EBUSY;
 
-	if (on) {
-		bool rt_mode = mlx5_real_time_mode(mdev);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	rt_mode = mlx5_real_time_mode(mdev);
 
+	if (!MLX5_PPS_CAP(mdev)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	if (on) {
 		pin_mode = MLX5_PIN_MODE_OUT;
 		pattern = MLX5_OUT_PATTERN_PERIODIC;
 
-		if (rt_mode &&  rq->perout.start.sec > U32_MAX)
-			return -EINVAL;
+		if (rt_mode &&  rq->perout.start.sec > U32_MAX) {
+			err = -EINVAL;
+			goto unlock;
+		}
 
 		field_select |= MLX5_MTPPS_FS_PIN_MODE |
 				MLX5_MTPPS_FS_PATTERN |
@@ -760,7 +868,7 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 		else
 			err = perout_conf_1pps(mdev, rq, &time_stamp, rt_mode);
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	MLX5_SET(mtpps_reg, in, pin, pin);
@@ -773,13 +881,16 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	MLX5_SET(mtpps_reg, in, out_pulse_duration_ns, out_pulse_duration_ns);
 	err = mlx5_set_mtpps(mdev, in, sizeof(in));
 	if (err)
-		return err;
+		goto unlock;
 
 	if (rt_mode)
-		return 0;
+		goto unlock;
 
-	return mlx5_set_mtppse(mdev, pin, 0,
-			       MLX5_EVENT_MODE_REPETETIVE & on);
+	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
+
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_pps_configure(struct ptp_clock_info *ptp,
@@ -852,6 +963,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = {
 	.settime64	= mlx5_ptp_settime,
 	.enable		= NULL,
 	.verify		= NULL,
+	.do_aux_work	= mlx5_timestamp_overflow,
 };
 
 static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
@@ -865,10 +977,8 @@ static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
 				    mtpps_size, MLX5_REG_MTPPS, 0, 0);
 }
 
-static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
+static int mlx5_get_pps_pin_mode(struct mlx5_core_dev *mdev, u8 pin)
 {
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {};
 	u8 mode;
 	int err;
@@ -887,8 +997,9 @@ static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
 	return PTP_PF_NONE;
 }
 
-static void mlx5_init_pin_config(struct mlx5_clock *clock)
+static void mlx5_init_pin_config(struct mlx5_core_dev *mdev)
 {
+	struct mlx5_clock *clock = mdev->clock;
 	int i;
 
 	if (!clock->ptp_info.n_pins)
@@ -904,20 +1015,27 @@ static void mlx5_init_pin_config(struct mlx5_clock *clock)
 	clock->ptp_info.verify = mlx5_ptp_verify;
 	clock->ptp_info.pps = 1;
 
+	clock->ptp_info.supported_extts_flags = PTP_RISING_EDGE |
+						PTP_FALLING_EDGE |
+						PTP_STRICT_FLAGS;
+
+	if (mlx5_npps_real_time_supported(mdev))
+		clock->ptp_info.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE;
+
 	for (i = 0; i < clock->ptp_info.n_pins; i++) {
 		snprintf(clock->ptp_info.pin_config[i].name,
 			 sizeof(clock->ptp_info.pin_config[i].name),
 			 "mlx5_pps%d", i);
 		clock->ptp_info.pin_config[i].index = i;
-		clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(clock, i);
+		clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(mdev, i);
 		clock->ptp_info.pin_config[i].chan = 0;
 	}
 }
 
 static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	struct mlx5_clock *clock = mdev->clock;
 
 	mlx5_query_mtpps(mdev, out, sizeof(out));
 
@@ -967,16 +1085,16 @@ static u64 perout_conf_next_event_timer(struct mlx5_core_dev *mdev,
 static int mlx5_pps_event(struct notifier_block *nb,
 			  unsigned long type, void *data)
 {
-	struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
+	struct mlx5_clock_dev_state *clock_state = mlx5_nb_cof(nb, struct mlx5_clock_dev_state,
+							       pps_nb);
+	struct mlx5_core_dev *mdev = clock_state->mdev;
+	struct mlx5_clock *clock = mdev->clock;
 	struct ptp_clock_event ptp_event;
 	struct mlx5_eqe *eqe = data;
 	int pin = eqe->data.pps.pin;
-	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	u64 ns;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	switch (clock->ptp_info.pin_config[pin].func) {
 	case PTP_PF_EXTTS:
 		ptp_event.index = pin;
@@ -996,11 +1114,15 @@ static int mlx5_pps_event(struct notifier_block *nb,
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:
+		if (clock->shared) {
+			mlx5_core_warn(mdev, " Received unexpected PPS out event\n");
+			break;
+		}
 		ns = perout_conf_next_event_timer(mdev, clock);
 		write_seqlock_irqsave(&clock->lock, flags);
 		clock->pps_info.start[pin] = ns;
 		write_sequnlock_irqrestore(&clock->lock, flags);
-		schedule_work(&clock->pps_info.out_work);
+		schedule_work(&clock_state->out_work);
 		break;
 	default:
 		mlx5_core_err(mdev, " Unhandled clock PPS event, func %d\n",
@@ -1012,7 +1134,7 @@ static int mlx5_pps_event(struct notifier_block *nb,
 
 static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u32 dev_freq;
 
@@ -1028,10 +1150,10 @@ static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 			 ktime_to_ns(ktime_get_real()));
 }
 
-static void mlx5_init_overflow_period(struct mlx5_clock *clock)
+static void mlx5_init_overflow_period(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u64 overflow_cycles;
 	u64 frac = 0;
@@ -1052,12 +1174,11 @@ static void mlx5_init_overflow_period(struct mlx5_clock *clock)
 	do_div(ns, NSEC_PER_SEC / HZ);
 	timer->overflow_period = ns;
 
-	INIT_DELAYED_WORK(&timer->overflow_work, mlx5_timestamp_overflow);
-	if (timer->overflow_period)
-		schedule_delayed_work(&timer->overflow_work, 0);
-	else
+	if (!timer->overflow_period) {
+		timer->overflow_period = HZ;
 		mlx5_core_warn(mdev,
-			       "invalid overflow period, overflow_work is not scheduled\n");
+			       "invalid overflow period, overflow_work is scheduled once per second\n");
+	}
 
 	if (clock_info)
 		clock_info->overflow_period = timer->overflow_period;
@@ -1065,7 +1186,7 @@ static void mlx5_init_overflow_period(struct mlx5_clock *clock)
 
 static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_ib_clock_info *info;
 	struct mlx5_timer *timer;
 
@@ -1088,7 +1209,7 @@ static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 	u8 log_max_freq_adjustment = 0;
@@ -1107,7 +1228,7 @@ static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 
 	/* Configure the PHC */
 	clock->ptp_info = mlx5_ptp_clock_info;
@@ -1123,38 +1244,30 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 
 	mlx5_timecounter_init(mdev);
 	mlx5_init_clock_info(mdev);
-	mlx5_init_overflow_period(clock);
+	mlx5_init_overflow_period(mdev);
 
 	if (mlx5_real_time_mode(mdev)) {
 		struct timespec64 ts;
 
 		ktime_get_real_ts64(&ts);
-		mlx5_ptp_settime(&clock->ptp_info, &ts);
+		mlx5_clock_settime(mdev, clock, &ts);
 	}
 }
 
 static void mlx5_init_pps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
 	if (!MLX5_PPS_CAP(mdev))
 		return;
 
 	mlx5_get_pps_caps(mdev);
-	mlx5_init_pin_config(clock);
+	mlx5_init_pin_config(mdev);
 }
 
-void mlx5_init_clock(struct mlx5_core_dev *mdev)
+static void mlx5_init_clock_dev(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
-	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
-		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
-		return;
-	}
+	struct mlx5_clock *clock = mdev->clock;
 
 	seqlock_init(&clock->lock);
-	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
 
 	/* Initialize the device clock */
 	mlx5_init_timer_clock(mdev);
@@ -1163,33 +1276,27 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 	mlx5_init_pps(mdev);
 
 	clock->ptp = ptp_clock_register(&clock->ptp_info,
-					&mdev->pdev->dev);
+					clock->shared ? NULL : &mdev->pdev->dev);
 	if (IS_ERR(clock->ptp)) {
-		mlx5_core_warn(mdev, "ptp_clock_register failed %ld\n",
+		mlx5_core_warn(mdev, "%sptp_clock_register failed %ld\n",
+			       clock->shared ? "shared clock " : "",
 			       PTR_ERR(clock->ptp));
 		clock->ptp = NULL;
 	}
 
-	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
-	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
+	if (clock->ptp)
+		ptp_schedule_worker(clock->ptp, 0);
 }
 
-void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+static void mlx5_destroy_clock_dev(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
-	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
-		return;
+	struct mlx5_clock *clock = mdev->clock;
 
-	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
 	if (clock->ptp) {
 		ptp_clock_unregister(clock->ptp);
 		clock->ptp = NULL;
 	}
 
-	cancel_work_sync(&clock->pps_info.out_work);
-	cancel_delayed_work_sync(&clock->timer.overflow_work);
-
 	if (mdev->clock_info) {
 		free_page((unsigned long)mdev->clock_info);
 		mdev->clock_info = NULL;
@@ -1197,3 +1304,248 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 
 	kfree(clock->ptp_info.pin_config);
 }
+
+static void mlx5_clock_free(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock_priv *cpriv = clock_priv(mdev->clock);
+
+	mlx5_destroy_clock_dev(mdev);
+	mutex_destroy(&cpriv->lock);
+	kfree(cpriv);
+	mdev->clock = NULL;
+}
+
+static int mlx5_clock_alloc(struct mlx5_core_dev *mdev, bool shared)
+{
+	struct mlx5_clock_priv *cpriv;
+	struct mlx5_clock *clock;
+
+	cpriv = kzalloc(sizeof(*cpriv), GFP_KERNEL);
+	if (!cpriv)
+		return -ENOMEM;
+
+	mutex_init(&cpriv->lock);
+	cpriv->mdev = mdev;
+	clock = &cpriv->clock;
+	clock->shared = shared;
+	mdev->clock = clock;
+	mlx5_clock_lock(clock);
+	mlx5_init_clock_dev(mdev);
+	mlx5_clock_unlock(clock);
+
+	if (!clock->shared)
+		return 0;
+
+	if (!clock->ptp) {
+		mlx5_core_warn(mdev, "failed to create ptp dev shared by multiple functions");
+		mlx5_clock_free(mdev);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void mlx5_shared_clock_register(struct mlx5_core_dev *mdev, u64 key)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_devcom_comp_dev *pos;
+
+	mdev->clock_state->compdev = mlx5_devcom_register_component(mdev->priv.devc,
+								    MLX5_DEVCOM_SHARED_CLOCK,
+								    key, NULL, mdev);
+	if (IS_ERR(mdev->clock_state->compdev))
+		return;
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	if (next) {
+		mdev->clock = next->clock;
+		/* clock info is shared among all the functions using the same clock */
+		mdev->clock_info = next->clock_info;
+	} else {
+		mlx5_clock_alloc(mdev, true);
+	}
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+	if (!mdev->clock) {
+		mlx5_devcom_unregister_component(mdev->clock_state->compdev);
+		mdev->clock_state->compdev = NULL;
+	}
+}
+
+static void mlx5_shared_clock_unregister(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_devcom_comp_dev *pos;
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock && peer_dev != mdev) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	if (next) {
+		struct mlx5_clock_priv *cpriv = clock_priv(clock);
+
+		mlx5_clock_lock(clock);
+		if (mdev == cpriv->mdev)
+			cpriv->mdev = next;
+		mlx5_clock_unlock(clock);
+	} else {
+		mlx5_clock_free(mdev);
+	}
+
+	mdev->clock = NULL;
+	mdev->clock_info = NULL;
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+	mlx5_devcom_unregister_component(mdev->clock_state->compdev);
+}
+
+static void mlx5_clock_arm_pps_in_event(struct mlx5_clock *clock,
+					struct mlx5_core_dev *new_mdev,
+					struct mlx5_core_dev *old_mdev)
+{
+	struct ptp_clock_info *ptp_info = &clock->ptp_info;
+	struct mlx5_clock_priv *cpriv = clock_priv(clock);
+	int i;
+
+	for (i = 0; i < ptp_info->n_pins; i++) {
+		if (ptp_info->pin_config[i].func != PTP_PF_EXTTS ||
+		    !clock->pps_info.pin_armed[i])
+			continue;
+
+		if (new_mdev) {
+			mlx5_set_mtppse(new_mdev, i, 0, MLX5_EVENT_MODE_REPETETIVE);
+			cpriv->event_mdev = new_mdev;
+		} else {
+			cpriv->event_mdev = NULL;
+		}
+
+		if (old_mdev)
+			mlx5_set_mtppse(old_mdev, i, 0, MLX5_EVENT_MODE_DISABLE);
+	}
+}
+
+void mlx5_clock_load(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_clock_priv *cpriv;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	INIT_WORK(&mdev->clock_state->out_work, mlx5_pps_out);
+	MLX5_NB_INIT(&mdev->clock_state->pps_nb, mlx5_pps_event, PPS_EVENT);
+	mlx5_eq_notifier_register(mdev, &mdev->clock_state->pps_nb);
+
+	if (!clock->shared) {
+		mlx5_clock_arm_pps_in_event(clock, mdev, NULL);
+		return;
+	}
+
+	cpriv = clock_priv(clock);
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_clock_lock(clock);
+	if (mdev == cpriv->mdev && mdev != cpriv->event_mdev)
+		mlx5_clock_arm_pps_in_event(clock, mdev, cpriv->event_mdev);
+	mlx5_clock_unlock(clock);
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+}
+
+void mlx5_clock_unload(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_devcom_comp_dev *pos;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	if (!clock->shared) {
+		mlx5_clock_arm_pps_in_event(clock, NULL, mdev);
+		goto out;
+	}
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock && peer_dev != mdev) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	mlx5_clock_lock(clock);
+	if (mdev == clock_priv(clock)->event_mdev)
+		mlx5_clock_arm_pps_in_event(clock, next, mdev);
+	mlx5_clock_unlock(clock);
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+out:
+	mlx5_eq_notifier_unregister(mdev, &mdev->clock_state->pps_nb);
+	cancel_work_sync(&mdev->clock_state->out_work);
+}
+
+static struct mlx5_clock null_clock;
+
+int mlx5_init_clock(struct mlx5_core_dev *mdev)
+{
+	u8 identity[MLX5_RT_CLOCK_IDENTITY_SIZE];
+	struct mlx5_clock_dev_state *clock_state;
+	u64 key;
+	int err;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
+		mdev->clock = &null_clock;
+		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
+		return 0;
+	}
+
+	clock_state = kzalloc(sizeof(*clock_state), GFP_KERNEL);
+	if (!clock_state)
+		return -ENOMEM;
+	clock_state->mdev = mdev;
+	mdev->clock_state = clock_state;
+
+	if (MLX5_CAP_MCAM_REG3(mdev, mrtcq) && mlx5_real_time_mode(mdev)) {
+		if (mlx5_clock_identity_get(mdev, identity)) {
+			mlx5_core_warn(mdev, "failed to get rt clock identity, create ptp dev per function\n");
+		} else {
+			memcpy(&key, &identity, sizeof(key));
+			mlx5_shared_clock_register(mdev, key);
+		}
+	}
+
+	if (!mdev->clock) {
+		err = mlx5_clock_alloc(mdev, false);
+		if (err) {
+			kfree(clock_state);
+			mdev->clock_state = NULL;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+{
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	if (mdev->clock->shared)
+		mlx5_shared_clock_unregister(mdev);
+	else
+		mlx5_clock_free(mdev);
+	kfree(mdev->clock_state);
+	mdev->clock_state = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index bd95b9f8d143..c18a652c0faa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -33,6 +33,35 @@
 #ifndef __LIB_CLOCK_H__
 #define __LIB_CLOCK_H__
 
+#include <linux/ptp_clock_kernel.h>
+
+#define MAX_PIN_NUM	8
+struct mlx5_pps {
+	u8                         pin_caps[MAX_PIN_NUM];
+	u64                        start[MAX_PIN_NUM];
+	u8                         enabled;
+	u64                        min_npps_period;
+	u64                        min_out_pulse_duration_ns;
+	bool                       pin_armed[MAX_PIN_NUM];
+};
+
+struct mlx5_timer {
+	struct cyclecounter        cycles;
+	struct timecounter         tc;
+	u32                        nominal_c_mult;
+	unsigned long              overflow_period;
+};
+
+struct mlx5_clock {
+	seqlock_t                  lock;
+	struct hwtstamp_config     hwtstamp_config;
+	struct ptp_clock          *ptp;
+	struct ptp_clock_info      ptp_info;
+	struct mlx5_pps            pps_info;
+	struct mlx5_timer          timer;
+	bool                       shared;
+};
+
 static inline bool mlx5_is_real_time_rq(struct mlx5_core_dev *mdev)
 {
 	u8 rq_ts_format_cap = MLX5_CAP_GEN(mdev, rq_ts_format);
@@ -54,12 +83,14 @@ static inline bool mlx5_is_real_time_sq(struct mlx5_core_dev *mdev)
 typedef ktime_t (*cqe_ts_to_ns)(struct mlx5_clock *, u64);
 
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-void mlx5_init_clock(struct mlx5_core_dev *mdev);
+int mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+void mlx5_clock_load(struct mlx5_core_dev *mdev);
+void mlx5_clock_unload(struct mlx5_core_dev *mdev);
 
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
-	return mdev->clock.ptp ? ptp_clock_index(mdev->clock.ptp) : -1;
+	return mdev->clock->ptp ? ptp_clock_index(mdev->clock->ptp) : -1;
 }
 
 static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
@@ -87,8 +118,10 @@ static inline ktime_t mlx5_real_time_cyc2time(struct mlx5_clock *clock,
 	return ns_to_ktime(time);
 }
 #else
-static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
+static inline int mlx5_init_clock(struct mlx5_core_dev *mdev) { return 0; }
 static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_clock_load(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_clock_unload(struct mlx5_core_dev *mdev) {}
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
 	return -1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index d58032dd0df7..c79699b94a02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -11,6 +11,7 @@ enum mlx5_devcom_component {
 	MLX5_DEVCOM_MPV,
 	MLX5_DEVCOM_HCA_PORTS,
 	MLX5_DEVCOM_SD_GROUP,
+	MLX5_DEVCOM_SHARED_CLOCK,
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index a80ecb672f33..0a3c260af377 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -161,7 +161,8 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
 				  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? FT_TBL_SZ : POOL_NEXT_SIZE;
+	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ?
+		FT_TBL_SZ : MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.max_fte = sz;
 
 	/* We use chains_default_ft(chains) as the table's next_ft till
@@ -196,6 +197,11 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ns = mlx5_get_flow_namespace(chains->dev, chains->ns);
 	}
 
+	if (!ns) {
+		mlx5_core_warn(chains->dev, "Failed to get flow namespace\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	ft_attr.autogroup.num_reserved_entries = 2;
 	ft_attr.autogroup.max_num_groups = chains->group_num;
 	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
@@ -699,7 +705,7 @@ mlx5_chains_create_global_table(struct mlx5_fs_chains *chains)
 		goto err_ignore;
 	}
 
-	chain = mlx5_chains_get_chain_range(chains),
+	chain = mlx5_chains_get_chain_range(chains);
 	prio = mlx5_chains_get_prio_range(chains);
 	level = mlx5_chains_get_level_range(chains);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
index 9f13cea16446..ca9ecec358b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -61,6 +61,25 @@ static void mlx5_cleanup_ttc_rules(struct mlx5_ttc_table *ttc)
 	}
 }
 
+static const char *mlx5_traffic_types_names[MLX5_NUM_TT] = {
+	[MLX5_TT_IPV4_TCP] =  "TT_IPV4_TCP",
+	[MLX5_TT_IPV6_TCP] =  "TT_IPV6_TCP",
+	[MLX5_TT_IPV4_UDP] =  "TT_IPV4_UDP",
+	[MLX5_TT_IPV6_UDP] =  "TT_IPV6_UDP",
+	[MLX5_TT_IPV4_IPSEC_AH] = "TT_IPV4_IPSEC_AH",
+	[MLX5_TT_IPV6_IPSEC_AH] = "TT_IPV6_IPSEC_AH",
+	[MLX5_TT_IPV4_IPSEC_ESP] = "TT_IPV4_IPSEC_ESP",
+	[MLX5_TT_IPV6_IPSEC_ESP] = "TT_IPV6_IPSEC_ESP",
+	[MLX5_TT_IPV4] = "TT_IPV4",
+	[MLX5_TT_IPV6] = "TT_IPV6",
+	[MLX5_TT_ANY] = "TT_ANY"
+};
+
+const char *mlx5_ttc_get_name(enum mlx5_traffic_types tt)
+{
+	return mlx5_traffic_types_names[tt];
+}
+
 struct mlx5_etype_proto {
 	u16 etype;
 	u8 proto;
@@ -618,10 +637,6 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -635,7 +650,16 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &inner_ttc_groups[TTC_GROUPS_DEFAULT];
 
@@ -691,10 +715,6 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -708,7 +728,16 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &ttc_groups[TTC_GROUPS_DEFAULT];
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
index 92eea6bea310..ab9434fe3ae6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
@@ -49,6 +49,7 @@ struct ttc_params {
 	struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_TT];
 };
 
+const char *mlx5_ttc_get_name(enum mlx5_traffic_types tt);
 struct mlx5_flow_table *mlx5_get_ttc_flow_table(struct mlx5_ttc_table *ttc);
 
 struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
index 4a078113e292..762d55ba9e51 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c
@@ -497,7 +497,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	memset(&dest, 0, sizeof(struct mlx5_flow_destination));
 	memset(&flow_act, 0, sizeof(flow_act));
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(tx_tables->check_miss_rule_counter);
+	dest.counter = tx_tables->check_miss_rule_counter;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	rule = mlx5_add_flow_rules(tx_tables->ft_check,  NULL, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
@@ -519,7 +519,7 @@ static int macsec_fs_tx_create(struct mlx5_macsec_fs *macsec_fs)
 	flow_act.flags = FLOW_ACT_NO_APPEND;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW | MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(tx_tables->check_rule_counter);
+	dest.counter = tx_tables->check_rule_counter;
 	rule = mlx5_add_flow_rules(tx_tables->ft_check, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -1200,7 +1200,7 @@ static int macsec_fs_rx_create_check_decap_rule(struct mlx5_macsec_fs *macsec_fs
 	flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
 			    MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	roce_dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	roce_dest[dstn].counter_id = mlx5_fc_id(rx_tables->check_rule_counter);
+	roce_dest[dstn].counter = rx_tables->check_rule_counter;
 	rule = mlx5_add_flow_rules(rx_tables->ft_check, spec, flow_act, roce_dest, dstn + 1);
 
 	if (IS_ERR(rule)) {
@@ -1592,7 +1592,7 @@ static int macsec_fs_rx_create(struct mlx5_macsec_fs *macsec_fs)
 	memset(&flow_act, 0, sizeof(flow_act));
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(rx_tables->check_miss_rule_counter);
+	dest.counter = rx_tables->check_miss_rule_counter;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	rule = mlx5_add_flow_rules(rx_tables->ft_check,  NULL, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 220a9ac75c8b..41e8660c819c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -368,6 +368,10 @@ int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_ty
 	u16 opmod = (cap_type << 1) | (cap_mode & 0x01);
 	int err;
 
+	if (WARN_ON(!dev->caps.hca[cap_type]))
+		/* this cap_type must be added to mlx5_hca_caps_alloc() */
+		return -EINVAL;
+
 	memset(in, 0, sizeof(in));
 	out = kzalloc(out_sz, GFP_KERNEL);
 	if (!out)
@@ -664,6 +668,10 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list,
 			 ilog2(max_uc_list));
 
+	/* enable absolute native port num */
+	if (MLX5_CAP_GEN_MAX(dev, abs_native_port_num))
+		MLX5_SET(cmd_hca_cap, set_hca_cap, abs_native_port_num, 1);
+
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
@@ -941,9 +949,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 
 	mlx5_pci_vsc_init(dev);
 
-	err = pci_enable_ptm(pdev, NULL);
-	if (err)
-		mlx5_core_info(dev, "PTM is not supported by PCIe\n");
+	pci_enable_ptm(pdev, NULL);
 
 	return 0;
 
@@ -1032,7 +1038,11 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 
 	mlx5_init_reserved_gids(dev);
 
-	mlx5_init_clock(dev);
+	err = mlx5_init_clock(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize hardware clock\n");
+		goto err_tables_cleanup;
+	}
 
 	dev->vxlan = mlx5_vxlan_create(dev);
 	dev->geneve = mlx5_geneve_create(dev);
@@ -1040,7 +1050,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	err = mlx5_init_rl_table(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init rate limiting\n");
-		goto err_tables_cleanup;
+		goto err_clock_cleanup;
 	}
 
 	err = mlx5_mpfs_init(dev);
@@ -1117,10 +1127,11 @@ err_mpfs_cleanup:
 	mlx5_mpfs_cleanup(dev);
 err_rl_cleanup:
 	mlx5_cleanup_rl_table(dev);
-err_tables_cleanup:
+err_clock_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
+err_tables_cleanup:
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
@@ -1199,24 +1210,24 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
 
-	mlx5_start_health_poll(dev);
-
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
-		goto stop_health_poll;
+		goto err_cmd_cleanup;
 	}
 
+	mlx5_start_health_poll(dev);
+
 	err = mlx5_core_set_issi(dev);
 	if (err) {
 		mlx5_core_err(dev, "failed to set issi\n");
-		goto err_disable_hca;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_satisfy_startup_pages(dev, 1);
 	if (err) {
 		mlx5_core_err(dev, "failed to allocate boot pages\n");
-		goto err_disable_hca;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_tout_query_dtor(dev);
@@ -1229,10 +1240,9 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 
 reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
-err_disable_hca:
-	mlx5_core_disable_hca(dev, 0);
 stop_health_poll:
 	mlx5_stop_health_poll(dev, boot);
+	mlx5_core_disable_hca(dev, 0);
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_disable(dev);
@@ -1243,8 +1253,8 @@ err_cmd_cleanup:
 static void mlx5_function_disable(struct mlx5_core_dev *dev, bool boot)
 {
 	mlx5_reclaim_startup_pages(dev);
-	mlx5_core_disable_hca(dev, 0);
 	mlx5_stop_health_poll(dev, boot);
+	mlx5_core_disable_hca(dev, 0);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_disable(dev);
 }
@@ -1353,6 +1363,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_eq_table;
 	}
 
+	mlx5_clock_load(dev);
+
 	err = mlx5_fw_tracer_init(dev->tracer);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init FW tracer %d\n", err);
@@ -1436,6 +1448,7 @@ err_fpga_start:
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_clock_unload(dev);
 	mlx5_eq_table_destroy(dev);
 err_eq_table:
 	mlx5_irq_table_destroy(dev);
@@ -1462,6 +1475,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_clock_unload(dev);
 	mlx5_eq_table_destroy(dev);
 	mlx5_irq_table_destroy(dev);
 	mlx5_pagealloc_stop(dev);
@@ -1788,6 +1802,8 @@ static const int types[] = {
 	MLX5_CAP_MACSEC,
 	MLX5_CAP_ADV_VIRTUALIZATION,
 	MLX5_CAP_CRYPTO,
+	MLX5_CAP_SHAMPO,
+	MLX5_CAP_ADV_RDMA,
 };
 
 static void mlx5_hca_caps_free(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 99de67c3aa74..2e02bdea8361 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -114,6 +114,26 @@ struct mlx5_cmd_alias_obj_create_attr {
 	u8 access_key[ACCESS_KEY_LEN];
 };
 
+struct mlx5_port_eth_proto {
+	u32 cap;
+	u32 admin;
+	u32 oper;
+};
+
+struct mlx5_module_eeprom_query_params {
+	u16 size;
+	u16 offset;
+	u16 i2c_address;
+	u32 page;
+	u32 bank;
+	u32 module_number;
+};
+
+struct mlx5_link_info {
+	u32 speed;
+	u32 lanes;
+};
+
 static inline void mlx5_printk(struct mlx5_core_dev *dev, int level, const char *format, ...)
 {
 	struct device *device = dev->device;
@@ -280,6 +300,78 @@ int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev);
 void mlx5_dm_cleanup(struct mlx5_core_dev *dev);
 
+void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
+int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
+			       enum mlx5_port_status status);
+int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
+				 enum mlx5_port_status *status);
+int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration);
+
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause);
+int mlx5_query_port_pause(struct mlx5_core_dev *dev,
+			  u32 *rx_pause, u32 *tx_pause);
+
+int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx);
+int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx,
+			u8 *pfc_en_rx);
+
+int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
+				  u16 stall_critical_watermark,
+				  u16 stall_minor_watermark);
+int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev,
+				    u16 *stall_critical_watermark,
+				    u16 *stall_minor_watermark);
+
+int mlx5_max_tc(struct mlx5_core_dev *mdev);
+int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc);
+int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
+			    u8 prio, u8 *tc);
+int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group);
+int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
+			     u8 tc, u8 *tc_group);
+int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw);
+int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
+				u8 tc, u8 *bw_pct);
+int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
+				    u8 *max_bw_value,
+				    u8 *max_bw_unit);
+int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
+				   u8 *max_bw_value,
+				   u8 *max_bw_unit);
+int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode);
+int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode);
+
+int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen);
+int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen);
+int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable);
+void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
+			 bool *enabled);
+int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
+			     u16 offset, u16 size, u8 *data);
+int
+mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
+				 struct mlx5_module_eeprom_query_params *params,
+				 u8 *data);
+
+int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
+int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
+int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
+int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
+int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
+int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5_port_eth_proto *eproto);
+bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev);
+const struct mlx5_link_info *mlx5_port_ptys2info(struct mlx5_core_dev *mdev,
+						 u32 eth_proto_oper,
+						 bool force_legacy);
+u32 mlx5_port_info2linkmodes(struct mlx5_core_dev *mdev,
+			     struct mlx5_link_info *info,
+			     bool force_legacy);
+int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
+
 #define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) &&		\
 			    MLX5_CAP_GEN((mdev), pps_modify) &&		\
 			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) &&	\
@@ -346,6 +438,8 @@ int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap
 #define mlx5_vport_get_other_func_general_cap(dev, vport, out)		\
 	mlx5_vport_get_other_func_cap(dev, vport, out, MLX5_CAP_GENERAL)
 
+int mlx5_vport_get_vhca_id(struct mlx5_core_dev *dev, u16 vport, u16 *vhca_id);
+
 static inline u32 mlx5_sriov_get_vf_total_msix(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
index 0881e961d8b1..586688da9940 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
@@ -10,12 +10,15 @@
 
 struct mlx5_irq;
 struct cpu_rmap;
+struct mlx5_irq_pool;
 
 int mlx5_irq_table_init(struct mlx5_core_dev *dev);
 void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_irq_table_create(struct mlx5_core_dev *dev);
 void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
 void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev);
+struct mlx5_irq_pool *
+mlx5_irq_table_get_comp_irq_pool(struct mlx5_core_dev *dev);
 int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table);
 int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table);
 struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev);
@@ -38,7 +41,6 @@ struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq);
 int mlx5_irq_get_index(struct mlx5_irq *irq);
 int mlx5_irq_get_irq(const struct mlx5_irq *irq);
 
-struct mlx5_irq_pool;
 #ifdef CONFIG_MLX5_SF
 struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
 						    struct cpumask *used_cpus, u16 vecidx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 972e8e9df585..9bc9bd83c232 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -291,7 +291,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function)
 static int alloc_system_page(struct mlx5_core_dev *dev, u32 function)
 {
 	struct device *device = mlx5_core_dma_dev(dev);
-	int nid = dev_to_node(device);
+	int nid = dev->priv.numa_node;
 	struct page *page;
 	u64 zero_addr = 1;
 	u64 addr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 7db9cab9bedf..40024cfa3099 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -148,7 +148,7 @@ out:
  * Free the IRQ and other resources such as rmap from the system.
  * BUT doesn't free or remove reference from mlx5.
  * This function is very important for the shutdown flow, where we need to
- * cleanup system resoruces but keep mlx5 objects alive,
+ * cleanup system resources but keep mlx5 objects alive,
  * see mlx5_irq_table_free_irqs().
  */
 static void mlx5_system_free_irq(struct mlx5_irq *irq)
@@ -378,6 +378,11 @@ int mlx5_irq_get_index(struct mlx5_irq *irq)
 	return irq->map.index;
 }
 
+struct mlx5_irq_pool *mlx5_irq_get_pool(struct mlx5_irq *irq)
+{
+	return irq->pool;
+}
+
 /* irq_pool API */
 
 /* requesting an irq from a given pool according to given index */
@@ -405,18 +410,20 @@ static struct mlx5_irq_pool *sf_ctrl_irq_pool_get(struct mlx5_irq_table *irq_tab
 	return irq_table->sf_ctrl_pool;
 }
 
-static struct mlx5_irq_pool *sf_irq_pool_get(struct mlx5_irq_table *irq_table)
+static struct mlx5_irq_pool *
+sf_comp_irq_pool_get(struct mlx5_irq_table *irq_table)
 {
 	return irq_table->sf_comp_pool;
 }
 
-struct mlx5_irq_pool *mlx5_irq_pool_get(struct mlx5_core_dev *dev)
+struct mlx5_irq_pool *
+mlx5_irq_table_get_comp_irq_pool(struct mlx5_core_dev *dev)
 {
 	struct mlx5_irq_table *irq_table = mlx5_irq_table_get(dev);
 	struct mlx5_irq_pool *pool = NULL;
 
 	if (mlx5_core_is_sf(dev))
-		pool = sf_irq_pool_get(irq_table);
+		pool = sf_comp_irq_pool_get(irq_table);
 
 	/* In some configs, there won't be a pool of SFs IRQs. Hence, returning
 	 * the PF IRQs pool in case the SF pool doesn't exist.
@@ -572,7 +579,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name,
 	pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ;
 	pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ;
 	mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d",
-		      name, size, start);
+		      name ? name : "mlx5_pcif_pool", size, start);
 	return pool;
 }
 
@@ -581,7 +588,7 @@ static void irq_pool_free(struct mlx5_irq_pool *pool)
 	struct mlx5_irq *irq;
 	unsigned long index;
 
-	/* There are cases in which we are destrying the irq_table before
+	/* There are cases in which we are destroying the irq_table before
 	 * freeing all the IRQs, fast teardown for example. Hence, free the irqs
 	 * which might not have been freed.
 	 */
@@ -610,7 +617,7 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pcif_vec,
 	if (!mlx5_sf_max_functions(dev))
 		return 0;
 	if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) {
-		mlx5_core_dbg(dev, "Not enught IRQs for SFs. SF may run at lower performance\n");
+		mlx5_core_dbg(dev, "Not enough IRQs for SFs. SF may run at lower performance\n");
 		return 0;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
index c4d377f8df30..cc064425fe16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
@@ -28,7 +28,6 @@ struct mlx5_irq_pool {
 	struct mlx5_core_dev *dev;
 };
 
-struct mlx5_irq_pool *mlx5_irq_pool_get(struct mlx5_core_dev *dev);
 static inline bool mlx5_irq_pool_is_sf_pool(struct mlx5_irq_pool *pool)
 {
 	return !strncmp("mlx5_sf", pool->name, strlen("mlx5_sf"));
@@ -40,5 +39,6 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 int mlx5_irq_get_locked(struct mlx5_irq *irq);
 int mlx5_irq_read_locked(struct mlx5_irq *irq);
 int mlx5_irq_put(struct mlx5_irq *irq);
+struct mlx5_irq_pool *mlx5_irq_get_pool(struct mlx5_irq *irq);
 
 #endif /* __PCI_IRQ_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 50931584132b..549f1066d2a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -196,7 +196,6 @@ void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
 	if (ps == MLX5_PORT_UP)
 		mlx5_set_port_admin_status(dev, MLX5_PORT_UP);
 }
-EXPORT_SYMBOL_GPL(mlx5_toggle_port_link);
 
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status)
@@ -210,7 +209,6 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PAOS, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_admin_status);
 
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status)
@@ -227,7 +225,6 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 	*status = MLX5_GET(paos_reg, out, admin_status);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status);
 
 static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu,
 				u16 *max_mtu, u16 *oper_mtu, u8 port)
@@ -257,7 +254,6 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				   sizeof(out), MLX5_REG_PMTU, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_mtu);
 
 void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu,
 			     u8 port)
@@ -447,7 +443,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 
 	return mlx5_query_mcia(dev, &query, data);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_module_eeprom);
 
 int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
 				     struct mlx5_module_eeprom_query_params *params,
@@ -467,7 +462,6 @@ int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
 
 	return mlx5_query_mcia(dev, params, data);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_module_eeprom_by_page);
 
 static int mlx5_query_port_pvlc(struct mlx5_core_dev *dev, u32 *pvlc,
 				int pvlc_size,  u8 local_port)
@@ -518,7 +512,6 @@ int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PFCC, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_pause);
 
 int mlx5_query_port_pause(struct mlx5_core_dev *dev,
 			  u32 *rx_pause, u32 *tx_pause)
@@ -538,7 +531,6 @@ int mlx5_query_port_pause(struct mlx5_core_dev *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_pause);
 
 int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
 				  u16 stall_critical_watermark,
@@ -597,7 +589,6 @@ int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PFCC, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_pfc);
 
 int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 {
@@ -616,7 +607,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_pfc);
 
 int mlx5_max_tc(struct mlx5_core_dev *mdev)
 {
@@ -667,7 +657,6 @@ int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_prio_tc);
 
 int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
 			    u8 prio, u8 *tc)
@@ -689,7 +678,6 @@ int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc);
 
 static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 				   int inlen)
@@ -728,7 +716,6 @@ int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group)
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_tc_group);
 
 int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
 			     u8 tc, u8 *tc_group)
@@ -749,7 +736,6 @@ int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_tc_group);
 
 int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw)
 {
@@ -763,7 +749,6 @@ int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw)
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc);
 
 int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
 				u8 tc, u8 *bw_pct)
@@ -784,7 +769,6 @@ int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_tc_bw_alloc);
 
 int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 				    u8 *max_bw_value,
@@ -808,7 +792,6 @@ int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_modify_port_ets_rate_limit);
 
 int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 				   u8 *max_bw_value,
@@ -834,7 +817,6 @@ int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit);
 
 int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode)
 {
@@ -845,7 +827,6 @@ int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode)
 	MLX5_SET(set_wol_rol_in, in, wol_mode, wol_mode);
 	return mlx5_cmd_exec_in(mdev, set_wol_rol, in);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_wol);
 
 int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 {
@@ -860,7 +841,6 @@ int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_wol);
 
 int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen)
 {
@@ -1058,53 +1038,57 @@ out:
 }
 
 /* speed in units of 1Mb */
-static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = {
-	[MLX5E_1000BASE_CX_SGMII] = 1000,
-	[MLX5E_1000BASE_KX]       = 1000,
-	[MLX5E_10GBASE_CX4]       = 10000,
-	[MLX5E_10GBASE_KX4]       = 10000,
-	[MLX5E_10GBASE_KR]        = 10000,
-	[MLX5E_20GBASE_KR2]       = 20000,
-	[MLX5E_40GBASE_CR4]       = 40000,
-	[MLX5E_40GBASE_KR4]       = 40000,
-	[MLX5E_56GBASE_R4]        = 56000,
-	[MLX5E_10GBASE_CR]        = 10000,
-	[MLX5E_10GBASE_SR]        = 10000,
-	[MLX5E_10GBASE_ER]        = 10000,
-	[MLX5E_40GBASE_SR4]       = 40000,
-	[MLX5E_40GBASE_LR4]       = 40000,
-	[MLX5E_50GBASE_SR2]       = 50000,
-	[MLX5E_100GBASE_CR4]      = 100000,
-	[MLX5E_100GBASE_SR4]      = 100000,
-	[MLX5E_100GBASE_KR4]      = 100000,
-	[MLX5E_100GBASE_LR4]      = 100000,
-	[MLX5E_100BASE_TX]        = 100,
-	[MLX5E_1000BASE_T]        = 1000,
-	[MLX5E_10GBASE_T]         = 10000,
-	[MLX5E_25GBASE_CR]        = 25000,
-	[MLX5E_25GBASE_KR]        = 25000,
-	[MLX5E_25GBASE_SR]        = 25000,
-	[MLX5E_50GBASE_CR2]       = 50000,
-	[MLX5E_50GBASE_KR2]       = 50000,
+static const struct mlx5_link_info mlx5e_link_info[MLX5E_LINK_MODES_NUMBER] = {
+	[MLX5E_1000BASE_CX_SGMII]	= {.speed = 1000, .lanes = 1},
+	[MLX5E_1000BASE_KX]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_10GBASE_CX4]		= {.speed = 10000, .lanes = 4},
+	[MLX5E_10GBASE_KX4]		= {.speed = 10000, .lanes = 4},
+	[MLX5E_10GBASE_KR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_20GBASE_KR2]		= {.speed = 20000, .lanes = 2},
+	[MLX5E_40GBASE_CR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_40GBASE_KR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_56GBASE_R4]		= {.speed = 56000, .lanes = 4},
+	[MLX5E_10GBASE_CR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_10GBASE_SR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_10GBASE_ER]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_40GBASE_SR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_40GBASE_LR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_50GBASE_SR2]		= {.speed = 50000, .lanes = 2},
+	[MLX5E_100GBASE_CR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_SR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_KR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_LR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100BASE_TX]		= {.speed = 100, .lanes = 1},
+	[MLX5E_1000BASE_T]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_10GBASE_T]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_25GBASE_CR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_25GBASE_KR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_25GBASE_SR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_50GBASE_CR2]		= {.speed = 50000, .lanes = 2},
+	[MLX5E_50GBASE_KR2]		= {.speed = 50000, .lanes = 2},
 };
 
-static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
-	[MLX5E_SGMII_100M] = 100,
-	[MLX5E_1000BASE_X_SGMII] = 1000,
-	[MLX5E_5GBASE_R] = 5000,
-	[MLX5E_10GBASE_XFI_XAUI_1] = 10000,
-	[MLX5E_40GBASE_XLAUI_4_XLPPI_4] = 40000,
-	[MLX5E_25GAUI_1_25GBASE_CR_KR] = 25000,
-	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = 50000,
-	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR] = 50000,
-	[MLX5E_CAUI_4_100GBASE_CR4_KR4] = 100000,
-	[MLX5E_100GAUI_2_100GBASE_CR2_KR2] = 100000,
-	[MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000,
-	[MLX5E_400GAUI_8_400GBASE_CR8] = 400000,
-	[MLX5E_100GAUI_1_100GBASE_CR_KR] = 100000,
-	[MLX5E_200GAUI_2_200GBASE_CR2_KR2] = 200000,
-	[MLX5E_400GAUI_4_400GBASE_CR4_KR4] = 400000,
-	[MLX5E_800GAUI_8_800GBASE_CR8_KR8] = 800000,
+static const struct mlx5_link_info
+mlx5e_ext_link_info[MLX5E_EXT_LINK_MODES_NUMBER] = {
+	[MLX5E_SGMII_100M]			= {.speed = 100, .lanes = 1},
+	[MLX5E_1000BASE_X_SGMII]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_5GBASE_R]			= {.speed = 5000, .lanes = 1},
+	[MLX5E_10GBASE_XFI_XAUI_1]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_40GBASE_XLAUI_4_XLPPI_4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_25GAUI_1_25GBASE_CR_KR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2]	= {.speed = 50000, .lanes = 2},
+	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= {.speed = 50000, .lanes = 1},
+	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GAUI_2_100GBASE_CR2_KR2]	= {.speed = 100000, .lanes = 2},
+	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= {.speed = 200000, .lanes = 4},
+	[MLX5E_400GAUI_8_400GBASE_CR8]		= {.speed = 400000, .lanes = 8},
+	[MLX5E_100GAUI_1_100GBASE_CR_KR]	= {.speed = 100000, .lanes = 1},
+	[MLX5E_200GAUI_2_200GBASE_CR2_KR2]	= {.speed = 200000, .lanes = 2},
+	[MLX5E_400GAUI_4_400GBASE_CR4_KR4]	= {.speed = 400000, .lanes = 4},
+	[MLX5E_800GAUI_8_800GBASE_CR8_KR8]	= {.speed = 800000, .lanes = 8},
+	[MLX5E_200GAUI_1_200GBASE_CR1_KR1]	= {.speed = 200000, .lanes = 1},
+	[MLX5E_400GAUI_2_400GBASE_CR2_KR2]	= {.speed = 400000, .lanes = 2},
+	[MLX5E_800GAUI_4_800GBASE_CR4_KR4]	= {.speed = 800000, .lanes = 4},
 };
 
 int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
@@ -1142,54 +1126,61 @@ bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev)
 	return !!eproto.cap;
 }
 
-static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
-				     const u32 **arr, u32 *size,
-				     bool force_legacy)
+static void mlx5e_port_get_link_mode_info_arr(struct mlx5_core_dev *mdev,
+					      const struct mlx5_link_info **arr,
+					      u32 *size,
+					      bool force_legacy)
 {
 	bool ext = force_legacy ? false : mlx5_ptys_ext_supported(mdev);
 
-	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
-		      ARRAY_SIZE(mlx5e_link_speed);
-	*arr  = ext ? mlx5e_ext_link_speed : mlx5e_link_speed;
+	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_info) :
+		      ARRAY_SIZE(mlx5e_link_info);
+	*arr  = ext ? mlx5e_ext_link_info : mlx5e_link_info;
 }
 
-u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
-			 bool force_legacy)
+const struct mlx5_link_info *mlx5_port_ptys2info(struct mlx5_core_dev *mdev,
+						 u32 eth_proto_oper,
+						 bool force_legacy)
 {
 	unsigned long temp = eth_proto_oper;
-	const u32 *table;
-	u32 speed = 0;
+	const struct mlx5_link_info *table;
 	u32 max_size;
 	int i;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size,
+					  force_legacy);
 	i = find_first_bit(&temp, max_size);
 	if (i < max_size)
-		speed = table[i];
-	return speed;
+		return &table[i];
+
+	return NULL;
 }
 
-u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
-			      bool force_legacy)
+u32 mlx5_port_info2linkmodes(struct mlx5_core_dev *mdev,
+			     struct mlx5_link_info *info,
+			     bool force_legacy)
 {
+	const struct mlx5_link_info *table;
 	u32 link_modes = 0;
-	const u32 *table;
 	u32 max_size;
 	int i;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size,
+					  force_legacy);
 	for (i = 0; i < max_size; ++i) {
-		if (table[i] == speed)
-			link_modes |= MLX5E_PROT_MASK(i);
+		if (table[i].speed == info->speed) {
+			if (!info->lanes || table[i].lanes == info->lanes)
+				link_modes |= MLX5E_PROT_MASK(i);
+		}
 	}
 	return link_modes;
 }
 
 int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
+	const struct mlx5_link_info *table;
 	struct mlx5_port_eth_proto eproto;
 	u32 max_speed = 0;
-	const u32 *table;
 	u32 max_size;
 	bool ext;
 	int err;
@@ -1200,10 +1191,10 @@ int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	if (err)
 		return err;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, false);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size, false);
 	for (i = 0; i < max_size; ++i)
 		if (eproto.cap & MLX5E_PROT_MASK(i))
-			max_speed = max(max_speed, table[i]);
+			max_speed = max(max_speed, table[i].speed);
 
 	*speed = max_speed;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index a42f6cd99b74..5c552b71e371 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -118,8 +118,8 @@ static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *
 
 static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
 {
+	u8 mac[ETH_ALEN] = {};
 	union ib_gid gid;
-	u8 mac[ETH_ALEN];
 
 	mlx5_rdma_make_default_gid(dev, &gid);
 	return mlx5_core_roce_gid_set(dev, 0,
@@ -140,17 +140,17 @@ void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
 	mlx5_nic_vport_disable_roce(dev);
 }
 
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 {
 	int err;
 
 	if (!MLX5_CAP_GEN(dev, roce))
-		return;
+		return 0;
 
 	err = mlx5_nic_vport_enable_roce(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
-		return;
+		return err;
 	}
 
 	err = mlx5_rdma_add_roce_addr(dev);
@@ -165,10 +165,11 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 		goto del_roce_addr;
 	}
 
-	return;
+	return err;
 
 del_roce_addr:
 	mlx5_rdma_del_roce_addr(dev);
 disable_roce:
 	mlx5_nic_vport_disable_roce(dev);
+	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
index 750cff2a71a4..3d9e76c3d42f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -8,12 +8,12 @@
 
 #ifdef CONFIG_MLX5_ESWITCH
 
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
 void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 
-static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
 
 #endif /* CONFIG_MLX5_ESWITCH */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index e393391966e0..39a209b9b684 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -56,6 +56,8 @@ bool mlx5_qos_tsar_type_supported(struct mlx5_core_dev *dev, int type, u8 hierar
 		return cap & TSAR_TYPE_CAP_MASK_ROUND_ROBIN;
 	case TSAR_ELEMENT_TSAR_TYPE_ETS:
 		return cap & TSAR_TYPE_CAP_MASK_ETS;
+	case TSAR_ELEMENT_TSAR_TYPE_TC_ARB:
+		return cap & TSAR_TYPE_CAP_MASK_TC_ARB;
 	}
 
 	return false;
@@ -87,6 +89,8 @@ bool mlx5_qos_element_type_supported(struct mlx5_core_dev *dev, int type, u8 hie
 		return cap & ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
 	case SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP:
 		return cap & ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT:
+		return cap & ELEMENT_TYPE_CAP_MASK_RATE_LIMIT;
 	}
 
 	return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index a96be98be032..0864ba625c07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -257,6 +257,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 	return 0;
 
 esw_err:
+	mlx5_sf_function_id_erase(table, sf);
 	mlx5_sf_free(table, sf);
 	return err;
 }
@@ -284,7 +285,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_
 		NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported");
 		return -EOPNOTSUPP;
 	}
-	if (new_attr->pfnum != mlx5_get_dev_index(dev)) {
+	if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
index a897cdc60fdb..447ea3f8722c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
@@ -11,31 +11,29 @@
 /* This is the longest supported action sequence for FDB table:
  * DECAP, POP_VLAN, MODIFY, CTR, ASO, PUSH_VLAN, MODIFY, ENCAP, Term.
  */
-static const u32 action_order_arr[MLX5HWS_TABLE_TYPE_MAX][MLX5HWS_ACTION_TYP_MAX] = {
-	[MLX5HWS_TABLE_TYPE_FDB] = {
-		BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2),
-		BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
-		BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3),
-		BIT(MLX5HWS_ACTION_TYP_CTR),
-		BIT(MLX5HWS_ACTION_TYP_TAG),
-		BIT(MLX5HWS_ACTION_TYP_ASO_METER),
-		BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
-		BIT(MLX5HWS_ACTION_TYP_TBL) |
-		BIT(MLX5HWS_ACTION_TYP_VPORT) |
-		BIT(MLX5HWS_ACTION_TYP_DROP) |
-		BIT(MLX5HWS_ACTION_TYP_SAMPLER) |
-		BIT(MLX5HWS_ACTION_TYP_RANGE) |
-		BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY),
-		BIT(MLX5HWS_ACTION_TYP_LAST),
-	},
+static const u32 action_order_arr[MLX5HWS_ACTION_TYP_MAX] = {
+	BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2),
+	BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
+	BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3),
+	BIT(MLX5HWS_ACTION_TYP_CTR),
+	BIT(MLX5HWS_ACTION_TYP_TAG),
+	BIT(MLX5HWS_ACTION_TYP_ASO_METER),
+	BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
+	BIT(MLX5HWS_ACTION_TYP_TBL) |
+	BIT(MLX5HWS_ACTION_TYP_VPORT) |
+	BIT(MLX5HWS_ACTION_TYP_DROP) |
+	BIT(MLX5HWS_ACTION_TYP_SAMPLER) |
+	BIT(MLX5HWS_ACTION_TYP_RANGE) |
+	BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY),
+	BIT(MLX5HWS_ACTION_TYP_LAST),
 };
 
 static const char * const mlx5hws_action_type_str[] = {
@@ -74,6 +72,11 @@ enum mlx5hws_action_type mlx5hws_action_get_type(struct mlx5hws_action *action)
 	return action->type;
 }
 
+struct mlx5_core_dev *mlx5hws_action_get_dev(struct mlx5hws_action *action)
+{
+	return action->ctx->mdev;
+}
+
 static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 					 enum mlx5hws_context_shared_stc_type stc_type,
 					 u8 tbl_type)
@@ -83,8 +86,8 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 	int ret;
 
 	mutex_lock(&ctx->ctrl_lock);
-	if (ctx->common_res[tbl_type].shared_stc[stc_type]) {
-		ctx->common_res[tbl_type].shared_stc[stc_type]->refcount++;
+	if (ctx->common_res.shared_stc[stc_type]) {
+		ctx->common_res.shared_stc[stc_type]->refcount++;
 		mutex_unlock(&ctx->ctrl_lock);
 		return 0;
 	}
@@ -124,8 +127,8 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 		goto free_shared_stc;
 	}
 
-	ctx->common_res[tbl_type].shared_stc[stc_type] = shared_stc;
-	ctx->common_res[tbl_type].shared_stc[stc_type]->refcount = 1;
+	ctx->common_res.shared_stc[stc_type] = shared_stc;
+	ctx->common_res.shared_stc[stc_type]->refcount = 1;
 
 	mutex_unlock(&ctx->ctrl_lock);
 
@@ -178,16 +181,16 @@ static void hws_action_put_shared_stc(struct mlx5hws_action *action,
 	}
 
 	mutex_lock(&ctx->ctrl_lock);
-	if (--ctx->common_res[tbl_type].shared_stc[stc_type]->refcount) {
+	if (--ctx->common_res.shared_stc[stc_type]->refcount) {
 		mutex_unlock(&ctx->ctrl_lock);
 		return;
 	}
 
-	shared_stc = ctx->common_res[tbl_type].shared_stc[stc_type];
+	shared_stc = ctx->common_res.shared_stc[stc_type];
 
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &shared_stc->stc_chunk);
 	kfree(shared_stc);
-	ctx->common_res[tbl_type].shared_stc[stc_type] = NULL;
+	ctx->common_res.shared_stc[stc_type] = NULL;
 	mutex_unlock(&ctx->ctrl_lock);
 }
 
@@ -206,10 +209,10 @@ bool mlx5hws_action_check_combo(struct mlx5hws_context *ctx,
 				enum mlx5hws_action_type *user_actions,
 				enum mlx5hws_table_type table_type)
 {
-	const u32 *order_arr = action_order_arr[table_type];
+	const u32 *order_arr = action_order_arr;
+	bool valid_combo;
 	u8 order_idx = 0;
 	u8 user_idx = 0;
-	bool valid_combo;
 
 	if (table_type >= MLX5HWS_TABLE_TYPE_MAX) {
 		mlx5hws_err(ctx, "Invalid table_type %d", table_type);
@@ -240,6 +243,7 @@ hws_action_fixup_stc_attr(struct mlx5hws_context *ctx,
 			  enum mlx5hws_table_type table_type,
 			  bool is_mirror)
 {
+	struct mlx5hws_pool *pool;
 	bool use_fixup = false;
 	u32 fw_tbl_type;
 	u32 base_id;
@@ -255,13 +259,11 @@ hws_action_fixup_stc_attr(struct mlx5hws_context *ctx,
 			use_fixup = true;
 			break;
 		}
+		pool = stc_attr->ste_table.ste_pool;
 		if (!is_mirror)
-			base_id = mlx5hws_pool_chunk_get_base_id(stc_attr->ste_table.ste_pool,
-								 &stc_attr->ste_table.ste);
+			base_id = mlx5hws_pool_get_base_id(pool);
 		else
-			base_id =
-				mlx5hws_pool_chunk_get_base_mirror_id(stc_attr->ste_table.ste_pool,
-								      &stc_attr->ste_table.ste);
+			base_id = mlx5hws_pool_get_base_mirror_id(pool);
 
 		*fixup_stc_attr = *stc_attr;
 		fixup_stc_attr->ste_table.ste_obj_id = base_id;
@@ -321,8 +323,8 @@ int mlx5hws_action_alloc_single_stc(struct mlx5hws_context *ctx,
 __must_hold(&ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_stc_modify_attr cleanup_stc_attr = {0};
-	struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type];
 	struct mlx5hws_cmd_stc_modify_attr fixup_stc_attr = {0};
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	bool use_fixup;
 	u32 obj_0_id;
 	int ret;
@@ -339,7 +341,7 @@ __must_hold(&ctx->ctrl_lock)
 	if (!mlx5hws_context_cap_dynamic_reparse(ctx))
 		stc_attr->reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
 
-	obj_0_id = mlx5hws_pool_chunk_get_base_id(stc_pool, stc);
+	obj_0_id = mlx5hws_pool_get_base_id(stc_pool);
 
 	/* According to table/action limitation change the stc_attr */
 	use_fixup = hws_action_fixup_stc_attr(ctx, stc_attr, &fixup_stc_attr, table_type, false);
@@ -355,7 +357,7 @@ __must_hold(&ctx->ctrl_lock)
 	if (table_type == MLX5HWS_TABLE_TYPE_FDB) {
 		u32 obj_1_id;
 
-		obj_1_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, stc);
+		obj_1_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 
 		use_fixup = hws_action_fixup_stc_attr(ctx, stc_attr,
 						      &fixup_stc_attr,
@@ -387,19 +389,19 @@ void mlx5hws_action_free_single_stc(struct mlx5hws_context *ctx,
 				    struct mlx5hws_pool_chunk *stc)
 __must_hold(&ctx->ctrl_lock)
 {
-	struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type];
 	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	u32 obj_id;
 
 	/* Modify the STC not to point to an object */
 	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_DROP;
 	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 	stc_attr.stc_offset = stc->offset;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, stc);
+	obj_id = mlx5hws_pool_get_base_id(stc_pool);
 	mlx5hws_cmd_stc_modify(ctx->mdev, obj_id, &stc_attr);
 
 	if (table_type == MLX5HWS_TABLE_TYPE_FDB) {
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, stc);
+		obj_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 		mlx5hws_cmd_stc_modify(ctx->mdev, obj_id, &stc_attr);
 	}
 
@@ -473,6 +475,7 @@ static void hws_action_fill_stc_attr(struct mlx5hws_action *action,
 		break;
 	case MLX5HWS_ACTION_TYP_TBL:
 	case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+	case MLX5HWS_ACTION_TYP_SAMPLER:
 		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_FT;
 		attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 		attr->dest_table_id = obj_id;
@@ -561,7 +564,7 @@ hws_action_create_stcs(struct mlx5hws_action *action, u32 obj_id)
 	if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB) {
 		ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr,
 						      MLX5HWS_TABLE_TYPE_FDB,
-						      &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+						      &action->stc);
 		if (ret)
 			goto out_err;
 	}
@@ -585,7 +588,7 @@ hws_action_destroy_stcs(struct mlx5hws_action *action)
 
 	if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB)
 		mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB,
-					       &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+					       &action->stc);
 
 	mutex_unlock(&ctx->ctrl_lock);
 }
@@ -1187,14 +1190,15 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 				    struct mlx5hws_action_mh_pattern *pattern,
 				    u32 log_bulk_size)
 {
+	u16 num_actions, max_mh_actions = 0, hw_max_actions;
 	struct mlx5hws_context *ctx = action->ctx;
-	u16 num_actions, max_mh_actions = 0;
 	int i, ret, size_in_bytes;
 	u32 pat_id, arg_id = 0;
 	__be64 *new_pattern;
 	size_t pat_max_sz;
 
 	pat_max_sz = MLX5HWS_ARG_CHUNK_SIZE_MAX * MLX5HWS_ARG_DATA_SIZE;
+	hw_max_actions = pat_max_sz / MLX5HWS_MODIFY_ACTION_SIZE;
 	size_in_bytes = pat_max_sz * sizeof(__be64);
 	new_pattern = kcalloc(num_of_patterns, size_in_bytes, GFP_KERNEL);
 	if (!new_pattern)
@@ -1204,16 +1208,20 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 	for (i = 0; i < num_of_patterns; i++) {
 		size_t new_num_actions;
 		size_t cur_num_actions;
-		u32 nope_location;
+		u32 nop_locations;
 
 		cur_num_actions = pattern[i].sz / MLX5HWS_MODIFY_ACTION_SIZE;
 
-		mlx5hws_pat_calc_nope(pattern[i].data, cur_num_actions,
-				      pat_max_sz / MLX5HWS_MODIFY_ACTION_SIZE,
-				      &new_num_actions, &nope_location,
-				      &new_pattern[i * pat_max_sz]);
+		ret = mlx5hws_pat_calc_nop(pattern[i].data, cur_num_actions,
+					   hw_max_actions, &new_num_actions,
+					   &nop_locations,
+					   &new_pattern[i * pat_max_sz]);
+		if (ret) {
+			mlx5hws_err(ctx, "Too many actions after nop insertion\n");
+			goto free_new_pat;
+		}
 
-		action[i].modify_header.nope_locations = nope_location;
+		action[i].modify_header.nop_locations = nop_locations;
 		action[i].modify_header.num_of_actions = new_num_actions;
 
 		max_mh_actions = max(max_mh_actions, new_num_actions);
@@ -1260,7 +1268,7 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 				MLX5_GET(set_action_in, pattern[i].data, action_type);
 		} else {
 			/* Multiple modify actions require a pattern */
-			if (unlikely(action[i].modify_header.nope_locations)) {
+			if (unlikely(action[i].modify_header.nop_locations)) {
 				size_t pattern_sz;
 
 				pattern_sz = action[i].modify_header.num_of_actions *
@@ -1362,8 +1370,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
 	struct mlx5hws_cmd_forward_tbl *fw_island;
 	struct mlx5hws_action *action;
-	u32 i /*, packet_reformat_id*/;
-	int ret;
+	int ret, last_dest_idx = -1;
+	u32 i;
 
 	if (num_dest <= 1) {
 		mlx5hws_err(ctx, "Action must have multiple dests\n");
@@ -1393,11 +1401,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 			dest_list[i].destination_id = dests[i].dest->dest_obj.obj_id;
 			fte_attr.action_flags |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 			fte_attr.ignore_flow_level = ignore_flow_level;
-			/* ToDo: In SW steering we have a handling of 'go to WIRE'
-			 * destination here by upper layer setting 'is_wire_ft' flag
-			 * if the destination is wire.
-			 * This is because uplink should be last dest in the list.
-			 */
+			if (dests[i].is_wire_ft)
+				last_dest_idx = i;
 			break;
 		case MLX5HWS_ACTION_TYP_VPORT:
 			dest_list[i].destination_type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
@@ -1421,6 +1426,9 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 		}
 	}
 
+	if (last_dest_idx != -1)
+		swap(dest_list[last_dest_idx], dest_list[num_dest - 1]);
+
 	fte_attr.dests_num = num_dest;
 	fte_attr.dests = dest_list;
 
@@ -1576,17 +1584,15 @@ hws_action_create_dest_match_range_definer(struct mlx5hws_context *ctx)
 	return definer;
 }
 
-static struct mlx5hws_matcher_action_ste *
+static struct mlx5hws_range_action_table *
 hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 					 struct mlx5hws_definer *definer,
 					 u32 miss_ft_id)
 {
 	struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0};
-	struct mlx5hws_action_default_stc *default_stc;
-	struct mlx5hws_matcher_action_ste *table_ste;
+	struct mlx5hws_range_action_table *table_ste;
 	struct mlx5hws_pool_attr pool_attr = {0};
 	struct mlx5hws_pool *ste_pool, *stc_pool;
-	struct mlx5hws_pool_chunk *ste;
 	u32 *rtc_0_id, *rtc_1_id;
 	u32 obj_id;
 	int ret;
@@ -1605,7 +1611,6 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 
 	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
 	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL;
 	pool_attr.alloc_log_sz = 1;
 	table_ste->pool = mlx5hws_pool_create(ctx, &pool_attr);
 	if (!table_ste->pool) {
@@ -1617,8 +1622,6 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	rtc_0_id = &table_ste->rtc_0_id;
 	rtc_1_id = &table_ste->rtc_1_id;
 	ste_pool = table_ste->pool;
-	ste = &table_ste->ste;
-	ste->order = 1;
 
 	rtc_attr.log_size = 0;
 	rtc_attr.log_depth = 0;
@@ -1630,18 +1633,16 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	rtc_attr.fw_gen_wqe = true;
 	rtc_attr.is_scnd_range = true;
 
-	obj_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+	obj_id = mlx5hws_pool_get_base_id(ste_pool);
 
 	rtc_attr.pd = ctx->pd_num;
 	rtc_attr.ste_base = obj_id;
-	rtc_attr.ste_offset = ste->offset;
 	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, false);
 
 	/* STC is a single resource (obj_id), use any STC for the ID */
-	stc_pool = ctx->stc_pool[MLX5HWS_TABLE_TYPE_FDB];
-	default_stc = ctx->common_res[MLX5HWS_TABLE_TYPE_FDB].default_stc;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
+	stc_pool = ctx->stc_pool;
+	obj_id = mlx5hws_pool_get_base_id(stc_pool);
 	rtc_attr.stc_base = obj_id;
 
 	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_0_id);
@@ -1651,11 +1652,11 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	}
 
 	/* Create mirror RTC */
-	obj_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+	obj_id = mlx5hws_pool_get_base_mirror_id(ste_pool);
 	rtc_attr.ste_base = obj_id;
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, true);
 
-	obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, &default_stc->default_hit);
+	obj_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 	rtc_attr.stc_base = obj_id;
 
 	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_1_id);
@@ -1678,9 +1679,9 @@ free_ste:
 	return NULL;
 }
 
-static void
-hws_action_destroy_dest_match_range_table(struct mlx5hws_context *ctx,
-					  struct mlx5hws_matcher_action_ste *table_ste)
+static void hws_action_destroy_dest_match_range_table(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_range_action_table *table_ste)
 {
 	mutex_lock(&ctx->ctrl_lock);
 
@@ -1692,12 +1693,11 @@ hws_action_destroy_dest_match_range_table(struct mlx5hws_context *ctx,
 	mutex_unlock(&ctx->ctrl_lock);
 }
 
-static int
-hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
-					      struct mlx5hws_matcher_action_ste *table_ste,
-					      struct mlx5hws_action *hit_ft_action,
-					      struct mlx5hws_definer *range_definer,
-					      u32 min, u32 max)
+static int hws_action_create_dest_match_range_fill_table(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_range_action_table *table_ste,
+	struct mlx5hws_action *hit_ft_action,
+	struct mlx5hws_definer *range_definer, u32 min, u32 max)
 {
 	struct mlx5hws_wqe_gta_data_seg_ste match_wqe_data = {0};
 	struct mlx5hws_wqe_gta_data_seg_ste range_wqe_data = {0};
@@ -1731,7 +1731,7 @@ hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
 	ste_attr.used_id_rtc_0 = &used_rtc_0_id;
 	ste_attr.used_id_rtc_1 = &used_rtc_1_id;
 
-	common_res = &ctx->common_res[MLX5HWS_TABLE_TYPE_FDB];
+	common_res = &ctx->common_res;
 
 	/* init an empty match STE which will always hit */
 	ste_attr.wqe_ctrl = &wqe_ctrl;
@@ -1750,7 +1750,7 @@ hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
 	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_CTRL] |=
 		htonl(MLX5HWS_ACTION_STC_IDX_LAST_COMBO2 << 29);
 	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_HIT] =
-		htonl(hit_ft_action->stc[MLX5HWS_TABLE_TYPE_FDB].offset);
+		htonl(hit_ft_action->stc.offset);
 
 	wqe_data_arr = (__force __be32 *)&range_wqe_data;
 
@@ -1793,7 +1793,7 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
 				       u32 min, u32 max, u32 flags)
 {
 	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
-	struct mlx5hws_matcher_action_ste *table_ste;
+	struct mlx5hws_range_action_table *table_ste;
 	struct mlx5hws_action *hit_ft_action;
 	struct mlx5hws_definer *definer;
 	struct mlx5hws_action *action;
@@ -1838,12 +1838,11 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
 	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
 	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
-	stc_attr.ste_table.ste = table_ste->ste;
 	stc_attr.ste_table.ste_pool = table_ste->pool;
 	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
 
 	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, MLX5HWS_TABLE_TYPE_FDB,
-					      &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+					      &action->stc);
 	if (ret)
 		goto error_unlock;
 
@@ -1875,7 +1874,50 @@ struct mlx5hws_action *
 mlx5hws_action_create_flow_sampler(struct mlx5hws_context *ctx,
 				   u32 sampler_id, u32 flags)
 {
-	mlx5hws_err(ctx, "Flow sampler action - unsupported\n");
+	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
+	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
+	struct mlx5hws_cmd_forward_tbl *fw_island;
+	struct mlx5hws_cmd_set_fte_dest dest;
+	struct mlx5hws_action *action;
+	int ret;
+
+	if (flags != (MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED)) {
+		mlx5hws_err(ctx, "Unsupported flags for flow sampler\n");
+		return NULL;
+	}
+
+	ft_attr.type = FS_FT_FDB;
+	ft_attr.level = ctx->caps->fdb_ft.max_level - 1;
+
+	dest.destination_type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
+	dest.destination_id = sampler_id;
+
+	fte_attr.dests_num = 1;
+	fte_attr.dests = &dest;
+	fte_attr.action_flags = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	fte_attr.ignore_flow_level = 1;
+
+	fw_island = mlx5hws_cmd_forward_tbl_create(ctx->mdev, &ft_attr, &fte_attr);
+	if (!fw_island)
+		return NULL;
+
+	action = hws_action_create_generic(ctx, flags,
+					   MLX5HWS_ACTION_TYP_SAMPLER);
+	if (!action)
+		goto destroy_fw_island;
+
+	ret = hws_action_create_stcs(action, fw_island->ft_id);
+	if (ret)
+		goto free_action;
+
+	action->flow_sampler.fw_island = fw_island;
+
+	return action;
+
+free_action:
+	kfree(action);
+destroy_fw_island:
+	mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, fw_island);
 	return NULL;
 }
 
@@ -1914,6 +1956,11 @@ static void hws_action_destroy_hws(struct mlx5hws_action *action)
 		}
 		kfree(action->dest_array.dest_list);
 		break;
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		hws_action_destroy_stcs(action);
+		mlx5hws_cmd_forward_tbl_destroy(action->ctx->mdev,
+						action->flow_sampler.fw_island);
+		break;
 	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
 	case MLX5HWS_ACTION_TYP_MODIFY_HDR:
 		shared_arg = false;
@@ -1970,8 +2017,8 @@ __must_hold(&ctx->ctrl_lock)
 	struct mlx5hws_action_default_stc *default_stc;
 	int ret;
 
-	if (ctx->common_res[tbl_type].default_stc) {
-		ctx->common_res[tbl_type].default_stc->refcount++;
+	if (ctx->common_res.default_stc) {
+		ctx->common_res.default_stc->refcount++;
 		return 0;
 	}
 
@@ -2023,8 +2070,8 @@ __must_hold(&ctx->ctrl_lock)
 		goto free_nop_dw7;
 	}
 
-	ctx->common_res[tbl_type].default_stc = default_stc;
-	ctx->common_res[tbl_type].default_stc->refcount++;
+	ctx->common_res.default_stc = default_stc;
+	ctx->common_res.default_stc->refcount++;
 
 	return 0;
 
@@ -2046,9 +2093,7 @@ __must_hold(&ctx->ctrl_lock)
 {
 	struct mlx5hws_action_default_stc *default_stc;
 
-	default_stc = ctx->common_res[tbl_type].default_stc;
-
-	default_stc = ctx->common_res[tbl_type].default_stc;
+	default_stc = ctx->common_res.default_stc;
 	if (--default_stc->refcount)
 		return;
 
@@ -2058,28 +2103,30 @@ __must_hold(&ctx->ctrl_lock)
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw5);
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_ctr);
 	kfree(default_stc);
-	ctx->common_res[tbl_type].default_stc = NULL;
+	ctx->common_res.default_stc = NULL;
 }
 
 static void hws_action_modify_write(struct mlx5hws_send_engine *queue,
 				    u32 arg_idx,
 				    u8 *arg_data,
 				    u16 num_of_actions,
-				    u32 nope_locations)
+				    u32 nop_locations)
 {
 	u8 *new_arg_data = NULL;
 	int i, j;
 
-	if (unlikely(nope_locations)) {
+	if (unlikely(nop_locations)) {
 		new_arg_data = kcalloc(num_of_actions,
 				       MLX5HWS_MODIFY_ACTION_SIZE, GFP_KERNEL);
 		if (unlikely(!new_arg_data))
 			return;
 
-		for (i = 0, j = 0; i < num_of_actions; i++, j++) {
-			memcpy(&new_arg_data[j], arg_data, MLX5HWS_MODIFY_ACTION_SIZE);
-			if (BIT(i) & nope_locations)
+		for (i = 0, j = 0; j < num_of_actions; i++, j++) {
+			if (BIT(i) & nop_locations)
 				j++;
+			memcpy(&new_arg_data[j * MLX5HWS_MODIFY_ACTION_SIZE],
+			       &arg_data[i * MLX5HWS_MODIFY_ACTION_SIZE],
+			       MLX5HWS_MODIFY_ACTION_SIZE);
 		}
 	}
 
@@ -2150,8 +2197,7 @@ hws_action_apply_stc(struct mlx5hws_actions_apply_data *apply,
 {
 	struct mlx5hws_action *action = apply->rule_action[action_idx].action;
 
-	apply->wqe_ctrl->stc_ix[stc_idx] =
-		htonl(action->stc[apply->tbl_type].offset);
+	apply->wqe_ctrl->stc_ix[stc_idx] = htonl(action->stc.offset);
 }
 
 static void
@@ -2176,12 +2222,13 @@ hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply,
 	struct mlx5hws_action *action;
 	u32 arg_sz, arg_idx;
 	u8 *single_action;
+	u8 max_actions;
 	__be32 stc_idx;
 
 	rule_action = &apply->rule_action[setter->idx_double];
 	action = rule_action->action;
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2203,21 +2250,23 @@ hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply,
 
 		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] =
 			*(__be32 *)MLX5_ADDR_OF(set_action_in, single_action, data);
-	} else {
-		/* Argument offset multiple with number of args per these actions */
-		arg_sz = mlx5hws_arg_get_arg_size(action->modify_header.max_num_of_actions);
-		arg_idx = rule_action->modify_header.offset * arg_sz;
-
-		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
-
-		if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
-			apply->require_dep = 1;
-			hws_action_modify_write(apply->queue,
-						action->modify_header.arg_id + arg_idx,
-						rule_action->modify_header.data,
-						action->modify_header.num_of_actions,
-						action->modify_header.nope_locations);
-		}
+		return;
+	}
+
+	/* Argument offset multiple with number of args per these actions */
+	max_actions = action->modify_header.max_num_of_actions;
+	arg_sz = mlx5hws_arg_get_arg_size(max_actions);
+	arg_idx = rule_action->modify_header.offset * arg_sz;
+
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
+
+	if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
+		apply->require_dep = 1;
+		hws_action_modify_write(apply->queue,
+					action->modify_header.arg_id + arg_idx,
+					rule_action->modify_header.data,
+					action->modify_header.num_of_actions,
+					action->modify_header.nop_locations);
 	}
 }
 
@@ -2240,7 +2289,7 @@ hws_action_setter_insert_ptr(struct mlx5hws_actions_apply_data *apply,
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2272,7 +2321,7 @@ hws_action_setter_tnl_l3_to_l2(struct mlx5hws_actions_apply_data *apply,
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2434,6 +2483,7 @@ int mlx5hws_action_template_process(struct mlx5hws_action_template *at)
 		case MLX5HWS_ACTION_TYP_DROP:
 		case MLX5HWS_ACTION_TYP_TBL:
 		case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+		case MLX5HWS_ACTION_TYP_SAMPLER:
 		case MLX5HWS_ACTION_TYP_VPORT:
 		case MLX5HWS_ACTION_TYP_MISS:
 			/* Hit action */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
index e8f562c31826..55a079fdd08f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
@@ -70,12 +70,12 @@ struct mlx5hws_action_default_stc {
 	struct mlx5hws_pool_chunk nop_dw6;
 	struct mlx5hws_pool_chunk nop_dw7;
 	struct mlx5hws_pool_chunk default_hit;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_action_shared_stc {
 	struct mlx5hws_pool_chunk stc_chunk;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_actions_apply_data {
@@ -118,19 +118,25 @@ struct mlx5hws_action_template {
 	u8 only_term;
 };
 
+struct mlx5hws_range_action_table {
+	struct mlx5hws_pool *pool;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+};
+
 struct mlx5hws_action {
 	u8 type;
 	u8 flags;
 	struct mlx5hws_context *ctx;
 	union {
 		struct {
-			struct mlx5hws_pool_chunk stc[MLX5HWS_TABLE_TYPE_MAX];
+			struct mlx5hws_pool_chunk stc;
 			union {
 				struct {
 					u32 pat_id;
 					u32 arg_id;
 					__be64 single_action;
-					u32 nope_locations;
+					u32 nop_locations;
 					u8 num_of_patterns;
 					u8 single_action_type;
 					u8 num_of_actions;
@@ -166,6 +172,9 @@ struct mlx5hws_action {
 					struct mlx5hws_cmd_set_fte_dest *dest_list;
 				} dest_array;
 				struct {
+					struct mlx5hws_cmd_forward_tbl *fw_island;
+				} flow_sampler;
+				struct {
 					u8 type;
 					u8 start_anchor;
 					u8 end_anchor;
@@ -183,7 +192,7 @@ struct mlx5hws_action {
 					size_t size;
 				} remove_header;
 				struct {
-					struct mlx5hws_matcher_action_ste *table_ste;
+					struct mlx5hws_range_action_table *table_ste;
 					struct mlx5hws_action *hit_ft_action;
 					struct mlx5hws_definer *definer;
 				} range;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c
new file mode 100644
index 000000000000..5766a9c82f96
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c
@@ -0,0 +1,467 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#include "internal.h"
+
+static const char *
+hws_pool_opt_to_str(enum mlx5hws_pool_optimize opt)
+{
+	switch (opt) {
+	case MLX5HWS_POOL_OPTIMIZE_NONE:
+		return "rx-and-tx";
+	case MLX5HWS_POOL_OPTIMIZE_ORIG:
+		return "rx-only";
+	case MLX5HWS_POOL_OPTIMIZE_MIRROR:
+		return "tx-only";
+	default:
+		return "unknown";
+	}
+}
+
+static int
+hws_action_ste_table_create_pool(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_table *action_tbl,
+				 enum mlx5hws_pool_optimize opt, size_t log_sz)
+{
+	struct mlx5hws_pool_attr pool_attr = { 0 };
+
+	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
+	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
+	pool_attr.flags = MLX5HWS_POOL_FLAG_BUDDY;
+	pool_attr.opt_type = opt;
+	pool_attr.alloc_log_sz = log_sz;
+
+	action_tbl->pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!action_tbl->pool) {
+		mlx5hws_err(ctx, "Failed to allocate STE pool\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hws_action_ste_table_create_single_rtc(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_action_ste_table *action_tbl,
+	enum mlx5hws_pool_optimize opt, size_t log_sz, bool tx)
+{
+	struct mlx5hws_cmd_rtc_create_attr rtc_attr = { 0 };
+	u32 *rtc_id;
+
+	rtc_attr.log_depth = 0;
+	rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+	/* Action STEs use the default always hit definer. */
+	rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
+	rtc_attr.is_frst_jumbo = false;
+	rtc_attr.miss_ft_id = 0;
+	rtc_attr.pd = ctx->pd_num;
+	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
+
+	if (tx) {
+		rtc_attr.table_type = FS_FT_FDB_TX;
+		rtc_attr.ste_base =
+			mlx5hws_pool_get_base_mirror_id(action_tbl->pool);
+		rtc_attr.stc_base =
+			mlx5hws_pool_get_base_mirror_id(ctx->stc_pool);
+		rtc_attr.log_size =
+			opt == MLX5HWS_POOL_OPTIMIZE_ORIG ? 0 : log_sz;
+		rtc_id = &action_tbl->rtc_1_id;
+	} else {
+		rtc_attr.table_type = FS_FT_FDB_RX;
+		rtc_attr.ste_base = mlx5hws_pool_get_base_id(action_tbl->pool);
+		rtc_attr.stc_base = mlx5hws_pool_get_base_id(ctx->stc_pool);
+		rtc_attr.log_size =
+			opt == MLX5HWS_POOL_OPTIMIZE_MIRROR ? 0 : log_sz;
+		rtc_id = &action_tbl->rtc_0_id;
+	}
+
+	return mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_id);
+}
+
+static int
+hws_action_ste_table_create_rtcs(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_table *action_tbl,
+				 enum mlx5hws_pool_optimize opt, size_t log_sz)
+{
+	int err;
+
+	err = hws_action_ste_table_create_single_rtc(ctx, action_tbl, opt,
+						     log_sz, false);
+	if (err)
+		return err;
+
+	err = hws_action_ste_table_create_single_rtc(ctx, action_tbl, opt,
+						     log_sz, true);
+	if (err) {
+		mlx5hws_cmd_rtc_destroy(ctx->mdev, action_tbl->rtc_0_id);
+		return err;
+	}
+
+	return 0;
+}
+
+static void
+hws_action_ste_table_destroy_rtcs(struct mlx5hws_action_ste_table *action_tbl)
+{
+	mlx5hws_cmd_rtc_destroy(action_tbl->pool->ctx->mdev,
+				action_tbl->rtc_1_id);
+	mlx5hws_cmd_rtc_destroy(action_tbl->pool->ctx->mdev,
+				action_tbl->rtc_0_id);
+}
+
+static int
+hws_action_ste_table_create_stc(struct mlx5hws_context *ctx,
+				struct mlx5hws_action_ste_table *action_tbl)
+{
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = { 0 };
+
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
+	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+	stc_attr.ste_table.ste_pool = action_tbl->pool;
+	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
+
+	return mlx5hws_action_alloc_single_stc(ctx, &stc_attr,
+					       MLX5HWS_TABLE_TYPE_FDB,
+					       &action_tbl->stc);
+}
+
+static struct mlx5hws_action_ste_table *
+hws_action_ste_table_alloc(struct mlx5hws_action_ste_pool_element *parent_elem)
+{
+	enum mlx5hws_pool_optimize opt = parent_elem->opt;
+	struct mlx5hws_context *ctx = parent_elem->ctx;
+	struct mlx5hws_action_ste_table *action_tbl;
+	size_t log_sz;
+	int err;
+
+	log_sz = min(parent_elem->log_sz ?
+			     parent_elem->log_sz +
+				     MLX5HWS_ACTION_STE_TABLE_STEP_LOG_SZ :
+				   MLX5HWS_ACTION_STE_TABLE_INIT_LOG_SZ,
+		     MLX5HWS_ACTION_STE_TABLE_MAX_LOG_SZ);
+
+	action_tbl = kzalloc(sizeof(*action_tbl), GFP_KERNEL);
+	if (!action_tbl)
+		return ERR_PTR(-ENOMEM);
+
+	err = hws_action_ste_table_create_pool(ctx, action_tbl, opt, log_sz);
+	if (err)
+		goto free_tbl;
+
+	err = hws_action_ste_table_create_rtcs(ctx, action_tbl, opt, log_sz);
+	if (err)
+		goto destroy_pool;
+
+	err = hws_action_ste_table_create_stc(ctx, action_tbl);
+	if (err)
+		goto destroy_rtcs;
+
+	action_tbl->parent_elem = parent_elem;
+	INIT_LIST_HEAD(&action_tbl->list_node);
+	action_tbl->last_used = jiffies;
+	list_add(&action_tbl->list_node, &parent_elem->available);
+	parent_elem->log_sz = log_sz;
+
+	mlx5hws_dbg(ctx,
+		    "Allocated %s action STE table log_sz %zu; STEs (%d, %d); RTCs (%d, %d); STC %d\n",
+		    hws_pool_opt_to_str(opt), log_sz,
+		    mlx5hws_pool_get_base_id(action_tbl->pool),
+		    mlx5hws_pool_get_base_mirror_id(action_tbl->pool),
+		    action_tbl->rtc_0_id, action_tbl->rtc_1_id,
+		    action_tbl->stc.offset);
+
+	return action_tbl;
+
+destroy_rtcs:
+	hws_action_ste_table_destroy_rtcs(action_tbl);
+destroy_pool:
+	mlx5hws_pool_destroy(action_tbl->pool);
+free_tbl:
+	kfree(action_tbl);
+
+	return ERR_PTR(err);
+}
+
+static void
+hws_action_ste_table_destroy(struct mlx5hws_action_ste_table *action_tbl)
+{
+	struct mlx5hws_context *ctx = action_tbl->parent_elem->ctx;
+
+	mlx5hws_dbg(ctx,
+		    "Destroying %s action STE table: STEs (%d, %d); RTCs (%d, %d); STC %d\n",
+		    hws_pool_opt_to_str(action_tbl->parent_elem->opt),
+		    mlx5hws_pool_get_base_id(action_tbl->pool),
+		    mlx5hws_pool_get_base_mirror_id(action_tbl->pool),
+		    action_tbl->rtc_0_id, action_tbl->rtc_1_id,
+		    action_tbl->stc.offset);
+
+	mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB,
+				       &action_tbl->stc);
+	hws_action_ste_table_destroy_rtcs(action_tbl);
+	mlx5hws_pool_destroy(action_tbl->pool);
+
+	list_del(&action_tbl->list_node);
+	kfree(action_tbl);
+}
+
+static int
+hws_action_ste_pool_element_init(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_pool_element *elem,
+				 enum mlx5hws_pool_optimize opt)
+{
+	elem->ctx = ctx;
+	elem->opt = opt;
+	INIT_LIST_HEAD(&elem->available);
+	INIT_LIST_HEAD(&elem->full);
+
+	return 0;
+}
+
+static void hws_action_ste_pool_element_destroy(
+	struct mlx5hws_action_ste_pool_element *elem)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+
+	/* This should be empty, but attempt to free its elements anyway. */
+	list_for_each_entry_safe(action_tbl, p, &elem->full, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+
+	list_for_each_entry_safe(action_tbl, p, &elem->available, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+}
+
+static int hws_action_ste_pool_init(struct mlx5hws_context *ctx,
+				    struct mlx5hws_action_ste_pool *pool)
+{
+	enum mlx5hws_pool_optimize opt;
+	int err;
+
+	mutex_init(&pool->lock);
+
+	/* Rules which are added for both RX and TX must use the same action STE
+	 * indices for both. If we were to use a single table, then RX-only and
+	 * TX-only rules would waste the unused entries. Thus, we use separate
+	 * table sets for the three cases.
+	 */
+	for (opt = MLX5HWS_POOL_OPTIMIZE_NONE; opt < MLX5HWS_POOL_OPTIMIZE_MAX;
+	     opt++) {
+		err = hws_action_ste_pool_element_init(ctx, &pool->elems[opt],
+						       opt);
+		if (err)
+			goto destroy_elems;
+		pool->elems[opt].parent_pool = pool;
+	}
+
+	return 0;
+
+destroy_elems:
+	while (opt-- > MLX5HWS_POOL_OPTIMIZE_NONE)
+		hws_action_ste_pool_element_destroy(&pool->elems[opt]);
+
+	return err;
+}
+
+static void hws_action_ste_pool_destroy(struct mlx5hws_action_ste_pool *pool)
+{
+	int opt;
+
+	for (opt = MLX5HWS_POOL_OPTIMIZE_MAX - 1;
+	     opt >= MLX5HWS_POOL_OPTIMIZE_NONE; opt--)
+		hws_action_ste_pool_element_destroy(&pool->elems[opt]);
+}
+
+static void hws_action_ste_pool_element_collect_stale(
+	struct mlx5hws_action_ste_pool_element *elem, struct list_head *cleanup)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+	unsigned long expire_time, now;
+
+	expire_time = secs_to_jiffies(MLX5HWS_ACTION_STE_POOL_EXPIRE_SECONDS);
+	now = jiffies;
+
+	list_for_each_entry_safe(action_tbl, p, &elem->available, list_node) {
+		if (mlx5hws_pool_full(action_tbl->pool) &&
+		    time_before(action_tbl->last_used + expire_time, now))
+			list_move(&action_tbl->list_node, cleanup);
+	}
+}
+
+static void hws_action_ste_table_cleanup_list(struct list_head *cleanup)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+
+	list_for_each_entry_safe(action_tbl, p, cleanup, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+}
+
+static void hws_action_ste_pool_cleanup(struct work_struct *work)
+{
+	enum mlx5hws_pool_optimize opt;
+	struct mlx5hws_context *ctx;
+	LIST_HEAD(cleanup);
+	int i;
+
+	ctx = container_of(work, struct mlx5hws_context,
+			   action_ste_cleanup.work);
+
+	for (i = 0; i < ctx->queues; i++) {
+		struct mlx5hws_action_ste_pool *p = &ctx->action_ste_pool[i];
+
+		mutex_lock(&p->lock);
+		for (opt = MLX5HWS_POOL_OPTIMIZE_NONE;
+		     opt < MLX5HWS_POOL_OPTIMIZE_MAX; opt++)
+			hws_action_ste_pool_element_collect_stale(
+				&p->elems[opt], &cleanup);
+		mutex_unlock(&p->lock);
+	}
+
+	hws_action_ste_table_cleanup_list(&cleanup);
+
+	schedule_delayed_work(&ctx->action_ste_cleanup,
+			      secs_to_jiffies(
+				  MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS));
+}
+
+int mlx5hws_action_ste_pool_init(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_action_ste_pool *pool;
+	size_t queues = ctx->queues;
+	int i, err;
+
+	pool = kcalloc(queues, sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return -ENOMEM;
+
+	for (i = 0; i < queues; i++) {
+		err = hws_action_ste_pool_init(ctx, &pool[i]);
+		if (err)
+			goto free_pool;
+	}
+
+	ctx->action_ste_pool = pool;
+
+	INIT_DELAYED_WORK(&ctx->action_ste_cleanup,
+			  hws_action_ste_pool_cleanup);
+	schedule_delayed_work(
+		&ctx->action_ste_cleanup,
+		secs_to_jiffies(MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS));
+
+	return 0;
+
+free_pool:
+	while (i--)
+		hws_action_ste_pool_destroy(&pool[i]);
+	kfree(pool);
+
+	return err;
+}
+
+void mlx5hws_action_ste_pool_uninit(struct mlx5hws_context *ctx)
+{
+	size_t queues = ctx->queues;
+	int i;
+
+	cancel_delayed_work_sync(&ctx->action_ste_cleanup);
+
+	for (i = 0; i < queues; i++)
+		hws_action_ste_pool_destroy(&ctx->action_ste_pool[i]);
+
+	kfree(ctx->action_ste_pool);
+}
+
+static struct mlx5hws_action_ste_pool_element *
+hws_action_ste_choose_elem(struct mlx5hws_action_ste_pool *pool,
+			   bool skip_rx, bool skip_tx)
+{
+	if (skip_rx)
+		return &pool->elems[MLX5HWS_POOL_OPTIMIZE_MIRROR];
+
+	if (skip_tx)
+		return &pool->elems[MLX5HWS_POOL_OPTIMIZE_ORIG];
+
+	return &pool->elems[MLX5HWS_POOL_OPTIMIZE_NONE];
+}
+
+static int
+hws_action_ste_table_chunk_alloc(struct mlx5hws_action_ste_table *action_tbl,
+				 struct mlx5hws_action_ste_chunk *chunk)
+{
+	int err;
+
+	err = mlx5hws_pool_chunk_alloc(action_tbl->pool, &chunk->ste);
+	if (err)
+		return err;
+
+	chunk->action_tbl = action_tbl;
+	action_tbl->last_used = jiffies;
+
+	return 0;
+}
+
+int mlx5hws_action_ste_chunk_alloc(struct mlx5hws_action_ste_pool *pool,
+				   bool skip_rx, bool skip_tx,
+				   struct mlx5hws_action_ste_chunk *chunk)
+{
+	struct mlx5hws_action_ste_pool_element *elem;
+	struct mlx5hws_action_ste_table *action_tbl;
+	bool found;
+	int err;
+
+	if (skip_rx && skip_tx)
+		return -EINVAL;
+
+	mutex_lock(&pool->lock);
+
+	elem = hws_action_ste_choose_elem(pool, skip_rx, skip_tx);
+
+	mlx5hws_dbg(elem->ctx,
+		    "Allocating action STEs skip_rx %d skip_tx %d order %d\n",
+		    skip_rx, skip_tx, chunk->ste.order);
+
+	found = false;
+	list_for_each_entry(action_tbl, &elem->available, list_node) {
+		if (!hws_action_ste_table_chunk_alloc(action_tbl, chunk)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		action_tbl = hws_action_ste_table_alloc(elem);
+		if (IS_ERR(action_tbl)) {
+			err = PTR_ERR(action_tbl);
+			goto out;
+		}
+
+		err = hws_action_ste_table_chunk_alloc(action_tbl, chunk);
+		if (err)
+			goto out;
+	}
+
+	if (mlx5hws_pool_empty(action_tbl->pool))
+		list_move(&action_tbl->list_node, &elem->full);
+
+	err = 0;
+
+out:
+	mutex_unlock(&pool->lock);
+
+	return err;
+}
+
+void mlx5hws_action_ste_chunk_free(struct mlx5hws_action_ste_chunk *chunk)
+{
+	struct mutex *lock = &chunk->action_tbl->parent_elem->parent_pool->lock;
+
+	mlx5hws_dbg(chunk->action_tbl->pool->ctx,
+		    "Freeing action STEs offset %d order %d\n",
+		    chunk->ste.offset, chunk->ste.order);
+
+	mutex_lock(lock);
+	mlx5hws_pool_chunk_free(chunk->action_tbl->pool, &chunk->ste);
+	chunk->action_tbl->last_used = jiffies;
+	list_move(&chunk->action_tbl->list_node,
+		  &chunk->action_tbl->parent_elem->available);
+	mutex_unlock(lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h
new file mode 100644
index 000000000000..a8ba97359e31
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#ifndef ACTION_STE_POOL_H_
+#define ACTION_STE_POOL_H_
+
+#define MLX5HWS_ACTION_STE_TABLE_INIT_LOG_SZ 10
+#define MLX5HWS_ACTION_STE_TABLE_STEP_LOG_SZ 1
+#define MLX5HWS_ACTION_STE_TABLE_MAX_LOG_SZ 20
+
+#define MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS 300
+#define MLX5HWS_ACTION_STE_POOL_EXPIRE_SECONDS 300
+
+struct mlx5hws_action_ste_pool_element;
+
+struct mlx5hws_action_ste_table {
+	struct mlx5hws_action_ste_pool_element *parent_elem;
+	/* Wraps the RTC and STE range for this given action. */
+	struct mlx5hws_pool *pool;
+	/* Match STEs use this STC to jump to this pool's RTC. */
+	struct mlx5hws_pool_chunk stc;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+	struct list_head list_node;
+	unsigned long last_used;
+};
+
+struct mlx5hws_action_ste_pool_element {
+	struct mlx5hws_context *ctx;
+	struct mlx5hws_action_ste_pool *parent_pool;
+	size_t log_sz;  /* Size of the largest table so far. */
+	enum mlx5hws_pool_optimize opt;
+	struct list_head available;
+	struct list_head full;
+};
+
+/* Central repository of action STEs. The context contains one of these pools
+ * per queue.
+ */
+struct mlx5hws_action_ste_pool {
+	/* Protects the entire pool. We have one pool per queue and only one
+	 * operation can be active per rule at a given time. Thus this lock
+	 * protects solely against concurrent garbage collection and we expect
+	 * very little contention.
+	 */
+	struct mutex lock;
+	struct mlx5hws_action_ste_pool_element elems[MLX5HWS_POOL_OPTIMIZE_MAX];
+};
+
+/* A chunk of STEs and the table it was allocated from. Used by rules. */
+struct mlx5hws_action_ste_chunk {
+	struct mlx5hws_action_ste_table *action_tbl;
+	struct mlx5hws_pool_chunk ste;
+};
+
+int mlx5hws_action_ste_pool_init(struct mlx5hws_context *ctx);
+
+void mlx5hws_action_ste_pool_uninit(struct mlx5hws_context *ctx);
+
+/* Callers are expected to fill chunk->ste.order. On success, this function
+ * populates chunk->tbl and chunk->ste.offset.
+ */
+int mlx5hws_action_ste_chunk_alloc(struct mlx5hws_action_ste_pool *pool,
+				   bool skip_rx, bool skip_tx,
+				   struct mlx5hws_action_ste_chunk *chunk);
+
+void mlx5hws_action_ste_chunk_free(struct mlx5hws_action_ste_chunk *chunk);
+
+#endif /* ACTION_STE_POOL_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
index baacf662c0ab..9e057f808ea5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
@@ -46,10 +46,14 @@ static void hws_bwc_unlock_all_queues(struct mlx5hws_context *ctx)
 	}
 }
 
-static void hws_bwc_matcher_init_attr(struct mlx5hws_matcher_attr *attr,
+static void hws_bwc_matcher_init_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
 				      u32 priority,
-				      u8 size_log)
+				      u8 size_log,
+				      struct mlx5hws_matcher_attr *attr)
 {
+	struct mlx5hws_bwc_matcher *first_matcher =
+		bwc_matcher->complex_first_bwc_matcher;
+
 	memset(attr, 0, sizeof(*attr));
 
 	attr->priority = priority;
@@ -61,6 +65,9 @@ static void hws_bwc_matcher_init_attr(struct mlx5hws_matcher_attr *attr,
 	attr->rule.num_log = size_log;
 	attr->resizable = true;
 	attr->max_num_of_at_attach = MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM;
+
+	attr->isolated_matcher_end_ft_id =
+		first_matcher ? first_matcher->matcher->end_ft_id : 0;
 }
 
 int mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
@@ -83,20 +90,27 @@ int mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
 	for (i = 0; i < bwc_queues; i++)
 		INIT_LIST_HEAD(&bwc_matcher->rules[i]);
 
-	hws_bwc_matcher_init_attr(&attr,
+	hws_bwc_matcher_init_attr(bwc_matcher,
 				  priority,
-				  MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG);
+				  MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG,
+				  &attr);
 
 	bwc_matcher->priority = priority;
 	bwc_matcher->size_log = MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG;
 
+	bwc_matcher->size_of_at_array = MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM;
+	bwc_matcher->at = kcalloc(bwc_matcher->size_of_at_array,
+				  sizeof(*bwc_matcher->at), GFP_KERNEL);
+	if (!bwc_matcher->at)
+		goto free_bwc_matcher_rules;
+
 	/* create dummy action template */
 	bwc_matcher->at[0] =
 		mlx5hws_action_template_create(action_types ?
 					       action_types : init_action_types);
 	if (!bwc_matcher->at[0]) {
 		mlx5hws_err(table->ctx, "BWC matcher: failed creating action template\n");
-		goto free_bwc_matcher_rules;
+		goto free_bwc_matcher_at_array;
 	}
 
 	bwc_matcher->num_of_at = 1;
@@ -126,6 +140,8 @@ free_mt:
 	mlx5hws_match_template_destroy(bwc_matcher->mt);
 free_at:
 	mlx5hws_action_template_destroy(bwc_matcher->at[0]);
+free_bwc_matcher_at_array:
+	kfree(bwc_matcher->at);
 free_bwc_matcher_rules:
 	kfree(bwc_matcher->rules);
 err:
@@ -152,6 +168,9 @@ mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
 	if (!bwc_matcher)
 		return NULL;
 
+	atomic_set(&bwc_matcher->num_of_rules, 0);
+	atomic_set(&bwc_matcher->rehash_required, false);
+
 	/* Check if the required match params can be all matched
 	 * in single STE, otherwise complex matcher is needed.
 	 */
@@ -190,6 +209,7 @@ int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 
 	for (i = 0; i < bwc_matcher->num_of_at; i++)
 		mlx5hws_action_template_destroy(bwc_matcher->at[i]);
+	kfree(bwc_matcher->at);
 
 	mlx5hws_match_template_destroy(bwc_matcher->mt);
 	kfree(bwc_matcher->rules);
@@ -199,22 +219,29 @@ int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 
 int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	if (bwc_matcher->num_of_rules)
+	u32 num_of_rules = atomic_read(&bwc_matcher->num_of_rules);
+
+	if (num_of_rules)
 		mlx5hws_err(bwc_matcher->matcher->tbl->ctx,
 			    "BWC matcher destroy: matcher still has %d rules\n",
-			    bwc_matcher->num_of_rules);
+			    num_of_rules);
 
-	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+	if (bwc_matcher->complex)
+		mlx5hws_bwc_matcher_destroy_complex(bwc_matcher);
+	else
+		mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
 
 	kfree(bwc_matcher);
 	return 0;
 }
 
-static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
-			      u16 queue_id,
-			      u32 *pending_rules,
-			      bool drain)
+int mlx5hws_bwc_queue_poll(struct mlx5hws_context *ctx,
+			   u16 queue_id,
+			   u32 *pending_rules,
+			   bool drain)
 {
+	unsigned long timeout = jiffies +
+				secs_to_jiffies(MLX5HWS_BWC_POLLING_TIMEOUT);
 	struct mlx5hws_flow_op_result comp[MLX5HWS_BWC_MATCHER_REHASH_BURST_TH];
 	u16 burst_th = hws_bwc_get_burst_th(ctx, queue_id);
 	bool got_comp = *pending_rules >= burst_th;
@@ -250,6 +277,11 @@ static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
 		}
 
 		got_comp = !!ret;
+
+		if (unlikely(!got_comp && time_after(jiffies, timeout))) {
+			mlx5hws_err(ctx, "BWC poll error: polling queue %d - TIMEOUT\n", queue_id);
+			return -ETIMEDOUT;
+		}
 	}
 
 	return err;
@@ -309,16 +341,12 @@ static void hws_bwc_rule_list_add(struct mlx5hws_bwc_rule *bwc_rule, u16 idx)
 {
 	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
 
-	bwc_matcher->num_of_rules++;
 	bwc_rule->bwc_queue_idx = idx;
 	list_add(&bwc_rule->list_node, &bwc_matcher->rules[idx]);
 }
 
 static void hws_bwc_rule_list_remove(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
-
-	bwc_matcher->num_of_rules--;
 	list_del_init(&bwc_rule->list_node);
 }
 
@@ -334,22 +362,22 @@ hws_bwc_rule_destroy_hws_sync(struct mlx5hws_bwc_rule *bwc_rule,
 			      struct mlx5hws_rule_attr *rule_attr)
 {
 	struct mlx5hws_context *ctx = bwc_rule->bwc_matcher->matcher->tbl->ctx;
-	struct mlx5hws_flow_op_result completion;
+	u32 expected_completions = 1;
 	int ret;
 
 	ret = hws_bwc_rule_destroy_hws_async(bwc_rule, rule_attr);
 	if (unlikely(ret))
 		return ret;
 
-	do {
-		ret = mlx5hws_send_queue_poll(ctx, rule_attr->queue_id, &completion, 1);
-	} while (ret != 1);
+	ret = mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				     &expected_completions, true);
+	if (unlikely(ret))
+		return ret;
 
-	if (unlikely(completion.status != MLX5HWS_FLOW_OP_SUCCESS ||
-		     (bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED &&
-		      bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING))) {
-		mlx5hws_err(ctx, "Failed destroying BWC rule: completion %d, rule status %d\n",
-			    completion.status, bwc_rule->rule->status);
+	if (unlikely(bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED &&
+		     bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING)) {
+		mlx5hws_err(ctx, "Failed destroying BWC rule: rule status %d\n",
+			    bwc_rule->rule->status);
 		return -EINVAL;
 	}
 
@@ -372,6 +400,7 @@ int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule)
 	mutex_lock(queue_lock);
 
 	ret = hws_bwc_rule_destroy_hws_sync(bwc_rule, &attr);
+	atomic_dec(&bwc_matcher->num_of_rules);
 	hws_bwc_rule_list_remove(bwc_rule);
 
 	mutex_unlock(queue_lock);
@@ -381,9 +410,13 @@ int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule)
 
 int mlx5hws_bwc_rule_destroy(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	int ret;
+	bool is_complex = !!bwc_rule->bwc_matcher->complex;
+	int ret = 0;
 
-	ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
+	if (is_complex)
+		ret = mlx5hws_bwc_rule_destroy_complex(bwc_rule);
+	else
+		ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
 
 	mlx5hws_bwc_rule_free(bwc_rule);
 	return ret;
@@ -423,9 +456,8 @@ hws_bwc_rule_create_sync(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret))
 		return ret;
 
-	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
-
-	return ret;
+	return mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				      &expected_completions, true);
 }
 
 static int
@@ -446,7 +478,8 @@ hws_bwc_rule_update_sync(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret))
 		return ret;
 
-	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
+	ret = mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				     &expected_completions, true);
 	if (unlikely(ret))
 		mlx5hws_err(ctx, "Failed updating BWC rule (%d)\n", ret);
 
@@ -458,8 +491,10 @@ hws_bwc_matcher_size_maxed_out(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
 	struct mlx5hws_cmd_query_caps *caps = bwc_matcher->matcher->tbl->ctx->caps;
 
-	return bwc_matcher->size_log + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH >=
-	       caps->ste_alloc_log_max - 1;
+	/* check the match RTC size */
+	return (bwc_matcher->size_log + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH +
+		MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP) >
+	       (caps->ste_alloc_log_max - 1);
 }
 
 static bool
@@ -496,6 +531,23 @@ hws_bwc_matcher_extend_at(struct mlx5hws_bwc_matcher *bwc_matcher,
 			  struct mlx5hws_rule_action rule_actions[])
 {
 	enum mlx5hws_action_type action_types[MLX5HWS_BWC_MAX_ACTS];
+	void *p;
+
+	if (unlikely(bwc_matcher->num_of_at >= bwc_matcher->size_of_at_array)) {
+		if (bwc_matcher->size_of_at_array >= MLX5HWS_MATCHER_MAX_AT)
+			return -ENOMEM;
+		bwc_matcher->size_of_at_array *= 2;
+		p = krealloc(bwc_matcher->at,
+			     bwc_matcher->size_of_at_array *
+				     sizeof(*bwc_matcher->at),
+			     __GFP_ZERO | GFP_KERNEL);
+		if (!p) {
+			bwc_matcher->size_of_at_array /= 2;
+			return -ENOMEM;
+		}
+
+		bwc_matcher->at = p;
+	}
 
 	hws_bwc_rule_actions_to_action_types(rule_actions, action_types);
 
@@ -558,93 +610,79 @@ hws_bwc_matcher_find_at(struct mlx5hws_bwc_matcher *bwc_matcher,
 
 static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
+	bool move_error = false, poll_error = false, drain_error = false;
 	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
 	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
-	struct mlx5hws_bwc_rule **bwc_rules;
 	struct mlx5hws_rule_attr rule_attr;
-	u32 *pending_rules;
-	int i, j, ret = 0;
-	bool all_done;
-	u16 burst_th;
+	struct mlx5hws_bwc_rule *bwc_rule;
+	struct mlx5hws_send_engine *queue;
+	struct list_head *rules_list;
+	u32 pending_rules;
+	int i, ret = 0;
 
 	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
 
-	pending_rules = kcalloc(bwc_queues, sizeof(*pending_rules), GFP_KERNEL);
-	if (!pending_rules)
-		return -ENOMEM;
-
-	bwc_rules = kcalloc(bwc_queues, sizeof(*bwc_rules), GFP_KERNEL);
-	if (!bwc_rules) {
-		ret = -ENOMEM;
-		goto free_pending_rules;
-	}
-
 	for (i = 0; i < bwc_queues; i++) {
 		if (list_empty(&bwc_matcher->rules[i]))
-			bwc_rules[i] = NULL;
-		else
-			bwc_rules[i] = list_first_entry(&bwc_matcher->rules[i],
-							struct mlx5hws_bwc_rule,
-							list_node);
-	}
+			continue;
 
-	do {
-		all_done = true;
+		pending_rules = 0;
+		rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
+		rules_list = &bwc_matcher->rules[i];
 
-		for (i = 0; i < bwc_queues; i++) {
-			rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
-			burst_th = hws_bwc_get_burst_th(ctx, rule_attr.queue_id);
-
-			for (j = 0; j < burst_th && bwc_rules[i]; j++) {
-				rule_attr.burst = !!((j + 1) % burst_th);
-				ret = mlx5hws_matcher_resize_rule_move(bwc_matcher->matcher,
-								       bwc_rules[i]->rule,
-								       &rule_attr);
-				if (unlikely(ret)) {
-					mlx5hws_err(ctx,
-						    "Moving BWC rule failed during rehash (%d)\n",
-						    ret);
-					goto free_bwc_rules;
-				}
-
-				all_done = false;
-				pending_rules[i]++;
-				bwc_rules[i] = list_is_last(&bwc_rules[i]->list_node,
-							    &bwc_matcher->rules[i]) ?
-					       NULL : list_next_entry(bwc_rules[i], list_node);
+		list_for_each_entry(bwc_rule, rules_list, list_node) {
+			ret = mlx5hws_matcher_resize_rule_move(matcher,
+							       bwc_rule->rule,
+							       &rule_attr);
+			if (unlikely(ret && !move_error)) {
+				mlx5hws_err(ctx,
+					    "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				move_error = true;
+			}
 
-				ret = hws_bwc_queue_poll(ctx, rule_attr.queue_id,
-							 &pending_rules[i], false);
-				if (unlikely(ret))
-					goto free_bwc_rules;
+			pending_rules++;
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &pending_rules,
+						     false);
+			if (unlikely(ret && !poll_error)) {
+				mlx5hws_err(ctx,
+					    "Moving BWC rule: poll failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				poll_error = true;
 			}
 		}
-	} while (!all_done);
 
-	/* drain all the bwc queues */
-	for (i = 0; i < bwc_queues; i++) {
-		if (pending_rules[i]) {
-			u16 queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
-
-			mlx5hws_send_engine_flush_queue(&ctx->send_queue[queue_id]);
-			ret = hws_bwc_queue_poll(ctx, queue_id,
-						 &pending_rules[i], true);
-			if (unlikely(ret))
-				goto free_bwc_rules;
+		if (pending_rules) {
+			queue = &ctx->send_queue[rule_attr.queue_id];
+			mlx5hws_send_engine_flush_queue(queue);
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &pending_rules,
+						     true);
+			if (unlikely(ret && !drain_error)) {
+				mlx5hws_err(ctx,
+					    "Moving BWC rule: drain failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				drain_error = true;
+			}
 		}
 	}
 
-free_bwc_rules:
-	kfree(bwc_rules);
-free_pending_rules:
-	kfree(pending_rules);
+	if (move_error || poll_error || drain_error)
+		ret = -EINVAL;
 
 	return ret;
 }
 
 static int hws_bwc_matcher_move_all(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	return hws_bwc_matcher_move_all_simple(bwc_matcher);
+	if (!bwc_matcher->complex)
+		return hws_bwc_matcher_move_all_simple(bwc_matcher);
+
+	return mlx5hws_bwc_matcher_move_all_complex(bwc_matcher);
 }
 
 static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
@@ -655,9 +693,10 @@ static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
 	struct mlx5hws_matcher *new_matcher;
 	int ret;
 
-	hws_bwc_matcher_init_attr(&matcher_attr,
+	hws_bwc_matcher_init_attr(bwc_matcher,
 				  bwc_matcher->priority,
-				  bwc_matcher->size_log);
+				  bwc_matcher->size_log,
+				  &matcher_attr);
 
 	old_matcher = bwc_matcher->matcher;
 	new_matcher = mlx5hws_matcher_create(old_matcher->tbl,
@@ -677,15 +716,18 @@ static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
 	}
 
 	ret = hws_bwc_matcher_move_all(bwc_matcher);
-	if (ret) {
-		mlx5hws_err(ctx, "Rehash error: moving rules failed\n");
-		return -ENOMEM;
-	}
+	if (ret)
+		mlx5hws_err(ctx, "Rehash error: moving rules failed, attempting to remove the old matcher\n");
+
+	/* Error during rehash can't be rolled back.
+	 * The best option here is to allow the rehash to complete and remove
+	 * the old matcher - can't leave the matcher in the 'in_resize' state.
+	 */
 
 	bwc_matcher->matcher = new_matcher;
 	mlx5hws_matcher_destroy(old_matcher);
 
-	return 0;
+	return ret;
 }
 
 static int
@@ -702,9 +744,10 @@ hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
 
 	/* It is possible that other rule has already performed rehash.
 	 * Need to check again if we really need rehash.
-	 * If the reason for rehash was size, but not any more - skip rehash.
 	 */
-	if (!hws_bwc_matcher_rehash_size_needed(bwc_matcher, bwc_matcher->num_of_rules))
+	if (!atomic_read(&bwc_matcher->rehash_required) &&
+	    !hws_bwc_matcher_rehash_size_needed(bwc_matcher,
+						atomic_read(&bwc_matcher->num_of_rules)))
 		return 0;
 
 	/* Now we're done all the checking - do the rehash:
@@ -714,6 +757,8 @@ hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
 	 *  - destroy the old matcher
 	 */
 
+	atomic_set(&bwc_matcher->rehash_required, false);
+
 	ret = hws_bwc_matcher_extend_size(bwc_matcher);
 	if (ret)
 		return ret;
@@ -721,17 +766,51 @@ hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
 	return hws_bwc_matcher_move(bwc_matcher);
 }
 
-static int
-hws_bwc_matcher_rehash_at(struct mlx5hws_bwc_matcher *bwc_matcher)
+static int hws_bwc_rule_get_at_idx(struct mlx5hws_bwc_rule *bwc_rule,
+				   struct mlx5hws_rule_action rule_actions[],
+				   u16 bwc_queue_idx)
 {
-	/* Rehash by action template doesn't require any additional checking.
-	 * The bwc_matcher already contains the new action template.
-	 * Just do the usual rehash:
-	 *  - create new matcher
-	 *  - move all the rules to the new matcher
-	 *  - destroy the old matcher
-	 */
-	return hws_bwc_matcher_move(bwc_matcher);
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mutex *queue_lock; /* Protect the queue */
+	int at_idx, ret;
+
+	/* check if rehash needed due to missing action template */
+	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	if (likely(at_idx >= 0))
+		return at_idx;
+
+	/* we need to extend BWC matcher action templates array */
+	queue_lock = hws_bwc_get_queue_lock(ctx, bwc_queue_idx);
+	mutex_unlock(queue_lock);
+	hws_bwc_lock_all_queues(ctx);
+
+	/* check again - perhaps other thread already did extend_at */
+	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	if (at_idx >= 0)
+		goto out;
+
+	ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx, "BWC rule: failed extending AT (%d)", ret);
+		at_idx = -EINVAL;
+		goto out;
+	}
+
+	/* action templates array was extended, we need the last idx */
+	at_idx = bwc_matcher->num_of_at - 1;
+	ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
+					bwc_matcher->at[at_idx]);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx, "BWC rule: failed attaching new AT (%d)", ret);
+		at_idx = -EINVAL;
+		goto out;
+	}
+
+out:
+	hws_bwc_unlock_all_queues(ctx);
+	mutex_lock(queue_lock);
+	return at_idx;
 }
 
 int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
@@ -754,50 +833,16 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 
 	mutex_lock(queue_lock);
 
-	/* check if rehash needed due to missing action template */
-	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	at_idx = hws_bwc_rule_get_at_idx(bwc_rule, rule_actions, bwc_queue_idx);
 	if (unlikely(at_idx < 0)) {
-		/* we need to extend BWC matcher action templates array */
 		mutex_unlock(queue_lock);
-		hws_bwc_lock_all_queues(ctx);
-
-		ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
-		if (unlikely(ret)) {
-			hws_bwc_unlock_all_queues(ctx);
-			return ret;
-		}
-
-		/* action templates array was extended, we need the last idx */
-		at_idx = bwc_matcher->num_of_at - 1;
-
-		ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
-						bwc_matcher->at[at_idx]);
-		if (unlikely(ret)) {
-			/* Action template attach failed, possibly due to
-			 * requiring more action STEs.
-			 * Need to attempt creating new matcher with all
-			 * the action templates, including the new one.
-			 */
-			ret = hws_bwc_matcher_rehash_at(bwc_matcher);
-			if (unlikely(ret)) {
-				mlx5hws_action_template_destroy(bwc_matcher->at[at_idx]);
-				bwc_matcher->at[at_idx] = NULL;
-				bwc_matcher->num_of_at--;
-
-				hws_bwc_unlock_all_queues(ctx);
-
-				mlx5hws_err(ctx,
-					    "BWC rule insertion: rehash AT failed (%d)\n", ret);
-				return ret;
-			}
-		}
-
-		hws_bwc_unlock_all_queues(ctx);
-		mutex_lock(queue_lock);
+		mlx5hws_err(ctx, "BWC rule create: failed getting AT (%d)",
+			    ret);
+		return -EINVAL;
 	}
 
 	/* check if number of rules require rehash */
-	num_of_rules = bwc_matcher->num_of_rules;
+	num_of_rules = atomic_inc_return(&bwc_matcher->num_of_rules);
 
 	if (unlikely(hws_bwc_matcher_rehash_size_needed(bwc_matcher, num_of_rules))) {
 		mutex_unlock(queue_lock);
@@ -811,6 +856,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 				    bwc_matcher->size_log - MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP,
 				    bwc_matcher->size_log,
 				    ret);
+			atomic_dec(&bwc_matcher->num_of_rules);
 			return ret;
 		}
 
@@ -835,6 +881,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 	 * Try rehash by size and insert rule again - last chance.
 	 */
 
+	atomic_set(&bwc_matcher->rehash_required, true);
 	mutex_unlock(queue_lock);
 
 	hws_bwc_lock_all_queues(ctx);
@@ -843,6 +890,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 
 	if (ret) {
 		mlx5hws_err(ctx, "BWC rule insertion: rehash failed (%d)\n", ret);
+		atomic_dec(&bwc_matcher->num_of_rules);
 		return ret;
 	}
 
@@ -858,6 +906,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret)) {
 		mutex_unlock(queue_lock);
 		mlx5hws_err(ctx, "BWC rule insertion failed (%d)\n", ret);
+		atomic_dec(&bwc_matcher->num_of_rules);
 		return ret;
 	}
 
@@ -889,11 +938,18 @@ mlx5hws_bwc_rule_create(struct mlx5hws_bwc_matcher *bwc_matcher,
 
 	bwc_queue_idx = hws_bwc_gen_queue_idx(ctx);
 
-	ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
-					     params->match_buf,
-					     rule_actions,
-					     flow_source,
-					     bwc_queue_idx);
+	if (bwc_matcher->complex)
+		ret = mlx5hws_bwc_rule_create_complex(bwc_rule,
+						      params,
+						      flow_source,
+						      rule_actions,
+						      bwc_queue_idx);
+	else
+		ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
+						     params->match_buf,
+						     rule_actions,
+						     flow_source,
+						     bwc_queue_idx);
 	if (unlikely(ret)) {
 		mlx5hws_bwc_rule_free(bwc_rule);
 		return NULL;
@@ -920,52 +976,11 @@ hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
 
 	mutex_lock(queue_lock);
 
-	/* check if rehash needed due to missing action template */
-	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	at_idx = hws_bwc_rule_get_at_idx(bwc_rule, rule_actions, idx);
 	if (unlikely(at_idx < 0)) {
-		/* we need to extend BWC matcher action templates array */
 		mutex_unlock(queue_lock);
-		hws_bwc_lock_all_queues(ctx);
-
-		/* check again - perhaps other thread already did extend_at */
-		at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
-		if (likely(at_idx < 0)) {
-			ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
-			if (unlikely(ret)) {
-				hws_bwc_unlock_all_queues(ctx);
-				mlx5hws_err(ctx, "BWC rule update: failed extending AT (%d)", ret);
-				return -EINVAL;
-			}
-
-			/* action templates array was extended, we need the last idx */
-			at_idx = bwc_matcher->num_of_at - 1;
-
-			ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
-							bwc_matcher->at[at_idx]);
-			if (unlikely(ret)) {
-				/* Action template attach failed, possibly due to
-				 * requiring more action STEs.
-				 * Need to attempt creating new matcher with all
-				 * the action templates, including the new one.
-				 */
-				ret = hws_bwc_matcher_rehash_at(bwc_matcher);
-				if (unlikely(ret)) {
-					mlx5hws_action_template_destroy(bwc_matcher->at[at_idx]);
-					bwc_matcher->at[at_idx] = NULL;
-					bwc_matcher->num_of_at--;
-
-					hws_bwc_unlock_all_queues(ctx);
-
-					mlx5hws_err(ctx,
-						    "BWC rule update: rehash AT failed (%d)\n",
-						    ret);
-					return ret;
-				}
-			}
-		}
-
-		hws_bwc_unlock_all_queues(ctx);
-		mutex_lock(queue_lock);
+		mlx5hws_err(ctx, "BWC rule update: failed getting AT\n");
+		return -EINVAL;
 	}
 
 	ret = hws_bwc_rule_update_sync(bwc_rule,
@@ -991,5 +1006,10 @@ int mlx5hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
 		return -EINVAL;
 	}
 
-	return hws_bwc_rule_action_update(bwc_rule, rule_actions);
+	/* For complex rule, the update should happen on the second matcher */
+	if (bwc_rule->isolated_bwc_rule)
+		return hws_bwc_rule_action_update(bwc_rule->isolated_bwc_rule,
+						  rule_actions);
+	else
+		return hws_bwc_rule_action_update(bwc_rule, rule_actions);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
index 0b745968e21e..d21fc247a510 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
@@ -8,24 +8,37 @@
 #define MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP 1
 #define MLX5HWS_BWC_MATCHER_REHASH_PERCENT_TH 70
 #define MLX5HWS_BWC_MATCHER_REHASH_BURST_TH 32
-#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 255
+
+/* Max number of AT attach operations for the same matcher.
+ * When the limit is reached, a larger buffer is allocated for the ATs.
+ */
+#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 8
 
 #define MLX5HWS_BWC_MAX_ACTS 16
 
+#define MLX5HWS_BWC_POLLING_TIMEOUT 60
+
+struct mlx5hws_bwc_matcher_complex_data;
 struct mlx5hws_bwc_matcher {
 	struct mlx5hws_matcher *matcher;
 	struct mlx5hws_match_template *mt;
-	struct mlx5hws_action_template *at[MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM];
+	struct mlx5hws_action_template **at;
+	struct mlx5hws_bwc_matcher_complex_data *complex;
+	struct mlx5hws_bwc_matcher *complex_first_bwc_matcher;
 	u8 num_of_at;
-	u16 priority;
+	u8 size_of_at_array;
 	u8 size_log;
-	u32 num_of_rules; /* atomically accessed */
+	u32 priority;
+	atomic_t num_of_rules;
+	atomic_t rehash_required;
 	struct list_head *rules;
 };
 
 struct mlx5hws_bwc_rule {
 	struct mlx5hws_bwc_matcher *bwc_matcher;
 	struct mlx5hws_rule *rule;
+	struct mlx5hws_bwc_rule *isolated_bwc_rule;
+	struct mlx5hws_bwc_complex_rule_hash_node *complex_hash_node;
 	u16 bwc_queue_idx;
 	struct list_head list_node;
 };
@@ -57,12 +70,19 @@ void mlx5hws_bwc_rule_fill_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
 				u32 flow_source,
 				struct mlx5hws_rule_attr *rule_attr);
 
+int mlx5hws_bwc_queue_poll(struct mlx5hws_context *ctx,
+			   u16 queue_id,
+			   u32 *pending_rules,
+			   bool drain);
+
 static inline u16 mlx5hws_bwc_queues(struct mlx5hws_context *ctx)
 {
 	/* Besides the control queue, half of the queues are
-	 * reguler HWS queues, and the other half are BWC queues.
+	 * regular HWS queues, and the other half are BWC queues.
 	 */
-	return (ctx->queues - 1) / 2;
+	if (mlx5hws_context_bwc_supported(ctx))
+		return (ctx->queues - 1) / 2;
+	return 0;
 }
 
 static inline u16 mlx5hws_bwc_get_queue_id(struct mlx5hws_context *ctx, u16 idx)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
index c00010ca86bd..ca7501c57468 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
@@ -3,6 +3,22 @@
 
 #include "internal.h"
 
+#define HWS_CLEAR_MATCH_PARAM(mask, field) \
+	MLX5_SET(fte_match_param, (mask)->match_buf, field, 0)
+
+#define HWS_SZ_MATCH_PARAM (MLX5_ST_SZ_DW_MATCH_PARAM * 4)
+
+static const struct rhashtable_params hws_refcount_hash = {
+	.key_len = sizeof_field(struct mlx5hws_bwc_complex_rule_hash_node,
+				match_buf),
+	.key_offset = offsetof(struct mlx5hws_bwc_complex_rule_hash_node,
+			       match_buf),
+	.head_offset = offsetof(struct mlx5hws_bwc_complex_rule_hash_node,
+				hash_node),
+	.automatic_shrinking = true,
+	.min_size = 1,
+};
+
 bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 					 u8 match_criteria_enable,
 					 struct mlx5hws_match_parameters *mask)
@@ -39,6 +55,8 @@ bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 		} else {
 			mlx5hws_err(ctx, "Failed to calculate matcher definer layout\n");
 		}
+	} else {
+		kfree(mt->fc);
 	}
 
 	mlx5hws_match_template_destroy(mt);
@@ -46,20 +64,1093 @@ bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 	return is_complex;
 }
 
+static void
+hws_bwc_matcher_complex_params_clear_fld(struct mlx5hws_context *ctx,
+					 enum mlx5hws_definer_fname fname,
+					 struct mlx5hws_match_parameters *mask)
+{
+	struct mlx5hws_cmd_query_caps *caps = ctx->caps;
+
+	switch (fname) {
+	case MLX5HWS_DEFINER_FNAME_ETH_TYPE_O:
+	case MLX5HWS_DEFINER_FNAME_ETH_TYPE_I:
+	case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_O:
+	case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_I:
+	case MLX5HWS_DEFINER_FNAME_IP_VERSION_O:
+	case MLX5HWS_DEFINER_FNAME_IP_VERSION_I:
+		/* Because of the strict requirements for IP address matching
+		 * that require ethtype/ip_version matching as well, don't clear
+		 * these fields - have them in both parts of the complex matcher
+		 */
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.smac_47_16);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.smac_47_16);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.smac_15_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.smac_15_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.dmac_47_16);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.dmac_47_16);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.dmac_15_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.dmac_15_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_TYPE_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.cvlan_tag);
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.svlan_tag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_TYPE_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.cvlan_tag);
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.svlan_tag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_FIRST_PRIO_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.first_prio);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_FIRST_PRIO_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.first_prio);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_CFI_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.first_cfi);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_CFI_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.first_cfi);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_ID_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.first_vid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_ID_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.first_vid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_TYPE_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.outer_second_cvlan_tag);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.outer_second_svlan_tag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_TYPE_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.inner_second_cvlan_tag);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.inner_second_svlan_tag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_PRIO_O:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.outer_second_prio);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_PRIO_I:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.inner_second_prio);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_CFI_O:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.outer_second_cfi);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_CFI_I:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.inner_second_cfi);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_ID_O:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.outer_second_vid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_ID_I:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.inner_second_vid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_IHL_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ipv4_ihl);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_IHL_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ipv4_ihl);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_DSCP_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ip_dscp);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_DSCP_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ip_dscp);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_ECN_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ip_ecn);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_ECN_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ip_ecn);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_TTL_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ttl_hoplimit);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_TTL_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ttl_hoplimit);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_DST_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_SRC_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_DST_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_SRC_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_FRAG_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.frag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_FRAG_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.frag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_FLOW_LABEL_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.outer_ipv6_flow_label);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_FLOW_LABEL_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.inner_ipv6_flow_label);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_95_64);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_63_32);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_95_64);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_63_32);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_95_64);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_63_32);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_95_64);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_63_32);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_PROTOCOL_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ip_protocol);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_PROTOCOL_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ip_protocol);
+		break;
+	case MLX5HWS_DEFINER_FNAME_L4_SPORT_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.tcp_sport);
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.udp_sport);
+		break;
+	case MLX5HWS_DEFINER_FNAME_L4_SPORT_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.tcp_dport);
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.udp_dport);
+		break;
+	case MLX5HWS_DEFINER_FNAME_L4_DPORT_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.tcp_dport);
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.udp_dport);
+		break;
+	case MLX5HWS_DEFINER_FNAME_L4_DPORT_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.tcp_dport);
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.udp_dport);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TCP_FLAGS_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.tcp_flags);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TCP_ACK_NUM:
+	case MLX5HWS_DEFINER_FNAME_TCP_SEQ_NUM:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_tcp_seq_num);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_tcp_ack_num);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.inner_tcp_seq_num);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.inner_tcp_ack_num);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GTP_TEID:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_teid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GTP_MSG_TYPE:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_msg_type);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_msg_flags);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GTPU_FIRST_EXT_DW0:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.gtpu_first_ext_dw_0);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_dw_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GTPU_DW2:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_dw_2);
+		break;
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_0:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_1:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_2:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_3:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_4:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_5:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_6:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_7:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_2.outer_first_mpls_over_gre);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_2.outer_first_mpls_over_udp);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.geneve_tlv_option_0_data);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_id_0);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_value_0);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_value_1);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_id_2);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_value_2);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_id_3);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_value_3);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_VNI:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.vxlan_vni);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_GPE_FLAGS:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_vxlan_gpe_flags);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_GPE_RSVD0:
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_GPE_PROTO:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_vxlan_gpe_next_protocol);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_GPE_VNI:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_vxlan_gpe_vni);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GENEVE_OPT_LEN:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.geneve_opt_len);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GENEVE_OAM:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.geneve_oam);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GENEVE_PROTO:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.geneve_protocol_type);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GENEVE_VNI:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.geneve_vni);
+		break;
+	case MLX5HWS_DEFINER_FNAME_SOURCE_QP:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.source_sqn);
+		break;
+	case MLX5HWS_DEFINER_FNAME_SOURCE_GVMI:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.source_port);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.source_eswitch_owner_vhca_id);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_0:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_1:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_1);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_2:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_2);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_3:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_3);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_4:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_4);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_5:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_5);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_7:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_7);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_A:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_a);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_C:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_c_present);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_K:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_k_present);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_S:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_s_present);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_PROTOCOL:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_protocol);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_OPT_KEY:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_key.key);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ICMP_DW1:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmp_header_data);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmp_type);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmp_code);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.icmpv6_header_data);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmpv6_type);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmpv6_code);
+		break;
+	case MLX5HWS_DEFINER_FNAME_MPLS0_O:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.outer_first_mpls);
+		break;
+	case MLX5HWS_DEFINER_FNAME_MPLS0_I:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.inner_first_mpls);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TNL_HDR_0:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_5.tunnel_header_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TNL_HDR_1:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_5.tunnel_header_1);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TNL_HDR_2:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_5.tunnel_header_2);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TNL_HDR_3:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_5.tunnel_header_3);
+		break;
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER0_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER1_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER2_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER3_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER4_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER5_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER6_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER7_OK:
+		/* assuming this is flex parser for geneve option */
+		if ((fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER0_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 0) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER1_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 1) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER2_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 2) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER3_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 3) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER4_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 4) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER5_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 5) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER6_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 6) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER7_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 7)) {
+			mlx5hws_err(ctx,
+				    "Complex params: unsupported field %s (%d), flex parser ID for geneve is %d\n",
+				    mlx5hws_definer_fname_to_str(fname), fname,
+				    caps->flex_parser_id_geneve_tlv_option_0);
+			break;
+		}
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.geneve_tlv_option_0_exist);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_6:
+	default:
+		mlx5hws_err(ctx, "Complex params: unsupported field %s (%d)\n",
+			    mlx5hws_definer_fname_to_str(fname), fname);
+		break;
+	}
+}
+
+static bool
+hws_bwc_matcher_complex_params_comb_is_valid(struct mlx5hws_definer_fc *fc,
+					     int fc_sz,
+					     u32 combination_num)
+{
+	bool m1[MLX5HWS_DEFINER_FNAME_MAX] = {0};
+	bool m2[MLX5HWS_DEFINER_FNAME_MAX] = {0};
+	bool is_first_matcher;
+	int i;
+
+	for (i = 0; i < fc_sz; i++) {
+		is_first_matcher = !(combination_num & BIT(i));
+		if (is_first_matcher)
+			m1[fc[i].fname] = true;
+		else
+			m2[fc[i].fname] = true;
+	}
+
+	/* Not all the fields can be split into separate matchers.
+	 * Some should be together on the same matcher.
+	 * For example, IPv6 parts - the whole IPv6 address should be on the
+	 * same matcher in order for us to deduce if it's IPv6 or IPv4 address.
+	 */
+	if (m1[MLX5HWS_DEFINER_FNAME_IP_FRAG_O] &&
+	    (m2[MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_O]))
+		return false;
+
+	if (m2[MLX5HWS_DEFINER_FNAME_IP_FRAG_O] &&
+	    (m1[MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_O]))
+		return false;
+
+	if (m1[MLX5HWS_DEFINER_FNAME_IP_FRAG_I] &&
+	    (m2[MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_I]))
+		return false;
+
+	if (m2[MLX5HWS_DEFINER_FNAME_IP_FRAG_I] &&
+	    (m1[MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_I]))
+		return false;
+
+	/* Don't split outer IPv6 dest address. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_O]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_O]))
+		return false;
+
+	/* Don't split outer IPv6 source address. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_O]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_O]))
+		return false;
+
+	/* Don't split inner IPv6 dest address. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_I]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_I]))
+		return false;
+
+	/* Don't split inner IPv6 source address. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_I]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_I]))
+		return false;
+
+	/* Don't split GRE parameters. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_GRE_C] ||
+	     m1[MLX5HWS_DEFINER_FNAME_GRE_K] ||
+	     m1[MLX5HWS_DEFINER_FNAME_GRE_S] ||
+	     m1[MLX5HWS_DEFINER_FNAME_GRE_PROTOCOL]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_GRE_C] ||
+	     m2[MLX5HWS_DEFINER_FNAME_GRE_K] ||
+	     m2[MLX5HWS_DEFINER_FNAME_GRE_S] ||
+	     m2[MLX5HWS_DEFINER_FNAME_GRE_PROTOCOL]))
+		return false;
+
+	/* Don't split TCP ack/seq numbers. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_TCP_ACK_NUM] ||
+	     m1[MLX5HWS_DEFINER_FNAME_TCP_SEQ_NUM]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_TCP_ACK_NUM] ||
+	     m2[MLX5HWS_DEFINER_FNAME_TCP_SEQ_NUM]))
+		return false;
+
+	/* Don't split flex parser. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_0] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_1] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_2] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_3] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_4] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_5] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_6] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_7]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_0] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_1] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_2] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_3] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_4] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_5] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_6] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_7]))
+		return false;
+
+	return true;
+}
+
+static void
+hws_bwc_matcher_complex_params_comb_create(struct mlx5hws_context *ctx,
+					   struct mlx5hws_match_parameters *m,
+					   struct mlx5hws_match_parameters *m1,
+					   struct mlx5hws_match_parameters *m2,
+					   struct mlx5hws_definer_fc *fc,
+					   int fc_sz,
+					   u32 combination_num)
+{
+	bool is_first_matcher;
+	int i;
+
+	memcpy(m1->match_buf, m->match_buf, m->match_sz);
+	memcpy(m2->match_buf, m->match_buf, m->match_sz);
+
+	for (i = 0; i < fc_sz; i++) {
+		is_first_matcher = !(combination_num & BIT(i));
+		hws_bwc_matcher_complex_params_clear_fld(ctx,
+							 fc[i].fname,
+							 is_first_matcher ?
+							 m2 : m1);
+	}
+
+	MLX5_SET(fte_match_param, m2->match_buf,
+		 misc_parameters_2.metadata_reg_c_6, -1);
+}
+
+static void
+hws_bwc_matcher_complex_params_destroy(struct mlx5hws_match_parameters *mask_1,
+				       struct mlx5hws_match_parameters *mask_2)
+{
+	kfree(mask_1->match_buf);
+	kfree(mask_2->match_buf);
+}
+
+static int
+hws_bwc_matcher_complex_params_create(struct mlx5hws_context *ctx,
+				      u8 match_criteria,
+				      struct mlx5hws_match_parameters *mask,
+				      struct mlx5hws_match_parameters *mask_1,
+				      struct mlx5hws_match_parameters *mask_2)
+{
+	struct mlx5hws_definer_fc *fc;
+	u32 num_of_combinations;
+	int fc_sz = 0;
+	int res = 0;
+	u32 i;
+
+	if (MLX5_GET(fte_match_param, mask->match_buf,
+		     misc_parameters_2.metadata_reg_c_6)) {
+		mlx5hws_err(ctx, "Complex matcher: REG_C_6 matching is reserved\n");
+		res = -EINVAL;
+		goto out;
+	}
+
+	mask_1->match_buf = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param),
+				    GFP_KERNEL);
+	mask_2->match_buf = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param),
+				    GFP_KERNEL);
+	if (!mask_1->match_buf || !mask_2->match_buf) {
+		mlx5hws_err(ctx, "Complex matcher: failed to allocate match_param\n");
+		res = -ENOMEM;
+		goto free_params;
+	}
+
+	mask_1->match_sz = mask->match_sz;
+	mask_2->match_sz = mask->match_sz;
+
+	fc = mlx5hws_definer_conv_match_params_to_compressed_fc(ctx,
+								match_criteria,
+								mask->match_buf,
+								&fc_sz);
+	if (!fc) {
+		res = -ENOMEM;
+		goto free_params;
+	}
+
+	if (fc_sz >= sizeof(num_of_combinations) * BITS_PER_BYTE) {
+		mlx5hws_err(ctx,
+			    "Complex matcher: too many match parameters (%d)\n",
+			    fc_sz);
+		res = -EINVAL;
+		goto free_fc;
+	}
+
+	/* We have list of all the match fields from the match parameter.
+	 * Now try all the possibilities of splitting them into two match
+	 * buffers and look for the supported combination.
+	 */
+	num_of_combinations = 1 << fc_sz;
+
+	/* Start from combination at index 1 - we know that 0 is unsupported */
+	for (i = 1; i < num_of_combinations; i++) {
+		if (!hws_bwc_matcher_complex_params_comb_is_valid(fc, fc_sz, i))
+			continue;
+
+		hws_bwc_matcher_complex_params_comb_create(ctx,
+							   mask, mask_1, mask_2,
+							   fc, fc_sz, i);
+		/* We now have two separate sets of match params.
+		 * Check if each of them can be used in its own matcher.
+		 */
+		if (!mlx5hws_bwc_match_params_is_complex(ctx,
+							 match_criteria,
+							 mask_1) &&
+		    !mlx5hws_bwc_match_params_is_complex(ctx,
+							 match_criteria,
+							 mask_2))
+			break;
+	}
+
+	if (i == num_of_combinations) {
+		/* We've scanned all the combinations, but to no avail */
+		mlx5hws_err(ctx, "Complex matcher: couldn't find match params combination\n");
+		res = -EINVAL;
+		goto free_fc;
+	}
+
+	kfree(fc);
+	return 0;
+
+free_fc:
+	kfree(fc);
+free_params:
+	hws_bwc_matcher_complex_params_destroy(mask_1, mask_2);
+out:
+	return res;
+}
+
+static int
+hws_bwc_isolated_table_create(struct mlx5hws_bwc_matcher *bwc_matcher,
+			      struct mlx5hws_table *table)
+{
+	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
+	struct mlx5hws_context *ctx = table->ctx;
+	struct mlx5hws_table_attr tbl_attr = {0};
+	struct mlx5hws_table *isolated_tbl;
+	int ret = 0;
+
+	tbl_attr.type = table->type;
+	tbl_attr.level = table->level;
+
+	bwc_matcher->complex->isolated_tbl =
+		mlx5hws_table_create(ctx, &tbl_attr);
+	isolated_tbl = bwc_matcher->complex->isolated_tbl;
+	if (!isolated_tbl)
+		return -EINVAL;
+
+	/* Set the default miss of the isolated table to
+	 * point to the end anchor of the original matcher.
+	 */
+	mlx5hws_cmd_set_attr_connect_miss_tbl(ctx,
+					      isolated_tbl->fw_ft_type,
+					      isolated_tbl->type,
+					      &ft_attr);
+	ft_attr.table_miss_id = bwc_matcher->matcher->end_ft_id;
+
+	ret = mlx5hws_cmd_flow_table_modify(ctx->mdev,
+					    &ft_attr,
+					    isolated_tbl->ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed setting isolated tbl default miss\n");
+		goto destroy_tbl;
+	}
+
+	return 0;
+
+destroy_tbl:
+	mlx5hws_table_destroy(isolated_tbl);
+	return ret;
+}
+
+static void hws_bwc_isolated_table_destroy(struct mlx5hws_table *isolated_tbl)
+{
+	/* This table is isolated - no table is pointing to it, no need to
+	 * disconnect it from anywhere, it won't affect any other table's miss.
+	 */
+	mlx5hws_table_destroy(isolated_tbl);
+}
+
+static int
+hws_bwc_isolated_matcher_create(struct mlx5hws_bwc_matcher *bwc_matcher,
+				struct mlx5hws_table *table,
+				u8 match_criteria_enable,
+				struct mlx5hws_match_parameters *mask)
+{
+	struct mlx5hws_table *isolated_tbl = bwc_matcher->complex->isolated_tbl;
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher;
+	struct mlx5hws_context *ctx = table->ctx;
+	int ret;
+
+	isolated_bwc_matcher = kzalloc(sizeof(*bwc_matcher), GFP_KERNEL);
+	if (!isolated_bwc_matcher)
+		return -ENOMEM;
+
+	bwc_matcher->complex->isolated_bwc_matcher = isolated_bwc_matcher;
+
+	/* Isolated BWC matcher needs access to the first BWC matcher */
+	isolated_bwc_matcher->complex_first_bwc_matcher = bwc_matcher;
+
+	/* Isolated matcher needs to match on REG_C_6,
+	 * so make sure its criteria bit is on.
+	 */
+	match_criteria_enable |= MLX5HWS_DEFINER_MATCH_CRITERIA_MISC2;
+
+	ret = mlx5hws_bwc_matcher_create_simple(isolated_bwc_matcher,
+						isolated_tbl,
+						0,
+						match_criteria_enable,
+						mask,
+						NULL);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed creating isolated BWC matcher\n");
+		goto free_matcher;
+	}
+
+	return 0;
+
+free_matcher:
+	kfree(bwc_matcher->complex->isolated_bwc_matcher);
+	return ret;
+}
+
+static void
+hws_bwc_isolated_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+	kfree(bwc_matcher);
+}
+
+static int
+hws_bwc_isolated_actions_create(struct mlx5hws_bwc_matcher *bwc_matcher,
+				struct mlx5hws_table *table)
+{
+	struct mlx5hws_table *isolated_tbl = bwc_matcher->complex->isolated_tbl;
+	u8 modify_hdr_action[MLX5_ST_SZ_BYTES(set_action_in)] = {0};
+	struct mlx5hws_context *ctx = table->ctx;
+	struct mlx5hws_action_mh_pattern ptrn;
+	int ret = 0;
+
+	/* Create action to jump to isolated table */
+
+	bwc_matcher->complex->action_go_to_tbl =
+		mlx5hws_action_create_dest_table(ctx,
+						 isolated_tbl,
+						 MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!bwc_matcher->complex->action_go_to_tbl) {
+		mlx5hws_err(ctx, "Complex matcher: failed to create go-to-tbl action\n");
+		return -EINVAL;
+	}
+
+	/* Create modify header action to set REG_C_6 */
+
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 action_type, MLX5_MODIFICATION_TYPE_SET);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 field, MLX5_MODI_META_REG_C_6);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 length, 0); /* zero means length of 32 */
+	MLX5_SET(set_action_in, modify_hdr_action, offset, 0);
+	MLX5_SET(set_action_in, modify_hdr_action, data, 0);
+
+	ptrn.data = (void *)modify_hdr_action;
+	ptrn.sz = MLX5HWS_ACTION_DOUBLE_SIZE;
+
+	bwc_matcher->complex->action_metadata =
+		mlx5hws_action_create_modify_header(ctx, 1, &ptrn, 0,
+						    MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!bwc_matcher->complex->action_metadata) {
+		ret = -EINVAL;
+		goto destroy_action_go_to_tbl;
+	}
+
+	/* Create last action */
+
+	bwc_matcher->complex->action_last =
+		mlx5hws_action_create_last(ctx, MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!bwc_matcher->complex->action_last) {
+		mlx5hws_err(ctx, "Complex matcher: failed to create last action\n");
+		ret = -EINVAL;
+		goto destroy_action_metadata;
+	}
+
+	return 0;
+
+destroy_action_metadata:
+	mlx5hws_action_destroy(bwc_matcher->complex->action_metadata);
+destroy_action_go_to_tbl:
+	mlx5hws_action_destroy(bwc_matcher->complex->action_go_to_tbl);
+	return ret;
+}
+
+static void
+hws_bwc_isolated_actions_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mlx5hws_action_destroy(bwc_matcher->complex->action_last);
+	mlx5hws_action_destroy(bwc_matcher->complex->action_metadata);
+	mlx5hws_action_destroy(bwc_matcher->complex->action_go_to_tbl);
+}
+
 int mlx5hws_bwc_matcher_create_complex(struct mlx5hws_bwc_matcher *bwc_matcher,
 				       struct mlx5hws_table *table,
 				       u32 priority,
 				       u8 match_criteria_enable,
 				       struct mlx5hws_match_parameters *mask)
 {
-	mlx5hws_err(table->ctx, "Complex matcher is not supported yet\n");
-	return -EOPNOTSUPP;
+	enum mlx5hws_action_type complex_init_action_types[3];
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher;
+	struct mlx5hws_match_parameters mask_1 = {0};
+	struct mlx5hws_match_parameters mask_2 = {0};
+	struct mlx5hws_context *ctx = table->ctx;
+	int ret;
+
+	ret = hws_bwc_matcher_complex_params_create(table->ctx,
+						    match_criteria_enable,
+						    mask, &mask_1, &mask_2);
+	if (ret)
+		goto err;
+
+	bwc_matcher->complex =
+		kzalloc(sizeof(*bwc_matcher->complex), GFP_KERNEL);
+	if (!bwc_matcher->complex) {
+		ret = -ENOMEM;
+		goto free_masks;
+	}
+
+	ret = rhashtable_init(&bwc_matcher->complex->refcount_hash,
+			      &hws_refcount_hash);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed to initialize rhashtable\n");
+		goto free_complex;
+	}
+
+	mutex_init(&bwc_matcher->complex->hash_lock);
+	ida_init(&bwc_matcher->complex->metadata_ida);
+
+	/* Create initial action template for the first matcher.
+	 * Usually the initial AT is just dummy, but in case of complex
+	 * matcher we know exactly which actions should it have.
+	 */
+
+	complex_init_action_types[0] = MLX5HWS_ACTION_TYP_MODIFY_HDR;
+	complex_init_action_types[1] = MLX5HWS_ACTION_TYP_TBL;
+	complex_init_action_types[2] = MLX5HWS_ACTION_TYP_LAST;
+
+	/* Create the first matcher */
+
+	ret = mlx5hws_bwc_matcher_create_simple(bwc_matcher,
+						table,
+						priority,
+						match_criteria_enable,
+						&mask_1,
+						complex_init_action_types);
+	if (ret)
+		goto destroy_ida;
+
+	/* Create isolated table to hold the second isolated matcher */
+
+	ret = hws_bwc_isolated_table_create(bwc_matcher, table);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed creating isolated table\n");
+		goto destroy_first_matcher;
+	}
+
+	/* Now create the second BWC matcher - the isolated one */
+
+	ret = hws_bwc_isolated_matcher_create(bwc_matcher, table,
+					      match_criteria_enable, &mask_2);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed creating isolated matcher\n");
+		goto destroy_isolated_tbl;
+	}
+
+	/* Create action for isolated matcher's rules */
+
+	ret = hws_bwc_isolated_actions_create(bwc_matcher, table);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed creating isolated actions\n");
+		goto destroy_isolated_matcher;
+	}
+
+	hws_bwc_matcher_complex_params_destroy(&mask_1, &mask_2);
+	return 0;
+
+destroy_isolated_matcher:
+	isolated_bwc_matcher = bwc_matcher->complex->isolated_bwc_matcher;
+	hws_bwc_isolated_matcher_destroy(isolated_bwc_matcher);
+destroy_isolated_tbl:
+	hws_bwc_isolated_table_destroy(bwc_matcher->complex->isolated_tbl);
+destroy_first_matcher:
+	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+destroy_ida:
+	ida_destroy(&bwc_matcher->complex->metadata_ida);
+	mutex_destroy(&bwc_matcher->complex->hash_lock);
+	rhashtable_destroy(&bwc_matcher->complex->refcount_hash);
+free_complex:
+	kfree(bwc_matcher->complex);
+	bwc_matcher->complex = NULL;
+free_masks:
+	hws_bwc_matcher_complex_params_destroy(&mask_1, &mask_2);
+err:
+	return ret;
 }
 
 void
 mlx5hws_bwc_matcher_destroy_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	/* nothing to do here */
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher =
+		bwc_matcher->complex->isolated_bwc_matcher;
+
+	hws_bwc_isolated_actions_destroy(bwc_matcher);
+	hws_bwc_isolated_matcher_destroy(isolated_bwc_matcher);
+	hws_bwc_isolated_table_destroy(bwc_matcher->complex->isolated_tbl);
+	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+	ida_destroy(&bwc_matcher->complex->metadata_ida);
+	mutex_destroy(&bwc_matcher->complex->hash_lock);
+	rhashtable_destroy(&bwc_matcher->complex->refcount_hash);
+	kfree(bwc_matcher->complex);
+	bwc_matcher->complex = NULL;
+}
+
+static void
+hws_bwc_matcher_complex_hash_lock(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mutex_lock(&bwc_matcher->complex->hash_lock);
+}
+
+static void
+hws_bwc_matcher_complex_hash_unlock(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mutex_unlock(&bwc_matcher->complex->hash_lock);
+}
+
+static int
+hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
+				   struct mlx5hws_match_parameters *params)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_bwc_complex_rule_hash_node *node, *old_node;
+	struct rhashtable *refcount_hash;
+	int ret, i;
+
+	bwc_rule->complex_hash_node = NULL;
+
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (unlikely(!node))
+		return -ENOMEM;
+
+	ret = ida_alloc(&bwc_matcher->complex->metadata_ida, GFP_KERNEL);
+	if (ret < 0)
+		goto err_free_node;
+	node->tag = ret;
+
+	refcount_set(&node->refcount, 1);
+
+	/* Clear match buffer - turn off all the unrelated fields
+	 * in accordance with the match params mask for the first
+	 * matcher out of the two parts of the complex matcher.
+	 * The resulting mask is the key for the hash.
+	 */
+	for (i = 0; i < MLX5_ST_SZ_DW_MATCH_PARAM; i++)
+		node->match_buf[i] = params->match_buf[i] &
+				     bwc_matcher->mt->match_param[i];
+
+	refcount_hash = &bwc_matcher->complex->refcount_hash;
+	old_node = rhashtable_lookup_get_insert_fast(refcount_hash,
+						     &node->hash_node,
+						     hws_refcount_hash);
+	if (IS_ERR(old_node)) {
+		ret = PTR_ERR(old_node);
+		goto err_free_ida;
+	}
+
+	if (old_node) {
+		/* Rule with the same tag already exists - update refcount */
+		refcount_inc(&old_node->refcount);
+		/* Let the new rule use the same tag as the existing rule.
+		 * Note that we don't have any indication for the rule creation
+		 * process that a rule with similar matching params already
+		 * exists - no harm done when this rule is be overwritten by
+		 * the same STE.
+		 * There's some performance advantage in skipping such cases,
+		 * so this is left for future optimizations.
+		 */
+		ida_free(&bwc_matcher->complex->metadata_ida, node->tag);
+		kfree(node);
+		node = old_node;
+	}
+
+	bwc_rule->complex_hash_node = node;
+	return 0;
+
+err_free_ida:
+	ida_free(&bwc_matcher->complex->metadata_ida, node->tag);
+err_free_node:
+	kfree(node);
+	return ret;
+}
+
+static void
+hws_bwc_rule_complex_hash_node_put(struct mlx5hws_bwc_rule *bwc_rule,
+				   bool *is_last_rule)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_bwc_complex_rule_hash_node *node;
+
+	if (is_last_rule)
+		*is_last_rule = false;
+
+	node = bwc_rule->complex_hash_node;
+	if (refcount_dec_and_test(&node->refcount)) {
+		rhashtable_remove_fast(&bwc_matcher->complex->refcount_hash,
+				       &node->hash_node,
+				       hws_refcount_hash);
+		ida_free(&bwc_matcher->complex->metadata_ida, node->tag);
+		kfree(node);
+		if (is_last_rule)
+			*is_last_rule = true;
+	}
+
+	bwc_rule->complex_hash_node = NULL;
 }
 
 int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
@@ -68,19 +1159,271 @@ int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
 				    struct mlx5hws_rule_action rule_actions[],
 				    u16 bwc_queue_idx)
 {
-	mlx5hws_err(bwc_rule->bwc_matcher->matcher->tbl->ctx,
-		    "Complex rule is not supported yet\n");
-	return -EOPNOTSUPP;
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	u8 modify_hdr_action[MLX5_ST_SZ_BYTES(set_action_in)] = {0};
+	struct mlx5hws_rule_action rule_actions_1[3] = {0};
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher;
+	u32 *match_buf_2;
+	u32 metadata_val;
+	int ret = 0;
+
+	isolated_bwc_matcher = bwc_matcher->complex->isolated_bwc_matcher;
+	bwc_rule->isolated_bwc_rule =
+		mlx5hws_bwc_rule_alloc(isolated_bwc_matcher);
+	if (unlikely(!bwc_rule->isolated_bwc_rule))
+		return -ENOMEM;
+
+	hws_bwc_matcher_complex_hash_lock(bwc_matcher);
+
+	/* Get a new hash node for this complex rule.
+	 * If this is a unique set of match params for the first matcher,
+	 * we will get a new hash node with newly allocated IDA.
+	 * Otherwise we will get an existing node with IDA and updated refcount.
+	 */
+	ret = hws_bwc_rule_complex_hash_node_get(bwc_rule, params);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx, "Complex rule: failed getting RHT node for this rule\n");
+		goto free_isolated_rule;
+	}
+
+	/* No need to clear match buffer's fields in accordance to what
+	 * will actually be matched on first and second matchers.
+	 * Both matchers were created with the appropriate masks
+	 * and each of them holds the appropriate field copy array,
+	 * so rule creation will use only the fields that will be copied
+	 * in accordance with setters in field copy array.
+	 * We do, however, need to temporary allocate match buffer
+	 * for the second (isolated) rule in order to not modify
+	 * user's match params buffer.
+	 */
+
+	match_buf_2 = kmemdup(params->match_buf,
+			      MLX5_ST_SZ_BYTES(fte_match_param),
+			      GFP_KERNEL);
+	if (unlikely(!match_buf_2)) {
+		mlx5hws_err(ctx, "Complex rule: failed allocating match_buf\n");
+		ret = -ENOMEM;
+		goto hash_node_put;
+	}
+
+	/* On 2nd matcher, use unique 32-bit ID as a matching tag */
+	metadata_val = bwc_rule->complex_hash_node->tag;
+	MLX5_SET(fte_match_param, match_buf_2,
+		 misc_parameters_2.metadata_reg_c_6, metadata_val);
+
+	/* Isolated rule's rule_actions contain all the original actions */
+	ret = mlx5hws_bwc_rule_create_simple(bwc_rule->isolated_bwc_rule,
+					     match_buf_2,
+					     rule_actions,
+					     flow_source,
+					     bwc_queue_idx);
+	kfree(match_buf_2);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx,
+			    "Complex rule: failed creating isolated BWC rule (%d)\n",
+			    ret);
+		goto hash_node_put;
+	}
+
+	/* First rule's rule_actions contain setting metadata and
+	 * jump to isolated table that contains the second matcher.
+	 * Set metadata value to a unique value for this rule.
+	 */
+
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 action_type, MLX5_MODIFICATION_TYPE_SET);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 field, MLX5_MODI_META_REG_C_6);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 length, 0); /* zero means length of 32 */
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 offset, 0);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 data, metadata_val);
+
+	rule_actions_1[0].action = bwc_matcher->complex->action_metadata;
+	rule_actions_1[0].modify_header.offset = 0;
+	rule_actions_1[0].modify_header.data = modify_hdr_action;
+
+	rule_actions_1[1].action = bwc_matcher->complex->action_go_to_tbl;
+	rule_actions_1[2].action = bwc_matcher->complex->action_last;
+
+	ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
+					     params->match_buf,
+					     rule_actions_1,
+					     flow_source,
+					     bwc_queue_idx);
+
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx,
+			    "Complex rule: failed creating first BWC rule (%d)\n",
+			    ret);
+		goto destroy_isolated_rule;
+	}
+
+	hws_bwc_matcher_complex_hash_unlock(bwc_matcher);
+
+	return 0;
+
+destroy_isolated_rule:
+	mlx5hws_bwc_rule_destroy_simple(bwc_rule->isolated_bwc_rule);
+hash_node_put:
+	hws_bwc_rule_complex_hash_node_put(bwc_rule, NULL);
+free_isolated_rule:
+	hws_bwc_matcher_complex_hash_unlock(bwc_matcher);
+	mlx5hws_bwc_rule_free(bwc_rule->isolated_bwc_rule);
+	return ret;
 }
 
 int mlx5hws_bwc_rule_destroy_complex(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	return 0;
+	struct mlx5hws_context *ctx = bwc_rule->bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_bwc_rule *isolated_bwc_rule;
+	int ret_isolated, ret;
+	bool is_last_rule;
+
+	hws_bwc_matcher_complex_hash_lock(bwc_rule->bwc_matcher);
+
+	hws_bwc_rule_complex_hash_node_put(bwc_rule, &is_last_rule);
+	bwc_rule->rule->skip_delete = !is_last_rule;
+
+	ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
+	if (unlikely(ret))
+		mlx5hws_err(ctx, "BWC complex rule: failed destroying first rule\n");
+
+	isolated_bwc_rule = bwc_rule->isolated_bwc_rule;
+	ret_isolated = mlx5hws_bwc_rule_destroy_simple(isolated_bwc_rule);
+	if (unlikely(ret_isolated))
+		mlx5hws_err(ctx, "BWC complex rule: failed destroying second (isolated) rule\n");
+
+	hws_bwc_matcher_complex_hash_unlock(bwc_rule->bwc_matcher);
+
+	mlx5hws_bwc_rule_free(isolated_bwc_rule);
+
+	return ret || ret_isolated;
 }
 
-int mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
+static void
+hws_bwc_matcher_clear_hash_rtcs(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	mlx5hws_err(bwc_matcher->matcher->tbl->ctx,
-		    "Moving complex rule is not supported yet\n");
-	return -EOPNOTSUPP;
+	struct mlx5hws_bwc_complex_rule_hash_node *node;
+	struct rhashtable_iter iter;
+
+	rhashtable_walk_enter(&bwc_matcher->complex->refcount_hash, &iter);
+	rhashtable_walk_start(&iter);
+
+	while ((node = rhashtable_walk_next(&iter)) != NULL) {
+		if (IS_ERR(node))
+			continue;
+		node->rtc_valid = false;
+	}
+
+	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
+}
+
+int
+mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
+	bool move_error = false, poll_error = false;
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mlx5hws_bwc_rule *tmp_bwc_rule;
+	struct mlx5hws_rule_attr rule_attr;
+	struct mlx5hws_table *isolated_tbl;
+	struct mlx5hws_rule *tmp_rule;
+	struct list_head *rules_list;
+	u32 expected_completions = 1;
+	u32 end_ft_id;
+	int i, ret;
+
+	/* We are rehashing the matcher that is the first part of the complex
+	 * matcher. Need to update the isolated matcher to point to the end_ft
+	 * of this new matcher. This needs to be done before moving any rules
+	 * to prevent possible steering loops.
+	 */
+	isolated_tbl = bwc_matcher->complex->isolated_tbl;
+	end_ft_id = bwc_matcher->matcher->resize_dst->end_ft_id;
+	ret = mlx5hws_matcher_update_end_ft_isolated(isolated_tbl, end_ft_id);
+	if (ret) {
+		mlx5hws_err(ctx,
+			    "Failed updating end_ft of isolated matcher (%d)\n",
+			    ret);
+		return ret;
+	}
+
+	hws_bwc_matcher_clear_hash_rtcs(bwc_matcher);
+
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
+
+	for (i = 0; i < bwc_queues; i++) {
+		rules_list = &bwc_matcher->rules[i];
+		if (list_empty(rules_list))
+			continue;
+
+		rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
+
+		list_for_each_entry(tmp_bwc_rule, rules_list, list_node) {
+			/* Check if a rule with similar tag has already
+			 * been moved.
+			 */
+			if (tmp_bwc_rule->complex_hash_node->rtc_valid) {
+				/* This rule is a duplicate of rule with similar
+				 * tag that has already been moved earlier.
+				 * Just update this rule's RTCs.
+				 */
+				tmp_bwc_rule->rule->rtc_0 =
+					tmp_bwc_rule->complex_hash_node->rtc_0;
+				tmp_bwc_rule->rule->rtc_1 =
+					tmp_bwc_rule->complex_hash_node->rtc_1;
+				tmp_bwc_rule->rule->matcher =
+					tmp_bwc_rule->rule->matcher->resize_dst;
+				continue;
+			}
+
+			/* First time we're moving rule with this tag.
+			 * Move it for real.
+			 */
+			tmp_rule = tmp_bwc_rule->rule;
+			tmp_rule->skip_delete = false;
+			ret = mlx5hws_matcher_resize_rule_move(matcher,
+							       tmp_rule,
+							       &rule_attr);
+			if (unlikely(ret && !move_error)) {
+				mlx5hws_err(ctx,
+					    "Moving complex BWC rule failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				move_error = true;
+			}
+
+			expected_completions = 1;
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &expected_completions,
+						     true);
+			if (unlikely(ret && !poll_error)) {
+				mlx5hws_err(ctx,
+					    "Moving complex BWC rule: poll failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				poll_error = true;
+			}
+
+			/* Done moving the rule to the new matcher,
+			 * now update RTCs for all the duplicated rules.
+			 */
+			tmp_bwc_rule->complex_hash_node->rtc_0 =
+				tmp_bwc_rule->rule->rtc_0;
+			tmp_bwc_rule->complex_hash_node->rtc_1 =
+				tmp_bwc_rule->rule->rtc_1;
+
+			tmp_bwc_rule->complex_hash_node->rtc_valid = true;
+		}
+	}
+
+	if (move_error || poll_error)
+		ret = -EINVAL;
+
+	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
index 340f0688e394..a6887c7e39d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
@@ -4,6 +4,27 @@
 #ifndef HWS_BWC_COMPLEX_H_
 #define HWS_BWC_COMPLEX_H_
 
+struct mlx5hws_bwc_complex_rule_hash_node {
+	u32 match_buf[MLX5_ST_SZ_DW_MATCH_PARAM];
+	u32 tag;
+	refcount_t refcount;
+	bool rtc_valid;
+	u32 rtc_0;
+	u32 rtc_1;
+	struct rhash_head hash_node;
+};
+
+struct mlx5hws_bwc_matcher_complex_data {
+	struct mlx5hws_table *isolated_tbl;
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher;
+	struct mlx5hws_action *action_metadata;
+	struct mlx5hws_action *action_go_to_tbl;
+	struct mlx5hws_action *action_last;
+	struct rhashtable refcount_hash;
+	struct mutex hash_lock; /* Protect the refcount rhashtable */
+	struct ida metadata_ida;
+};
+
 bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 					 u8 match_criteria_enable,
 					 struct mlx5hws_match_parameters *mask);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
index c00c138c3366..9c83753e4592 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
@@ -130,12 +130,6 @@ int mlx5hws_cmd_flow_table_destroy(struct mlx5_core_dev *mdev,
 	return mlx5_cmd_exec_in(mdev, destroy_flow_table, in);
 }
 
-void mlx5hws_cmd_alias_flow_table_destroy(struct mlx5_core_dev *mdev,
-					  u32 table_id)
-{
-	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_FT_ALIAS, table_id);
-}
-
 static int hws_cmd_flow_group_create(struct mlx5_core_dev *mdev,
 				     struct mlx5hws_cmd_fg_attr *fg_attr,
 				     u32 *group_id)
@@ -257,6 +251,12 @@ int mlx5hws_cmd_set_fte(struct mlx5_core_dev *mdev,
 						 dest->ext_reformat_id);
 				}
 				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+				MLX5_SET(dest_format, in_dests,
+					 destination_type, ifc_dest_type);
+				MLX5_SET(dest_format, in_dests, destination_id,
+					 dest->destination_id);
+				break;
 			default:
 				ret = -EOPNOTSUPP;
 				goto out;
@@ -359,7 +359,7 @@ void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx,
 	ft_attr->type = fw_ft_type;
 	ft_attr->table_miss_action = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL;
 
-	default_miss_tbl = ctx->common_res[type].default_miss->ft_id;
+	default_miss_tbl = ctx->common_res.default_miss->ft_id;
 	if (!default_miss_tbl) {
 		pr_warn("HWS: no flow table ID for default miss\n");
 		return;
@@ -406,7 +406,6 @@ int mlx5hws_cmd_rtc_create(struct mlx5_core_dev *mdev,
 	MLX5_SET(rtc, attr, match_definer_1, rtc_attr->match_definer_1);
 	MLX5_SET(rtc, attr, stc_id, rtc_attr->stc_base);
 	MLX5_SET(rtc, attr, ste_table_base_id, rtc_attr->ste_base);
-	MLX5_SET(rtc, attr, ste_table_offset, rtc_attr->ste_offset);
 	MLX5_SET(rtc, attr, miss_flow_table_id, rtc_attr->miss_ft_id);
 	MLX5_SET(rtc, attr, reparse_mode, rtc_attr->reparse_mode);
 
@@ -622,12 +621,12 @@ int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev,
 			   u32 pd,
 			   u32 *arg_id)
 {
+	u32 in[MLX5_ST_SZ_DW(create_modify_header_arg_in)] = {0};
 	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
-	u32 in[MLX5_ST_SZ_DW(create_arg_in)] = {0};
 	void *attr;
 	int ret;
 
-	attr = MLX5_ADDR_OF(create_arg_in, in, hdr);
+	attr = MLX5_ADDR_OF(create_modify_header_arg_in, in, hdr);
 	MLX5_SET(general_obj_in_cmd_hdr,
 		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
 	MLX5_SET(general_obj_in_cmd_hdr,
@@ -635,8 +634,8 @@ int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev,
 	MLX5_SET(general_obj_in_cmd_hdr,
 		 attr, op_param.create.log_obj_range, log_obj_range);
 
-	attr = MLX5_ADDR_OF(create_arg_in, in, arg);
-	MLX5_SET(arg, attr, access_pd, pd);
+	attr = MLX5_ADDR_OF(create_modify_header_arg_in, in, arg);
+	MLX5_SET(modify_header_arg, attr, access_pd, pd);
 
 	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (ret) {
@@ -812,7 +811,7 @@ int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev,
 				       struct mlx5hws_cmd_packet_reformat_create_attr *attr,
 				       u32 *reformat_id)
 {
-	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {0};
 	size_t insz, cmd_data_sz, cmd_total_sz;
 	void *prctx;
 	void *pdata;
@@ -845,7 +844,7 @@ int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev,
 		goto out;
 	}
 
-	*reformat_id = MLX5_GET(alloc_packet_reformat_out, out, packet_reformat_id);
+	*reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id);
 out:
 	kfree(in);
 	return ret;
@@ -854,13 +853,13 @@ out:
 int mlx5hws_cmd_packet_reformat_destroy(struct mlx5_core_dev *mdev,
 					u32 reformat_id)
 {
-	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {0};
 	int ret;
 
-	MLX5_SET(dealloc_packet_reformat_in, in, opcode,
+	MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
-	MLX5_SET(dealloc_packet_reformat_in, in,
+	MLX5_SET(dealloc_packet_reformat_context_in, in,
 		 packet_reformat_id, reformat_id);
 
 	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
@@ -889,73 +888,6 @@ int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn)
 	return ret;
 }
 
-int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev,
-					struct mlx5hws_cmd_allow_other_vhca_access_attr *attr)
-{
-	u32 out[MLX5_ST_SZ_DW(allow_other_vhca_access_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(allow_other_vhca_access_in)] = {0};
-	void *key;
-	int ret;
-
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, opcode, MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS);
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, object_type_to_be_accessed, attr->obj_type);
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, object_id_to_be_accessed, attr->obj_id);
-
-	key = MLX5_ADDR_OF(allow_other_vhca_access_in, in, access_key);
-	memcpy(key, attr->access_key, sizeof(attr->access_key));
-
-	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-	if (ret)
-		mlx5_core_err(mdev, "Failed to execute ALLOW_OTHER_VHCA_ACCESS command\n");
-
-	return ret;
-}
-
-int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev,
-				 struct mlx5hws_cmd_alias_obj_create_attr *alias_attr,
-				 u32 *obj_id)
-{
-	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
-	u32 in[MLX5_ST_SZ_DW(create_alias_obj_in)] = {0};
-	void *attr;
-	void *key;
-	int ret;
-
-	attr = MLX5_ADDR_OF(create_alias_obj_in, in, hdr);
-	MLX5_SET(general_obj_in_cmd_hdr,
-		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
-	MLX5_SET(general_obj_in_cmd_hdr,
-		 attr, obj_type, alias_attr->obj_type);
-	MLX5_SET(general_obj_in_cmd_hdr, attr, op_param.create.alias_object, 1);
-
-	attr = MLX5_ADDR_OF(create_alias_obj_in, in, alias_ctx);
-	MLX5_SET(alias_context, attr, vhca_id_to_be_accessed, alias_attr->vhca_id);
-	MLX5_SET(alias_context, attr, object_id_to_be_accessed, alias_attr->obj_id);
-
-	key = MLX5_ADDR_OF(alias_context, attr, access_key);
-	memcpy(key, alias_attr->access_key, sizeof(alias_attr->access_key));
-
-	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to create ALIAS OBJ\n");
-		goto out;
-	}
-
-	*obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
-out:
-	return ret;
-}
-
-int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev,
-				  u16 obj_type,
-				  u32 obj_id)
-{
-	return hws_cmd_general_obj_destroy(mdev, obj_type, obj_id);
-}
-
 int mlx5hws_cmd_generate_wqe(struct mlx5_core_dev *mdev,
 			     struct mlx5hws_cmd_generate_wqe_attr *attr,
 			     struct mlx5_cqe64 *ret_cqe)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
index 434f62b0904e..fa6bff210266 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
@@ -63,14 +63,13 @@ struct mlx5hws_cmd_forward_tbl {
 	u8 type;
 	u32 ft_id;
 	u32 fg_id;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_cmd_rtc_create_attr {
 	u32 pd;
 	u32 stc_base;
 	u32 ste_base;
-	u32 ste_offset;
 	u32 miss_ft_id;
 	bool fw_gen_wqe;
 	u8 update_index_mode;
@@ -258,9 +257,6 @@ int mlx5hws_cmd_flow_table_query(struct mlx5_core_dev *mdev,
 int mlx5hws_cmd_flow_table_destroy(struct mlx5_core_dev *mdev,
 				   u8 fw_ft_type, u32 table_id);
 
-void mlx5hws_cmd_alias_flow_table_destroy(struct mlx5_core_dev *mdev,
-					  u32 table_id);
-
 int mlx5hws_cmd_rtc_create(struct mlx5_core_dev *mdev,
 			   struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
 			   u32 *rtc_id);
@@ -334,14 +330,6 @@ mlx5hws_cmd_forward_tbl_create(struct mlx5_core_dev *mdev,
 void mlx5hws_cmd_forward_tbl_destroy(struct mlx5_core_dev *mdev,
 				     struct mlx5hws_cmd_forward_tbl *tbl);
 
-int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev,
-				 struct mlx5hws_cmd_alias_obj_create_attr *alias_attr,
-				 u32 *obj_id);
-
-int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev,
-				  u16 obj_type,
-				  u32 obj_id);
-
 int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn);
 
 int mlx5hws_cmd_query_caps(struct mlx5_core_dev *mdev,
@@ -352,9 +340,6 @@ void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx,
 					   enum mlx5hws_table_type type,
 					   struct mlx5hws_cmd_ft_modify_attr *ft_attr);
 
-int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev,
-					struct mlx5hws_cmd_allow_other_vhca_access_attr *attr);
-
 int mlx5hws_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_function,
 			   u16 vport_number, u16 *gvmi);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
index fd48b05e91e0..428dae869706 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
@@ -23,7 +23,6 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx)
 	struct mlx5hws_pool_attr pool_attr = {0};
 	u8 max_log_sz;
 	int ret;
-	int i;
 
 	ret = mlx5hws_pat_init_pattern_cache(&ctx->pattern_cache);
 	if (ret)
@@ -35,27 +34,20 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx)
 
 	/* Create an STC pool per FT type */
 	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STC;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STC_POOL;
 	max_log_sz = min(MLX5HWS_POOL_STC_LOG_SZ, ctx->caps->stc_alloc_log_max);
 	pool_attr.alloc_log_sz = max(max_log_sz, ctx->caps->stc_alloc_log_gran);
 
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		pool_attr.table_type = i;
-		ctx->stc_pool[i] = mlx5hws_pool_create(ctx, &pool_attr);
-		if (!ctx->stc_pool[i]) {
-			mlx5hws_err(ctx, "Failed to allocate STC pool [%d]", i);
-			ret = -ENOMEM;
-			goto free_stc_pools;
-		}
+	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
+	ctx->stc_pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!ctx->stc_pool) {
+		mlx5hws_err(ctx, "Failed to allocate STC pool\n");
+		ret = -ENOMEM;
+		goto uninit_cache;
 	}
 
 	return 0;
 
-free_stc_pools:
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++)
-		if (ctx->stc_pool[i])
-			mlx5hws_pool_destroy(ctx->stc_pool[i]);
-
+uninit_cache:
 	mlx5hws_definer_uninit_cache(ctx->definer_cache);
 uninit_pat_cache:
 	mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache);
@@ -64,12 +56,8 @@ uninit_pat_cache:
 
 static void hws_context_pools_uninit(struct mlx5hws_context *ctx)
 {
-	int i;
-
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		if (ctx->stc_pool[i])
-			mlx5hws_pool_destroy(ctx->stc_pool[i]);
-	}
+	if (ctx->stc_pool)
+		mlx5hws_pool_destroy(ctx->stc_pool);
 
 	mlx5hws_definer_uninit_cache(ctx->definer_cache);
 	mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache);
@@ -161,17 +149,25 @@ static int hws_context_init_hws(struct mlx5hws_context *ctx,
 	if (ret)
 		goto uninit_pd;
 
-	if (attr->bwc)
-		ctx->flags |= MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT;
+	/* Context has support for backward compatible API,
+	 * and does not have support for native HWS API.
+	 */
+	ctx->flags |= MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT;
 
 	ret = mlx5hws_send_queues_open(ctx, attr->queues, attr->queue_size);
 	if (ret)
 		goto pools_uninit;
 
+	ret = mlx5hws_action_ste_pool_init(ctx);
+	if (ret)
+		goto close_queues;
+
 	INIT_LIST_HEAD(&ctx->tbl_list);
 
 	return 0;
 
+close_queues:
+	mlx5hws_send_queues_close(ctx);
 pools_uninit:
 	hws_context_pools_uninit(ctx);
 uninit_pd:
@@ -184,6 +180,7 @@ static void hws_context_uninit_hws(struct mlx5hws_context *ctx)
 	if (!(ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT))
 		return;
 
+	mlx5hws_action_ste_pool_uninit(ctx);
 	mlx5hws_send_queues_close(ctx);
 	hws_context_pools_uninit(ctx);
 	hws_context_uninit_pd(ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
index 47f5cc8de73f..3f8938c73dc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
@@ -8,6 +8,7 @@ enum mlx5hws_context_flags {
 	MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT = 1 << 0,
 	MLX5HWS_CONTEXT_FLAG_PRIVATE_PD = 1 << 1,
 	MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT = 1 << 2,
+	MLX5HWS_CONTEXT_FLAG_NATIVE_SUPPORT = 1 << 3,
 };
 
 enum mlx5hws_context_shared_stc_type {
@@ -37,8 +38,10 @@ struct mlx5hws_context {
 	struct mlx5_core_dev *mdev;
 	struct mlx5hws_cmd_query_caps *caps;
 	u32 pd_num;
-	struct mlx5hws_pool *stc_pool[MLX5HWS_TABLE_TYPE_MAX];
-	struct mlx5hws_context_common_res common_res[MLX5HWS_TABLE_TYPE_MAX];
+	struct mlx5hws_pool *stc_pool;
+	struct mlx5hws_action_ste_pool *action_ste_pool; /* One per queue */
+	struct delayed_work action_ste_cleanup;
+	struct mlx5hws_context_common_res common_res;
 	struct mlx5hws_pattern_cache *pattern_cache;
 	struct mlx5hws_definer_cache *definer_cache;
 	struct mutex ctrl_lock; /* control lock to protect the whole context */
@@ -58,6 +61,11 @@ static inline bool mlx5hws_context_bwc_supported(struct mlx5hws_context *ctx)
 	return ctx->flags & MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT;
 }
 
+static inline bool mlx5hws_context_native_supported(struct mlx5hws_context *ctx)
+{
+	return ctx->flags & MLX5HWS_CONTEXT_FLAG_NATIVE_SUPPORT;
+}
+
 bool mlx5hws_context_cap_dynamic_reparse(struct mlx5hws_context *ctx);
 
 u8 mlx5hws_context_get_reparse_mode(struct mlx5hws_context *ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
index 5b200b4bc1a8..91568d6c1dac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
@@ -118,7 +118,6 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 {
 	enum mlx5hws_table_type tbl_type = matcher->tbl->type;
 	struct mlx5hws_cmd_ft_query_attr ft_attr = {0};
-	struct mlx5hws_pool_chunk *ste;
 	struct mlx5hws_pool *ste_pool;
 	u64 icm_addr_0 = 0;
 	u64 icm_addr_1 = 0;
@@ -134,12 +133,11 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 		   matcher->end_ft_id,
 		   matcher->col_matcher ? HWS_PTR_TO_ID(matcher->col_matcher) : 0);
 
-	ste = &matcher->match_ste.ste;
 	ste_pool = matcher->match_ste.pool;
 	if (ste_pool) {
-		ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+		ste_0_id = mlx5hws_pool_get_base_id(ste_pool);
 		if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
-			ste_1_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+			ste_1_id = mlx5hws_pool_get_base_mirror_id(ste_pool);
 	}
 
 	seq_printf(f, ",%d,%d,%d,%d",
@@ -148,19 +146,6 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 		   matcher->match_ste.rtc_1_id,
 		   (int)ste_1_id);
 
-	ste = &matcher->action_ste[0].ste;
-	ste_pool = matcher->action_ste[0].pool;
-	if (ste_pool) {
-		ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
-		if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
-			ste_1_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
-		else
-			ste_1_id = -1;
-	} else {
-		ste_0_id = -1;
-		ste_1_id = -1;
-	}
-
 	ft_attr.type = matcher->tbl->fw_ft_type;
 	ret = mlx5hws_cmd_flow_table_query(matcher->tbl->ctx->mdev,
 					   matcher->end_ft_id,
@@ -170,12 +155,7 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 	if (ret)
 		return ret;
 
-	seq_printf(f, ",%d,%d,%d,%d,%d,0x%llx,0x%llx\n",
-		   matcher->action_ste[0].rtc_0_id,
-		   (int)ste_0_id,
-		   matcher->action_ste[0].rtc_1_id,
-		   (int)ste_1_id,
-		   0,
+	seq_printf(f, ",-1,-1,-1,-1,0,0x%llx,0x%llx\n",
 		   mlx5hws_debug_icm_to_idx(icm_addr_0),
 		   mlx5hws_debug_icm_to_idx(icm_addr_1));
 
@@ -368,9 +348,10 @@ static int hws_debug_dump_context_info(struct seq_file *f, struct mlx5hws_contex
 
 static int hws_debug_dump_context_stc_resource(struct seq_file *f,
 					       struct mlx5hws_context *ctx,
-					       u32 tbl_type,
 					       struct mlx5hws_pool_resource *resource)
 {
+	u32 tbl_type = MLX5HWS_TABLE_TYPE_BASE + MLX5HWS_TABLE_TYPE_FDB;
+
 	seq_printf(f, "%d,0x%llx,%u,%u\n",
 		   MLX5HWS_DEBUG_RES_TYPE_CONTEXT_STC,
 		   HWS_PTR_TO_ID(ctx),
@@ -382,40 +363,65 @@ static int hws_debug_dump_context_stc_resource(struct seq_file *f,
 
 static int hws_debug_dump_context_stc(struct seq_file *f, struct mlx5hws_context *ctx)
 {
-	struct mlx5hws_pool *stc_pool;
-	u32 table_type;
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	int ret;
-	int i;
 
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		stc_pool = ctx->stc_pool[i];
-		table_type = MLX5HWS_TABLE_TYPE_BASE + i;
+	if (!stc_pool)
+		return 0;
 
-		if (!stc_pool)
-			continue;
+	if (stc_pool->resource) {
+		ret = hws_debug_dump_context_stc_resource(f, ctx,
+							  stc_pool->resource);
+		if (ret)
+			return ret;
+	}
 
-		if (stc_pool->resource[0]) {
-			ret = hws_debug_dump_context_stc_resource(f, ctx, table_type,
-								  stc_pool->resource[0]);
-			if (ret)
-				return ret;
-		}
+	if (stc_pool->mirror_resource) {
+		struct mlx5hws_pool_resource *res = stc_pool->mirror_resource;
 
-		if (i == MLX5HWS_TABLE_TYPE_FDB && stc_pool->mirror_resource[0]) {
-			ret = hws_debug_dump_context_stc_resource(f, ctx, table_type,
-								  stc_pool->mirror_resource[0]);
-			if (ret)
-				return ret;
-		}
+		ret = hws_debug_dump_context_stc_resource(f, ctx, res);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
 }
 
+static void
+hws_debug_dump_action_ste_table(struct seq_file *f,
+				struct mlx5hws_action_ste_table *action_tbl)
+{
+	int ste_0_id = mlx5hws_pool_get_base_id(action_tbl->pool);
+	int ste_1_id = mlx5hws_pool_get_base_mirror_id(action_tbl->pool);
+
+	seq_printf(f, "%d,0x%llx,%d,%d,%d,%d\n",
+		   MLX5HWS_DEBUG_RES_TYPE_ACTION_STE_TABLE,
+		   HWS_PTR_TO_ID(action_tbl),
+		   action_tbl->rtc_0_id, ste_0_id,
+		   action_tbl->rtc_1_id, ste_1_id);
+}
+
+static void hws_debug_dump_action_ste_pool(struct seq_file *f,
+					   struct mlx5hws_action_ste_pool *pool)
+{
+	struct mlx5hws_action_ste_table *action_tbl;
+	enum mlx5hws_pool_optimize opt;
+
+	mutex_lock(&pool->lock);
+	for (opt = MLX5HWS_POOL_OPTIMIZE_NONE; opt < MLX5HWS_POOL_OPTIMIZE_MAX;
+	     opt++) {
+		list_for_each_entry(action_tbl, &pool->elems[opt].available,
+				    list_node) {
+			hws_debug_dump_action_ste_table(f, action_tbl);
+		}
+	}
+	mutex_unlock(&pool->lock);
+}
+
 static int hws_debug_dump_context(struct seq_file *f, struct mlx5hws_context *ctx)
 {
 	struct mlx5hws_table *tbl;
-	int ret;
+	int ret, i;
 
 	ret = hws_debug_dump_context_info(f, ctx);
 	if (ret)
@@ -435,6 +441,9 @@ static int hws_debug_dump_context(struct seq_file *f, struct mlx5hws_context *ct
 			return ret;
 	}
 
+	for (i = 0; i < ctx->queues; i++)
+		hws_debug_dump_action_ste_pool(f, &ctx->action_ste_pool[i]);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
index e44e7ae28f93..89c396f9f266 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
@@ -26,6 +26,8 @@ enum mlx5hws_debug_res_type {
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_HASH_DEFINER = 4205,
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_RANGE_DEFINER = 4206,
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_COMPARE_MATCH_DEFINER = 4207,
+
+	MLX5HWS_DEBUG_RES_TYPE_ACTION_STE_TABLE = 4300,
 };
 
 static inline u64
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index 8fe96eb76baf..d45e1145d197 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -70,7 +70,7 @@
 			u32 second_dw_mask = (mask) & ((1 << _bit_off) - 1); \
 			_HWS_SET32(p, (v) >> _bit_off, byte_off, 0, (mask) >> _bit_off); \
 			_HWS_SET32(p, (v) & second_dw_mask, (byte_off) + DW_SIZE, \
-				    (bit_off) % BITS_IN_DW, second_dw_mask); \
+				    (bit_off + BITS_IN_DW) % BITS_IN_DW, second_dw_mask); \
 		} else { \
 			_HWS_SET32(p, v, byte_off, (bit_off), (mask)); \
 		} \
@@ -158,6 +158,218 @@ struct mlx5hws_definer_conv_data {
 	u32 match_flags;
 };
 
+#define HWS_DEFINER_ENTRY(name)[MLX5HWS_DEFINER_FNAME_##name] = #name
+
+static const char * const hws_definer_fname_to_str[] = {
+	HWS_DEFINER_ENTRY(ETH_SMAC_47_16_O),
+	HWS_DEFINER_ENTRY(ETH_SMAC_47_16_I),
+	HWS_DEFINER_ENTRY(ETH_SMAC_15_0_O),
+	HWS_DEFINER_ENTRY(ETH_SMAC_15_0_I),
+	HWS_DEFINER_ENTRY(ETH_DMAC_47_16_O),
+	HWS_DEFINER_ENTRY(ETH_DMAC_47_16_I),
+	HWS_DEFINER_ENTRY(ETH_DMAC_15_0_O),
+	HWS_DEFINER_ENTRY(ETH_DMAC_15_0_I),
+	HWS_DEFINER_ENTRY(ETH_TYPE_O),
+	HWS_DEFINER_ENTRY(ETH_TYPE_I),
+	HWS_DEFINER_ENTRY(ETH_L3_TYPE_O),
+	HWS_DEFINER_ENTRY(ETH_L3_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_TYPE_O),
+	HWS_DEFINER_ENTRY(VLAN_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_FIRST_PRIO_O),
+	HWS_DEFINER_ENTRY(VLAN_FIRST_PRIO_I),
+	HWS_DEFINER_ENTRY(VLAN_CFI_O),
+	HWS_DEFINER_ENTRY(VLAN_CFI_I),
+	HWS_DEFINER_ENTRY(VLAN_ID_O),
+	HWS_DEFINER_ENTRY(VLAN_ID_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_TYPE_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_PRIO_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_PRIO_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_CFI_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_CFI_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_ID_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_ID_I),
+	HWS_DEFINER_ENTRY(IPV4_IHL_O),
+	HWS_DEFINER_ENTRY(IPV4_IHL_I),
+	HWS_DEFINER_ENTRY(IP_DSCP_O),
+	HWS_DEFINER_ENTRY(IP_DSCP_I),
+	HWS_DEFINER_ENTRY(IP_ECN_O),
+	HWS_DEFINER_ENTRY(IP_ECN_I),
+	HWS_DEFINER_ENTRY(IP_TTL_O),
+	HWS_DEFINER_ENTRY(IP_TTL_I),
+	HWS_DEFINER_ENTRY(IPV4_DST_O),
+	HWS_DEFINER_ENTRY(IPV4_DST_I),
+	HWS_DEFINER_ENTRY(IPV4_SRC_O),
+	HWS_DEFINER_ENTRY(IPV4_SRC_I),
+	HWS_DEFINER_ENTRY(IP_VERSION_O),
+	HWS_DEFINER_ENTRY(IP_VERSION_I),
+	HWS_DEFINER_ENTRY(IP_FRAG_O),
+	HWS_DEFINER_ENTRY(IP_FRAG_I),
+	HWS_DEFINER_ENTRY(IP_LEN_O),
+	HWS_DEFINER_ENTRY(IP_LEN_I),
+	HWS_DEFINER_ENTRY(IP_TOS_O),
+	HWS_DEFINER_ENTRY(IP_TOS_I),
+	HWS_DEFINER_ENTRY(IPV6_FLOW_LABEL_O),
+	HWS_DEFINER_ENTRY(IPV6_FLOW_LABEL_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_127_96_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_95_64_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_63_32_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_31_0_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_127_96_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_95_64_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_63_32_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_31_0_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_127_96_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_95_64_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_63_32_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_31_0_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_127_96_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_95_64_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_63_32_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_31_0_I),
+	HWS_DEFINER_ENTRY(IP_PROTOCOL_O),
+	HWS_DEFINER_ENTRY(IP_PROTOCOL_I),
+	HWS_DEFINER_ENTRY(L4_SPORT_O),
+	HWS_DEFINER_ENTRY(L4_SPORT_I),
+	HWS_DEFINER_ENTRY(L4_DPORT_O),
+	HWS_DEFINER_ENTRY(L4_DPORT_I),
+	HWS_DEFINER_ENTRY(TCP_FLAGS_I),
+	HWS_DEFINER_ENTRY(TCP_FLAGS_O),
+	HWS_DEFINER_ENTRY(TCP_SEQ_NUM),
+	HWS_DEFINER_ENTRY(TCP_ACK_NUM),
+	HWS_DEFINER_ENTRY(GTP_TEID),
+	HWS_DEFINER_ENTRY(GTP_MSG_TYPE),
+	HWS_DEFINER_ENTRY(GTP_EXT_FLAG),
+	HWS_DEFINER_ENTRY(GTP_NEXT_EXT_HDR),
+	HWS_DEFINER_ENTRY(GTP_EXT_HDR_PDU),
+	HWS_DEFINER_ENTRY(GTP_EXT_HDR_QFI),
+	HWS_DEFINER_ENTRY(GTPU_DW0),
+	HWS_DEFINER_ENTRY(GTPU_FIRST_EXT_DW0),
+	HWS_DEFINER_ENTRY(GTPU_DW2),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_0),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_1),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_2),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_3),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_4),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_5),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_6),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_7),
+	HWS_DEFINER_ENTRY(VPORT_REG_C_0),
+	HWS_DEFINER_ENTRY(VXLAN_FLAGS),
+	HWS_DEFINER_ENTRY(VXLAN_VNI),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_FLAGS),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_RSVD0),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_PROTO),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_VNI),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_RSVD1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_LEN),
+	HWS_DEFINER_ENTRY(GENEVE_OAM),
+	HWS_DEFINER_ENTRY(GENEVE_PROTO),
+	HWS_DEFINER_ENTRY(GENEVE_VNI),
+	HWS_DEFINER_ENTRY(SOURCE_QP),
+	HWS_DEFINER_ENTRY(SOURCE_GVMI),
+	HWS_DEFINER_ENTRY(REG_0),
+	HWS_DEFINER_ENTRY(REG_1),
+	HWS_DEFINER_ENTRY(REG_2),
+	HWS_DEFINER_ENTRY(REG_3),
+	HWS_DEFINER_ENTRY(REG_4),
+	HWS_DEFINER_ENTRY(REG_5),
+	HWS_DEFINER_ENTRY(REG_6),
+	HWS_DEFINER_ENTRY(REG_7),
+	HWS_DEFINER_ENTRY(REG_8),
+	HWS_DEFINER_ENTRY(REG_9),
+	HWS_DEFINER_ENTRY(REG_10),
+	HWS_DEFINER_ENTRY(REG_11),
+	HWS_DEFINER_ENTRY(REG_A),
+	HWS_DEFINER_ENTRY(REG_B),
+	HWS_DEFINER_ENTRY(GRE_KEY_PRESENT),
+	HWS_DEFINER_ENTRY(GRE_C),
+	HWS_DEFINER_ENTRY(GRE_K),
+	HWS_DEFINER_ENTRY(GRE_S),
+	HWS_DEFINER_ENTRY(GRE_PROTOCOL),
+	HWS_DEFINER_ENTRY(GRE_OPT_KEY),
+	HWS_DEFINER_ENTRY(GRE_OPT_SEQ),
+	HWS_DEFINER_ENTRY(GRE_OPT_CHECKSUM),
+	HWS_DEFINER_ENTRY(INTEGRITY_O),
+	HWS_DEFINER_ENTRY(INTEGRITY_I),
+	HWS_DEFINER_ENTRY(ICMP_DW1),
+	HWS_DEFINER_ENTRY(ICMP_DW2),
+	HWS_DEFINER_ENTRY(ICMP_DW3),
+	HWS_DEFINER_ENTRY(IPSEC_SPI),
+	HWS_DEFINER_ENTRY(IPSEC_SEQUENCE_NUMBER),
+	HWS_DEFINER_ENTRY(IPSEC_SYNDROME),
+	HWS_DEFINER_ENTRY(MPLS0_O),
+	HWS_DEFINER_ENTRY(MPLS1_O),
+	HWS_DEFINER_ENTRY(MPLS2_O),
+	HWS_DEFINER_ENTRY(MPLS3_O),
+	HWS_DEFINER_ENTRY(MPLS4_O),
+	HWS_DEFINER_ENTRY(MPLS0_I),
+	HWS_DEFINER_ENTRY(MPLS1_I),
+	HWS_DEFINER_ENTRY(MPLS2_I),
+	HWS_DEFINER_ENTRY(MPLS3_I),
+	HWS_DEFINER_ENTRY(MPLS4_I),
+	HWS_DEFINER_ENTRY(FLEX_PARSER0_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER1_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER2_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER3_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER4_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER5_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER6_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER7_OK),
+	HWS_DEFINER_ENTRY(OKS2_MPLS0_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS1_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS2_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS3_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS4_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS0_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS1_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS2_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS3_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS4_I),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_0),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_2),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_3),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_4),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_5),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_6),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_7),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_0),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_2),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_3),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_4),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_5),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_6),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_7),
+	HWS_DEFINER_ENTRY(IB_L4_OPCODE),
+	HWS_DEFINER_ENTRY(IB_L4_QPN),
+	HWS_DEFINER_ENTRY(IB_L4_A),
+	HWS_DEFINER_ENTRY(RANDOM_NUM),
+	HWS_DEFINER_ENTRY(PTYPE_L2_O),
+	HWS_DEFINER_ENTRY(PTYPE_L2_I),
+	HWS_DEFINER_ENTRY(PTYPE_L3_O),
+	HWS_DEFINER_ENTRY(PTYPE_L3_I),
+	HWS_DEFINER_ENTRY(PTYPE_L4_O),
+	HWS_DEFINER_ENTRY(PTYPE_L4_I),
+	HWS_DEFINER_ENTRY(PTYPE_L4_EXT_O),
+	HWS_DEFINER_ENTRY(PTYPE_L4_EXT_I),
+	HWS_DEFINER_ENTRY(PTYPE_FRAG_O),
+	HWS_DEFINER_ENTRY(PTYPE_FRAG_I),
+	HWS_DEFINER_ENTRY(TNL_HDR_0),
+	HWS_DEFINER_ENTRY(TNL_HDR_1),
+	HWS_DEFINER_ENTRY(TNL_HDR_2),
+	HWS_DEFINER_ENTRY(TNL_HDR_3),
+	[MLX5HWS_DEFINER_FNAME_MAX] = "DEFINER_FNAME_UNKNOWN",
+};
+
+const char *mlx5hws_definer_fname_to_str(enum mlx5hws_definer_fname fname)
+{
+	if (fname > MLX5HWS_DEFINER_FNAME_MAX)
+		fname = MLX5HWS_DEFINER_FNAME_MAX;
+	return hws_definer_fname_to_str[fname];
+}
+
 static void
 hws_definer_ones_set(struct mlx5hws_definer_fc *fc,
 		     void *match_param,
@@ -500,7 +712,8 @@ hws_definer_check_match_flags(struct mlx5hws_definer_conv_data *cd)
 	return 0;
 
 err_conflict:
-	mlx5hws_err(cd->ctx, "Invalid definer fields combination\n");
+	mlx5hws_err(cd->ctx, "Invalid definer fields combination: match_flags = 0x%08x\n",
+		    cd->match_flags);
 	return -EINVAL;
 }
 
@@ -508,7 +721,7 @@ static int
 hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		       u32 *match_param)
 {
-	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	bool is_ipv6, smac_set, dmac_set, ip_addr_set, ip_ver_set;
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 	u32 *s_ipv6, *d_ipv6;
@@ -520,6 +733,20 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		return -EINVAL;
 	}
 
+	ip_addr_set = HWS_IS_FLD_SET_SZ(match_param,
+					outer_headers.src_ipv4_src_ipv6,
+					0x80) ||
+		      HWS_IS_FLD_SET_SZ(match_param,
+					outer_headers.dst_ipv4_dst_ipv6, 0x80);
+	ip_ver_set = HWS_IS_FLD_SET(match_param, outer_headers.ip_version) ||
+		     HWS_IS_FLD_SET(match_param, outer_headers.ethertype);
+
+	if (ip_addr_set && !ip_ver_set) {
+		mlx5hws_err(cd->ctx,
+			    "Unsupported match on IP address without version or ethertype\n");
+		return -EINVAL;
+	}
+
 	/* L2 Check ethertype */
 	HWS_SET_HDR(fc, match_param, ETH_TYPE_O,
 		    outer_headers.ethertype,
@@ -558,6 +785,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 	HWS_SET_HDR(fc, match_param, IP_PROTOCOL_O,
 		    outer_headers.ip_protocol,
 		    eth_l3_outer.protocol_next_header);
+	HWS_SET_HDR(fc, match_param, IP_VERSION_O,
+		    outer_headers.ip_version,
+		    eth_l3_outer.ip_version);
 	HWS_SET_HDR(fc, match_param, IP_TTL_O,
 		    outer_headers.ttl_hoplimit,
 		    eth_l3_outer.time_to_live_hop_limit);
@@ -569,10 +799,16 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 			      outer_headers.dst_ipv4_dst_ipv6.ipv6_layout);
 
 	/* Assume IPv6 is used if ipv6 bits are set */
-	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
-	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+	is_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2] ||
+		  d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+
+	/* IHL is an IPv4-specific field. */
+	if (is_ipv6 && HWS_IS_FLD_SET(match_param, outer_headers.ipv4_ihl)) {
+		mlx5hws_err(cd->ctx, "Unsupported match on IPv6 address and IPv4 IHL\n");
+		return -EINVAL;
+	}
 
-	if (is_s_ipv6) {
+	if (is_ipv6) {
 		/* Handle IPv6 source address */
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_O,
 			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -586,13 +822,6 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_O,
 			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_src_outer.ipv6_address_31_0);
-	} else {
-		/* Handle IPv4 source address */
-		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
-			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
-			    ipv4_src_dest_outer.source_address);
-	}
-	if (is_d_ipv6) {
 		/* Handle IPv6 destination address */
 		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_O,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -607,6 +836,10 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_dst_outer.ipv6_address_31_0);
 	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_outer.source_address);
 		/* Handle IPv4 destination address */
 		HWS_SET_HDR(fc, match_param, IPV4_DST_O,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
@@ -664,7 +897,7 @@ static int
 hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		       u32 *match_param)
 {
-	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	bool is_ipv6, smac_set, dmac_set, ip_addr_set, ip_ver_set;
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 	u32 *s_ipv6, *d_ipv6;
@@ -676,6 +909,20 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		return -EINVAL;
 	}
 
+	ip_addr_set = HWS_IS_FLD_SET_SZ(match_param,
+					inner_headers.src_ipv4_src_ipv6,
+					0x80) ||
+		      HWS_IS_FLD_SET_SZ(match_param,
+					inner_headers.dst_ipv4_dst_ipv6, 0x80);
+	ip_ver_set = HWS_IS_FLD_SET(match_param, inner_headers.ip_version) ||
+		     HWS_IS_FLD_SET(match_param, inner_headers.ethertype);
+
+	if (ip_addr_set && !ip_ver_set) {
+		mlx5hws_err(cd->ctx,
+			    "Unsupported match on IP address without version or ethertype\n");
+		return -EINVAL;
+	}
+
 	/* L2 Check ethertype */
 	HWS_SET_HDR(fc, match_param, ETH_TYPE_I,
 		    inner_headers.ethertype,
@@ -727,10 +974,16 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 			      inner_headers.dst_ipv4_dst_ipv6.ipv6_layout);
 
 	/* Assume IPv6 is used if ipv6 bits are set */
-	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
-	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+	is_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2] ||
+		  d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
 
-	if (is_s_ipv6) {
+	/* IHL is an IPv4-specific field. */
+	if (is_ipv6 && HWS_IS_FLD_SET(match_param, inner_headers.ipv4_ihl)) {
+		mlx5hws_err(cd->ctx, "Unsupported match on IPv6 address and IPv4 IHL\n");
+		return -EINVAL;
+	}
+
+	if (is_ipv6) {
 		/* Handle IPv6 source address */
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_I,
 			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -744,13 +997,6 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_I,
 			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_src_inner.ipv6_address_31_0);
-	} else {
-		/* Handle IPv4 source address */
-		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
-			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
-			    ipv4_src_dest_inner.source_address);
-	}
-	if (is_d_ipv6) {
 		/* Handle IPv6 destination address */
 		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_I,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -765,6 +1011,10 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_dst_inner.ipv6_address_31_0);
 	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_inner.source_address);
 		/* Handle IPv4 destination address */
 		HWS_SET_HDR(fc, match_param, IPV4_DST_I,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
@@ -1985,8 +2235,7 @@ int mlx5hws_definer_get_obj(struct mlx5hws_context *ctx,
 			continue;
 
 		/* Reuse definer and set LRU (move to be first in the list) */
-		list_del_init(&cached_definer->list_node);
-		list_add(&cached_definer->list_node, &cache->list_head);
+		list_move(&cached_definer->list_node, &cache->list_head);
 		cached_definer->refcount++;
 		return cached_definer->definer.obj_id;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
index 9432d5084def..62da55389331 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
@@ -785,7 +785,7 @@ struct mlx5hws_definer_cache {
 
 struct mlx5hws_definer_cache_item {
 	struct mlx5hws_definer definer;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 	struct list_head list_node;
 };
 
@@ -831,4 +831,6 @@ mlx5hws_definer_conv_match_params_to_compressed_fc(struct mlx5hws_context *ctx,
 						   u32 *match_param,
 						   int *fc_sz);
 
+const char *mlx5hws_definer_fname_to_str(enum mlx5hws_definer_fname fname);
+
 #endif /* HWS_DEFINER_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
new file mode 100644
index 000000000000..bf4643d0ce17
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -0,0 +1,1648 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#include <linux/mlx5/vport.h>
+#include <mlx5_core.h>
+#include <fs_core.h>
+#include <fs_cmd.h>
+#include "fs_hws_pools.h"
+#include "mlx5hws.h"
+
+#define MLX5HWS_CTX_MAX_NUM_OF_QUEUES 16
+#define MLX5HWS_CTX_QUEUE_SIZE 256
+
+static struct mlx5hws_action *
+mlx5_fs_create_action_remove_header_vlan(struct mlx5hws_context *ctx);
+static void
+mlx5_fs_destroy_pr_pool(struct mlx5_fs_pool *pool, struct xarray *pr_pools,
+			unsigned long index);
+static void
+mlx5_fs_destroy_mh_pool(struct mlx5_fs_pool *pool, struct xarray *mh_pools,
+			unsigned long index);
+
+static int mlx5_fs_init_hws_actions_pool(struct mlx5_core_dev *dev,
+					 struct mlx5_fs_hws_context *fs_ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool;
+	struct mlx5hws_action_reformat_header reformat_hdr = {};
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	enum mlx5hws_action_type action_type;
+	int err = -ENOSPC;
+
+	hws_pool->tag_action = mlx5hws_action_create_tag(ctx, flags);
+	if (!hws_pool->tag_action)
+		return err;
+	hws_pool->pop_vlan_action = mlx5hws_action_create_pop_vlan(ctx, flags);
+	if (!hws_pool->pop_vlan_action)
+		goto destroy_tag;
+	hws_pool->push_vlan_action = mlx5hws_action_create_push_vlan(ctx, flags);
+	if (!hws_pool->push_vlan_action)
+		goto destroy_pop_vlan;
+	hws_pool->drop_action = mlx5hws_action_create_dest_drop(ctx, flags);
+	if (!hws_pool->drop_action)
+		goto destroy_push_vlan;
+	action_type = MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2;
+	hws_pool->decapl2_action =
+		mlx5hws_action_create_reformat(ctx, action_type, 1,
+					       &reformat_hdr, 0, flags);
+	if (!hws_pool->decapl2_action)
+		goto destroy_drop;
+	hws_pool->remove_hdr_vlan_action =
+		mlx5_fs_create_action_remove_header_vlan(ctx);
+	if (!hws_pool->remove_hdr_vlan_action)
+		goto destroy_decapl2;
+	err = mlx5_fs_hws_pr_pool_init(&hws_pool->insert_hdr_pool, dev, 0,
+				       MLX5HWS_ACTION_TYP_INSERT_HEADER);
+	if (err)
+		goto destroy_remove_hdr;
+	err = mlx5_fs_hws_pr_pool_init(&hws_pool->dl3tnltol2_pool, dev, 0,
+				       MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2);
+	if (err)
+		goto cleanup_insert_hdr;
+	xa_init(&hws_pool->el2tol3tnl_pools);
+	xa_init(&hws_pool->el2tol2tnl_pools);
+	xa_init(&hws_pool->mh_pools);
+	xa_init(&hws_pool->table_dests);
+	xa_init(&hws_pool->vport_dests);
+	xa_init(&hws_pool->vport_vhca_dests);
+	xa_init(&hws_pool->aso_meters);
+	xa_init(&hws_pool->sample_dests);
+	return 0;
+
+cleanup_insert_hdr:
+	mlx5_fs_hws_pr_pool_cleanup(&hws_pool->insert_hdr_pool);
+destroy_remove_hdr:
+	mlx5hws_action_destroy(hws_pool->remove_hdr_vlan_action);
+destroy_decapl2:
+	mlx5hws_action_destroy(hws_pool->decapl2_action);
+destroy_drop:
+	mlx5hws_action_destroy(hws_pool->drop_action);
+destroy_push_vlan:
+	mlx5hws_action_destroy(hws_pool->push_vlan_action);
+destroy_pop_vlan:
+	mlx5hws_action_destroy(hws_pool->pop_vlan_action);
+destroy_tag:
+	mlx5hws_action_destroy(hws_pool->tag_action);
+	return err;
+}
+
+static void mlx5_fs_cleanup_hws_actions_pool(struct mlx5_fs_hws_context *fs_ctx)
+{
+	struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool;
+	struct mlx5_fs_hws_data *fs_hws_data;
+	struct mlx5hws_action *action;
+	struct mlx5_fs_pool *pool;
+	unsigned long i;
+
+	xa_for_each(&hws_pool->sample_dests, i, fs_hws_data)
+		kfree(fs_hws_data);
+	xa_destroy(&hws_pool->sample_dests);
+	xa_for_each(&hws_pool->aso_meters, i, fs_hws_data)
+		kfree(fs_hws_data);
+	xa_destroy(&hws_pool->aso_meters);
+	xa_for_each(&hws_pool->vport_vhca_dests, i, action)
+		mlx5hws_action_destroy(action);
+	xa_destroy(&hws_pool->vport_vhca_dests);
+	xa_for_each(&hws_pool->vport_dests, i, action)
+		mlx5hws_action_destroy(action);
+	xa_destroy(&hws_pool->vport_dests);
+	xa_destroy(&hws_pool->table_dests);
+	xa_for_each(&hws_pool->mh_pools, i, pool)
+		mlx5_fs_destroy_mh_pool(pool, &hws_pool->mh_pools, i);
+	xa_destroy(&hws_pool->mh_pools);
+	xa_for_each(&hws_pool->el2tol2tnl_pools, i, pool)
+		mlx5_fs_destroy_pr_pool(pool, &hws_pool->el2tol2tnl_pools, i);
+	xa_destroy(&hws_pool->el2tol2tnl_pools);
+	xa_for_each(&hws_pool->el2tol3tnl_pools, i, pool)
+		mlx5_fs_destroy_pr_pool(pool, &hws_pool->el2tol3tnl_pools, i);
+	xa_destroy(&hws_pool->el2tol3tnl_pools);
+	mlx5_fs_hws_pr_pool_cleanup(&hws_pool->dl3tnltol2_pool);
+	mlx5_fs_hws_pr_pool_cleanup(&hws_pool->insert_hdr_pool);
+	mlx5hws_action_destroy(hws_pool->remove_hdr_vlan_action);
+	mlx5hws_action_destroy(hws_pool->decapl2_action);
+	mlx5hws_action_destroy(hws_pool->drop_action);
+	mlx5hws_action_destroy(hws_pool->push_vlan_action);
+	mlx5hws_action_destroy(hws_pool->pop_vlan_action);
+	mlx5hws_action_destroy(hws_pool->tag_action);
+}
+
+static int mlx5_cmd_hws_create_ns(struct mlx5_flow_root_namespace *ns)
+{
+	struct mlx5hws_context_attr hws_ctx_attr = {};
+	int err;
+
+	hws_ctx_attr.queues = min_t(int, num_online_cpus(),
+				    MLX5HWS_CTX_MAX_NUM_OF_QUEUES);
+	hws_ctx_attr.queue_size = MLX5HWS_CTX_QUEUE_SIZE;
+
+	ns->fs_hws_context.hws_ctx =
+		mlx5hws_context_open(ns->dev, &hws_ctx_attr);
+	if (!ns->fs_hws_context.hws_ctx) {
+		mlx5_core_err(ns->dev, "Failed to create hws flow namespace\n");
+		return -EINVAL;
+	}
+	err = mlx5_fs_init_hws_actions_pool(ns->dev, &ns->fs_hws_context);
+	if (err) {
+		mlx5_core_err(ns->dev, "Failed to init hws actions pool\n");
+		mlx5hws_context_close(ns->fs_hws_context.hws_ctx);
+		return err;
+	}
+	return 0;
+}
+
+static int mlx5_cmd_hws_destroy_ns(struct mlx5_flow_root_namespace *ns)
+{
+	mlx5_fs_cleanup_hws_actions_pool(&ns->fs_hws_context);
+	return mlx5hws_context_close(ns->fs_hws_context.hws_ctx);
+}
+
+static int mlx5_cmd_hws_set_peer(struct mlx5_flow_root_namespace *ns,
+				 struct mlx5_flow_root_namespace *peer_ns,
+				 u16 peer_vhca_id)
+{
+	struct mlx5hws_context *peer_ctx = NULL;
+
+	if (peer_ns)
+		peer_ctx = peer_ns->fs_hws_context.hws_ctx;
+	mlx5hws_context_set_peer(ns->fs_hws_context.hws_ctx, peer_ctx,
+				 peer_vhca_id);
+	return 0;
+}
+
+static int mlx5_fs_set_ft_default_miss(struct mlx5_flow_root_namespace *ns,
+				       struct mlx5_flow_table *ft,
+				       struct mlx5_flow_table *next_ft)
+{
+	struct mlx5hws_table *next_tbl;
+	int err;
+
+	if (!ns->fs_hws_context.hws_ctx)
+		return -EINVAL;
+
+	/* if no change required, return */
+	if (!next_ft && !ft->fs_hws_table.miss_ft_set)
+		return 0;
+
+	next_tbl = next_ft ? next_ft->fs_hws_table.hws_table : NULL;
+	err = mlx5hws_table_set_default_miss(ft->fs_hws_table.hws_table, next_tbl);
+	if (err) {
+		mlx5_core_err(ns->dev, "Failed setting FT default miss (%d)\n", err);
+		return err;
+	}
+	ft->fs_hws_table.miss_ft_set = !!next_tbl;
+	return 0;
+}
+
+static int mlx5_fs_add_flow_table_dest_action(struct mlx5_flow_root_namespace *ns,
+					      struct mlx5_flow_table *ft)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+	struct mlx5hws_action *dest_ft_action;
+	struct xarray *dests_xa;
+	int err;
+
+	dest_ft_action = mlx5hws_action_create_dest_table_num(fs_ctx->hws_ctx,
+							      ft->id, flags);
+	if (!dest_ft_action) {
+		mlx5_core_err(ns->dev, "Failed creating dest table action\n");
+		return -ENOMEM;
+	}
+
+	dests_xa = &fs_ctx->hws_pool.table_dests;
+	err = xa_insert(dests_xa, ft->id, dest_ft_action, GFP_KERNEL);
+	if (err)
+		mlx5hws_action_destroy(dest_ft_action);
+	return err;
+}
+
+static int mlx5_fs_del_flow_table_dest_action(struct mlx5_flow_root_namespace *ns,
+					      struct mlx5_flow_table *ft)
+{
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+	struct mlx5hws_action *dest_ft_action;
+	struct xarray *dests_xa;
+	int err;
+
+	dests_xa = &fs_ctx->hws_pool.table_dests;
+	dest_ft_action = xa_erase(dests_xa, ft->id);
+	if (!dest_ft_action) {
+		mlx5_core_err(ns->dev, "Failed to erase dest ft action\n");
+		return -ENOENT;
+	}
+
+	err = mlx5hws_action_destroy(dest_ft_action);
+	if (err)
+		mlx5_core_err(ns->dev, "Failed to destroy dest ft action\n");
+	return err;
+}
+
+static int mlx5_cmd_hws_create_flow_table(struct mlx5_flow_root_namespace *ns,
+					  struct mlx5_flow_table *ft,
+					  struct mlx5_flow_table_attr *ft_attr,
+					  struct mlx5_flow_table *next_ft)
+{
+	struct mlx5hws_context *ctx = ns->fs_hws_context.hws_ctx;
+	struct mlx5hws_table_attr tbl_attr = {};
+	struct mlx5hws_table *tbl;
+	int err;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft)) {
+		err = mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, ft_attr,
+								   next_ft);
+		if (err)
+			return err;
+		err = mlx5_fs_add_flow_table_dest_action(ns, ft);
+		if (err)
+			mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft);
+		return err;
+	}
+
+	if (ns->table_type != FS_FT_FDB) {
+		mlx5_core_err(ns->dev, "Table type %d not supported for HWS\n",
+			      ns->table_type);
+		return -EOPNOTSUPP;
+	}
+
+	tbl_attr.type = MLX5HWS_TABLE_TYPE_FDB;
+	tbl_attr.level = ft_attr->level;
+	tbl = mlx5hws_table_create(ctx, &tbl_attr);
+	if (!tbl) {
+		mlx5_core_err(ns->dev, "Failed creating hws flow_table\n");
+		return -EINVAL;
+	}
+
+	ft->fs_hws_table.hws_table = tbl;
+	ft->id = mlx5hws_table_get_id(tbl);
+
+	if (next_ft) {
+		err = mlx5_fs_set_ft_default_miss(ns, ft, next_ft);
+		if (err)
+			goto destroy_table;
+	}
+
+	ft->max_fte = INT_MAX;
+
+	err = mlx5_fs_add_flow_table_dest_action(ns, ft);
+	if (err)
+		goto clear_ft_miss;
+	return 0;
+
+clear_ft_miss:
+	mlx5_fs_set_ft_default_miss(ns, ft, NULL);
+destroy_table:
+	mlx5hws_table_destroy(tbl);
+	ft->fs_hws_table.hws_table = NULL;
+	return err;
+}
+
+static int mlx5_cmd_hws_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
+					   struct mlx5_flow_table *ft)
+{
+	int err;
+
+	err = mlx5_fs_del_flow_table_dest_action(ns, ft);
+	if (err)
+		mlx5_core_err(ns->dev, "Failed to remove dest action (%d)\n", err);
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft);
+
+	err = mlx5_fs_set_ft_default_miss(ns, ft, NULL);
+	if (err)
+		mlx5_core_err(ns->dev, "Failed to disconnect next table (%d)\n", err);
+
+	err = mlx5hws_table_destroy(ft->fs_hws_table.hws_table);
+	if (err)
+		mlx5_core_err(ns->dev, "Failed to destroy flow_table (%d)\n", err);
+
+	return err;
+}
+
+static int mlx5_cmd_hws_modify_flow_table(struct mlx5_flow_root_namespace *ns,
+					  struct mlx5_flow_table *ft,
+					  struct mlx5_flow_table *next_ft)
+{
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->modify_flow_table(ns, ft, next_ft);
+
+	return mlx5_fs_set_ft_default_miss(ns, ft, next_ft);
+}
+
+static int mlx5_cmd_hws_update_root_ft(struct mlx5_flow_root_namespace *ns,
+				       struct mlx5_flow_table *ft,
+				       u32 underlay_qpn,
+				       bool disconnect)
+{
+	return mlx5_fs_cmd_get_fw_cmds()->update_root_ft(ns, ft, underlay_qpn,
+							 disconnect);
+}
+
+static int mlx5_cmd_hws_create_flow_group(struct mlx5_flow_root_namespace *ns,
+					  struct mlx5_flow_table *ft, u32 *in,
+					  struct mlx5_flow_group *fg)
+{
+	struct mlx5hws_match_parameters mask;
+	struct mlx5hws_bwc_matcher *matcher;
+	u8 match_criteria_enable;
+	u32 priority;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in, fg);
+
+	mask.match_buf = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+	mask.match_sz = sizeof(fg->mask.match_criteria);
+
+	match_criteria_enable = MLX5_GET(create_flow_group_in, in,
+					 match_criteria_enable);
+	priority = MLX5_GET(create_flow_group_in, in, start_flow_index);
+	matcher = mlx5hws_bwc_matcher_create(ft->fs_hws_table.hws_table,
+					     priority, match_criteria_enable,
+					     &mask);
+	if (!matcher) {
+		mlx5_core_err(ns->dev, "Failed creating matcher\n");
+		return -EINVAL;
+	}
+
+	fg->fs_hws_matcher.matcher = matcher;
+	return 0;
+}
+
+static int mlx5_cmd_hws_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
+					   struct mlx5_flow_table *ft,
+					   struct mlx5_flow_group *fg)
+{
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg);
+
+	return mlx5hws_bwc_matcher_destroy(fg->fs_hws_matcher.matcher);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_ft(struct mlx5_fs_hws_context *fs_ctx,
+			   struct mlx5_flow_rule *dst)
+{
+	return xa_load(&fs_ctx->hws_pool.table_dests, dst->dest_attr.ft->id);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_table_num(struct mlx5_fs_hws_context *fs_ctx,
+				  struct mlx5_flow_rule *dst)
+{
+	u32 table_num = dst->dest_attr.ft_num;
+
+	return xa_load(&fs_ctx->hws_pool.table_dests, table_num);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_dest_action_table_num(struct mlx5_fs_hws_context *fs_ctx,
+				     struct mlx5_flow_rule *dst)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	u32 table_num = dst->dest_attr.ft_num;
+
+	return mlx5hws_action_create_dest_table_num(ctx, table_num, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_vport(struct mlx5_fs_hws_context *fs_ctx,
+			      struct mlx5_flow_rule *dst,
+			      bool is_dest_type_uplink)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_flow_destination *dest_attr = &dst->dest_attr;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5hws_action *dest;
+	struct xarray *dests_xa;
+	bool vhca_id_valid;
+	unsigned long idx;
+	u16 vport_num;
+	int err;
+
+	vhca_id_valid = is_dest_type_uplink ||
+			(dest_attr->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID);
+	vport_num = is_dest_type_uplink ? MLX5_VPORT_UPLINK : dest_attr->vport.num;
+	if (vhca_id_valid) {
+		dests_xa = &fs_ctx->hws_pool.vport_vhca_dests;
+		idx = (unsigned long)dest_attr->vport.vhca_id << 16 | vport_num;
+	} else {
+		dests_xa = &fs_ctx->hws_pool.vport_dests;
+		idx = vport_num;
+	}
+dest_load:
+	dest = xa_load(dests_xa, idx);
+	if (dest)
+		return dest;
+
+	dest = mlx5hws_action_create_dest_vport(ctx, vport_num,	vhca_id_valid,
+						dest_attr->vport.vhca_id, flags);
+
+	err = xa_insert(dests_xa, idx, dest, GFP_KERNEL);
+	if (err) {
+		mlx5hws_action_destroy(dest);
+		dest = NULL;
+
+		if (err == -EBUSY)
+			/* xarray entry was already stored by another thread */
+			goto dest_load;
+	}
+
+	return dest;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_dest_action_range(struct mlx5hws_context *ctx,
+				 struct mlx5_flow_rule *dst)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_flow_destination *dest_attr = &dst->dest_attr;
+
+	return mlx5hws_action_create_dest_match_range(ctx,
+						      dest_attr->range.field,
+						      dest_attr->range.hit_ft,
+						      dest_attr->range.miss_ft,
+						      dest_attr->range.min,
+						      dest_attr->range.max,
+						      flags);
+}
+
+static struct mlx5_fs_hws_data *
+mlx5_fs_get_cached_hws_data(struct xarray *cache_xa, unsigned long index)
+{
+	struct mlx5_fs_hws_data *fs_hws_data;
+	int err;
+
+	xa_lock(cache_xa);
+	fs_hws_data = xa_load(cache_xa, index);
+	if (!fs_hws_data) {
+		fs_hws_data = kzalloc(sizeof(*fs_hws_data), GFP_ATOMIC);
+		if (!fs_hws_data) {
+			xa_unlock(cache_xa);
+			return NULL;
+		}
+		refcount_set(&fs_hws_data->hws_action_refcount, 0);
+		mutex_init(&fs_hws_data->lock);
+		err = __xa_insert(cache_xa, index, fs_hws_data, GFP_ATOMIC);
+		if (err) {
+			kfree(fs_hws_data);
+			xa_unlock(cache_xa);
+			return NULL;
+		}
+	}
+	xa_unlock(cache_xa);
+
+	return fs_hws_data;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_aso_meter(struct mlx5_fs_hws_context *fs_ctx,
+			     struct mlx5_exe_aso *exe_aso)
+{
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5_fs_hws_data *meter_hws_data;
+	u32 id = exe_aso->base_id;
+	struct xarray *meters_xa;
+
+	meters_xa = &fs_ctx->hws_pool.aso_meters;
+	meter_hws_data = mlx5_fs_get_cached_hws_data(meters_xa, id);
+	if (!meter_hws_data)
+		return NULL;
+
+	create_ctx.hws_ctx = ctx;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_ASO_METER;
+	create_ctx.id = id;
+	create_ctx.return_reg_id = exe_aso->return_reg_id;
+
+	return mlx5_fs_get_hws_action(meter_hws_data, &create_ctx);
+}
+
+static void mlx5_fs_put_action_aso_meter(struct mlx5_fs_hws_context *fs_ctx,
+					 struct mlx5_exe_aso *exe_aso)
+{
+	struct mlx5_fs_hws_data *meter_hws_data;
+	struct xarray *meters_xa;
+
+	meters_xa = &fs_ctx->hws_pool.aso_meters;
+	meter_hws_data = xa_load(meters_xa, exe_aso->base_id);
+	if (!meter_hws_data)
+		return;
+	return mlx5_fs_put_hws_action(meter_hws_data);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_sampler(struct mlx5_fs_hws_context *fs_ctx,
+				struct mlx5_flow_rule *dst)
+{
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5_fs_hws_data *sampler_hws_data;
+	u32 id = dst->dest_attr.sampler_id;
+	struct xarray *sampler_xa;
+
+	sampler_xa = &fs_ctx->hws_pool.sample_dests;
+	sampler_hws_data = mlx5_fs_get_cached_hws_data(sampler_xa, id);
+	if (!sampler_hws_data)
+		return NULL;
+
+	create_ctx.hws_ctx = ctx;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_SAMPLER;
+	create_ctx.id = id;
+
+	return mlx5_fs_get_hws_action(sampler_hws_data, &create_ctx);
+}
+
+static void mlx5_fs_put_dest_action_sampler(struct mlx5_fs_hws_context *fs_ctx,
+					    u32 sampler_id)
+{
+	struct mlx5_fs_hws_data *sampler_hws_data;
+	struct xarray *sampler_xa;
+
+	sampler_xa = &fs_ctx->hws_pool.sample_dests;
+	sampler_hws_data = xa_load(sampler_xa, sampler_id);
+	if (!sampler_hws_data)
+		return;
+
+	mlx5_fs_put_hws_action(sampler_hws_data);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_action_dest_array(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_dest_attr *dests,
+				 u32 num_of_dests, bool ignore_flow_level,
+				 u32 flow_source)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+
+	return mlx5hws_action_create_dest_array(ctx, num_of_dests, dests,
+						ignore_flow_level,
+						flow_source, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_push_vlan(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.push_vlan_action;
+}
+
+static u32 mlx5_fs_calc_vlan_hdr(struct mlx5_fs_vlan *vlan)
+{
+	u16 n_ethtype = vlan->ethtype;
+	u8 prio = vlan->prio;
+	u16 vid = vlan->vid;
+
+	return (u32)n_ethtype << 16 | (u32)(prio) << 12 | (u32)vid;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_pop_vlan(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.pop_vlan_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_decap_tnl_l2_to_l2(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.decapl2_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_drop(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.drop_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_tag(struct mlx5_fs_hws_context *fs_ctx)
+{
+	return fs_ctx->hws_pool.tag_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_action_last(struct mlx5hws_context *ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+
+	return mlx5hws_action_create_last(ctx, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_hws_action(struct mlx5_fs_hws_create_action_ctx *create_ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+
+	switch (create_ctx->actions_type) {
+	case MLX5HWS_ACTION_TYP_CTR:
+		return mlx5hws_action_create_counter(create_ctx->hws_ctx,
+						     create_ctx->id, flags);
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+		return mlx5hws_action_create_aso_meter(create_ctx->hws_ctx,
+						       create_ctx->id,
+						       create_ctx->return_reg_id,
+						       flags);
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		return mlx5hws_action_create_flow_sampler(create_ctx->hws_ctx,
+							  create_ctx->id, flags);
+	default:
+		return NULL;
+	}
+}
+
+struct mlx5hws_action *
+mlx5_fs_get_hws_action(struct mlx5_fs_hws_data *fs_hws_data,
+		       struct mlx5_fs_hws_create_action_ctx *create_ctx)
+{
+	/* try avoid locking if not necessary */
+	if (refcount_inc_not_zero(&fs_hws_data->hws_action_refcount))
+		return fs_hws_data->hws_action;
+
+	mutex_lock(&fs_hws_data->lock);
+	if (refcount_inc_not_zero(&fs_hws_data->hws_action_refcount)) {
+		mutex_unlock(&fs_hws_data->lock);
+		return fs_hws_data->hws_action;
+	}
+	fs_hws_data->hws_action = mlx5_fs_create_hws_action(create_ctx);
+	if (!fs_hws_data->hws_action) {
+		mutex_unlock(&fs_hws_data->lock);
+		return NULL;
+	}
+	refcount_set(&fs_hws_data->hws_action_refcount, 1);
+	mutex_unlock(&fs_hws_data->lock);
+
+	return fs_hws_data->hws_action;
+}
+
+void mlx5_fs_put_hws_action(struct mlx5_fs_hws_data *fs_hws_data)
+{
+	if (!fs_hws_data)
+		return;
+
+	/* try avoid locking if not necessary */
+	if (refcount_dec_not_one(&fs_hws_data->hws_action_refcount))
+		return;
+
+	mutex_lock(&fs_hws_data->lock);
+	if (!refcount_dec_and_test(&fs_hws_data->hws_action_refcount)) {
+		mutex_unlock(&fs_hws_data->lock);
+		return;
+	}
+	mlx5hws_action_destroy(fs_hws_data->hws_action);
+	fs_hws_data->hws_action = NULL;
+	mutex_unlock(&fs_hws_data->lock);
+}
+
+static void mlx5_fs_destroy_fs_action(struct mlx5_flow_root_namespace *ns,
+				      struct mlx5_fs_hws_rule_action *fs_action)
+{
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+
+	switch (mlx5hws_action_get_type(fs_action->action)) {
+	case MLX5HWS_ACTION_TYP_CTR:
+		mlx5_fc_put_hws_action(fs_action->counter);
+		break;
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+		mlx5_fs_put_action_aso_meter(fs_ctx, fs_action->exe_aso);
+		break;
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		mlx5_fs_put_dest_action_sampler(fs_ctx, fs_action->sampler_id);
+		break;
+	default:
+		mlx5hws_action_destroy(fs_action->action);
+	}
+}
+
+static void
+mlx5_fs_destroy_fs_actions(struct mlx5_flow_root_namespace *ns,
+			   struct mlx5_fs_hws_rule_action **fs_actions,
+			   int *num_fs_actions)
+{
+	int i;
+
+	/* Free in reverse order to handle action dependencies */
+	for (i = *num_fs_actions - 1; i >= 0; i--)
+		mlx5_fs_destroy_fs_action(ns, *fs_actions + i);
+	*num_fs_actions = 0;
+	kfree(*fs_actions);
+	*fs_actions = NULL;
+}
+
+/* Splits FTE's actions into cached, rule and destination actions.
+ * The cached and destination actions are saved on the fte hws rule.
+ * The rule actions are returned as a parameter, together with their count.
+ * We want to support a rule with 32 destinations, which means we need to
+ * account for 32 destinations plus usually a counter plus one more action
+ * for a multi-destination flow table.
+ * 32 is SW limitation for array size, keep. HWS limitation is 16M STEs per matcher
+ */
+#define MLX5_FLOW_CONTEXT_ACTION_MAX 34
+static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
+				       struct mlx5_flow_table *ft,
+				       struct mlx5_flow_group *group,
+				       struct fs_fte *fte,
+				       struct mlx5hws_rule_action **ractions)
+{
+	struct mlx5_flow_act *fte_action = &fte->act_dests.action;
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+	struct mlx5hws_action_dest_attr *dest_actions;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5_fs_hws_rule_action *fs_actions;
+	struct mlx5_core_dev *dev = ns->dev;
+	struct mlx5hws_action *dest_action;
+	struct mlx5hws_action *tmp_action;
+	struct mlx5_fs_hws_pr *pr_data;
+	struct mlx5_fs_hws_mh *mh_data;
+	bool delay_encap_set = false;
+	struct mlx5_flow_rule *dst;
+	int num_dest_actions = 0;
+	int num_fs_actions = 0;
+	int num_actions = 0;
+	int err;
+
+	*ractions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(**ractions),
+			    GFP_KERNEL);
+	if (!*ractions) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	fs_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX,
+			     sizeof(*fs_actions), GFP_KERNEL);
+	if (!fs_actions) {
+		err = -ENOMEM;
+		goto free_actions_alloc;
+	}
+
+	dest_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX,
+			       sizeof(*dest_actions), GFP_KERNEL);
+	if (!dest_actions) {
+		err = -ENOMEM;
+		goto free_fs_actions_alloc;
+	}
+
+	/* The order of the actions are must to be kept, only the following
+	 * order is supported by HW steering:
+	 * HWS: decap -> remove_hdr -> pop_vlan -> modify header -> push_vlan
+	 *      -> reformat (insert_hdr/encap) -> ctr -> tag -> aso
+	 *      -> drop -> FWD:tbl/vport/sampler/tbl_num/range -> dest_array -> last
+	 */
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
+		tmp_action = mlx5_fs_get_action_decap_tnl_l2_to_l2(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_dest_actions_alloc;
+		}
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
+		int reformat_type = fte_action->pkt_reformat->reformat_type;
+
+		if (fte_action->pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_FW) {
+			mlx5_core_err(dev, "FW-owned reformat can't be used in HWS rule\n");
+			err = -EINVAL;
+			goto free_actions;
+		}
+
+		if (reformat_type == MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2) {
+			pr_data = fte_action->pkt_reformat->fs_hws_action.pr_data;
+			(*ractions)[num_actions].reformat.offset = pr_data->offset;
+			(*ractions)[num_actions].reformat.hdr_idx = pr_data->hdr_idx;
+			(*ractions)[num_actions].reformat.data = pr_data->data;
+			(*ractions)[num_actions++].action =
+				fte_action->pkt_reformat->fs_hws_action.hws_action;
+		} else if (reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR) {
+			(*ractions)[num_actions++].action =
+				fte_action->pkt_reformat->fs_hws_action.hws_action;
+		} else {
+			delay_encap_set = true;
+		}
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) {
+		tmp_action = mlx5_fs_get_action_pop_vlan(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) {
+		tmp_action = mlx5_fs_get_action_pop_vlan(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+		mh_data = fte_action->modify_hdr->fs_hws_action.mh_data;
+		(*ractions)[num_actions].modify_header.offset = mh_data->offset;
+		(*ractions)[num_actions].modify_header.data = mh_data->data;
+		(*ractions)[num_actions++].action =
+			fte_action->modify_hdr->fs_hws_action.hws_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
+		tmp_action = mlx5_fs_get_action_push_vlan(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].push_vlan.vlan_hdr =
+			htonl(mlx5_fs_calc_vlan_hdr(&fte_action->vlan[0]));
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
+		tmp_action = mlx5_fs_get_action_push_vlan(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].push_vlan.vlan_hdr =
+			htonl(mlx5_fs_calc_vlan_hdr(&fte_action->vlan[1]));
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (delay_encap_set) {
+		pr_data = fte_action->pkt_reformat->fs_hws_action.pr_data;
+		(*ractions)[num_actions].reformat.offset = pr_data->offset;
+		(*ractions)[num_actions].reformat.data = pr_data->data;
+		(*ractions)[num_actions++].action =
+			fte_action->pkt_reformat->fs_hws_action.hws_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+		list_for_each_entry(dst, &fte->node.children, node.list) {
+			struct mlx5_fc *counter;
+
+			if (dst->dest_attr.type !=
+			    MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+				continue;
+
+			if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+				err = -EOPNOTSUPP;
+				goto free_actions;
+			}
+
+			counter = dst->dest_attr.counter;
+			tmp_action = mlx5_fc_get_hws_action(ctx, counter);
+			if (!tmp_action) {
+				err = -EINVAL;
+				goto free_actions;
+			}
+
+			(*ractions)[num_actions].counter.offset =
+				mlx5_fc_id(counter) - mlx5_fc_get_base_id(counter);
+			(*ractions)[num_actions++].action = tmp_action;
+			fs_actions[num_fs_actions].action = tmp_action;
+			fs_actions[num_fs_actions++].counter = counter;
+		}
+	}
+
+	if (fte->act_dests.flow_context.flow_tag) {
+		if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+		tmp_action = mlx5_fs_get_action_tag(fs_ctx);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].tag.value = fte->act_dests.flow_context.flow_tag;
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) {
+		if (fte_action->exe_aso.type != MLX5_EXE_ASO_FLOW_METER ||
+		    num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+
+		tmp_action = mlx5_fs_get_action_aso_meter(fs_ctx,
+							  &fte_action->exe_aso);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].aso_meter.offset =
+			fte_action->exe_aso.flow_meter.meter_idx;
+		(*ractions)[num_actions].aso_meter.init_color =
+			fte_action->exe_aso.flow_meter.init_color;
+		(*ractions)[num_actions++].action = tmp_action;
+		fs_actions[num_fs_actions].action = tmp_action;
+		fs_actions[num_fs_actions++].exe_aso = &fte_action->exe_aso;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
+		dest_action = mlx5_fs_get_dest_action_drop(fs_ctx);
+		if (!dest_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		dest_actions[num_dest_actions++].dest = dest_action;
+	}
+
+	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+		list_for_each_entry(dst, &fte->node.children, node.list) {
+			struct mlx5_flow_destination *attr = &dst->dest_attr;
+			bool type_uplink =
+				attr->type == MLX5_FLOW_DESTINATION_TYPE_UPLINK;
+
+			if (num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX ||
+			    num_dest_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+				err = -EOPNOTSUPP;
+				goto free_actions;
+			}
+			if (attr->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+				continue;
+
+			switch (attr->type) {
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
+				dest_action = mlx5_fs_get_dest_action_ft(fs_ctx, dst);
+				if (dst->dest_attr.ft->flags &
+				    MLX5_FLOW_TABLE_UPLINK_VPORT)
+					dest_actions[num_dest_actions].is_wire_ft = true;
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
+				dest_action = mlx5_fs_get_dest_action_table_num(fs_ctx,
+										dst);
+				if (dest_action)
+					break;
+				dest_action = mlx5_fs_create_dest_action_table_num(fs_ctx,
+										   dst);
+				fs_actions[num_fs_actions++].action = dest_action;
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_RANGE:
+				dest_action = mlx5_fs_create_dest_action_range(ctx, dst);
+				fs_actions[num_fs_actions++].action = dest_action;
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_UPLINK:
+			case MLX5_FLOW_DESTINATION_TYPE_VPORT:
+				dest_action = mlx5_fs_get_dest_action_vport(fs_ctx, dst,
+									    type_uplink);
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+				dest_action =
+					mlx5_fs_get_dest_action_sampler(fs_ctx,
+									dst);
+				fs_actions[num_fs_actions].action = dest_action;
+				fs_actions[num_fs_actions++].sampler_id =
+							dst->dest_attr.sampler_id;
+				break;
+			default:
+				err = -EOPNOTSUPP;
+				goto free_actions;
+			}
+			if (!dest_action) {
+				err = -ENOMEM;
+				goto free_actions;
+			}
+			dest_actions[num_dest_actions++].dest = dest_action;
+		}
+	}
+
+	if (num_dest_actions == 1) {
+		if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+		(*ractions)[num_actions++].action = dest_actions->dest;
+	} else if (num_dest_actions > 1) {
+		u32 flow_source = fte->act_dests.flow_context.flow_source;
+		bool ignore_flow_level;
+
+		if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX ||
+		    num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+		ignore_flow_level =
+			!!(fte_action->flags & FLOW_ACT_IGNORE_FLOW_LEVEL);
+		tmp_action = mlx5_fs_create_action_dest_array(ctx, dest_actions,
+							      num_dest_actions,
+							      ignore_flow_level,
+							      flow_source);
+		if (!tmp_action) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+		fs_actions[num_fs_actions++].action = tmp_action;
+		(*ractions)[num_actions++].action = tmp_action;
+	}
+
+	if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX ||
+	    num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+		err = -EOPNOTSUPP;
+		goto free_actions;
+	}
+
+	tmp_action = mlx5_fs_create_action_last(ctx);
+	if (!tmp_action) {
+		err = -ENOMEM;
+		goto free_actions;
+	}
+	fs_actions[num_fs_actions++].action = tmp_action;
+	(*ractions)[num_actions++].action = tmp_action;
+
+	kfree(dest_actions);
+
+	/* Actions created specifically for this rule will be destroyed
+	 * once rule is deleted.
+	 */
+	fte->fs_hws_rule.num_fs_actions = num_fs_actions;
+	fte->fs_hws_rule.hws_fs_actions = fs_actions;
+
+	return 0;
+
+free_actions:
+	mlx5_fs_destroy_fs_actions(ns, &fs_actions, &num_fs_actions);
+free_dest_actions_alloc:
+	kfree(dest_actions);
+free_fs_actions_alloc:
+	kfree(fs_actions);
+free_actions_alloc:
+	kfree(*ractions);
+	*ractions = NULL;
+out_err:
+	return err;
+}
+
+static int mlx5_cmd_hws_create_fte(struct mlx5_flow_root_namespace *ns,
+				   struct mlx5_flow_table *ft,
+				   struct mlx5_flow_group *group,
+				   struct fs_fte *fte)
+{
+	struct mlx5hws_match_parameters params;
+	struct mlx5hws_rule_action *ractions;
+	struct mlx5hws_bwc_rule *rule;
+	int err = 0;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte);
+
+	err = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions);
+	if (err)
+		goto out_err;
+
+	params.match_sz = sizeof(fte->val);
+	params.match_buf = fte->val;
+
+	rule = mlx5hws_bwc_rule_create(group->fs_hws_matcher.matcher, &params,
+				       fte->act_dests.flow_context.flow_source,
+				       ractions);
+	kfree(ractions);
+	if (!rule) {
+		err = -EINVAL;
+		goto free_actions;
+	}
+
+	fte->fs_hws_rule.bwc_rule = rule;
+	return 0;
+
+free_actions:
+	mlx5_fs_destroy_fs_actions(ns, &fte->fs_hws_rule.hws_fs_actions,
+				   &fte->fs_hws_rule.num_fs_actions);
+out_err:
+	mlx5_core_err(ns->dev, "Failed to create hws rule err(%d)\n", err);
+	return err;
+}
+
+static int mlx5_cmd_hws_delete_fte(struct mlx5_flow_root_namespace *ns,
+				   struct mlx5_flow_table *ft,
+				   struct fs_fte *fte)
+{
+	struct mlx5_fs_hws_rule *rule = &fte->fs_hws_rule;
+	int err;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte);
+
+	err = mlx5hws_bwc_rule_destroy(rule->bwc_rule);
+	rule->bwc_rule = NULL;
+
+	mlx5_fs_destroy_fs_actions(ns, &rule->hws_fs_actions,
+				   &rule->num_fs_actions);
+
+	return err;
+}
+
+static int mlx5_cmd_hws_update_fte(struct mlx5_flow_root_namespace *ns,
+				   struct mlx5_flow_table *ft,
+				   struct mlx5_flow_group *group,
+				   int modify_mask,
+				   struct fs_fte *fte)
+{
+	int allowed_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
+		BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST) |
+		BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
+	struct mlx5_fs_hws_rule_action *saved_hws_fs_actions;
+	struct mlx5hws_rule_action *ractions;
+	int saved_num_fs_actions;
+	int ret;
+
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
+		return mlx5_fs_cmd_get_fw_cmds()->update_fte(ns, ft, group,
+							     modify_mask, fte);
+
+	if ((modify_mask & ~allowed_mask) != 0)
+		return -EINVAL;
+
+	saved_hws_fs_actions = fte->fs_hws_rule.hws_fs_actions;
+	saved_num_fs_actions = fte->fs_hws_rule.num_fs_actions;
+
+	ret = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions);
+	if (ret)
+		return ret;
+
+	ret = mlx5hws_bwc_rule_action_update(fte->fs_hws_rule.bwc_rule, ractions);
+	kfree(ractions);
+	if (ret)
+		goto restore_actions;
+
+	mlx5_fs_destroy_fs_actions(ns, &saved_hws_fs_actions,
+				   &saved_num_fs_actions);
+	return ret;
+
+restore_actions:
+	mlx5_fs_destroy_fs_actions(ns, &fte->fs_hws_rule.hws_fs_actions,
+				   &fte->fs_hws_rule.num_fs_actions);
+	fte->fs_hws_rule.hws_fs_actions = saved_hws_fs_actions;
+	fte->fs_hws_rule.num_fs_actions = saved_num_fs_actions;
+	return ret;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_create_action_remove_header_vlan(struct mlx5hws_context *ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5hws_action_remove_header_attr remove_hdr_vlan = {};
+
+	/* MAC anchor not supported in HWS reformat, use VLAN anchor */
+	remove_hdr_vlan.anchor = MLX5_REFORMAT_CONTEXT_ANCHOR_VLAN_START;
+	remove_hdr_vlan.offset = 0;
+	remove_hdr_vlan.size = sizeof(struct vlan_hdr);
+	return mlx5hws_action_create_remove_header(ctx, &remove_hdr_vlan, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_remove_header_vlan(struct mlx5_fs_hws_context *fs_ctx,
+				      struct mlx5_pkt_reformat_params *params)
+{
+	if (!params ||
+	    params->param_0 != MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START ||
+	    params->param_1 != offsetof(struct vlan_ethhdr, h_vlan_proto) ||
+	    params->size != sizeof(struct vlan_hdr))
+		return NULL;
+
+	return fs_ctx->hws_pool.remove_hdr_vlan_action;
+}
+
+static int
+mlx5_fs_verify_insert_header_params(struct mlx5_core_dev *mdev,
+				    struct mlx5_pkt_reformat_params *params)
+{
+	if ((!params->data && params->size) || (params->data && !params->size) ||
+	    MLX5_CAP_GEN_2(mdev, max_reformat_insert_size) < params->size ||
+	    MLX5_CAP_GEN_2(mdev, max_reformat_insert_offset) < params->param_1) {
+		mlx5_core_err(mdev, "Invalid reformat params for INSERT_HDR\n");
+		return -EINVAL;
+	}
+	if (params->param_0 != MLX5_FS_INSERT_HDR_VLAN_ANCHOR ||
+	    params->param_1 != MLX5_FS_INSERT_HDR_VLAN_OFFSET ||
+	    params->size != MLX5_FS_INSERT_HDR_VLAN_SIZE) {
+		mlx5_core_err(mdev, "Only vlan insert header supported\n");
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int
+mlx5_fs_verify_encap_decap_params(struct mlx5_core_dev *dev,
+				  struct mlx5_pkt_reformat_params *params)
+{
+	if (params->param_0 || params->param_1) {
+		mlx5_core_err(dev, "Invalid reformat params\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct mlx5_fs_pool *
+mlx5_fs_get_pr_encap_pool(struct mlx5_core_dev *dev, struct xarray *pr_pools,
+			  enum mlx5hws_action_type reformat_type, size_t size)
+{
+	struct mlx5_fs_pool *pr_pool;
+	unsigned long index = size;
+	int err;
+
+	pr_pool = xa_load(pr_pools, index);
+	if (pr_pool)
+		return pr_pool;
+
+	pr_pool = kzalloc(sizeof(*pr_pool), GFP_KERNEL);
+	if (!pr_pool)
+		return ERR_PTR(-ENOMEM);
+	err = mlx5_fs_hws_pr_pool_init(pr_pool, dev, size, reformat_type);
+	if (err)
+		goto free_pr_pool;
+	err = xa_insert(pr_pools, index, pr_pool, GFP_KERNEL);
+	if (err)
+		goto cleanup_pr_pool;
+	return pr_pool;
+
+cleanup_pr_pool:
+	mlx5_fs_hws_pr_pool_cleanup(pr_pool);
+free_pr_pool:
+	kfree(pr_pool);
+	return ERR_PTR(err);
+}
+
+static void
+mlx5_fs_destroy_pr_pool(struct mlx5_fs_pool *pool, struct xarray *pr_pools,
+			unsigned long index)
+{
+	xa_erase(pr_pools, index);
+	mlx5_fs_hws_pr_pool_cleanup(pool);
+	kfree(pool);
+}
+
+static int
+mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
+				   struct mlx5_pkt_reformat_params *params,
+				   enum mlx5_flow_namespace_type namespace,
+				   struct mlx5_pkt_reformat *pkt_reformat)
+{
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+	struct mlx5_fs_hws_actions_pool *hws_pool;
+	struct mlx5hws_action *hws_action = NULL;
+	struct mlx5_fs_hws_pr *pr_data = NULL;
+	struct mlx5_fs_pool *pr_pool = NULL;
+	struct mlx5_core_dev *dev = ns->dev;
+	u8 hdr_idx = 0;
+	int err;
+
+	if (!params)
+		return -EINVAL;
+
+	hws_pool = &fs_ctx->hws_pool;
+
+	switch (params->type) {
+	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
+	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
+	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
+		if (mlx5_fs_verify_encap_decap_params(dev, params))
+			return -EINVAL;
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2,
+						    params->size);
+		if (IS_ERR(pr_pool))
+			return PTR_ERR(pr_pool);
+		break;
+	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
+		if (mlx5_fs_verify_encap_decap_params(dev, params))
+			return -EINVAL;
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol3tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3,
+						    params->size);
+		if (IS_ERR(pr_pool))
+			return PTR_ERR(pr_pool);
+		break;
+	case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
+		if (mlx5_fs_verify_encap_decap_params(dev, params))
+			return -EINVAL;
+		pr_pool = &hws_pool->dl3tnltol2_pool;
+		hdr_idx = params->size == ETH_HLEN ?
+			  MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX :
+			  MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX;
+		break;
+	case MLX5_REFORMAT_TYPE_INSERT_HDR:
+		err = mlx5_fs_verify_insert_header_params(dev, params);
+		if (err)
+			return err;
+		pr_pool = &hws_pool->insert_hdr_pool;
+		break;
+	case MLX5_REFORMAT_TYPE_REMOVE_HDR:
+		hws_action = mlx5_fs_get_action_remove_header_vlan(fs_ctx, params);
+		if (!hws_action)
+			mlx5_core_err(dev, "Only vlan remove header supported\n");
+		break;
+	default:
+		mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n",
+			      params->type);
+		return -EOPNOTSUPP;
+	}
+
+	if (pr_pool) {
+		pr_data = mlx5_fs_hws_pr_pool_acquire_pr(pr_pool);
+		if (IS_ERR_OR_NULL(pr_data))
+			return !pr_data ? -EINVAL : PTR_ERR(pr_data);
+		hws_action = pr_data->bulk->hws_action;
+		if (!hws_action) {
+			mlx5_core_err(dev,
+				      "Failed allocating packet-reformat action\n");
+			err = -EINVAL;
+			goto release_pr;
+		}
+		pr_data->data = kmemdup(params->data, params->size, GFP_KERNEL);
+		if (!pr_data->data) {
+			err = -ENOMEM;
+			goto release_pr;
+		}
+		pr_data->hdr_idx = hdr_idx;
+		pr_data->data_size = params->size;
+		pkt_reformat->fs_hws_action.pr_data = pr_data;
+	}
+
+	mutex_init(&pkt_reformat->fs_hws_action.lock);
+	pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_HWS;
+	pkt_reformat->fs_hws_action.hws_action = hws_action;
+	return 0;
+
+release_pr:
+	if (pr_pool && pr_data)
+		mlx5_fs_hws_pr_pool_release_pr(pr_pool, pr_data);
+	return err;
+}
+
+static void mlx5_cmd_hws_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
+						 struct mlx5_pkt_reformat *pkt_reformat)
+{
+	struct mlx5_fs_hws_actions_pool *hws_pool = &ns->fs_hws_context.hws_pool;
+	struct mlx5_core_dev *dev = ns->dev;
+	struct mlx5_fs_hws_pr *pr_data;
+	struct mlx5_fs_pool *pr_pool;
+
+	if (pkt_reformat->fs_hws_action.fw_reformat_id != 0) {
+		struct mlx5_pkt_reformat fw_pkt_reformat = { 0 };
+
+		fw_pkt_reformat.id = pkt_reformat->fs_hws_action.fw_reformat_id;
+		mlx5_fs_cmd_get_fw_cmds()->
+			packet_reformat_dealloc(ns, &fw_pkt_reformat);
+		pkt_reformat->fs_hws_action.fw_reformat_id = 0;
+	}
+
+	if (pkt_reformat->reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR)
+		return;
+
+	if (!pkt_reformat->fs_hws_action.pr_data) {
+		mlx5_core_err(ns->dev, "Failed release packet-reformat\n");
+		return;
+	}
+	pr_data = pkt_reformat->fs_hws_action.pr_data;
+
+	switch (pkt_reformat->reformat_type) {
+	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
+	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
+	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2,
+						    pr_data->data_size);
+		break;
+	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2,
+						    pr_data->data_size);
+		break;
+	case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
+		pr_pool = &hws_pool->dl3tnltol2_pool;
+		break;
+	case MLX5_REFORMAT_TYPE_INSERT_HDR:
+		pr_pool = &hws_pool->insert_hdr_pool;
+		break;
+	default:
+		mlx5_core_err(ns->dev, "Unknown packet-reformat type\n");
+		return;
+	}
+	if (!pkt_reformat->fs_hws_action.pr_data || IS_ERR(pr_pool)) {
+		mlx5_core_err(ns->dev, "Failed release packet-reformat\n");
+		return;
+	}
+	kfree(pr_data->data);
+	mlx5_fs_hws_pr_pool_release_pr(pr_pool, pr_data);
+	pkt_reformat->fs_hws_action.pr_data = NULL;
+}
+
+static struct mlx5_fs_pool *
+mlx5_fs_create_mh_pool(struct mlx5_core_dev *dev,
+		       struct mlx5hws_action_mh_pattern *pattern,
+		       struct xarray *mh_pools, unsigned long index)
+{
+	struct mlx5_fs_pool *pool;
+	int err;
+
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return ERR_PTR(-ENOMEM);
+	err = mlx5_fs_hws_mh_pool_init(pool, dev, pattern);
+	if (err)
+		goto free_pool;
+	err = xa_insert(mh_pools, index, pool, GFP_KERNEL);
+	if (err)
+		goto cleanup_pool;
+	return pool;
+
+cleanup_pool:
+	mlx5_fs_hws_mh_pool_cleanup(pool);
+free_pool:
+	kfree(pool);
+	return ERR_PTR(err);
+}
+
+static void
+mlx5_fs_destroy_mh_pool(struct mlx5_fs_pool *pool, struct xarray *mh_pools,
+			unsigned long index)
+{
+	xa_erase(mh_pools, index);
+	mlx5_fs_hws_mh_pool_cleanup(pool);
+	kfree(pool);
+}
+
+static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
+					    u8 namespace, u8 num_actions,
+					    void *modify_actions,
+					    struct mlx5_modify_hdr *modify_hdr)
+{
+	struct mlx5_fs_hws_actions_pool *hws_pool = &ns->fs_hws_context.hws_pool;
+	struct mlx5hws_action_mh_pattern pattern = {};
+	struct mlx5_fs_hws_mh *mh_data = NULL;
+	struct mlx5hws_action *hws_action;
+	struct mlx5_fs_pool *pool;
+	unsigned long i, cnt = 0;
+	bool known_pattern;
+	int err;
+
+	pattern.sz = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) * num_actions;
+	pattern.data = modify_actions;
+
+	known_pattern = false;
+	xa_for_each(&hws_pool->mh_pools, i, pool) {
+		if (mlx5_fs_hws_mh_pool_match(pool, &pattern)) {
+			known_pattern = true;
+			break;
+		}
+		cnt++;
+	}
+
+	if (!known_pattern) {
+		pool = mlx5_fs_create_mh_pool(ns->dev, &pattern,
+					      &hws_pool->mh_pools, cnt);
+		if (IS_ERR(pool))
+			return PTR_ERR(pool);
+	}
+	mh_data = mlx5_fs_hws_mh_pool_acquire_mh(pool);
+	if (IS_ERR(mh_data)) {
+		err = PTR_ERR(mh_data);
+		goto destroy_pool;
+	}
+	hws_action = mh_data->bulk->hws_action;
+	mh_data->data = kmemdup(pattern.data, pattern.sz, GFP_KERNEL);
+	if (!mh_data->data) {
+		err = -ENOMEM;
+		goto release_mh;
+	}
+	modify_hdr->fs_hws_action.mh_data = mh_data;
+	modify_hdr->fs_hws_action.fs_pool = pool;
+	modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW;
+	modify_hdr->fs_hws_action.hws_action = hws_action;
+
+	return 0;
+
+release_mh:
+	mlx5_fs_hws_mh_pool_release_mh(pool, mh_data);
+destroy_pool:
+	if (!known_pattern)
+		mlx5_fs_destroy_mh_pool(pool, &hws_pool->mh_pools, cnt);
+	return err;
+}
+
+static void mlx5_cmd_hws_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
+					       struct mlx5_modify_hdr *modify_hdr)
+{
+	struct mlx5_fs_hws_mh *mh_data;
+	struct mlx5_fs_pool *pool;
+
+	if (!modify_hdr->fs_hws_action.fs_pool || !modify_hdr->fs_hws_action.mh_data) {
+		mlx5_core_err(ns->dev, "Failed release modify-header\n");
+		return;
+	}
+
+	mh_data = modify_hdr->fs_hws_action.mh_data;
+	kfree(mh_data->data);
+	pool = modify_hdr->fs_hws_action.fs_pool;
+	mlx5_fs_hws_mh_pool_release_mh(pool, mh_data);
+	modify_hdr->fs_hws_action.mh_data = NULL;
+}
+
+int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id)
+{
+	enum mlx5_flow_namespace_type ns_type = pkt_reformat->ns_type;
+	struct mutex *lock = &pkt_reformat->fs_hws_action.lock;
+	u32 *id = &pkt_reformat->fs_hws_action.fw_reformat_id;
+	struct mlx5_pkt_reformat fw_pkt_reformat = { 0 };
+	struct mlx5_pkt_reformat_params params = { 0 };
+	struct mlx5_flow_root_namespace *ns;
+	struct mlx5_core_dev *dev;
+	int ret;
+
+	mutex_lock(lock);
+
+	if (*id != 0) {
+		*reformat_id = *id;
+		ret = 0;
+		goto unlock;
+	}
+
+	dev = mlx5hws_action_get_dev(pkt_reformat->fs_hws_action.hws_action);
+	if (!dev) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	ns = mlx5_get_root_namespace(dev, ns_type);
+	if (!ns) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	params.type = pkt_reformat->reformat_type;
+	params.size = pkt_reformat->fs_hws_action.pr_data->data_size;
+	params.data = pkt_reformat->fs_hws_action.pr_data->data;
+
+	ret = mlx5_fs_cmd_get_fw_cmds()->
+		packet_reformat_alloc(ns, &params, ns_type, &fw_pkt_reformat);
+	if (ret)
+		goto unlock;
+
+	*id = fw_pkt_reformat.id;
+	*reformat_id = *id;
+	ret = 0;
+
+unlock:
+	mutex_unlock(lock);
+
+	return ret;
+}
+
+static int mlx5_cmd_hws_create_match_definer(struct mlx5_flow_root_namespace *ns,
+					     u16 format_id, u32 *match_mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static int mlx5_cmd_hws_destroy_match_definer(struct mlx5_flow_root_namespace *ns,
+					      int definer_id)
+{
+	return -EOPNOTSUPP;
+}
+
+static u32 mlx5_cmd_hws_get_capabilities(struct mlx5_flow_root_namespace *ns,
+					 enum fs_flow_table_type ft_type)
+{
+	if (ft_type != FS_FT_FDB)
+		return 0;
+
+	return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX |
+	       MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX |
+	       MLX5_FLOW_STEERING_CAP_MATCH_RANGES;
+}
+
+bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev)
+{
+	return mlx5hws_is_supported(dev);
+}
+
+static const struct mlx5_flow_cmds mlx5_flow_cmds_hws = {
+	.create_flow_table = mlx5_cmd_hws_create_flow_table,
+	.destroy_flow_table = mlx5_cmd_hws_destroy_flow_table,
+	.modify_flow_table = mlx5_cmd_hws_modify_flow_table,
+	.update_root_ft = mlx5_cmd_hws_update_root_ft,
+	.create_flow_group = mlx5_cmd_hws_create_flow_group,
+	.destroy_flow_group = mlx5_cmd_hws_destroy_flow_group,
+	.create_fte = mlx5_cmd_hws_create_fte,
+	.delete_fte = mlx5_cmd_hws_delete_fte,
+	.update_fte = mlx5_cmd_hws_update_fte,
+	.packet_reformat_alloc = mlx5_cmd_hws_packet_reformat_alloc,
+	.packet_reformat_dealloc = mlx5_cmd_hws_packet_reformat_dealloc,
+	.modify_header_alloc = mlx5_cmd_hws_modify_header_alloc,
+	.modify_header_dealloc = mlx5_cmd_hws_modify_header_dealloc,
+	.create_match_definer = mlx5_cmd_hws_create_match_definer,
+	.destroy_match_definer = mlx5_cmd_hws_destroy_match_definer,
+	.create_ns = mlx5_cmd_hws_create_ns,
+	.destroy_ns = mlx5_cmd_hws_destroy_ns,
+	.set_peer = mlx5_cmd_hws_set_peer,
+	.get_capabilities = mlx5_cmd_hws_get_capabilities,
+};
+
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void)
+{
+	return &mlx5_flow_cmds_hws;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
new file mode 100644
index 000000000000..b92d55b2d147
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#ifndef _MLX5_FS_HWS_
+#define _MLX5_FS_HWS_
+
+#include "mlx5hws.h"
+#include "fs_hws_pools.h"
+
+struct mlx5_fs_hws_actions_pool {
+	struct mlx5hws_action *tag_action;
+	struct mlx5hws_action *pop_vlan_action;
+	struct mlx5hws_action *push_vlan_action;
+	struct mlx5hws_action *drop_action;
+	struct mlx5hws_action *decapl2_action;
+	struct mlx5hws_action *remove_hdr_vlan_action;
+	struct mlx5_fs_pool insert_hdr_pool;
+	struct mlx5_fs_pool dl3tnltol2_pool;
+	struct xarray el2tol3tnl_pools;
+	struct xarray el2tol2tnl_pools;
+	struct xarray mh_pools;
+	struct xarray table_dests;
+	struct xarray vport_vhca_dests;
+	struct xarray vport_dests;
+	struct xarray aso_meters;
+	struct xarray sample_dests;
+};
+
+struct mlx5_fs_hws_context {
+	struct mlx5hws_context	*hws_ctx;
+	struct mlx5_fs_hws_actions_pool hws_pool;
+};
+
+struct mlx5_fs_hws_table {
+	struct mlx5hws_table *hws_table;
+	bool miss_ft_set;
+};
+
+struct mlx5_fs_hws_action {
+	struct mlx5hws_action *hws_action;
+	struct mlx5_fs_pool *fs_pool;
+	struct mlx5_fs_hws_pr *pr_data;
+	struct mlx5_fs_hws_mh *mh_data;
+	u32 fw_reformat_id;
+	/* Protect `fw_reformat_id` against being initialized from multiple
+	 * threads.
+	 */
+	struct mutex lock;
+};
+
+struct mlx5_fs_hws_matcher {
+	struct mlx5hws_bwc_matcher *matcher;
+};
+
+struct mlx5_fs_hws_rule_action {
+	struct mlx5hws_action *action;
+	union {
+		struct mlx5_fc *counter;
+		struct mlx5_exe_aso *exe_aso;
+		u32 sampler_id;
+	};
+};
+
+struct mlx5_fs_hws_rule {
+	struct mlx5hws_bwc_rule *bwc_rule;
+	struct mlx5_fs_hws_rule_action *hws_fs_actions;
+	int num_fs_actions;
+};
+
+struct mlx5_fs_hws_data {
+	struct mlx5hws_action *hws_action;
+	struct mutex lock; /* protects hws_action */
+	refcount_t hws_action_refcount;
+};
+
+struct mlx5_fs_hws_create_action_ctx {
+	enum mlx5hws_action_type actions_type;
+	struct mlx5hws_context *hws_ctx;
+	u32 id;
+	union {
+		u8 return_reg_id;
+	};
+};
+
+struct mlx5hws_action *
+mlx5_fs_get_hws_action(struct mlx5_fs_hws_data *fs_hws_data,
+		       struct mlx5_fs_hws_create_action_ctx *create_ctx);
+void mlx5_fs_put_hws_action(struct mlx5_fs_hws_data *fs_hws_data);
+
+#ifdef CONFIG_MLX5_HW_STEERING
+
+int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id);
+
+bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev);
+
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void);
+
+#else
+
+static inline int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev)
+{
+	return false;
+}
+
+static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_MLX5_HWS_STEERING */
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c
new file mode 100644
index 000000000000..f1ecdba74e1f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c
@@ -0,0 +1,421 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#include <mlx5_core.h>
+#include "fs_hws_pools.h"
+
+#define MLX5_FS_HWS_DEFAULT_BULK_LEN 65536
+#define MLX5_FS_HWS_POOL_MAX_THRESHOLD BIT(18)
+#define MLX5_FS_HWS_POOL_USED_BUFF_RATIO 10
+
+static struct mlx5hws_action *
+mlx5_fs_dl3tnltol2_bulk_action_create(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_action_reformat_header reformat_hdr[2] = {};
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	enum mlx5hws_action_type reformat_type;
+	u32 log_bulk_size;
+
+	reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2;
+	reformat_hdr[MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX].sz = ETH_HLEN;
+	reformat_hdr[MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX].sz = ETH_HLEN + VLAN_HLEN;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	return mlx5hws_action_create_reformat(ctx, reformat_type, 2,
+					      reformat_hdr, log_bulk_size, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_el2tol3tnl_bulk_action_create(struct mlx5hws_context *ctx, size_t data_size)
+{
+	struct mlx5hws_action_reformat_header reformat_hdr = {};
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	enum mlx5hws_action_type reformat_type;
+	u32 log_bulk_size;
+
+	reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3;
+	reformat_hdr.sz = data_size;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	return mlx5hws_action_create_reformat(ctx, reformat_type, 1,
+					      &reformat_hdr, log_bulk_size, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_el2tol2tnl_bulk_action_create(struct mlx5hws_context *ctx, size_t data_size)
+{
+	struct mlx5hws_action_reformat_header reformat_hdr = {};
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	enum mlx5hws_action_type reformat_type;
+	u32 log_bulk_size;
+
+	reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2;
+	reformat_hdr.sz = data_size;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	return mlx5hws_action_create_reformat(ctx, reformat_type, 1,
+					      &reformat_hdr, log_bulk_size, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_insert_hdr_bulk_action_create(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_action_insert_header insert_hdr = {};
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	u32 log_bulk_size;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	insert_hdr.hdr.sz = MLX5_FS_INSERT_HDR_VLAN_SIZE;
+	insert_hdr.anchor = MLX5_FS_INSERT_HDR_VLAN_ANCHOR;
+	insert_hdr.offset = MLX5_FS_INSERT_HDR_VLAN_OFFSET;
+
+	return mlx5hws_action_create_insert_header(ctx, 1, &insert_hdr,
+						   log_bulk_size, flags);
+}
+
+static struct mlx5hws_action *
+mlx5_fs_pr_bulk_action_create(struct mlx5_core_dev *dev,
+			      struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx)
+{
+	struct mlx5_flow_root_namespace *root_ns;
+	struct mlx5hws_context *ctx;
+	size_t encap_data_size;
+
+	root_ns = mlx5_get_root_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns || root_ns->mode != MLX5_FLOW_STEERING_MODE_HMFS)
+		return NULL;
+
+	ctx = root_ns->fs_hws_context.hws_ctx;
+	if (!ctx)
+		return NULL;
+
+	encap_data_size = pr_pool_ctx->encap_data_size;
+	switch (pr_pool_ctx->reformat_type) {
+	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
+		return mlx5_fs_dl3tnltol2_bulk_action_create(ctx);
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3:
+		return mlx5_fs_el2tol3tnl_bulk_action_create(ctx, encap_data_size);
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2:
+		return mlx5_fs_el2tol2tnl_bulk_action_create(ctx, encap_data_size);
+	case MLX5HWS_ACTION_TYP_INSERT_HEADER:
+		return mlx5_fs_insert_hdr_bulk_action_create(ctx);
+	default:
+		return NULL;
+	}
+	return NULL;
+}
+
+static struct mlx5_fs_bulk *
+mlx5_fs_hws_pr_bulk_create(struct mlx5_core_dev *dev, void *pool_ctx)
+{
+	struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx;
+	struct mlx5_fs_hws_pr_bulk *pr_bulk;
+	int bulk_len;
+	int i;
+
+	if (!pool_ctx)
+		return NULL;
+	pr_pool_ctx = pool_ctx;
+	bulk_len = MLX5_FS_HWS_DEFAULT_BULK_LEN;
+	pr_bulk = kvzalloc(struct_size(pr_bulk, prs_data, bulk_len), GFP_KERNEL);
+	if (!pr_bulk)
+		return NULL;
+
+	if (mlx5_fs_bulk_init(dev, &pr_bulk->fs_bulk, bulk_len))
+		goto free_pr_bulk;
+
+	for (i = 0; i < bulk_len; i++) {
+		pr_bulk->prs_data[i].bulk = pr_bulk;
+		pr_bulk->prs_data[i].offset = i;
+	}
+
+	pr_bulk->hws_action = mlx5_fs_pr_bulk_action_create(dev, pr_pool_ctx);
+	if (!pr_bulk->hws_action)
+		goto cleanup_fs_bulk;
+
+	return &pr_bulk->fs_bulk;
+
+cleanup_fs_bulk:
+	mlx5_fs_bulk_cleanup(&pr_bulk->fs_bulk);
+free_pr_bulk:
+	kvfree(pr_bulk);
+	return NULL;
+}
+
+static int
+mlx5_fs_hws_pr_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk)
+{
+	struct mlx5_fs_hws_pr_bulk *pr_bulk;
+
+	pr_bulk = container_of(fs_bulk, struct mlx5_fs_hws_pr_bulk, fs_bulk);
+	if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) {
+		mlx5_core_err(dev, "Freeing bulk before all reformats were released\n");
+		return -EBUSY;
+	}
+
+	mlx5hws_action_destroy(pr_bulk->hws_action);
+	mlx5_fs_bulk_cleanup(fs_bulk);
+	kvfree(pr_bulk);
+
+	return 0;
+}
+
+static void mlx5_hws_pool_update_threshold(struct mlx5_fs_pool *hws_pool)
+{
+	hws_pool->threshold = min_t(int, MLX5_FS_HWS_POOL_MAX_THRESHOLD,
+				    hws_pool->used_units / MLX5_FS_HWS_POOL_USED_BUFF_RATIO);
+}
+
+static const struct mlx5_fs_pool_ops mlx5_fs_hws_pr_pool_ops = {
+	.bulk_create = mlx5_fs_hws_pr_bulk_create,
+	.bulk_destroy = mlx5_fs_hws_pr_bulk_destroy,
+	.update_threshold = mlx5_hws_pool_update_threshold,
+};
+
+int mlx5_fs_hws_pr_pool_init(struct mlx5_fs_pool *pr_pool,
+			     struct mlx5_core_dev *dev, size_t encap_data_size,
+			     enum mlx5hws_action_type reformat_type)
+{
+	struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx;
+
+	if (reformat_type != MLX5HWS_ACTION_TYP_INSERT_HEADER &&
+	    reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2 &&
+	    reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3 &&
+	    reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2)
+		return -EOPNOTSUPP;
+
+	pr_pool_ctx = kzalloc(sizeof(*pr_pool_ctx), GFP_KERNEL);
+	if (!pr_pool_ctx)
+		return -ENOMEM;
+	pr_pool_ctx->reformat_type = reformat_type;
+	pr_pool_ctx->encap_data_size = encap_data_size;
+	mlx5_fs_pool_init(pr_pool, dev, &mlx5_fs_hws_pr_pool_ops, pr_pool_ctx);
+	return 0;
+}
+
+void mlx5_fs_hws_pr_pool_cleanup(struct mlx5_fs_pool *pr_pool)
+{
+	struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx;
+
+	mlx5_fs_pool_cleanup(pr_pool);
+	pr_pool_ctx = pr_pool->pool_ctx;
+	if (!pr_pool_ctx)
+		return;
+	kfree(pr_pool_ctx);
+}
+
+struct mlx5_fs_hws_pr *
+mlx5_fs_hws_pr_pool_acquire_pr(struct mlx5_fs_pool *pr_pool)
+{
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_fs_hws_pr_bulk *pr_bulk;
+	int err;
+
+	err = mlx5_fs_pool_acquire_index(pr_pool, &pool_index);
+	if (err)
+		return ERR_PTR(err);
+	pr_bulk = container_of(pool_index.fs_bulk, struct mlx5_fs_hws_pr_bulk,
+			       fs_bulk);
+	return &pr_bulk->prs_data[pool_index.index];
+}
+
+void mlx5_fs_hws_pr_pool_release_pr(struct mlx5_fs_pool *pr_pool,
+				    struct mlx5_fs_hws_pr *pr_data)
+{
+	struct mlx5_fs_bulk *fs_bulk = &pr_data->bulk->fs_bulk;
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_core_dev *dev = pr_pool->dev;
+
+	pool_index.fs_bulk = fs_bulk;
+	pool_index.index = pr_data->offset;
+	if (mlx5_fs_pool_release_index(pr_pool, &pool_index))
+		mlx5_core_warn(dev, "Attempted to release packet reformat which is not acquired\n");
+}
+
+struct mlx5hws_action *mlx5_fs_hws_pr_get_action(struct mlx5_fs_hws_pr *pr_data)
+{
+	return pr_data->bulk->hws_action;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_mh_bulk_action_create(struct mlx5hws_context *ctx,
+			      struct mlx5hws_action_mh_pattern *pattern)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB;
+	u32 log_bulk_size;
+
+	log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN);
+	return mlx5hws_action_create_modify_header(ctx, 1, pattern,
+						   log_bulk_size, flags);
+}
+
+static struct mlx5_fs_bulk *
+mlx5_fs_hws_mh_bulk_create(struct mlx5_core_dev *dev, void *pool_ctx)
+{
+	struct mlx5hws_action_mh_pattern *pattern;
+	struct mlx5_flow_root_namespace *root_ns;
+	struct mlx5_fs_hws_mh_bulk *mh_bulk;
+	struct mlx5hws_context *ctx;
+	int bulk_len;
+
+	if (!pool_ctx)
+		return NULL;
+
+	root_ns = mlx5_get_root_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns || root_ns->mode != MLX5_FLOW_STEERING_MODE_HMFS)
+		return NULL;
+
+	ctx = root_ns->fs_hws_context.hws_ctx;
+	if (!ctx)
+		return NULL;
+
+	pattern = pool_ctx;
+	bulk_len = MLX5_FS_HWS_DEFAULT_BULK_LEN;
+	mh_bulk = kvzalloc(struct_size(mh_bulk, mhs_data, bulk_len), GFP_KERNEL);
+	if (!mh_bulk)
+		return NULL;
+
+	if (mlx5_fs_bulk_init(dev, &mh_bulk->fs_bulk, bulk_len))
+		goto free_mh_bulk;
+
+	for (int i = 0; i < bulk_len; i++) {
+		mh_bulk->mhs_data[i].bulk = mh_bulk;
+		mh_bulk->mhs_data[i].offset = i;
+	}
+
+	mh_bulk->hws_action = mlx5_fs_mh_bulk_action_create(ctx, pattern);
+	if (!mh_bulk->hws_action)
+		goto cleanup_fs_bulk;
+
+	return &mh_bulk->fs_bulk;
+
+cleanup_fs_bulk:
+	mlx5_fs_bulk_cleanup(&mh_bulk->fs_bulk);
+free_mh_bulk:
+	kvfree(mh_bulk);
+	return NULL;
+}
+
+static int
+mlx5_fs_hws_mh_bulk_destroy(struct mlx5_core_dev *dev,
+			    struct mlx5_fs_bulk *fs_bulk)
+{
+	struct mlx5_fs_hws_mh_bulk *mh_bulk;
+
+	mh_bulk = container_of(fs_bulk, struct mlx5_fs_hws_mh_bulk, fs_bulk);
+	if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) {
+		mlx5_core_err(dev, "Freeing bulk before all modify header were released\n");
+		return -EBUSY;
+	}
+
+	mlx5hws_action_destroy(mh_bulk->hws_action);
+	mlx5_fs_bulk_cleanup(fs_bulk);
+	kvfree(mh_bulk);
+
+	return 0;
+}
+
+static const struct mlx5_fs_pool_ops mlx5_fs_hws_mh_pool_ops = {
+	.bulk_create = mlx5_fs_hws_mh_bulk_create,
+	.bulk_destroy = mlx5_fs_hws_mh_bulk_destroy,
+	.update_threshold = mlx5_hws_pool_update_threshold,
+};
+
+int mlx5_fs_hws_mh_pool_init(struct mlx5_fs_pool *fs_hws_mh_pool,
+			     struct mlx5_core_dev *dev,
+			     struct mlx5hws_action_mh_pattern *pattern)
+{
+	struct mlx5hws_action_mh_pattern *pool_pattern;
+
+	pool_pattern = kzalloc(sizeof(*pool_pattern), GFP_KERNEL);
+	if (!pool_pattern)
+		return -ENOMEM;
+	pool_pattern->data = kmemdup(pattern->data, pattern->sz, GFP_KERNEL);
+	if (!pool_pattern->data) {
+		kfree(pool_pattern);
+		return -ENOMEM;
+	}
+	pool_pattern->sz = pattern->sz;
+	mlx5_fs_pool_init(fs_hws_mh_pool, dev, &mlx5_fs_hws_mh_pool_ops,
+			  pool_pattern);
+	return 0;
+}
+
+void mlx5_fs_hws_mh_pool_cleanup(struct mlx5_fs_pool *fs_hws_mh_pool)
+{
+	struct mlx5hws_action_mh_pattern *pool_pattern;
+
+	mlx5_fs_pool_cleanup(fs_hws_mh_pool);
+	pool_pattern = fs_hws_mh_pool->pool_ctx;
+	if (!pool_pattern)
+		return;
+	kfree(pool_pattern->data);
+	kfree(pool_pattern);
+}
+
+struct mlx5_fs_hws_mh *
+mlx5_fs_hws_mh_pool_acquire_mh(struct mlx5_fs_pool *mh_pool)
+{
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_fs_hws_mh_bulk *mh_bulk;
+	int err;
+
+	err = mlx5_fs_pool_acquire_index(mh_pool, &pool_index);
+	if (err)
+		return ERR_PTR(err);
+	mh_bulk = container_of(pool_index.fs_bulk, struct mlx5_fs_hws_mh_bulk,
+			       fs_bulk);
+	return &mh_bulk->mhs_data[pool_index.index];
+}
+
+void mlx5_fs_hws_mh_pool_release_mh(struct mlx5_fs_pool *mh_pool,
+				    struct mlx5_fs_hws_mh *mh_data)
+{
+	struct mlx5_fs_bulk *fs_bulk = &mh_data->bulk->fs_bulk;
+	struct mlx5_fs_pool_index pool_index = {};
+	struct mlx5_core_dev *dev = mh_pool->dev;
+
+	pool_index.fs_bulk = fs_bulk;
+	pool_index.index = mh_data->offset;
+	if (mlx5_fs_pool_release_index(mh_pool, &pool_index))
+		mlx5_core_warn(dev, "Attempted to release modify header which is not acquired\n");
+}
+
+bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool,
+			       struct mlx5hws_action_mh_pattern *pattern)
+{
+	struct mlx5hws_action_mh_pattern *pool_pattern;
+	int num_actions, i;
+
+	pool_pattern = mh_pool->pool_ctx;
+	if (WARN_ON_ONCE(!pool_pattern))
+		return false;
+
+	if (pattern->sz != pool_pattern->sz)
+		return false;
+	num_actions = pattern->sz / MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto);
+	for (i = 0; i < num_actions; i++) {
+		if ((__force __be32)pattern->data[i] !=
+		    (__force __be32)pool_pattern->data[i])
+			return false;
+	}
+	return true;
+}
+
+struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx,
+					      struct mlx5_fc *counter)
+{
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
+	struct mlx5_fc_bulk *fc_bulk = counter->bulk;
+
+	create_ctx.hws_ctx = ctx;
+	create_ctx.id = fc_bulk->base_id;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_CTR;
+
+	return mlx5_fs_get_hws_action(&fc_bulk->hws_data, &create_ctx);
+}
+
+void mlx5_fc_put_hws_action(struct mlx5_fc *counter)
+{
+	mlx5_fs_put_hws_action(&counter->bulk->hws_data);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h
new file mode 100644
index 000000000000..34072551dd21
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#ifndef __MLX5_FS_HWS_POOLS_H__
+#define __MLX5_FS_HWS_POOLS_H__
+
+#include <linux/if_vlan.h>
+#include "fs_pool.h"
+#include "fs_core.h"
+
+#define MLX5_FS_INSERT_HDR_VLAN_ANCHOR MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START
+#define MLX5_FS_INSERT_HDR_VLAN_OFFSET offsetof(struct vlan_ethhdr, h_vlan_proto)
+#define MLX5_FS_INSERT_HDR_VLAN_SIZE sizeof(struct vlan_hdr)
+
+enum {
+	MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX = 0,
+	MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX,
+};
+
+struct mlx5_fs_hws_pr {
+	struct mlx5_fs_hws_pr_bulk *bulk;
+	u32 offset;
+	u8 hdr_idx;
+	u8 *data;
+	size_t data_size;
+};
+
+struct mlx5_fs_hws_pr_bulk {
+	struct mlx5_fs_bulk fs_bulk;
+	struct mlx5hws_action *hws_action;
+	struct mlx5_fs_hws_pr prs_data[];
+};
+
+struct mlx5_fs_hws_pr_pool_ctx {
+	enum mlx5hws_action_type reformat_type;
+	size_t encap_data_size;
+};
+
+struct mlx5_fs_hws_mh {
+	struct mlx5_fs_hws_mh_bulk *bulk;
+	u32 offset;
+	u8 *data;
+};
+
+struct mlx5_fs_hws_mh_bulk {
+	struct mlx5_fs_bulk fs_bulk;
+	struct mlx5_fs_pool *mh_pool;
+	struct mlx5hws_action *hws_action;
+	struct mlx5_fs_hws_mh mhs_data[];
+};
+
+int mlx5_fs_hws_pr_pool_init(struct mlx5_fs_pool *pr_pool,
+			     struct mlx5_core_dev *dev, size_t encap_data_size,
+			     enum mlx5hws_action_type reformat_type);
+void mlx5_fs_hws_pr_pool_cleanup(struct mlx5_fs_pool *pr_pool);
+
+struct mlx5_fs_hws_pr *mlx5_fs_hws_pr_pool_acquire_pr(struct mlx5_fs_pool *pr_pool);
+void mlx5_fs_hws_pr_pool_release_pr(struct mlx5_fs_pool *pr_pool,
+				    struct mlx5_fs_hws_pr *pr_data);
+struct mlx5hws_action *mlx5_fs_hws_pr_get_action(struct mlx5_fs_hws_pr *pr_data);
+int mlx5_fs_hws_mh_pool_init(struct mlx5_fs_pool *fs_hws_mh_pool,
+			     struct mlx5_core_dev *dev,
+			     struct mlx5hws_action_mh_pattern *pattern);
+void mlx5_fs_hws_mh_pool_cleanup(struct mlx5_fs_pool *fs_hws_mh_pool);
+struct mlx5_fs_hws_mh *mlx5_fs_hws_mh_pool_acquire_mh(struct mlx5_fs_pool *mh_pool);
+void mlx5_fs_hws_mh_pool_release_mh(struct mlx5_fs_pool *mh_pool,
+				    struct mlx5_fs_hws_mh *mh_data);
+bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool,
+			       struct mlx5hws_action_mh_pattern *pattern);
+struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx,
+					      struct mlx5_fc *counter);
+void mlx5_fc_put_hws_action(struct mlx5_fc *counter);
+#endif /* __MLX5_FS_HWS_POOLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
index 3c8635f286ce..21279d503117 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
@@ -17,6 +17,7 @@
 #include "context.h"
 #include "table.h"
 #include "send.h"
+#include "action_ste_pool.h"
 #include "rule.h"
 #include "cmd.h"
 #include "action.h"
@@ -39,7 +40,6 @@
 #define mlx5hws_dbg(ctx, arg...) mlx5_core_dbg((ctx)->mdev, ##arg)
 
 #define MLX5HWS_TABLE_TYPE_BASE 2
-#define MLX5HWS_ACTION_STE_IDX_ANY 0
 
 static inline bool is_mem_zero(const u8 *mem, size_t size)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
index 1bb3a6f8c3cd..ce28ee1c0e41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
@@ -3,25 +3,6 @@
 
 #include "internal.h"
 
-enum mlx5hws_matcher_rtc_type {
-	HWS_MATCHER_RTC_TYPE_MATCH,
-	HWS_MATCHER_RTC_TYPE_STE_ARRAY,
-	HWS_MATCHER_RTC_TYPE_MAX,
-};
-
-static const char * const mlx5hws_matcher_rtc_type_str[] = {
-	[HWS_MATCHER_RTC_TYPE_MATCH] = "MATCH",
-	[HWS_MATCHER_RTC_TYPE_STE_ARRAY] = "STE_ARRAY",
-	[HWS_MATCHER_RTC_TYPE_MAX] = "UNKNOWN",
-};
-
-static const char *hws_matcher_rtc_type_to_str(enum mlx5hws_matcher_rtc_type rtc_type)
-{
-	if (rtc_type > HWS_MATCHER_RTC_TYPE_MAX)
-		rtc_type = HWS_MATCHER_RTC_TYPE_MAX;
-	return mlx5hws_matcher_rtc_type_str[rtc_type];
-}
-
 static bool hws_matcher_requires_col_tbl(u8 log_num_of_rules)
 {
 	/* Collision table concatenation is done only for large rule tables */
@@ -42,19 +23,199 @@ static void hws_matcher_destroy_end_ft(struct mlx5hws_matcher *matcher)
 	mlx5hws_table_destroy_default_ft(matcher->tbl, matcher->end_ft_id);
 }
 
+int mlx5hws_matcher_update_end_ft_isolated(struct mlx5hws_table *tbl,
+					   u32 miss_ft_id)
+{
+	struct mlx5hws_matcher *tmp_matcher;
+
+	if (list_empty(&tbl->matchers_list))
+		return -EINVAL;
+
+	/* Update isolated_matcher_end_ft_id attribute for all
+	 * the matchers in isolated table.
+	 */
+	list_for_each_entry(tmp_matcher, &tbl->matchers_list, list_node)
+		tmp_matcher->attr.isolated_matcher_end_ft_id = miss_ft_id;
+
+	tmp_matcher = list_last_entry(&tbl->matchers_list,
+				      struct mlx5hws_matcher,
+				      list_node);
+
+	return mlx5hws_table_ft_set_next_ft(tbl->ctx,
+					    tmp_matcher->end_ft_id,
+					    tbl->fw_ft_type,
+					    miss_ft_id);
+}
+
+static int hws_matcher_connect_end_ft_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	u32 end_ft_id;
+	int ret;
+
+	/* Reset end_ft next RTCs */
+	ret = mlx5hws_table_ft_set_next_rtc(tbl->ctx,
+					    matcher->end_ft_id,
+					    matcher->tbl->fw_ft_type,
+					    0, 0);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to reset FT's next RTCs\n");
+		return ret;
+	}
+
+	/* Connect isolated matcher's end_ft to the complex matcher's end FT */
+	end_ft_id = matcher->attr.isolated_matcher_end_ft_id;
+	ret = mlx5hws_table_ft_set_next_ft(tbl->ctx,
+					   matcher->end_ft_id,
+					   matcher->tbl->fw_ft_type,
+					   end_ft_id);
+
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to set FT's miss_ft_id\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int hws_matcher_create_end_ft_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	int ret;
+
+	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+					      tbl,
+					      &matcher->end_ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to create end flow table\n");
+		return ret;
+	}
+
+	ret = hws_matcher_connect_end_ft_isolated(matcher);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to connect end FT\n");
+		goto destroy_default_ft;
+	}
+
+	return 0;
+
+destroy_default_ft:
+	mlx5hws_table_destroy_default_ft(tbl, matcher->end_ft_id);
+	return ret;
+}
+
 static int hws_matcher_create_end_ft(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_table *tbl = matcher->tbl;
 	int ret;
 
-	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &matcher->end_ft_id);
+	if (mlx5hws_matcher_is_isolated(matcher))
+		ret = hws_matcher_create_end_ft_isolated(matcher);
+	else
+		ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl,
+						      &matcher->end_ft_id);
+
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Failed to create matcher end flow table\n");
 		return ret;
 	}
+
+	return 0;
+}
+
+static int hws_matcher_connect_isolated_first(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	int ret;
+
+	/* Isolated matcher's end_ft is already pointing to the end_ft
+	 * of the complex matcher - it was set at creation of end_ft,
+	 * so no need to connect it.
+	 * We still need to connect the isolated table's start FT to
+	 * this matcher's RTC.
+	 */
+	ret = mlx5hws_table_ft_set_next_rtc(ctx,
+					    tbl->ft_id,
+					    tbl->fw_ft_type,
+					    matcher->match_ste.rtc_0_id,
+					    matcher->match_ste.rtc_1_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to connect start FT to match RTC\n");
+		return ret;
+	}
+
+	/* Reset table's FT default miss (drop refcount) */
+	ret = mlx5hws_table_ft_set_default_next_ft(tbl, tbl->ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to reset table ft default miss\n");
+		return ret;
+	}
+
+	list_add(&matcher->list_node, &tbl->matchers_list);
+
+	return ret;
+}
+
+static int hws_matcher_connect_isolated_last(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	struct mlx5hws_matcher *last;
+	int ret;
+
+	last = list_last_entry(&tbl->matchers_list,
+			       struct mlx5hws_matcher,
+			       list_node);
+
+	/* New matcher's end_ft is already pointing to the end_ft of
+	 * the complex matcher.
+	 * Connect previous matcher's end_ft to this new matcher RTC.
+	 */
+	ret = mlx5hws_table_ft_set_next_rtc(ctx,
+					    last->end_ft_id,
+					    tbl->fw_ft_type,
+					    matcher->match_ste.rtc_0_id,
+					    matcher->match_ste.rtc_1_id);
+	if (ret) {
+		mlx5hws_err(ctx,
+			    "Isolated matcher: failed to connect matcher end_ft to new match RTC\n");
+		return ret;
+	}
+
+	/* Reset prev matcher FT default miss (drop refcount) */
+	ret = mlx5hws_table_ft_set_default_next_ft(tbl, last->end_ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to reset matcher ft default miss\n");
+		return ret;
+	}
+
+	/* Insert after the last matcher */
+	list_add(&matcher->list_node, &last->list_node);
+
 	return 0;
 }
 
+static int hws_matcher_connect_isolated(struct mlx5hws_matcher *matcher)
+{
+	/* Isolated matcher is expected to be the only one in its table.
+	 * However, it can have a collision matcher, and it can go through
+	 * rehash process, in which case we will temporary have both old and
+	 * new matchers in the isolated table.
+	 * Check if this is the first matcher in the isolated table.
+	 */
+	if (list_empty(&matcher->tbl->matchers_list))
+		return hws_matcher_connect_isolated_first(matcher);
+
+	/* If this wasn't the first matcher, then we have 3 possible cases:
+	 *  - this is a collision matcher for the first matcher
+	 *  - this is a new rehash dest matcher
+	 *  - this is a collision matcher for the new rehash dest matcher
+	 * The logic to add new matcher is the same for all these cases.
+	 */
+	return hws_matcher_connect_isolated_last(matcher);
+}
+
 static int hws_matcher_connect(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_table *tbl = matcher->tbl;
@@ -64,6 +225,9 @@ static int hws_matcher_connect(struct mlx5hws_matcher *matcher)
 	struct mlx5hws_matcher *tmp_matcher;
 	int ret;
 
+	if (mlx5hws_matcher_is_isolated(matcher))
+		return hws_matcher_connect_isolated(matcher);
+
 	/* Find location in matcher list */
 	if (list_empty(&tbl->matchers_list)) {
 		list_add(&matcher->list_node, &tbl->matchers_list);
@@ -140,6 +304,92 @@ remove_from_list:
 	return ret;
 }
 
+static int hws_matcher_disconnect_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher *first, *last, *prev, *next;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	u32 end_ft_id;
+	int ret;
+
+	first = list_first_entry(&tbl->matchers_list,
+				 struct mlx5hws_matcher,
+				 list_node);
+	last = list_last_entry(&tbl->matchers_list,
+			       struct mlx5hws_matcher,
+			       list_node);
+	prev = list_prev_entry(matcher, list_node);
+	next = list_next_entry(matcher, list_node);
+
+	list_del_init(&matcher->list_node);
+
+	if (first == last) {
+		/* This was the only matcher in the list.
+		 * Reset isolated table FT next RTCs and connect it
+		 * to the whole complex matcher end FT instead.
+		 */
+		ret = mlx5hws_table_ft_set_next_rtc(ctx,
+						    tbl->ft_id,
+						    tbl->fw_ft_type,
+						    0, 0);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Isolated matcher: failed to reset FT's next RTCs\n");
+			return ret;
+		}
+
+		end_ft_id = matcher->attr.isolated_matcher_end_ft_id;
+		ret = mlx5hws_table_ft_set_next_ft(tbl->ctx,
+						   tbl->ft_id,
+						   tbl->fw_ft_type,
+						   end_ft_id);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Isolated matcher: failed to set FT's miss_ft_id\n");
+			return ret;
+		}
+
+		return 0;
+	}
+
+	/* At this point we know that there are more matchers in the list */
+
+	if (matcher == first) {
+		/* We've disconnected the first matcher.
+		 * Now update isolated table default FT.
+		 */
+		if (!next)
+			return -EINVAL;
+		return mlx5hws_table_ft_set_next_rtc(ctx,
+						     tbl->ft_id,
+						     tbl->fw_ft_type,
+						     next->match_ste.rtc_0_id,
+						     next->match_ste.rtc_1_id);
+	}
+
+	if (matcher == last) {
+		/* If we've disconnected the last matcher - update prev
+		 * matcher's end_ft to point to the complex matcher end_ft.
+		 */
+		if (!prev)
+			return -EINVAL;
+		return hws_matcher_connect_end_ft_isolated(prev);
+	}
+
+	/* This wasn't the first or the last matcher, which means that it has
+	 * both prev and next matchers. Note that this only happens if we're
+	 * disconnecting collision matcher of the old matcher during rehash.
+	 */
+	if (!prev || !next ||
+	    !(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION))
+		return -EINVAL;
+
+	/* Update prev end FT to point to next match RTC */
+	return mlx5hws_table_ft_set_next_rtc(ctx,
+					     prev->end_ft_id,
+					     tbl->fw_ft_type,
+					     next->match_ste.rtc_0_id,
+					     next->match_ste.rtc_1_id);
+}
+
 static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher *next = NULL, *prev = NULL;
@@ -147,6 +397,9 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 	u32 prev_ft_id = tbl->ft_id;
 	int ret;
 
+	if (mlx5hws_matcher_is_isolated(matcher))
+		return hws_matcher_disconnect_isolated(matcher);
+
 	if (!list_is_first(&matcher->list_node, &tbl->matchers_list)) {
 		prev = list_prev_entry(matcher, list_node);
 		prev_ft_id = prev->end_ft_id;
@@ -165,14 +418,14 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 						    next->match_ste.rtc_0_id,
 						    next->match_ste.rtc_1_id);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Failed to disconnect matcher\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect matcher\n");
+			return ret;
 		}
 	} else {
 		ret = mlx5hws_table_connect_to_miss_table(tbl, tbl->default_miss.miss_tbl);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Failed to disconnect last matcher\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect last matcher\n");
+			return ret;
 		}
 	}
 
@@ -180,169 +433,113 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 	if (prev_ft_id == tbl->ft_id) {
 		ret = mlx5hws_table_update_connected_miss_tables(tbl);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Fatal error, failed to update connected miss table\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx,
+				    "Fatal error, failed to update connected miss table\n");
+			return ret;
 		}
 	}
 
 	ret = mlx5hws_table_ft_set_default_next_ft(tbl, prev_ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Fatal error, failed to restore matcher ft default miss\n");
-		goto matcher_reconnect;
+		return ret;
 	}
 
 	return 0;
-
-matcher_reconnect:
-	if (list_empty(&tbl->matchers_list) || !prev)
-		list_add(&matcher->list_node, &tbl->matchers_list);
-	else
-		/* insert after prev matcher */
-		list_add(&matcher->list_node, &prev->list_node);
-
-	return ret;
 }
 
 static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher,
 					struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
-					enum mlx5hws_matcher_rtc_type rtc_type,
 					bool is_mirror)
 {
-	struct mlx5hws_pool_chunk *ste = &matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].ste;
 	enum mlx5hws_matcher_flow_src flow_src = matcher->attr.optimize_flow_src;
-	bool is_match_rtc = rtc_type == HWS_MATCHER_RTC_TYPE_MATCH;
 
 	if ((flow_src == MLX5HWS_MATCHER_FLOW_SRC_VPORT && !is_mirror) ||
 	    (flow_src == MLX5HWS_MATCHER_FLOW_SRC_WIRE && is_mirror)) {
 		/* Optimize FDB RTC */
 		rtc_attr->log_size = 0;
 		rtc_attr->log_depth = 0;
-	} else {
-		/* Keep original values */
-		rtc_attr->log_size = is_match_rtc ? matcher->attr.table.sz_row_log : ste->order;
-		rtc_attr->log_depth = is_match_rtc ? matcher->attr.table.sz_col_log : 0;
 	}
 }
 
-static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher,
-				  enum mlx5hws_matcher_rtc_type rtc_type,
-				  u8 action_ste_selector)
+static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher_attr *attr = &matcher->attr;
 	struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0};
 	struct mlx5hws_match_template *mt = matcher->mt;
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
-	struct mlx5hws_action_default_stc *default_stc;
-	struct mlx5hws_matcher_action_ste *action_ste;
 	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool *ste_pool, *stc_pool;
-	struct mlx5hws_pool_chunk *ste;
-	u32 *rtc_0_id, *rtc_1_id;
 	u32 obj_id;
 	int ret;
 
-	switch (rtc_type) {
-	case HWS_MATCHER_RTC_TYPE_MATCH:
-		rtc_0_id = &matcher->match_ste.rtc_0_id;
-		rtc_1_id = &matcher->match_ste.rtc_1_id;
-		ste_pool = matcher->match_ste.pool;
-		ste = &matcher->match_ste.ste;
-		ste->order = attr->table.sz_col_log + attr->table.sz_row_log;
-
-		rtc_attr.log_size = attr->table.sz_row_log;
-		rtc_attr.log_depth = attr->table.sz_col_log;
-		rtc_attr.is_frst_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
-		rtc_attr.is_scnd_range = 0;
-		rtc_attr.miss_ft_id = matcher->end_ft_id;
-
-		if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH) {
-			/* The usual Hash Table */
-			rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH;
-
-			/* The first mt is used since all share the same definer */
-			rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
-		} else if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX) {
-			rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
-			rtc_attr.num_hash_definer = 1;
-
-			if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
-				/* Hash Split Table */
-				rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH;
-				rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
-			} else if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR) {
-				/* Linear Lookup Table */
-				rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR;
-				rtc_attr.match_definer_0 = ctx->caps->linear_match_definer;
-			}
-		}
-
-		/* Match pool requires implicit allocation */
-		ret = mlx5hws_pool_chunk_alloc(ste_pool, ste);
-		if (ret) {
-			mlx5hws_err(ctx, "Failed to allocate STE for %s RTC",
-				    hws_matcher_rtc_type_to_str(rtc_type));
-			return ret;
+	rtc_attr.log_size = attr->table.sz_row_log;
+	rtc_attr.log_depth = attr->table.sz_col_log;
+	rtc_attr.is_frst_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
+	rtc_attr.is_scnd_range = 0;
+	rtc_attr.miss_ft_id = matcher->end_ft_id;
+
+	if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH) {
+		/* The usual Hash Table */
+		rtc_attr.update_index_mode =
+			MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH;
+
+		/* The first mt is used since all share the same definer */
+		rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
+	} else if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX) {
+		rtc_attr.update_index_mode =
+			MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+		rtc_attr.num_hash_definer = 1;
+
+		if (attr->distribute_mode ==
+		    MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
+			/* Hash Split Table */
+			rtc_attr.access_index_mode =
+				MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH;
+			rtc_attr.match_definer_0 =
+				mlx5hws_definer_get_id(mt->definer);
+		} else if (attr->distribute_mode ==
+			   MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR) {
+			/* Linear Lookup Table */
+			rtc_attr.access_index_mode =
+				MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR;
+			rtc_attr.match_definer_0 =
+				ctx->caps->linear_match_definer;
 		}
-		break;
-
-	case HWS_MATCHER_RTC_TYPE_STE_ARRAY:
-		action_ste = &matcher->action_ste[action_ste_selector];
-
-		rtc_0_id = &action_ste->rtc_0_id;
-		rtc_1_id = &action_ste->rtc_1_id;
-		ste_pool = action_ste->pool;
-		ste = &action_ste->ste;
-		ste->order = ilog2(roundup_pow_of_two(action_ste->max_stes)) +
-			     attr->table.sz_row_log;
-		rtc_attr.log_size = ste->order;
-		rtc_attr.log_depth = 0;
-		rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
-		/* The action STEs use the default always hit definer */
-		rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
-		rtc_attr.is_frst_jumbo = false;
-		rtc_attr.miss_ft_id = 0;
-		break;
-
-	default:
-		mlx5hws_err(ctx, "HWS Invalid RTC type\n");
-		return -EINVAL;
 	}
 
-	obj_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+	obj_id = mlx5hws_pool_get_base_id(matcher->match_ste.pool);
 
 	rtc_attr.pd = ctx->pd_num;
 	rtc_attr.ste_base = obj_id;
-	rtc_attr.ste_offset = ste->offset;
 	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(tbl->type, false);
-	hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, false);
+	hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, false);
 
 	/* STC is a single resource (obj_id), use any STC for the ID */
-	stc_pool = ctx->stc_pool[tbl->type];
-	default_stc = ctx->common_res[tbl->type].default_stc;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
+	obj_id = mlx5hws_pool_get_base_id(ctx->stc_pool);
 	rtc_attr.stc_base = obj_id;
 
-	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_0_id);
+	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr,
+				     &matcher->match_ste.rtc_0_id);
 	if (ret) {
-		mlx5hws_err(ctx, "Failed to create matcher RTC of type %s",
-			    hws_matcher_rtc_type_to_str(rtc_type));
-		goto free_ste;
+		mlx5hws_err(ctx, "Failed to create matcher RTC\n");
+		return ret;
 	}
 
 	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+		obj_id = mlx5hws_pool_get_base_mirror_id(
+			matcher->match_ste.pool);
 		rtc_attr.ste_base = obj_id;
 		rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(tbl->type, true);
 
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, &default_stc->default_hit);
+		obj_id = mlx5hws_pool_get_base_mirror_id(ctx->stc_pool);
 		rtc_attr.stc_base = obj_id;
-		hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, true);
+		hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, true);
 
-		ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_1_id);
+		ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr,
+					     &matcher->match_ste.rtc_1_id);
 		if (ret) {
-			mlx5hws_err(ctx, "Failed to create peer matcher RTC of type %s",
-				    hws_matcher_rtc_type_to_str(rtc_type));
+			mlx5hws_err(ctx, "Failed to create mirror matcher RTC\n");
 			goto destroy_rtc_0;
 		}
 	}
@@ -350,47 +547,18 @@ static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher,
 	return 0;
 
 destroy_rtc_0:
-	mlx5hws_cmd_rtc_destroy(ctx->mdev, *rtc_0_id);
-free_ste:
-	if (rtc_type == HWS_MATCHER_RTC_TYPE_MATCH)
-		mlx5hws_pool_chunk_free(ste_pool, ste);
+	mlx5hws_cmd_rtc_destroy(ctx->mdev, matcher->match_ste.rtc_0_id);
 	return ret;
 }
 
-static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher,
-				    enum mlx5hws_matcher_rtc_type rtc_type,
-				    u8 action_ste_selector)
+static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher)
 {
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool_chunk *ste;
-	struct mlx5hws_pool *ste_pool;
-	u32 rtc_0_id, rtc_1_id;
-
-	switch (rtc_type) {
-	case HWS_MATCHER_RTC_TYPE_MATCH:
-		rtc_0_id = matcher->match_ste.rtc_0_id;
-		rtc_1_id = matcher->match_ste.rtc_1_id;
-		ste_pool = matcher->match_ste.pool;
-		ste = &matcher->match_ste.ste;
-		break;
-	case HWS_MATCHER_RTC_TYPE_STE_ARRAY:
-		action_ste = &matcher->action_ste[action_ste_selector];
-		rtc_0_id = action_ste->rtc_0_id;
-		rtc_1_id = action_ste->rtc_1_id;
-		ste_pool = action_ste->pool;
-		ste = &action_ste->ste;
-		break;
-	default:
-		return;
-	}
+	struct mlx5_core_dev *mdev = matcher->tbl->ctx->mdev;
 
-	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB)
-		mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, rtc_1_id);
+	if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB)
+		mlx5hws_cmd_rtc_destroy(mdev, matcher->match_ste.rtc_1_id);
 
-	mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, rtc_0_id);
-	if (rtc_type == HWS_MATCHER_RTC_TYPE_MATCH)
-		mlx5hws_pool_chunk_free(ste_pool, ste);
+	mlx5hws_cmd_rtc_destroy(mdev, matcher->match_ste.rtc_0_id);
 }
 
 static int
@@ -458,170 +626,17 @@ static int hws_matcher_check_and_process_at(struct mlx5hws_matcher *matcher,
 	return 0;
 }
 
-static int hws_matcher_resize_init(struct mlx5hws_matcher *src_matcher)
-{
-	struct mlx5hws_matcher_resize_data *resize_data;
-
-	resize_data = kzalloc(sizeof(*resize_data), GFP_KERNEL);
-	if (!resize_data)
-		return -ENOMEM;
-
-	resize_data->max_stes = src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes;
-
-	resize_data->action_ste[0].stc = src_matcher->action_ste[0].stc;
-	resize_data->action_ste[0].rtc_0_id = src_matcher->action_ste[0].rtc_0_id;
-	resize_data->action_ste[0].rtc_1_id = src_matcher->action_ste[0].rtc_1_id;
-	resize_data->action_ste[0].pool = src_matcher->action_ste[0].max_stes ?
-					  src_matcher->action_ste[0].pool :
-					  NULL;
-	resize_data->action_ste[1].stc = src_matcher->action_ste[1].stc;
-	resize_data->action_ste[1].rtc_0_id = src_matcher->action_ste[1].rtc_0_id;
-	resize_data->action_ste[1].rtc_1_id = src_matcher->action_ste[1].rtc_1_id;
-	resize_data->action_ste[1].pool = src_matcher->action_ste[1].max_stes ?
-					  src_matcher->action_ste[1].pool :
-					   NULL;
-
-	/* Place the new resized matcher on the dst matcher's list */
-	list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data);
-
-	/* Move all the previous resized matchers to the dst matcher's list */
-	while (!list_empty(&src_matcher->resize_data)) {
-		resize_data = list_first_entry(&src_matcher->resize_data,
-					       struct mlx5hws_matcher_resize_data,
-					       list_node);
-		list_del_init(&resize_data->list_node);
-		list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data);
-	}
-
-	return 0;
-}
-
-static void hws_matcher_resize_uninit(struct mlx5hws_matcher *matcher)
-{
-	struct mlx5hws_matcher_resize_data *resize_data;
-
-	if (!mlx5hws_matcher_is_resizable(matcher))
-		return;
-
-	while (!list_empty(&matcher->resize_data)) {
-		resize_data = list_first_entry(&matcher->resize_data,
-					       struct mlx5hws_matcher_resize_data,
-					       list_node);
-		list_del_init(&resize_data->list_node);
-
-		if (resize_data->max_stes) {
-			mlx5hws_action_free_single_stc(matcher->tbl->ctx,
-						       matcher->tbl->type,
-						       &resize_data->action_ste[1].stc);
-			mlx5hws_action_free_single_stc(matcher->tbl->ctx,
-						       matcher->tbl->type,
-						       &resize_data->action_ste[0].stc);
-
-			if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
-				mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-							resize_data->action_ste[1].rtc_1_id);
-				mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-							resize_data->action_ste[0].rtc_1_id);
-			}
-			mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-						resize_data->action_ste[1].rtc_0_id);
-			mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-						resize_data->action_ste[0].rtc_0_id);
-			if (resize_data->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].pool) {
-				mlx5hws_pool_destroy(resize_data->action_ste[1].pool);
-				mlx5hws_pool_destroy(resize_data->action_ste[0].pool);
-			}
-		}
-
-		kfree(resize_data);
-	}
-}
-
-static int
-hws_matcher_bind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector)
-{
-	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool_attr pool_attr = {0};
-	struct mlx5hws_context *ctx = tbl->ctx;
-	int ret;
-
-	action_ste = &matcher->action_ste[action_ste_selector];
-
-	/* Allocate action STE mempool */
-	pool_attr.table_type = tbl->type;
-	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL;
-	pool_attr.alloc_log_sz = ilog2(roundup_pow_of_two(action_ste->max_stes)) +
-				 matcher->attr.table.sz_row_log;
-	hws_matcher_set_pool_attr(&pool_attr, matcher);
-	action_ste->pool = mlx5hws_pool_create(ctx, &pool_attr);
-	if (!action_ste->pool) {
-		mlx5hws_err(ctx, "Failed to create action ste pool\n");
-		return -EINVAL;
-	}
-
-	/* Allocate action RTC */
-	ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
-	if (ret) {
-		mlx5hws_err(ctx, "Failed to create action RTC\n");
-		goto free_ste_pool;
-	}
-
-	/* Allocate STC for jumps to STE */
-	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
-	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
-	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
-	stc_attr.ste_table.ste = action_ste->ste;
-	stc_attr.ste_table.ste_pool = action_ste->pool;
-	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
-
-	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl->type,
-					      &action_ste->stc);
-	if (ret) {
-		mlx5hws_err(ctx, "Failed to create action jump to table STC\n");
-		goto free_rtc;
-	}
-
-	return 0;
-
-free_rtc:
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
-free_ste_pool:
-	mlx5hws_pool_destroy(action_ste->pool);
-	return ret;
-}
-
-static void hws_matcher_unbind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector)
-{
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-
-	action_ste = &matcher->action_ste[action_ste_selector];
-
-	if (!action_ste->max_stes ||
-	    matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION ||
-	    mlx5hws_matcher_is_in_resize(matcher))
-		return;
-
-	mlx5hws_action_free_single_stc(tbl->ctx, tbl->type, &action_ste->stc);
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
-	mlx5hws_pool_destroy(action_ste->pool);
-}
-
 static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher)
 {
 	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt);
-	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_context *ctx = tbl->ctx;
-	u32 required_stes;
-	u8 max_stes = 0;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 required_stes, max_stes;
 	int i, ret;
 
 	if (matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION)
 		return 0;
 
+	max_stes = 0;
 	for (i = 0; i < matcher->num_of_at; i++) {
 		struct mlx5hws_action_template *at = &matcher->at[i];
 
@@ -637,32 +652,33 @@ static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher)
 		/* Future: Optimize reparse */
 	}
 
-	/* There are no additional STEs required for matcher */
-	if (!max_stes)
-		return 0;
-
-	matcher->action_ste[0].max_stes = max_stes;
-	matcher->action_ste[1].max_stes = max_stes;
-
-	ret = hws_matcher_bind_at_idx(matcher, 0);
-	if (ret)
-		return ret;
-
-	ret = hws_matcher_bind_at_idx(matcher, 1);
-	if (ret)
-		goto free_at_0;
+	matcher->num_of_action_stes = max_stes;
 
 	return 0;
-
-free_at_0:
-	hws_matcher_unbind_at_idx(matcher, 0);
-	return ret;
 }
 
-static void hws_matcher_unbind_at(struct mlx5hws_matcher *matcher)
+static void hws_matcher_set_ip_version_match(struct mlx5hws_matcher *matcher)
 {
-	hws_matcher_unbind_at_idx(matcher, 1);
-	hws_matcher_unbind_at_idx(matcher, 0);
+	int i;
+
+	for (i = 0; i < matcher->mt->fc_sz; i++) {
+		switch (matcher->mt->fc[i].fname) {
+		case MLX5HWS_DEFINER_FNAME_ETH_TYPE_O:
+			matcher->matches_outer_ethertype = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_O:
+			matcher->matches_outer_ip_version = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_TYPE_I:
+			matcher->matches_inner_ethertype = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_I:
+			matcher->matches_inner_ip_version = 1;
+			break;
+		default:
+			break;
+		}
+	}
 }
 
 static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher)
@@ -681,10 +697,11 @@ static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher)
 		}
 	}
 
+	hws_matcher_set_ip_version_match(matcher);
+
 	/* Create an STE pool per matcher*/
 	pool_attr.table_type = matcher->tbl->type;
 	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_MATCHER_STE_POOL;
 	pool_attr.alloc_log_sz = matcher->attr.table.sz_col_log +
 				 matcher->attr.table.sz_row_log;
 	hws_matcher_set_pool_attr(&pool_attr, matcher);
@@ -786,6 +803,8 @@ hws_matcher_process_attr(struct mlx5hws_cmd_query_caps *caps,
 		attr->table.sz_col_log = hws_matcher_rules_to_tbl_depth(attr->rule.num_log);
 
 	matcher->flags |= attr->resizable ? MLX5HWS_MATCHER_FLAGS_RESIZABLE : 0;
+	matcher->flags |= attr->isolated_matcher_end_ft_id ?
+			  MLX5HWS_MATCHER_FLAGS_ISOLATED : 0;
 
 	return hws_matcher_check_attr_sz(caps, matcher);
 }
@@ -807,10 +826,10 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher)
 	/* Create matcher end flow table anchor */
 	ret = hws_matcher_create_end_ft(matcher);
 	if (ret)
-		goto unbind_at;
+		goto unbind_mt;
 
 	/* Allocate the RTC for the new matcher */
-	ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+	ret = hws_matcher_create_rtc(matcher);
 	if (ret)
 		goto destroy_end_ft;
 
@@ -822,11 +841,9 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher)
 	return 0;
 
 destroy_rtc:
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+	hws_matcher_destroy_rtc(matcher);
 destroy_end_ft:
 	hws_matcher_destroy_end_ft(matcher);
-unbind_at:
-	hws_matcher_unbind_at(matcher);
 unbind_mt:
 	hws_matcher_unbind_mt(matcher);
 	return ret;
@@ -834,11 +851,9 @@ unbind_mt:
 
 static void hws_matcher_destroy_and_disconnect(struct mlx5hws_matcher *matcher)
 {
-	hws_matcher_resize_uninit(matcher);
 	hws_matcher_disconnect(matcher);
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+	hws_matcher_destroy_rtc(matcher);
 	hws_matcher_destroy_end_ft(matcher);
-	hws_matcher_unbind_at(matcher);
 	hws_matcher_unbind_mt(matcher);
 }
 
@@ -860,8 +875,6 @@ hws_matcher_create_col_matcher(struct mlx5hws_matcher *matcher)
 	if (!col_matcher)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&col_matcher->resize_data);
-
 	col_matcher->tbl = matcher->tbl;
 	col_matcher->mt = matcher->mt;
 	col_matcher->at = matcher->at;
@@ -878,6 +891,8 @@ hws_matcher_create_col_matcher(struct mlx5hws_matcher *matcher)
 		col_matcher->attr.table.sz_row_log -= MLX5HWS_MATCHER_ASSURED_ROW_RATIO;
 
 	col_matcher->attr.max_num_of_at_attach = matcher->attr.max_num_of_at_attach;
+	col_matcher->attr.isolated_matcher_end_ft_id =
+		matcher->attr.isolated_matcher_end_ft_id;
 
 	ret = hws_matcher_process_attr(ctx->caps, col_matcher);
 	if (ret)
@@ -915,8 +930,6 @@ static int hws_matcher_init(struct mlx5hws_matcher *matcher)
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 	int ret;
 
-	INIT_LIST_HEAD(&matcher->resize_data);
-
 	mutex_lock(&ctx->ctrl_lock);
 
 	/* Allocate matcher resource and connect to the packet pipe */
@@ -951,18 +964,44 @@ static int hws_matcher_uninit(struct mlx5hws_matcher *matcher)
 	return 0;
 }
 
+static int hws_matcher_grow_at_array(struct mlx5hws_matcher *matcher)
+{
+	void *p;
+
+	if (matcher->size_of_at_array >= MLX5HWS_MATCHER_MAX_AT)
+		return -ENOMEM;
+
+	matcher->size_of_at_array *= 2;
+	p = krealloc(matcher->at,
+		     matcher->size_of_at_array * sizeof(*matcher->at),
+		     __GFP_ZERO | GFP_KERNEL);
+	if (!p) {
+		matcher->size_of_at_array /= 2;
+		return -ENOMEM;
+	}
+
+	matcher->at = p;
+
+	return 0;
+}
+
 int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
 			      struct mlx5hws_action_template *at)
 {
 	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt);
-	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 	u32 required_stes;
 	int ret;
 
-	if (!matcher->attr.max_num_of_at_attach) {
-		mlx5hws_dbg(ctx, "Num of current at (%d) exceed allowed value\n",
-			    matcher->num_of_at);
-		return -EOPNOTSUPP;
+	if (unlikely(matcher->num_of_at >= matcher->size_of_at_array)) {
+		ret = hws_matcher_grow_at_array(matcher);
+		if (ret)
+			return ret;
+
+		if (matcher->col_matcher) {
+			ret = hws_matcher_grow_at_array(matcher->col_matcher);
+			if (ret)
+				return ret;
+		}
 	}
 
 	ret = hws_matcher_check_and_process_at(matcher, at);
@@ -970,16 +1009,11 @@ int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
 		return ret;
 
 	required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term);
-	if (matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes < required_stes) {
-		mlx5hws_dbg(ctx, "Required STEs [%d] exceeds initial action template STE [%d]\n",
-			    required_stes,
-			    matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes);
-		return -ENOMEM;
-	}
+	if (matcher->num_of_action_stes < required_stes)
+		matcher->num_of_action_stes = required_stes;
 
 	matcher->at[matcher->num_of_at] = *at;
 	matcher->num_of_at += 1;
-	matcher->attr.max_num_of_at_attach -= 1;
 
 	if (matcher->col_matcher)
 		matcher->col_matcher->num_of_at = matcher->num_of_at;
@@ -1007,9 +1041,10 @@ hws_matcher_set_templates(struct mlx5hws_matcher *matcher,
 	if (!matcher->mt)
 		return -ENOMEM;
 
-	matcher->at = kcalloc(num_of_at + matcher->attr.max_num_of_at_attach,
-			      sizeof(*matcher->at),
-			      GFP_KERNEL);
+	matcher->size_of_at_array =
+		num_of_at + matcher->attr.max_num_of_at_attach;
+	matcher->at = kvcalloc(matcher->size_of_at_array, sizeof(*matcher->at),
+			       GFP_KERNEL);
 	if (!matcher->at) {
 		mlx5hws_err(ctx, "Failed to allocate action template array\n");
 		ret = -ENOMEM;
@@ -1035,7 +1070,7 @@ free_mt:
 static void
 hws_matcher_unset_templates(struct mlx5hws_matcher *matcher)
 {
-	kfree(matcher->at);
+	kvfree(matcher->at);
 	kfree(matcher->mt);
 }
 
@@ -1157,8 +1192,7 @@ static int hws_matcher_resize_precheck(struct mlx5hws_matcher *src_matcher,
 		return -EINVAL;
 	}
 
-	if (src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes >
-	    dst_matcher->action_ste[0].max_stes) {
+	if (src_matcher->num_of_action_stes > dst_matcher->num_of_action_stes) {
 		mlx5hws_err(ctx, "Src/dst matcher max STEs mismatch\n");
 		return -EINVAL;
 	}
@@ -1187,10 +1221,6 @@ int mlx5hws_matcher_resize_set_target(struct mlx5hws_matcher *src_matcher,
 
 	src_matcher->resize_dst = dst_matcher;
 
-	ret = hws_matcher_resize_init(src_matcher);
-	if (ret)
-		src_matcher->resize_dst = NULL;
-
 out:
 	mutex_unlock(&src_matcher->tbl->ctx->ctrl_lock);
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
index 81ff487f57be..32e83cddcd60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
@@ -18,6 +18,14 @@
 /* Required depth of the main large table */
 #define MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH 2
 
+/* Action RTC size multiplier that is required in order
+ * to support rule update for rules with action STEs.
+ */
+#define MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT 1
+
+/* Maximum number of action templates that can be attached to a matcher. */
+#define MLX5HWS_MATCHER_MAX_AT 128
+
 enum mlx5hws_matcher_offset {
 	MLX5HWS_MATCHER_OFFSET_TAG_DW1 = 12,
 	MLX5HWS_MATCHER_OFFSET_TAG_DW0 = 13,
@@ -26,6 +34,7 @@ enum mlx5hws_matcher_offset {
 enum mlx5hws_matcher_flags {
 	MLX5HWS_MATCHER_FLAGS_COLLISION = 1 << 2,
 	MLX5HWS_MATCHER_FLAGS_RESIZABLE	= 1 << 3,
+	MLX5HWS_MATCHER_FLAGS_ISOLATED	= 1 << 4,
 };
 
 struct mlx5hws_match_template {
@@ -37,32 +46,15 @@ struct mlx5hws_match_template {
 };
 
 struct mlx5hws_matcher_match_ste {
-	struct mlx5hws_pool_chunk ste;
-	u32 rtc_0_id;
-	u32 rtc_1_id;
-	struct mlx5hws_pool *pool;
-};
-
-struct mlx5hws_matcher_action_ste {
-	struct mlx5hws_pool_chunk ste;
-	struct mlx5hws_pool_chunk stc;
-	u32 rtc_0_id;
-	u32 rtc_1_id;
-	struct mlx5hws_pool *pool;
-	u8 max_stes;
-};
-
-struct mlx5hws_matcher_resize_data_node {
-	struct mlx5hws_pool_chunk stc;
 	u32 rtc_0_id;
 	u32 rtc_1_id;
 	struct mlx5hws_pool *pool;
 };
 
-struct mlx5hws_matcher_resize_data {
-	struct mlx5hws_matcher_resize_data_node action_ste[2];
-	u8 max_stes;
-	struct list_head list_node;
+enum {
+	MLX5HWS_MATCHER_IPV_UNSET = 0,
+	MLX5HWS_MATCHER_IPV_4 = 1,
+	MLX5HWS_MATCHER_IPV_6 = 2,
 };
 
 struct mlx5hws_matcher {
@@ -71,16 +63,22 @@ struct mlx5hws_matcher {
 	struct mlx5hws_match_template *mt;
 	struct mlx5hws_action_template *at;
 	u8 num_of_at;
+	u8 size_of_at_array;
 	u8 num_of_mt;
+	u8 num_of_action_stes;
 	/* enum mlx5hws_matcher_flags */
 	u8 flags;
+	u8 matches_outer_ethertype:1;
+	u8 matches_outer_ip_version:1;
+	u8 matches_inner_ethertype:1;
+	u8 matches_inner_ip_version:1;
+	u8 outer_ip_version:2;
+	u8 inner_ip_version:2;
 	u32 end_ft_id;
 	struct mlx5hws_matcher *col_matcher;
 	struct mlx5hws_matcher *resize_dst;
 	struct mlx5hws_matcher_match_ste match_ste;
-	struct mlx5hws_matcher_action_ste action_ste[2];
 	struct list_head list_node;
-	struct list_head resize_data;
 };
 
 static inline bool
@@ -99,9 +97,17 @@ static inline bool mlx5hws_matcher_is_in_resize(struct mlx5hws_matcher *matcher)
 	return !!matcher->resize_dst;
 }
 
+static inline bool mlx5hws_matcher_is_isolated(struct mlx5hws_matcher *matcher)
+{
+	return !!(matcher->flags & MLX5HWS_MATCHER_FLAGS_ISOLATED);
+}
+
 static inline bool mlx5hws_matcher_is_insert_by_idx(struct mlx5hws_matcher *matcher)
 {
 	return matcher->attr.insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX;
 }
 
+int mlx5hws_matcher_update_end_ft_isolated(struct mlx5hws_table *tbl,
+					   u32 miss_ft_id);
+
 #endif /* HWS_MATCHER_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
index f39d636ff39a..d8ac6c196211 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
@@ -70,7 +70,6 @@ enum mlx5hws_send_queue_actions {
 struct mlx5hws_context_attr {
 	u16 queues;
 	u16 queue_size;
-	bool bwc; /* add support for backward compatible API*/
 };
 
 struct mlx5hws_table_attr {
@@ -120,6 +119,8 @@ struct mlx5hws_matcher_attr {
 	};
 	/* Optional AT attach configuration - Max number of additional AT */
 	u8 max_num_of_at_attach;
+	/* Optional end FT (miss FT ID) for match RTC (for isolated matcher) */
+	u32 isolated_matcher_end_ft_id;
 };
 
 struct mlx5hws_rule_attr {
@@ -212,6 +213,7 @@ struct mlx5hws_action_dest_attr {
 	struct mlx5hws_action *dest;
 	/* Optional reformat action */
 	struct mlx5hws_action *reformat;
+	bool is_wire_ft;
 };
 
 /**
@@ -503,6 +505,15 @@ enum mlx5hws_action_type
 mlx5hws_action_get_type(struct mlx5hws_action *action);
 
 /**
+ * mlx5hws_action_get_dev - Get mlx5 core device.
+ *
+ * @action: The action to get the device from.
+ *
+ * Return: mlx5 core device.
+ */
+struct mlx5_core_dev *mlx5hws_action_get_dev(struct mlx5hws_action *action);
+
+/**
  * mlx5hws_action_create_dest_drop - Create a direct rule drop action.
  *
  * @ctx: The context in which the new action will be created.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
index 06db5e4726ae..51e4c551e0ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
@@ -153,8 +153,7 @@ mlx5hws_pat_get_existing_cached_pattern(struct mlx5hws_pattern_cache *cache,
 	cached_pattern = mlx5hws_pat_find_cached_pattern(cache, num_of_actions, actions);
 	if (cached_pattern) {
 		/* LRU: move it to be first in the list */
-		list_del_init(&cached_pattern->ptrn_list_node);
-		list_add(&cached_pattern->ptrn_list_node, &cache->ptrn_list);
+		list_move(&cached_pattern->ptrn_list_node, &cache->ptrn_list);
 		cached_pattern->refcount++;
 	}
 
@@ -344,7 +343,7 @@ void mlx5hws_arg_write(struct mlx5hws_send_engine *queue,
 		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len);
 		memset(wqe_ctrl, 0, wqe_len);
 		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_arg, &wqe_len);
-		memcpy(wqe_arg, arg_data, wqe_len);
+		memcpy(wqe_arg, arg_data, MLX5HWS_ARG_DATA_SIZE);
 		send_attr.id = arg_idx++;
 		mlx5hws_send_engine_post_end(&ctrl, &send_attr);
 
@@ -491,8 +490,8 @@ hws_action_modify_get_target_fields(u8 action_type, __be64 *pattern,
 	switch (action_type) {
 	case MLX5_ACTION_TYPE_SET:
 	case MLX5_ACTION_TYPE_ADD:
-		*src_field = MLX5_GET(set_action_in, pattern, field);
-		*dst_field = INVALID_FIELD;
+		*src_field = INVALID_FIELD;
+		*dst_field = MLX5_GET(set_action_in, pattern, field);
 		break;
 	case MLX5_ACTION_TYPE_COPY:
 		*src_field = MLX5_GET(copy_action_in, pattern, src_field);
@@ -523,57 +522,59 @@ bool mlx5hws_pat_verify_actions(struct mlx5hws_context *ctx, __be64 pattern[], s
 	return true;
 }
 
-void mlx5hws_pat_calc_nope(__be64 *pattern, size_t num_actions,
-			   size_t max_actions, size_t *new_size,
-			   u32 *nope_location, __be64 *new_pat)
+int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
+			 size_t max_actions, size_t *new_size,
+			 u32 *nop_locations, __be64 *new_pat)
 {
-	u16 prev_src_field = 0, prev_dst_field = 0;
+	u16 prev_src_field = INVALID_FIELD, prev_dst_field = INVALID_FIELD;
 	u16 src_field, dst_field;
 	u8 action_type;
+	bool dependent;
 	size_t i, j;
 
 	*new_size = num_actions;
-	*nope_location = 0;
+	*nop_locations = 0;
 
 	if (num_actions == 1)
-		return;
+		return 0;
 
 	for (i = 0, j = 0; i < num_actions; i++, j++) {
-		action_type = MLX5_GET(set_action_in, &pattern[i], action_type);
+		if (j >= max_actions)
+			return -EINVAL;
 
+		action_type = MLX5_GET(set_action_in, &pattern[i], action_type);
 		hws_action_modify_get_target_fields(action_type, &pattern[i],
 						    &src_field, &dst_field);
-		if (i % 2) {
-			if (action_type == MLX5_ACTION_TYPE_COPY &&
-			    (prev_src_field == src_field ||
-			     prev_dst_field == dst_field)) {
-				/* need Nope */
-				*new_size += 1;
-				*nope_location |= BIT(i);
-				memset(&new_pat[j], 0, MLX5HWS_MODIFY_ACTION_SIZE);
-				MLX5_SET(set_action_in, &new_pat[j],
-					 action_type,
-					 MLX5_MODIFICATION_TYPE_NOP);
-				j++;
-			} else if (prev_src_field == src_field) {
-				/* need Nope*/
-				*new_size += 1;
-				*nope_location |= BIT(i);
-				MLX5_SET(set_action_in, &new_pat[j],
-					 action_type,
-					 MLX5_MODIFICATION_TYPE_NOP);
-				j++;
-			}
-		}
-		memcpy(&new_pat[j], &pattern[i], MLX5HWS_MODIFY_ACTION_SIZE);
-		/* check if no more space */
-		if (j > max_actions) {
-			*new_size = num_actions;
-			*nope_location = 0;
-			return;
+
+		/* For every action, look at it and the previous one. The two
+		 * actions are dependent if:
+		 */
+		dependent =
+			(i > 0) &&
+			/* At least one of the actions is a write and */
+			(dst_field != INVALID_FIELD ||
+			 prev_dst_field != INVALID_FIELD) &&
+			/* One reads from the other's source */
+			(dst_field == prev_src_field ||
+			 src_field == prev_dst_field ||
+			 /* Or both write to the same destination */
+			 dst_field == prev_dst_field);
+
+		if (dependent) {
+			*new_size += 1;
+			*nop_locations |= BIT(i);
+			memset(&new_pat[j], 0, MLX5HWS_MODIFY_ACTION_SIZE);
+			MLX5_SET(set_action_in, &new_pat[j], action_type,
+				 MLX5_MODIFICATION_TYPE_NOP);
+			j++;
+			if (j >= max_actions)
+				return -EINVAL;
 		}
 
+		memcpy(&new_pat[j], &pattern[i], MLX5HWS_MODIFY_ACTION_SIZE);
 		prev_src_field = src_field;
 		prev_dst_field = dst_field;
 	}
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
index 27ca93385b08..7fbd8dc7aa18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
@@ -31,7 +31,7 @@ struct mlx5hws_pattern_cache_item {
 		u8 *data;
 		u16 num_of_actions;
 	} mh_data;
-	u32 refcount;
+	u32 refcount; /* protected by pattern_cache lock */
 	struct list_head ptrn_list_node;
 };
 
@@ -96,6 +96,7 @@ int mlx5hws_arg_write_inline_arg_data(struct mlx5hws_context *ctx,
 				      u8 *arg_data,
 				      size_t data_size);
 
-void mlx5hws_pat_calc_nope(__be64 *pattern, size_t num_actions, size_t max_actions,
-			   size_t *new_size, u32 *nope_location, __be64 *new_pat);
+int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
+			 size_t max_actions, size_t *new_size,
+			 u32 *nop_locations, __be64 *new_pat);
 #endif /* MLX5HWS_PAT_ARG_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
index fed2d913f3b8..7e37d6e9eb83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
@@ -20,15 +20,14 @@ static void hws_pool_free_one_resource(struct mlx5hws_pool_resource *resource)
 	kfree(resource);
 }
 
-static void hws_pool_resource_free(struct mlx5hws_pool *pool,
-				   int resource_idx)
+static void hws_pool_resource_free(struct mlx5hws_pool *pool)
 {
-	hws_pool_free_one_resource(pool->resource[resource_idx]);
-	pool->resource[resource_idx] = NULL;
+	hws_pool_free_one_resource(pool->resource);
+	pool->resource = NULL;
 
 	if (pool->tbl_type == MLX5HWS_TABLE_TYPE_FDB) {
-		hws_pool_free_one_resource(pool->mirror_resource[resource_idx]);
-		pool->mirror_resource[resource_idx] = NULL;
+		hws_pool_free_one_resource(pool->mirror_resource);
+		pool->mirror_resource = NULL;
 	}
 }
 
@@ -61,10 +60,8 @@ hws_pool_create_one_resource(struct mlx5hws_pool *pool, u32 log_range,
 		ret = -EINVAL;
 	}
 
-	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to allocate resource objects\n");
+	if (ret)
 		goto free_resource;
-	}
 
 	resource->pool = pool;
 	resource->range = 1 << log_range;
@@ -77,199 +74,114 @@ free_resource:
 	return NULL;
 }
 
-static int
-hws_pool_resource_alloc(struct mlx5hws_pool *pool, u32 log_range, int idx)
+static int hws_pool_resource_alloc(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_pool_resource *resource;
 	u32 fw_ft_type, opt_log_range;
 
 	fw_ft_type = mlx5hws_table_get_res_fw_ft_type(pool->tbl_type, false);
-	opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_ORIG ? 0 : log_range;
+	opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_MIRROR ?
+				0 : pool->alloc_log_sz;
 	resource = hws_pool_create_one_resource(pool, opt_log_range, fw_ft_type);
 	if (!resource) {
-		mlx5hws_err(pool->ctx, "Failed allocating resource\n");
+		mlx5hws_err(pool->ctx, "Failed to allocate resource\n");
 		return -EINVAL;
 	}
 
-	pool->resource[idx] = resource;
+	pool->resource = resource;
 
 	if (pool->tbl_type == MLX5HWS_TABLE_TYPE_FDB) {
 		struct mlx5hws_pool_resource *mirror_resource;
 
 		fw_ft_type = mlx5hws_table_get_res_fw_ft_type(pool->tbl_type, true);
-		opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_MIRROR ? 0 : log_range;
+		opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_ORIG ?
+					0 : pool->alloc_log_sz;
 		mirror_resource = hws_pool_create_one_resource(pool, opt_log_range, fw_ft_type);
 		if (!mirror_resource) {
-			mlx5hws_err(pool->ctx, "Failed allocating mirrored resource\n");
+			mlx5hws_err(pool->ctx, "Failed to allocate mirrored resource\n");
 			hws_pool_free_one_resource(resource);
-			pool->resource[idx] = NULL;
+			pool->resource = NULL;
 			return -EINVAL;
 		}
-		pool->mirror_resource[idx] = mirror_resource;
+		pool->mirror_resource = mirror_resource;
 	}
 
 	return 0;
 }
 
-static unsigned long *hws_pool_create_and_init_bitmap(u32 log_range)
-{
-	unsigned long *cur_bmp;
-
-	cur_bmp = bitmap_zalloc(1 << log_range, GFP_KERNEL);
-	if (!cur_bmp)
-		return NULL;
-
-	bitmap_fill(cur_bmp, 1 << log_range);
-
-	return cur_bmp;
-}
-
-static void hws_pool_buddy_db_put_chunk(struct mlx5hws_pool *pool,
-					struct mlx5hws_pool_chunk *chunk)
+static int hws_pool_buddy_init(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_buddy_mem *buddy;
 
-	buddy = pool->db.buddy_manager->buddies[chunk->resource_idx];
+	buddy = mlx5hws_buddy_create(pool->alloc_log_sz);
 	if (!buddy) {
-		mlx5hws_err(pool->ctx, "No such buddy (%d)\n", chunk->resource_idx);
-		return;
-	}
-
-	mlx5hws_buddy_free_mem(buddy, chunk->offset, chunk->order);
-}
-
-static struct mlx5hws_buddy_mem *
-hws_pool_buddy_get_next_buddy(struct mlx5hws_pool *pool, int idx,
-			      u32 order, bool *is_new_buddy)
-{
-	static struct mlx5hws_buddy_mem *buddy;
-	u32 new_buddy_size;
-
-	buddy = pool->db.buddy_manager->buddies[idx];
-	if (buddy)
-		return buddy;
-
-	new_buddy_size = max(pool->alloc_log_sz, order);
-	*is_new_buddy = true;
-	buddy = mlx5hws_buddy_create(new_buddy_size);
-	if (!buddy) {
-		mlx5hws_err(pool->ctx, "Failed to create buddy order: %d index: %d\n",
-			    new_buddy_size, idx);
-		return NULL;
+		mlx5hws_err(pool->ctx, "Failed to create buddy order: %zu\n",
+			    pool->alloc_log_sz);
+		return -ENOMEM;
 	}
 
-	if (hws_pool_resource_alloc(pool, new_buddy_size, idx) != 0) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, new_buddy_size, idx);
+	if (hws_pool_resource_alloc(pool) != 0) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d size %zu\n",
+			    pool->type, pool->alloc_log_sz);
 		mlx5hws_buddy_cleanup(buddy);
-		return NULL;
+		return -ENOMEM;
 	}
 
-	pool->db.buddy_manager->buddies[idx] = buddy;
+	pool->db.buddy = buddy;
 
-	return buddy;
+	return 0;
 }
 
-static int hws_pool_buddy_get_mem_chunk(struct mlx5hws_pool *pool,
-					int order,
-					u32 *buddy_idx,
-					int *seg)
+static int hws_pool_buddy_db_get_chunk(struct mlx5hws_pool *pool,
+				       struct mlx5hws_pool_chunk *chunk)
 {
-	struct mlx5hws_buddy_mem *buddy;
-	bool new_mem = false;
-	int ret = 0;
-	int i;
-
-	*seg = -1;
-
-	/* Find the next free place from the buddy array */
-	while (*seg == -1) {
-		for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-			buddy = hws_pool_buddy_get_next_buddy(pool, i,
-							      order,
-							      &new_mem);
-			if (!buddy) {
-				ret = -ENOMEM;
-				goto out;
-			}
-
-			*seg = mlx5hws_buddy_alloc_mem(buddy, order);
-			if (*seg != -1)
-				goto found;
-
-			if (pool->flags & MLX5HWS_POOL_FLAGS_ONE_RESOURCE) {
-				mlx5hws_err(pool->ctx,
-					    "Fail to allocate seg for one resource pool\n");
-				ret = -ENOMEM;
-				goto out;
-			}
-
-			if (new_mem) {
-				/* We have new memory pool, should be place for us */
-				mlx5hws_err(pool->ctx,
-					    "No memory for order: %d with buddy no: %d\n",
-					    order, i);
-				ret = -ENOMEM;
-				goto out;
-			}
-		}
+	struct mlx5hws_buddy_mem *buddy = pool->db.buddy;
+
+	if (!buddy) {
+		mlx5hws_err(pool->ctx, "Bad buddy state\n");
+		return -EINVAL;
 	}
 
-found:
-	*buddy_idx = i;
-out:
-	return ret;
+	chunk->offset = mlx5hws_buddy_alloc_mem(buddy, chunk->order);
+	if (chunk->offset >= 0)
+		return 0;
+
+	return -ENOMEM;
 }
 
-static int hws_pool_buddy_db_get_chunk(struct mlx5hws_pool *pool,
-				       struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_buddy_db_put_chunk(struct mlx5hws_pool *pool,
+					struct mlx5hws_pool_chunk *chunk)
 {
-	int ret = 0;
+	struct mlx5hws_buddy_mem *buddy;
 
-	/* Go over the buddies and find next free slot */
-	ret = hws_pool_buddy_get_mem_chunk(pool, chunk->order,
-					   &chunk->resource_idx,
-					   &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
+	buddy = pool->db.buddy;
+	if (!buddy) {
+		mlx5hws_err(pool->ctx, "Bad buddy state\n");
+		return;
+	}
 
-	return ret;
+	mlx5hws_buddy_free_mem(buddy, chunk->offset, chunk->order);
 }
 
 static void hws_pool_buddy_db_uninit(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_buddy_mem *buddy;
-	int i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		buddy = pool->db.buddy_manager->buddies[i];
-		if (buddy) {
-			mlx5hws_buddy_cleanup(buddy);
-			kfree(buddy);
-			pool->db.buddy_manager->buddies[i] = NULL;
-		}
-	}
 
-	kfree(pool->db.buddy_manager);
+	buddy = pool->db.buddy;
+	if (buddy) {
+		mlx5hws_buddy_cleanup(buddy);
+		kfree(buddy);
+		pool->db.buddy = NULL;
+	}
 }
 
-static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool, u32 log_range)
+static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool)
 {
-	pool->db.buddy_manager = kzalloc(sizeof(*pool->db.buddy_manager), GFP_KERNEL);
-	if (!pool->db.buddy_manager)
-		return -ENOMEM;
-
-	if (pool->flags & MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE) {
-		bool new_buddy;
+	int ret;
 
-		if (!hws_pool_buddy_get_next_buddy(pool, 0, log_range, &new_buddy)) {
-			mlx5hws_err(pool->ctx,
-				    "Failed allocating memory on create log_sz: %d\n", log_range);
-			kfree(pool->db.buddy_manager);
-			return -ENOMEM;
-		}
-	}
+	ret = hws_pool_buddy_init(pool);
+	if (ret)
+		return ret;
 
 	pool->p_db_uninit = &hws_pool_buddy_db_uninit;
 	pool->p_get_chunk = &hws_pool_buddy_db_get_chunk;
@@ -278,261 +190,105 @@ static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool, u32 log_range)
 	return 0;
 }
 
-static int hws_pool_create_resource_on_index(struct mlx5hws_pool *pool,
-					     u32 alloc_size, int idx)
-{
-	int ret = hws_pool_resource_alloc(pool, alloc_size, idx);
-
-	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, alloc_size, idx);
-		return ret;
-	}
-
-	return 0;
-}
-
-static struct mlx5hws_pool_elements *
-hws_pool_element_create_new_elem(struct mlx5hws_pool *pool, u32 order, int idx)
+static unsigned long *hws_pool_create_and_init_bitmap(u32 log_range)
 {
-	struct mlx5hws_pool_elements *elem;
-	u32 alloc_size;
-
-	alloc_size = pool->alloc_log_sz;
+	unsigned long *bitmap;
 
-	elem = kzalloc(sizeof(*elem), GFP_KERNEL);
-	if (!elem)
+	bitmap = bitmap_zalloc(1 << log_range, GFP_KERNEL);
+	if (!bitmap)
 		return NULL;
 
-	/* Sharing the same resource, also means that all the elements are with size 1 */
-	if ((pool->flags & MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS) &&
-	    !(pool->flags & MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK)) {
-		 /* Currently all chunks in size 1 */
-		elem->bitmap = hws_pool_create_and_init_bitmap(alloc_size - order);
-		if (!elem->bitmap) {
-			mlx5hws_err(pool->ctx,
-				    "Failed to create bitmap type: %d: size %d index: %d\n",
-				    pool->type, alloc_size, idx);
-			goto free_elem;
-		}
-
-		elem->log_size = alloc_size - order;
-	}
-
-	if (hws_pool_create_resource_on_index(pool, alloc_size, idx)) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, alloc_size, idx);
-		goto free_db;
-	}
-
-	pool->db.element_manager->elements[idx] = elem;
-
-	return elem;
+	bitmap_fill(bitmap, 1 << log_range);
 
-free_db:
-	bitmap_free(elem->bitmap);
-free_elem:
-	kfree(elem);
-	return NULL;
+	return bitmap;
 }
 
-static int hws_pool_element_find_seg(struct mlx5hws_pool_elements *elem, int *seg)
+static int hws_pool_bitmap_init(struct mlx5hws_pool *pool)
 {
-	unsigned int segment, size;
-
-	size = 1 << elem->log_size;
+	unsigned long *bitmap;
 
-	segment = find_first_bit(elem->bitmap, size);
-	if (segment >= size) {
-		elem->is_full = true;
+	bitmap = hws_pool_create_and_init_bitmap(pool->alloc_log_sz);
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Failed to create bitmap order: %zu\n",
+			    pool->alloc_log_sz);
 		return -ENOMEM;
 	}
 
-	bitmap_clear(elem->bitmap, segment, 1);
-	*seg = segment;
-	return 0;
-}
-
-static int
-hws_pool_onesize_element_get_mem_chunk(struct mlx5hws_pool *pool, u32 order,
-				       u32 *idx, int *seg)
-{
-	struct mlx5hws_pool_elements *elem;
-
-	elem = pool->db.element_manager->elements[0];
-	if (!elem)
-		elem = hws_pool_element_create_new_elem(pool, order, 0);
-	if (!elem)
-		goto err_no_elem;
-
-	if (hws_pool_element_find_seg(elem, seg) != 0) {
-		mlx5hws_err(pool->ctx, "No more resources (last request order: %d)\n", order);
+	if (hws_pool_resource_alloc(pool) != 0) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %zu\n",
+			    pool->type, pool->alloc_log_sz);
+		bitmap_free(bitmap);
 		return -ENOMEM;
 	}
 
-	*idx = 0;
-	elem->num_of_elements++;
-	return 0;
+	pool->db.bitmap = bitmap;
 
-err_no_elem:
-	mlx5hws_err(pool->ctx, "Failed to allocate element for order: %d\n", order);
-	return -ENOMEM;
-}
-
-static int
-hws_pool_general_element_get_mem_chunk(struct mlx5hws_pool *pool, u32 order,
-				       u32 *idx, int *seg)
-{
-	int ret, i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		if (!pool->resource[i]) {
-			ret = hws_pool_create_resource_on_index(pool, order, i);
-			if (ret)
-				goto err_no_res;
-			*idx = i;
-			*seg = 0; /* One memory slot in that element */
-			return 0;
-		}
-	}
-
-	mlx5hws_err(pool->ctx, "No more resources (last request order: %d)\n", order);
-	return -ENOMEM;
-
-err_no_res:
-	mlx5hws_err(pool->ctx, "Failed to allocate element for order: %d\n", order);
-	return -ENOMEM;
+	return 0;
 }
 
-static int hws_pool_general_element_db_get_chunk(struct mlx5hws_pool *pool,
-						 struct mlx5hws_pool_chunk *chunk)
+static int hws_pool_bitmap_db_get_chunk(struct mlx5hws_pool *pool,
+					struct mlx5hws_pool_chunk *chunk)
 {
-	int ret;
-
-	/* Go over all memory elements and find/allocate free slot */
-	ret = hws_pool_general_element_get_mem_chunk(pool, chunk->order,
-						     &chunk->resource_idx,
-						     &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
+	unsigned long *bitmap, size;
 
-	return ret;
-}
+	if (chunk->order != 0) {
+		mlx5hws_err(pool->ctx, "Pool only supports order 0 allocs\n");
+		return -EINVAL;
+	}
 
-static void hws_pool_general_element_db_put_chunk(struct mlx5hws_pool *pool,
-						  struct mlx5hws_pool_chunk *chunk)
-{
-	if (unlikely(!pool->resource[chunk->resource_idx]))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
+	bitmap = pool->db.bitmap;
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Bad bitmap state\n");
+		return -EINVAL;
+	}
 
-	if (pool->flags & MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE)
-		hws_pool_resource_free(pool, chunk->resource_idx);
-}
+	size = 1 << pool->alloc_log_sz;
 
-static void hws_pool_general_element_db_uninit(struct mlx5hws_pool *pool)
-{
-	(void)pool;
-}
+	chunk->offset = find_first_bit(bitmap, size);
+	if (chunk->offset >= size)
+		return -ENOMEM;
 
-/* This memory management works as the following:
- * - At start doesn't allocate no mem at all.
- * - When new request for chunk arrived:
- *	allocate resource and give it.
- * - When free that chunk:
- *	the resource is freed.
- */
-static int hws_pool_general_element_db_init(struct mlx5hws_pool *pool)
-{
-	pool->p_db_uninit = &hws_pool_general_element_db_uninit;
-	pool->p_get_chunk = &hws_pool_general_element_db_get_chunk;
-	pool->p_put_chunk = &hws_pool_general_element_db_put_chunk;
+	bitmap_clear(bitmap, chunk->offset, 1);
 
 	return 0;
 }
 
-static void hws_onesize_element_db_destroy_element(struct mlx5hws_pool *pool,
-						   struct mlx5hws_pool_elements *elem,
-						   struct mlx5hws_pool_chunk *chunk)
-{
-	if (unlikely(!pool->resource[chunk->resource_idx]))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
-
-	hws_pool_resource_free(pool, chunk->resource_idx);
-	kfree(elem);
-	pool->db.element_manager->elements[chunk->resource_idx] = NULL;
-}
-
-static void hws_onesize_element_db_put_chunk(struct mlx5hws_pool *pool,
-					     struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_bitmap_db_put_chunk(struct mlx5hws_pool *pool,
+					 struct mlx5hws_pool_chunk *chunk)
 {
-	struct mlx5hws_pool_elements *elem;
+	unsigned long *bitmap;
 
-	if (unlikely(chunk->resource_idx))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
-
-	elem = pool->db.element_manager->elements[chunk->resource_idx];
-	if (!elem) {
-		mlx5hws_err(pool->ctx, "No such element (%d)\n", chunk->resource_idx);
+	bitmap = pool->db.bitmap;
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Bad bitmap state\n");
 		return;
 	}
 
-	bitmap_set(elem->bitmap, chunk->offset, 1);
-	elem->is_full = false;
-	elem->num_of_elements--;
-
-	if (pool->flags & MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE &&
-	    !elem->num_of_elements)
-		hws_onesize_element_db_destroy_element(pool, elem, chunk);
+	bitmap_set(bitmap, chunk->offset, 1);
 }
 
-static int hws_onesize_element_db_get_chunk(struct mlx5hws_pool *pool,
-					    struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_bitmap_db_uninit(struct mlx5hws_pool *pool)
 {
-	int ret = 0;
+	unsigned long *bitmap;
 
-	/* Go over all memory elements and find/allocate free slot */
-	ret = hws_pool_onesize_element_get_mem_chunk(pool, chunk->order,
-						     &chunk->resource_idx,
-						     &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
-
-	return ret;
-}
-
-static void hws_onesize_element_db_uninit(struct mlx5hws_pool *pool)
-{
-	struct mlx5hws_pool_elements *elem;
-	int i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		elem = pool->db.element_manager->elements[i];
-		if (elem) {
-			bitmap_free(elem->bitmap);
-			kfree(elem);
-			pool->db.element_manager->elements[i] = NULL;
-		}
+	bitmap = pool->db.bitmap;
+	if (bitmap) {
+		bitmap_free(bitmap);
+		pool->db.bitmap = NULL;
 	}
-	kfree(pool->db.element_manager);
 }
 
-/* This memory management works as the following:
- * - At start doesn't allocate no mem at all.
- * - When new request for chunk arrived:
- *  aloocate the first and only slot of memory/resource
- *  when it ended return error.
- */
-static int hws_pool_onesize_element_db_init(struct mlx5hws_pool *pool)
+static int hws_pool_bitmap_db_init(struct mlx5hws_pool *pool)
 {
-	pool->db.element_manager = kzalloc(sizeof(*pool->db.element_manager), GFP_KERNEL);
-	if (!pool->db.element_manager)
-		return -ENOMEM;
+	int ret;
 
-	pool->p_db_uninit = &hws_onesize_element_db_uninit;
-	pool->p_get_chunk = &hws_onesize_element_db_get_chunk;
-	pool->p_put_chunk = &hws_onesize_element_db_put_chunk;
+	ret = hws_pool_bitmap_init(pool);
+	if (ret)
+		return ret;
+
+	pool->p_db_uninit = &hws_pool_bitmap_db_uninit;
+	pool->p_get_chunk = &hws_pool_bitmap_db_get_chunk;
+	pool->p_put_chunk = &hws_pool_bitmap_db_put_chunk;
 
 	return 0;
 }
@@ -542,15 +298,14 @@ static int hws_pool_db_init(struct mlx5hws_pool *pool,
 {
 	int ret;
 
-	if (db_type == MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE)
-		ret = hws_pool_general_element_db_init(pool);
-	else if (db_type == MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE)
-		ret = hws_pool_onesize_element_db_init(pool);
+	if (db_type == MLX5HWS_POOL_DB_TYPE_BITMAP)
+		ret = hws_pool_bitmap_db_init(pool);
 	else
-		ret = hws_pool_buddy_db_init(pool, pool->alloc_log_sz);
+		ret = hws_pool_buddy_db_init(pool);
 
 	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to init general db : %d (ret: %d)\n", db_type, ret);
+		mlx5hws_err(pool->ctx, "Failed to init pool type: %d (ret: %d)\n",
+			    db_type, ret);
 		return ret;
 	}
 
@@ -569,6 +324,8 @@ int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 
 	mutex_lock(&pool->lock);
 	ret = pool->p_get_chunk(pool, chunk);
+	if (ret == 0)
+		pool->available_elems -= 1 << chunk->order;
 	mutex_unlock(&pool->lock);
 
 	return ret;
@@ -579,6 +336,7 @@ void mlx5hws_pool_chunk_free(struct mlx5hws_pool *pool,
 {
 	mutex_lock(&pool->lock);
 	pool->p_put_chunk(pool, chunk);
+	pool->available_elems += 1 << chunk->order;
 	mutex_unlock(&pool->lock);
 }
 
@@ -599,17 +357,13 @@ mlx5hws_pool_create(struct mlx5hws_context *ctx, struct mlx5hws_pool_attr *pool_
 	pool->tbl_type = pool_attr->table_type;
 	pool->opt_type = pool_attr->opt_type;
 
-	/* Support general db */
-	if (pool->flags == (MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE |
-			    MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK))
-		res_db_type = MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE;
-	else if (pool->flags == (MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-				 MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS))
-		res_db_type = MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE;
-	else
+	if (pool->flags & MLX5HWS_POOL_FLAG_BUDDY)
 		res_db_type = MLX5HWS_POOL_DB_TYPE_BUDDY;
+	else
+		res_db_type = MLX5HWS_POOL_DB_TYPE_BITMAP;
 
 	pool->alloc_log_sz = pool_attr->alloc_log_sz;
+	pool->available_elems = 1 << pool_attr->alloc_log_sz;
 
 	if (hws_pool_db_init(pool, res_db_type))
 		goto free_pool;
@@ -623,18 +377,17 @@ free_pool:
 	return NULL;
 }
 
-int mlx5hws_pool_destroy(struct mlx5hws_pool *pool)
+void mlx5hws_pool_destroy(struct mlx5hws_pool *pool)
 {
-	int i;
-
 	mutex_destroy(&pool->lock);
 
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++)
-		if (pool->resource[i])
-			hws_pool_resource_free(pool, i);
+	if (pool->available_elems != 1 << pool->alloc_log_sz)
+		mlx5hws_err(pool->ctx, "Attempting to destroy non-empty pool\n");
+
+	if (pool->resource)
+		hws_pool_resource_free(pool);
 
 	hws_pool_db_unint(pool);
 
 	kfree(pool);
-	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
index 621298b352b2..33e33d5f1fb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
@@ -6,16 +6,12 @@
 
 #define MLX5HWS_POOL_STC_LOG_SZ 15
 
-#define MLX5HWS_POOL_RESOURCE_ARR_SZ 100
-
 enum mlx5hws_pool_type {
 	MLX5HWS_POOL_TYPE_STE,
 	MLX5HWS_POOL_TYPE_STC,
 };
 
 struct mlx5hws_pool_chunk {
-	u32 resource_idx;
-	/* Internal offset, relative to base index */
 	int offset;
 	int order;
 };
@@ -27,35 +23,17 @@ struct mlx5hws_pool_resource {
 };
 
 enum mlx5hws_pool_flags {
-	/* Only a one resource in that pool */
-	MLX5HWS_POOL_FLAGS_ONE_RESOURCE = 1 << 0,
-	MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE = 1 << 1,
-	/* No sharing resources between chunks */
-	MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK = 1 << 2,
-	/* All objects are in the same size */
-	MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS = 1 << 3,
-	/* Managed by buddy allocator */
-	MLX5HWS_POOL_FLAGS_BUDDY_MANAGED = 1 << 4,
-	/* Allocate pool_type memory on pool creation */
-	MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE = 1 << 5,
-
-	/* These values should be used by the caller */
-	MLX5HWS_POOL_FLAGS_FOR_STC_POOL =
-		MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS,
-	MLX5HWS_POOL_FLAGS_FOR_MATCHER_STE_POOL =
-		MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK,
-	MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL =
-		MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_BUDDY_MANAGED |
-		MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE,
+	/* Managed by a buddy allocator. If this is not set only allocations of
+	 * order 0 are supported.
+	 */
+	MLX5HWS_POOL_FLAG_BUDDY = BIT(0),
 };
 
 enum mlx5hws_pool_optimize {
 	MLX5HWS_POOL_OPTIMIZE_NONE = 0x0,
 	MLX5HWS_POOL_OPTIMIZE_ORIG = 0x1,
 	MLX5HWS_POOL_OPTIMIZE_MIRROR = 0x2,
+	MLX5HWS_POOL_OPTIMIZE_MAX = 0x3,
 };
 
 struct mlx5hws_pool_attr {
@@ -68,34 +46,17 @@ struct mlx5hws_pool_attr {
 };
 
 enum mlx5hws_db_type {
-	/* Uses for allocating chunk of big memory, each element has its own resource in the FW*/
-	MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE,
-	/* One resource only, all the elements are with same one size */
-	MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE,
-	/* Many resources, the memory allocated with buddy mechanism */
+	/* Uses a bitmap, supports only allocations of order 0. */
+	MLX5HWS_POOL_DB_TYPE_BITMAP,
+	/* Entries are managed using a buddy mechanism. */
 	MLX5HWS_POOL_DB_TYPE_BUDDY,
 };
 
-struct mlx5hws_buddy_manager {
-	struct mlx5hws_buddy_mem *buddies[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-};
-
-struct mlx5hws_pool_elements {
-	u32 num_of_elements;
-	unsigned long *bitmap;
-	u32 log_size;
-	bool is_full;
-};
-
-struct mlx5hws_element_manager {
-	struct mlx5hws_pool_elements *elements[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-};
-
 struct mlx5hws_pool_db {
 	enum mlx5hws_db_type type;
 	union {
-		struct mlx5hws_element_manager *element_manager;
-		struct mlx5hws_buddy_manager *buddy_manager;
+		unsigned long *bitmap;
+		struct mlx5hws_buddy_mem *buddy;
 	};
 };
 
@@ -111,11 +72,11 @@ struct mlx5hws_pool {
 	enum mlx5hws_pool_flags flags;
 	struct mutex lock; /* protect the pool */
 	size_t alloc_log_sz;
+	size_t available_elems;
 	enum mlx5hws_table_type tbl_type;
 	enum mlx5hws_pool_optimize opt_type;
-	struct mlx5hws_pool_resource *resource[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-	struct mlx5hws_pool_resource *mirror_resource[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-	/* DB */
+	struct mlx5hws_pool_resource *resource;
+	struct mlx5hws_pool_resource *mirror_resource;
 	struct mlx5hws_pool_db db;
 	/* Functions */
 	mlx5hws_pool_unint_db p_db_uninit;
@@ -127,7 +88,7 @@ struct mlx5hws_pool *
 mlx5hws_pool_create(struct mlx5hws_context *ctx,
 		    struct mlx5hws_pool_attr *pool_attr);
 
-int mlx5hws_pool_destroy(struct mlx5hws_pool *pool);
+void mlx5hws_pool_destroy(struct mlx5hws_pool *pool);
 
 int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 			     struct mlx5hws_pool_chunk *chunk);
@@ -135,17 +96,37 @@ int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 void mlx5hws_pool_chunk_free(struct mlx5hws_pool *pool,
 			     struct mlx5hws_pool_chunk *chunk);
 
-static inline u32
-mlx5hws_pool_chunk_get_base_id(struct mlx5hws_pool *pool,
-			       struct mlx5hws_pool_chunk *chunk)
+static inline u32 mlx5hws_pool_get_base_id(struct mlx5hws_pool *pool)
 {
-	return pool->resource[chunk->resource_idx]->base_id;
+	return pool->resource->base_id;
 }
 
-static inline u32
-mlx5hws_pool_chunk_get_base_mirror_id(struct mlx5hws_pool *pool,
-				      struct mlx5hws_pool_chunk *chunk)
+static inline u32 mlx5hws_pool_get_base_mirror_id(struct mlx5hws_pool *pool)
 {
-	return pool->mirror_resource[chunk->resource_idx]->base_id;
+	return pool->mirror_resource->base_id;
+}
+
+static inline bool
+mlx5hws_pool_empty(struct mlx5hws_pool *pool)
+{
+	bool ret;
+
+	mutex_lock(&pool->lock);
+	ret = pool->available_elems == 0;
+	mutex_unlock(&pool->lock);
+
+	return ret;
+}
+
+static inline bool
+mlx5hws_pool_full(struct mlx5hws_pool *pool)
+{
+	bool ret;
+
+	mutex_lock(&pool->lock);
+	ret = pool->available_elems == (1 << pool->alloc_log_sz);
+	mutex_unlock(&pool->lock);
+
+	return ret;
 }
 #endif /* MLX5HWS_POOL_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
index de92cecbeb92..271490a51b96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
@@ -390,11 +390,6 @@ struct mlx5_ifc_definer_bits {
 	u8 match_mask[0x160];
 };
 
-struct mlx5_ifc_arg_bits {
-	u8 rsvd0[0x88];
-	u8 access_pd[0x18];
-};
-
 struct mlx5_ifc_header_modify_pattern_in_bits {
 	u8 modify_field_select[0x40];
 
@@ -428,11 +423,6 @@ struct mlx5_ifc_create_definer_in_bits {
 	struct mlx5_ifc_definer_bits definer;
 };
 
-struct mlx5_ifc_create_arg_in_bits {
-	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
-	struct mlx5_ifc_arg_bits arg;
-};
-
 struct mlx5_ifc_create_header_modify_pattern_in_bits {
 	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
 	struct mlx5_ifc_header_modify_pattern_in_bits pattern;
@@ -479,36 +469,4 @@ enum {
 	MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL = 1,
 };
 
-struct mlx5_ifc_alloc_packet_reformat_out_bits {
-	u8 status[0x8];
-	u8 reserved_at_8[0x18];
-
-	u8 syndrome[0x20];
-
-	u8 packet_reformat_id[0x20];
-
-	u8 reserved_at_60[0x20];
-};
-
-struct mlx5_ifc_dealloc_packet_reformat_in_bits {
-	u8 opcode[0x10];
-	u8 reserved_at_10[0x10];
-
-	u8 reserved_at_20[0x10];
-	u8 op_mod[0x10];
-
-	u8 packet_reformat_id[0x20];
-
-	u8 reserved_at_60[0x20];
-};
-
-struct mlx5_ifc_dealloc_packet_reformat_out_bits {
-	u8 status[0x8];
-	u8 reserved_at_8[0x18];
-
-	u8 syndrome[0x20];
-
-	u8 reserved_at_40[0x40];
-};
-
 #endif /* MLX5_PRM_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
index e20c67a04203..5342a4cc7194 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
@@ -129,27 +129,18 @@ static void hws_rule_gen_comp(struct mlx5hws_send_engine *queue,
 
 static void
 hws_rule_save_resize_info(struct mlx5hws_rule *rule,
-			  struct mlx5hws_send_ste_attr *ste_attr,
-			  bool is_update)
+			  struct mlx5hws_send_ste_attr *ste_attr)
 {
 	if (!mlx5hws_matcher_is_resizable(rule->matcher))
 		return;
 
-	if (likely(!is_update)) {
+	/* resize_info might already exist (if we're in update flow) */
+	if (likely(!rule->resize_info)) {
 		rule->resize_info = kzalloc(sizeof(*rule->resize_info), GFP_KERNEL);
 		if (unlikely(!rule->resize_info)) {
 			pr_warn("HWS: resize info isn't allocated for rule\n");
 			return;
 		}
-
-		rule->resize_info->max_stes =
-			rule->matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes;
-		rule->resize_info->action_ste_pool[0] = rule->matcher->action_ste[0].max_stes ?
-							rule->matcher->action_ste[0].pool :
-							NULL;
-		rule->resize_info->action_ste_pool[1] = rule->matcher->action_ste[1].max_stes ?
-							rule->matcher->action_ste[1].pool :
-							NULL;
 	}
 
 	memcpy(rule->resize_info->ctrl_seg, ste_attr->wqe_ctrl,
@@ -204,84 +195,30 @@ hws_rule_load_delete_info(struct mlx5hws_rule *rule,
 	}
 }
 
-static int hws_rule_alloc_action_ste_idx(struct mlx5hws_rule *rule,
-					 u8 action_ste_selector)
-{
-	struct mlx5hws_matcher *matcher = rule->matcher;
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_pool_chunk ste = {0};
-	int ret;
-
-	action_ste = &matcher->action_ste[action_ste_selector];
-	ste.order = ilog2(roundup_pow_of_two(action_ste->max_stes));
-	ret = mlx5hws_pool_chunk_alloc(action_ste->pool, &ste);
-	if (unlikely(ret)) {
-		mlx5hws_err(matcher->tbl->ctx,
-			    "Failed to allocate STE for rule actions");
-		return ret;
-	}
-	rule->action_ste_idx = ste.offset;
-
-	return 0;
-}
-
-static void hws_rule_free_action_ste_idx(struct mlx5hws_rule *rule,
-					 u8 action_ste_selector)
+static int mlx5hws_rule_alloc_action_ste(struct mlx5hws_rule *rule,
+					 u16 queue_id, bool skip_rx,
+					 bool skip_tx)
 {
 	struct mlx5hws_matcher *matcher = rule->matcher;
-	struct mlx5hws_pool_chunk ste = {0};
-	struct mlx5hws_pool *pool;
-	u8 max_stes;
-
-	if (mlx5hws_matcher_is_resizable(matcher)) {
-		/* Free the original action pool if rule was resized */
-		max_stes = rule->resize_info->max_stes;
-		pool = rule->resize_info->action_ste_pool[action_ste_selector];
-	} else {
-		max_stes = matcher->action_ste[action_ste_selector].max_stes;
-		pool = matcher->action_ste[action_ste_selector].pool;
-	}
-
-	/* This release is safe only when the rule match part was deleted */
-	ste.order = ilog2(roundup_pow_of_two(max_stes));
-	ste.offset = rule->action_ste_idx;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 
-	mlx5hws_pool_chunk_free(pool, &ste);
+	rule->action_ste.ste.order =
+		ilog2(roundup_pow_of_two(matcher->num_of_action_stes));
+	return mlx5hws_action_ste_chunk_alloc(&ctx->action_ste_pool[queue_id],
+					      skip_rx, skip_tx,
+					      &rule->action_ste);
 }
 
-static int hws_rule_alloc_action_ste(struct mlx5hws_rule *rule,
-				     struct mlx5hws_rule_attr *attr)
+void mlx5hws_rule_free_action_ste(struct mlx5hws_action_ste_chunk *action_ste)
 {
-	int action_ste_idx;
-	int ret;
-
-	ret = hws_rule_alloc_action_ste_idx(rule, 0);
-	if (unlikely(ret))
-		return ret;
-
-	action_ste_idx = rule->action_ste_idx;
-
-	ret = hws_rule_alloc_action_ste_idx(rule, 1);
-	if (unlikely(ret)) {
-		hws_rule_free_action_ste_idx(rule, 0);
-		return ret;
-	}
-
-	/* Both pools have to return the same index */
-	if (unlikely(rule->action_ste_idx != action_ste_idx)) {
-		pr_warn("HWS: allocation of action STE failed - pool indexes mismatch\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
+	if (!action_ste->action_tbl)
+		return;
 
-void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule)
-{
-	if (rule->action_ste_idx > -1) {
-		hws_rule_free_action_ste_idx(rule, 1);
-		hws_rule_free_action_ste_idx(rule, 0);
-	}
+	/* This release is safe only when the rule match STE was deleted
+	 * (when the rule is being deleted) or replaced with the new STE that
+	 * isn't pointing to old action STEs (when the rule is being updated).
+	 */
+	mlx5hws_action_ste_chunk_free(action_ste);
 }
 
 static void hws_rule_create_init(struct mlx5hws_rule *rule,
@@ -298,14 +235,17 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule,
 		/* In update we use these rtc's */
 		rule->rtc_0 = 0;
 		rule->rtc_1 = 0;
-		rule->action_ste_selector = 0;
+
+		rule->status = MLX5HWS_RULE_STATUS_CREATING;
 	} else {
-		rule->action_ste_selector = !rule->action_ste_selector;
+		rule->status = MLX5HWS_RULE_STATUS_UPDATING;
+		/* Save the old action STE info so we can free it after writing
+		 * new action STEs and a corresponding match STE.
+		 */
+		rule->old_action_ste = rule->action_ste;
 	}
 
 	rule->pending_wqes = 0;
-	rule->action_ste_idx = -1;
-	rule->status = MLX5HWS_RULE_STATUS_CREATING;
 
 	/* Init default send STE attributes */
 	ste_attr->gta_opcode = MLX5HWS_WQE_GTA_OP_ACTIVATE;
@@ -315,8 +255,7 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule,
 
 	/* Init default action apply */
 	apply->tbl_type = tbl->type;
-	apply->common_res = &ctx->common_res[tbl->type];
-	apply->jump_to_action_stc = matcher->action_ste[0].stc.offset;
+	apply->common_res = &ctx->common_res;
 	apply->require_dep = 0;
 }
 
@@ -332,8 +271,6 @@ static void hws_rule_move_init(struct mlx5hws_rule *rule,
 	rule->rtc_1 = 0;
 
 	rule->pending_wqes = 0;
-	rule->action_ste_idx = -1;
-	rule->action_ste_selector = 0;
 	rule->status = MLX5HWS_RULE_STATUS_CREATING;
 	rule->resize_info->state = MLX5HWS_RULE_RESIZE_STATE_WRITING;
 }
@@ -394,21 +331,24 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule,
 
 	if (action_stes) {
 		/* Allocate action STEs for rules that need more than match STE */
-		if (!is_update) {
-			ret = hws_rule_alloc_action_ste(rule, attr);
-			if (ret) {
-				mlx5hws_err(ctx, "Failed to allocate action memory %d", ret);
-				mlx5hws_send_abort_new_dep_wqe(queue);
-				return ret;
-			}
+		ret = mlx5hws_rule_alloc_action_ste(rule, attr->queue_id,
+						    !!ste_attr.rtc_0,
+						    !!ste_attr.rtc_1);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed to allocate action memory %d", ret);
+			mlx5hws_send_abort_new_dep_wqe(queue);
+			return ret;
 		}
+		apply.jump_to_action_stc =
+			rule->action_ste.action_tbl->stc.offset;
 		/* Skip RX/TX based on the dep_wqe init */
 		ste_attr.rtc_0 = dep_wqe->rtc_0 ?
-				 matcher->action_ste[rule->action_ste_selector].rtc_0_id : 0;
+				 rule->action_ste.action_tbl->rtc_0_id : 0;
 		ste_attr.rtc_1 = dep_wqe->rtc_1 ?
-				 matcher->action_ste[rule->action_ste_selector].rtc_1_id : 0;
+				 rule->action_ste.action_tbl->rtc_1_id : 0;
 		/* Action STEs are written to a specific index last to first */
-		ste_attr.direct_index = rule->action_ste_idx + action_stes;
+		ste_attr.direct_index =
+			rule->action_ste.ste.offset + action_stes;
 		apply.next_direct_idx = ste_attr.direct_index;
 	} else {
 		apply.next_direct_idx = 0;
@@ -459,7 +399,7 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule,
 	if (!is_update)
 		hws_rule_save_delete_info(rule, &ste_attr);
 
-	hws_rule_save_resize_info(rule, &ste_attr, is_update);
+	hws_rule_save_resize_info(rule, &ste_attr);
 	mlx5hws_send_engine_inc_rule(queue);
 
 	if (!attr->burst)
@@ -480,7 +420,10 @@ static void hws_rule_destroy_failed_hws(struct mlx5hws_rule *rule,
 			  attr->user_data, MLX5HWS_RULE_STATUS_DELETED);
 
 	/* Rule failed now we can safely release action STEs */
-	mlx5hws_rule_free_action_ste(rule);
+	mlx5hws_rule_free_action_ste(&rule->action_ste);
+
+	/* Perhaps the rule failed updating - release old action STEs as well */
+	mlx5hws_rule_free_action_ste(&rule->old_action_ste);
 
 	/* Clear complex tag */
 	hws_rule_clear_delete_info(rule);
@@ -517,7 +460,8 @@ static int hws_rule_destroy_hws(struct mlx5hws_rule *rule,
 	}
 
 	/* Rule is not completed yet */
-	if (rule->status == MLX5HWS_RULE_STATUS_CREATING)
+	if (rule->status == MLX5HWS_RULE_STATUS_CREATING ||
+	    rule->status == MLX5HWS_RULE_STATUS_UPDATING)
 		return -EBUSY;
 
 	/* Rule failed and doesn't require cleanup */
@@ -534,7 +478,7 @@ static int hws_rule_destroy_hws(struct mlx5hws_rule *rule,
 		hws_rule_gen_comp(queue, rule, false,
 				  attr->user_data, MLX5HWS_RULE_STATUS_DELETED);
 
-		mlx5hws_rule_free_action_ste(rule);
+		mlx5hws_rule_free_action_ste(&rule->action_ste);
 		mlx5hws_rule_clear_resize_info(rule);
 		return 0;
 	}
@@ -711,6 +655,124 @@ int mlx5hws_rule_move_hws_add(struct mlx5hws_rule *rule,
 	return 0;
 }
 
+static u8 hws_rule_ethertype_to_matcher_ipv(u32 ethertype)
+{
+	switch (ethertype) {
+	case ETH_P_IP:
+		return MLX5HWS_MATCHER_IPV_4;
+	case ETH_P_IPV6:
+		return MLX5HWS_MATCHER_IPV_6;
+	default:
+		return MLX5HWS_MATCHER_IPV_UNSET;
+	}
+}
+
+static u8 hws_rule_ip_version_to_matcher_ipv(u32 ip_version)
+{
+	switch (ip_version) {
+	case 4:
+		return MLX5HWS_MATCHER_IPV_4;
+	case 6:
+		return MLX5HWS_MATCHER_IPV_6;
+	default:
+		return MLX5HWS_MATCHER_IPV_UNSET;
+	}
+}
+
+static int hws_rule_check_outer_ip_version(struct mlx5hws_matcher *matcher,
+					   u32 *match_param)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 outer_ipv_ether = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 outer_ipv_ip = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 outer_ipv, ver;
+
+	if (matcher->matches_outer_ethertype) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       outer_headers.ethertype);
+		outer_ipv_ether = hws_rule_ethertype_to_matcher_ipv(ver);
+	}
+	if (matcher->matches_outer_ip_version) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       outer_headers.ip_version);
+		outer_ipv_ip = hws_rule_ip_version_to_matcher_ipv(ver);
+	}
+
+	if (outer_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv_ip != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv_ether != outer_ipv_ip) {
+		mlx5hws_err(ctx, "Rule matches on inconsistent outer ethertype and ip version\n");
+		return -EINVAL;
+	}
+
+	outer_ipv = outer_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET ?
+		    outer_ipv_ether : outer_ipv_ip;
+	if (outer_ipv != MLX5HWS_MATCHER_IPV_UNSET &&
+	    matcher->outer_ip_version != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv != matcher->outer_ip_version) {
+		mlx5hws_err(ctx, "Matcher and rule disagree on outer IP version\n");
+		return -EINVAL;
+	}
+	matcher->outer_ip_version = outer_ipv;
+
+	return 0;
+}
+
+static int hws_rule_check_inner_ip_version(struct mlx5hws_matcher *matcher,
+					   u32 *match_param)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 inner_ipv_ether = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 inner_ipv_ip = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 inner_ipv, ver;
+
+	if (matcher->matches_inner_ethertype) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       inner_headers.ethertype);
+		inner_ipv_ether = hws_rule_ethertype_to_matcher_ipv(ver);
+	}
+	if (matcher->matches_inner_ip_version) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       inner_headers.ip_version);
+		inner_ipv_ip = hws_rule_ip_version_to_matcher_ipv(ver);
+	}
+
+	if (inner_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv_ip != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv_ether != inner_ipv_ip) {
+		mlx5hws_err(ctx, "Rule matches on inconsistent inner ethertype and ip version\n");
+		return -EINVAL;
+	}
+
+	inner_ipv = inner_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET ?
+		    inner_ipv_ether : inner_ipv_ip;
+	if (inner_ipv != MLX5HWS_MATCHER_IPV_UNSET &&
+	    matcher->inner_ip_version != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv != matcher->inner_ip_version) {
+		mlx5hws_err(ctx, "Matcher and rule disagree on inner IP version\n");
+		return -EINVAL;
+	}
+	matcher->inner_ip_version = inner_ipv;
+
+	return 0;
+}
+
+static int hws_rule_check_ip_version(struct mlx5hws_matcher *matcher,
+				     u32 *match_param)
+{
+	int ret;
+
+	ret = hws_rule_check_outer_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
+	ret = hws_rule_check_inner_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
+	return 0;
+}
+
 int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
 			u8 mt_idx,
 			u32 *match_param,
@@ -721,6 +783,10 @@ int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
 {
 	int ret;
 
+	ret = hws_rule_check_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
 	rule_handle->matcher = matcher;
 
 	ret = hws_rule_enqueue_precheck_create(rule_handle, attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
index 495cdd17e9f3..1c47a9c11572 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
@@ -15,6 +15,8 @@ enum mlx5hws_rule_status {
 	MLX5HWS_RULE_STATUS_UNKNOWN,
 	MLX5HWS_RULE_STATUS_CREATING,
 	MLX5HWS_RULE_STATUS_CREATED,
+	MLX5HWS_RULE_STATUS_UPDATING,
+	MLX5HWS_RULE_STATUS_UPDATED,
 	MLX5HWS_RULE_STATUS_DELETING,
 	MLX5HWS_RULE_STATUS_DELETED,
 	MLX5HWS_RULE_STATUS_FAILING,
@@ -42,12 +44,10 @@ struct mlx5hws_rule_match_tag {
 };
 
 struct mlx5hws_rule_resize_info {
-	struct mlx5hws_pool *action_ste_pool[2];
 	u32 rtc_0;
 	u32 rtc_1;
 	u32 rule_idx;
 	u8 state;
-	u8 max_stes;
 	u8 ctrl_seg[MLX5HWS_WQE_SZ_GTA_CTRL]; /* Ctrl segment of STE: 48 bytes */
 	u8 data_seg[MLX5HWS_WQE_SZ_GTA_DATA]; /* Data segment of STE: 64 bytes */
 };
@@ -58,18 +58,18 @@ struct mlx5hws_rule {
 		struct mlx5hws_rule_match_tag tag;
 		struct mlx5hws_rule_resize_info *resize_info;
 	};
+	struct mlx5hws_action_ste_chunk action_ste;
+	struct mlx5hws_action_ste_chunk old_action_ste;
 	u32 rtc_0; /* The RTC into which the STE was inserted */
 	u32 rtc_1; /* The RTC into which the STE was inserted */
-	int action_ste_idx; /* STE array index */
 	u8 status; /* enum mlx5hws_rule_status */
-	u8 action_ste_selector; /* For rule update - which action STE is in use */
 	u8 pending_wqes;
 	bool skip_delete; /* For complex rules - another rule with same tag
 			   * still exists, so don't actually delete this rule.
 			   */
 };
 
-void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule);
+void mlx5hws_rule_free_action_ste(struct mlx5hws_action_ste_chunk *action_ste);
 
 int mlx5hws_rule_move_hws_remove(struct mlx5hws_rule *rule,
 				 void *queue, void *user_data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
index 424797b6d802..c4b22be19a9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
@@ -344,18 +344,133 @@ hws_send_engine_update_rule_resize(struct mlx5hws_send_engine *queue,
 	}
 }
 
+static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
+					   struct mlx5hws_send_ring_priv *priv,
+					   struct mlx5_cqe64 *cqe)
+{
+	u8 wqe_opcode = cqe ? be32_to_cpu(cqe->sop_drop_qpn) >> 24 : 0;
+	struct mlx5hws_context *ctx = priv->rule->matcher->tbl->ctx;
+	u32 opcode = cqe ? get_cqe_opcode(cqe) : 0;
+	struct mlx5hws_rule *rule = priv->rule;
+
+	/* If something bad happens and lots of rules are failing, we don't
+	 * want to pollute dmesg. Print only the first bad cqe per engine,
+	 * the one that started the avalanche.
+	 */
+	if (queue->error_cqe_printed)
+		return;
+
+	queue->error_cqe_printed = true;
+
+	if (mlx5hws_rule_move_in_progress(rule))
+		mlx5hws_err(ctx,
+			    "--- rule 0x%08llx: error completion moving rule: phase %s, wqes left %d\n",
+			    HWS_PTR_TO_ID(rule),
+			    rule->resize_info->state ==
+			    MLX5HWS_RULE_RESIZE_STATE_WRITING ? "WRITING" :
+			    rule->resize_info->state ==
+			    MLX5HWS_RULE_RESIZE_STATE_DELETING ? "DELETING" :
+			    "UNKNOWN",
+			    rule->pending_wqes);
+	else
+		mlx5hws_err(ctx,
+			    "--- rule 0x%08llx: error completion %s (%d), wqes left %d\n",
+			    HWS_PTR_TO_ID(rule),
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_CREATING ? "CREATING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_DELETING ? "DELETING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_FAILING ? "FAILING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_UPDATING ? "UPDATING" : "NA",
+			    rule->status,
+			    rule->pending_wqes);
+
+	mlx5hws_err(ctx, "    rule 0x%08llx: matcher 0x%llx %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    HWS_PTR_TO_ID(rule->matcher),
+		    (rule->matcher->flags & MLX5HWS_MATCHER_FLAGS_ISOLATED) ?
+		    "(isolated)" : "");
+
+	if (!cqe) {
+		mlx5hws_err(ctx, "    rule 0x%08llx: no CQE\n",
+			    HWS_PTR_TO_ID(rule));
+		return;
+	}
+
+	mlx5hws_err(ctx, "    rule 0x%08llx: cqe->opcode      = %d %s\n",
+		    HWS_PTR_TO_ID(rule), opcode,
+		    opcode == MLX5_CQE_REQ ? "(MLX5_CQE_REQ)" :
+		    opcode == MLX5_CQE_REQ_ERR ? "(MLX5_CQE_REQ_ERR)" : " ");
+
+	if (opcode == MLX5_CQE_REQ_ERR) {
+		struct mlx5_err_cqe *err_cqe = (struct mlx5_err_cqe *)cqe;
+
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- hw_error_syndrome = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->rsvd1[16]);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- hw_syndrome_type = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->rsvd1[17] >> 4);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- vendor_err_synd = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->vendor_err_synd);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- syndrome = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->syndrome);
+	}
+
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx: cqe->byte_cnt      = 0x%08x\n",
+		    HWS_PTR_TO_ID(rule), be32_to_cpu(cqe->byte_cnt));
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |-- UPDATE STATUS = %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    (be32_to_cpu(cqe->byte_cnt) & 0x80000000) ?
+		    "FAILURE" : "SUCCESS");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |------- SYNDROME = %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 1) ?
+		    "SET_FLOW_FAIL" :
+		    ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 2) ?
+		    "DISABLE_FLOW_FAIL" : "UNKNOWN");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx: cqe->sop_drop_qpn  = 0x%08x\n",
+		    HWS_PTR_TO_ID(rule), be32_to_cpu(cqe->sop_drop_qpn));
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |-send wqe opcode = 0x%02x %s\n",
+		    HWS_PTR_TO_ID(rule), wqe_opcode,
+		    wqe_opcode == MLX5HWS_WQE_OPCODE_TBL_ACCESS ?
+		    "(MLX5HWS_WQE_OPCODE_TBL_ACCESS)" : "(UNKNOWN)");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |------------ qpn = 0x%06x\n",
+		    HWS_PTR_TO_ID(rule),
+		    be32_to_cpu(cqe->sop_drop_qpn) & 0xffffff);
+}
+
 static void hws_send_engine_update_rule(struct mlx5hws_send_engine *queue,
 					struct mlx5hws_send_ring_priv *priv,
 					u16 wqe_cnt,
-					enum mlx5hws_flow_op_status *status)
+					enum mlx5hws_flow_op_status *status,
+					struct mlx5_cqe64 *cqe)
 {
 	priv->rule->pending_wqes--;
 
-	if (*status == MLX5HWS_FLOW_OP_ERROR) {
+	if (unlikely(*status == MLX5HWS_FLOW_OP_ERROR)) {
 		if (priv->retry_id) {
+			/* If there is a retry_id, then it's not an error yet,
+			 * retry to insert this rule in the collision RTC.
+			 */
 			hws_send_engine_retry_post_send(queue, priv, wqe_cnt);
 			return;
 		}
+		hws_send_engine_dump_error_cqe(queue, priv, cqe);
 		/* Some part of the rule failed */
 		priv->rule->status = MLX5HWS_RULE_STATUS_FAILING;
 		*priv->used_id = 0;
@@ -377,17 +492,25 @@ static void hws_send_engine_update_rule(struct mlx5hws_send_engine *queue,
 
 			*status = MLX5HWS_FLOW_OP_ERROR;
 		} else {
-			/* Increase the status, this only works on good flow as the enum
-			 * is arrange it away creating -> created -> deleting -> deleted
+			/* Increase the status, this only works on good flow as
+			 * the enum is arranged this way:
+			 *  - creating -> created
+			 *  - updating -> updated
+			 *  - deleting -> deleted
 			 */
 			priv->rule->status++;
 			*status = MLX5HWS_FLOW_OP_SUCCESS;
-			/* Rule was deleted now we can safely release action STEs
-			 * and clear resize info
-			 */
 			if (priv->rule->status == MLX5HWS_RULE_STATUS_DELETED) {
-				mlx5hws_rule_free_action_ste(priv->rule);
+				/* Rule was deleted, now we can safely release
+				 * action STEs and clear resize info
+				 */
+				mlx5hws_rule_free_action_ste(&priv->rule->action_ste);
 				mlx5hws_rule_clear_resize_info(priv->rule);
+			} else if (priv->rule->status == MLX5HWS_RULE_STATUS_UPDATED) {
+				/* Rule was updated, free the old action STEs */
+				mlx5hws_rule_free_action_ste(&priv->rule->old_action_ste);
+				/* Update completed - move the rule back to "created" */
+				priv->rule->status = MLX5HWS_RULE_STATUS_CREATED;
 			}
 		}
 	}
@@ -412,7 +535,8 @@ static void hws_send_engine_update(struct mlx5hws_send_engine *queue,
 
 	if (priv->user_data) {
 		if (priv->rule) {
-			hws_send_engine_update_rule(queue, priv, wqe_cnt, &status);
+			hws_send_engine_update_rule(queue, priv, wqe_cnt,
+						    &status, cqe);
 			/* Completion is provided on the last rule WQE */
 			if (priv->rule->pending_wqes)
 				return;
@@ -633,6 +757,7 @@ static int hws_send_ring_create_sq(struct mlx5_core_dev *mdev, u32 pdn,
 
 	MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
 	MLX5_SET(sqc, sqc, flush_in_error_en, 1);
+	MLX5_SET(sqc, sqc, non_wire, 1);
 
 	ts_format = mlx5_is_real_time_sq(mdev) ? MLX5_TIMESTAMP_FORMAT_REAL_TIME :
 						 MLX5_TIMESTAMP_FORMAT_FREE_RUNNING;
@@ -896,15 +1021,18 @@ close_cq:
 	return err;
 }
 
-void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue)
+static void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue)
 {
+	if (!queue->num_entries)
+		return; /* this queue wasn't initialized */
+
 	hws_send_ring_close(queue);
 	kfree(queue->completed.entries);
 }
 
-int mlx5hws_send_queue_open(struct mlx5hws_context *ctx,
-			    struct mlx5hws_send_engine *queue,
-			    u16 queue_size)
+static int mlx5hws_send_queue_open(struct mlx5hws_context *ctx,
+				   struct mlx5hws_send_engine *queue,
+				   u16 queue_size)
 {
 	int err;
 
@@ -990,6 +1118,7 @@ static int hws_bwc_send_queues_init(struct mlx5hws_context *ctx)
 	for (i = 0; i < bwc_queues; i++) {
 		mutex_init(&ctx->bwc_send_queue_locks[i]);
 		lockdep_register_key(ctx->bwc_lock_class_keys + i);
+		lockdep_set_class(ctx->bwc_send_queue_locks + i, ctx->bwc_lock_class_keys + i);
 	}
 
 	return 0;
@@ -1004,7 +1133,7 @@ int mlx5hws_send_queues_open(struct mlx5hws_context *ctx,
 			     u16 queue_size)
 {
 	int err = 0;
-	u32 i;
+	int i = 0;
 
 	/* Open one extra queue for control path */
 	ctx->queues = queues + 1;
@@ -1020,7 +1149,13 @@ int mlx5hws_send_queues_open(struct mlx5hws_context *ctx,
 		goto free_bwc_locks;
 	}
 
-	for (i = 0; i < ctx->queues; i++) {
+	/* If native API isn't supported, skip the unused native queues:
+	 * initialize BWC queues and control queue only.
+	 */
+	if (!mlx5hws_context_native_supported(ctx))
+		i = mlx5hws_bwc_get_queue_id(ctx, 0);
+
+	for (; i < ctx->queues; i++) {
 		err = mlx5hws_send_queue_open(ctx, &ctx->send_queue[i], queue_size);
 		if (err)
 			goto close_send_queues;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
index b50825d6dc53..3fb8e99309b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
@@ -140,6 +140,7 @@ struct mlx5hws_send_engine {
 	u16 used_entries;
 	u16 num_entries;
 	bool err;
+	bool error_cqe_printed;
 	struct mutex lock; /* Protects the send engine */
 };
 
@@ -189,12 +190,6 @@ void mlx5hws_send_abort_new_dep_wqe(struct mlx5hws_send_engine *queue);
 
 void mlx5hws_send_all_dep_wqe(struct mlx5hws_send_engine *queue);
 
-void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue);
-
-int mlx5hws_send_queue_open(struct mlx5hws_context *ctx,
-			    struct mlx5hws_send_engine *queue,
-			    u16 queue_size);
-
 void mlx5hws_send_queues_close(struct mlx5hws_context *ctx);
 
 int mlx5hws_send_queues_open(struct mlx5hws_context *ctx,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
index 9576e02d00c3..568f691733f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
@@ -37,6 +37,7 @@ static void hws_table_set_cap_attr(struct mlx5hws_table *tbl,
 }
 
 static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
+__must_hold(&tbl->ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
 	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
@@ -48,8 +49,8 @@ static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
 	if (tbl->type != MLX5HWS_TABLE_TYPE_FDB)
 		return 0;
 
-	if (ctx->common_res[tbl_type].default_miss) {
-		ctx->common_res[tbl_type].default_miss->refcount++;
+	if (ctx->common_res.default_miss) {
+		ctx->common_res.default_miss->refcount++;
 		return 0;
 	}
 
@@ -70,29 +71,28 @@ static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
 		return -EINVAL;
 	}
 
-	/* ctx->ctrl_lock must be held here */
-	ctx->common_res[tbl_type].default_miss = default_miss;
-	ctx->common_res[tbl_type].default_miss->refcount++;
+	ctx->common_res.default_miss = default_miss;
+	ctx->common_res.default_miss->refcount++;
 
 	return 0;
 }
 
 /* Called under ctx->ctrl_lock */
 static void hws_table_down_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
+__must_hold(&tbl->ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_forward_tbl *default_miss;
 	struct mlx5hws_context *ctx = tbl->ctx;
-	u8 tbl_type = tbl->type;
 
 	if (tbl->type != MLX5HWS_TABLE_TYPE_FDB)
 		return;
 
-	default_miss = ctx->common_res[tbl_type].default_miss;
+	default_miss = ctx->common_res.default_miss;
 	if (--default_miss->refcount)
 		return;
 
 	mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, default_miss);
-	ctx->common_res[tbl_type].default_miss = NULL;
+	ctx->common_res.default_miss = NULL;
 }
 
 static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32 ft_id)
@@ -342,10 +342,10 @@ int mlx5hws_table_ft_set_next_rtc(struct mlx5hws_context *ctx,
 	return mlx5hws_cmd_flow_table_modify(ctx->mdev, &ft_attr, ft_id);
 }
 
-static int hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
-				    u32 ft_id,
-				    u32 fw_ft_type,
-				    u32 next_ft_id)
+int mlx5hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
+				 u32 ft_id,
+				 u32 fw_ft_type,
+				 u32 next_ft_id)
 {
 	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
 
@@ -389,10 +389,10 @@ int mlx5hws_table_connect_to_miss_table(struct mlx5hws_table *src_tbl,
 	if (dst_tbl) {
 		if (list_empty(&dst_tbl->matchers_list)) {
 			/* Connect src_tbl last_ft to dst_tbl start anchor */
-			ret = hws_table_ft_set_next_ft(src_tbl->ctx,
-						       last_ft_id,
-						       src_tbl->fw_ft_type,
-						       dst_tbl->ft_id);
+			ret = mlx5hws_table_ft_set_next_ft(src_tbl->ctx,
+							   last_ft_id,
+							   src_tbl->fw_ft_type,
+							   dst_tbl->ft_id);
 			if (ret)
 				return ret;
 
@@ -478,15 +478,9 @@ int mlx5hws_table_set_default_miss(struct mlx5hws_table *tbl,
 	if (old_miss_tbl)
 		list_del_init(&tbl->default_miss.next);
 
-	old_miss_tbl = tbl->default_miss.miss_tbl;
-	if (old_miss_tbl)
-		list_del_init(&old_miss_tbl->default_miss.head);
-
 	if (miss_tbl)
 		list_add(&tbl->default_miss.next, &miss_tbl->default_miss.head);
 
-	mutex_unlock(&ctx->ctrl_lock);
-	return 0;
 out:
 	mutex_unlock(&ctx->ctrl_lock);
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
index dd50420eec9e..0400cce0c317 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
@@ -65,4 +65,9 @@ int mlx5hws_table_ft_set_next_rtc(struct mlx5hws_context *ctx,
 				  u32 rtc_0_id,
 				  u32 rtc_1_id);
 
+int mlx5hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
+				 u32 ft_id,
+				 u32 fw_ft_type,
+				 u32 next_ft_id);
+
 #endif /* MLX5HWS_TABLE_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
index 3d74109f8230..65740bb68b09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
@@ -8,7 +8,7 @@
 #define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type)	\
 	((dmn)->info.caps.dmn_type##_sw_owner ||	\
 	 ((dmn)->info.caps.dmn_type##_sw_owner_v2 &&	\
-	  (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_7))
+	  (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_8))
 
 bool mlx5dr_domain_is_support_ptrn_arg(struct mlx5dr_domain *dmn)
 {
@@ -297,7 +297,9 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport)
 	if (ret) {
 		mlx5dr_dbg(dmn, "Couldn't insert new vport into xarray (%d)\n", ret);
 		kvfree(vport_caps);
-		return ERR_PTR(ret);
+		if (ret == -EBUSY)
+			return ERR_PTR(-EBUSY);
+		return NULL;
 	}
 
 	return vport_caps;
@@ -514,30 +516,6 @@ def_xa_destroy:
 	return NULL;
 }
 
-/* Assure synchronization of the device steering tables with updates made by SW
- * insertion.
- */
-int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags)
-{
-	int ret = 0;
-
-	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) {
-		mlx5dr_domain_lock(dmn);
-		ret = mlx5dr_send_ring_force_drain(dmn);
-		mlx5dr_domain_unlock(dmn);
-		if (ret) {
-			mlx5dr_err(dmn, "Force drain failed flags: %d, ret: %d\n",
-				   flags, ret);
-			return ret;
-		}
-	}
-
-	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW)
-		ret = mlx5dr_cmd_sync_steering(dmn->mdev);
-
-	return ret;
-}
-
 int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
 {
 	if (WARN_ON_ONCE(refcount_read(&dmn->refcount) > 1))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
index 6fa06ba2d346..4fd4e8483382 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
@@ -1067,7 +1067,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	int inlen, err, eqn;
 	void *cqc, *in;
 	__be64 *pas;
-	int vector;
 	u32 i;
 
 	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
@@ -1096,8 +1095,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	if (!in)
 		goto err_cqwq;
 
-	vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev);
-	err = mlx5_comp_eqn_get(mdev, vector, &eqn);
+	err = mlx5_comp_eqn_get(mdev, 0, &eqn);
 	if (err) {
 		kvfree(in);
 		goto err_cqwq;
@@ -1333,36 +1331,3 @@ void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
 	kfree(send_ring->sync_buff);
 	kfree(send_ring);
 }
-
-int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
-{
-	struct mlx5dr_send_ring *send_ring = dmn->send_ring;
-	struct postsend_info send_info = {};
-	u8 data[DR_STE_SIZE];
-	int num_of_sends_req;
-	int ret;
-	int i;
-
-	/* Sending this amount of requests makes sure we will get drain */
-	num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2;
-
-	/* Send fake requests forcing the last to be signaled */
-	send_info.write.addr = (uintptr_t)data;
-	send_info.write.length = DR_STE_SIZE;
-	send_info.write.lkey = 0;
-	/* Using the sync_mr in order to write/read */
-	send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr;
-	send_info.rkey = send_ring->sync_mr->mkey;
-
-	for (i = 0; i < num_of_sends_req; i++) {
-		ret = dr_postsend_icm_data(dmn, &send_info);
-		if (ret)
-			return ret;
-	}
-
-	spin_lock(&send_ring->lock);
-	ret = dr_handle_pending_wc(dmn, send_ring);
-	spin_unlock(&send_ring->lock);
-
-	return ret;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c
index e94fbb015efa..c8b8ff80c7c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c
@@ -555,7 +555,7 @@ void mlx5dr_ste_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx,
 			       struct mlx5dr_ste_actions_attr *attr,
 			       u32 *added_stes)
 {
-	ste_ctx->set_actions_tx(dmn, action_type_set, ste_ctx->actions_caps,
+	ste_ctx->set_actions_tx(ste_ctx, dmn, action_type_set, ste_ctx->actions_caps,
 				hw_ste_arr, attr, added_stes);
 }
 
@@ -566,7 +566,7 @@ void mlx5dr_ste_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx,
 			       struct mlx5dr_ste_actions_attr *attr,
 			       u32 *added_stes)
 {
-	ste_ctx->set_actions_rx(dmn, action_type_set, ste_ctx->actions_caps,
+	ste_ctx->set_actions_rx(ste_ctx, dmn, action_type_set, ste_ctx->actions_caps,
 				hw_ste_arr, attr, added_stes);
 }
 
@@ -1458,6 +1458,8 @@ struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx(u8 version)
 		return mlx5dr_ste_get_ctx_v1();
 	else if (version == MLX5_STEERING_FORMAT_CONNECTX_7)
 		return mlx5dr_ste_get_ctx_v2();
+	else if (version == MLX5_STEERING_FORMAT_CONNECTX_8)
+		return mlx5dr_ste_get_ctx_v3();
 
 	return NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
index 54a6619c3ecb..3d5afc832fa5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
@@ -160,13 +160,15 @@ struct mlx5dr_ste_ctx {
 
 	/* Actions */
 	u32 actions_caps;
-	void (*set_actions_rx)(struct mlx5dr_domain *dmn,
+	void (*set_actions_rx)(struct mlx5dr_ste_ctx *ste_ctx,
+			       struct mlx5dr_domain *dmn,
 			       u8 *action_type_set,
 			       u32 actions_caps,
 			       u8 *hw_ste_arr,
 			       struct mlx5dr_ste_actions_attr *attr,
 			       u32 *added_stes);
-	void (*set_actions_tx)(struct mlx5dr_domain *dmn,
+	void (*set_actions_tx)(struct mlx5dr_ste_ctx *ste_ctx,
+			       struct mlx5dr_domain *dmn,
 			       u8 *action_type_set,
 			       u32 actions_caps,
 			       u8 *hw_ste_arr,
@@ -197,7 +199,21 @@ struct mlx5dr_ste_ctx {
 					u16 *used_hw_action_num);
 	int (*alloc_modify_hdr_chunk)(struct mlx5dr_action *action);
 	void (*dealloc_modify_hdr_chunk)(struct mlx5dr_action *action);
-
+	/* Actions bit set */
+	void (*set_encap)(u8 *hw_ste_p, u8 *d_action,
+			  u32 reformat_id, int size);
+	void (*set_push_vlan)(u8 *ste, u8 *d_action,
+			      u32 vlan_hdr);
+	void (*set_pop_vlan)(u8 *hw_ste_p, u8 *s_action,
+			     u8 vlans_num);
+	void (*set_rx_decap)(u8 *hw_ste_p, u8 *s_action);
+	void (*set_encap_l3)(u8 *hw_ste_p, u8 *frst_s_action,
+			     u8 *scnd_d_action, u32 reformat_id,
+			     int size);
+	void (*set_insert_hdr)(u8 *hw_ste_p, u8 *d_action, u32 reformat_id,
+			       u8 anchor, u8 offset, int size);
+	void (*set_remove_hdr)(u8 *hw_ste_p, u8 *s_action, u8 anchor,
+			       u8 offset, int size);
 	/* Send */
 	void (*prepare_for_postsend)(u8 *hw_ste_p, u32 ste_size);
 };
@@ -205,5 +221,6 @@ struct mlx5dr_ste_ctx {
 struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v0(void);
 struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v1(void);
 struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v2(void);
+struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v3(void);
 
 #endif  /* _DR_STE_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c
index e9f6c7ed7a7b..42536bee55e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c
@@ -406,7 +406,8 @@ static void dr_ste_v0_arr_init_next(u8 **last_ste,
 }
 
 static void
-dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn,
+dr_ste_v0_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx,
+			 struct mlx5dr_domain *dmn,
 			 u8 *action_type_set,
 			 u32 actions_caps,
 			 u8 *last_ste,
@@ -476,7 +477,8 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn,
 }
 
 static void
-dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn,
+dr_ste_v0_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx,
+			 struct mlx5dr_domain *dmn,
 			 u8 *action_type_set,
 			 u32 actions_caps,
 			 u8 *last_ste,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
index 1d49704b9542..6447efbae00d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
@@ -5,136 +5,6 @@
 #include "mlx5_ifc_dr_ste_v1.h"
 #include "dr_ste_v1.h"
 
-#define DR_STE_CALC_DFNR_TYPE(lookup_type, inner) \
-	((inner) ? DR_STE_V1_LU_TYPE_##lookup_type##_I : \
-		   DR_STE_V1_LU_TYPE_##lookup_type##_O)
-
-enum dr_ste_v1_entry_format {
-	DR_STE_V1_TYPE_BWC_BYTE	= 0x0,
-	DR_STE_V1_TYPE_BWC_DW	= 0x1,
-	DR_STE_V1_TYPE_MATCH	= 0x2,
-	DR_STE_V1_TYPE_MATCH_RANGES = 0x7,
-};
-
-/* Lookup type is built from 2B: [ Definer mode 1B ][ Definer index 1B ] */
-enum {
-	DR_STE_V1_LU_TYPE_NOP				= 0x0000,
-	DR_STE_V1_LU_TYPE_ETHL2_TNL			= 0x0002,
-	DR_STE_V1_LU_TYPE_IBL3_EXT			= 0x0102,
-	DR_STE_V1_LU_TYPE_ETHL2_O			= 0x0003,
-	DR_STE_V1_LU_TYPE_IBL4				= 0x0103,
-	DR_STE_V1_LU_TYPE_ETHL2_I			= 0x0004,
-	DR_STE_V1_LU_TYPE_SRC_QP_GVMI			= 0x0104,
-	DR_STE_V1_LU_TYPE_ETHL2_SRC_O			= 0x0005,
-	DR_STE_V1_LU_TYPE_ETHL2_HEADERS_O		= 0x0105,
-	DR_STE_V1_LU_TYPE_ETHL2_SRC_I			= 0x0006,
-	DR_STE_V1_LU_TYPE_ETHL2_HEADERS_I		= 0x0106,
-	DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_O		= 0x0007,
-	DR_STE_V1_LU_TYPE_IPV6_DES_O			= 0x0107,
-	DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_I		= 0x0008,
-	DR_STE_V1_LU_TYPE_IPV6_DES_I			= 0x0108,
-	DR_STE_V1_LU_TYPE_ETHL4_O			= 0x0009,
-	DR_STE_V1_LU_TYPE_IPV6_SRC_O			= 0x0109,
-	DR_STE_V1_LU_TYPE_ETHL4_I			= 0x000a,
-	DR_STE_V1_LU_TYPE_IPV6_SRC_I			= 0x010a,
-	DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_O		= 0x000b,
-	DR_STE_V1_LU_TYPE_MPLS_O			= 0x010b,
-	DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_I		= 0x000c,
-	DR_STE_V1_LU_TYPE_MPLS_I			= 0x010c,
-	DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_O		= 0x000d,
-	DR_STE_V1_LU_TYPE_GRE				= 0x010d,
-	DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER	= 0x000e,
-	DR_STE_V1_LU_TYPE_GENERAL_PURPOSE		= 0x010e,
-	DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_I		= 0x000f,
-	DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0		= 0x010f,
-	DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1		= 0x0110,
-	DR_STE_V1_LU_TYPE_FLEX_PARSER_OK		= 0x0011,
-	DR_STE_V1_LU_TYPE_FLEX_PARSER_0			= 0x0111,
-	DR_STE_V1_LU_TYPE_FLEX_PARSER_1			= 0x0112,
-	DR_STE_V1_LU_TYPE_ETHL4_MISC_O			= 0x0113,
-	DR_STE_V1_LU_TYPE_ETHL4_MISC_I			= 0x0114,
-	DR_STE_V1_LU_TYPE_INVALID			= 0x00ff,
-	DR_STE_V1_LU_TYPE_DONT_CARE			= MLX5DR_STE_LU_TYPE_DONT_CARE,
-};
-
-enum dr_ste_v1_header_anchors {
-	DR_STE_HEADER_ANCHOR_START_OUTER		= 0x00,
-	DR_STE_HEADER_ANCHOR_1ST_VLAN			= 0x02,
-	DR_STE_HEADER_ANCHOR_IPV6_IPV4			= 0x07,
-	DR_STE_HEADER_ANCHOR_INNER_MAC			= 0x13,
-	DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4		= 0x19,
-};
-
-enum dr_ste_v1_action_size {
-	DR_STE_ACTION_SINGLE_SZ = 4,
-	DR_STE_ACTION_DOUBLE_SZ = 8,
-	DR_STE_ACTION_TRIPLE_SZ = 12,
-};
-
-enum dr_ste_v1_action_insert_ptr_attr {
-	DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE = 0,  /* Regular push header (e.g. push vlan) */
-	DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP = 1, /* Encapsulation / Tunneling */
-	DR_STE_V1_ACTION_INSERT_PTR_ATTR_ESP = 2,   /* IPsec */
-};
-
-enum dr_ste_v1_action_id {
-	DR_STE_V1_ACTION_ID_NOP				= 0x00,
-	DR_STE_V1_ACTION_ID_COPY			= 0x05,
-	DR_STE_V1_ACTION_ID_SET				= 0x06,
-	DR_STE_V1_ACTION_ID_ADD				= 0x07,
-	DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE		= 0x08,
-	DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER	= 0x09,
-	DR_STE_V1_ACTION_ID_INSERT_INLINE		= 0x0a,
-	DR_STE_V1_ACTION_ID_INSERT_POINTER		= 0x0b,
-	DR_STE_V1_ACTION_ID_FLOW_TAG			= 0x0c,
-	DR_STE_V1_ACTION_ID_QUEUE_ID_SEL		= 0x0d,
-	DR_STE_V1_ACTION_ID_ACCELERATED_LIST		= 0x0e,
-	DR_STE_V1_ACTION_ID_MODIFY_LIST			= 0x0f,
-	DR_STE_V1_ACTION_ID_ASO				= 0x12,
-	DR_STE_V1_ACTION_ID_TRAILER			= 0x13,
-	DR_STE_V1_ACTION_ID_COUNTER_ID			= 0x14,
-	DR_STE_V1_ACTION_ID_MAX				= 0x21,
-	/* use for special cases */
-	DR_STE_V1_ACTION_ID_SPECIAL_ENCAP_L3		= 0x22,
-};
-
-enum {
-	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_0		= 0x00,
-	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1		= 0x01,
-	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2		= 0x02,
-	DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0		= 0x08,
-	DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_1		= 0x09,
-	DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0		= 0x0e,
-	DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0		= 0x18,
-	DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_1		= 0x19,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_0		= 0x40,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_1		= 0x41,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_0	= 0x44,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_1	= 0x45,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_2	= 0x46,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_3	= 0x47,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_0	= 0x4c,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_1	= 0x4d,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_2	= 0x4e,
-	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
-	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
-	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
-	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
-	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
-	DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
-	DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_0		= 0x8c,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_1		= 0x8d,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_0		= 0x8e,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_1		= 0x8f,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_0		= 0x90,
-	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_1		= 0x91,
-};
-
-enum dr_ste_v1_aso_ctx_type {
-	DR_STE_V1_ASO_CTX_TYPE_POLICERS = 0x2,
-};
-
 static const struct mlx5dr_ste_action_modify_field dr_ste_v1_action_modify_field_arr[] = {
 	[MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = {
 		.hw_field = DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31,
@@ -379,13 +249,12 @@ static void dr_ste_v1_set_counter_id(u8 *hw_ste_p, u32 ctr_id)
 	MLX5_SET(ste_match_bwc_v1, hw_ste_p, counter_id, ctr_id);
 }
 
-static void dr_ste_v1_set_reparse(u8 *hw_ste_p)
+void dr_ste_v1_set_reparse(u8 *hw_ste_p)
 {
 	MLX5_SET(ste_match_bwc_v1, hw_ste_p, reparse, 1);
 }
 
-static void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action,
-				u32 reformat_id, int size)
+void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, u32 reformat_id, int size)
 {
 	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, action_id,
 		 DR_STE_V1_ACTION_ID_INSERT_POINTER);
@@ -397,10 +266,10 @@ static void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
-				     u32 reformat_id,
-				     u8 anchor, u8 offset,
-				     int size)
+void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
+			      u32 reformat_id,
+			      u8 anchor, u8 offset,
+			      int size)
 {
 	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action,
 		 action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER);
@@ -417,9 +286,9 @@ static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
-				     u8 anchor, u8 offset,
-				     int size)
+void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
+			      u8 anchor, u8 offset,
+			      int size)
 {
 	MLX5_SET(ste_single_action_remove_header_size_v1, s_action,
 		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
@@ -432,8 +301,7 @@ static void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action,
-				    u32 vlan_hdr)
+void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, u32 vlan_hdr)
 {
 	MLX5_SET(ste_double_action_insert_with_inline_v1, d_action,
 		 action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE);
@@ -446,7 +314,7 @@ static void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num)
+void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num)
 {
 	MLX5_SET(ste_single_action_remove_header_size_v1, s_action,
 		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
@@ -459,11 +327,8 @@ static void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num)
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_encap_l3(u8 *hw_ste_p,
-				   u8 *frst_s_action,
-				   u8 *scnd_d_action,
-				   u32 reformat_id,
-				   int size)
+void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, u8 *frst_s_action, u8 *scnd_d_action,
+			    u32 reformat_id, int size)
 {
 	/* Remove L2 headers */
 	MLX5_SET(ste_single_action_remove_header_v1, frst_s_action, action_id,
@@ -483,7 +348,7 @@ static void dr_ste_v1_set_encap_l3(u8 *hw_ste_p,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action)
+void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action)
 {
 	MLX5_SET(ste_single_action_remove_header_v1, s_action, action_id,
 		 DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER);
@@ -620,7 +485,8 @@ static void dr_ste_v1_arr_init_next_match_range(u8 **last_ste,
 	dr_ste_v1_set_entry_type(*last_ste, DR_STE_V1_TYPE_MATCH_RANGES);
 }
 
-void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
+void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx,
+			      struct mlx5dr_domain *dmn,
 			      u8 *action_type_set,
 			      u32 actions_caps,
 			      u8 *last_ste,
@@ -640,7 +506,7 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 					      last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count);
+		ste_ctx->set_pop_vlan(last_ste, action, attr->vlans.count);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 
@@ -677,8 +543,8 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 				action_sz = DR_STE_ACTION_TRIPLE_SZ;
 				allow_encap = true;
 			}
-			dr_ste_v1_set_push_vlan(last_ste, action,
-						attr->vlans.headers[i]);
+			ste_ctx->set_push_vlan(last_ste, action,
+					       attr->vlans.headers[i]);
 			action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 			action += DR_STE_ACTION_DOUBLE_SZ;
 		}
@@ -691,9 +557,9 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 			allow_encap = true;
 		}
-		dr_ste_v1_set_encap(last_ste, action,
-				    attr->reformat.id,
-				    attr->reformat.size);
+		ste_ctx->set_encap(last_ste, action,
+				   attr->reformat.id,
+				   attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 	} else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) {
@@ -706,10 +572,10 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 		}
 		d_action = action + DR_STE_ACTION_SINGLE_SZ;
 
-		dr_ste_v1_set_encap_l3(last_ste,
-				       action, d_action,
-				       attr->reformat.id,
-				       attr->reformat.size);
+		ste_ctx->set_encap_l3(last_ste,
+				      action, d_action,
+				      attr->reformat.id,
+				      attr->reformat.size);
 		action_sz -= DR_STE_ACTION_TRIPLE_SZ;
 		action += DR_STE_ACTION_TRIPLE_SZ;
 	} else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) {
@@ -718,11 +584,11 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_insert_hdr(last_ste, action,
-					 attr->reformat.id,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_insert_hdr(last_ste, action,
+					attr->reformat.id,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 	} else if (action_type_set[DR_ACTION_TYP_REMOVE_HDR]) {
@@ -731,10 +597,10 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_remove_hdr(last_ste, action,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_remove_hdr(last_ste, action,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 	}
@@ -776,7 +642,8 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 	dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1);
 }
 
-void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
+void dr_ste_v1_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx,
+			      struct mlx5dr_domain *dmn,
 			      u8 *action_type_set,
 			      u32 actions_caps,
 			      u8 *last_ste,
@@ -799,7 +666,7 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 		allow_modify_hdr = false;
 		allow_ctr = false;
 	} else if (action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2]) {
-		dr_ste_v1_set_rx_decap(last_ste, action);
+		ste_ctx->set_rx_decap(last_ste, action);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 		allow_modify_hdr = false;
@@ -827,7 +694,7 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
 
-		dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count);
+		ste_ctx->set_pop_vlan(last_ste, action, attr->vlans.count);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 		allow_ctr = false;
@@ -868,8 +735,8 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 						      last_ste, action);
 				action_sz = DR_STE_ACTION_TRIPLE_SZ;
 			}
-			dr_ste_v1_set_push_vlan(last_ste, action,
-						attr->vlans.headers[i]);
+			ste_ctx->set_push_vlan(last_ste, action,
+					       attr->vlans.headers[i]);
 			action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 			action += DR_STE_ACTION_DOUBLE_SZ;
 		}
@@ -895,9 +762,9 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_encap(last_ste, action,
-				    attr->reformat.id,
-				    attr->reformat.size);
+		ste_ctx->set_encap(last_ste, action,
+				   attr->reformat.id,
+				   attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 		allow_modify_hdr = false;
@@ -912,10 +779,10 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 
 		d_action = action + DR_STE_ACTION_SINGLE_SZ;
 
-		dr_ste_v1_set_encap_l3(last_ste,
-				       action, d_action,
-				       attr->reformat.id,
-				       attr->reformat.size);
+		ste_ctx->set_encap_l3(last_ste,
+				      action, d_action,
+				      attr->reformat.id,
+				      attr->reformat.size);
 		action_sz -= DR_STE_ACTION_TRIPLE_SZ;
 		allow_modify_hdr = false;
 	} else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) {
@@ -925,11 +792,11 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_insert_hdr(last_ste, action,
-					 attr->reformat.id,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_insert_hdr(last_ste, action,
+					attr->reformat.id,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 		allow_modify_hdr = false;
@@ -941,10 +808,10 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 			allow_modify_hdr = true;
 			allow_ctr = true;
 		}
-		dr_ste_v1_set_remove_hdr(last_ste, action,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_remove_hdr(last_ste, action,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 	}
@@ -1027,9 +894,6 @@ void dr_ste_v1_set_action_copy(u8 *d_action,
 	MLX5_SET(ste_double_action_copy_v1, d_action, source_right_shifter, src_shifter);
 }
 
-#define DR_STE_DECAP_L3_ACTION_NUM	8
-#define DR_STE_L2_HDR_MAX_SZ		20
-
 int dr_ste_v1_set_action_decap_l3_list(void *data,
 				       u32 data_sz,
 				       u8 *hw_action,
@@ -2330,7 +2194,14 @@ static struct mlx5dr_ste_ctx ste_ctx_v1 = {
 	.set_action_decap_l3_list	= &dr_ste_v1_set_action_decap_l3_list,
 	.alloc_modify_hdr_chunk		= &dr_ste_v1_alloc_modify_hdr_ptrn_arg,
 	.dealloc_modify_hdr_chunk	= &dr_ste_v1_free_modify_hdr_ptrn_arg,
-
+	/* Actions bit set */
+	.set_encap			= &dr_ste_v1_set_encap,
+	.set_push_vlan			= &dr_ste_v1_set_push_vlan,
+	.set_pop_vlan			= &dr_ste_v1_set_pop_vlan,
+	.set_rx_decap			= &dr_ste_v1_set_rx_decap,
+	.set_encap_l3			= &dr_ste_v1_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v1_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v1_set_remove_hdr,
 	/* Send */
 	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
index e2fc69867088..591c20c95a6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
@@ -7,6 +7,138 @@
 #include "dr_types.h"
 #include "dr_ste.h"
 
+#define DR_STE_DECAP_L3_ACTION_NUM	8
+#define DR_STE_L2_HDR_MAX_SZ		20
+#define DR_STE_CALC_DFNR_TYPE(lookup_type, inner) \
+	((inner) ? DR_STE_V1_LU_TYPE_##lookup_type##_I : \
+		   DR_STE_V1_LU_TYPE_##lookup_type##_O)
+
+enum dr_ste_v1_entry_format {
+	DR_STE_V1_TYPE_BWC_BYTE	= 0x0,
+	DR_STE_V1_TYPE_BWC_DW	= 0x1,
+	DR_STE_V1_TYPE_MATCH	= 0x2,
+	DR_STE_V1_TYPE_MATCH_RANGES = 0x7,
+};
+
+/* Lookup type is built from 2B: [ Definer mode 1B ][ Definer index 1B ] */
+enum {
+	DR_STE_V1_LU_TYPE_NOP				= 0x0000,
+	DR_STE_V1_LU_TYPE_ETHL2_TNL			= 0x0002,
+	DR_STE_V1_LU_TYPE_IBL3_EXT			= 0x0102,
+	DR_STE_V1_LU_TYPE_ETHL2_O			= 0x0003,
+	DR_STE_V1_LU_TYPE_IBL4				= 0x0103,
+	DR_STE_V1_LU_TYPE_ETHL2_I			= 0x0004,
+	DR_STE_V1_LU_TYPE_SRC_QP_GVMI			= 0x0104,
+	DR_STE_V1_LU_TYPE_ETHL2_SRC_O			= 0x0005,
+	DR_STE_V1_LU_TYPE_ETHL2_HEADERS_O		= 0x0105,
+	DR_STE_V1_LU_TYPE_ETHL2_SRC_I			= 0x0006,
+	DR_STE_V1_LU_TYPE_ETHL2_HEADERS_I		= 0x0106,
+	DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_O		= 0x0007,
+	DR_STE_V1_LU_TYPE_IPV6_DES_O			= 0x0107,
+	DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_I		= 0x0008,
+	DR_STE_V1_LU_TYPE_IPV6_DES_I			= 0x0108,
+	DR_STE_V1_LU_TYPE_ETHL4_O			= 0x0009,
+	DR_STE_V1_LU_TYPE_IPV6_SRC_O			= 0x0109,
+	DR_STE_V1_LU_TYPE_ETHL4_I			= 0x000a,
+	DR_STE_V1_LU_TYPE_IPV6_SRC_I			= 0x010a,
+	DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_O		= 0x000b,
+	DR_STE_V1_LU_TYPE_MPLS_O			= 0x010b,
+	DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_I		= 0x000c,
+	DR_STE_V1_LU_TYPE_MPLS_I			= 0x010c,
+	DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_O		= 0x000d,
+	DR_STE_V1_LU_TYPE_GRE				= 0x010d,
+	DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER	= 0x000e,
+	DR_STE_V1_LU_TYPE_GENERAL_PURPOSE		= 0x010e,
+	DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_I		= 0x000f,
+	DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0		= 0x010f,
+	DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1		= 0x0110,
+	DR_STE_V1_LU_TYPE_FLEX_PARSER_OK		= 0x0011,
+	DR_STE_V1_LU_TYPE_FLEX_PARSER_0			= 0x0111,
+	DR_STE_V1_LU_TYPE_FLEX_PARSER_1			= 0x0112,
+	DR_STE_V1_LU_TYPE_ETHL4_MISC_O			= 0x0113,
+	DR_STE_V1_LU_TYPE_ETHL4_MISC_I			= 0x0114,
+	DR_STE_V1_LU_TYPE_INVALID			= 0x00ff,
+	DR_STE_V1_LU_TYPE_DONT_CARE			= MLX5DR_STE_LU_TYPE_DONT_CARE,
+};
+
+enum dr_ste_v1_header_anchors {
+	DR_STE_HEADER_ANCHOR_START_OUTER		= 0x00,
+	DR_STE_HEADER_ANCHOR_1ST_VLAN			= 0x02,
+	DR_STE_HEADER_ANCHOR_IPV6_IPV4			= 0x07,
+	DR_STE_HEADER_ANCHOR_INNER_MAC			= 0x13,
+	DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4		= 0x19,
+};
+
+enum dr_ste_v1_action_size {
+	DR_STE_ACTION_SINGLE_SZ = 4,
+	DR_STE_ACTION_DOUBLE_SZ = 8,
+	DR_STE_ACTION_TRIPLE_SZ = 12,
+};
+
+enum dr_ste_v1_action_insert_ptr_attr {
+	DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE = 0,  /* Regular push header (e.g. push vlan) */
+	DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP = 1, /* Encapsulation / Tunneling */
+	DR_STE_V1_ACTION_INSERT_PTR_ATTR_ESP = 2,   /* IPsec */
+};
+
+enum dr_ste_v1_action_id {
+	DR_STE_V1_ACTION_ID_NOP				= 0x00,
+	DR_STE_V1_ACTION_ID_COPY			= 0x05,
+	DR_STE_V1_ACTION_ID_SET				= 0x06,
+	DR_STE_V1_ACTION_ID_ADD				= 0x07,
+	DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE		= 0x08,
+	DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER	= 0x09,
+	DR_STE_V1_ACTION_ID_INSERT_INLINE		= 0x0a,
+	DR_STE_V1_ACTION_ID_INSERT_POINTER		= 0x0b,
+	DR_STE_V1_ACTION_ID_FLOW_TAG			= 0x0c,
+	DR_STE_V1_ACTION_ID_QUEUE_ID_SEL		= 0x0d,
+	DR_STE_V1_ACTION_ID_ACCELERATED_LIST		= 0x0e,
+	DR_STE_V1_ACTION_ID_MODIFY_LIST			= 0x0f,
+	DR_STE_V1_ACTION_ID_ASO				= 0x12,
+	DR_STE_V1_ACTION_ID_TRAILER			= 0x13,
+	DR_STE_V1_ACTION_ID_COUNTER_ID			= 0x14,
+	DR_STE_V1_ACTION_ID_MAX				= 0x21,
+	/* use for special cases */
+	DR_STE_V1_ACTION_ID_SPECIAL_ENCAP_L3		= 0x22,
+};
+
+enum {
+	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_0		= 0x00,
+	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1		= 0x01,
+	DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2		= 0x02,
+	DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0		= 0x08,
+	DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_1		= 0x09,
+	DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0		= 0x0e,
+	DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0		= 0x18,
+	DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_1		= 0x19,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_0		= 0x40,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_1		= 0x41,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_0	= 0x44,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_1	= 0x45,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_2	= 0x46,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_3	= 0x47,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_0	= 0x4c,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_1	= 0x4d,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_2	= 0x4e,
+	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
+	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
+	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
+	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
+	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
+	DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
+	DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_0		= 0x8c,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_1		= 0x8d,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_0		= 0x8e,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_1		= 0x8f,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_0		= 0x90,
+	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_1		= 0x91,
+};
+
+enum dr_ste_v1_aso_ctx_type {
+	DR_STE_V1_ASO_CTX_TYPE_POLICERS = 0x2,
+};
+
 bool dr_ste_v1_is_miss_addr_set(u8 *hw_ste_p);
 void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr);
 u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p);
@@ -17,11 +149,22 @@ u16 dr_ste_v1_get_next_lu_type(u8 *hw_ste_p);
 void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size);
 void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, bool is_rx, u16 gvmi);
 void dr_ste_v1_prepare_for_postsend(u8 *hw_ste_p, u32 ste_size);
-void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, u8 *action_type_set,
-			      u32 actions_caps, u8 *last_ste,
+void dr_ste_v1_set_reparse(u8 *hw_ste_p);
+void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, u32 reformat_id, int size);
+void dr_ste_v1_set_push_vlan(u8 *hw_ste_p, u8 *d_action, u32 vlan_hdr);
+void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num);
+void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, u8 *frst_s_action, u8 *scnd_d_action,
+			    u32 reformat_id, int size);
+void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action);
+void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action, u32 reformat_id,
+			      u8 anchor, u8 offset, int size);
+void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action, u8 anchor,
+			      u8 offset, int size);
+void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_domain *dmn,
+			      u8 *action_type_set, u32 actions_caps, u8 *last_ste,
 			      struct mlx5dr_ste_actions_attr *attr, u32 *added_stes);
-void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, u8 *action_type_set,
-			      u32 actions_caps, u8 *last_ste,
+void dr_ste_v1_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_domain *dmn,
+			      u8 *action_type_set, u32 actions_caps, u8 *last_ste,
 			      struct mlx5dr_ste_actions_attr *attr, u32 *added_stes);
 void dr_ste_v1_set_action_set(u8 *d_action, u8 hw_field, u8 shifter,
 			      u8 length, u32 data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
index 808b013cf48c..d0ebaf820d42 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
@@ -2,167 +2,7 @@
 /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
 
 #include "dr_ste_v1.h"
-
-enum {
-	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0		= 0x00,
-	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1		= 0x01,
-	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2		= 0x02,
-	DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0		= 0x08,
-	DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1		= 0x09,
-	DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0		= 0x0e,
-	DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0		= 0x18,
-	DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1		= 0x19,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0		= 0x40,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1		= 0x41,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0	= 0x44,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1	= 0x45,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2	= 0x46,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3	= 0x47,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0	= 0x4c,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1	= 0x4d,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2	= 0x4e,
-	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
-	DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
-	DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
-	DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
-	DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
-	DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
-	DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0		= 0x90,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1		= 0x91,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0		= 0x92,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1		= 0x93,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0		= 0x94,
-	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1		= 0x95,
-};
-
-static const struct mlx5dr_ste_action_modify_field dr_ste_v2_action_modify_field_arr[] = {
-	[MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1, .start = 16, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 0, .end = 15,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 16, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 18, .end = 23,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1, .start = 16, .end = 24,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15,
-		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_SIPV4] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_DIPV4] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1, .start = 0, .end = 31,
-		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_A] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_B] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31,
-	},
-	[MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = {
-		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15,
-	},
-};
+#include "dr_ste_v2.h"
 
 static struct mlx5dr_ste_ctx ste_ctx_v2 = {
 	/* Builders */
@@ -223,7 +63,14 @@ static struct mlx5dr_ste_ctx ste_ctx_v2 = {
 	.set_action_decap_l3_list	= &dr_ste_v1_set_action_decap_l3_list,
 	.alloc_modify_hdr_chunk		= &dr_ste_v1_alloc_modify_hdr_ptrn_arg,
 	.dealloc_modify_hdr_chunk	= &dr_ste_v1_free_modify_hdr_ptrn_arg,
-
+	/* Actions bit set */
+	.set_encap			= &dr_ste_v1_set_encap,
+	.set_push_vlan			= &dr_ste_v1_set_push_vlan,
+	.set_pop_vlan			= &dr_ste_v1_set_pop_vlan,
+	.set_rx_decap			= &dr_ste_v1_set_rx_decap,
+	.set_encap_l3			= &dr_ste_v1_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v1_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v1_set_remove_hdr,
 	/* Send */
 	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h
new file mode 100644
index 000000000000..d853fde49cfc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef	_DR_STE_V2_
+#define	_DR_STE_V2_
+
+enum {
+	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0		= 0x00,
+	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1		= 0x01,
+	DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2		= 0x02,
+	DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0		= 0x08,
+	DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1		= 0x09,
+	DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0		= 0x0e,
+	DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0		= 0x18,
+	DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1		= 0x19,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0		= 0x40,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1		= 0x41,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0	= 0x44,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1	= 0x45,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2	= 0x46,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3	= 0x47,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0	= 0x4c,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1	= 0x4d,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2	= 0x4e,
+	DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
+	DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
+	DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
+	DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
+	DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
+	DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
+	DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0		= 0x90,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1		= 0x91,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0		= 0x92,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1		= 0x93,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0		= 0x94,
+	DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1		= 0x95,
+};
+
+static const struct mlx5dr_ste_action_modify_field dr_ste_v2_action_modify_field_arr[] = {
+	[MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1, .start = 16, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 0, .end = 15,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 16, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 18, .end = 23,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1, .start = 16, .end = 24,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15,
+		.l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_SIPV4] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_DIPV4] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1, .start = 0, .end = 31,
+		.l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_A] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_B] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = {
+		.hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15,
+	},
+};
+
+#endif  /* _DR_STE_V2_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c
new file mode 100644
index 000000000000..e468a9ae44e8
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "dr_ste_v1.h"
+#include "dr_ste_v2.h"
+
+static void dr_ste_v3_set_encap(u8 *hw_ste_p, u8 *d_action,
+				u32 reformat_id, int size)
+{
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, action_id,
+		 DR_STE_V1_ACTION_ID_INSERT_POINTER);
+	/* The hardware expects here size in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, size, size / 2);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, pointer, reformat_id);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action, attributes,
+		 DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP);
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_push_vlan(u8 *ste, u8 *d_action,
+				    u32 vlan_hdr)
+{
+	MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, action_id,
+		 DR_STE_V1_ACTION_ID_INSERT_INLINE);
+	/* The hardware expects here offset to vlan header in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, start_offset,
+		 HDR_LEN_L2_MACS >> 1);
+	MLX5_SET(ste_double_action_insert_with_inline_v3, d_action, inline_data, vlan_hdr);
+	dr_ste_v1_set_reparse(ste);
+}
+
+static void dr_ste_v3_set_pop_vlan(u8 *hw_ste_p, u8 *s_action,
+				   u8 vlans_num)
+{
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 start_anchor, DR_STE_HEADER_ANCHOR_1ST_VLAN);
+	/* The hardware expects here size in words (2 byte) */
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 remove_size, (HDR_LEN_L2_VLAN >> 1) * vlans_num);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_encap_l3(u8 *hw_ste_p,
+				   u8 *frst_s_action,
+				   u8 *scnd_d_action,
+				   u32 reformat_id,
+				   int size)
+{
+	/* Remove L2 headers */
+	MLX5_SET(ste_single_action_remove_header_v3, frst_s_action, action_id,
+		 DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER);
+	MLX5_SET(ste_single_action_remove_header_v3, frst_s_action, end_anchor,
+		 DR_STE_HEADER_ANCHOR_IPV6_IPV4);
+
+	/* Encapsulate with given reformat ID */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, action_id,
+		 DR_STE_V1_ACTION_ID_INSERT_POINTER);
+	/* The hardware expects here size in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, size, size / 2);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, pointer, reformat_id);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, scnd_d_action, attributes,
+		 DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_rx_decap(u8 *hw_ste_p, u8 *s_action)
+{
+	MLX5_SET(ste_single_action_remove_header_v3, s_action, action_id,
+		 DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER);
+	MLX5_SET(ste_single_action_remove_header_v3, s_action, decap, 1);
+	MLX5_SET(ste_single_action_remove_header_v3, s_action, vni_to_cqe, 1);
+	MLX5_SET(ste_single_action_remove_header_v3, s_action, end_anchor,
+		 DR_STE_HEADER_ANCHOR_INNER_MAC);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
+				     u32 reformat_id, u8 anchor,
+				     u8 offset, int size)
+{
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 start_anchor, anchor);
+
+	/* The hardware expects here size and offset in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 size, size / 2);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 start_offset, offset / 2);
+
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 pointer, reformat_id);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 attributes, DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
+				     u8 anchor, u8 offset, int size)
+{
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 start_anchor, anchor);
+
+	/* The hardware expects here size and offset in words (2 byte) */
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 remove_size, size / 2);
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 start_offset, offset / 2);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static int
+dr_ste_v3_set_action_decap_l3_list(void *data, u32 data_sz,
+				   u8 *hw_action, u32 hw_action_sz,
+				   uint16_t *used_hw_action_num)
+{
+	u8 padded_data[DR_STE_L2_HDR_MAX_SZ] = {};
+	void *data_ptr = padded_data;
+	u16 used_actions = 0;
+	u32 inline_data_sz;
+	u32 i;
+
+	if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM)
+		return -EINVAL;
+
+	inline_data_sz =
+		MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v3, inline_data);
+
+	/* Add an alignment padding  */
+	memcpy(padded_data + data_sz % inline_data_sz, data, data_sz);
+
+	/* Remove L2L3 outer headers */
+	MLX5_SET(ste_single_action_remove_header_v3, hw_action, action_id,
+		 DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER);
+	MLX5_SET(ste_single_action_remove_header_v3, hw_action, decap, 1);
+	MLX5_SET(ste_single_action_remove_header_v3, hw_action, vni_to_cqe, 1);
+	MLX5_SET(ste_single_action_remove_header_v3, hw_action, end_anchor,
+		 DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4);
+	hw_action += DR_STE_ACTION_DOUBLE_SZ;
+	used_actions++; /* Remove and NOP are a single double action */
+
+	/* Point to the last dword of the header */
+	data_ptr += (data_sz / inline_data_sz) * inline_data_sz;
+
+	/* Add the new header using inline action 4Byte at a time, the header
+	 * is added in reversed order to the beginning of the packet to avoid
+	 * incorrect parsing by the HW. Since header is 14B or 18B an extra
+	 * two bytes are padded and later removed.
+	 */
+	for (i = 0; i < data_sz / inline_data_sz + 1; i++) {
+		void *addr_inline;
+
+		MLX5_SET(ste_double_action_insert_with_inline_v3, hw_action, action_id,
+			 DR_STE_V1_ACTION_ID_INSERT_INLINE);
+		/* The hardware expects here offset to words (2 bytes) */
+		MLX5_SET(ste_double_action_insert_with_inline_v3, hw_action, start_offset, 0);
+
+		/* Copy bytes one by one to avoid endianness problem */
+		addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v3,
+					   hw_action, inline_data);
+		memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz);
+		hw_action += DR_STE_ACTION_DOUBLE_SZ;
+		used_actions++;
+	}
+
+	/* Remove first 2 extra bytes */
+	MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, action_id,
+		 DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
+	MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, start_offset, 0);
+	/* The hardware expects here size in words (2 bytes) */
+	MLX5_SET(ste_single_action_remove_header_size_v3, hw_action, remove_size, 1);
+	used_actions++;
+
+	*used_hw_action_num = used_actions;
+
+	return 0;
+}
+
+static struct mlx5dr_ste_ctx ste_ctx_v3 = {
+	/* Builders */
+	.build_eth_l2_src_dst_init	= &dr_ste_v1_build_eth_l2_src_dst_init,
+	.build_eth_l3_ipv6_src_init	= &dr_ste_v1_build_eth_l3_ipv6_src_init,
+	.build_eth_l3_ipv6_dst_init	= &dr_ste_v1_build_eth_l3_ipv6_dst_init,
+	.build_eth_l3_ipv4_5_tuple_init	= &dr_ste_v1_build_eth_l3_ipv4_5_tuple_init,
+	.build_eth_l2_src_init		= &dr_ste_v1_build_eth_l2_src_init,
+	.build_eth_l2_dst_init		= &dr_ste_v1_build_eth_l2_dst_init,
+	.build_eth_l2_tnl_init		= &dr_ste_v1_build_eth_l2_tnl_init,
+	.build_eth_l3_ipv4_misc_init	= &dr_ste_v1_build_eth_l3_ipv4_misc_init,
+	.build_eth_ipv6_l3_l4_init	= &dr_ste_v1_build_eth_ipv6_l3_l4_init,
+	.build_mpls_init		= &dr_ste_v1_build_mpls_init,
+	.build_tnl_gre_init		= &dr_ste_v1_build_tnl_gre_init,
+	.build_tnl_mpls_init		= &dr_ste_v1_build_tnl_mpls_init,
+	.build_tnl_mpls_over_udp_init	= &dr_ste_v1_build_tnl_mpls_over_udp_init,
+	.build_tnl_mpls_over_gre_init	= &dr_ste_v1_build_tnl_mpls_over_gre_init,
+	.build_icmp_init		= &dr_ste_v1_build_icmp_init,
+	.build_general_purpose_init	= &dr_ste_v1_build_general_purpose_init,
+	.build_eth_l4_misc_init		= &dr_ste_v1_build_eth_l4_misc_init,
+	.build_tnl_vxlan_gpe_init	= &dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init,
+	.build_tnl_geneve_init		= &dr_ste_v1_build_flex_parser_tnl_geneve_init,
+	.build_tnl_geneve_tlv_opt_init	= &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init,
+	.build_tnl_geneve_tlv_opt_exist_init =
+				  &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_init,
+	.build_register_0_init		= &dr_ste_v1_build_register_0_init,
+	.build_register_1_init		= &dr_ste_v1_build_register_1_init,
+	.build_src_gvmi_qpn_init	= &dr_ste_v1_build_src_gvmi_qpn_init,
+	.build_flex_parser_0_init	= &dr_ste_v1_build_flex_parser_0_init,
+	.build_flex_parser_1_init	= &dr_ste_v1_build_flex_parser_1_init,
+	.build_tnl_gtpu_init		= &dr_ste_v1_build_flex_parser_tnl_gtpu_init,
+	.build_tnl_header_0_1_init	= &dr_ste_v1_build_tnl_header_0_1_init,
+	.build_tnl_gtpu_flex_parser_0_init = &dr_ste_v1_build_tnl_gtpu_flex_parser_0_init,
+	.build_tnl_gtpu_flex_parser_1_init = &dr_ste_v1_build_tnl_gtpu_flex_parser_1_init,
+
+	/* Getters and Setters */
+	.ste_init			= &dr_ste_v1_init,
+	.set_next_lu_type		= &dr_ste_v1_set_next_lu_type,
+	.get_next_lu_type		= &dr_ste_v1_get_next_lu_type,
+	.is_miss_addr_set		= &dr_ste_v1_is_miss_addr_set,
+	.set_miss_addr			= &dr_ste_v1_set_miss_addr,
+	.get_miss_addr			= &dr_ste_v1_get_miss_addr,
+	.set_hit_addr			= &dr_ste_v1_set_hit_addr,
+	.set_byte_mask			= &dr_ste_v1_set_byte_mask,
+	.get_byte_mask			= &dr_ste_v1_get_byte_mask,
+
+	/* Actions */
+	.actions_caps			= DR_STE_CTX_ACTION_CAP_TX_POP |
+					  DR_STE_CTX_ACTION_CAP_RX_PUSH |
+					  DR_STE_CTX_ACTION_CAP_RX_ENCAP,
+	.set_actions_rx			= &dr_ste_v1_set_actions_rx,
+	.set_actions_tx			= &dr_ste_v1_set_actions_tx,
+	.modify_field_arr_sz		= ARRAY_SIZE(dr_ste_v2_action_modify_field_arr),
+	.modify_field_arr		= dr_ste_v2_action_modify_field_arr,
+	.set_action_set			= &dr_ste_v1_set_action_set,
+	.set_action_add			= &dr_ste_v1_set_action_add,
+	.set_action_copy		= &dr_ste_v1_set_action_copy,
+	.set_action_decap_l3_list	= &dr_ste_v3_set_action_decap_l3_list,
+	.alloc_modify_hdr_chunk		= &dr_ste_v1_alloc_modify_hdr_ptrn_arg,
+	.dealloc_modify_hdr_chunk	= &dr_ste_v1_free_modify_hdr_ptrn_arg,
+	/* Actions bit set */
+	.set_encap			= &dr_ste_v3_set_encap,
+	.set_push_vlan			= &dr_ste_v3_set_push_vlan,
+	.set_pop_vlan			= &dr_ste_v3_set_pop_vlan,
+	.set_rx_decap			= &dr_ste_v3_set_rx_decap,
+	.set_encap_l3			= &dr_ste_v3_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v3_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v3_set_remove_hdr,
+	/* Send */
+	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
+};
+
+struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v3(void)
+{
+	return &ste_ctx_v3;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
index 7618c6147f86..cc328292bf84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
@@ -1473,7 +1473,6 @@ struct mlx5dr_send_ring {
 int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn);
 void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
 			   struct mlx5dr_send_ring *send_ring);
-int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn);
 int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn,
 			     struct mlx5dr_ste *ste,
 			     u8 *data,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
index 4b349d4005e4..f367997ab61e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
@@ -521,7 +521,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 				goto free_actions;
 			}
 
-			id = dst->dest_attr.counter_id;
+			id = mlx5_fc_id(dst->dest_attr.counter);
 			tmp_action =
 				mlx5dr_action_create_flow_counter(id);
 			if (!tmp_action) {
@@ -833,15 +833,21 @@ static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns,
 	return steering_caps;
 }
 
-int mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat)
+int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id)
 {
+	struct mlx5dr_action *dr_action;
+
 	switch (pkt_reformat->reformat_type) {
 	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
 	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
 	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
 	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
 	case MLX5_REFORMAT_TYPE_INSERT_HDR:
-		return mlx5dr_action_get_pkt_reformat_id(pkt_reformat->fs_dr_action.dr_action);
+		dr_action = pkt_reformat->fs_dr_action.dr_action;
+		*reformat_id = mlx5dr_action_get_pkt_reformat_id(dr_action);
+		return 0;
 	}
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
index 99a3b2eff6b8..f869f2daefbf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
@@ -38,7 +38,9 @@ struct mlx5_fs_dr_table {
 
 bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev);
 
-int mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat);
+int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id);
 
 const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void);
 
@@ -49,9 +51,11 @@ static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void)
 	return NULL;
 }
 
-static inline u32 mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat)
+static inline int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id)
 {
-	return 0;
+	return -EOPNOTSUPP;
 }
 
 static inline bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h
index fb078fa0f0cc..898c3618ff26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h
@@ -600,4 +600,44 @@ struct mlx5_ifc_ste_double_action_aso_v1_bits {
 	};
 };
 
+struct mlx5_ifc_ste_single_action_remove_header_v3_bits {
+	u8         action_id[0x8];
+	u8         start_anchor[0x7];
+	u8         end_anchor[0x7];
+	u8         reserved_at_16[0x1];
+	u8         outer_l4_remove[0x1];
+	u8         reserved_at_18[0x4];
+	u8         decap[0x1];
+	u8         vni_to_cqe[0x1];
+	u8         qos_profile[0x2];
+};
+
+struct mlx5_ifc_ste_single_action_remove_header_size_v3_bits {
+	u8         action_id[0x8];
+	u8         start_anchor[0x7];
+	u8         start_offset[0x8];
+	u8         outer_l4_remove[0x1];
+	u8         reserved_at_18[0x2];
+	u8         remove_size[0x6];
+};
+
+struct mlx5_ifc_ste_double_action_insert_with_inline_v3_bits {
+	u8         action_id[0x8];
+	u8         start_anchor[0x7];
+	u8         start_offset[0x8];
+	u8         reserved_at_17[0x9];
+
+	u8         inline_data[0x20];
+};
+
+struct mlx5_ifc_ste_double_action_insert_with_ptr_v3_bits {
+	u8         action_id[0x8];
+	u8         start_anchor[0x7];
+	u8         start_offset[0x8];
+	u8         size[0x6];
+	u8         attributes[0x3];
+
+	u8         pointer[0x20];
+};
+
 #endif /* MLX5_IFC_DR_H */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
index 3ac7dc67509f..fc8a2169d1a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
@@ -45,8 +45,6 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type);
 
 int mlx5dr_domain_destroy(struct mlx5dr_domain *domain);
 
-int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags);
-
 void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 			    struct mlx5dr_domain *peer_dmn,
 			    u16 peer_vhca_id);
@@ -160,7 +158,7 @@ mlx5dr_is_supported(struct mlx5_core_dev *dev)
 	       (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) ||
 		(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) &&
 		 (MLX5_CAP_GEN(dev, steering_format_version) <=
-		  MLX5_STEERING_FORMAT_CONNECTX_7)));
+		  MLX5_STEERING_FORMAT_CONNECTX_8)));
 }
 
 /* buddy functions & structure */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 0d5f750faa45..da5c24fc7b30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -465,19 +465,22 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 {
 	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	int err;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	if (err)
+		goto out;
 
 	*node_guid = MLX5_GET64(query_nic_vport_context_out, out,
 				nic_vport_context.node_guid);
-
+out:
 	kvfree(out);
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
 
@@ -519,19 +522,22 @@ int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 {
 	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	int err;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	if (err)
+		goto out;
 
 	*qkey_viol_cntr = MLX5_GET(query_nic_vport_context_out, out,
 				   nic_vport_context.qkey_violation_counter);
-
+out:
 	kvfree(out);
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_qkey_viol_cntr);
 
@@ -1199,6 +1205,31 @@ int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 vport, void *ou
 }
 EXPORT_SYMBOL_GPL(mlx5_vport_get_other_func_cap);
 
+int mlx5_vport_get_vhca_id(struct mlx5_core_dev *dev, u16 vport, u16 *vhca_id)
+{
+	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *query_ctx;
+	void *hca_caps;
+	int err;
+
+	*vhca_id = 0;
+
+	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
+	if (!query_ctx)
+		return -ENOMEM;
+
+	err = mlx5_vport_get_other_func_general_cap(dev, vport, query_ctx);
+	if (err)
+		goto out_free;
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	*vhca_id = MLX5_GET(cmd_hca_cap, hca_caps, vhca_id);
+
+out_free:
+	kfree(query_ctx);
+	return err;
+}
+
 int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap,
 				  u16 vport, u16 opmod)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wc.c b/drivers/net/ethernet/mellanox/mlx5/core/wc.c
index 1bed75eca97d..740b719e7072 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wc.c
@@ -382,6 +382,7 @@ err_alloc_bfreg:
 
 bool mlx5_wc_support_get(struct mlx5_core_dev *mdev)
 {
+	struct mutex *wc_state_lock = &mdev->wc_state_lock;
 	struct mlx5_core_dev *parent = NULL;
 
 	if (!MLX5_CAP_GEN(mdev, bf)) {
@@ -400,32 +401,31 @@ bool mlx5_wc_support_get(struct mlx5_core_dev *mdev)
 		 */
 		goto out;
 
-	mutex_lock(&mdev->wc_state_lock);
-
-	if (mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED)
-		goto unlock;
-
 #ifdef CONFIG_MLX5_SF
-	if (mlx5_core_is_sf(mdev))
+	if (mlx5_core_is_sf(mdev)) {
 		parent = mdev->priv.parent_mdev;
+		wc_state_lock = &parent->wc_state_lock;
+	}
 #endif
 
-	if (parent) {
-		mutex_lock(&parent->wc_state_lock);
+	mutex_lock(wc_state_lock);
 
+	if (mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED)
+		goto unlock;
+
+	if (parent) {
 		mlx5_core_test_wc(parent);
 
 		mlx5_core_dbg(mdev, "parent set wc_state=%d\n",
 			      parent->wc_state);
 		mdev->wc_state = parent->wc_state;
 
-		mutex_unlock(&parent->wc_state_lock);
+	} else {
+		mlx5_core_test_wc(mdev);
 	}
 
-	mlx5_core_test_wc(mdev);
-
 unlock:
-	mutex_unlock(&mdev->wc_state_lock);
+	mutex_unlock(wc_state_lock);
 out:
 	mlx5_core_dbg(mdev, "wc_state=%d\n", mdev->wc_state);
 
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
index fb2e5b844c15..d76d7a945899 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -447,8 +447,10 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 	priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX);
 
 	phy_irq = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(&pdev->dev), "phy", 0);
-	if (phy_irq < 0) {
-		dev_err(&pdev->dev, "Error getting PHY irq. Use polling instead");
+	if (phy_irq == -EPROBE_DEFER) {
+		err = -EPROBE_DEFER;
+		goto out;
+	} else if (phy_irq < 0) {
 		phy_irq = PHY_POLL;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 46245e0b2462..43c84900369a 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -14,7 +14,6 @@
 #define MLXFW_FSM_STATE_WAIT_TIMEOUT_MS 30000
 #define MLXFW_FSM_STATE_WAIT_ROUNDS \
 	(MLXFW_FSM_STATE_WAIT_TIMEOUT_MS / MLXFW_FSM_STATE_WAIT_CYCLE_MS)
-#define MLXFW_FSM_MAX_COMPONENT_SIZE (10 * (1 << 20))
 
 static const int mlxfw_fsm_state_errno[] = {
 	[MLXFW_FSM_STATE_ERR_ERROR] = -EIO,
@@ -229,7 +228,6 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev,
 		return err;
 	}
 
-	comp_max_size = min_t(u32, comp_max_size, MLXFW_FSM_MAX_COMPONENT_SIZE);
 	if (comp->data_size > comp_max_size) {
 		MLXFW_ERR_MSG(mlxfw_dev, extack,
 			      "Component size is bigger than limit", -EINVAL);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 4a79c0d7e7ad..2bb2b77351bd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -35,6 +35,7 @@
 #include "reg.h"
 #include "resources.h"
 #include "../mlxfw/mlxfw.h"
+#include "txheader.h"
 
 static LIST_HEAD(mlxsw_core_driver_list);
 static DEFINE_SPINLOCK(mlxsw_core_driver_list_lock);
@@ -677,7 +678,7 @@ struct mlxsw_reg_trans {
 	struct list_head bulk_list;
 	struct mlxsw_core *core;
 	struct sk_buff *tx_skb;
-	struct mlxsw_tx_info tx_info;
+	struct mlxsw_txhdr_info txhdr_info;
 	struct delayed_work timeout_dw;
 	unsigned int retries;
 	u64 tid;
@@ -737,12 +738,11 @@ static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
 	if (!skb)
 		return -ENOMEM;
 
-	trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0,
-			    skb->data + mlxsw_core->driver->txhdr_len,
-			    skb->len - mlxsw_core->driver->txhdr_len);
+	trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0, skb->data,
+			    skb->len);
 
 	atomic_set(&trans->active, 1);
-	err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->txhdr_info);
 	if (err) {
 		dev_kfree_skb(skb);
 		return err;
@@ -944,7 +944,7 @@ static struct sk_buff *mlxsw_emad_alloc(const struct mlxsw_core *mlxsw_core,
 
 	emad_len = (reg_len + sizeof(u32) + MLXSW_EMAD_ETH_HDR_LEN +
 		    (MLXSW_EMAD_OP_TLV_LEN + MLXSW_EMAD_END_TLV_LEN) *
-		    sizeof(u32) + mlxsw_core->driver->txhdr_len);
+		    sizeof(u32) + MLXSW_TXHDR_LEN);
 	if (mlxsw_core->emad.enable_string_tlv)
 		emad_len += MLXSW_EMAD_STRING_TLV_LEN * sizeof(u32);
 	if (mlxsw_core->emad.enable_latency_tlv)
@@ -984,8 +984,8 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core,
 	list_add_tail(&trans->bulk_list, bulk_list);
 	trans->core = mlxsw_core;
 	trans->tx_skb = skb;
-	trans->tx_info.local_port = MLXSW_PORT_CPU_PORT;
-	trans->tx_info.is_emad = true;
+	trans->txhdr_info.tx_info.local_port = MLXSW_PORT_CPU_PORT;
+	trans->txhdr_info.tx_info.is_emad = true;
 	INIT_DELAYED_WORK(&trans->timeout_dw, mlxsw_emad_trans_timeout_work);
 	trans->tid = tid;
 	init_completion(&trans->completion);
@@ -995,7 +995,6 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core,
 	trans->type = type;
 
 	mlxsw_emad_construct(mlxsw_core, skb, reg, payload, type, trans->tid);
-	mlxsw_core->driver->txhdr_construct(skb, &trans->tx_info);
 
 	spin_lock_bh(&mlxsw_core->emad.trans_list_lock);
 	list_add_tail_rcu(&trans->list, &mlxsw_core->emad.trans_list);
@@ -2330,10 +2329,10 @@ bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 EXPORT_SYMBOL(mlxsw_core_skb_transmit_busy);
 
 int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
-			    const struct mlxsw_tx_info *tx_info)
+			    const struct mlxsw_txhdr_info *txhdr_info)
 {
 	return mlxsw_core->bus->skb_transmit(mlxsw_core->bus_priv, skb,
-					     tx_info);
+					     txhdr_info);
 }
 EXPORT_SYMBOL(mlxsw_core_skb_transmit);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 6d11225594dd..1a871397a6df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -72,7 +72,14 @@ struct mlxsw_tx_info {
 	bool is_emad;
 };
 
+struct mlxsw_txhdr_info {
+	struct mlxsw_tx_info tx_info;
+	bool data;
+	u16 max_fid; /* Used for PTP packets which are sent as data. */
+};
+
 struct mlxsw_rx_md_info {
+	struct napi_struct *napi;
 	u32 cookie_index;
 	u32 latency;
 	u32 tx_congestion;
@@ -94,7 +101,7 @@ struct mlxsw_rx_md_info {
 bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_tx_info *tx_info);
 int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
-			    const struct mlxsw_tx_info *tx_info);
+			    const struct mlxsw_txhdr_info *txhdr_info);
 void mlxsw_core_ptp_transmitted(struct mlxsw_core *mlxsw_core,
 				struct sk_buff *skb, u16 local_port);
 
@@ -425,8 +432,6 @@ struct mlxsw_driver {
 	int (*trap_policer_counter_get)(struct mlxsw_core *mlxsw_core,
 					const struct devlink_trap_policer *policer,
 					u64 *p_drops);
-	void (*txhdr_construct)(struct sk_buff *skb,
-				const struct mlxsw_tx_info *tx_info);
 	int (*resources_register)(struct mlxsw_core *mlxsw_core);
 	int (*kvd_sizes_get)(struct mlxsw_core *mlxsw_core,
 			     const struct mlxsw_config_profile *profile,
@@ -439,7 +444,6 @@ struct mlxsw_driver {
 	void (*ptp_transmitted)(struct mlxsw_core *mlxsw_core,
 				struct sk_buff *skb, u16 local_port);
 
-	u8 txhdr_len;
 	const struct mlxsw_config_profile *profile;
 	bool sdq_supports_cqe_v2;
 };
@@ -486,7 +490,7 @@ struct mlxsw_bus {
 	bool (*skb_transmit_busy)(void *bus_priv,
 				  const struct mlxsw_tx_info *tx_info);
 	int (*skb_transmit)(void *bus_priv, struct sk_buff *skb,
-			    const struct mlxsw_tx_info *tx_info);
+			    const struct mlxsw_txhdr_info *txhdr_info);
 	int (*cmd_exec)(void *bus_priv, u16 opcode, u8 opcode_mod,
 			u32 in_mod, bool out_mbox_direct,
 			char *in_mbox, size_t in_mbox_size,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index e746cd9c68ed..eac9a14a6058 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -205,11 +205,11 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static struct thermal_zone_params mlxsw_thermal_params = {
+static const struct thermal_zone_params mlxsw_thermal_params = {
 	.no_hwmon = true,
 };
 
-static struct thermal_zone_device_ops mlxsw_thermal_ops = {
+static const struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.should_bind = mlxsw_thermal_should_bind,
 	.get_temp = mlxsw_thermal_get_temp,
 };
@@ -252,7 +252,7 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
+static const struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.should_bind	= mlxsw_thermal_module_should_bind,
 	.get_temp	= mlxsw_thermal_module_temp_get,
 };
@@ -280,7 +280,7 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
+static const struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
 	.should_bind	= mlxsw_thermal_module_should_bind,
 	.get_temp	= mlxsw_thermal_gearbox_temp_get,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index 1e150ce1c73a..f9f565c1036d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -516,7 +516,7 @@ static bool mlxsw_i2c_skb_transmit_busy(void *bus_priv,
 }
 
 static int mlxsw_i2c_skb_transmit(void *bus_priv, struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
+				  const struct mlxsw_txhdr_info *txhdr_info)
 {
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index d6f37456fb31..058dcabfaa2e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -21,6 +21,7 @@
 #include "cmd.h"
 #include "port.h"
 #include "resources.h"
+#include "txheader.h"
 
 #define mlxsw_pci_write32(mlxsw_pci, reg, val) \
 	iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg))
@@ -737,6 +738,7 @@ static void mlxsw_pci_cqe_rdq_md_init(struct sk_buff *skb, const char *cqe)
 }
 
 static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
+				     struct napi_struct *napi,
 				     struct mlxsw_pci_queue *q,
 				     u16 consumer_counter_limit,
 				     enum mlxsw_pci_cqe_v cqe_v, char *cqe)
@@ -807,6 +809,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	}
 
 	mlxsw_pci_skb_cb_ts_set(mlxsw_pci, skb, cqe_v, cqe);
+	mlxsw_skb_cb(skb)->rx_md_info.napi = napi;
 
 	mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
 
@@ -869,7 +872,7 @@ static int mlxsw_pci_napi_poll_cq_rx(struct napi_struct *napi, int budget)
 			continue;
 		}
 
-		mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq,
+		mlxsw_pci_cqe_rdq_handle(mlxsw_pci, napi, rdq,
 					 wqe_counter, q->u.cq.v, cqe);
 
 		if (++work_done == budget)
@@ -2093,6 +2096,39 @@ static void mlxsw_pci_fini(void *bus_priv)
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
 }
 
+static int mlxsw_pci_txhdr_construct(struct sk_buff *skb,
+				     const struct mlxsw_txhdr_info *txhdr_info)
+{
+	const struct mlxsw_tx_info tx_info = txhdr_info->tx_info;
+	char *txhdr;
+
+	if (skb_cow_head(skb, MLXSW_TXHDR_LEN))
+		return -ENOMEM;
+
+	txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
+	memset(txhdr, 0, MLXSW_TXHDR_LEN);
+
+	mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1);
+	mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
+	mlxsw_tx_hdr_swid_set(txhdr, 0);
+
+	if (unlikely(txhdr_info->data)) {
+		u16 fid = txhdr_info->max_fid + tx_info.local_port - 1;
+
+		mlxsw_tx_hdr_rx_is_router_set(txhdr, true);
+		mlxsw_tx_hdr_fid_valid_set(txhdr, true);
+		mlxsw_tx_hdr_fid_set(txhdr, fid);
+		mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_DATA);
+	} else {
+		mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL);
+		mlxsw_tx_hdr_control_tclass_set(txhdr, 1);
+		mlxsw_tx_hdr_port_mid_set(txhdr, tx_info.local_port);
+		mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
+	}
+
+	return 0;
+}
+
 static struct mlxsw_pci_queue *
 mlxsw_pci_sdq_pick(struct mlxsw_pci *mlxsw_pci,
 		   const struct mlxsw_tx_info *tx_info)
@@ -2120,7 +2156,7 @@ static bool mlxsw_pci_skb_transmit_busy(void *bus_priv,
 }
 
 static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
+				  const struct mlxsw_txhdr_info *txhdr_info)
 {
 	struct mlxsw_pci *mlxsw_pci = bus_priv;
 	struct mlxsw_pci_queue *q;
@@ -2129,13 +2165,17 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 	int i;
 	int err;
 
+	err = mlxsw_pci_txhdr_construct(skb, txhdr_info);
+	if (err)
+		return err;
+
 	if (skb_shinfo(skb)->nr_frags > MLXSW_PCI_WQE_SG_ENTRIES - 1) {
 		err = skb_linearize(skb);
 		if (err)
 			return err;
 	}
 
-	q = mlxsw_pci_sdq_pick(mlxsw_pci, tx_info);
+	q = mlxsw_pci_sdq_pick(mlxsw_pci, &txhdr_info->tx_info);
 	spin_lock_bh(&q->lock);
 	elem_info = mlxsw_pci_queue_elem_info_producer_get(q);
 	if (!elem_info) {
@@ -2143,7 +2183,7 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 		err = -EAGAIN;
 		goto unlock;
 	}
-	mlxsw_skb_cb(skb)->tx_info = *tx_info;
+	mlxsw_skb_cb(skb)->tx_info = txhdr_info->tx_info;
 	elem_info->sdq.skb = skb;
 
 	wqe = elem_info->elem;
@@ -2174,6 +2214,8 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 	for (i++; i < MLXSW_PCI_WQE_SG_ENTRIES; i++)
 		mlxsw_pci_wqe_byte_count_set(wqe, i, 0);
 
+	mlxsw_pci_wqe_ipcs_set(wqe, skb->ip_summed == CHECKSUM_PARTIAL);
+
 	/* Everything is set up, ring producer doorbell to get HW going */
 	q->producer_counter++;
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 6bed495dcf0f..7fa94e5828de 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -90,6 +90,11 @@ MLXSW_ITEM32(pci, wqe, lp, 0x00, 30, 1);
  */
 MLXSW_ITEM32(pci, wqe, type, 0x00, 23, 4);
 
+/* pci_wqe_ipcs
+ * Calculate IPv4 and TCP / UDP checksums.
+ */
+MLXSW_ITEM32(pci, wqe, ipcs, 0x00, 14, 1);
+
 /* pci_wqe_byte_count
  * Size of i-th scatter/gather entry, 0 if entry is unused.
  */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3f5e5d99251b..618957d65663 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -107,74 +107,6 @@ static const unsigned char mlxsw_sp2_mac_mask[ETH_ALEN] = {
 	0xff, 0xff, 0xff, 0xff, 0xf0, 0x00
 };
 
-/* tx_hdr_version
- * Tx header version.
- * Must be set to 1.
- */
-MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4);
-
-/* tx_hdr_ctl
- * Packet control type.
- * 0 - Ethernet control (e.g. EMADs, LACP)
- * 1 - Ethernet data
- */
-MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2);
-
-/* tx_hdr_proto
- * Packet protocol type. Must be set to 1 (Ethernet).
- */
-MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3);
-
-/* tx_hdr_rx_is_router
- * Packet is sent from the router. Valid for data packets only.
- */
-MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1);
-
-/* tx_hdr_fid_valid
- * Indicates if the 'fid' field is valid and should be used for
- * forwarding lookup. Valid for data packets only.
- */
-MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1);
-
-/* tx_hdr_swid
- * Switch partition ID. Must be set to 0.
- */
-MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3);
-
-/* tx_hdr_control_tclass
- * Indicates if the packet should use the control TClass and not one
- * of the data TClasses.
- */
-MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1);
-
-/* tx_hdr_etclass
- * Egress TClass to be used on the egress device on the egress port.
- */
-MLXSW_ITEM32(tx, hdr, etclass, 0x00, 0, 4);
-
-/* tx_hdr_port_mid
- * Destination local port for unicast packets.
- * Destination multicast ID for multicast packets.
- *
- * Control packets are directed to a specific egress port, while data
- * packets are transmitted through the CPU port (0) into the switch partition,
- * where forwarding rules are applied.
- */
-MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16);
-
-/* tx_hdr_fid
- * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is
- * set, otherwise calculated based on the packet's VID using VID to FID mapping.
- * Valid for data packets only.
- */
-MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16);
-
-/* tx_hdr_type
- * 0 - Data packets
- * 6 - Control packets
- */
-MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4);
-
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
 			      unsigned int counter_index, bool clear,
 			      u64 *packets, u64 *bytes)
@@ -233,61 +165,6 @@ void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
 			       counter_index);
 }
 
-void mlxsw_sp_txhdr_construct(struct sk_buff *skb,
-			      const struct mlxsw_tx_info *tx_info)
-{
-	char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
-
-	memset(txhdr, 0, MLXSW_TXHDR_LEN);
-
-	mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1);
-	mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL);
-	mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
-	mlxsw_tx_hdr_swid_set(txhdr, 0);
-	mlxsw_tx_hdr_control_tclass_set(txhdr, 1);
-	mlxsw_tx_hdr_port_mid_set(txhdr, tx_info->local_port);
-	mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
-}
-
-int
-mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core,
-				  struct mlxsw_sp_port *mlxsw_sp_port,
-				  struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
-{
-	char *txhdr;
-	u16 max_fid;
-	int err;
-
-	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
-		err = -ENOMEM;
-		goto err_skb_cow_head;
-	}
-
-	if (!MLXSW_CORE_RES_VALID(mlxsw_core, FID)) {
-		err = -EIO;
-		goto err_res_valid;
-	}
-	max_fid = MLXSW_CORE_RES_GET(mlxsw_core, FID);
-
-	txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
-	memset(txhdr, 0, MLXSW_TXHDR_LEN);
-
-	mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1);
-	mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
-	mlxsw_tx_hdr_rx_is_router_set(txhdr, true);
-	mlxsw_tx_hdr_fid_valid_set(txhdr, true);
-	mlxsw_tx_hdr_fid_set(txhdr, max_fid + tx_info->local_port - 1);
-	mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_DATA);
-	return 0;
-
-err_res_valid:
-err_skb_cow_head:
-	this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-	dev_kfree_skb_any(skb);
-	return err;
-}
-
 static bool mlxsw_sp_skb_requires_ts(struct sk_buff *skb)
 {
 	unsigned int type;
@@ -299,30 +176,49 @@ static bool mlxsw_sp_skb_requires_ts(struct sk_buff *skb)
 	return !!ptp_parse_header(skb, type);
 }
 
-static int mlxsw_sp_txhdr_handle(struct mlxsw_core *mlxsw_core,
-				 struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info)
+static void mlxsw_sp_txhdr_info_data_init(struct mlxsw_core *mlxsw_core,
+					  struct sk_buff *skb,
+					  struct mlxsw_txhdr_info *txhdr_info)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	/* Resource validation was done as part of PTP init. */
+	u16 max_fid = MLXSW_CORE_RES_GET(mlxsw_core, FID);
+
+	txhdr_info->data = true;
+	txhdr_info->max_fid = max_fid;
+}
 
-	/* In Spectrum-2 and Spectrum-3, PTP events that require a time stamp
-	 * need special handling and cannot be transmitted as regular control
-	 * packets.
+static struct sk_buff *
+mlxsw_sp_vlan_tag_push(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb)
+{
+	/* In some Spectrum ASICs, in order for PTP event packets to have their
+	 * correction field correctly set on the egress port they must be
+	 * transmitted as data packets. Such packets ingress the ASIC via the
+	 * CPU port and must have a VLAN tag, as the CPU port is not configured
+	 * with a PVID. Push the default VLAN (4095), which is configured as
+	 * egress untagged on all the ports.
 	 */
-	if (unlikely(mlxsw_sp_skb_requires_ts(skb)))
-		return mlxsw_sp->ptp_ops->txhdr_construct(mlxsw_core,
-							  mlxsw_sp_port, skb,
-							  tx_info);
+	if (skb_vlan_tagged(skb))
+		return skb;
 
-	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
-		this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-		dev_kfree_skb_any(skb);
-		return -ENOMEM;
-	}
+	return vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
+					 MLXSW_SP_DEFAULT_VID);
+}
 
-	mlxsw_sp_txhdr_construct(skb, tx_info);
-	return 0;
+static struct sk_buff *
+mlxsw_sp_txhdr_preparations(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			    struct mlxsw_txhdr_info *txhdr_info)
+{
+	if (likely(!mlxsw_sp_skb_requires_ts(skb)))
+		return skb;
+
+	if (!mlxsw_sp->ptp_ops->tx_as_data)
+		return skb;
+
+	/* Special handling for PTP events that require a time stamp and cannot
+	 * be transmitted as regular control packets.
+	 */
+	mlxsw_sp_txhdr_info_data_init(mlxsw_sp->core, skb, txhdr_info);
+	return mlxsw_sp_vlan_tag_push(mlxsw_sp, skb);
 }
 
 enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state)
@@ -721,16 +617,16 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port_pcpu_stats *pcpu_stats;
-	const struct mlxsw_tx_info tx_info = {
-		.local_port = mlxsw_sp_port->local_port,
-		.is_emad = false,
+	struct mlxsw_txhdr_info txhdr_info = {
+		.tx_info.local_port = mlxsw_sp_port->local_port,
+		.tx_info.is_emad = false,
 	};
 	u64 len;
 	int err;
 
 	memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
 
-	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info))
+	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &txhdr_info.tx_info))
 		return NETDEV_TX_BUSY;
 
 	if (eth_skb_pad(skb)) {
@@ -738,10 +634,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 
-	err = mlxsw_sp_txhdr_handle(mlxsw_sp->core, mlxsw_sp_port, skb,
-				    &tx_info);
-	if (err)
+	skb = mlxsw_sp_txhdr_preparations(mlxsw_sp, skb, &txhdr_info);
+	if (!skb) {
+		this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
 		return NETDEV_TX_OK;
+	}
 
 	/* TX header is consumed by HW on the way so we shouldn't count its
 	 * bytes as being sent.
@@ -751,7 +648,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
-	err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &txhdr_info);
 
 	if (!err) {
 		pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats);
@@ -1262,63 +1159,31 @@ static int mlxsw_sp_set_features(struct net_device *dev,
 	return 0;
 }
 
-static int mlxsw_sp_port_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct ifreq *ifr)
+static int mlxsw_sp_port_hwtstamp_set(struct net_device *dev,
+				      struct kernel_hwtstamp_config *config,
+				      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
-	int err;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port,
-							     &config);
-	if (err)
-		return err;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
-	return 0;
+	return mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port,
+							      config, extack);
 }
 
-static int mlxsw_sp_port_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct ifreq *ifr)
+static int mlxsw_sp_port_hwtstamp_get(struct net_device *dev,
+				      struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
-	int err;
-
-	err = mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_get(mlxsw_sp_port,
-							     &config);
-	if (err)
-		return err;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
-	return 0;
+	return mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_get(mlxsw_sp_port,
+							      config);
 }
 
 static inline void mlxsw_sp_port_ptp_clear(struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	struct hwtstamp_config config = {0};
+	struct kernel_hwtstamp_config config = {};
 
-	mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port, &config);
-}
-
-static int
-mlxsw_sp_port_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return mlxsw_sp_port_hwtstamp_set(mlxsw_sp_port, ifr);
-	case SIOCGHWTSTAMP:
-		return mlxsw_sp_port_hwtstamp_get(mlxsw_sp_port, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port, &config,
+						       NULL);
 }
 
 static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
@@ -1335,7 +1200,8 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= mlxsw_sp_port_add_vid,
 	.ndo_vlan_rx_kill_vid	= mlxsw_sp_port_kill_vid,
 	.ndo_set_features	= mlxsw_sp_set_features,
-	.ndo_eth_ioctl		= mlxsw_sp_port_ioctl,
+	.ndo_hwtstamp_get	= mlxsw_sp_port_hwtstamp_get,
+	.ndo_hwtstamp_set	= mlxsw_sp_port_hwtstamp_set,
 };
 
 static int
@@ -1677,10 +1543,12 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 	netif_carrier_off(dev);
 
 	dev->features |= NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_FILTER |
-			 NETIF_F_HW_TC;
-	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK;
+			 NETIF_F_HW_TC | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK |
+			    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	dev->lltx = true;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR;
@@ -2449,7 +2317,7 @@ void mlxsw_sp_rx_listener_no_mark_func(struct sk_buff *skb,
 	u64_stats_update_end(&pcpu_stats->syncp);
 
 	skb->protocol = eth_type_trans(skb, skb->dev);
-	netif_receive_skb(skb);
+	napi_gro_receive(mlxsw_skb_cb(skb)->rx_md_info.napi, skb);
 }
 
 static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u16 local_port,
@@ -2510,8 +2378,6 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* Multicast Router Traps */
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
 	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
-	/* NVE traps */
-	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, NEIGH_DISCOVERY, false),
 };
 
 static const struct mlxsw_listener mlxsw_sp1_listener[] = {
@@ -2792,7 +2658,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = {
 	.get_stats_count = mlxsw_sp1_get_stats_count,
 	.get_stats_strings = mlxsw_sp1_get_stats_strings,
 	.get_stats	= mlxsw_sp1_get_stats,
-	.txhdr_construct = mlxsw_sp_ptp_txhdr_construct,
 };
 
 static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = {
@@ -2811,7 +2676,7 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = {
 	.get_stats_count = mlxsw_sp2_get_stats_count,
 	.get_stats_strings = mlxsw_sp2_get_stats_strings,
 	.get_stats	= mlxsw_sp2_get_stats,
-	.txhdr_construct = mlxsw_sp2_ptp_txhdr_construct,
+	.tx_as_data     = true,
 };
 
 static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = {
@@ -2830,7 +2695,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = {
 	.get_stats_count = mlxsw_sp2_get_stats_count,
 	.get_stats_strings = mlxsw_sp2_get_stats_strings,
 	.get_stats	= mlxsw_sp2_get_stats,
-	.txhdr_construct = mlxsw_sp_ptp_txhdr_construct,
 };
 
 struct mlxsw_sp_sample_trigger_node {
@@ -3992,11 +3856,9 @@ static struct mlxsw_driver mlxsw_sp1_driver = {
 	.trap_policer_fini		= mlxsw_sp_trap_policer_fini,
 	.trap_policer_set		= mlxsw_sp_trap_policer_set,
 	.trap_policer_counter_get	= mlxsw_sp_trap_policer_counter_get,
-	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp1_resources_register,
 	.kvd_sizes_get			= mlxsw_sp_kvd_sizes_get,
 	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
-	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp1_config_profile,
 	.sdq_supports_cqe_v2		= false,
 };
@@ -4030,10 +3892,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
 	.trap_policer_fini		= mlxsw_sp_trap_policer_fini,
 	.trap_policer_set		= mlxsw_sp_trap_policer_set,
 	.trap_policer_counter_get	= mlxsw_sp_trap_policer_counter_get,
-	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
 	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
-	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp2_config_profile,
 	.sdq_supports_cqe_v2		= true,
 };
@@ -4067,10 +3927,8 @@ static struct mlxsw_driver mlxsw_sp3_driver = {
 	.trap_policer_fini		= mlxsw_sp_trap_policer_fini,
 	.trap_policer_set		= mlxsw_sp_trap_policer_set,
 	.trap_policer_counter_get	= mlxsw_sp_trap_policer_counter_get,
-	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
 	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
-	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp2_config_profile,
 	.sdq_supports_cqe_v2		= true,
 };
@@ -4102,10 +3960,8 @@ static struct mlxsw_driver mlxsw_sp4_driver = {
 	.trap_policer_fini		= mlxsw_sp_trap_policer_fini,
 	.trap_policer_set		= mlxsw_sp_trap_policer_set,
 	.trap_policer_counter_get	= mlxsw_sp_trap_policer_counter_get,
-	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
 	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
-	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp4_config_profile,
 	.sdq_supports_cqe_v2		= true,
 };
@@ -5343,25 +5199,13 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			return 0;
 		if (!mlxsw_sp_bridge_vxlan_is_valid(upper_dev, extack))
 			return -EOPNOTSUPP;
-		if (cu_info->linking) {
-			if (!netif_running(dev))
-				return 0;
-			/* When the bridge is VLAN-aware, the VNI of the VxLAN
-			 * device needs to be mapped to a VLAN, but at this
-			 * point no VLANs are configured on the VxLAN device
-			 */
-			if (br_vlan_enabled(upper_dev))
-				return 0;
+		if (!netif_running(dev))
+			return 0;
+		if (cu_info->linking)
 			return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev,
 							  dev, 0, extack);
-		} else {
-			/* VLANs were already flushed, which triggered the
-			 * necessary cleanup
-			 */
-			if (br_vlan_enabled(upper_dev))
-				return 0;
+		else
 			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
-		}
 		break;
 	case NETDEV_PRE_UP:
 		upper_dev = netdev_master_upper_dev_get(dev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 8d3c61287696..b03ff9e044f9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -233,9 +233,10 @@ struct mlxsw_sp_ptp_ops {
 			    u16 local_port);
 
 	int (*hwtstamp_get)(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct hwtstamp_config *config);
+			    struct kernel_hwtstamp_config *config);
 	int (*hwtstamp_set)(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct hwtstamp_config *config);
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack);
 	void (*shaper_work)(struct work_struct *work);
 	int (*get_ts_info)(struct mlxsw_sp *mlxsw_sp,
 			   struct kernel_ethtool_ts_info *info);
@@ -243,10 +244,7 @@ struct mlxsw_sp_ptp_ops {
 	void (*get_stats_strings)(u8 **p);
 	void (*get_stats)(struct mlxsw_sp_port *mlxsw_sp_port,
 			  u64 *data, int data_index);
-	int (*txhdr_construct)(struct mlxsw_core *mlxsw_core,
-			       struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct sk_buff *skb,
-			       const struct mlxsw_tx_info *tx_info);
+	bool tx_as_data;
 };
 
 struct mlxsw_sp_fid_core_ops {
@@ -354,7 +352,7 @@ struct mlxsw_sp_port {
 	struct mlxsw_sp_flow_block *eg_flow_block;
 	struct {
 		struct delayed_work shaper_dw;
-		struct hwtstamp_config hwtstamp_config;
+		struct kernel_hwtstamp_config hwtstamp_config;
 		u16 ing_types;
 		u16 egr_types;
 		struct mlxsw_sp_ptp_port_stats stats;
@@ -664,10 +662,10 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
 					 const struct net_device *br_dev);
 int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev, u16 vid,
+			       struct net_device *vxlan_dev, u16 vid,
 			       struct netlink_ext_ack *extack);
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *vxlan_dev);
+				 struct net_device *vxlan_dev);
 extern struct notifier_block mlxsw_sp_switchdev_notifier;
 
 /* spectrum.c */
@@ -711,12 +709,6 @@ int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
 				unsigned int *p_counter_index);
 void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
 				unsigned int counter_index);
-void mlxsw_sp_txhdr_construct(struct sk_buff *skb,
-			      const struct mlxsw_tx_info *tx_info);
-int mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core,
-				      struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct sk_buff *skb,
-				      const struct mlxsw_tx_info *tx_info);
 bool mlxsw_sp_port_dev_check(const struct net_device *dev);
 struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev);
 struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev);
@@ -763,9 +755,6 @@ void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
 				 struct net_device *dev);
-bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev);
-u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev);
 u16 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
 				      enum mlxsw_sp_l3proto ul_proto,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
index a54eedb69a3f..067f0055a55a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -212,7 +212,22 @@ static const u8 mlxsw_sp4_acl_bf_crc6_tab[256] = {
  * This array defines key offsets for easy access when copying key blocks from
  * entry key to Bloom filter chunk.
  */
-static const u8 chunk_key_offsets[MLXSW_BLOOM_KEY_CHUNKS] = {2, 20, 38};
+static char *
+mlxsw_sp_acl_bf_enc_key_get(struct mlxsw_sp_acl_atcam_entry *aentry,
+			    u8 chunk_index)
+{
+	switch (chunk_index) {
+	case 0:
+		return &aentry->ht_key.enc_key[2];
+	case 1:
+		return &aentry->ht_key.enc_key[20];
+	case 2:
+		return &aentry->ht_key.enc_key[38];
+	default:
+		WARN_ON_ONCE(1);
+		return &aentry->ht_key.enc_key[0];
+	}
+}
 
 static u16 mlxsw_sp2_acl_bf_crc16_byte(u16 crc, u8 c)
 {
@@ -235,9 +250,10 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 			     u8 key_offset, u8 chunk_key_len, u8 chunk_len)
 {
 	struct mlxsw_afk_key_info *key_info = aregion->region->key_info;
-	u8 chunk_index, chunk_count, block_count;
+	u8 chunk_index, chunk_count;
 	char *chunk = output;
 	__be16 erp_region_id;
+	u32 block_count;
 
 	block_count = mlxsw_afk_key_info_blocks_count_get(key_info);
 	chunk_count = 1 + ((block_count - 1) >> 2);
@@ -245,12 +261,13 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 				   (aregion->region->id << 4));
 	for (chunk_index = max_chunks - chunk_count; chunk_index < max_chunks;
 	     chunk_index++) {
+		char *enc_key;
+
 		memset(chunk, 0, pad_bytes);
 		memcpy(chunk + pad_bytes, &erp_region_id,
 		       sizeof(erp_region_id));
-		memcpy(chunk + key_offset,
-		       &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]],
-		       chunk_key_len);
+		enc_key = mlxsw_sp_acl_bf_enc_key_get(aentry, chunk_index);
+		memcpy(chunk + key_offset, enc_key, chunk_key_len);
 		chunk += chunk_len;
 	}
 	*len = chunk_count * chunk_len;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index 6fe185ea6732..1850a975b380 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -324,6 +324,10 @@ static const struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_5b[] =
 	MLXSW_AFK_ELEMENT_INST_EXT_U32(SRC_SYS_PORT, 0x04, 0, 9, -1, true), /* RX_ACL_SYSTEM_PORT */
 };
 
+static const struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_1b[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x04, 4),
+};
+
 static const struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_5b[] = {
 	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER, 0x04, 20, 12),
 };
@@ -341,7 +345,7 @@ static const struct mlxsw_afk_block mlxsw_sp4_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0x14, mlxsw_sp_afk_element_info_mac_4),
 	MLXSW_AFK_BLOCK_HIGH_ENTROPY(0x1A, mlxsw_sp_afk_element_info_mac_5b),
 	MLXSW_AFK_BLOCK_HIGH_ENTROPY(0x38, mlxsw_sp_afk_element_info_ipv4_0),
-	MLXSW_AFK_BLOCK_HIGH_ENTROPY(0x39, mlxsw_sp_afk_element_info_ipv4_1),
+	MLXSW_AFK_BLOCK_HIGH_ENTROPY(0x3F, mlxsw_sp_afk_element_info_ipv4_1b),
 	MLXSW_AFK_BLOCK(0x3A, mlxsw_sp_afk_element_info_ipv4_2),
 	MLXSW_AFK_BLOCK(0x36, mlxsw_sp_afk_element_info_ipv4_5b),
 	MLXSW_AFK_BLOCK(0x40, mlxsw_sp_afk_element_info_ipv6_0),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 2bed8c86b7cf..0a8fb9c842d3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -262,7 +262,7 @@ err_port_pause_configure:
 }
 
 struct mlxsw_sp_port_hw_stats {
-	char str[ETH_GSTRING_LEN];
+	char str[ETH_GSTRING_LEN] __nonstring;
 	u64 (*getter)(const char *payload);
 	bool cells_bytes;
 };
@@ -768,7 +768,9 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
 	err = mlxsw_sp_get_hw_stats_by_group(&hw_stats, &len, grp);
 	if (err)
 		return;
-	mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
+	err = mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
+	if (err)
+		return;
 	for (i = 0; i < len; i++) {
 		data[data_index + i] = hw_stats[i].getter(ppcnt_pl);
 		if (!hw_stats[i].cells_bytes)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index f07955b5439f..6a4a81c63451 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -192,6 +192,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 				return -EOPNOTSUPP;
 			}
 
+			if (sample_act_count) {
+				NL_SET_ERR_MSG_MOD(extack, "Mirror action after sample action is not supported");
+				return -EOPNOTSUPP;
+			}
+
 			err = mlxsw_sp_acl_rulei_act_mirror(mlxsw_sp, rulei,
 							    block, out_dev,
 							    extack);
@@ -265,6 +270,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 				return -EOPNOTSUPP;
 			}
 
+			if (mirror_act_count) {
+				NL_SET_ERR_MSG_MOD(extack, "Sample action after mirror action is not supported");
+				return -EOPNOTSUPP;
+			}
+
 			err = mlxsw_sp_acl_rulei_act_sample(mlxsw_sp, rulei,
 							    block,
 							    act->sample.psample_group,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index 69cd689dbc83..5afe6b155ef0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -1003,10 +1003,10 @@ static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp,
 	mr->mr_ops->route_stats(mlxsw_sp, mr_route->route_priv, &packets,
 				&bytes);
 
-	if (mr_route->mfc->mfc_un.res.pkt != packets)
-		mr_route->mfc->mfc_un.res.lastuse = jiffies;
-	mr_route->mfc->mfc_un.res.pkt = packets;
-	mr_route->mfc->mfc_un.res.bytes = bytes;
+	if (atomic_long_read(&mr_route->mfc->mfc_un.res.pkt) != packets)
+		WRITE_ONCE(mr_route->mfc->mfc_un.res.lastuse, jiffies);
+	atomic_long_set(&mr_route->mfc->mfc_un.res.pkt, packets);
+	atomic_long_set(&mr_route->mfc->mfc_un.res.bytes, bytes);
 }
 
 static void mlxsw_sp_mr_stats_update(struct work_struct *work)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index d94081c7658e..e8182dd76c7d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -46,7 +46,7 @@ struct mlxsw_sp2_ptp_state {
 	refcount_t ptp_port_enabled_ref; /* Number of ports with time stamping
 					  * enabled.
 					  */
-	struct hwtstamp_config config;
+	struct kernel_hwtstamp_config config;
 	struct mutex lock; /* Protects 'config' and HW configuration. */
 };
 
@@ -1083,14 +1083,14 @@ void mlxsw_sp1_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state_common)
 }
 
 int mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config)
 {
 	*config = mlxsw_sp_port->ptp.hwtstamp_config;
 	return 0;
 }
 
 static int
-mlxsw_sp1_ptp_get_message_types(const struct hwtstamp_config *config,
+mlxsw_sp1_ptp_get_message_types(const struct kernel_hwtstamp_config *config,
 				u16 *p_ing_types, u16 *p_egr_types,
 				enum hwtstamp_rx_filters *p_rx_filter)
 {
@@ -1246,7 +1246,8 @@ void mlxsw_sp1_ptp_shaper_work(struct work_struct *work)
 }
 
 int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
 	enum hwtstamp_rx_filters rx_filter;
 	u16 ing_types;
@@ -1270,7 +1271,7 @@ int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (err)
 		return err;
 
-	/* Notify the ioctl caller what we are actually timestamping. */
+	/* Notify the caller what we are actually timestamping. */
 	config->rx_filter = rx_filter;
 
 	return 0;
@@ -1353,6 +1354,10 @@ struct mlxsw_sp_ptp_state *mlxsw_sp2_ptp_init(struct mlxsw_sp *mlxsw_sp)
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
 
+	/* Max FID will be used in data path, check validity as part of init. */
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, FID))
+		return ERR_PTR(-EIO);
+
 	ptp_state = kzalloc(sizeof(*ptp_state), GFP_KERNEL);
 	if (!ptp_state)
 		return ERR_PTR(-ENOMEM);
@@ -1447,7 +1452,7 @@ void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 }
 
 int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 
@@ -1461,7 +1466,7 @@ int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int
-mlxsw_sp2_ptp_get_message_types(const struct hwtstamp_config *config,
+mlxsw_sp2_ptp_get_message_types(const struct kernel_hwtstamp_config *config,
 				u16 *p_ing_types, u16 *p_egr_types,
 				enum hwtstamp_rx_filters *p_rx_filter)
 {
@@ -1538,7 +1543,7 @@ static int mlxsw_sp2_ptp_mtpcpc_set(struct mlxsw_sp *mlxsw_sp, bool ptp_trap_en,
 
 static int mlxsw_sp2_ptp_enable(struct mlxsw_sp *mlxsw_sp, u16 ing_types,
 				u16 egr_types,
-				struct hwtstamp_config new_config)
+				struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp);
 	int err;
@@ -1552,7 +1557,7 @@ static int mlxsw_sp2_ptp_enable(struct mlxsw_sp *mlxsw_sp, u16 ing_types,
 }
 
 static int mlxsw_sp2_ptp_disable(struct mlxsw_sp *mlxsw_sp,
-				 struct hwtstamp_config new_config)
+				 struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp);
 	int err;
@@ -1567,7 +1572,7 @@ static int mlxsw_sp2_ptp_disable(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp2_ptp_configure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 					u16 ing_types, u16 egr_types,
-					struct hwtstamp_config new_config)
+					struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
@@ -1588,7 +1593,7 @@ static int mlxsw_sp2_ptp_configure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int mlxsw_sp2_ptp_deconfigure_port(struct mlxsw_sp_port *mlxsw_sp_port,
-					  struct hwtstamp_config new_config)
+					  struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
@@ -1610,11 +1615,12 @@ err_ptp_disable:
 }
 
 int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
+	struct kernel_hwtstamp_config new_config;
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	enum hwtstamp_rx_filters rx_filter;
-	struct hwtstamp_config new_config;
 	u16 new_ing_types, new_egr_types;
 	bool ptp_enabled;
 	int err;
@@ -1648,7 +1654,7 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->ptp.ing_types = new_ing_types;
 	mlxsw_sp_port->ptp.egr_types = new_egr_types;
 
-	/* Notify the ioctl caller what we are actually timestamping. */
+	/* Notify the caller what we are actually timestamping. */
 	config->rx_filter = rx_filter;
 	mutex_unlock(&ptp_state->lock);
 
@@ -1679,43 +1685,3 @@ int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
 
 	return 0;
 }
-
-int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				 struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info)
-{
-	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
-		this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-		dev_kfree_skb_any(skb);
-		return -ENOMEM;
-	}
-
-	mlxsw_sp_txhdr_construct(skb, tx_info);
-	return 0;
-}
-
-int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				  struct mlxsw_sp_port *mlxsw_sp_port,
-				  struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
-{
-	/* In Spectrum-2 and Spectrum-3, in order for PTP event packets to have
-	 * their correction field correctly set on the egress port they must be
-	 * transmitted as data packets. Such packets ingress the ASIC via the
-	 * CPU port and must have a VLAN tag, as the CPU port is not configured
-	 * with a PVID. Push the default VLAN (4095), which is configured as
-	 * egress untagged on all the ports.
-	 */
-	if (!skb_vlan_tagged(skb)) {
-		skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
-						MLXSW_SP_DEFAULT_VID);
-		if (!skb) {
-			this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-			return -ENOMEM;
-		}
-	}
-
-	return mlxsw_sp_txhdr_ptp_data_construct(mlxsw_core, mlxsw_sp_port, skb,
-						 tx_info);
-}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
index c8aa1452fbb9..df37f1470830 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
@@ -34,10 +34,11 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
 				 u64 timestamp);
 
 int mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config);
 
 int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack);
 
 void mlxsw_sp1_ptp_shaper_work(struct work_struct *work);
 
@@ -49,11 +50,6 @@ void mlxsw_sp1_get_stats_strings(u8 **p);
 void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 			 u64 *data, int data_index);
 
-int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				 struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info);
-
 struct mlxsw_sp_ptp_clock *
 mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev);
 
@@ -70,19 +66,15 @@ void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 			       struct sk_buff *skb, u16 local_port);
 
 int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config);
 
 int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack);
 
 int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
 			      struct kernel_ethtool_ts_info *info);
 
-int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				  struct mlxsw_sp_port *mlxsw_sp_port,
-				  struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info);
-
 #else
 
 static inline struct mlxsw_sp_ptp_clock *
@@ -127,14 +119,15 @@ mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
 
 static inline int
 mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
 
 static inline int
 mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
@@ -157,15 +150,6 @@ static inline void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 }
 
-static inline int
-mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-			     struct mlxsw_sp_port *mlxsw_sp_port,
-			     struct sk_buff *skb,
-			     const struct mlxsw_tx_info *tx_info)
-{
-	return -EOPNOTSUPP;
-}
-
 static inline struct mlxsw_sp_ptp_clock *
 mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev)
 {
@@ -200,23 +184,15 @@ static inline void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 
 static inline int
 mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
 
 static inline int
 mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int
-mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-			      struct mlxsw_sp_port *mlxsw_sp_port,
-			      struct sk_buff *skb,
-			      const struct mlxsw_tx_info *tx_info)
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7d6d859cef3f..a2033837182e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3014,6 +3014,9 @@ static int mlxsw_sp_neigh_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
 		.rif = rif,
 	};
 
+	if (!mlxsw_sp_dev_lower_is_port(mlxsw_sp_rif_dev(rif)))
+		return 0;
+
 	neigh_for_each(&arp_tbl, mlxsw_sp_neigh_rif_made_sync_each, &rms);
 	if (rms.err)
 		goto err_arp;
@@ -8184,41 +8187,6 @@ mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev)
-{
-	struct mlxsw_sp_rif *rif;
-
-	mutex_lock(&mlxsw_sp->router->lock);
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	mutex_unlock(&mlxsw_sp->router->lock);
-
-	return rif;
-}
-
-u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev)
-{
-	struct mlxsw_sp_rif *rif;
-	u16 vid = 0;
-
-	mutex_lock(&mlxsw_sp->router->lock);
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!rif)
-		goto out;
-
-	/* We only return the VID for VLAN RIFs. Otherwise we return an
-	 * invalid value (0).
-	 */
-	if (rif->ops->type != MLXSW_SP_RIF_TYPE_VLAN)
-		goto out;
-
-	vid = mlxsw_sp_fid_8021q_vid(rif->fid);
-
-out:
-	mutex_unlock(&mlxsw_sp->router->lock);
-	return vid;
-}
-
 static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
 {
 	char ritr_pl[MLXSW_REG_RITR_LEN];
@@ -8417,19 +8385,6 @@ u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 	return lb_rif->common.rif_index;
 }
 
-u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
-{
-	struct net_device *dev = mlxsw_sp_rif_dev(&lb_rif->common);
-	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(dev);
-	struct mlxsw_sp_vr *ul_vr;
-
-	ul_vr = mlxsw_sp_vr_get(lb_rif->common.mlxsw_sp, ul_tb_id, NULL);
-	if (WARN_ON(IS_ERR(ul_vr)))
-		return 0;
-
-	return ul_vr->id;
-}
-
 u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 {
 	return lb_rif->ul_rif_id;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 0432c7cc6b07..313efab5c324 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -90,7 +90,6 @@ struct mlxsw_sp_ipip_entry;
 struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 					   u16 rif_index);
 u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif);
-u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif);
 u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif);
 u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 4b5fd71c897d..32d2e61f2b82 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -423,8 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-			    0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0,
-			    0);
+			    0, 0, tun->net, parms.link, tun->fwmark, 0, 0);
 
 	rt = ip_route_output_key(tun->net, &fl4);
 	if (IS_ERR(rt))
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 6397ff0dc951..a48bf342084d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2929,23 +2929,8 @@ void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_bridge_port_put(mlxsw_sp->bridge, bridge_port);
 }
 
-int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
-			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev, u16 vid,
-			       struct netlink_ext_ack *extack)
-{
-	struct mlxsw_sp_bridge_device *bridge_device;
-
-	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
-	if (WARN_ON(!bridge_device))
-		return -EINVAL;
-
-	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
-					      extack);
-}
-
-void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *vxlan_dev)
+static void __mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
+					  const struct net_device *vxlan_dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
 	struct mlxsw_sp_fid *fid;
@@ -2963,6 +2948,47 @@ void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_fid_put(fid);
 }
 
+int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
+			       const struct net_device *br_dev,
+			       struct net_device *vxlan_dev, u16 vid,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	int err;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (WARN_ON(!bridge_device))
+		return -EINVAL;
+
+	mlxsw_sp_port = mlxsw_sp_port_dev_lower_find(bridge_device->dev);
+	if (!mlxsw_sp_port)
+		return -EINVAL;
+
+	err = bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
+					     extack);
+	if (err)
+		return err;
+
+	err = switchdev_bridge_port_offload(vxlan_dev, mlxsw_sp_port->dev,
+					    NULL, NULL, NULL, false, extack);
+	if (err)
+		goto err_bridge_port_offload;
+
+	return 0;
+
+err_bridge_port_offload:
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	return err;
+}
+
+void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
+				 struct net_device *vxlan_dev)
+{
+	switchdev_bridge_port_unoffload(vxlan_dev, NULL, NULL, NULL);
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+}
+
 static void
 mlxsw_sp_switchdev_vxlan_addr_convert(const union vxlan_addr *vxlan_addr,
 				      enum mlxsw_sp_l3proto *proto,
@@ -3867,7 +3893,7 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 			mlxsw_sp_fid_put(fid);
 			return -EINVAL;
 		}
-		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+		__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 		mlxsw_sp_fid_put(fid);
 		return 0;
 	}
@@ -3883,7 +3909,7 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 	/* Fourth case: Thew new VLAN is PVID, which means the VLAN currently
 	 * mapped to the VNI should be unmapped
 	 */
-	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 	mlxsw_sp_fid_put(fid);
 
 	/* Fifth case: The new VLAN is also egress untagged, which means the
@@ -3923,7 +3949,7 @@ mlxsw_sp_switchdev_vxlan_vlan_del(struct mlxsw_sp *mlxsw_sp,
 	if (mlxsw_sp_fid_8021q_vid(fid) != vid)
 		goto out;
 
-	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 
 out:
 	mlxsw_sp_fid_put(fid);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 899c954e0e5f..b5c3f789c685 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -173,7 +173,7 @@ static void mlxsw_sp_rx_no_mark_listener(struct sk_buff *skb, u16 local_port,
 	if (err)
 		return;
 
-	netif_receive_skb(skb);
+	napi_gro_receive(mlxsw_skb_cb(skb)->rx_md_info.napi, skb);
 }
 
 static void mlxsw_sp_rx_mark_listener(struct sk_buff *skb, u16 local_port,
@@ -959,18 +959,18 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 	},
 	{
 		.trap = MLXSW_SP_TRAP_CONTROL(ARP_REQUEST, NEIGH_DISCOVERY,
-					      MIRROR),
+					      TRAP),
 		.listeners_arr = {
-			MLXSW_SP_RXL_MARK(ROUTER_ARPBC, NEIGH_DISCOVERY,
-					  TRAP_TO_CPU, false),
+			MLXSW_SP_RXL_NO_MARK(ARPBC, NEIGH_DISCOVERY,
+					     TRAP_TO_CPU, false),
 		},
 	},
 	{
 		.trap = MLXSW_SP_TRAP_CONTROL(ARP_RESPONSE, NEIGH_DISCOVERY,
-					      MIRROR),
+					      TRAP),
 		.listeners_arr = {
-			MLXSW_SP_RXL_MARK(ROUTER_ARPUC, NEIGH_DISCOVERY,
-					  TRAP_TO_CPU, false),
+			MLXSW_SP_RXL_NO_MARK(ARPUC, NEIGH_DISCOVERY,
+					     TRAP_TO_CPU, false),
 		},
 	},
 	{
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 83477c8e6971..80ee5c4825dc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -29,6 +29,8 @@ enum {
 	MLXSW_TRAP_ID_FDB_MISMATCH = 0x3B,
 	MLXSW_TRAP_ID_FID_MISS = 0x3D,
 	MLXSW_TRAP_ID_DECAP_ECN0 = 0x40,
+	MLXSW_TRAP_ID_ARPBC = 0x50,
+	MLXSW_TRAP_ID_ARPUC = 0x51,
 	MLXSW_TRAP_ID_MTUERROR = 0x52,
 	MLXSW_TRAP_ID_TTLERROR = 0x53,
 	MLXSW_TRAP_ID_LBERROR = 0x54,
@@ -66,13 +68,10 @@ enum {
 	MLXSW_TRAP_ID_HOST_MISS_IPV6 = 0x92,
 	MLXSW_TRAP_ID_IPIP_DECAP_ERROR = 0xB1,
 	MLXSW_TRAP_ID_NVE_DECAP_ARP = 0xB8,
-	MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD,
 	MLXSW_TRAP_ID_IPV4_BFD = 0xD0,
 	MLXSW_TRAP_ID_IPV6_BFD = 0xD1,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7,
-	MLXSW_TRAP_ID_ROUTER_ARPBC = 0xE0,
-	MLXSW_TRAP_ID_ROUTER_ARPUC = 0xE1,
 	MLXSW_TRAP_ID_DISCARD_NON_ROUTABLE = 0x11A,
 	MLXSW_TRAP_ID_DISCARD_ROUTER2 = 0x130,
 	MLXSW_TRAP_ID_DISCARD_ROUTER3 = 0x131,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/txheader.h b/drivers/net/ethernet/mellanox/mlxsw/txheader.h
index da51dd9d5e44..e78cba5821b6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/txheader.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/txheader.h
@@ -4,6 +4,69 @@
 #ifndef _MLXSW_TXHEADER_H
 #define _MLXSW_TXHEADER_H
 
+/* tx_hdr_version
+ * Tx header version.
+ * Must be set to 1.
+ */
+MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4);
+
+/* tx_hdr_ctl
+ * Packet control type.
+ * 0 - Ethernet control (e.g. EMADs, LACP)
+ * 1 - Ethernet data
+ */
+MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2);
+
+/* tx_hdr_proto
+ * Packet protocol type. Must be set to 1 (Ethernet).
+ */
+MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3);
+
+/* tx_hdr_rx_is_router
+ * Packet is sent from the router. Valid for data packets only.
+ */
+MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1);
+
+/* tx_hdr_fid_valid
+ * Indicates if the 'fid' field is valid and should be used for
+ * forwarding lookup. Valid for data packets only.
+ */
+MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1);
+
+/* tx_hdr_swid
+ * Switch partition ID. Must be set to 0.
+ */
+MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3);
+
+/* tx_hdr_control_tclass
+ * Indicates if the packet should use the control TClass and not one
+ * of the data TClasses.
+ */
+MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1);
+
+/* tx_hdr_port_mid
+ * Destination local port for unicast packets.
+ * Destination multicast ID for multicast packets.
+ *
+ * Control packets are directed to a specific egress port, while data
+ * packets are transmitted through the CPU port (0) into the switch partition,
+ * where forwarding rules are applied.
+ */
+MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16);
+
+/* tx_hdr_fid
+ * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is
+ * set, otherwise calculated based on the packet's VID using VID to FID mapping.
+ * Valid for data packets only.
+ */
+MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16);
+
+/* tx_hdr_type
+ * 0 - Data packets
+ * 6 - Control packets
+ */
+MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4);
+
 #define MLXSW_TXHDR_LEN 0x10
 #define MLXSW_TXHDR_VERSION_0 0
 #define MLXSW_TXHDR_VERSION_1 1
diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig
index 831921b9d4d5..3ba527514f1e 100644
--- a/drivers/net/ethernet/meta/Kconfig
+++ b/drivers/net/ethernet/meta/Kconfig
@@ -27,6 +27,7 @@ config FBNIC
 	select NET_DEVLINK
 	select PAGE_POOL
 	select PHYLINK
+	select PLDMFW
 	help
 	  This driver supports Meta Platforms Host Network Interface.
 
diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile
index 239b2258ec65..0dbc634adb4b 100644
--- a/drivers/net/ethernet/meta/fbnic/Makefile
+++ b/drivers/net/ethernet/meta/fbnic/Makefile
@@ -20,6 +20,7 @@ fbnic-y := fbnic_csr.o \
 	   fbnic_pci.o \
 	   fbnic_phylink.o \
 	   fbnic_rpc.o \
+	   fbnic_time.o \
 	   fbnic_tlv.o \
 	   fbnic_txrx.o \
-	   fbnic_time.o
+# End of objects
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 706ae6104c8e..65815d4f379e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -16,6 +16,11 @@
 #include "fbnic_mac.h"
 #include "fbnic_rpc.h"
 
+struct fbnic_napi_vector;
+
+#define FBNIC_MAX_NAPI_VECTORS		128u
+#define FBNIC_MBX_CMPL_SLOTS		4
+
 struct fbnic_dev {
 	struct device *dev;
 	struct net_device *netdev;
@@ -29,11 +34,16 @@ struct fbnic_dev {
 	unsigned int pcs_msix_vector;
 	unsigned short num_irqs;
 
+	struct {
+		u8 users;
+		char name[IFNAMSIZ + 9];
+	} napi_irq[FBNIC_MAX_NAPI_VECTORS];
+
 	struct delayed_work service_task;
 
 	struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES];
 	struct fbnic_fw_cap fw_cap;
-	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_fw_completion *cmpl_data[FBNIC_MBX_CMPL_SLOTS];
 	/* Lock protecting Tx Mailbox queue to prevent possible races */
 	spinlock_t fw_tx_lock;
 
@@ -51,6 +61,12 @@ struct fbnic_dev {
 	u8 mac_addr_boundary;
 	u8 tce_tcam_last;
 
+	/* IP TCAM */
+	struct fbnic_ip_addr ip_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ip_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+
 	/* Number of TCQs/RCQs available on hardware */
 	u16 max_num_queues;
 
@@ -66,6 +82,9 @@ struct fbnic_dev {
 
 	/* Local copy of hardware statistics */
 	struct fbnic_hw_stats hw_stats;
+
+	/* Lock protecting access to hw_stats */
+	spinlock_t hw_stats_lock;
 };
 
 /* Reserve entry 0 in the MSI-X "others" array until we have filled all
@@ -139,15 +158,21 @@ struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev);
 void fbnic_devlink_register(struct fbnic_dev *fbd);
 void fbnic_devlink_unregister(struct fbnic_dev *fbd);
 
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd);
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd);
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd);
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd);
 
 void fbnic_hwmon_register(struct fbnic_dev *fbd);
 void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
 
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd);
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd);
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd);
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd);
 
+void fbnic_napi_name_irqs(struct fbnic_dev *fbd);
+int fbnic_napi_request_irq(struct fbnic_dev *fbd,
+			   struct fbnic_napi_vector *nv);
+void fbnic_napi_free_irq(struct fbnic_dev *fbd,
+			 struct fbnic_napi_vector *nv);
+void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr);
 int fbnic_request_irq(struct fbnic_dev *dev, int nr, irq_handler_t handler,
 		      unsigned long flags, const char *name, void *data);
 void fbnic_free_irq(struct fbnic_dev *dev, int nr, void *data);
@@ -165,6 +190,9 @@ void fbnic_dbg_exit(void);
 void fbnic_csr_get_regs(struct fbnic_dev *fbd, u32 *data, u32 *regs_version);
 int fbnic_csr_regs_len(struct fbnic_dev *fbd);
 
+void fbnic_config_txrx_usecs(struct fbnic_napi_vector *nv, u32 arm);
+void fbnic_config_rx_frames(struct fbnic_napi_vector *nv);
+
 enum fbnic_boards {
 	fbnic_board_asic
 };
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
index 2118901b25e9..d9c0dc1c2af9 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
@@ -30,6 +30,7 @@ static const struct fbnic_csr_bounds fbnic_csr_sects[] = {
 	FBNIC_BOUNDS(RSFEC),
 	FBNIC_BOUNDS(MAC_MAC),
 	FBNIC_BOUNDS(SIG),
+	FBNIC_BOUNDS(PCIE_SS_COMPHY),
 	FBNIC_BOUNDS(PUL_USER),
 	FBNIC_BOUNDS(QUEUE),
 	FBNIC_BOUNDS(RPC_RAM),
@@ -64,7 +65,7 @@ static void fbnic_csr_get_regs_rpc_ram(struct fbnic_dev *fbd, u32 **data_p)
 	u32 i, j;
 
 	*(data++) = start;
-	*(data++) = end - 1;
+	*(data++) = end;
 
 	/* FBNIC_RPC_TCAM_ACT */
 	for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) {
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 02bb81b3c506..36393a17d92d 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -397,6 +397,15 @@ enum {
 #define FBNIC_TCE_DROP_CTRL_TTI_FRM_DROP_EN	CSR_BIT(1)
 #define FBNIC_TCE_DROP_CTRL_TTI_TBI_DROP_EN	CSR_BIT(2)
 
+#define FBNIC_TCE_TTI_CM_DROP_PKTS	0x0403e		/* 0x100f8 */
+#define FBNIC_TCE_TTI_CM_DROP_BYTE_L	0x0403f		/* 0x100fc */
+#define FBNIC_TCE_TTI_CM_DROP_BYTE_H	0x04040		/* 0x10100 */
+#define FBNIC_TCE_TTI_FRAME_DROP_PKTS	0x04041		/* 0x10104 */
+#define FBNIC_TCE_TTI_FRAME_DROP_BYTE_L	0x04042		/* 0x10108 */
+#define FBNIC_TCE_TTI_FRAME_DROP_BYTE_H	0x04043		/* 0x1010c */
+#define FBNIC_TCE_TBI_DROP_PKTS		0x04044		/* 0x10110 */
+#define FBNIC_TCE_TBI_DROP_BYTE_L	0x04045		/* 0x10114 */
+
 #define FBNIC_TCE_TCAM_IDX2DEST_MAP	0x0404A		/* 0x10128 */
 #define FBNIC_TCE_TCAM_IDX2DEST_MAP_DEST_ID_0	CSR_GENMASK(3, 0)
 enum {
@@ -432,6 +441,11 @@ enum {
 #define FBNIC_TMI_SOP_PROT_CTRL		0x04400		/* 0x11000 */
 #define FBNIC_TMI_DROP_CTRL		0x04401		/* 0x11004 */
 #define FBNIC_TMI_DROP_CTRL_EN			CSR_BIT(0)
+#define FBNIC_TMI_DROP_PKTS		0x04402		/* 0x11008 */
+#define FBNIC_TMI_DROP_BYTE_L		0x04403		/* 0x1100c */
+#define FBNIC_TMI_ILLEGAL_PTP_REQS	0x04409		/* 0x11024 */
+#define FBNIC_TMI_GOOD_PTP_TS		0x0440a		/* 0x11028 */
+#define FBNIC_TMI_BAD_PTP_TS		0x0440b		/* 0x1102c */
 #define FBNIC_CSR_END_TMI		0x0443f	/* CSR section delimiter */
 
 /* Precision Time Protocol Registers */
@@ -485,6 +499,14 @@ enum {
 	FBNIC_RXB_FIFO_INDICES		= 8
 };
 
+enum {
+	FBNIC_RXB_INTF_NET = 0,
+	FBNIC_RXB_INTF_RBT = 1,
+	/* Unused */
+	/* Unused */
+	FBNIC_RXB_INTF_INDICES	= 4
+};
+
 #define FBNIC_RXB_CT_SIZE(n)		(0x08000 + (n))	/* 0x20000 + 4*n */
 #define FBNIC_RXB_CT_SIZE_CNT			8
 #define FBNIC_RXB_CT_SIZE_HEADER		CSR_GENMASK(5, 0)
@@ -605,8 +627,11 @@ enum {
 	FBNIC_RPC_ACT_TBL0_DEST_EI	= 4,
 };
 
+#define FBNIC_RPC_ACT_TBL0_Q_SEL		CSR_BIT(4)
+#define FBNIC_RPC_ACT_TBL0_Q_ID			CSR_GENMASK(15, 8)
 #define FBNIC_RPC_ACT_TBL0_DMA_HINT		CSR_GENMASK(24, 16)
 #define FBNIC_RPC_ACT_TBL0_TS_ENA		CSR_BIT(28)
+#define FBNIC_RPC_ACT_TBL0_ACT_TBL_IDX		CSR_BIT(29)
 #define FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID		CSR_BIT(30)
 
 #define FBNIC_RPC_ACT_TBL1_DEFAULT	0x0840b		/* 0x2102c */
@@ -677,6 +702,9 @@ enum {
 
 #define FBNIC_RPC_TCAM_OUTER_IPSRC(m, n)\
 	(0x08c00 + 0x08 * (n) + (m))		/* 0x023000 + 32*n + 4*m */
+#define FBNIC_RPC_TCAM_IP_ADDR_VALUE		CSR_GENMASK(15, 0)
+#define FBNIC_RPC_TCAM_IP_ADDR_MASK		CSR_GENMASK(31, 16)
+
 #define FBNIC_RPC_TCAM_OUTER_IPDST(m, n)\
 	(0x08c48 + 0x08 * (n) + (m))		/* 0x023120 + 32*n + 4*m */
 #define FBNIC_RPC_TCAM_IPSRC(m, n)\
@@ -782,13 +810,54 @@ enum {
 #define FBNIC_MAC_STAT_TX_MULTICAST_H	0x11a4b		/* 0x4692c */
 #define FBNIC_MAC_STAT_TX_BROADCAST_L	0x11a4c		/* 0x46930 */
 #define FBNIC_MAC_STAT_TX_BROADCAST_H	0x11a4d		/* 0x46934 */
+
+/* PCIE Comphy Registers */
+#define FBNIC_CSR_START_PCIE_SS_COMPHY	0x2442e /* CSR section delimiter */
+#define FBNIC_CSR_END_PCIE_SS_COMPHY	0x279d7	/* CSR section delimiter */
+
 /* PUL User Registers */
 #define FBNIC_CSR_START_PUL_USER	0x31000	/* CSR section delimiter */
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG	0x3103d		/* 0xc40f4 */
+#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME		CSR_BIT(18)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG	0x3103e		/* 0xc40f8 */
+#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME		CSR_BIT(18)
-#define FBNIC_CSR_END_PUL_USER	0x31080	/* CSR section delimiter */
+#define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
+					0x3106e		/* 0xc41b8 */
+#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_31_0 \
+					0x31070		/* 0xc41c0 */
+#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_63_32 \
+					0x31071		/* 0xc41c4 */
+#define FBNIC_PUL_USER_OB_WR_TLP_CNT_31_0 \
+					0x31072		/* 0xc41c8 */
+#define FBNIC_PUL_USER_OB_WR_TLP_CNT_63_32 \
+					0x31073		/* 0xc41cc */
+#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_31_0 \
+					0x31074		/* 0xc41d0 */
+#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_63_32 \
+					0x31075		/* 0xc41d4 */
+#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_31_0 \
+					0x31076		/* 0xc41d8 */
+#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_63_32 \
+					0x31077		/* 0xc41dc */
+#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_31_0 \
+					0x31078		/* 0xc41e0 */
+#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_63_32 \
+					0x31079		/* 0xc41e4 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_31_0 \
+					0x3107a		/* 0xc41e8 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_63_32 \
+					0x3107b		/* 0xc41ec */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_31_0 \
+					0x3107c		/* 0xc41f0 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_63_32 \
+					0x3107d		/* 0xc41f4 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_31_0 \
+					0x3107e		/* 0xc41f8 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_63_32 \
+					0x3107f		/* 0xc41fc */
+#define FBNIC_CSR_END_PUL_USER	0x310ea	/* CSR section delimiter */
 
 /* Queue Registers
  *
@@ -819,6 +888,12 @@ enum {
 #define FBNIC_QUEUE_TWQ1_BAL		0x022		/* 0x088 */
 #define FBNIC_QUEUE_TWQ1_BAH		0x023		/* 0x08c */
 
+/* Tx Work Queue Statistics Registers */
+#define FBNIC_QUEUE_TWQ0_PKT_CNT	0x062		/* 0x188 */
+#define FBNIC_QUEUE_TWQ0_ERR_CNT	0x063		/* 0x18c */
+#define FBNIC_QUEUE_TWQ1_PKT_CNT	0x072		/* 0x1c8 */
+#define FBNIC_QUEUE_TWQ1_ERR_CNT	0x073		/* 0x1cc */
+
 /* Tx Completion Queue Registers */
 #define FBNIC_QUEUE_TCQ_CTL		0x080		/* 0x200 */
 #define FBNIC_QUEUE_TCQ_CTL_RESET		CSR_BIT(0)
@@ -908,6 +983,12 @@ enum {
 	FBNIC_QUEUE_RDE_CTL1_PAYLD_PACK_RSS	= 2,
 };
 
+/* Rx Per CQ Statistics Counters */
+#define FBNIC_QUEUE_RDE_PKT_CNT		0x2a2		/* 0xa88 */
+#define FBNIC_QUEUE_RDE_PKT_ERR_CNT	0x2a3		/* 0xa8c */
+#define FBNIC_QUEUE_RDE_CQ_DROP_CNT	0x2a4		/* 0xa90 */
+#define FBNIC_QUEUE_RDE_BDQ_DROP_CNT	0x2a5		/* 0xa94 */
+
 /* Rx Interrupt Manager Registers */
 #define FBNIC_QUEUE_RIM_CTL		0x2c0		/* 0xb00 */
 #define FBNIC_QUEUE_RIM_CTL_MSIX_MASK		CSR_GENMASK(7, 0)
@@ -928,43 +1009,6 @@ enum {
 #define FBNIC_MAX_QUEUES		128
 #define FBNIC_CSR_END_QUEUE	(0x40000 + 0x400 * FBNIC_MAX_QUEUES - 1)
 
-/* PUL User Registers*/
-#define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
-					0x3106e		/* 0xc41b8 */
-#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_31_0 \
-					0x31070		/* 0xc41c0 */
-#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_63_32 \
-					0x31071		/* 0xc41c4 */
-#define FBNIC_PUL_USER_OB_WR_TLP_CNT_31_0 \
-					0x31072		/* 0xc41c8 */
-#define FBNIC_PUL_USER_OB_WR_TLP_CNT_63_32 \
-					0x31073		/* 0xc41cc */
-#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_31_0 \
-					0x31074		/* 0xc41d0 */
-#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_63_32 \
-					0x31075		/* 0xc41d4 */
-#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_31_0 \
-					0x31076		/* 0xc41d8 */
-#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_63_32 \
-					0x31077		/* 0xc41dc */
-#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_31_0 \
-					0x31078		/* 0xc41e0 */
-#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_63_32 \
-					0x31079		/* 0xc41e4 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_31_0 \
-					0x3107a		/* 0xc41e8 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_63_32 \
-					0x3107b		/* 0xc41ec */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_31_0 \
-					0x3107c		/* 0xc41f0 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_63_32 \
-					0x3107d		/* 0xc41f4 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_31_0 \
-					0x3107e		/* 0xc41f8 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_63_32 \
-					0x3107f		/* 0xc41fc */
-#define FBNIC_CSR_END_PUL_USER	0x31080	/* CSR section delimiter */
-
 /* BAR 4 CSRs */
 
 /* The IPC mailbox consists of 32 mailboxes, with each mailbox consisting
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
index 59951b5abdb7..e8f2d7f2d962 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
@@ -10,6 +10,166 @@
 
 static struct dentry *fbnic_dbg_root;
 
+static void fbnic_dbg_desc_break(struct seq_file *s, int i)
+{
+	while (i--)
+		seq_putc(s, '-');
+
+	seq_putc(s, '\n');
+}
+
+static int fbnic_dbg_mac_addr_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES; i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   i, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_mac_addr);
+
+static int fbnic_dbg_tce_tcam_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	int i, tcam_idx = 0;
+	char hdr[80];
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < ARRAY_SIZE(fbd->mac_addr); i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		/* Verify BMC bit is set */
+		if (!test_bit(FBNIC_MAC_ADDR_T_BMC, mac_addr->act_tcam))
+			continue;
+
+		if (tcam_idx == FBNIC_TCE_TCAM_NUM_ENTRIES)
+			break;
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   tcam_idx, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+		tcam_idx++;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_tce_tcam);
+
+static int fbnic_dbg_act_tcam_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-55s %-4s %s\n",
+		 "Idx", "S", "Value/Mask", "RSS", "Dest");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) {
+		struct fbnic_act_tcam *act_tcam = &fbd->act_tcam[i];
+
+		seq_printf(s, "%02d  %d %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x  %04x %08x\n",
+			   i, act_tcam->state,
+			   act_tcam->value.tcam[10], act_tcam->value.tcam[9],
+			   act_tcam->value.tcam[8], act_tcam->value.tcam[7],
+			   act_tcam->value.tcam[6], act_tcam->value.tcam[5],
+			   act_tcam->value.tcam[4], act_tcam->value.tcam[3],
+			   act_tcam->value.tcam[2], act_tcam->value.tcam[1],
+			   act_tcam->value.tcam[0], act_tcam->rss_en_mask,
+			   act_tcam->dest);
+		seq_printf(s, "      %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x\n",
+			   act_tcam->mask.tcam[10], act_tcam->mask.tcam[9],
+			   act_tcam->mask.tcam[8], act_tcam->mask.tcam[7],
+			   act_tcam->mask.tcam[6], act_tcam->mask.tcam[5],
+			   act_tcam->mask.tcam[4], act_tcam->mask.tcam[3],
+			   act_tcam->mask.tcam[2], act_tcam->mask.tcam[1],
+			   act_tcam->mask.tcam[0]);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_act_tcam);
+
+static int fbnic_dbg_ip_addr_show(struct seq_file *s,
+				  struct fbnic_ip_addr *ip_addr)
+{
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "V", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i++, ip_addr++) {
+		seq_printf(s, "%02d  %d %64pb %d %pi6\n",
+			   i, ip_addr->state, ip_addr->act_tcam,
+			   ip_addr->version, &ip_addr->value);
+		seq_printf(s, "                          %pi6\n",
+			   &ip_addr->mask);
+	}
+
+	return 0;
+}
+
+static int fbnic_dbg_ip_src_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ip_src);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_src);
+
+static int fbnic_dbg_ip_dst_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ip_dst);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_dst);
+
+static int fbnic_dbg_ipo_src_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ipo_src);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_src);
+
+static int fbnic_dbg_ipo_dst_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ipo_dst);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_dst);
+
 static int fbnic_dbg_pcie_stats_show(struct seq_file *s, void *v)
 {
 	struct fbnic_dev *fbd = s->private;
@@ -48,6 +208,20 @@ void fbnic_dbg_fbd_init(struct fbnic_dev *fbd)
 	fbd->dbg_fbd = debugfs_create_dir(name, fbnic_dbg_root);
 	debugfs_create_file("pcie_stats", 0400, fbd->dbg_fbd, fbd,
 			    &fbnic_dbg_pcie_stats_fops);
+	debugfs_create_file("mac_addr", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_mac_addr_fops);
+	debugfs_create_file("tce_tcam", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_tce_tcam_fops);
+	debugfs_create_file("act_tcam", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_act_tcam_fops);
+	debugfs_create_file("ip_src", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ip_src_fops);
+	debugfs_create_file("ip_dst", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ip_dst_fops);
+	debugfs_create_file("ipo_src", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ipo_src_fops);
+	debugfs_create_file("ipo_dst", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ipo_dst_fops);
 }
 
 void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
index 0072d612215e..4c4938eedd7b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
@@ -3,10 +3,12 @@
 
 #include <linux/unaligned.h>
 #include <linux/pci.h>
+#include <linux/pldmfw.h>
 #include <linux/types.h>
 #include <net/devlink.h>
 
 #include "fbnic.h"
+#include "fbnic_tlv.h"
 
 #define FBNIC_SN_STR_LEN	24
 
@@ -109,8 +111,262 @@ static int fbnic_devlink_info_get(struct devlink *devlink,
 	return 0;
 }
 
+static bool
+fbnic_pldm_match_record(struct pldmfw *context, struct pldmfw_record *record)
+{
+	struct pldmfw_desc_tlv *desc;
+	u32 anti_rollback_ver = 0;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+	struct pci_dev *pdev;
+
+	/* First, use the standard PCI matching function */
+	if (!pldmfw_op_pci_match_record(context, record))
+		return false;
+
+	pdev = to_pci_dev(context->dev);
+	fbd = pci_get_drvdata(pdev);
+	devlink = priv_to_devlink(fbd);
+
+	/* If PCI match is successful, check for vendor-specific descriptors */
+	list_for_each_entry(desc, &record->descs, entry) {
+		if (desc->type != PLDM_DESC_ID_VENDOR_DEFINED)
+			continue;
+
+		if (desc->size < 21 || desc->data[0] != 1 ||
+		    desc->data[1] != 15)
+			continue;
+
+		if (memcmp(desc->data + 2, "AntiRollbackVer", 15) != 0)
+			continue;
+
+		anti_rollback_ver = get_unaligned_le32(desc->data + 17);
+		break;
+	}
+
+	/* Compare versions and return error if they do not match */
+	if (anti_rollback_ver < fbd->fw_cap.anti_rollback_version) {
+		char buf[128];
+
+		snprintf(buf, sizeof(buf),
+			 "New firmware anti-rollback version (0x%x) is older than device version (0x%x)!",
+			 anti_rollback_ver, fbd->fw_cap.anti_rollback_version);
+		devlink_flash_update_status_notify(devlink, buf,
+						   "Anti-Rollback", 0, 0);
+
+		return false;
+	}
+
+	return true;
+}
+
+static int
+fbnic_flash_start(struct fbnic_dev *fbd, struct pldmfw_component *component)
+{
+	struct fbnic_fw_completion *cmpl;
+	int err;
+
+	cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ);
+	if (!cmpl)
+		return -ENOMEM;
+
+	err = fbnic_fw_xmit_fw_start_upgrade(fbd, cmpl,
+					     component->identifier,
+					     component->component_size);
+	if (err)
+		goto cmpl_free;
+
+	/* Wait for firmware to ack firmware upgrade start */
+	if (wait_for_completion_timeout(&cmpl->done, 10 * HZ))
+		err = cmpl->result;
+	else
+		err = -ETIMEDOUT;
+
+	fbnic_fw_clear_cmpl(fbd, cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(cmpl);
+
+	return err;
+}
+
+static int
+fbnic_flash_component(struct pldmfw *context,
+		      struct pldmfw_component *component)
+{
+	const u8 *data = component->component_data;
+	const u32 size = component->component_size;
+	struct fbnic_fw_completion *cmpl;
+	const char *component_name;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+	struct pci_dev *pdev;
+	u32 offset = 0;
+	u32 length = 0;
+	char buf[32];
+	int err;
+
+	pdev = to_pci_dev(context->dev);
+	fbd = pci_get_drvdata(pdev);
+	devlink = priv_to_devlink(fbd);
+
+	switch (component->identifier) {
+	case QSPI_SECTION_CMRT:
+		component_name = "boot1";
+		break;
+	case QSPI_SECTION_CONTROL_FW:
+		component_name = "boot2";
+		break;
+	case QSPI_SECTION_OPTION_ROM:
+		component_name = "option-rom";
+		break;
+	default:
+		snprintf(buf, sizeof(buf), "Unknown component ID %u!",
+			 component->identifier);
+		devlink_flash_update_status_notify(devlink, buf, NULL, 0,
+						   size);
+		return -EINVAL;
+	}
+
+	/* Once firmware receives the request to start upgrading it responds
+	 * with two messages:
+	 * 1. An ACK that it received the message and possible error code
+	 *    indicating that an upgrade is not currently possible.
+	 * 2. A request for the first chunk of data
+	 *
+	 * Setup completions for write before issuing the start message so
+	 * the driver can catch both messages.
+	 */
+	cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ);
+	if (!cmpl)
+		return -ENOMEM;
+
+	err = fbnic_mbx_set_cmpl(fbd, cmpl);
+	if (err)
+		goto cmpl_free;
+
+	devlink_flash_update_timeout_notify(devlink, "Initializing",
+					    component_name, 15);
+	err = fbnic_flash_start(fbd, component);
+	if (err)
+		goto err_no_msg;
+
+	while (offset < size) {
+		if (!wait_for_completion_timeout(&cmpl->done, 15 * HZ)) {
+			err = -ETIMEDOUT;
+			break;
+		}
+
+		err = cmpl->result;
+		if (err)
+			break;
+
+		/* Verify firmware is requesting the next chunk in the seq. */
+		if (cmpl->u.fw_update.offset != offset + length) {
+			err = -EFAULT;
+			break;
+		}
+
+		offset = cmpl->u.fw_update.offset;
+		length = cmpl->u.fw_update.length;
+
+		if (length > TLV_MAX_DATA || offset + length > size) {
+			err = -EFAULT;
+			break;
+		}
+
+		devlink_flash_update_status_notify(devlink, "Flashing",
+						   component_name,
+						   offset, size);
+
+		/* Mailbox will set length to 0 once it receives the finish
+		 * message.
+		 */
+		if (!length)
+			continue;
+
+		reinit_completion(&cmpl->done);
+		err = fbnic_fw_xmit_fw_write_chunk(fbd, data, offset, length,
+						   0);
+		if (err)
+			break;
+	}
+
+	if (err) {
+		fbnic_fw_xmit_fw_write_chunk(fbd, NULL, 0, 0, err);
+err_no_msg:
+		snprintf(buf, sizeof(buf), "Mailbox encountered error %d!",
+			 err);
+		devlink_flash_update_status_notify(devlink, buf,
+						   component_name, 0, 0);
+	}
+
+	fbnic_fw_clear_cmpl(fbd, cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(cmpl);
+
+	return err;
+}
+
+static const struct pldmfw_ops fbnic_pldmfw_ops = {
+	.match_record = fbnic_pldm_match_record,
+	.flash_component = fbnic_flash_component,
+};
+
+static int
+fbnic_devlink_flash_update(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_priv(devlink);
+	const struct firmware *fw = params->fw;
+	struct device *dev = fbd->dev;
+	struct pldmfw context;
+	char *err_msg;
+	int err;
+
+	context.ops = &fbnic_pldmfw_ops;
+	context.dev = dev;
+
+	err = pldmfw_flash_image(&context, fw);
+	if (err) {
+		switch (err) {
+		case -EINVAL:
+			err_msg = "Invalid image";
+			break;
+		case -EOPNOTSUPP:
+			err_msg = "Unsupported image";
+			break;
+		case -ENOMEM:
+			err_msg = "Out of memory";
+			break;
+		case -EFAULT:
+			err_msg = "Invalid header";
+			break;
+		case -ENOENT:
+			err_msg = "No matching record";
+			break;
+		case -ENODEV:
+			err_msg = "No matching device";
+			break;
+		case -ETIMEDOUT:
+			err_msg = "Timed out waiting for reply";
+			break;
+		default:
+			err_msg = "Unknown error";
+			break;
+		}
+
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Failed to flash PLDM Image: %s (error: %d)",
+				       err_msg, err);
+	}
+
+	return err;
+}
+
 static const struct devlink_ops fbnic_devlink_ops = {
-	.info_get = fbnic_devlink_info_get,
+	.info_get	= fbnic_devlink_info_get,
+	.flash_update	= fbnic_devlink_flash_update,
 };
 
 void fbnic_devlink_free(struct fbnic_dev *fbd)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index cc8ca94529ca..5c7556c8c4c5 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -4,6 +4,7 @@
 #include <linux/ethtool.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <net/ipv6.h>
 
 #include "fbnic.h"
 #include "fbnic_netdev.h"
@@ -26,6 +27,19 @@ struct fbnic_stat {
 	FBNIC_STAT_FIELDS(fbnic_hw_stats, name, stat)
 
 static const struct fbnic_stat fbnic_gstrings_hw_stats[] = {
+	/* TTI */
+	FBNIC_HW_STAT("tti_cm_drop_frames", tti.cm_drop.frames),
+	FBNIC_HW_STAT("tti_cm_drop_bytes", tti.cm_drop.bytes),
+	FBNIC_HW_STAT("tti_frame_drop_frames", tti.frame_drop.frames),
+	FBNIC_HW_STAT("tti_frame_drop_bytes", tti.frame_drop.bytes),
+	FBNIC_HW_STAT("tti_tbi_drop_frames", tti.tbi_drop.frames),
+	FBNIC_HW_STAT("tti_tbi_drop_bytes", tti.tbi_drop.bytes),
+
+	/* TMI */
+	FBNIC_HW_STAT("ptp_illegal_req", tmi.ptp_illegal_req),
+	FBNIC_HW_STAT("ptp_good_ts", tmi.ptp_good_ts),
+	FBNIC_HW_STAT("ptp_bad_ts", tmi.ptp_bad_ts),
+
 	/* RPC */
 	FBNIC_HW_STAT("rpc_unkn_etype", rpc.unkn_etype),
 	FBNIC_HW_STAT("rpc_unkn_ext_hdr", rpc.unkn_ext_hdr),
@@ -38,36 +52,64 @@ static const struct fbnic_stat fbnic_gstrings_hw_stats[] = {
 };
 
 #define FBNIC_HW_FIXED_STATS_LEN ARRAY_SIZE(fbnic_gstrings_hw_stats)
-#define FBNIC_HW_STATS_LEN	FBNIC_HW_FIXED_STATS_LEN
 
-static int
-fbnic_get_ts_info(struct net_device *netdev,
-		  struct kernel_ethtool_ts_info *tsinfo)
-{
-	struct fbnic_net *fbn = netdev_priv(netdev);
+#define FBNIC_RXB_ENQUEUE_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_enqueue_stats, name, stat)
 
-	tsinfo->phc_index = ptp_clock_index(fbn->fbd->ptp);
+static const struct fbnic_stat fbnic_gstrings_rxb_enqueue_stats[] = {
+	FBNIC_RXB_ENQUEUE_STAT("rxb_integrity_err%u", integrity_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_mac_err%u", mac_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_parser_err%u", parser_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_frm_err%u", frm_err),
 
-	tsinfo->so_timestamping =
-		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_TX_HARDWARE |
-		SOF_TIMESTAMPING_RX_HARDWARE |
-		SOF_TIMESTAMPING_RAW_HARDWARE;
+	FBNIC_RXB_ENQUEUE_STAT("rxb_drbo%u_frames", drbo.frames),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_drbo%u_bytes", drbo.bytes),
+};
 
-	tsinfo->tx_types =
-		BIT(HWTSTAMP_TX_OFF) |
-		BIT(HWTSTAMP_TX_ON);
+#define FBNIC_HW_RXB_ENQUEUE_STATS_LEN \
+	ARRAY_SIZE(fbnic_gstrings_rxb_enqueue_stats)
 
-	tsinfo->rx_filters =
-		BIT(HWTSTAMP_FILTER_NONE) |
-		BIT(HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
-		BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
-		BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
-		BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) |
-		BIT(HWTSTAMP_FILTER_ALL);
+#define FBNIC_RXB_FIFO_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_fifo_stats, name, stat)
 
-	return 0;
-}
+static const struct fbnic_stat fbnic_gstrings_rxb_fifo_stats[] = {
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_drop", trans_drop),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_dropped_frames", drop.frames),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_ecn", trans_ecn),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_level", level),
+};
+
+#define FBNIC_HW_RXB_FIFO_STATS_LEN ARRAY_SIZE(fbnic_gstrings_rxb_fifo_stats)
+
+#define FBNIC_RXB_DEQUEUE_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_dequeue_stats, name, stat)
+
+static const struct fbnic_stat fbnic_gstrings_rxb_dequeue_stats[] = {
+	FBNIC_RXB_DEQUEUE_STAT("rxb_intf%u_frames", intf.frames),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_intf%u_bytes", intf.bytes),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_pbuf%u_frames", pbuf.frames),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_pbuf%u_bytes", pbuf.bytes),
+};
+
+#define FBNIC_HW_RXB_DEQUEUE_STATS_LEN \
+	ARRAY_SIZE(fbnic_gstrings_rxb_dequeue_stats)
+
+#define FBNIC_HW_Q_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_hw_q_stats, name, stat.value)
+
+static const struct fbnic_stat fbnic_gstrings_hw_q_stats[] = {
+	FBNIC_HW_Q_STAT("rde_%u_pkt_err", rde_pkt_err),
+	FBNIC_HW_Q_STAT("rde_%u_pkt_cq_drop", rde_pkt_cq_drop),
+	FBNIC_HW_Q_STAT("rde_%u_pkt_bdq_drop", rde_pkt_bdq_drop),
+};
+
+#define FBNIC_HW_Q_STATS_LEN ARRAY_SIZE(fbnic_gstrings_hw_q_stats)
+#define FBNIC_HW_STATS_LEN \
+	(FBNIC_HW_FIXED_STATS_LEN + \
+	 FBNIC_HW_RXB_ENQUEUE_STATS_LEN * FBNIC_RXB_ENQUEUE_INDICES + \
+	 FBNIC_HW_RXB_FIFO_STATS_LEN * FBNIC_RXB_FIFO_INDICES + \
+	 FBNIC_HW_RXB_DEQUEUE_STATS_LEN * FBNIC_RXB_DEQUEUE_INDICES + \
+	 FBNIC_HW_Q_STATS_LEN * FBNIC_MAX_QUEUES)
 
 static void
 fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
@@ -79,24 +121,374 @@ fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 				    sizeof(drvinfo->fw_version));
 }
 
-static void fbnic_set_counter(u64 *stat, struct fbnic_stat_counter *counter)
+static int fbnic_get_regs_len(struct net_device *netdev)
 {
-	if (counter->reported)
-		*stat = counter->value;
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	return fbnic_csr_regs_len(fbn->fbd) * sizeof(u32);
 }
 
-static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data)
+static void fbnic_get_regs(struct net_device *netdev,
+			   struct ethtool_regs *regs, void *data)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	fbnic_csr_get_regs(fbn->fbd, data, &regs->version);
+}
+
+static struct fbnic_net *fbnic_clone_create(struct fbnic_net *orig)
+{
+	struct fbnic_net *clone;
+
+	clone = kmemdup(orig, sizeof(*orig), GFP_KERNEL);
+	if (!clone)
+		return NULL;
+
+	memset(clone->tx, 0, sizeof(clone->tx));
+	memset(clone->rx, 0, sizeof(clone->rx));
+	memset(clone->napi, 0, sizeof(clone->napi));
+	return clone;
+}
+
+static void fbnic_clone_swap_cfg(struct fbnic_net *orig,
+				 struct fbnic_net *clone)
+{
+	swap(clone->rcq_size, orig->rcq_size);
+	swap(clone->hpq_size, orig->hpq_size);
+	swap(clone->ppq_size, orig->ppq_size);
+	swap(clone->txq_size, orig->txq_size);
+	swap(clone->num_rx_queues, orig->num_rx_queues);
+	swap(clone->num_tx_queues, orig->num_tx_queues);
+	swap(clone->num_napi, orig->num_napi);
+}
+
+static void fbnic_aggregate_vector_counters(struct fbnic_net *fbn,
+					    struct fbnic_napi_vector *nv)
+{
+	int i, j;
+
+	for (i = 0; i < nv->txt_count; i++) {
+		fbnic_aggregate_ring_tx_counters(fbn, &nv->qt[i].sub0);
+		fbnic_aggregate_ring_tx_counters(fbn, &nv->qt[i].sub1);
+		fbnic_aggregate_ring_tx_counters(fbn, &nv->qt[i].cmpl);
+	}
+
+	for (j = 0; j < nv->rxt_count; j++, i++) {
+		fbnic_aggregate_ring_rx_counters(fbn, &nv->qt[i].sub0);
+		fbnic_aggregate_ring_rx_counters(fbn, &nv->qt[i].sub1);
+		fbnic_aggregate_ring_rx_counters(fbn, &nv->qt[i].cmpl);
+	}
+}
+
+static void fbnic_clone_swap(struct fbnic_net *orig,
+			     struct fbnic_net *clone)
+{
+	struct fbnic_dev *fbd = orig->fbd;
+	unsigned int i;
+
+	for (i = 0; i < max(clone->num_napi, orig->num_napi); i++)
+		fbnic_synchronize_irq(fbd, FBNIC_NON_NAPI_VECTORS + i);
+	for (i = 0; i < orig->num_napi; i++)
+		fbnic_aggregate_vector_counters(orig, orig->napi[i]);
+
+	fbnic_clone_swap_cfg(orig, clone);
+
+	for (i = 0; i < ARRAY_SIZE(orig->napi); i++)
+		swap(clone->napi[i], orig->napi[i]);
+	for (i = 0; i < ARRAY_SIZE(orig->tx); i++)
+		swap(clone->tx[i], orig->tx[i]);
+	for (i = 0; i < ARRAY_SIZE(orig->rx); i++)
+		swap(clone->rx[i], orig->rx[i]);
+}
+
+static void fbnic_clone_free(struct fbnic_net *clone)
+{
+	kfree(clone);
+}
+
+static int fbnic_get_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	ec->tx_coalesce_usecs = fbn->tx_usecs;
+	ec->rx_coalesce_usecs = fbn->rx_usecs;
+	ec->rx_max_coalesced_frames = fbn->rx_max_frames;
+
+	return 0;
+}
+
+static int fbnic_set_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	/* Verify against hardware limits */
+	if (ec->rx_coalesce_usecs > FIELD_MAX(FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT)) {
+		NL_SET_ERR_MSG_MOD(extack, "rx_usecs is above device max");
+		return -EINVAL;
+	}
+	if (ec->tx_coalesce_usecs > FIELD_MAX(FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT)) {
+		NL_SET_ERR_MSG_MOD(extack, "tx_usecs is above device max");
+		return -EINVAL;
+	}
+	if (ec->rx_max_coalesced_frames >
+	    FIELD_MAX(FBNIC_QUEUE_RIM_THRESHOLD_RCD_MASK) /
+	    FBNIC_MIN_RXD_PER_FRAME) {
+		NL_SET_ERR_MSG_MOD(extack, "rx_frames is above device max");
+		return -EINVAL;
+	}
+
+	fbn->tx_usecs = ec->tx_coalesce_usecs;
+	fbn->rx_usecs = ec->rx_coalesce_usecs;
+	fbn->rx_max_frames = ec->rx_max_coalesced_frames;
+
+	if (netif_running(netdev)) {
+		int i;
+
+		for (i = 0; i < fbn->num_napi; i++) {
+			struct fbnic_napi_vector *nv = fbn->napi[i];
+
+			fbnic_config_txrx_usecs(nv, 0);
+			fbnic_config_rx_frames(nv);
+		}
+	}
+
+	return 0;
+}
+
+static void
+fbnic_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
+		    struct kernel_ethtool_ringparam *kernel_ring,
+		    struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	ring->rx_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->rx_mini_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->rx_jumbo_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->tx_max_pending = FBNIC_QUEUE_SIZE_MAX;
+
+	ring->rx_pending = fbn->rcq_size;
+	ring->rx_mini_pending = fbn->hpq_size;
+	ring->rx_jumbo_pending = fbn->ppq_size;
+	ring->tx_pending = fbn->txq_size;
+}
+
+static void fbnic_set_rings(struct fbnic_net *fbn,
+			    struct ethtool_ringparam *ring)
+{
+	fbn->rcq_size = ring->rx_pending;
+	fbn->hpq_size = ring->rx_mini_pending;
+	fbn->ppq_size = ring->rx_jumbo_pending;
+	fbn->txq_size = ring->tx_pending;
+}
+
+static int
+fbnic_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
+		    struct kernel_ethtool_ringparam *kernel_ring,
+		    struct netlink_ext_ack *extack)
+
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_net *clone;
+	int err;
+
+	ring->rx_pending	= roundup_pow_of_two(ring->rx_pending);
+	ring->rx_mini_pending	= roundup_pow_of_two(ring->rx_mini_pending);
+	ring->rx_jumbo_pending	= roundup_pow_of_two(ring->rx_jumbo_pending);
+	ring->tx_pending	= roundup_pow_of_two(ring->tx_pending);
+
+	/* These are absolute minimums allowing the device and driver to operate
+	 * but not necessarily guarantee reasonable performance. Settings below
+	 * Rx queue size of 128 and BDQs smaller than 64 are likely suboptimal
+	 * at best.
+	 */
+	if (ring->rx_pending < max(FBNIC_QUEUE_SIZE_MIN, FBNIC_RX_DESC_MIN) ||
+	    ring->rx_mini_pending < FBNIC_QUEUE_SIZE_MIN ||
+	    ring->rx_jumbo_pending < FBNIC_QUEUE_SIZE_MIN ||
+	    ring->tx_pending < max(FBNIC_QUEUE_SIZE_MIN, FBNIC_TX_DESC_MIN)) {
+		NL_SET_ERR_MSG_MOD(extack, "requested ring size too small");
+		return -EINVAL;
+	}
+
+	if (!netif_running(netdev)) {
+		fbnic_set_rings(fbn, ring);
+		return 0;
+	}
+
+	clone = fbnic_clone_create(fbn);
+	if (!clone)
+		return -ENOMEM;
+
+	fbnic_set_rings(clone, ring);
+
+	err = fbnic_alloc_napi_vectors(clone);
+	if (err)
+		goto err_free_clone;
+
+	err = fbnic_alloc_resources(clone);
+	if (err)
+		goto err_free_napis;
+
+	fbnic_down_noidle(fbn);
+	err = fbnic_wait_all_queues_idle(fbn->fbd, true);
+	if (err)
+		goto err_start_stack;
+
+	err = fbnic_set_netif_queues(clone);
+	if (err)
+		goto err_start_stack;
+
+	/* Nothing can fail past this point */
+	fbnic_flush(fbn);
+
+	fbnic_clone_swap(fbn, clone);
+
+	fbnic_up(fbn);
+
+	fbnic_free_resources(clone);
+	fbnic_free_napi_vectors(clone);
+	fbnic_clone_free(clone);
+
+	return 0;
+
+err_start_stack:
+	fbnic_flush(fbn);
+	fbnic_up(fbn);
+	fbnic_free_resources(clone);
+err_free_napis:
+	fbnic_free_napi_vectors(clone);
+err_free_clone:
+	fbnic_clone_free(clone);
+	return err;
+}
+
+static void fbnic_get_rxb_enqueue_strings(u8 **data, unsigned int idx)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	stat = fbnic_gstrings_rxb_enqueue_stats;
+	for (i = 0; i < FBNIC_HW_RXB_ENQUEUE_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_rxb_fifo_strings(u8 **data, unsigned int idx)
 {
+	const struct fbnic_stat *stat;
 	int i;
 
+	stat = fbnic_gstrings_rxb_fifo_stats;
+	for (i = 0; i < FBNIC_HW_RXB_FIFO_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_rxb_dequeue_strings(u8 **data, unsigned int idx)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	stat = fbnic_gstrings_rxb_dequeue_stats;
+	for (i = 0; i < FBNIC_HW_RXB_DEQUEUE_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data)
+{
+	const struct fbnic_stat *stat;
+	int i, idx;
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		for (i = 0; i < FBNIC_HW_STATS_LEN; i++)
+		for (i = 0; i < FBNIC_HW_FIXED_STATS_LEN; i++)
 			ethtool_puts(&data, fbnic_gstrings_hw_stats[i].string);
+
+		for (i = 0; i < FBNIC_RXB_ENQUEUE_INDICES; i++)
+			fbnic_get_rxb_enqueue_strings(&data, i);
+
+		for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+			fbnic_get_rxb_fifo_strings(&data, i);
+
+		for (i = 0; i < FBNIC_RXB_DEQUEUE_INDICES; i++)
+			fbnic_get_rxb_dequeue_strings(&data, i);
+
+		for (idx = 0; idx < FBNIC_MAX_QUEUES; idx++) {
+			stat = fbnic_gstrings_hw_q_stats;
+
+			for (i = 0; i < FBNIC_HW_Q_STATS_LEN; i++, stat++)
+				ethtool_sprintf(&data, stat->string, idx);
+		}
 		break;
 	}
 }
 
+static void fbnic_report_hw_stats(const struct fbnic_stat *stat,
+				  const void *base, int len, u64 **data)
+{
+	while (len--) {
+		u8 *curr = (u8 *)base + stat->offset;
+
+		**data = *(u64 *)curr;
+
+		stat++;
+		(*data)++;
+	}
+}
+
+static void fbnic_get_ethtool_stats(struct net_device *dev,
+				    struct ethtool_stats *stats, u64 *data)
+{
+	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_dev *fbd = fbn->fbd;
+	int i;
+
+	fbnic_get_hw_stats(fbn->fbd);
+
+	spin_lock(&fbd->hw_stats_lock);
+	fbnic_report_hw_stats(fbnic_gstrings_hw_stats, &fbd->hw_stats,
+			      FBNIC_HW_FIXED_STATS_LEN, &data);
+
+	for (i = 0; i < FBNIC_RXB_ENQUEUE_INDICES; i++) {
+		const struct fbnic_rxb_enqueue_stats *enq;
+
+		enq = &fbd->hw_stats.rxb.enq[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_enqueue_stats,
+				      enq, FBNIC_HW_RXB_ENQUEUE_STATS_LEN,
+				      &data);
+	}
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++) {
+		const struct fbnic_rxb_fifo_stats *fifo;
+
+		fifo = &fbd->hw_stats.rxb.fifo[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_fifo_stats,
+				      fifo, FBNIC_HW_RXB_FIFO_STATS_LEN,
+				      &data);
+	}
+
+	for (i = 0; i < FBNIC_RXB_DEQUEUE_INDICES; i++) {
+		const struct fbnic_rxb_dequeue_stats *deq;
+
+		deq = &fbd->hw_stats.rxb.deq[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_dequeue_stats,
+				      deq, FBNIC_HW_RXB_DEQUEUE_STATS_LEN,
+				      &data);
+	}
+
+	for (i  = 0; i < FBNIC_MAX_QUEUES; i++) {
+		const struct fbnic_hw_q_stats *hw_q = &fbd->hw_stats.hw_q[i];
+
+		fbnic_report_hw_stats(fbnic_gstrings_hw_q_stats, hw_q,
+				      FBNIC_HW_Q_STATS_LEN, &data);
+	}
+	spin_unlock(&fbd->hw_stats_lock);
+}
+
 static int fbnic_get_sset_count(struct net_device *dev, int sset)
 {
 	switch (sset) {
@@ -107,19 +499,1075 @@ static int fbnic_get_sset_count(struct net_device *dev, int sset)
 	}
 }
 
-static void fbnic_get_ethtool_stats(struct net_device *dev,
-				    struct ethtool_stats *stats, u64 *data)
+static int fbnic_get_rss_hash_idx(u32 flow_type)
+{
+	switch (flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) {
+	case TCP_V4_FLOW:
+		return FBNIC_TCP4_HASH_OPT;
+	case TCP_V6_FLOW:
+		return FBNIC_TCP6_HASH_OPT;
+	case UDP_V4_FLOW:
+		return FBNIC_UDP4_HASH_OPT;
+	case UDP_V6_FLOW:
+		return FBNIC_UDP6_HASH_OPT;
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case IPV4_FLOW:
+	case IPV4_USER_FLOW:
+		return FBNIC_IPV4_HASH_OPT;
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case IPV6_FLOW:
+	case IPV6_USER_FLOW:
+		return FBNIC_IPV6_HASH_OPT;
+	case ETHER_FLOW:
+		return FBNIC_ETHER_HASH_OPT;
+	}
+
+	return -1;
+}
+
+static int
+fbnic_get_rss_hash_opts(struct fbnic_net *fbn, struct ethtool_rxnfc *cmd)
+{
+	int hash_opt_idx = fbnic_get_rss_hash_idx(cmd->flow_type);
+
+	if (hash_opt_idx < 0)
+		return -EINVAL;
+
+	/* Report options from rss_en table in fbn */
+	cmd->data = fbn->rss_flow_hash[hash_opt_idx];
+
+	return 0;
+}
+
+static int fbnic_get_cls_rule_all(struct fbnic_net *fbn,
+				  struct ethtool_rxnfc *cmd,
+				  u32 *rule_locs)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int i, cnt = 0;
+
+	/* Report maximum rule count */
+	cmd->data = FBNIC_RPC_ACT_TBL_NFC_ENTRIES;
+
+	for (i = 0; i < FBNIC_RPC_ACT_TBL_NFC_ENTRIES; i++) {
+		int idx = i + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+		struct fbnic_act_tcam *act_tcam;
+
+		act_tcam = &fbd->act_tcam[idx];
+		if (act_tcam->state != FBNIC_TCAM_S_VALID)
+			continue;
+
+		if (rule_locs) {
+			if (cnt == cmd->rule_cnt)
+				return -EMSGSIZE;
+
+			rule_locs[cnt] = i;
+		}
+
+		cnt++;
+	}
+
+	return cnt;
+}
+
+static int fbnic_get_cls_rule(struct fbnic_net *fbn, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	int idx;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location >= FBNIC_RPC_ACT_TBL_NFC_ENTRIES)
+		return -EINVAL;
+
+	idx = fsp->location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	if (act_tcam->state != FBNIC_TCAM_S_VALID)
+		return -EINVAL;
+
+	/* Report maximum rule count */
+	cmd->data = FBNIC_RPC_ACT_TBL_NFC_ENTRIES;
+
+	/* Set flow type field */
+	if (!(act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_IP_VALID)) {
+		fsp->flow_type = ETHER_FLOW;
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+			       act_tcam->mask.tcam[1])) {
+			struct fbnic_mac_addr *mac_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+					act_tcam->value.tcam[1]);
+			mac_addr = &fbd->mac_addr[idx];
+
+			ether_addr_copy(fsp->h_u.ether_spec.h_dest,
+					mac_addr->value.addr8);
+			eth_broadcast_addr(fsp->m_u.ether_spec.h_dest);
+		}
+	} else if (act_tcam->value.tcam[1] &
+		   FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID) {
+		fsp->flow_type = IPV6_USER_FLOW;
+		fsp->h_u.usr_ip6_spec.l4_proto = IPPROTO_IPV6;
+		fsp->m_u.usr_ip6_spec.l4_proto = 0xff;
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ipo_src[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6src[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6src[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ipo_dst[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6dst[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6dst[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+	} else if ((act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_IP_IS_V6)) {
+		if (act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L4_VALID) {
+			if (act_tcam->value.tcam[1] &
+			    FBNIC_RPC_TCAM_ACT1_L4_IS_UDP)
+				fsp->flow_type = UDP_V6_FLOW;
+			else
+				fsp->flow_type = TCP_V6_FLOW;
+			fsp->h_u.tcp_ip6_spec.psrc =
+				cpu_to_be16(act_tcam->value.tcam[3]);
+			fsp->m_u.tcp_ip6_spec.psrc =
+				cpu_to_be16(~act_tcam->mask.tcam[3]);
+			fsp->h_u.tcp_ip6_spec.pdst =
+				cpu_to_be16(act_tcam->value.tcam[4]);
+			fsp->m_u.tcp_ip6_spec.pdst =
+				cpu_to_be16(~act_tcam->mask.tcam[4]);
+		} else {
+			fsp->flow_type = IPV6_USER_FLOW;
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_src[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6src[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6src[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_dst[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6dst[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6dst[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+	} else {
+		if (act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L4_VALID) {
+			if (act_tcam->value.tcam[1] &
+			    FBNIC_RPC_TCAM_ACT1_L4_IS_UDP)
+				fsp->flow_type = UDP_V4_FLOW;
+			else
+				fsp->flow_type = TCP_V4_FLOW;
+			fsp->h_u.tcp_ip4_spec.psrc =
+				cpu_to_be16(act_tcam->value.tcam[3]);
+			fsp->m_u.tcp_ip4_spec.psrc =
+				cpu_to_be16(~act_tcam->mask.tcam[3]);
+			fsp->h_u.tcp_ip4_spec.pdst =
+				cpu_to_be16(act_tcam->value.tcam[4]);
+			fsp->m_u.tcp_ip4_spec.pdst =
+				cpu_to_be16(~act_tcam->mask.tcam[4]);
+		} else {
+			fsp->flow_type = IPV4_USER_FLOW;
+			fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_src[idx];
+
+			fsp->h_u.usr_ip4_spec.ip4src =
+				ip_addr->value.s6_addr32[3];
+			fsp->m_u.usr_ip4_spec.ip4src =
+				~ip_addr->mask.s6_addr32[3];
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_dst[idx];
+
+			fsp->h_u.usr_ip4_spec.ip4dst =
+				ip_addr->value.s6_addr32[3];
+			fsp->m_u.usr_ip4_spec.ip4dst =
+				~ip_addr->mask.s6_addr32[3];
+		}
+	}
+
+	/* Record action */
+	if (act_tcam->dest & FBNIC_RPC_ACT_TBL0_DROP)
+		fsp->ring_cookie = RX_CLS_FLOW_DISC;
+	else if (act_tcam->dest & FBNIC_RPC_ACT_TBL0_Q_SEL)
+		fsp->ring_cookie = FIELD_GET(FBNIC_RPC_ACT_TBL0_Q_ID,
+					     act_tcam->dest);
+	else
+		fsp->flow_type |= FLOW_RSS;
+
+	cmd->rss_context = FIELD_GET(FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID,
+				     act_tcam->dest);
+
+	return 0;
+}
+
+static int fbnic_get_rxnfc(struct net_device *netdev,
+			   struct ethtool_rxnfc *cmd, u32 *rule_locs)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	int ret = -EOPNOTSUPP;
+	u32 special = 0;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = fbn->num_rx_queues;
+		ret = 0;
+		break;
+	case ETHTOOL_GRXFH:
+		ret = fbnic_get_rss_hash_opts(fbn, cmd);
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		ret = fbnic_get_cls_rule(fbn, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		rule_locs = NULL;
+		special = RX_CLS_LOC_SPECIAL;
+		fallthrough;
+	case ETHTOOL_GRXCLSRLALL:
+		ret = fbnic_get_cls_rule_all(fbn, cmd, rule_locs);
+		if (ret < 0)
+			break;
+
+		cmd->data |= special;
+		cmd->rule_cnt = ret;
+		ret = 0;
+		break;
+	}
+
+	return ret;
+}
+
+#define FBNIC_L2_HASH_OPTIONS \
+	(RXH_L2DA | RXH_DISCARD)
+#define FBNIC_L3_HASH_OPTIONS \
+	(FBNIC_L2_HASH_OPTIONS | RXH_IP_SRC | RXH_IP_DST)
+#define FBNIC_L4_HASH_OPTIONS \
+	(FBNIC_L3_HASH_OPTIONS | RXH_L4_B_0_1 | RXH_L4_B_2_3)
+
+static int
+fbnic_set_rss_hash_opts(struct fbnic_net *fbn, const struct ethtool_rxnfc *cmd)
+{
+	int hash_opt_idx;
+
+	/* Verify the type requested is correct */
+	hash_opt_idx = fbnic_get_rss_hash_idx(cmd->flow_type);
+	if (hash_opt_idx < 0)
+		return -EINVAL;
+
+	/* Verify the fields asked for can actually be assigned based on type */
+	if (cmd->data & ~FBNIC_L4_HASH_OPTIONS ||
+	    (hash_opt_idx > FBNIC_L4_HASH_OPT &&
+	     cmd->data & ~FBNIC_L3_HASH_OPTIONS) ||
+	    (hash_opt_idx > FBNIC_IP_HASH_OPT &&
+	     cmd->data & ~FBNIC_L2_HASH_OPTIONS))
+		return -EINVAL;
+
+	fbn->rss_flow_hash[hash_opt_idx] = cmd->data;
+
+	if (netif_running(fbn->netdev)) {
+		fbnic_rss_reinit(fbn->fbd, fbn);
+		fbnic_write_rules(fbn->fbd);
+	}
+
+	return 0;
+}
+
+static int fbnic_cls_rule_any_loc(struct fbnic_dev *fbd)
 {
-	struct fbnic_net *fbn = netdev_priv(dev);
-	const struct fbnic_stat *stat;
 	int i;
 
-	fbnic_get_hw_stats(fbn->fbd);
+	for (i = FBNIC_RPC_ACT_TBL_NFC_ENTRIES; i--;) {
+		int idx = i + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
 
-	for (i = 0; i < FBNIC_HW_STATS_LEN; i++) {
-		stat = &fbnic_gstrings_hw_stats[i];
-		data[i] = *(u64 *)((u8 *)&fbn->fbd->hw_stats + stat->offset);
+		if (fbd->act_tcam[idx].state != FBNIC_TCAM_S_VALID)
+			return i;
 	}
+
+	return -ENOSPC;
+}
+
+static int fbnic_set_cls_rule_ins(struct fbnic_net *fbn,
+				  const struct ethtool_rxnfc *cmd)
+{
+	u16 flow_value = 0, flow_mask = 0xffff, ip_value = 0, ip_mask = 0xffff;
+	u16 sport = 0, sport_mask = ~0, dport = 0, dport_mask = ~0;
+	u16 misc = 0, misc_mask = ~0;
+	u32 dest = FIELD_PREP(FBNIC_RPC_ACT_TBL0_DEST_MASK,
+			      FBNIC_RPC_ACT_TBL0_DEST_HOST);
+	struct fbnic_ip_addr *ip_src = NULL, *ip_dst = NULL;
+	struct fbnic_mac_addr *mac_addr = NULL;
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	struct in6_addr *addr6, *mask6;
+	struct in_addr *addr4, *mask4;
+	int hash_idx, location;
+	u32 flow_type;
+	int idx, j;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location != RX_CLS_LOC_ANY)
+		return -EINVAL;
+	location = fbnic_cls_rule_any_loc(fbd);
+	if (location < 0)
+		return location;
+
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		dest = FBNIC_RPC_ACT_TBL0_DROP;
+	} else if (fsp->flow_type & FLOW_RSS) {
+		if (cmd->rss_context == 1)
+			dest |= FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID;
+	} else {
+		u32 ring_idx = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+
+		if (ring_idx >= fbn->num_rx_queues)
+			return -EINVAL;
+
+		dest |= FBNIC_RPC_ACT_TBL0_Q_SEL |
+			FIELD_PREP(FBNIC_RPC_ACT_TBL0_Q_ID, ring_idx);
+	}
+
+	idx = location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	/* Do not allow overwriting for now.
+	 * To support overwriting rules we will need to add logic to free
+	 * any IP or MACDA TCAMs that may be associated with the old rule.
+	 */
+	if (act_tcam->state != FBNIC_TCAM_S_DISABLED)
+		return -EBUSY;
+
+	flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_RSS);
+	hash_idx = fbnic_get_rss_hash_idx(flow_type);
+
+	switch (flow_type) {
+	case UDP_V4_FLOW:
+udp4_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_IS_UDP;
+		fallthrough;
+	case TCP_V4_FLOW:
+tcp4_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_L4_IS_UDP |
+			       FBNIC_RPC_TCAM_ACT1_L4_VALID);
+
+		sport = be16_to_cpu(fsp->h_u.tcp_ip4_spec.psrc);
+		sport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip4_spec.psrc);
+		dport = be16_to_cpu(fsp->h_u.tcp_ip4_spec.pdst);
+		dport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip4_spec.pdst);
+		goto ip4_flow;
+	case IP_USER_FLOW:
+		if (!fsp->m_u.usr_ip4_spec.proto)
+			goto ip4_flow;
+		if (fsp->m_u.usr_ip4_spec.proto != 0xff)
+			return -EINVAL;
+		if (fsp->h_u.usr_ip4_spec.proto == IPPROTO_UDP)
+			goto udp4_flow;
+		if (fsp->h_u.usr_ip4_spec.proto == IPPROTO_TCP)
+			goto tcp4_flow;
+		return -EINVAL;
+ip4_flow:
+		addr4 = (struct in_addr *)&fsp->h_u.usr_ip4_spec.ip4src;
+		mask4 = (struct in_addr *)&fsp->m_u.usr_ip4_spec.ip4src;
+		if (mask4->s_addr) {
+			ip_src = __fbnic_ip4_sync(fbd, fbd->ip_src,
+						  addr4, mask4);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					       ip_src - fbd->ip_src);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				     FBNIC_RPC_TCAM_ACT0_IPSRC_IDX);
+		}
+
+		addr4 = (struct in_addr *)&fsp->h_u.usr_ip4_spec.ip4dst;
+		mask4 = (struct in_addr *)&fsp->m_u.usr_ip4_spec.ip4dst;
+		if (mask4->s_addr) {
+			ip_dst = __fbnic_ip4_sync(fbd, fbd->ip_dst,
+						  addr4, mask4);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					       ip_dst - fbd->ip_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				     FBNIC_RPC_TCAM_ACT0_IPDST_IDX);
+		}
+		flow_value |= FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			      FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			       FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			       FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID);
+		break;
+	case UDP_V6_FLOW:
+udp6_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_IS_UDP;
+		fallthrough;
+	case TCP_V6_FLOW:
+tcp6_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_L4_IS_UDP |
+			  FBNIC_RPC_TCAM_ACT1_L4_VALID);
+
+		sport = be16_to_cpu(fsp->h_u.tcp_ip6_spec.psrc);
+		sport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip6_spec.psrc);
+		dport = be16_to_cpu(fsp->h_u.tcp_ip6_spec.pdst);
+		dport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip6_spec.pdst);
+		goto ipv6_flow;
+	case IPV6_USER_FLOW:
+		if (!fsp->m_u.usr_ip6_spec.l4_proto)
+			goto ipv6_flow;
+
+		if (fsp->m_u.usr_ip6_spec.l4_proto != 0xff)
+			return -EINVAL;
+		if (fsp->h_u.usr_ip6_spec.l4_proto == IPPROTO_UDP)
+			goto udp6_flow;
+		if (fsp->h_u.usr_ip6_spec.l4_proto == IPPROTO_TCP)
+			goto tcp6_flow;
+		if (fsp->h_u.usr_ip6_spec.l4_proto != IPPROTO_IPV6)
+			return -EINVAL;
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6src;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6src;
+		if (!ipv6_addr_any(mask6)) {
+			ip_src = __fbnic_ip6_sync(fbd, fbd->ipo_src,
+						  addr6, mask6);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |=
+				FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+					   ip_src - fbd->ipo_src);
+			ip_mask &=
+				~(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+				  FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX);
+		}
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6dst;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6dst;
+		if (!ipv6_addr_any(mask6)) {
+			ip_dst = __fbnic_ip6_sync(fbd, fbd->ipo_dst,
+						  addr6, mask6);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |=
+				FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID |
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+					   ip_dst - fbd->ipo_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID |
+				     FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX);
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID;
+		flow_mask &= FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID;
+ipv6_flow:
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6src;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6src;
+		if (!ip_src && !ipv6_addr_any(mask6)) {
+			ip_src = __fbnic_ip6_sync(fbd, fbd->ip_src,
+						  addr6, mask6);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					       ip_src - fbd->ip_src);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				       FBNIC_RPC_TCAM_ACT0_IPSRC_IDX);
+		}
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6dst;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6dst;
+		if (!ip_dst && !ipv6_addr_any(mask6)) {
+			ip_dst = __fbnic_ip6_sync(fbd, fbd->ip_dst,
+						  addr6, mask6);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					       ip_dst - fbd->ip_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				       FBNIC_RPC_TCAM_ACT0_IPDST_IDX);
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			      FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			      FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			       FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			       FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID);
+		break;
+	case ETHER_FLOW:
+		if (!is_zero_ether_addr(fsp->m_u.ether_spec.h_dest)) {
+			u8 *addr = fsp->h_u.ether_spec.h_dest;
+			u8 *mask = fsp->m_u.ether_spec.h_dest;
+
+			/* Do not allow MAC addr of 0 */
+			if (is_zero_ether_addr(addr))
+				return -EINVAL;
+
+			/* Only support full MAC address to avoid
+			 * conflicts with other MAC addresses.
+			 */
+			if (!is_broadcast_ether_addr(mask))
+				return -EINVAL;
+
+			if (is_multicast_ether_addr(addr))
+				mac_addr = __fbnic_mc_sync(fbd, addr);
+			else
+				mac_addr = __fbnic_uc_sync(fbd, addr);
+
+			if (!mac_addr)
+				return -ENOSPC;
+
+			set_bit(idx, mac_addr->act_tcam);
+			flow_value |=
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+					   mac_addr - fbd->mac_addr);
+			flow_mask &= ~FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX;
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Write action table values */
+	act_tcam->dest = dest;
+	act_tcam->rss_en_mask = fbnic_flow_hash_2_rss_en_mask(fbn, hash_idx);
+
+	/* Write IP Match value/mask to action_tcam[0] */
+	act_tcam->value.tcam[0] = ip_value;
+	act_tcam->mask.tcam[0] = ip_mask;
+
+	/* Write flow type value/mask to action_tcam[1] */
+	act_tcam->value.tcam[1] = flow_value;
+	act_tcam->mask.tcam[1] = flow_mask;
+
+	/* Write error, DSCP, extra L4 matches to action_tcam[2] */
+	act_tcam->value.tcam[2] = misc;
+	act_tcam->mask.tcam[2] = misc_mask;
+
+	/* Write source/destination port values */
+	act_tcam->value.tcam[3] = sport;
+	act_tcam->mask.tcam[3] = sport_mask;
+	act_tcam->value.tcam[4] = dport;
+	act_tcam->mask.tcam[4] = dport_mask;
+
+	for (j = 5; j < FBNIC_RPC_TCAM_ACT_WORD_LEN; j++)
+		act_tcam->mask.tcam[j] = 0xffff;
+
+	act_tcam->state = FBNIC_TCAM_S_UPDATE;
+	fsp->location = location;
+
+	if (netif_running(fbn->netdev)) {
+		fbnic_write_rules(fbd);
+		if (ip_src || ip_dst)
+			fbnic_write_ip_addr(fbd);
+		if (mac_addr)
+			fbnic_write_macda(fbd);
+	}
+
+	return 0;
+}
+
+static void fbnic_clear_nfc_macda(struct fbnic_net *fbn,
+				  unsigned int tcam_idx)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->mac_addr); idx--;)
+		__fbnic_xc_unsync(&fbd->mac_addr[idx], tcam_idx);
+
+	/* Write updates to hardware */
+	if (netif_running(fbn->netdev))
+		fbnic_write_macda(fbd);
+}
+
+static void fbnic_clear_nfc_ip_addr(struct fbnic_net *fbn,
+				    unsigned int tcam_idx)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->ip_src); idx--;)
+		__fbnic_ip_unsync(&fbd->ip_src[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ip_dst); idx--;)
+		__fbnic_ip_unsync(&fbd->ip_dst[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ipo_src); idx--;)
+		__fbnic_ip_unsync(&fbd->ipo_src[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ipo_dst); idx--;)
+		__fbnic_ip_unsync(&fbd->ipo_dst[idx], tcam_idx);
+
+	/* Write updates to hardware */
+	if (netif_running(fbn->netdev))
+		fbnic_write_ip_addr(fbd);
+}
+
+static int fbnic_set_cls_rule_del(struct fbnic_net *fbn,
+				  const struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	int idx;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location >= FBNIC_RPC_ACT_TBL_NFC_ENTRIES)
+		return -EINVAL;
+
+	idx = fsp->location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	if (act_tcam->state != FBNIC_TCAM_S_VALID)
+		return -EINVAL;
+
+	act_tcam->state = FBNIC_TCAM_S_DELETE;
+
+	if ((act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID) &&
+	    (~act_tcam->mask.tcam[1] & FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX))
+		fbnic_clear_nfc_macda(fbn, idx);
+
+	if ((act_tcam->value.tcam[0] &
+	     (FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+	      FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID)) &&
+	    (~act_tcam->mask.tcam[0] &
+	     (FBNIC_RPC_TCAM_ACT0_IPSRC_IDX |
+	      FBNIC_RPC_TCAM_ACT0_IPDST_IDX |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX)))
+		fbnic_clear_nfc_ip_addr(fbn, idx);
+
+	if (netif_running(fbn->netdev))
+		fbnic_write_rules(fbd);
+
+	return 0;
+}
+
+static int fbnic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		ret = fbnic_set_rss_hash_opts(fbn, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLINS:
+		ret = fbnic_set_cls_rule_ins(fbn, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = fbnic_set_cls_rule_del(fbn, cmd);
+		break;
+	}
+
+	return ret;
+}
+
+static u32 fbnic_get_rxfh_key_size(struct net_device *netdev)
+{
+	return FBNIC_RPC_RSS_KEY_BYTE_LEN;
+}
+
+static u32 fbnic_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return FBNIC_RPC_RSS_TBL_SIZE;
+}
+
+static int
+fbnic_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	unsigned int i;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+
+	if (rxfh->key) {
+		for (i = 0; i < FBNIC_RPC_RSS_KEY_BYTE_LEN; i++) {
+			u32 rss_key = fbn->rss_key[i / 4] << ((i % 4) * 8);
+
+			rxfh->key[i] = rss_key >> 24;
+		}
+	}
+
+	if (rxfh->indir) {
+		for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++)
+			rxfh->indir[i] = fbn->indir_tbl[0][i];
+	}
+
+	return 0;
+}
+
+static unsigned int
+fbnic_set_indir(struct fbnic_net *fbn, unsigned int idx, const u32 *indir)
+{
+	unsigned int i, changes = 0;
+
+	for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++) {
+		if (fbn->indir_tbl[idx][i] == indir[i])
+			continue;
+
+		fbn->indir_tbl[idx][i] = indir[i];
+		changes++;
+	}
+
+	return changes;
+}
+
+static int
+fbnic_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+	       struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	unsigned int i, changes = 0;
+
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EINVAL;
+
+	if (rxfh->key) {
+		u32 rss_key = 0;
+
+		for (i = FBNIC_RPC_RSS_KEY_BYTE_LEN; i--;) {
+			rss_key >>= 8;
+			rss_key |= (u32)(rxfh->key[i]) << 24;
+
+			if (i % 4)
+				continue;
+
+			if (fbn->rss_key[i / 4] == rss_key)
+				continue;
+
+			fbn->rss_key[i / 4] = rss_key;
+			changes++;
+		}
+	}
+
+	if (rxfh->indir)
+		changes += fbnic_set_indir(fbn, 0, rxfh->indir);
+
+	if (changes && netif_running(netdev))
+		fbnic_rss_reinit_hw(fbn->fbd, fbn);
+
+	return 0;
+}
+
+static int
+fbnic_modify_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx,
+			  const struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	const u32 *indir = rxfh->indir;
+	unsigned int changes;
+
+	if (!indir)
+		indir = ethtool_rxfh_context_indir(ctx);
+
+	changes = fbnic_set_indir(fbn, rxfh->rss_context, indir);
+	if (changes && netif_running(netdev))
+		fbnic_rss_reinit_hw(fbn->fbd, fbn);
+
+	return 0;
+}
+
+static int
+fbnic_create_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx,
+			  const struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) {
+		NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported");
+		return -EOPNOTSUPP;
+	}
+	ctx->hfunc = ETH_RSS_HASH_TOP;
+
+	if (!rxfh->indir) {
+		u32 *indir = ethtool_rxfh_context_indir(ctx);
+		unsigned int num_rx = fbn->num_rx_queues;
+		unsigned int i;
+
+		for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++)
+			indir[i] = ethtool_rxfh_indir_default(i, num_rx);
+	}
+
+	return fbnic_modify_rxfh_context(netdev, ctx, rxfh, extack);
+}
+
+static int
+fbnic_remove_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx, u32 rss_context,
+			  struct netlink_ext_ack *extack)
+{
+	/* Nothing to do, contexts are allocated statically */
+	return 0;
+}
+
+static void fbnic_get_channels(struct net_device *netdev,
+			       struct ethtool_channels *ch)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	ch->max_rx = fbd->max_num_queues;
+	ch->max_tx = fbd->max_num_queues;
+	ch->max_combined = min(ch->max_rx, ch->max_tx);
+	ch->max_other =	FBNIC_NON_NAPI_VECTORS;
+
+	if (fbn->num_rx_queues > fbn->num_napi ||
+	    fbn->num_tx_queues > fbn->num_napi)
+		ch->combined_count = min(fbn->num_rx_queues,
+					 fbn->num_tx_queues);
+	else
+		ch->combined_count =
+			fbn->num_rx_queues + fbn->num_tx_queues - fbn->num_napi;
+	ch->rx_count = fbn->num_rx_queues - ch->combined_count;
+	ch->tx_count = fbn->num_tx_queues - ch->combined_count;
+	ch->other_count = FBNIC_NON_NAPI_VECTORS;
+}
+
+static void fbnic_set_queues(struct fbnic_net *fbn, struct ethtool_channels *ch,
+			     unsigned int max_napis)
+{
+	fbn->num_rx_queues = ch->rx_count + ch->combined_count;
+	fbn->num_tx_queues = ch->tx_count + ch->combined_count;
+	fbn->num_napi = min(ch->rx_count + ch->tx_count + ch->combined_count,
+			    max_napis);
+}
+
+static int fbnic_set_channels(struct net_device *netdev,
+			      struct ethtool_channels *ch)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	unsigned int max_napis, standalone;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_net *clone;
+	int err;
+
+	max_napis = fbd->num_irqs - FBNIC_NON_NAPI_VECTORS;
+	standalone = ch->rx_count + ch->tx_count;
+
+	/* Limits for standalone queues:
+	 *  - each queue has it's own NAPI (num_napi >= rx + tx + combined)
+	 *  - combining queues (combined not 0, rx or tx must be 0)
+	 */
+	if ((ch->rx_count && ch->tx_count && ch->combined_count) ||
+	    (standalone && standalone + ch->combined_count > max_napis) ||
+	    ch->rx_count + ch->combined_count > fbd->max_num_queues ||
+	    ch->tx_count + ch->combined_count > fbd->max_num_queues ||
+	    ch->other_count != FBNIC_NON_NAPI_VECTORS)
+		return -EINVAL;
+
+	if (!netif_running(netdev)) {
+		fbnic_set_queues(fbn, ch, max_napis);
+		fbnic_reset_indir_tbl(fbn);
+		return 0;
+	}
+
+	clone = fbnic_clone_create(fbn);
+	if (!clone)
+		return -ENOMEM;
+
+	fbnic_set_queues(clone, ch, max_napis);
+
+	err = fbnic_alloc_napi_vectors(clone);
+	if (err)
+		goto err_free_clone;
+
+	err = fbnic_alloc_resources(clone);
+	if (err)
+		goto err_free_napis;
+
+	fbnic_down_noidle(fbn);
+	err = fbnic_wait_all_queues_idle(fbn->fbd, true);
+	if (err)
+		goto err_start_stack;
+
+	err = fbnic_set_netif_queues(clone);
+	if (err)
+		goto err_start_stack;
+
+	/* Nothing can fail past this point */
+	fbnic_flush(fbn);
+
+	fbnic_clone_swap(fbn, clone);
+
+	/* Reset RSS indirection table */
+	fbnic_reset_indir_tbl(fbn);
+
+	fbnic_up(fbn);
+
+	fbnic_free_resources(clone);
+	fbnic_free_napi_vectors(clone);
+	fbnic_clone_free(clone);
+
+	return 0;
+
+err_start_stack:
+	fbnic_flush(fbn);
+	fbnic_up(fbn);
+	fbnic_free_resources(clone);
+err_free_napis:
+	fbnic_free_napi_vectors(clone);
+err_free_clone:
+	fbnic_clone_free(clone);
+	return err;
+}
+
+static int
+fbnic_get_ts_info(struct net_device *netdev,
+		  struct kernel_ethtool_ts_info *tsinfo)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	tsinfo->phc_index = ptp_clock_index(fbn->fbd->ptp);
+
+	tsinfo->so_timestamping =
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_TX_HARDWARE |
+		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	tsinfo->tx_types =
+		BIT(HWTSTAMP_TX_OFF) |
+		BIT(HWTSTAMP_TX_ON);
+
+	tsinfo->rx_filters =
+		BIT(HWTSTAMP_FILTER_NONE) |
+		BIT(HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
+		BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
+		BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+		BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) |
+		BIT(HWTSTAMP_FILTER_ALL);
+
+	return 0;
+}
+
+static void fbnic_get_ts_stats(struct net_device *netdev,
+			       struct ethtool_ts_stats *ts_stats)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	u64 ts_packets, ts_lost;
+	struct fbnic_ring *ring;
+	unsigned int start;
+	int i;
+
+	ts_stats->pkts = fbn->tx_stats.twq.ts_packets;
+	ts_stats->lost = fbn->tx_stats.twq.ts_lost;
+	for (i = 0; i < fbn->num_tx_queues; i++) {
+		ring = fbn->tx[i];
+		do {
+			start = u64_stats_fetch_begin(&ring->stats.syncp);
+			ts_packets = ring->stats.twq.ts_packets;
+			ts_lost = ring->stats.twq.ts_lost;
+		} while (u64_stats_fetch_retry(&ring->stats.syncp, start));
+		ts_stats->pkts += ts_packets;
+		ts_stats->lost += ts_lost;
+	}
+}
+
+static void fbnic_set_counter(u64 *stat, struct fbnic_stat_counter *counter)
+{
+	if (counter->reported)
+		*stat = counter->value;
 }
 
 static void
@@ -164,51 +1612,32 @@ fbnic_get_eth_mac_stats(struct net_device *netdev,
 			  &mac_stats->eth_mac.FrameTooLongErrors);
 }
 
-static void fbnic_get_ts_stats(struct net_device *netdev,
-			       struct ethtool_ts_stats *ts_stats)
-{
-	struct fbnic_net *fbn = netdev_priv(netdev);
-	u64 ts_packets, ts_lost;
-	struct fbnic_ring *ring;
-	unsigned int start;
-	int i;
-
-	ts_stats->pkts = fbn->tx_stats.ts_packets;
-	ts_stats->lost = fbn->tx_stats.ts_lost;
-	for (i = 0; i < fbn->num_tx_queues; i++) {
-		ring = fbn->tx[i];
-		do {
-			start = u64_stats_fetch_begin(&ring->stats.syncp);
-			ts_packets = ring->stats.ts_packets;
-			ts_lost = ring->stats.ts_lost;
-		} while (u64_stats_fetch_retry(&ring->stats.syncp, start));
-		ts_stats->pkts += ts_packets;
-		ts_stats->lost += ts_lost;
-	}
-}
-
-static void fbnic_get_regs(struct net_device *netdev,
-			   struct ethtool_regs *regs, void *data)
-{
-	struct fbnic_net *fbn = netdev_priv(netdev);
-
-	fbnic_csr_get_regs(fbn->fbd, data, &regs->version);
-}
-
-static int fbnic_get_regs_len(struct net_device *netdev)
-{
-	struct fbnic_net *fbn = netdev_priv(netdev);
-
-	return fbnic_csr_regs_len(fbn->fbd) * sizeof(u32);
-}
-
 static const struct ethtool_ops fbnic_ethtool_ops = {
+	.supported_coalesce_params	=
+				  ETHTOOL_COALESCE_USECS |
+				  ETHTOOL_COALESCE_RX_MAX_FRAMES,
+	.rxfh_max_num_contexts	= FBNIC_RPC_RSS_TBL_COUNT,
 	.get_drvinfo		= fbnic_get_drvinfo,
 	.get_regs_len		= fbnic_get_regs_len,
 	.get_regs		= fbnic_get_regs,
+	.get_coalesce		= fbnic_get_coalesce,
+	.set_coalesce		= fbnic_set_coalesce,
+	.get_ringparam		= fbnic_get_ringparam,
+	.set_ringparam		= fbnic_set_ringparam,
 	.get_strings		= fbnic_get_strings,
 	.get_ethtool_stats	= fbnic_get_ethtool_stats,
 	.get_sset_count		= fbnic_get_sset_count,
+	.get_rxnfc		= fbnic_get_rxnfc,
+	.set_rxnfc		= fbnic_set_rxnfc,
+	.get_rxfh_key_size	= fbnic_get_rxfh_key_size,
+	.get_rxfh_indir_size	= fbnic_get_rxfh_indir_size,
+	.get_rxfh		= fbnic_get_rxfh,
+	.set_rxfh		= fbnic_set_rxfh,
+	.create_rxfh_context	= fbnic_create_rxfh_context,
+	.modify_rxfh_context	= fbnic_modify_rxfh_context,
+	.remove_rxfh_context	= fbnic_remove_rxfh_context,
+	.get_channels		= fbnic_get_channels,
+	.set_channels		= fbnic_set_channels,
 	.get_ts_info		= fbnic_get_ts_info,
 	.get_ts_stats		= fbnic_get_ts_stats,
 	.get_eth_mac_stats	= fbnic_get_eth_mac_stats,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 8f7a2a19ddf8..4521d0483d18 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -17,11 +17,29 @@ static void __fbnic_mbx_wr_desc(struct fbnic_dev *fbd, int mbx_idx,
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
 
+	/* Write the upper 32b and then the lower 32b. Doing this the
+	 * FW can then read lower, upper, lower to verify that the state
+	 * of the descriptor wasn't changed mid-transaction.
+	 */
 	fw_wr32(fbd, desc_offset + 1, upper_32_bits(desc));
 	fw_wrfl(fbd);
 	fw_wr32(fbd, desc_offset, lower_32_bits(desc));
 }
 
+static void __fbnic_mbx_invalidate_desc(struct fbnic_dev *fbd, int mbx_idx,
+					int desc_idx, u32 desc)
+{
+	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+
+	/* For initialization we write the lower 32b of the descriptor first.
+	 * This way we can set the state to mark it invalid before we clear the
+	 * upper 32b.
+	 */
+	fw_wr32(fbd, desc_offset, desc);
+	fw_wrfl(fbd);
+	fw_wr32(fbd, desc_offset + 1, 0);
+}
+
 static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
@@ -33,29 +51,41 @@ static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 	return desc;
 }
 
-static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_reset_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int desc_idx;
 
+	/* Disable DMA transactions from the device,
+	 * and flush any transactions triggered during cleaning
+	 */
+	switch (mbx_idx) {
+	case FBNIC_IPC_MBX_RX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH);
+		break;
+	case FBNIC_IPC_MBX_TX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH);
+		break;
+	}
+
+	wrfl(fbd);
+
 	/* Initialize first descriptor to all 0s. Doing this gives us a
 	 * solid stop for the firmware to hit when it is done looping
 	 * through the ring.
 	 */
-	__fbnic_mbx_wr_desc(fbd, mbx_idx, 0, 0);
-
-	fw_wrfl(fbd);
+	__fbnic_mbx_invalidate_desc(fbd, mbx_idx, 0, 0);
 
 	/* We then fill the rest of the ring starting at the end and moving
 	 * back toward descriptor 0 with skip descriptors that have no
 	 * length nor address, and tell the firmware that they can skip
 	 * them and just move past them to the one we initialized to 0.
 	 */
-	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) {
-		__fbnic_mbx_wr_desc(fbd, mbx_idx, desc_idx,
-				    FBNIC_IPC_MBX_DESC_FW_CMPL |
-				    FBNIC_IPC_MBX_DESC_HOST_CMPL);
-		fw_wrfl(fbd);
-	}
+	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;)
+		__fbnic_mbx_invalidate_desc(fbd, mbx_idx, desc_idx,
+					    FBNIC_IPC_MBX_DESC_FW_CMPL |
+					    FBNIC_IPC_MBX_DESC_HOST_CMPL);
 }
 
 void fbnic_mbx_init(struct fbnic_dev *fbd)
@@ -76,7 +106,7 @@ void fbnic_mbx_init(struct fbnic_dev *fbd)
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_init_desc_ring(fbd, i);
+		fbnic_mbx_reset_desc_ring(fbd, i);
 }
 
 static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
@@ -97,11 +127,8 @@ static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
 		return -EBUSY;
 
 	addr = dma_map_single(fbd->dev, msg, PAGE_SIZE, direction);
-	if (dma_mapping_error(fbd->dev, addr)) {
-		free_page((unsigned long)msg);
-
+	if (dma_mapping_error(fbd->dev, addr))
 		return -ENOSPC;
-	}
 
 	mbx->buf_info[tail].msg = msg;
 	mbx->buf_info[tail].addr = addr;
@@ -141,7 +168,7 @@ static void fbnic_mbx_clean_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int i;
 
-	fbnic_mbx_init_desc_ring(fbd, mbx_idx);
+	fbnic_mbx_reset_desc_ring(fbd, mbx_idx);
 
 	for (i = FBNIC_IPC_MBX_DESC_LEN; i--;)
 		fbnic_mbx_unmap_and_free_msg(fbd, mbx_idx, i);
@@ -207,6 +234,44 @@ static int fbnic_mbx_map_tlv_msg(struct fbnic_dev *fbd,
 	return err;
 }
 
+static int fbnic_mbx_set_cmpl_slot(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data)
+{
+	struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
+	int free = -EXFULL;
+	int i;
+
+	if (!tx_mbx->ready)
+		return -ENODEV;
+
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (!fbd->cmpl_data[i])
+			free = i;
+		else if (fbd->cmpl_data[i]->msg_type == cmpl_data->msg_type)
+			return -EEXIST;
+	}
+
+	if (free == -EXFULL)
+		return -EXFULL;
+
+	fbd->cmpl_data[free] = cmpl_data;
+
+	return 0;
+}
+
+static void fbnic_mbx_clear_cmpl_slot(struct fbnic_dev *fbd,
+				      struct fbnic_fw_completion *cmpl_data)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (fbd->cmpl_data[i] == cmpl_data) {
+			fbd->cmpl_data[i] = NULL;
+			break;
+		}
+	}
+}
+
 static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd)
 {
 	struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
@@ -228,6 +293,79 @@ static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd)
 	tx_mbx->head = head;
 }
 
+int fbnic_mbx_set_cmpl(struct fbnic_dev *fbd,
+		       struct fbnic_fw_completion *cmpl_data)
+{
+	unsigned long flags;
+	int err;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	err = fbnic_mbx_set_cmpl_slot(fbd, cmpl_data);
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+
+	return err;
+}
+
+static int fbnic_mbx_map_req_w_cmpl(struct fbnic_dev *fbd,
+				    struct fbnic_tlv_msg *msg,
+				    struct fbnic_fw_completion *cmpl_data)
+{
+	unsigned long flags;
+	int err;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	if (cmpl_data) {
+		err = fbnic_mbx_set_cmpl_slot(fbd, cmpl_data);
+		if (err)
+			goto unlock_mbx;
+	}
+
+	err = fbnic_mbx_map_msg(fbd, FBNIC_IPC_MBX_TX_IDX, msg,
+				le16_to_cpu(msg->hdr.len) * sizeof(u32), 1);
+
+	/* If we successfully reserved a completion and msg failed
+	 * then clear completion data for next caller
+	 */
+	if (err && cmpl_data)
+		fbnic_mbx_clear_cmpl_slot(fbd, cmpl_data);
+
+unlock_mbx:
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+
+	return err;
+}
+
+static void fbnic_fw_release_cmpl_data(struct kref *kref)
+{
+	struct fbnic_fw_completion *cmpl_data;
+
+	cmpl_data = container_of(kref, struct fbnic_fw_completion,
+				 ref_count);
+	kfree(cmpl_data);
+}
+
+static struct fbnic_fw_completion *
+fbnic_fw_get_cmpl_by_type(struct fbnic_dev *fbd, u32 msg_type)
+{
+	struct fbnic_fw_completion *cmpl_data = NULL;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (fbd->cmpl_data[i] &&
+		    fbd->cmpl_data[i]->msg_type == msg_type) {
+			cmpl_data = fbd->cmpl_data[i];
+			kref_get(&cmpl_data->ref_count);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+
+	return cmpl_data;
+}
+
 /**
  * fbnic_fw_xmit_simple_msg - Transmit a simple single TLV message w/o data
  * @fbd: FBNIC device structure
@@ -265,67 +403,41 @@ static int fbnic_fw_xmit_simple_msg(struct fbnic_dev *fbd, u32 msg_type)
 	return err;
 }
 
-/**
- * fbnic_fw_xmit_cap_msg - Allocate and populate a FW capabilities message
- * @fbd: FBNIC device structure
- *
- * Return: NULL on failure to allocate, error pointer on error, or pointer
- * to new TLV test message.
- *
- * Sends a single TLV header indicating the host wants the firmware to
- * confirm the capabilities and version.
- **/
-static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd)
-{
-	int err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
-
-	/* Return 0 if we are not calling this on ASIC */
-	return (err == -EOPNOTSUPP) ? 0 : err;
-}
-
-static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
 
-	/* This is a one time init, so just exit if it is completed */
-	if (mbx->ready)
-		return;
-
 	mbx->ready = true;
 
 	switch (mbx_idx) {
 	case FBNIC_IPC_MBX_RX_IDX:
+		/* Enable DMA writes from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
+
 		/* Make sure we have a page for the FW to write to */
 		fbnic_mbx_alloc_rx_msgs(fbd);
 		break;
 	case FBNIC_IPC_MBX_TX_IDX:
-		/* Force version to 1 if we successfully requested an update
-		 * from the firmware. This should be overwritten once we get
-		 * the actual version from the firmware in the capabilities
-		 * request message.
-		 */
-		if (!fbnic_fw_xmit_cap_msg(fbd) &&
-		    !fbd->fw_cap.running.mgmt.version)
-			fbd->fw_cap.running.mgmt.version = 1;
+		/* Enable DMA reads from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
 		break;
 	}
 }
 
-static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
+static bool fbnic_mbx_event(struct fbnic_dev *fbd)
 {
-	int i;
-
-	/* We only need to do this on the first interrupt following init.
+	/* We only need to do this on the first interrupt following reset.
 	 * this primes the mailbox so that we will have cleared all the
 	 * skip descriptors.
 	 */
 	if (!(rd32(fbd, FBNIC_INTR_STATUS(0)) & (1u << FBNIC_FW_MSIX_ENTRY)))
-		return;
+		return false;
 
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
-	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_postinit_desc_ring(fbd, i);
+	return true;
 }
 
 /**
@@ -403,6 +515,7 @@ static const struct fbnic_tlv_index fbnic_fw_cap_resp_index[] = {
 	FBNIC_TLV_ATTR_U32(FBNIC_FW_CAP_RESP_UEFI_VERSION),
 	FBNIC_TLV_ATTR_STRING(FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR,
 			      FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION),
 	FBNIC_TLV_ATTR_LAST
 };
 
@@ -437,16 +550,13 @@ static int fbnic_fw_parse_bmc_addrs(u8 bmc_mac_addr[][ETH_ALEN],
 
 static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 {
-	u32 active_slot = 0, all_multi = 0;
+	u32 all_multi = 0, version = 0;
 	struct fbnic_dev *fbd = opaque;
-	u32 speed = 0, fec = 0;
-	size_t commit_size = 0;
 	bool bmc_present;
 	int err;
 
-	get_unsigned_result(FBNIC_FW_CAP_RESP_VERSION,
-			    fbd->fw_cap.running.mgmt.version);
-
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_VERSION);
+	fbd->fw_cap.running.mgmt.version = version;
 	if (!fbd->fw_cap.running.mgmt.version)
 		return -EINVAL;
 
@@ -467,43 +577,41 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 		return -EINVAL;
 	}
 
-	get_string_result(FBNIC_FW_CAP_RESP_VERSION_COMMIT_STR, commit_size,
-			  fbd->fw_cap.running.mgmt.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-	if (!commit_size)
+	if (fta_get_str(results, FBNIC_FW_CAP_RESP_VERSION_COMMIT_STR,
+			fbd->fw_cap.running.mgmt.commit,
+			FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE) <= 0)
 		dev_warn(fbd->dev, "Firmware did not send mgmt commit!\n");
 
-	get_unsigned_result(FBNIC_FW_CAP_RESP_STORED_VERSION,
-			    fbd->fw_cap.stored.mgmt.version);
-	get_string_result(FBNIC_FW_CAP_RESP_STORED_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.mgmt.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_CMRT_VERSION,
-			    fbd->fw_cap.running.bootloader.version);
-	get_string_result(FBNIC_FW_CAP_RESP_CMRT_COMMIT_STR, commit_size,
-			  fbd->fw_cap.running.bootloader.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_STORED_CMRT_VERSION,
-			    fbd->fw_cap.stored.bootloader.version);
-	get_string_result(FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.bootloader.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_UEFI_VERSION,
-			    fbd->fw_cap.stored.undi.version);
-	get_string_result(FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.undi.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_ACTIVE_FW_SLOT, active_slot);
-	fbd->fw_cap.active_slot = active_slot;
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_FW_LINK_SPEED, speed);
-	get_unsigned_result(FBNIC_FW_CAP_RESP_FW_LINK_FEC, fec);
-	fbd->fw_cap.link_speed = speed;
-	fbd->fw_cap.link_fec = fec;
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_STORED_VERSION);
+	fbd->fw_cap.stored.mgmt.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_STORED_COMMIT_STR,
+		    fbd->fw_cap.stored.mgmt.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_CMRT_VERSION);
+	fbd->fw_cap.running.bootloader.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_CMRT_COMMIT_STR,
+		    fbd->fw_cap.running.bootloader.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_STORED_CMRT_VERSION);
+	fbd->fw_cap.stored.bootloader.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR,
+		    fbd->fw_cap.stored.bootloader.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_UEFI_VERSION);
+	fbd->fw_cap.stored.undi.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR,
+		    fbd->fw_cap.stored.undi.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	fbd->fw_cap.active_slot =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_ACTIVE_FW_SLOT);
+	fbd->fw_cap.link_speed =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_FW_LINK_SPEED);
+	fbd->fw_cap.link_fec =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_FW_LINK_FEC);
 
 	bmc_present = !!results[FBNIC_FW_CAP_RESP_BMC_PRESENT];
 	if (bmc_present) {
@@ -518,7 +626,8 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 		if (err)
 			return err;
 
-		get_unsigned_result(FBNIC_FW_CAP_RESP_BMC_ALL_MULTI, all_multi);
+		all_multi =
+			fta_get_uint(results, FBNIC_FW_CAP_RESP_BMC_ALL_MULTI);
 	} else {
 		memset(fbd->fw_cap.bmc_mac_addr, 0,
 		       sizeof(fbd->fw_cap.bmc_mac_addr));
@@ -529,6 +638,9 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 	if (results[FBNIC_FW_CAP_RESP_BMC_ALL_MULTI] || !bmc_present)
 		fbd->fw_cap.all_multi = all_multi;
 
+	fbd->fw_cap.anti_rollback_version =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION);
+
 	return 0;
 }
 
@@ -651,6 +763,265 @@ void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd)
 		dev_warn(fbd->dev, "Failed to send heartbeat message\n");
 }
 
+int fbnic_fw_xmit_fw_start_upgrade(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data,
+				   unsigned int id, unsigned int len)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	if (!fbnic_fw_present(fbd))
+		return -ENODEV;
+
+	if (!len)
+		return -EINVAL;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_START_UPGRADE_SECTION, id);
+	if (err)
+		goto free_message;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_START_UPGRADE_IMAGE_LENGTH,
+				     len);
+	if (err)
+		goto free_message;
+
+	err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_start_upgrade_resp_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_START_UPGRADE_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_start_upgrade_resp(void *opaque,
+						struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	s32 err;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Check for errors */
+	err = fta_get_sint(results, FBNIC_FW_START_UPGRADE_ERROR);
+
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
+int fbnic_fw_xmit_fw_write_chunk(struct fbnic_dev *fbd,
+				 const u8 *data, u32 offset, u16 length,
+				 int cancel_error)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_RESP);
+	if (!msg)
+		return -ENOMEM;
+
+	/* Report error to FW to cancel upgrade */
+	if (cancel_error) {
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_ERROR,
+					     cancel_error);
+		if (err)
+			goto free_message;
+	}
+
+	if (data) {
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_OFFSET,
+					     offset);
+		if (err)
+			goto free_message;
+
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_LENGTH,
+					     length);
+		if (err)
+			goto free_message;
+
+		err = fbnic_tlv_attr_put_value(msg, FBNIC_FW_WRITE_CHUNK_DATA,
+					       data + offset, length);
+		if (err)
+			goto free_message;
+	}
+
+	err = fbnic_mbx_map_tlv_msg(fbd, msg);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_write_chunk_req_index[] = {
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_WRITE_CHUNK_OFFSET),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_WRITE_CHUNK_LENGTH),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_write_chunk_req(void *opaque,
+					     struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	u32 offset;
+	u32 length;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Pull length/offset pair and mark it as complete */
+	offset = fta_get_uint(results, FBNIC_FW_WRITE_CHUNK_OFFSET);
+	length = fta_get_uint(results, FBNIC_FW_WRITE_CHUNK_LENGTH);
+	cmpl_data->u.fw_update.offset = offset;
+	cmpl_data->u.fw_update.length = length;
+
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_finish_upgrade_req_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_FINISH_UPGRADE_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_finish_upgrade_req(void *opaque,
+						struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	s32 err;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Check for errors */
+	err = fta_get_sint(results, FBNIC_FW_FINISH_UPGRADE_ERROR);
+
+	/* Close out update by incrementing offset by length which should
+	 * match the total size of the component. Set length to 0 since no
+	 * new chunks will be requested.
+	 */
+	cmpl_data->u.fw_update.offset += cmpl_data->u.fw_update.length;
+	cmpl_data->u.fw_update.length = 0;
+
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
+/**
+ * fbnic_fw_xmit_tsene_read_msg - Create and transmit a sensor read request
+ * @fbd: FBNIC device structure
+ * @cmpl_data: Completion data structure to store sensor response
+ *
+ * Asks the firmware to provide an update with the latest sensor data.
+ * The response will contain temperature and voltage readings.
+ *
+ * Return: 0 on success, negative error value on failure
+ */
+int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd,
+				 struct fbnic_fw_completion *cmpl_data)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	if (!fbnic_fw_present(fbd))
+		return -ENODEV;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_TSENE_READ_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_tsene_read_resp_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_THERM),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_VOLT),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_tsene_read_resp(void *opaque,
+					  struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	s32 err_resp;
+	int err = 0;
+
+	/* Verify we have a completion pointer to provide with data */
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd,
+					      FBNIC_TLV_MSG_ID_TSENE_READ_RESP);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	err_resp = fta_get_sint(results, FBNIC_FW_TSENE_ERROR);
+	if (err_resp)
+		goto msg_err;
+
+	if (!results[FBNIC_FW_TSENE_THERM] || !results[FBNIC_FW_TSENE_VOLT]) {
+		err = -EINVAL;
+		goto msg_err;
+	}
+
+	cmpl_data->u.tsene.millidegrees =
+		fta_get_sint(results, FBNIC_FW_TSENE_THERM);
+	cmpl_data->u.tsene.millivolts =
+		fta_get_sint(results, FBNIC_FW_TSENE_VOLT);
+
+msg_err:
+	cmpl_data->result = err_resp ? : err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return err;
+}
+
 static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = {
 	FBNIC_TLV_PARSER(FW_CAP_RESP, fbnic_fw_cap_resp_index,
 			 fbnic_fw_parse_cap_resp),
@@ -658,6 +1029,18 @@ static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = {
 			 fbnic_fw_parse_ownership_resp),
 	FBNIC_TLV_PARSER(HEARTBEAT_RESP, fbnic_heartbeat_resp_index,
 			 fbnic_fw_parse_heartbeat_resp),
+	FBNIC_TLV_PARSER(FW_START_UPGRADE_RESP,
+			 fbnic_fw_start_upgrade_resp_index,
+			 fbnic_fw_parse_fw_start_upgrade_resp),
+	FBNIC_TLV_PARSER(FW_WRITE_CHUNK_REQ,
+			 fbnic_fw_write_chunk_req_index,
+			 fbnic_fw_parse_fw_write_chunk_req),
+	FBNIC_TLV_PARSER(FW_FINISH_UPGRADE_REQ,
+			 fbnic_fw_finish_upgrade_req_index,
+			 fbnic_fw_parse_fw_finish_upgrade_req),
+	FBNIC_TLV_PARSER(TSENE_READ_RESP,
+			 fbnic_tsene_read_resp_index,
+			 fbnic_fw_parse_tsene_read_resp),
 	FBNIC_TLV_MSG_ERROR
 };
 
@@ -726,7 +1109,7 @@ next_page:
 
 void fbnic_mbx_poll(struct fbnic_dev *fbd)
 {
-	fbnic_mbx_postinit(fbd);
+	fbnic_mbx_event(fbd);
 
 	fbnic_mbx_process_tx_msgs(fbd);
 	fbnic_mbx_process_rx_msgs(fbd);
@@ -734,60 +1117,103 @@ void fbnic_mbx_poll(struct fbnic_dev *fbd)
 
 int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 {
-	struct fbnic_fw_mbx *tx_mbx;
-	int attempts = 50;
+	unsigned long timeout = jiffies + 10 * HZ + 1;
+	int err, i;
 
-	/* Immediate fail if BAR4 isn't there */
-	if (!fbnic_fw_present(fbd))
-		return -ENODEV;
+	do {
+		if (!time_is_after_jiffies(timeout))
+			return -ETIMEDOUT;
 
-	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
-	while (!tx_mbx->ready && --attempts) {
 		/* Force the firmware to trigger an interrupt response to
 		 * avoid the mailbox getting stuck closed if the interrupt
 		 * is reset.
 		 */
-		fbnic_mbx_init_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
+		fbnic_mbx_reset_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
 
-		msleep(200);
+		/* Immediate fail if BAR4 went away */
+		if (!fbnic_fw_present(fbd))
+			return -ENODEV;
+
+		msleep(20);
+	} while (!fbnic_mbx_event(fbd));
+
+	/* FW has shown signs of life. Enable DMA and start Tx/Rx */
+	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
+		fbnic_mbx_init_desc_ring(fbd, i);
+
+	/* Request an update from the firmware. This should overwrite
+	 * mgmt.version once we get the actual version from the firmware
+	 * in the capabilities request message.
+	 */
+	err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
+	if (err)
+		goto clean_mbx;
+
+	/* Use "1" to indicate we entered the state waiting for a response */
+	fbd->fw_cap.running.mgmt.version = 1;
+
+	return 0;
+clean_mbx:
+	/* Cleanup Rx buffers and disable mailbox */
+	fbnic_mbx_clean(fbd);
+	return err;
+}
+
+static void __fbnic_fw_evict_cmpl(struct fbnic_fw_completion *cmpl_data)
+{
+	cmpl_data->result = -EPIPE;
+	complete(&cmpl_data->done);
+}
+
+static void fbnic_mbx_evict_all_cmpl(struct fbnic_dev *fbd)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		struct fbnic_fw_completion *cmpl_data = fbd->cmpl_data[i];
 
-		fbnic_mbx_poll(fbd);
+		if (cmpl_data)
+			__fbnic_fw_evict_cmpl(cmpl_data);
 	}
 
-	return attempts ? 0 : -ETIMEDOUT;
+	memset(fbd->cmpl_data, 0, sizeof(fbd->cmpl_data));
 }
 
 void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
 {
+	unsigned long timeout = jiffies + 10 * HZ + 1;
 	struct fbnic_fw_mbx *tx_mbx;
-	int attempts = 50;
-	u8 count = 0;
-
-	/* Nothing to do if there is no mailbox */
-	if (!fbnic_fw_present(fbd))
-		return;
+	u8 tail;
 
 	/* Record current Rx stats */
 	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
 
-	/* Nothing to do if mailbox never got to ready */
-	if (!tx_mbx->ready)
-		return;
+	spin_lock_irq(&fbd->fw_tx_lock);
+
+	/* Clear ready to prevent any further attempts to transmit */
+	tx_mbx->ready = false;
+
+	/* Read tail to determine the last tail state for the ring */
+	tail = tx_mbx->tail;
+
+	/* Flush any completions as we are no longer processing Rx */
+	fbnic_mbx_evict_all_cmpl(fbd);
+
+	spin_unlock_irq(&fbd->fw_tx_lock);
 
 	/* Give firmware time to process packet,
-	 * we will wait up to 10 seconds which is 50 waits of 200ms.
+	 * we will wait up to 10 seconds which is 500 waits of 20ms.
 	 */
 	do {
 		u8 head = tx_mbx->head;
 
-		if (head == tx_mbx->tail)
+		/* Tx ring is empty once head == tail */
+		if (head == tail)
 			break;
 
-		msleep(200);
+		msleep(20);
 		fbnic_mbx_process_tx_msgs(fbd);
-
-		count += (tx_mbx->head - head) % FBNIC_IPC_MBX_DESC_LEN;
-	} while (count < FBNIC_IPC_MBX_DESC_LEN && --attempts);
+	} while (time_is_after_jiffies(timeout));
 }
 
 void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
@@ -802,3 +1228,33 @@ void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
 	fbnic_mk_full_fw_ver_str(mgmt->version, delim, mgmt->commit,
 				 fw_version, str_sz);
 }
+
+struct fbnic_fw_completion *fbnic_fw_alloc_cmpl(u32 msg_type)
+{
+	struct fbnic_fw_completion *cmpl;
+
+	cmpl = kzalloc(sizeof(*cmpl), GFP_KERNEL);
+	if (!cmpl)
+		return NULL;
+
+	cmpl->msg_type = msg_type;
+	init_completion(&cmpl->done);
+	kref_init(&cmpl->ref_count);
+
+	return cmpl;
+}
+
+void fbnic_fw_clear_cmpl(struct fbnic_dev *fbd,
+			 struct fbnic_fw_completion *fw_cmpl)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	fbnic_mbx_clear_cmpl_slot(fbd, fw_cmpl);
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+}
+
+void fbnic_fw_put_cmpl(struct fbnic_fw_completion *fw_cmpl)
+{
+	kref_put(&fw_cmpl->ref_count, fbnic_fw_release_cmpl_data);
+}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
index 7cd8841920e4..08bc4b918de7 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
@@ -42,23 +42,48 @@ struct fbnic_fw_cap {
 	u8	all_multi	: 1;
 	u8	link_speed;
 	u8	link_fec;
+	u32	anti_rollback_version;
 };
 
 struct fbnic_fw_completion {
-	struct {
-		s32 millivolts;
-		s32 millidegrees;
-	} tsene;
+	u32 msg_type;
+	struct completion done;
+	struct kref ref_count;
+	int result;
+	union {
+		struct {
+			u32 offset;
+			u32 length;
+		} fw_update;
+		struct {
+			s32 millivolts;
+			s32 millidegrees;
+		} tsene;
+	} u;
 };
 
 void fbnic_mbx_init(struct fbnic_dev *fbd);
 void fbnic_mbx_clean(struct fbnic_dev *fbd);
+int fbnic_mbx_set_cmpl(struct fbnic_dev *fbd,
+		       struct fbnic_fw_completion *cmpl_data);
 void fbnic_mbx_poll(struct fbnic_dev *fbd);
 int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd);
 void fbnic_mbx_flush_tx(struct fbnic_dev *fbd);
 int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership);
 int fbnic_fw_init_heartbeat(struct fbnic_dev *fbd, bool poll);
 void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd);
+int fbnic_fw_xmit_fw_start_upgrade(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data,
+				   unsigned int id, unsigned int len);
+int fbnic_fw_xmit_fw_write_chunk(struct fbnic_dev *fbd,
+				 const u8 *data, u32 offset, u16 length,
+				 int cancel_error);
+int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd,
+				 struct fbnic_fw_completion *cmpl_data);
+struct fbnic_fw_completion *fbnic_fw_alloc_cmpl(u32 msg_type);
+void fbnic_fw_clear_cmpl(struct fbnic_dev *fbd,
+			 struct fbnic_fw_completion *cmpl_data);
+void fbnic_fw_put_cmpl(struct fbnic_fw_completion *cmpl_data);
 
 #define fbnic_mk_full_fw_ver_str(_rev_id, _delim, _commit, _str, _str_sz) \
 do {									\
@@ -74,6 +99,15 @@ do {									\
 #define fbnic_mk_fw_ver_str(_rev_id, _str) \
 	fbnic_mk_full_fw_ver_str(_rev_id, "", "", _str, sizeof(_str))
 
+enum {
+	QSPI_SECTION_CMRT			= 0,
+	QSPI_SECTION_CONTROL_FW			= 1,
+	QSPI_SECTION_UCODE			= 2,
+	QSPI_SECTION_OPTION_ROM			= 3,
+	QSPI_SECTION_USER			= 4,
+	QSPI_SECTION_INVALID,
+};
+
 #define FW_HEARTBEAT_PERIOD		(10 * HZ)
 
 enum {
@@ -83,6 +117,14 @@ enum {
 	FBNIC_TLV_MSG_ID_OWNERSHIP_RESP			= 0x13,
 	FBNIC_TLV_MSG_ID_HEARTBEAT_REQ			= 0x14,
 	FBNIC_TLV_MSG_ID_HEARTBEAT_RESP			= 0x15,
+	FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ		= 0x22,
+	FBNIC_TLV_MSG_ID_FW_START_UPGRADE_RESP		= 0x23,
+	FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ		= 0x24,
+	FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_RESP		= 0x25,
+	FBNIC_TLV_MSG_ID_FW_FINISH_UPGRADE_REQ		= 0x28,
+	FBNIC_TLV_MSG_ID_FW_FINISH_UPGRADE_RESP		= 0x29,
+	FBNIC_TLV_MSG_ID_TSENE_READ_REQ			= 0x3C,
+	FBNIC_TLV_MSG_ID_TSENE_READ_RESP		= 0x3D,
 };
 
 #define FBNIC_FW_CAP_RESP_VERSION_MAJOR		CSR_GENMASK(31, 24)
@@ -108,6 +150,7 @@ enum {
 	FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR	= 0x10,
 	FBNIC_FW_CAP_RESP_UEFI_VERSION			= 0x11,
 	FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR		= 0x12,
+	FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION		= 0x15,
 	FBNIC_FW_CAP_RESP_MSG_MAX
 };
 
@@ -125,7 +168,35 @@ enum {
 };
 
 enum {
+	FBNIC_FW_TSENE_THERM			= 0x0,
+	FBNIC_FW_TSENE_VOLT			= 0x1,
+	FBNIC_FW_TSENE_ERROR			= 0x2,
+	FBNIC_FW_TSENE_MSG_MAX
+};
+
+enum {
 	FBNIC_FW_OWNERSHIP_FLAG			= 0x0,
 	FBNIC_FW_OWNERSHIP_MSG_MAX
 };
+
+enum {
+	FBNIC_FW_START_UPGRADE_ERROR		= 0x0,
+	FBNIC_FW_START_UPGRADE_SECTION		= 0x1,
+	FBNIC_FW_START_UPGRADE_IMAGE_LENGTH	= 0x2,
+	FBNIC_FW_START_UPGRADE_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_WRITE_CHUNK_OFFSET		= 0x0,
+	FBNIC_FW_WRITE_CHUNK_LENGTH		= 0x1,
+	FBNIC_FW_WRITE_CHUNK_DATA		= 0x2,
+	FBNIC_FW_WRITE_CHUNK_ERROR		= 0x3,
+	FBNIC_FW_WRITE_CHUNK_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_FINISH_UPGRADE_ERROR		= 0x0,
+	FBNIC_FW_FINISH_UPGRADE_MSG_MAX
+};
+
 #endif /* _FBNIC_FW_H_ */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
index 89ac6bc8c7fc..4223d8100e64 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
@@ -70,6 +70,100 @@ static void fbnic_hw_stat_rd64(struct fbnic_dev *fbd, u32 reg, s32 offset,
 	stat->u.old_reg_value_64 = new_reg_value;
 }
 
+static void fbnic_reset_tmi_stats(struct fbnic_dev *fbd,
+				  struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_DROP_PKTS, &tmi->drop.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_TMI_DROP_BYTE_L, 1, &tmi->drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TMI_ILLEGAL_PTP_REQS,
+			    &tmi->ptp_illegal_req);
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_GOOD_PTP_TS, &tmi->ptp_good_ts);
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_BAD_PTP_TS, &tmi->ptp_bad_ts);
+}
+
+static void fbnic_get_tmi_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_DROP_PKTS, &tmi->drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TMI_ILLEGAL_PTP_REQS,
+			   &tmi->ptp_illegal_req);
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_GOOD_PTP_TS, &tmi->ptp_good_ts);
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_BAD_PTP_TS, &tmi->ptp_bad_ts);
+}
+
+static void fbnic_get_tmi_stats(struct fbnic_dev *fbd,
+				struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_TMI_DROP_BYTE_L, 1, &tmi->drop.bytes);
+}
+
+static void fbnic_reset_tti_stats(struct fbnic_dev *fbd,
+				  struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TTI_CM_DROP_PKTS,
+			    &tti->cm_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TTI_CM_DROP_BYTE_L,
+			    1,
+			    &tti->cm_drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TTI_FRAME_DROP_PKTS,
+			    &tti->frame_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TTI_FRAME_DROP_BYTE_L,
+			    1,
+			    &tti->frame_drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TBI_DROP_PKTS,
+			    &tti->tbi_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TBI_DROP_BYTE_L,
+			    1,
+			    &tti->tbi_drop.bytes);
+}
+
+static void fbnic_get_tti_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TTI_CM_DROP_PKTS,
+			   &tti->cm_drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TTI_FRAME_DROP_PKTS,
+			   &tti->frame_drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TBI_DROP_PKTS,
+			   &tti->tbi_drop.frames);
+}
+
+static void fbnic_get_tti_stats(struct fbnic_dev *fbd,
+				struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TTI_CM_DROP_BYTE_L,
+			   1,
+			   &tti->cm_drop.bytes);
+
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TTI_FRAME_DROP_BYTE_L,
+			   1,
+			   &tti->frame_drop.bytes);
+
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TBI_DROP_BYTE_L,
+			   1,
+			   &tti->tbi_drop.bytes);
+}
+
 static void fbnic_reset_rpc_stats(struct fbnic_dev *fbd,
 				  struct fbnic_rpc_stats *rpc)
 {
@@ -117,6 +211,221 @@ static void fbnic_get_rpc_stats32(struct fbnic_dev *fbd,
 			   &rpc->ovr_size_err);
 }
 
+static void fbnic_reset_rxb_fifo_stats(struct fbnic_dev *fbd, int i,
+				       struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_DROP_FRMS_STS(i),
+			    &fifo->drop.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_DROP_BYTES_STS_L(i), 1,
+			    &fifo->drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRUN_FRMS_STS(i),
+			    &fifo->trunc.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_TRUN_BYTES_STS_L(i), 1,
+			    &fifo->trunc.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRANS_DROP_STS(i),
+			    &fifo->trans_drop);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRANS_ECN_STS(i),
+			    &fifo->trans_ecn);
+
+	fifo->level.u.old_reg_value_32 = 0;
+}
+
+static void fbnic_reset_rxb_enq_stats(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_DRBO_FRM_CNT_SRC(i),
+			    &enq->drbo.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_DRBO_BYTE_CNT_SRC_L(i), 4,
+			    &enq->drbo.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_INTEGRITY_ERR(i),
+			    &enq->integrity_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_MAC_ERR(i),
+			    &enq->mac_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_PARSER_ERR(i),
+			    &enq->parser_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_FRM_ERR(i),
+			    &enq->frm_err);
+}
+
+static void fbnic_reset_rxb_deq_stats(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_INTF_FRM_CNT_DST(i),
+			    &deq->intf.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_INTF_BYTE_CNT_DST_L(i), 4,
+			    &deq->intf.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_PBUF_FRM_CNT_DST(i),
+			    &deq->pbuf.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_PBUF_BYTE_CNT_DST_L(i), 4,
+			    &deq->pbuf.bytes);
+}
+
+static void fbnic_reset_rxb_stats(struct fbnic_dev *fbd,
+				  struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_reset_rxb_fifo_stats(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_reset_rxb_enq_stats(fbd, i, &rxb->enq[i]);
+		fbnic_reset_rxb_deq_stats(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_get_rxb_fifo_stats32(struct fbnic_dev *fbd, int i,
+				       struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_DROP_FRMS_STS(i),
+			   &fifo->drop.frames);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRUN_FRMS_STS(i),
+			   &fifo->trunc.frames);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRANS_DROP_STS(i),
+			   &fifo->trans_drop);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRANS_ECN_STS(i),
+			   &fifo->trans_ecn);
+
+	fifo->level.value = rd32(fbd, FBNIC_RXB_PBUF_FIFO_LEVEL(i));
+}
+
+static void fbnic_get_rxb_fifo_stats(struct fbnic_dev *fbd, int i,
+				     struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_DROP_BYTES_STS_L(i), 1,
+			   &fifo->drop.bytes);
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_TRUN_BYTES_STS_L(i), 1,
+			   &fifo->trunc.bytes);
+
+	fbnic_get_rxb_fifo_stats32(fbd, i, fifo);
+}
+
+static void fbnic_get_rxb_enq_stats32(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_DRBO_FRM_CNT_SRC(i),
+			   &enq->drbo.frames);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_INTEGRITY_ERR(i),
+			   &enq->integrity_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_MAC_ERR(i),
+			   &enq->mac_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_PARSER_ERR(i),
+			   &enq->parser_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_FRM_ERR(i),
+			   &enq->frm_err);
+}
+
+static void fbnic_get_rxb_enq_stats(struct fbnic_dev *fbd, int i,
+				    struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_DRBO_BYTE_CNT_SRC_L(i), 4,
+			   &enq->drbo.bytes);
+
+	fbnic_get_rxb_enq_stats32(fbd, i, enq);
+}
+
+static void fbnic_get_rxb_deq_stats32(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_INTF_FRM_CNT_DST(i),
+			   &deq->intf.frames);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_PBUF_FRM_CNT_DST(i),
+			   &deq->pbuf.frames);
+}
+
+static void fbnic_get_rxb_deq_stats(struct fbnic_dev *fbd, int i,
+				    struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_INTF_BYTE_CNT_DST_L(i), 4,
+			   &deq->intf.bytes);
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_PBUF_BYTE_CNT_DST_L(i), 4,
+			   &deq->pbuf.bytes);
+
+	fbnic_get_rxb_deq_stats32(fbd, i, deq);
+}
+
+static void fbnic_get_rxb_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_get_rxb_fifo_stats32(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_get_rxb_enq_stats32(fbd, i, &rxb->enq[i]);
+		fbnic_get_rxb_deq_stats32(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_get_rxb_stats(struct fbnic_dev *fbd,
+				struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_get_rxb_fifo_stats(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_get_rxb_enq_stats(fbd, i, &rxb->enq[i]);
+		fbnic_get_rxb_deq_stats(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_reset_hw_rxq_stats(struct fbnic_dev *fbd,
+				     struct fbnic_hw_q_stats *hw_q)
+{
+	int i;
+
+	for (i = 0; i < fbd->max_num_queues; i++, hw_q++) {
+		u32 base = FBNIC_QUEUE(i);
+
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_PKT_ERR_CNT,
+				    &hw_q->rde_pkt_err);
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_CQ_DROP_CNT,
+				    &hw_q->rde_pkt_cq_drop);
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_BDQ_DROP_CNT,
+				    &hw_q->rde_pkt_bdq_drop);
+	}
+}
+
+static void fbnic_get_hw_rxq_stats32(struct fbnic_dev *fbd,
+				     struct fbnic_hw_q_stats *hw_q)
+{
+	int i;
+
+	for (i = 0; i < fbd->max_num_queues; i++, hw_q++) {
+		u32 base = FBNIC_QUEUE(i);
+
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_PKT_ERR_CNT,
+				   &hw_q->rde_pkt_err);
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_CQ_DROP_CNT,
+				   &hw_q->rde_pkt_cq_drop);
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_BDQ_DROP_CNT,
+				   &hw_q->rde_pkt_bdq_drop);
+	}
+}
+
+void fbnic_get_hw_q_stats(struct fbnic_dev *fbd,
+			  struct fbnic_hw_q_stats *hw_q)
+{
+	spin_lock(&fbd->hw_stats_lock);
+	fbnic_get_hw_rxq_stats32(fbd, hw_q);
+	spin_unlock(&fbd->hw_stats_lock);
+}
+
 static void fbnic_reset_pcie_stats_asic(struct fbnic_dev *fbd,
 					struct fbnic_pcie_stats *pcie)
 {
@@ -203,18 +512,40 @@ static void fbnic_get_pcie_stats_asic64(struct fbnic_dev *fbd,
 
 void fbnic_reset_hw_stats(struct fbnic_dev *fbd)
 {
+	spin_lock(&fbd->hw_stats_lock);
+	fbnic_reset_tmi_stats(fbd, &fbd->hw_stats.tmi);
+	fbnic_reset_tti_stats(fbd, &fbd->hw_stats.tti);
 	fbnic_reset_rpc_stats(fbd, &fbd->hw_stats.rpc);
+	fbnic_reset_rxb_stats(fbd, &fbd->hw_stats.rxb);
+	fbnic_reset_hw_rxq_stats(fbd, fbd->hw_stats.hw_q);
 	fbnic_reset_pcie_stats_asic(fbd, &fbd->hw_stats.pcie);
+	spin_unlock(&fbd->hw_stats_lock);
 }
 
-void fbnic_get_hw_stats32(struct fbnic_dev *fbd)
+static void __fbnic_get_hw_stats32(struct fbnic_dev *fbd)
 {
+	fbnic_get_tmi_stats32(fbd, &fbd->hw_stats.tmi);
+	fbnic_get_tti_stats32(fbd, &fbd->hw_stats.tti);
 	fbnic_get_rpc_stats32(fbd, &fbd->hw_stats.rpc);
+	fbnic_get_rxb_stats32(fbd, &fbd->hw_stats.rxb);
+	fbnic_get_hw_rxq_stats32(fbd, fbd->hw_stats.hw_q);
+}
+
+void fbnic_get_hw_stats32(struct fbnic_dev *fbd)
+{
+	spin_lock(&fbd->hw_stats_lock);
+	__fbnic_get_hw_stats32(fbd);
+	spin_unlock(&fbd->hw_stats_lock);
 }
 
 void fbnic_get_hw_stats(struct fbnic_dev *fbd)
 {
-	fbnic_get_hw_stats32(fbd);
+	spin_lock(&fbd->hw_stats_lock);
+	__fbnic_get_hw_stats32(fbd);
 
+	fbnic_get_tmi_stats(fbd, &fbd->hw_stats.tmi);
+	fbnic_get_tti_stats(fbd, &fbd->hw_stats.tti);
+	fbnic_get_rxb_stats(fbd, &fbd->hw_stats.rxb);
 	fbnic_get_pcie_stats_asic64(fbd, &fbd->hw_stats.pcie);
+	spin_unlock(&fbd->hw_stats_lock);
 }
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h
index 78df56b87745..07e54bb75bf3 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h
@@ -17,6 +17,11 @@ struct fbnic_stat_counter {
 	bool reported;
 };
 
+struct fbnic_hw_stat {
+	struct fbnic_stat_counter frames;
+	struct fbnic_stat_counter bytes;
+};
+
 struct fbnic_eth_mac_stats {
 	struct fbnic_stat_counter FramesTransmittedOK;
 	struct fbnic_stat_counter FramesReceivedOK;
@@ -37,12 +42,49 @@ struct fbnic_mac_stats {
 	struct fbnic_eth_mac_stats eth_mac;
 };
 
+struct fbnic_tmi_stats {
+	struct fbnic_hw_stat drop;
+	struct fbnic_stat_counter ptp_illegal_req, ptp_good_ts, ptp_bad_ts;
+};
+
+struct fbnic_tti_stats {
+	struct fbnic_hw_stat cm_drop, frame_drop, tbi_drop;
+};
+
 struct fbnic_rpc_stats {
 	struct fbnic_stat_counter unkn_etype, unkn_ext_hdr;
 	struct fbnic_stat_counter ipv4_frag, ipv6_frag, ipv4_esp, ipv6_esp;
 	struct fbnic_stat_counter tcp_opt_err, out_of_hdr_err, ovr_size_err;
 };
 
+struct fbnic_rxb_enqueue_stats {
+	struct fbnic_hw_stat drbo;
+	struct fbnic_stat_counter integrity_err, mac_err;
+	struct fbnic_stat_counter parser_err, frm_err;
+};
+
+struct fbnic_rxb_fifo_stats {
+	struct fbnic_hw_stat drop, trunc;
+	struct fbnic_stat_counter trans_drop, trans_ecn;
+	struct fbnic_stat_counter level;
+};
+
+struct fbnic_rxb_dequeue_stats {
+	struct fbnic_hw_stat intf, pbuf;
+};
+
+struct fbnic_rxb_stats {
+	struct fbnic_rxb_enqueue_stats enq[FBNIC_RXB_ENQUEUE_INDICES];
+	struct fbnic_rxb_fifo_stats fifo[FBNIC_RXB_FIFO_INDICES];
+	struct fbnic_rxb_dequeue_stats deq[FBNIC_RXB_DEQUEUE_INDICES];
+};
+
+struct fbnic_hw_q_stats {
+	struct fbnic_stat_counter rde_pkt_err;
+	struct fbnic_stat_counter rde_pkt_cq_drop;
+	struct fbnic_stat_counter rde_pkt_bdq_drop;
+};
+
 struct fbnic_pcie_stats {
 	struct fbnic_stat_counter ob_rd_tlp, ob_rd_dword;
 	struct fbnic_stat_counter ob_wr_tlp, ob_wr_dword;
@@ -55,13 +97,19 @@ struct fbnic_pcie_stats {
 
 struct fbnic_hw_stats {
 	struct fbnic_mac_stats mac;
+	struct fbnic_tmi_stats tmi;
+	struct fbnic_tti_stats tti;
 	struct fbnic_rpc_stats rpc;
+	struct fbnic_rxb_stats rxb;
+	struct fbnic_hw_q_stats hw_q[FBNIC_MAX_QUEUES];
 	struct fbnic_pcie_stats pcie;
 };
 
 u64 fbnic_stat_rd64(struct fbnic_dev *fbd, u32 reg, u32 offset);
 
 void fbnic_reset_hw_stats(struct fbnic_dev *fbd);
+void fbnic_get_hw_q_stats(struct fbnic_dev *fbd,
+			  struct fbnic_hw_q_stats *hw_q);
 void fbnic_get_hw_stats32(struct fbnic_dev *fbd);
 void fbnic_get_hw_stats(struct fbnic_dev *fbd);
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c
index bcd1086e3768..def8598aceec 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c
@@ -66,7 +66,7 @@ void fbnic_hwmon_register(struct fbnic_dev *fbd)
 	if (IS_ERR(fbd->hwmon)) {
 		dev_notice(fbd->dev,
 			   "Failed to register hwmon device %pe\n",
-			fbd->hwmon);
+			   fbd->hwmon);
 		fbd->hwmon = NULL;
 	}
 }
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
index 914362195920..1c88a2bf3a7a 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
@@ -19,69 +19,105 @@ static irqreturn_t fbnic_fw_msix_intr(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static int __fbnic_fw_enable_mbx(struct fbnic_dev *fbd, int vector)
+{
+	int err;
+
+	/* Initialize mailbox and attempt to poll it into ready state */
+	fbnic_mbx_init(fbd);
+	err = fbnic_mbx_poll_tx_ready(fbd);
+	if (err) {
+		dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+		return err;
+	}
+
+	/* Enable interrupt and unmask the vector */
+	enable_irq(vector);
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+
+	return 0;
+}
+
 /**
- * fbnic_fw_enable_mbx - Configure and initialize Firmware Mailbox
+ * fbnic_fw_request_mbx - Configure and initialize Firmware Mailbox
  * @fbd: Pointer to device to initialize
  *
- * This function will initialize the firmware mailbox rings, enable the IRQ
- * and initialize the communication between the Firmware and the host. The
- * firmware is expected to respond to the initialization by sending an
- * interrupt essentially notifying the host that it has seen the
- * initialization and is now synced up.
+ * This function will allocate the IRQ and then reinitialize the mailbox
+ * starting communication between the host and firmware.
  *
  * Return: non-zero on failure.
  **/
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd)
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd)
 {
-	u32 vector = fbd->fw_msix_vector;
-	int err;
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int vector, err;
+
+	WARN_ON(fbd->fw_msix_vector);
+
+	vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
+	if (vector < 0)
+		return vector;
 
 	/* Request the IRQ for FW Mailbox vector. */
 	err = request_threaded_irq(vector, NULL, &fbnic_fw_msix_intr,
-				   IRQF_ONESHOT, dev_name(fbd->dev), fbd);
+				   IRQF_ONESHOT | IRQF_NO_AUTOEN,
+				   dev_name(fbd->dev), fbd);
 	if (err)
 		return err;
 
 	/* Initialize mailbox and attempt to poll it into ready state */
-	fbnic_mbx_init(fbd);
-	err = fbnic_mbx_poll_tx_ready(fbd);
-	if (err) {
-		dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+	err = __fbnic_fw_enable_mbx(fbd, vector);
+	if (err)
 		free_irq(vector, fbd);
-		return err;
-	}
 
-	/* Enable interrupts */
-	fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+	fbd->fw_msix_vector = vector;
 
-	return 0;
+	return err;
 }
 
 /**
- * fbnic_fw_disable_mbx - Disable mailbox and place it in standby state
- * @fbd: Pointer to device to disable
+ * fbnic_fw_disable_mbx - Temporarily place mailbox in standby state
+ * @fbd: Pointer to device
  *
- * This function will disable the mailbox interrupt, free any messages still
- * in the mailbox and place it into a standby state. The firmware is
- * expected to see the update and assume that the host is in the reset state.
+ * Shutdown the mailbox by notifying the firmware to stop sending us logs, mask
+ * and synchronize the IRQ, and then clean up the rings.
  **/
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
+static void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
 {
-	/* Disable interrupt and free vector */
-	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
+	/* Disable interrupt and synchronize the IRQ */
+	disable_irq(fbd->fw_msix_vector);
 
-	/* Free the vector */
-	free_irq(fbd->fw_msix_vector, fbd);
+	/* Mask the vector */
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	/* Make sure disabling logs message is sent, must be done here to
 	 * avoid risk of completing without a running interrupt.
 	 */
 	fbnic_mbx_flush_tx(fbd);
-
-	/* Reset the mailboxes to the initialized state */
 	fbnic_mbx_clean(fbd);
 }
 
+/**
+ * fbnic_fw_free_mbx - Disable mailbox and place it in standby state
+ * @fbd: Pointer to device to disable
+ *
+ * This function will disable the mailbox interrupt, free any messages still
+ * in the mailbox and place it into a disabled state. The firmware is
+ * expected to see the update and assume that the host is in the reset state.
+ **/
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd)
+{
+	/* Vector has already been freed */
+	if (!fbd->fw_msix_vector)
+		return;
+
+	fbnic_fw_disable_mbx(fbd);
+
+	/* Free the vector */
+	free_irq(fbd->fw_msix_vector, fbd);
+	fbd->fw_msix_vector = 0;
+}
+
 static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
 {
 	struct fbnic_dev *fbd = data;
@@ -101,7 +137,7 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
 }
 
 /**
- * fbnic_pcs_irq_enable - Configure the MAC to enable it to advertise link
+ * fbnic_pcs_request_irq - Configure the PCS to enable it to advertise link
  * @fbd: Pointer to device to initialize
  *
  * This function provides basic bringup for the MAC/PCS IRQ. For now the IRQ
@@ -109,41 +145,72 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
  *
  * Return: non-zero on failure.
  **/
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd)
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd)
 {
-	u32 vector = fbd->pcs_msix_vector;
-	int err;
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int vector, err;
+
+	WARN_ON(fbd->pcs_msix_vector);
+
+	vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
+	if (vector < 0)
+		return vector;
 
-	/* Request the IRQ for MAC link vector.
-	 * Map MAC cause to it, and unmask it
+	/* Request the IRQ for PCS link vector.
+	 * Map PCS cause to it, and unmask it
 	 */
 	err = request_irq(vector, &fbnic_pcs_msix_intr, 0,
 			  fbd->netdev->name, fbd);
 	if (err)
 		return err;
 
+	/* Map and enable interrupt, unmask vector after link is configured */
 	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
 		   FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE);
 
+	fbd->pcs_msix_vector = vector;
+
 	return 0;
 }
 
 /**
- * fbnic_pcs_irq_disable - Teardown the MAC IRQ to prepare for stopping
+ * fbnic_pcs_free_irq - Teardown the PCS IRQ to prepare for stopping
  * @fbd: Pointer to device that is stopping
  *
- * This function undoes the work done in fbnic_pcs_irq_enable and prepares
+ * This function undoes the work done in fbnic_pcs_request_irq and prepares
  * the device to no longer receive traffic on the host interface.
  **/
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd)
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd)
 {
+	/* Vector has already been freed */
+	if (!fbd->pcs_msix_vector)
+		return;
+
 	/* Disable interrupt */
 	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
 		   FBNIC_PCS_MSIX_ENTRY);
+	fbnic_wrfl(fbd);
+
+	/* Synchronize IRQ to prevent race that would unmask vector */
+	synchronize_irq(fbd->pcs_msix_vector);
+
+	/* Mask the vector */
 	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY);
 
 	/* Free the vector */
 	free_irq(fbd->pcs_msix_vector, fbd);
+	fbd->pcs_msix_vector = 0;
+}
+
+void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr)
+{
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int irq = pci_irq_vector(pdev, nr);
+
+	if (irq < 0)
+		return;
+
+	synchronize_irq(irq);
 }
 
 int fbnic_request_irq(struct fbnic_dev *fbd, int nr, irq_handler_t handler,
@@ -169,13 +236,52 @@ void fbnic_free_irq(struct fbnic_dev *fbd, int nr, void *data)
 	free_irq(irq, data);
 }
 
+void fbnic_napi_name_irqs(struct fbnic_dev *fbd)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(fbd->napi_irq); i++)
+		snprintf(fbd->napi_irq[i].name,
+			 sizeof(fbd->napi_irq[i].name),
+			 "%s-TxRx-%u", fbd->netdev->name, i);
+}
+
+int fbnic_napi_request_irq(struct fbnic_dev *fbd,
+			   struct fbnic_napi_vector *nv)
+{
+	struct fbnic_net *fbn = netdev_priv(fbd->netdev);
+	int i = fbnic_napi_idx(nv);
+	int err;
+
+	if (!fbd->napi_irq[i].users) {
+		err = fbnic_request_irq(fbd, nv->v_idx,
+					fbnic_msix_clean_rings,	0,
+					fbd->napi_irq[i].name,
+					&fbn->napi[i]);
+		if (err)
+			return err;
+	}
+
+	fbd->napi_irq[i].users++;
+	return 0;
+}
+
+void fbnic_napi_free_irq(struct fbnic_dev *fbd,
+			 struct fbnic_napi_vector *nv)
+{
+	struct fbnic_net *fbn = netdev_priv(fbd->netdev);
+	int i = fbnic_napi_idx(nv);
+
+	if (--fbd->napi_irq[i].users)
+		return;
+
+	fbnic_free_irq(fbd, nv->v_idx, &fbn->napi[i]);
+}
+
 void fbnic_free_irqs(struct fbnic_dev *fbd)
 {
 	struct pci_dev *pdev = to_pci_dev(fbd->dev);
 
-	fbd->pcs_msix_vector = 0;
-	fbd->fw_msix_vector = 0;
-
 	fbd->num_irqs = 0;
 
 	pci_free_irq_vectors(pdev);
@@ -201,8 +307,5 @@ int fbnic_alloc_irqs(struct fbnic_dev *fbd)
 
 	fbd->num_irqs = num_irqs;
 
-	fbd->pcs_msix_vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
-	fbd->fw_msix_vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
-
 	return 0;
 }
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
index 80b82ff12c4d..10e108c1fcd0 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
@@ -79,12 +79,6 @@ static void fbnic_mac_init_axi(struct fbnic_dev *fbd)
 	fbnic_init_readrq(fbd, FBNIC_QM_RNI_RBP_CTL, cls, readrq);
 	fbnic_init_mps(fbd, FBNIC_QM_RNI_RDE_CTL, cls, mps);
 	fbnic_init_mps(fbd, FBNIC_QM_RNI_RCM_CTL, cls, mps);
-
-	/* Enable XALI AR/AW outbound */
-	wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
-	     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
-	wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
-	     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
 }
 
 static void fbnic_mac_init_qm(struct fbnic_dev *fbd)
@@ -686,25 +680,72 @@ fbnic_mac_get_eth_mac_stats(struct fbnic_dev *fbd, bool reset,
 			    MAC_STAT_TX_BROADCAST);
 }
 
-static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id, long *val)
+static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id,
+				     long *val)
 {
-	struct fbnic_fw_completion fw_cmpl;
+	struct fbnic_fw_completion *fw_cmpl;
+	int err = 0, retries = 5;
 	s32 *sensor;
 
+	fw_cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_TSENE_READ_RESP);
+	if (!fw_cmpl)
+		return -ENOMEM;
+
 	switch (id) {
 	case FBNIC_SENSOR_TEMP:
-		sensor = &fw_cmpl.tsene.millidegrees;
+		sensor = &fw_cmpl->u.tsene.millidegrees;
 		break;
 	case FBNIC_SENSOR_VOLTAGE:
-		sensor = &fw_cmpl.tsene.millivolts;
+		sensor = &fw_cmpl->u.tsene.millivolts;
 		break;
 	default:
-		return -EINVAL;
+		err = -EINVAL;
+		goto exit_free;
+	}
+
+	err = fbnic_fw_xmit_tsene_read_msg(fbd, fw_cmpl);
+	if (err) {
+		dev_err(fbd->dev,
+			"Failed to transmit TSENE read msg, err %d\n",
+			err);
+		goto exit_free;
+	}
+
+	/* Allow 2 seconds for reply, resend and try up to 5 times */
+	while (!wait_for_completion_timeout(&fw_cmpl->done, 2 * HZ)) {
+		retries--;
+
+		if (retries == 0) {
+			dev_err(fbd->dev,
+				"Timed out waiting for TSENE read\n");
+			err = -ETIMEDOUT;
+			goto exit_cleanup;
+		}
+
+		err = fbnic_fw_xmit_tsene_read_msg(fbd, NULL);
+		if (err) {
+			dev_err(fbd->dev,
+				"Failed to transmit TSENE read msg, err %d\n",
+				err);
+			goto exit_cleanup;
+		}
+	}
+
+	/* Handle error returned by firmware */
+	if (fw_cmpl->result) {
+		err = fw_cmpl->result;
+		dev_err(fbd->dev, "%s: Firmware returned error %d\n",
+			__func__, err);
+		goto exit_cleanup;
 	}
 
 	*val = *sensor;
+exit_cleanup:
+	fbnic_fw_clear_cmpl(fbd, fw_cmpl);
+exit_free:
+	fbnic_fw_put_cmpl(fw_cmpl);
 
-	return 0;
+	return err;
 }
 
 static const struct fbnic_mac fbnic_mac_asic = {
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index fc7d80db5fa6..aa812c63d5af 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -23,13 +23,7 @@ int __fbnic_open(struct fbnic_net *fbn)
 	if (err)
 		goto free_napi_vectors;
 
-	err = netif_set_real_num_tx_queues(fbn->netdev,
-					   fbn->num_tx_queues);
-	if (err)
-		goto free_resources;
-
-	err = netif_set_real_num_rx_queues(fbn->netdev,
-					   fbn->num_rx_queues);
+	err = fbnic_set_netif_queues(fbn);
 	if (err)
 		goto free_resources;
 
@@ -50,9 +44,10 @@ int __fbnic_open(struct fbnic_net *fbn)
 	if (err)
 		goto time_stop;
 
-	err = fbnic_pcs_irq_enable(fbd);
+	err = fbnic_pcs_request_irq(fbd);
 	if (err)
 		goto time_stop;
+
 	/* Pull the BMC config and initialize the RPC */
 	fbnic_bmc_rpc_init(fbd);
 	fbnic_rss_reinit(fbd, fbn);
@@ -74,6 +69,8 @@ static int fbnic_open(struct net_device *netdev)
 	struct fbnic_net *fbn = netdev_priv(netdev);
 	int err;
 
+	fbnic_napi_name_irqs(fbn->fbd);
+
 	err = __fbnic_open(fbn);
 	if (!err)
 		fbnic_up(fbn);
@@ -86,11 +83,12 @@ static int fbnic_stop(struct net_device *netdev)
 	struct fbnic_net *fbn = netdev_priv(netdev);
 
 	fbnic_down(fbn);
-	fbnic_pcs_irq_disable(fbn->fbd);
+	fbnic_pcs_free_irq(fbn->fbd);
 
 	fbnic_time_stop(fbn);
 	fbnic_fw_xmit_ownership_msg(fbn->fbd, false);
 
+	fbnic_reset_netif_queues(fbn);
 	fbnic_free_resources(fbn);
 	fbnic_free_napi_vectors(fbn);
 
@@ -406,12 +404,16 @@ static int fbnic_hwtstamp_set(struct net_device *netdev,
 static void fbnic_get_stats64(struct net_device *dev,
 			      struct rtnl_link_stats64 *stats64)
 {
+	u64 rx_bytes, rx_packets, rx_dropped = 0, rx_errors = 0;
 	u64 tx_bytes, tx_packets, tx_dropped = 0;
-	u64 rx_bytes, rx_packets, rx_dropped = 0;
 	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_dev *fbd = fbn->fbd;
 	struct fbnic_queue_stats *stats;
+	u64 rx_over = 0, rx_missed = 0;
 	unsigned int start, i;
 
+	fbnic_get_hw_stats(fbd);
+
 	stats = &fbn->tx_stats;
 
 	tx_bytes = stats->bytes;
@@ -422,6 +424,12 @@ static void fbnic_get_stats64(struct net_device *dev,
 	stats64->tx_packets = tx_packets;
 	stats64->tx_dropped = tx_dropped;
 
+	/* Record drops from Tx HW Datapath */
+	tx_dropped += fbd->hw_stats.tmi.drop.frames.value +
+		      fbd->hw_stats.tti.cm_drop.frames.value +
+		      fbd->hw_stats.tti.frame_drop.frames.value +
+		      fbd->hw_stats.tti.tbi_drop.frames.value;
+
 	for (i = 0; i < fbn->num_tx_queues; i++) {
 		struct fbnic_ring *txr = fbn->tx[i];
 
@@ -447,9 +455,34 @@ static void fbnic_get_stats64(struct net_device *dev,
 	rx_packets = stats->packets;
 	rx_dropped = stats->dropped;
 
+	spin_lock(&fbd->hw_stats_lock);
+	/* Record drops for the host FIFOs.
+	 * 4: network to Host,	6: BMC to Host
+	 * Exclude the BMC and MC FIFOs as those stats may contain drops
+	 * due to unrelated items such as TCAM misses. They are still
+	 * accessible through the ethtool stats.
+	 */
+	i = FBNIC_RXB_FIFO_HOST;
+	rx_missed += fbd->hw_stats.rxb.fifo[i].drop.frames.value;
+	i = FBNIC_RXB_FIFO_BMC_TO_HOST;
+	rx_missed += fbd->hw_stats.rxb.fifo[i].drop.frames.value;
+
+	for (i = 0; i < fbd->max_num_queues; i++) {
+		/* Report packets dropped due to CQ/BDQ being full/empty */
+		rx_over += fbd->hw_stats.hw_q[i].rde_pkt_cq_drop.value;
+		rx_over += fbd->hw_stats.hw_q[i].rde_pkt_bdq_drop.value;
+
+		/* Report packets with errors */
+		rx_errors += fbd->hw_stats.hw_q[i].rde_pkt_err.value;
+	}
+	spin_unlock(&fbd->hw_stats_lock);
+
 	stats64->rx_bytes = rx_bytes;
 	stats64->rx_packets = rx_packets;
 	stats64->rx_dropped = rx_dropped;
+	stats64->rx_over_errors = rx_over;
+	stats64->rx_errors = rx_errors;
+	stats64->rx_missed_errors = rx_missed;
 
 	for (i = 0; i < fbn->num_rx_queues; i++) {
 		struct fbnic_ring *rxr = fbn->rx[i];
@@ -489,9 +522,11 @@ static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx,
 {
 	struct fbnic_net *fbn = netdev_priv(dev);
 	struct fbnic_ring *rxr = fbn->rx[idx];
+	struct fbnic_dev *fbd = fbn->fbd;
 	struct fbnic_queue_stats *stats;
+	u64 bytes, packets, alloc_fail;
+	u64 csum_complete, csum_none;
 	unsigned int start;
-	u64 bytes, packets;
 
 	if (!rxr)
 		return;
@@ -501,10 +536,25 @@ static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx,
 		start = u64_stats_fetch_begin(&stats->syncp);
 		bytes = stats->bytes;
 		packets = stats->packets;
+		alloc_fail = stats->rx.alloc_failed;
+		csum_complete = stats->rx.csum_complete;
+		csum_none = stats->rx.csum_none;
 	} while (u64_stats_fetch_retry(&stats->syncp, start));
 
 	rx->bytes = bytes;
 	rx->packets = packets;
+	rx->alloc_fail = alloc_fail;
+	rx->csum_complete = csum_complete;
+	rx->csum_none = csum_none;
+
+	fbnic_get_hw_q_stats(fbd, fbd->hw_stats.hw_q);
+
+	spin_lock(&fbd->hw_stats_lock);
+	rx->hw_drop_overruns = fbd->hw_stats.hw_q[idx].rde_pkt_cq_drop.value +
+			       fbd->hw_stats.hw_q[idx].rde_pkt_bdq_drop.value;
+	rx->hw_drops = fbd->hw_stats.hw_q[idx].rde_pkt_err.value +
+		       rx->hw_drop_overruns;
+	spin_unlock(&fbd->hw_stats_lock);
 }
 
 static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
@@ -513,6 +563,7 @@ static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
 	struct fbnic_net *fbn = netdev_priv(dev);
 	struct fbnic_ring *txr = fbn->tx[idx];
 	struct fbnic_queue_stats *stats;
+	u64 stop, wake, csum, lso;
 	unsigned int start;
 	u64 bytes, packets;
 
@@ -524,10 +575,18 @@ static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
 		start = u64_stats_fetch_begin(&stats->syncp);
 		bytes = stats->bytes;
 		packets = stats->packets;
+		csum = stats->twq.csum_partial;
+		lso = stats->twq.lso;
+		stop = stats->twq.stop;
+		wake = stats->twq.wake;
 	} while (u64_stats_fetch_retry(&stats->syncp, start));
 
 	tx->bytes = bytes;
 	tx->packets = packets;
+	tx->needs_csum = csum + lso;
+	tx->hw_gso_wire_packets = lso;
+	tx->stop = stop;
+	tx->wake = wake;
 }
 
 static void fbnic_get_base_stats(struct net_device *dev,
@@ -538,9 +597,16 @@ static void fbnic_get_base_stats(struct net_device *dev,
 
 	tx->bytes = fbn->tx_stats.bytes;
 	tx->packets = fbn->tx_stats.packets;
+	tx->needs_csum = fbn->tx_stats.twq.csum_partial + fbn->tx_stats.twq.lso;
+	tx->hw_gso_wire_packets = fbn->tx_stats.twq.lso;
+	tx->stop = fbn->tx_stats.twq.stop;
+	tx->wake = fbn->tx_stats.twq.wake;
 
 	rx->bytes = fbn->rx_stats.bytes;
 	rx->packets = fbn->rx_stats.packets;
+	rx->alloc_fail = fbn->rx_stats.rx.alloc_failed;
+	rx->csum_complete = fbn->rx_stats.rx.csum_complete;
+	rx->csum_none = fbn->rx_stats.rx.csum_none;
 }
 
 static const struct netdev_stat_ops fbnic_stat_ops = {
@@ -591,7 +657,7 @@ void fbnic_netdev_free(struct fbnic_dev *fbd)
  * Allocate and initialize the netdev and netdev private structure. Bind
  * together the hardware, netdev, and pci data structures.
  *
- *  Return: 0 on success, negative on failure
+ *  Return: Pointer to net_device on success, NULL on failure
  **/
 struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 {
@@ -615,13 +681,16 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 
 	fbn->netdev = netdev;
 	fbn->fbd = fbd;
-	INIT_LIST_HEAD(&fbn->napis);
 
 	fbn->txq_size = FBNIC_TXQ_SIZE_DEFAULT;
 	fbn->hpq_size = FBNIC_HPQ_SIZE_DEFAULT;
 	fbn->ppq_size = FBNIC_PPQ_SIZE_DEFAULT;
 	fbn->rcq_size = FBNIC_RCQ_SIZE_DEFAULT;
 
+	fbn->tx_usecs = FBNIC_TX_USECS_DEFAULT;
+	fbn->rx_usecs = FBNIC_RX_USECS_DEFAULT;
+	fbn->rx_max_frames = FBNIC_RX_FRAMES_DEFAULT;
+
 	default_queues = netif_get_num_default_rss_queues();
 	if (default_queues > fbd->max_num_queues)
 		default_queues = fbd->max_num_queues;
@@ -632,15 +701,32 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	fbnic_rss_key_fill(fbn->rss_key);
 	fbnic_rss_init_en_mask(fbn);
 
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
+	netdev->gso_partial_features =
+		NETIF_F_GSO_GRE |
+		NETIF_F_GSO_GRE_CSUM |
+		NETIF_F_GSO_IPXIP4 |
+		NETIF_F_GSO_UDP_TUNNEL |
+		NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
 	netdev->features |=
+		netdev->gso_partial_features |
+		FBNIC_TUN_GSO_FEATURES |
 		NETIF_F_RXHASH |
 		NETIF_F_SG |
 		NETIF_F_HW_CSUM |
-		NETIF_F_RXCSUM;
+		NETIF_F_RXCSUM |
+		NETIF_F_TSO |
+		NETIF_F_TSO_ECN |
+		NETIF_F_TSO6 |
+		NETIF_F_GSO_PARTIAL |
+		NETIF_F_GSO_UDP_L4;
 
 	netdev->hw_features |= netdev->features;
 	netdev->vlan_features |= netdev->features;
 	netdev->hw_enc_features |= netdev->features;
+	netdev->features |= NETIF_F_NTUPLE;
 
 	netdev->min_mtu = IPV6_MIN_MTU;
 	netdev->max_mtu = FBNIC_MAX_JUMBO_FRAME_SIZE - ETH_HLEN;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
index b8417b300778..561837e80ec8 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
@@ -11,10 +11,18 @@
 #include "fbnic_rpc.h"
 #include "fbnic_txrx.h"
 
+#define FBNIC_MAX_NAPI_VECTORS		128u
+#define FBNIC_MIN_RXD_PER_FRAME		2
+
+/* Natively supported tunnel GSO features (not thru GSO_PARTIAL) */
+#define FBNIC_TUN_GSO_FEATURES		NETIF_F_GSO_IPXIP6
+
 struct fbnic_net {
 	struct fbnic_ring *tx[FBNIC_MAX_TXQS];
 	struct fbnic_ring *rx[FBNIC_MAX_RXQS];
 
+	struct fbnic_napi_vector *napi[FBNIC_MAX_NAPI_VECTORS];
+
 	struct net_device *netdev;
 	struct fbnic_dev *fbd;
 
@@ -23,6 +31,11 @@ struct fbnic_net {
 	u32 ppq_size;
 	u32 rcq_size;
 
+	u16 rx_usecs;
+	u16 tx_usecs;
+
+	u32 rx_max_frames;
+
 	u16 num_napi;
 
 	struct phylink *phylink;
@@ -56,13 +69,12 @@ struct fbnic_net {
 
 	/* Time stampinn filter config */
 	struct kernel_hwtstamp_config hwtstamp_config;
-
-	struct list_head napis;
 };
 
 int __fbnic_open(struct fbnic_net *fbn);
 void fbnic_up(struct fbnic_net *fbn);
 void fbnic_down(struct fbnic_net *fbn);
+void fbnic_down_noidle(struct fbnic_net *fbn);
 
 struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd);
 void fbnic_netdev_free(struct fbnic_dev *fbd);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index 32702dc4a066..249d3ef862d5 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/rtnetlink.h>
 #include <linux/types.h>
+#include <net/devlink.h>
 
 #include "fbnic.h"
 #include "fbnic_drvinfo.h"
@@ -145,7 +146,7 @@ void fbnic_up(struct fbnic_net *fbn)
 	fbnic_service_task_start(fbn);
 }
 
-static void fbnic_down_noidle(struct fbnic_net *fbn)
+void fbnic_down_noidle(struct fbnic_net *fbn)
 {
 	fbnic_service_task_stop(fbn);
 
@@ -283,7 +284,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto free_irqs;
 	}
 
-	err = fbnic_fw_enable_mbx(fbd);
+	err = fbnic_fw_request_mbx(fbd);
 	if (err) {
 		dev_err(&pdev->dev,
 			"Firmware mailbox initialization failure\n");
@@ -292,6 +293,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	fbnic_devlink_register(fbd);
 	fbnic_dbg_fbd_init(fbd);
+	spin_lock_init(&fbd->hw_stats_lock);
 
 	/* Capture snapshot of hardware stats so netdev can calculate delta */
 	fbnic_reset_hw_stats(fbd);
@@ -363,7 +365,7 @@ static void fbnic_remove(struct pci_dev *pdev)
 	fbnic_hwmon_unregister(fbd);
 	fbnic_dbg_fbd_exit(fbd);
 	fbnic_devlink_unregister(fbd);
-	fbnic_fw_disable_mbx(fbd);
+	fbnic_fw_free_mbx(fbd);
 	fbnic_free_irqs(fbd);
 
 	fbnic_devlink_free(fbd);
@@ -387,7 +389,11 @@ static int fbnic_pm_suspend(struct device *dev)
 	rtnl_unlock();
 
 null_uc_addr:
-	fbnic_fw_disable_mbx(fbd);
+	devl_lock(priv_to_devlink(fbd));
+
+	fbnic_fw_free_mbx(fbd);
+
+	devl_unlock(priv_to_devlink(fbd));
 
 	/* Free the IRQs so they aren't trying to occupy sleeping CPUs */
 	fbnic_free_irqs(fbd);
@@ -419,11 +425,15 @@ static int __fbnic_pm_resume(struct device *dev)
 
 	fbd->mac->init_regs(fbd);
 
+	devl_lock(priv_to_devlink(fbd));
+
 	/* Re-enable mailbox */
-	err = fbnic_fw_enable_mbx(fbd);
+	err = fbnic_fw_request_mbx(fbd);
 	if (err)
 		goto err_free_irqs;
 
+	devl_unlock(priv_to_devlink(fbd));
+
 	/* No netdev means there isn't a network interface to bring up */
 	if (fbnic_init_failure(fbd))
 		return 0;
@@ -438,15 +448,15 @@ static int __fbnic_pm_resume(struct device *dev)
 	if (netif_running(netdev)) {
 		err = __fbnic_open(fbn);
 		if (err)
-			goto err_disable_mbx;
+			goto err_free_mbx;
 	}
 
 	rtnl_unlock();
 
 	return 0;
-err_disable_mbx:
+err_free_mbx:
 	rtnl_unlock();
-	fbnic_fw_disable_mbx(fbd);
+	fbnic_fw_free_mbx(fbd);
 err_free_irqs:
 	fbnic_free_irqs(fbd);
 err_invalidate_uc_addr:
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c
index 1a5e1e719b30..860b02b22c15 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c
@@ -15,7 +15,7 @@ fbnic_pcs_to_net(struct phylink_pcs *pcs)
 }
 
 static void
-fbnic_phylink_pcs_get_state(struct phylink_pcs *pcs,
+fbnic_phylink_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 			    struct phylink_link_state *state)
 {
 	struct fbnic_net *fbn = fbnic_pcs_to_net(pcs);
@@ -133,7 +133,6 @@ int fbnic_phylink_init(struct net_device *netdev)
 	struct fbnic_net *fbn = netdev_priv(netdev);
 	struct phylink *phylink;
 
-	fbn->phylink_pcs.neg_mode = true;
 	fbn->phylink_pcs.ops = &fbnic_phylink_pcs_ops;
 
 	fbn->phylink_config.dev = &netdev->dev;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
index 908c098cd59e..8ff07b5562e3 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
@@ -3,6 +3,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <net/ipv6.h>
 
 #include "fbnic.h"
 #include "fbnic_netdev.h"
@@ -13,10 +14,11 @@ void fbnic_reset_indir_tbl(struct fbnic_net *fbn)
 	unsigned int num_rx = fbn->num_rx_queues;
 	unsigned int i;
 
-	for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++) {
+	if (netif_is_rxfh_configured(fbn->netdev))
+		return;
+
+	for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++)
 		fbn->indir_tbl[0][i] = ethtool_rxfh_indir_default(i, num_rx);
-		fbn->indir_tbl[1][i] = ethtool_rxfh_indir_default(i, num_rx);
-	}
 }
 
 void fbnic_rss_key_fill(u32 *buffer)
@@ -59,7 +61,7 @@ void fbnic_rss_disable_hw(struct fbnic_dev *fbd)
 #define FBNIC_FH_2_RSSEM_BIT(_fh, _rssem, _val)		\
 	FIELD_PREP(FBNIC_RPC_ACT_TBL1_RSS_ENA_##_rssem,	\
 		   FIELD_GET(RXH_##_fh, _val))
-static u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type)
+u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type)
 {
 	u32 flow_hash = fbn->rss_flow_hash[flow_type];
 	u32 rss_en_mask = 0;
@@ -697,6 +699,359 @@ void fbnic_write_tce_tcam(struct fbnic_dev *fbd)
 		__fbnic_write_tce_tcam(fbd);
 }
 
+struct fbnic_ip_addr *__fbnic_ip4_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in_addr *addr,
+				       const struct in_addr *mask)
+{
+	struct fbnic_ip_addr *avail_addr = NULL;
+	unsigned int i;
+
+	/* Scan from top of list to bottom, filling bottom up. */
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i++, ip_addr++) {
+		struct in6_addr *m = &ip_addr->mask;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DISABLED) {
+			avail_addr = ip_addr;
+			continue;
+		}
+
+		if (ip_addr->version != 4)
+			continue;
+
+		/* Drop avail_addr if mask is a subset of our current mask,
+		 * This prevents us from inserting a longer prefix behind a
+		 * shorter one.
+		 *
+		 * The mask is stored inverted value so as an example:
+		 * m	ffff ffff ffff ffff ffff ffff ffff 0000 0000
+		 * mask 0000 0000 0000 0000 0000 0000 0000 ffff ffff
+		 *
+		 * "m" and "mask" represent typical IPv4 mask stored in
+		 * the TCAM and those provided by the stack. The code below
+		 * should return a non-zero result if there is a 0 stored
+		 * anywhere in "m" where "mask" has a 0.
+		 */
+		if (~m->s6_addr32[3] & ~mask->s_addr) {
+			avail_addr = NULL;
+			continue;
+		}
+
+		/* Check to see if the mask actually contains fewer bits than
+		 * our new mask "m". The XOR below should only result in 0 if
+		 * "m" is masking a bit that we are looking for in our new
+		 * "mask", we eliminated the 0^0 case with the check above.
+		 *
+		 * If it contains fewer bits we need to stop here, otherwise
+		 * we might be adding an unreachable rule.
+		 */
+		if (~(m->s6_addr32[3] ^ mask->s_addr))
+			break;
+
+		if (ip_addr->value.s6_addr32[3] == addr->s_addr) {
+			avail_addr = ip_addr;
+			break;
+		}
+	}
+
+	if (avail_addr && avail_addr->state == FBNIC_TCAM_S_DISABLED) {
+		ipv6_addr_set(&avail_addr->value, 0, 0, 0, addr->s_addr);
+		ipv6_addr_set(&avail_addr->mask, htonl(~0), htonl(~0),
+			      htonl(~0), ~mask->s_addr);
+		avail_addr->version = 4;
+
+		avail_addr->state = FBNIC_TCAM_S_ADD;
+	}
+
+	return avail_addr;
+}
+
+struct fbnic_ip_addr *__fbnic_ip6_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in6_addr *addr,
+				       const struct in6_addr *mask)
+{
+	struct fbnic_ip_addr *avail_addr = NULL;
+	unsigned int i;
+
+	ip_addr = &ip_addr[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES - 1];
+
+	/* Scan from bottom of list to top, filling top down. */
+	for (i = FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i--; ip_addr--) {
+		struct in6_addr *m = &ip_addr->mask;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DISABLED) {
+			avail_addr = ip_addr;
+			continue;
+		}
+
+		if (ip_addr->version != 6)
+			continue;
+
+		/* Drop avail_addr if mask is a superset of our current mask.
+		 * This prevents us from inserting a longer prefix behind a
+		 * shorter one.
+		 *
+		 * The mask is stored inverted value so as an example:
+		 * m	0000 0000 0000 0000 0000 0000 0000 0000 0000
+		 * mask ffff ffff ffff ffff ffff ffff ffff ffff ffff
+		 *
+		 * "m" and "mask" represent typical IPv6 mask stored in
+		 * the TCAM and those provided by the stack. The code below
+		 * should return a non-zero result which will cause us
+		 * to drop the avail_addr value that might be cached
+		 * to prevent us from dropping a v6 address behind it.
+		 */
+		if ((m->s6_addr32[0] & mask->s6_addr32[0]) |
+		    (m->s6_addr32[1] & mask->s6_addr32[1]) |
+		    (m->s6_addr32[2] & mask->s6_addr32[2]) |
+		    (m->s6_addr32[3] & mask->s6_addr32[3])) {
+			avail_addr = NULL;
+			continue;
+		}
+
+		/* The previous test eliminated any overlap between the
+		 * two values so now we need to check for gaps.
+		 *
+		 * If the mask is equal to our current mask then it should
+		 * result with m ^ mask = ffff ffff, if however the value
+		 * stored in m is bigger then we should see a 0 appear
+		 * somewhere in the mask.
+		 */
+		if (~(m->s6_addr32[0] ^ mask->s6_addr32[0]) |
+		    ~(m->s6_addr32[1] ^ mask->s6_addr32[1]) |
+		    ~(m->s6_addr32[2] ^ mask->s6_addr32[2]) |
+		    ~(m->s6_addr32[3] ^ mask->s6_addr32[3]))
+			break;
+
+		if (ipv6_addr_cmp(&ip_addr->value, addr))
+			continue;
+
+		avail_addr = ip_addr;
+		break;
+	}
+
+	if (avail_addr && avail_addr->state == FBNIC_TCAM_S_DISABLED) {
+		memcpy(&avail_addr->value, addr, sizeof(*addr));
+		ipv6_addr_set(&avail_addr->mask,
+			      ~mask->s6_addr32[0], ~mask->s6_addr32[1],
+			      ~mask->s6_addr32[2], ~mask->s6_addr32[3]);
+		avail_addr->version = 6;
+
+		avail_addr->state = FBNIC_TCAM_S_ADD;
+	}
+
+	return avail_addr;
+}
+
+int __fbnic_ip_unsync(struct fbnic_ip_addr *ip_addr, unsigned int tcam_idx)
+{
+	if (!test_and_clear_bit(tcam_idx, ip_addr->act_tcam))
+		return -ENOENT;
+
+	if (bitmap_empty(ip_addr->act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES))
+		ip_addr->state = FBNIC_TCAM_S_DELETE;
+
+	return 0;
+}
+
+static void fbnic_clear_ip_src_entry(struct fbnic_dev *fbd, unsigned int idx)
+{
+	int i;
+
+	/* Invalidate entry and clear addr state info */
+	for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i), 0);
+}
+
+static void fbnic_clear_ip_dst_entry(struct fbnic_dev *fbd, unsigned int idx)
+{
+	int i;
+
+	/* Invalidate entry and clear addr state info */
+	for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i), 0);
+}
+
+static void fbnic_clear_ip_outer_src_entry(struct fbnic_dev *fbd,
+					   unsigned int idx)
+{
+	int i;
+
+	/* Invalidate entry and clear addr state info */
+	for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i), 0);
+}
+
+static void fbnic_clear_ip_outer_dst_entry(struct fbnic_dev *fbd,
+					   unsigned int idx)
+{
+	int i;
+
+	/* Invalidate entry and clear addr state info */
+	for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i), 0);
+}
+
+static void fbnic_write_ip_src_entry(struct fbnic_dev *fbd, unsigned int idx,
+				     struct fbnic_ip_addr *ip_addr)
+{
+	__be16 *mask, *value;
+	int i;
+
+	mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+	value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i),
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) |
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--)));
+	wrfl(fbd);
+
+	/* Bit 129 is used to flag for v4/v6 */
+	wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i),
+	     (ip_addr->version == 6) | FBNIC_RPC_TCAM_VALIDATE);
+}
+
+static void fbnic_write_ip_dst_entry(struct fbnic_dev *fbd, unsigned int idx,
+				     struct fbnic_ip_addr *ip_addr)
+{
+	__be16 *mask, *value;
+	int i;
+
+	mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+	value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i),
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) |
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--)));
+	wrfl(fbd);
+
+	/* Bit 129 is used to flag for v4/v6 */
+	wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i),
+	     (ip_addr->version == 6) | FBNIC_RPC_TCAM_VALIDATE);
+}
+
+static void fbnic_write_ip_outer_src_entry(struct fbnic_dev *fbd,
+					   unsigned int idx,
+					   struct fbnic_ip_addr *ip_addr)
+{
+	__be16 *mask, *value;
+	int i;
+
+	mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+	value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i),
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) |
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--)));
+	wrfl(fbd);
+
+	wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i), FBNIC_RPC_TCAM_VALIDATE);
+}
+
+static void fbnic_write_ip_outer_dst_entry(struct fbnic_dev *fbd,
+					   unsigned int idx,
+					   struct fbnic_ip_addr *ip_addr)
+{
+	__be16 *mask, *value;
+	int i;
+
+	mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+	value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i),
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) |
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--)));
+	wrfl(fbd);
+
+	wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i), FBNIC_RPC_TCAM_VALIDATE);
+}
+
+void fbnic_write_ip_addr(struct fbnic_dev *fbd)
+{
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->ip_src); idx--;) {
+		struct fbnic_ip_addr *ip_addr = &fbd->ip_src[idx];
+
+		/* Check if update flag is set else skip. */
+		if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE))
+			continue;
+
+		/* Clear by writing 0s. */
+		if (ip_addr->state == FBNIC_TCAM_S_DELETE) {
+			/* Invalidate entry and clear addr state info */
+			fbnic_clear_ip_src_entry(fbd, idx);
+			memset(ip_addr, 0, sizeof(*ip_addr));
+
+			continue;
+		}
+
+		fbnic_write_ip_src_entry(fbd, idx, ip_addr);
+
+		ip_addr->state = FBNIC_TCAM_S_VALID;
+	}
+
+	/* Repeat process for other IP TCAMs */
+	for (idx = ARRAY_SIZE(fbd->ip_dst); idx--;) {
+		struct fbnic_ip_addr *ip_addr = &fbd->ip_dst[idx];
+
+		if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE))
+			continue;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DELETE) {
+			fbnic_clear_ip_dst_entry(fbd, idx);
+			memset(ip_addr, 0, sizeof(*ip_addr));
+
+			continue;
+		}
+
+		fbnic_write_ip_dst_entry(fbd, idx, ip_addr);
+
+		ip_addr->state = FBNIC_TCAM_S_VALID;
+	}
+
+	for (idx = ARRAY_SIZE(fbd->ipo_src); idx--;) {
+		struct fbnic_ip_addr *ip_addr = &fbd->ipo_src[idx];
+
+		if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE))
+			continue;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DELETE) {
+			fbnic_clear_ip_outer_src_entry(fbd, idx);
+			memset(ip_addr, 0, sizeof(*ip_addr));
+
+			continue;
+		}
+
+		fbnic_write_ip_outer_src_entry(fbd, idx, ip_addr);
+
+		ip_addr->state = FBNIC_TCAM_S_VALID;
+	}
+
+	for (idx = ARRAY_SIZE(fbd->ipo_dst); idx--;) {
+		struct fbnic_ip_addr *ip_addr = &fbd->ipo_dst[idx];
+
+		if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE))
+			continue;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DELETE) {
+			fbnic_clear_ip_outer_dst_entry(fbd, idx);
+			memset(ip_addr, 0, sizeof(*ip_addr));
+
+			continue;
+		}
+
+		fbnic_write_ip_outer_dst_entry(fbd, idx, ip_addr);
+
+		ip_addr->state = FBNIC_TCAM_S_VALID;
+	}
+}
+
 void fbnic_clear_rules(struct fbnic_dev *fbd)
 {
 	u32 dest = FIELD_PREP(FBNIC_RPC_ACT_TBL0_DEST_MASK,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
index 0d8285fa5b45..6892414195c3 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
@@ -7,6 +7,8 @@
 #include <uapi/linux/in6.h>
 #include <linux/bitfield.h>
 
+struct in_addr;
+
 /*  The TCAM state definitions follow an expected ordering.
  *  They start out disabled, then move through the following states:
  *  Disabled  0	-> Add	      2
@@ -32,6 +34,12 @@ enum {
 #define FBNIC_RPC_TCAM_MACDA_WORD_LEN		3
 #define FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES	32
 
+/* 8 IPSRC and IPDST TCAM Entries each
+ * 8 registers, Validate each
+ */
+#define FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN		8
+#define FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES	8
+
 #define FBNIC_RPC_TCAM_ACT_WORD_LEN		11
 #define FBNIC_RPC_TCAM_ACT_NUM_ENTRIES		64
 
@@ -47,6 +55,13 @@ struct fbnic_mac_addr {
 	DECLARE_BITMAP(act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES);
 };
 
+struct fbnic_ip_addr {
+	struct in6_addr mask, value;
+	unsigned char version;
+	unsigned char state;
+	DECLARE_BITMAP(act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES);
+};
+
 struct fbnic_act_tcam {
 	struct {
 		u16 tcam[FBNIC_RPC_TCAM_ACT_WORD_LEN];
@@ -81,6 +96,11 @@ enum {
 #define FBNIC_RPC_ACT_TBL_BMC_OFFSET		0
 #define FBNIC_RPC_ACT_TBL_BMC_ALL_MULTI_OFFSET	1
 
+/* This should leave us with 48 total entries in the TCAM that can be used
+ * for NFC after also deducting the 14 needed for RSS table programming.
+ */
+#define FBNIC_RPC_ACT_TBL_NFC_OFFSET		2
+
 /* We reserve the last 14 entries for RSS rules on the host. The BMC
  * unicast rule will need to be populated above these and is expected to
  * use MACDA TCAM entry 23 to store the BMC MAC address.
@@ -88,6 +108,9 @@ enum {
 #define FBNIC_RPC_ACT_TBL_RSS_OFFSET \
 	(FBNIC_RPC_ACT_TBL_NUM_ENTRIES - FBNIC_RSS_EN_NUM_ENTRIES)
 
+#define FBNIC_RPC_ACT_TBL_NFC_ENTRIES \
+	(FBNIC_RPC_ACT_TBL_RSS_OFFSET - FBNIC_RPC_ACT_TBL_NFC_OFFSET)
+
 /* Flags used to identify the owner for this MAC filter. Note that any
  * flags set for Broadcast thru Promisc indicate that the rule belongs
  * to the RSS filters for the host.
@@ -168,6 +191,7 @@ void fbnic_rss_init_en_mask(struct fbnic_net *fbn);
 void fbnic_rss_disable_hw(struct fbnic_dev *fbd);
 void fbnic_rss_reinit_hw(struct fbnic_dev *fbd, struct fbnic_net *fbn);
 void fbnic_rss_reinit(struct fbnic_dev *fbd, struct fbnic_net *fbn);
+u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type);
 
 int __fbnic_xc_unsync(struct fbnic_mac_addr *mac_addr, unsigned int tcam_idx);
 struct fbnic_mac_addr *__fbnic_uc_sync(struct fbnic_dev *fbd,
@@ -177,6 +201,17 @@ struct fbnic_mac_addr *__fbnic_mc_sync(struct fbnic_dev *fbd,
 void fbnic_sift_macda(struct fbnic_dev *fbd);
 void fbnic_write_macda(struct fbnic_dev *fbd);
 
+struct fbnic_ip_addr *__fbnic_ip4_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in_addr *addr,
+				       const struct in_addr *mask);
+struct fbnic_ip_addr *__fbnic_ip6_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in6_addr *addr,
+				       const struct in6_addr *mask);
+int __fbnic_ip_unsync(struct fbnic_ip_addr *ip_addr, unsigned int tcam_idx);
+void fbnic_write_ip_addr(struct fbnic_dev *fbd);
+
 static inline int __fbnic_uc_unsync(struct fbnic_mac_addr *mac_addr)
 {
 	return __fbnic_xc_unsync(mac_addr, FBNIC_MAC_ADDR_T_UNICAST);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
index 2a174ab062a3..517ed8b2f1cb 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
@@ -196,13 +196,17 @@ int fbnic_tlv_attr_put_string(struct fbnic_tlv_msg *msg, u16 attr_id,
 /**
  * fbnic_tlv_attr_get_unsigned - Retrieve unsigned value from result
  * @attr: Attribute to retrieve data from
+ * @def: The default value if attr is NULL
  *
  * Return: unsigned 64b value containing integer value
  **/
-u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr)
+u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr, u64 def)
 {
 	__le64 le64_value = 0;
 
+	if (!attr)
+		return def;
+
 	memcpy(&le64_value, &attr->value[0],
 	       le16_to_cpu(attr->hdr.len) - sizeof(*attr));
 
@@ -212,15 +216,21 @@ u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr)
 /**
  * fbnic_tlv_attr_get_signed - Retrieve signed value from result
  * @attr: Attribute to retrieve data from
+ * @def: The default value if attr is NULL
  *
  * Return: signed 64b value containing integer value
  **/
-s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr)
+s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr, s64 def)
 {
-	int shift = (8 + sizeof(*attr) - le16_to_cpu(attr->hdr.len)) * 8;
 	__le64 le64_value = 0;
+	int shift;
 	s64 value;
 
+	if (!attr)
+		return def;
+
+	shift = (8 + sizeof(*attr) - le16_to_cpu(attr->hdr.len)) * 8;
+
 	/* Copy the value and adjust for byte ordering */
 	memcpy(&le64_value, &attr->value[0],
 	       le16_to_cpu(attr->hdr.len) - sizeof(*attr));
@@ -233,19 +243,40 @@ s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr)
 /**
  * fbnic_tlv_attr_get_string - Retrieve string value from result
  * @attr: Attribute to retrieve data from
- * @str: Pointer to an allocated string to store the data
- * @max_size: The maximum size which can be in str
+ * @dst: Pointer to an allocated string to store the data
+ * @dstsize: The maximum size which can be in dst
  *
- * Return: the size of the string read from firmware
+ * Return: the size of the string read from firmware or negative error.
  **/
-size_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *str,
-				 size_t max_size)
+ssize_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *dst,
+				  size_t dstsize)
 {
-	max_size = min_t(size_t, max_size,
-			 (le16_to_cpu(attr->hdr.len) * 4) - sizeof(*attr));
-	memcpy(str, &attr->value, max_size);
+	size_t srclen, len;
+	ssize_t ret;
+
+	if (!attr)
+		return -EINVAL;
+
+	if (dstsize == 0)
+		return -E2BIG;
+
+	srclen = le16_to_cpu(attr->hdr.len) - sizeof(*attr);
+	if (srclen > 0 && ((char *)attr->value)[srclen - 1] == '\0')
+		srclen--;
+
+	if (srclen >= dstsize) {
+		len = dstsize - 1;
+		ret = -E2BIG;
+	} else {
+		len = srclen;
+		ret = len;
+	}
+
+	memcpy(dst, &attr->value, len);
+	/* Zero pad end of dst. */
+	memset(dst + len, 0, dstsize - len);
 
-	return max_size;
+	return ret;
 }
 
 /**
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
index 67300ab44353..c34bf87eeec9 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
@@ -114,34 +114,10 @@ static inline bool fbnic_tlv_attr_get_bool(struct fbnic_tlv_msg *attr)
 	return !!attr;
 }
 
-u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr);
-s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr);
-size_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *str,
-				 size_t max_size);
-
-#define get_unsigned_result(id, location) \
-do { \
-	struct fbnic_tlv_msg *result = results[id]; \
-	if (result) \
-		location = fbnic_tlv_attr_get_unsigned(result); \
-} while (0)
-
-#define get_signed_result(id, location) \
-do { \
-	struct fbnic_tlv_msg *result = results[id]; \
-	if (result) \
-		location = fbnic_tlv_attr_get_signed(result); \
-} while (0)
-
-#define get_string_result(id, size, str, max_size) \
-do { \
-	struct fbnic_tlv_msg *result = results[id]; \
-	if (result) \
-		size = fbnic_tlv_attr_get_string(result, str, max_size); \
-} while (0)
-
-#define get_bool(id) (!!(results[id]))
-
+u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr, u64 def);
+s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr, s64 def);
+ssize_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *dst,
+				  size_t dstsize);
 struct fbnic_tlv_msg *fbnic_tlv_msg_alloc(u16 msg_id);
 int fbnic_tlv_attr_put_flag(struct fbnic_tlv_msg *msg, const u16 attr_id);
 int fbnic_tlv_attr_put_value(struct fbnic_tlv_msg *msg, const u16 attr_id,
@@ -170,6 +146,13 @@ int fbnic_tlv_msg_parse(void *opaque, struct fbnic_tlv_msg *msg,
 			const struct fbnic_tlv_parser *parser);
 int fbnic_tlv_parser_error(void *opaque, struct fbnic_tlv_msg **results);
 
+#define fta_get_uint(_results, _id) \
+	fbnic_tlv_attr_get_unsigned(_results[_id], 0)
+#define fta_get_sint(_results, _id) \
+	fbnic_tlv_attr_get_signed(_results[_id], 0)
+#define fta_get_str(_results, _id, _dst, _dstsize) \
+	fbnic_tlv_attr_get_string(_results[_id], _dst, _dstsize)
+
 #define FBNIC_TLV_MSG_ERROR \
 	FBNIC_TLV_PARSER(UNKNOWN, NULL, fbnic_tlv_parser_error)
 #endif /* _FBNIC_TLV_H_ */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index b5050fabe8fe..ac11389a764c 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <net/netdev_queues.h>
 #include <net/page_pool/helpers.h>
+#include <net/tcp.h>
 
 #include "fbnic.h"
 #include "fbnic_csr.h"
@@ -18,6 +19,7 @@ enum {
 
 struct fbnic_xmit_cb {
 	u32 bytecount;
+	u16 gso_segs;
 	u8 desc_count;
 	u8 flags;
 	int hw_head;
@@ -113,6 +115,11 @@ static int fbnic_maybe_stop_tx(const struct net_device *dev,
 
 	res = netif_txq_maybe_stop(txq, fbnic_desc_unused(ring), size,
 				   FBNIC_TX_DESC_WAKEUP);
+	if (!res) {
+		u64_stats_update_begin(&ring->stats.syncp);
+		ring->stats.twq.stop++;
+		u64_stats_update_end(&ring->stats.syncp);
+	}
 
 	return !res;
 }
@@ -174,8 +181,72 @@ static bool fbnic_tx_tstamp(struct sk_buff *skb)
 }
 
 static bool
+fbnic_tx_lso(struct fbnic_ring *ring, struct sk_buff *skb,
+	     struct skb_shared_info *shinfo, __le64 *meta,
+	     unsigned int *l2len, unsigned int *i3len)
+{
+	unsigned int l3_type, l4_type, l4len, hdrlen;
+	unsigned char *l4hdr;
+	__be16 payload_len;
+
+	if (unlikely(skb_cow_head(skb, 0)))
+		return true;
+
+	if (shinfo->gso_type & SKB_GSO_PARTIAL) {
+		l3_type = FBNIC_TWD_L3_TYPE_OTHER;
+	} else if (!skb->encapsulation) {
+		if (ip_hdr(skb)->version == 4)
+			l3_type = FBNIC_TWD_L3_TYPE_IPV4;
+		else
+			l3_type = FBNIC_TWD_L3_TYPE_IPV6;
+	} else {
+		unsigned int o3len;
+
+		o3len = skb_inner_network_header(skb) - skb_network_header(skb);
+		*i3len -= o3len;
+		*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L3_OHLEN_MASK,
+						o3len / 2));
+		l3_type = FBNIC_TWD_L3_TYPE_V6V6;
+	}
+
+	l4hdr = skb_checksum_start(skb);
+	payload_len = cpu_to_be16(skb->len - (l4hdr - skb->data));
+
+	if (shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+		struct tcphdr *tcph = (struct tcphdr *)l4hdr;
+
+		l4_type = FBNIC_TWD_L4_TYPE_TCP;
+		l4len = __tcp_hdrlen((struct tcphdr *)l4hdr);
+		csum_replace_by_diff(&tcph->check, (__force __wsum)payload_len);
+	} else {
+		struct udphdr *udph = (struct udphdr *)l4hdr;
+
+		l4_type = FBNIC_TWD_L4_TYPE_UDP;
+		l4len = sizeof(struct udphdr);
+		csum_replace_by_diff(&udph->check, (__force __wsum)payload_len);
+	}
+
+	hdrlen = (l4hdr - skb->data) + l4len;
+	*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L3_TYPE_MASK, l3_type) |
+			     FIELD_PREP(FBNIC_TWD_L4_TYPE_MASK, l4_type) |
+			     FIELD_PREP(FBNIC_TWD_L4_HLEN_MASK, l4len / 4) |
+			     FIELD_PREP(FBNIC_TWD_MSS_MASK, shinfo->gso_size) |
+			     FBNIC_TWD_FLAG_REQ_LSO);
+
+	FBNIC_XMIT_CB(skb)->bytecount += (shinfo->gso_segs - 1) * hdrlen;
+	FBNIC_XMIT_CB(skb)->gso_segs = shinfo->gso_segs;
+
+	u64_stats_update_begin(&ring->stats.syncp);
+	ring->stats.twq.lso += shinfo->gso_segs;
+	u64_stats_update_end(&ring->stats.syncp);
+
+	return false;
+}
+
+static bool
 fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta)
 {
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	unsigned int l2len, i3len;
 
 	if (fbnic_tx_tstamp(skb))
@@ -190,7 +261,15 @@ fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta)
 	*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_CSUM_OFFSET_MASK,
 					skb->csum_offset / 2));
 
-	*meta |= cpu_to_le64(FBNIC_TWD_FLAG_REQ_CSO);
+	if (shinfo->gso_size) {
+		if (fbnic_tx_lso(ring, skb, shinfo, meta, &l2len, &i3len))
+			return true;
+	} else {
+		*meta |= cpu_to_le64(FBNIC_TWD_FLAG_REQ_CSO);
+		u64_stats_update_begin(&ring->stats.syncp);
+		ring->stats.twq.csum_partial++;
+		u64_stats_update_end(&ring->stats.syncp);
+	}
 
 	*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L2_HLEN_MASK, l2len / 2) |
 			     FIELD_PREP(FBNIC_TWD_L3_IHLEN_MASK, i3len / 2));
@@ -198,12 +277,15 @@ fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta)
 }
 
 static void
-fbnic_rx_csum(u64 rcd, struct sk_buff *skb, struct fbnic_ring *rcq)
+fbnic_rx_csum(u64 rcd, struct sk_buff *skb, struct fbnic_ring *rcq,
+	      u64 *csum_cmpl, u64 *csum_none)
 {
 	skb_checksum_none_assert(skb);
 
-	if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM)))
+	if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM))) {
+		(*csum_none)++;
 		return;
+	}
 
 	if (FIELD_GET(FBNIC_RCD_META_L4_CSUM_UNNECESSARY, rcd)) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -212,6 +294,7 @@ fbnic_rx_csum(u64 rcd, struct sk_buff *skb, struct fbnic_ring *rcq)
 
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = (__force __wsum)csum;
+		(*csum_cmpl)++;
 	}
 }
 
@@ -329,7 +412,9 @@ fbnic_xmit_frame_ring(struct sk_buff *skb, struct fbnic_ring *ring)
 
 	/* Write all members within DWORD to condense this into 2 4B writes */
 	FBNIC_XMIT_CB(skb)->bytecount = skb->len;
+	FBNIC_XMIT_CB(skb)->gso_segs = 1;
 	FBNIC_XMIT_CB(skb)->desc_count = 0;
+	FBNIC_XMIT_CB(skb)->flags = 0;
 
 	if (fbnic_tx_offloads(ring, skb, meta))
 		goto err_free;
@@ -356,6 +441,59 @@ netdev_tx_t fbnic_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 	return fbnic_xmit_frame_ring(skb, fbn->tx[q_map]);
 }
 
+static netdev_features_t
+fbnic_features_check_encap_gso(struct sk_buff *skb, struct net_device *dev,
+			       netdev_features_t features, unsigned int l3len)
+{
+	netdev_features_t skb_gso_features;
+	struct ipv6hdr *ip6_hdr;
+	unsigned char l4_hdr;
+	unsigned int start;
+	__be16 frag_off;
+
+	/* Require MANGLEID for GSO_PARTIAL of IPv4.
+	 * In theory we could support TSO with single, innermost v4 header
+	 * by pretending everything before it is L2, but that needs to be
+	 * parsed case by case.. so leaving it for when the need arises.
+	 */
+	if (!(features & NETIF_F_TSO_MANGLEID))
+		features &= ~NETIF_F_TSO;
+
+	skb_gso_features = skb_shinfo(skb)->gso_type;
+	skb_gso_features <<= NETIF_F_GSO_SHIFT;
+
+	/* We'd only clear the native GSO features, so don't bother validating
+	 * if the match can only be on those supported thru GSO_PARTIAL.
+	 */
+	if (!(skb_gso_features & FBNIC_TUN_GSO_FEATURES))
+		return features;
+
+	/* We can only do IPv6-in-IPv6, not v4-in-v6. It'd be nice
+	 * to fall back to partial for this, or any failure below.
+	 * This is just an optimization, UDPv4 will be caught later on.
+	 */
+	if (skb_gso_features & NETIF_F_TSO)
+		return features & ~FBNIC_TUN_GSO_FEATURES;
+
+	/* Inner headers multiple of 2 */
+	if ((skb_inner_network_header(skb) - skb_network_header(skb)) % 2)
+		return features & ~FBNIC_TUN_GSO_FEATURES;
+
+	/* Encapsulated GSO packet, make 100% sure it's IPv6-in-IPv6. */
+	ip6_hdr = ipv6_hdr(skb);
+	if (ip6_hdr->version != 6)
+		return features & ~FBNIC_TUN_GSO_FEATURES;
+
+	l4_hdr = ip6_hdr->nexthdr;
+	start = (unsigned char *)ip6_hdr - skb->data + sizeof(struct ipv6hdr);
+	start = ipv6_skip_exthdr(skb, start, &l4_hdr, &frag_off);
+	if (frag_off || l4_hdr != IPPROTO_IPV6 ||
+	    skb->data + start != skb_inner_network_header(skb))
+		return features & ~FBNIC_TUN_GSO_FEATURES;
+
+	return features;
+}
+
 netdev_features_t
 fbnic_features_check(struct sk_buff *skb, struct net_device *dev,
 		     netdev_features_t features)
@@ -376,9 +514,12 @@ fbnic_features_check(struct sk_buff *skb, struct net_device *dev,
 	    !FIELD_FIT(FBNIC_TWD_L2_HLEN_MASK, l2len / 2) ||
 	    !FIELD_FIT(FBNIC_TWD_L3_IHLEN_MASK, l3len / 2) ||
 	    !FIELD_FIT(FBNIC_TWD_CSUM_OFFSET_MASK, skb->csum_offset / 2))
-		return features & ~NETIF_F_CSUM_MASK;
+		return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 
-	return features;
+	if (likely(!skb->encapsulation) || !skb_is_gso(skb))
+		return features;
+
+	return fbnic_features_check_encap_gso(skb, dev, features, l3len);
 }
 
 static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
@@ -429,7 +570,7 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
 		}
 
 		total_bytes += FBNIC_XMIT_CB(skb)->bytecount;
-		total_packets += 1;
+		total_packets += FBNIC_XMIT_CB(skb)->gso_segs;
 
 		napi_consume_skb(skb, napi_budget);
 	}
@@ -444,7 +585,7 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
 	if (unlikely(discard)) {
 		u64_stats_update_begin(&ring->stats.syncp);
 		ring->stats.dropped += total_packets;
-		ring->stats.ts_lost += ts_lost;
+		ring->stats.twq.ts_lost += ts_lost;
 		u64_stats_update_end(&ring->stats.syncp);
 
 		netdev_tx_completed_queue(txq, total_packets, total_bytes);
@@ -456,9 +597,13 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
 	ring->stats.packets += total_packets;
 	u64_stats_update_end(&ring->stats.syncp);
 
-	netif_txq_completed_wake(txq, total_packets, total_bytes,
-				 fbnic_desc_unused(ring),
-				 FBNIC_TX_DESC_WAKEUP);
+	if (!netif_txq_completed_wake(txq, total_packets, total_bytes,
+				      fbnic_desc_unused(ring),
+				      FBNIC_TX_DESC_WAKEUP)) {
+		u64_stats_update_begin(&ring->stats.syncp);
+		ring->stats.twq.wake++;
+		u64_stats_update_end(&ring->stats.syncp);
+	}
 }
 
 static void fbnic_clean_tsq(struct fbnic_napi_vector *nv,
@@ -507,7 +652,7 @@ static void fbnic_clean_tsq(struct fbnic_napi_vector *nv,
 
 	skb_tstamp_tx(skb, &hwtstamp);
 	u64_stats_update_begin(&ring->stats.syncp);
-	ring->stats.ts_packets++;
+	ring->stats.twq.ts_packets++;
 	u64_stats_update_end(&ring->stats.syncp);
 }
 
@@ -661,8 +806,13 @@ static void fbnic_fill_bdq(struct fbnic_napi_vector *nv, struct fbnic_ring *bdq)
 		struct page *page;
 
 		page = page_pool_dev_alloc_pages(nv->page_pool);
-		if (!page)
+		if (!page) {
+			u64_stats_update_begin(&bdq->stats.syncp);
+			bdq->stats.rx.alloc_failed++;
+			u64_stats_update_end(&bdq->stats.syncp);
+
 			break;
+		}
 
 		fbnic_page_pool_init(bdq, i, page);
 		fbnic_bd_prep(bdq, i, page);
@@ -875,12 +1025,13 @@ static void fbnic_rx_tstamp(struct fbnic_napi_vector *nv, u64 rcd,
 
 static void fbnic_populate_skb_fields(struct fbnic_napi_vector *nv,
 				      u64 rcd, struct sk_buff *skb,
-				      struct fbnic_q_triad *qt)
+				      struct fbnic_q_triad *qt,
+				      u64 *csum_cmpl, u64 *csum_none)
 {
 	struct net_device *netdev = nv->napi.dev;
 	struct fbnic_ring *rcq = &qt->cmpl;
 
-	fbnic_rx_csum(rcd, skb, rcq);
+	fbnic_rx_csum(rcd, skb, rcq, csum_cmpl, csum_none);
 
 	if (netdev->features & NETIF_F_RXHASH)
 		skb_set_hash(skb,
@@ -898,7 +1049,8 @@ static bool fbnic_rcd_metadata_err(u64 rcd)
 static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 			   struct fbnic_q_triad *qt, int budget)
 {
-	unsigned int packets = 0, bytes = 0, dropped = 0;
+	unsigned int packets = 0, bytes = 0, dropped = 0, alloc_failed = 0;
+	u64 csum_complete = 0, csum_none = 0;
 	struct fbnic_ring *rcq = &qt->cmpl;
 	struct fbnic_pkt_buff *pkt;
 	s32 head0 = -1, head1 = -1;
@@ -947,14 +1099,22 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 
 			/* Populate skb and invalidate XDP */
 			if (!IS_ERR_OR_NULL(skb)) {
-				fbnic_populate_skb_fields(nv, rcd, skb, qt);
+				fbnic_populate_skb_fields(nv, rcd, skb, qt,
+							  &csum_complete,
+							  &csum_none);
 
 				packets++;
 				bytes += skb->len;
 
 				napi_gro_receive(&nv->napi, skb);
 			} else {
-				dropped++;
+				if (!skb) {
+					alloc_failed++;
+					dropped++;
+				} else {
+					dropped++;
+				}
+
 				fbnic_put_pkt_buff(nv, pkt, 1);
 			}
 
@@ -977,6 +1137,9 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 	/* Re-add ethernet header length (removed in fbnic_build_skb) */
 	rcq->stats.bytes += ETH_HLEN * packets;
 	rcq->stats.dropped += dropped;
+	rcq->stats.rx.alloc_failed += alloc_failed;
+	rcq->stats.rx.csum_complete += csum_complete;
+	rcq->stats.rx.csum_none += csum_none;
 	u64_stats_update_end(&rcq->stats.syncp);
 
 	/* Unmap and free processed buffers */
@@ -1033,20 +1196,20 @@ static int fbnic_poll(struct napi_struct *napi, int budget)
 	if (likely(napi_complete_done(napi, work_done)))
 		fbnic_nv_irq_rearm(nv);
 
-	return 0;
+	return work_done;
 }
 
-static irqreturn_t fbnic_msix_clean_rings(int __always_unused irq, void *data)
+irqreturn_t fbnic_msix_clean_rings(int __always_unused irq, void *data)
 {
-	struct fbnic_napi_vector *nv = data;
+	struct fbnic_napi_vector *nv = *(void **)data;
 
 	napi_schedule_irqoff(&nv->napi);
 
 	return IRQ_HANDLED;
 }
 
-static void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn,
-					     struct fbnic_ring *rxr)
+void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn,
+				      struct fbnic_ring *rxr)
 {
 	struct fbnic_queue_stats *stats = &rxr->stats;
 
@@ -1054,10 +1217,15 @@ static void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn,
 	fbn->rx_stats.bytes += stats->bytes;
 	fbn->rx_stats.packets += stats->packets;
 	fbn->rx_stats.dropped += stats->dropped;
+	fbn->rx_stats.rx.alloc_failed += stats->rx.alloc_failed;
+	fbn->rx_stats.rx.csum_complete += stats->rx.csum_complete;
+	fbn->rx_stats.rx.csum_none += stats->rx.csum_none;
+	/* Remember to add new stats here */
+	BUILD_BUG_ON(sizeof(fbn->rx_stats.rx) / 8 != 3);
 }
 
-static void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
-					     struct fbnic_ring *txr)
+void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
+				      struct fbnic_ring *txr)
 {
 	struct fbnic_queue_stats *stats = &txr->stats;
 
@@ -1065,8 +1233,14 @@ static void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
 	fbn->tx_stats.bytes += stats->bytes;
 	fbn->tx_stats.packets += stats->packets;
 	fbn->tx_stats.dropped += stats->dropped;
-	fbn->tx_stats.ts_lost += stats->ts_lost;
-	fbn->tx_stats.ts_packets += stats->ts_packets;
+	fbn->tx_stats.twq.csum_partial += stats->twq.csum_partial;
+	fbn->tx_stats.twq.lso += stats->twq.lso;
+	fbn->tx_stats.twq.ts_lost += stats->twq.ts_lost;
+	fbn->tx_stats.twq.ts_packets += stats->twq.ts_packets;
+	fbn->tx_stats.twq.stop += stats->twq.stop;
+	fbn->tx_stats.twq.wake += stats->twq.wake;
+	/* Remember to add new stats here */
+	BUILD_BUG_ON(sizeof(fbn->tx_stats.twq) / 8 != 6);
 }
 
 static void fbnic_remove_tx_ring(struct fbnic_net *fbn,
@@ -1099,7 +1273,6 @@ static void fbnic_free_napi_vector(struct fbnic_net *fbn,
 				   struct fbnic_napi_vector *nv)
 {
 	struct fbnic_dev *fbd = nv->fbd;
-	u32 v_idx = nv->v_idx;
 	int i, j;
 
 	for (i = 0; i < nv->txt_count; i++) {
@@ -1113,31 +1286,20 @@ static void fbnic_free_napi_vector(struct fbnic_net *fbn,
 		fbnic_remove_rx_ring(fbn, &nv->qt[i].cmpl);
 	}
 
-	fbnic_free_irq(fbd, v_idx, nv);
+	fbnic_napi_free_irq(fbd, nv);
 	page_pool_destroy(nv->page_pool);
 	netif_napi_del(&nv->napi);
-	list_del(&nv->napis);
+	fbn->napi[fbnic_napi_idx(nv)] = NULL;
 	kfree(nv);
 }
 
 void fbnic_free_napi_vectors(struct fbnic_net *fbn)
 {
-	struct fbnic_napi_vector *nv, *temp;
-
-	list_for_each_entry_safe(nv, temp, &fbn->napis, napis)
-		fbnic_free_napi_vector(fbn, nv);
-}
-
-static void fbnic_name_napi_vector(struct fbnic_napi_vector *nv)
-{
-	unsigned char *dev_name = nv->napi.dev->name;
+	int i;
 
-	if (!nv->rxt_count)
-		snprintf(nv->name, sizeof(nv->name), "%s-Tx-%u", dev_name,
-			 nv->v_idx - FBNIC_NON_NAPI_VECTORS);
-	else
-		snprintf(nv->name, sizeof(nv->name), "%s-TxRx-%u", dev_name,
-			 nv->v_idx - FBNIC_NON_NAPI_VECTORS);
+	for (i = 0; i < fbn->num_napi; i++)
+		if (fbn->napi[i])
+			fbnic_free_napi_vector(fbn, fbn->napi[i]);
 }
 
 #define FBNIC_PAGE_POOL_FLAGS \
@@ -1154,7 +1316,9 @@ static int fbnic_alloc_nv_page_pool(struct fbnic_net *fbn,
 		.dev = nv->dev,
 		.dma_dir = DMA_BIDIRECTIONAL,
 		.offset = 0,
-		.max_len = PAGE_SIZE
+		.max_len = PAGE_SIZE,
+		.napi	= &nv->napi,
+		.netdev	= fbn->netdev,
 	};
 	struct page_pool *pp;
 
@@ -1222,7 +1386,7 @@ static int fbnic_alloc_napi_vector(struct fbnic_dev *fbd, struct fbnic_net *fbn,
 	nv->v_idx = v_idx;
 
 	/* Tie napi to netdev */
-	list_add(&nv->napis, &fbn->napis);
+	fbn->napi[fbnic_napi_idx(nv)] = nv;
 	netif_napi_add(fbn->netdev, &nv->napi, fbnic_poll);
 
 	/* Record IRQ to NAPI struct */
@@ -1239,12 +1403,8 @@ static int fbnic_alloc_napi_vector(struct fbnic_dev *fbd, struct fbnic_net *fbn,
 			goto napi_del;
 	}
 
-	/* Initialize vector name */
-	fbnic_name_napi_vector(nv);
-
 	/* Request the IRQ for napi vector */
-	err = fbnic_request_irq(fbd, v_idx, &fbnic_msix_clean_rings,
-				IRQF_SHARED, nv->name, nv);
+	err = fbnic_napi_request_irq(fbd, nv);
 	if (err)
 		goto pp_destroy;
 
@@ -1307,7 +1467,7 @@ pp_destroy:
 	page_pool_destroy(nv->page_pool);
 napi_del:
 	netif_napi_del(&nv->napi);
-	list_del(&nv->napis);
+	fbn->napi[fbnic_napi_idx(nv)] = NULL;
 	kfree(nv);
 	return err;
 }
@@ -1612,19 +1772,18 @@ free_resources:
 
 void fbnic_free_resources(struct fbnic_net *fbn)
 {
-	struct fbnic_napi_vector *nv;
+	int i;
 
-	list_for_each_entry(nv, &fbn->napis, napis)
-		fbnic_free_nv_resources(fbn, nv);
+	for (i = 0; i < fbn->num_napi; i++)
+		fbnic_free_nv_resources(fbn, fbn->napi[i]);
 }
 
 int fbnic_alloc_resources(struct fbnic_net *fbn)
 {
-	struct fbnic_napi_vector *nv;
-	int err = -ENODEV;
+	int i, err = -ENODEV;
 
-	list_for_each_entry(nv, &fbn->napis, napis) {
-		err = fbnic_alloc_nv_resources(fbn, nv);
+	for (i = 0; i < fbn->num_napi; i++) {
+		err = fbnic_alloc_nv_resources(fbn, fbn->napi[i]);
 		if (err)
 			goto free_resources;
 	}
@@ -1632,12 +1791,77 @@ int fbnic_alloc_resources(struct fbnic_net *fbn)
 	return 0;
 
 free_resources:
-	list_for_each_entry_continue_reverse(nv, &fbn->napis, napis)
-		fbnic_free_nv_resources(fbn, nv);
+	while (i--)
+		fbnic_free_nv_resources(fbn, fbn->napi[i]);
 
 	return err;
 }
 
+static void fbnic_set_netif_napi(struct fbnic_napi_vector *nv)
+{
+	int i, j;
+
+	/* Associate Tx queue with NAPI */
+	for (i = 0; i < nv->txt_count; i++) {
+		struct fbnic_q_triad *qt = &nv->qt[i];
+
+		netif_queue_set_napi(nv->napi.dev, qt->sub0.q_idx,
+				     NETDEV_QUEUE_TYPE_TX, &nv->napi);
+	}
+
+	/* Associate Rx queue with NAPI */
+	for (j = 0; j < nv->rxt_count; j++, i++) {
+		struct fbnic_q_triad *qt = &nv->qt[i];
+
+		netif_queue_set_napi(nv->napi.dev, qt->cmpl.q_idx,
+				     NETDEV_QUEUE_TYPE_RX, &nv->napi);
+	}
+}
+
+static void fbnic_reset_netif_napi(struct fbnic_napi_vector *nv)
+{
+	int i, j;
+
+	/* Disassociate Tx queue from NAPI */
+	for (i = 0; i < nv->txt_count; i++) {
+		struct fbnic_q_triad *qt = &nv->qt[i];
+
+		netif_queue_set_napi(nv->napi.dev, qt->sub0.q_idx,
+				     NETDEV_QUEUE_TYPE_TX, NULL);
+	}
+
+	/* Disassociate Rx queue from NAPI */
+	for (j = 0; j < nv->rxt_count; j++, i++) {
+		struct fbnic_q_triad *qt = &nv->qt[i];
+
+		netif_queue_set_napi(nv->napi.dev, qt->cmpl.q_idx,
+				     NETDEV_QUEUE_TYPE_RX, NULL);
+	}
+}
+
+int fbnic_set_netif_queues(struct fbnic_net *fbn)
+{
+	int i, err;
+
+	err = netif_set_real_num_queues(fbn->netdev, fbn->num_tx_queues,
+					fbn->num_rx_queues);
+	if (err)
+		return err;
+
+	for (i = 0; i < fbn->num_napi; i++)
+		fbnic_set_netif_napi(fbn->napi[i]);
+
+	return 0;
+}
+
+void fbnic_reset_netif_queues(struct fbnic_net *fbn)
+{
+	int i;
+
+	for (i = 0; i < fbn->num_napi; i++)
+		fbnic_reset_netif_napi(fbn->napi[i]);
+}
+
 static void fbnic_disable_twq0(struct fbnic_ring *txr)
 {
 	u32 twq_ctl = fbnic_ring_rd32(txr, FBNIC_QUEUE_TWQ0_CTL);
@@ -1670,33 +1894,34 @@ static void fbnic_disable_rcq(struct fbnic_ring *rxr)
 
 void fbnic_napi_disable(struct fbnic_net *fbn)
 {
-	struct fbnic_napi_vector *nv;
+	int i;
 
-	list_for_each_entry(nv, &fbn->napis, napis) {
-		napi_disable(&nv->napi);
+	for (i = 0; i < fbn->num_napi; i++) {
+		napi_disable(&fbn->napi[i]->napi);
 
-		fbnic_nv_irq_disable(nv);
+		fbnic_nv_irq_disable(fbn->napi[i]);
 	}
 }
 
 void fbnic_disable(struct fbnic_net *fbn)
 {
 	struct fbnic_dev *fbd = fbn->fbd;
-	struct fbnic_napi_vector *nv;
-	int i, j;
+	int i, j, t;
+
+	for (i = 0; i < fbn->num_napi; i++) {
+		struct fbnic_napi_vector *nv = fbn->napi[i];
 
-	list_for_each_entry(nv, &fbn->napis, napis) {
 		/* Disable Tx queue triads */
-		for (i = 0; i < nv->txt_count; i++) {
-			struct fbnic_q_triad *qt = &nv->qt[i];
+		for (t = 0; t < nv->txt_count; t++) {
+			struct fbnic_q_triad *qt = &nv->qt[t];
 
 			fbnic_disable_twq0(&qt->sub0);
 			fbnic_disable_tcq(&qt->cmpl);
 		}
 
 		/* Disable Rx queue triads */
-		for (j = 0; j < nv->rxt_count; j++, i++) {
-			struct fbnic_q_triad *qt = &nv->qt[i];
+		for (j = 0; j < nv->rxt_count; j++, t++) {
+			struct fbnic_q_triad *qt = &nv->qt[t];
 
 			fbnic_disable_bdq(&qt->sub0, &qt->sub1);
 			fbnic_disable_rcq(&qt->cmpl);
@@ -1792,14 +2017,15 @@ int fbnic_wait_all_queues_idle(struct fbnic_dev *fbd, bool may_fail)
 
 void fbnic_flush(struct fbnic_net *fbn)
 {
-	struct fbnic_napi_vector *nv;
+	int i;
 
-	list_for_each_entry(nv, &fbn->napis, napis) {
-		int i, j;
+	for (i = 0; i < fbn->num_napi; i++) {
+		struct fbnic_napi_vector *nv = fbn->napi[i];
+		int j, t;
 
 		/* Flush any processed Tx Queue Triads and drop the rest */
-		for (i = 0; i < nv->txt_count; i++) {
-			struct fbnic_q_triad *qt = &nv->qt[i];
+		for (t = 0; t < nv->txt_count; t++) {
+			struct fbnic_q_triad *qt = &nv->qt[t];
 			struct netdev_queue *tx_queue;
 
 			/* Clean the work queues of unprocessed work */
@@ -1816,15 +2042,11 @@ void fbnic_flush(struct fbnic_net *fbn)
 			tx_queue = netdev_get_tx_queue(nv->napi.dev,
 						       qt->sub0.q_idx);
 			netdev_tx_reset_queue(tx_queue);
-
-			/* Disassociate Tx queue from NAPI */
-			netif_queue_set_napi(nv->napi.dev, qt->sub0.q_idx,
-					     NETDEV_QUEUE_TYPE_TX, NULL);
 		}
 
 		/* Flush any processed Rx Queue Triads and drop the rest */
-		for (j = 0; j < nv->rxt_count; j++, i++) {
-			struct fbnic_q_triad *qt = &nv->qt[i];
+		for (j = 0; j < nv->rxt_count; j++, t++) {
+			struct fbnic_q_triad *qt = &nv->qt[t];
 
 			/* Clean the work queues of unprocessed work */
 			fbnic_clean_bdq(nv, 0, &qt->sub0, qt->sub0.tail);
@@ -1835,43 +2057,23 @@ void fbnic_flush(struct fbnic_net *fbn)
 
 			fbnic_put_pkt_buff(nv, qt->cmpl.pkt, 0);
 			qt->cmpl.pkt->buff.data_hard_start = NULL;
-
-			/* Disassociate Rx queue from NAPI */
-			netif_queue_set_napi(nv->napi.dev, qt->cmpl.q_idx,
-					     NETDEV_QUEUE_TYPE_RX, NULL);
 		}
 	}
 }
 
 void fbnic_fill(struct fbnic_net *fbn)
 {
-	struct fbnic_napi_vector *nv;
-
-	list_for_each_entry(nv, &fbn->napis, napis) {
-		int i, j;
-
-		/* Configure NAPI mapping for Tx */
-		for (i = 0; i < nv->txt_count; i++) {
-			struct fbnic_q_triad *qt = &nv->qt[i];
-
-			/* Nothing to do if Tx queue is disabled */
-			if (qt->sub0.flags & FBNIC_RING_F_DISABLED)
-				continue;
+	int i;
 
-			/* Associate Tx queue with NAPI */
-			netif_queue_set_napi(nv->napi.dev, qt->sub0.q_idx,
-					     NETDEV_QUEUE_TYPE_TX, &nv->napi);
-		}
+	for (i = 0; i < fbn->num_napi; i++) {
+		struct fbnic_napi_vector *nv = fbn->napi[i];
+		int j, t;
 
 		/* Configure NAPI mapping and populate pages
 		 * in the BDQ rings to use for Rx
 		 */
-		for (j = 0; j < nv->rxt_count; j++, i++) {
-			struct fbnic_q_triad *qt = &nv->qt[i];
-
-			/* Associate Rx queue with NAPI */
-			netif_queue_set_napi(nv->napi.dev, qt->cmpl.q_idx,
-					     NETDEV_QUEUE_TYPE_RX, &nv->napi);
+		for (j = 0, t = nv->txt_count; j < nv->rxt_count; j++, t++) {
+			struct fbnic_q_triad *qt = &nv->qt[t];
 
 			/* Populate the header and payload BDQs */
 			fbnic_fill_bdq(nv, &qt->sub0);
@@ -1984,9 +2186,51 @@ static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv,
 	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RDE_CTL0, rcq_ctl);
 }
 
+static void fbnic_config_rim_threshold(struct fbnic_ring *rcq, u16 nv_idx, u32 rx_desc)
+{
+	u32 threshold;
+
+	/* Set the threhsold to half the ring size if rx_frames
+	 * is not configured
+	 */
+	threshold = rx_desc ? : rcq->size_mask / 2;
+
+	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_CTL, nv_idx);
+	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_THRESHOLD, threshold);
+}
+
+void fbnic_config_txrx_usecs(struct fbnic_napi_vector *nv, u32 arm)
+{
+	struct fbnic_net *fbn = netdev_priv(nv->napi.dev);
+	struct fbnic_dev *fbd = nv->fbd;
+	u32 val = arm;
+
+	val |= FIELD_PREP(FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT, fbn->rx_usecs) |
+	       FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT_UPD_EN;
+	val |= FIELD_PREP(FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT, fbn->tx_usecs) |
+	       FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT_UPD_EN;
+
+	fbnic_wr32(fbd, FBNIC_INTR_CQ_REARM(nv->v_idx), val);
+}
+
+void fbnic_config_rx_frames(struct fbnic_napi_vector *nv)
+{
+	struct fbnic_net *fbn = netdev_priv(nv->napi.dev);
+	int i;
+
+	for (i = nv->txt_count; i < nv->rxt_count + nv->txt_count; i++) {
+		struct fbnic_q_triad *qt = &nv->qt[i];
+
+		fbnic_config_rim_threshold(&qt->cmpl, nv->v_idx,
+					   fbn->rx_max_frames *
+					   FBNIC_MIN_RXD_PER_FRAME);
+	}
+}
+
 static void fbnic_enable_rcq(struct fbnic_napi_vector *nv,
 			     struct fbnic_ring *rcq)
 {
+	struct fbnic_net *fbn = netdev_priv(nv->napi.dev);
 	u32 log_size = fls(rcq->size_mask);
 	u32 rcq_ctl;
 
@@ -2014,8 +2258,8 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv,
 	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RCQ_SIZE, log_size & 0xf);
 
 	/* Store interrupt information for the completion queue */
-	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_CTL, nv->v_idx);
-	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_THRESHOLD, rcq->size_mask / 2);
+	fbnic_config_rim_threshold(rcq, nv->v_idx, fbn->rx_max_frames *
+						   FBNIC_MIN_RXD_PER_FRAME);
 	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_MASK, 0);
 
 	/* Enable queue */
@@ -2025,21 +2269,23 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv,
 void fbnic_enable(struct fbnic_net *fbn)
 {
 	struct fbnic_dev *fbd = fbn->fbd;
-	struct fbnic_napi_vector *nv;
-	int i, j;
+	int i;
+
+	for (i = 0; i < fbn->num_napi; i++) {
+		struct fbnic_napi_vector *nv = fbn->napi[i];
+		int j, t;
 
-	list_for_each_entry(nv, &fbn->napis, napis) {
 		/* Setup Tx Queue Triads */
-		for (i = 0; i < nv->txt_count; i++) {
-			struct fbnic_q_triad *qt = &nv->qt[i];
+		for (t = 0; t < nv->txt_count; t++) {
+			struct fbnic_q_triad *qt = &nv->qt[t];
 
 			fbnic_enable_twq0(&qt->sub0);
 			fbnic_enable_tcq(nv, &qt->cmpl);
 		}
 
 		/* Setup Rx Queue Triads */
-		for (j = 0; j < nv->rxt_count; j++, i++) {
-			struct fbnic_q_triad *qt = &nv->qt[i];
+		for (j = 0; j < nv->rxt_count; j++, t++) {
+			struct fbnic_q_triad *qt = &nv->qt[t];
 
 			fbnic_enable_bdq(&qt->sub0, &qt->sub1);
 			fbnic_config_drop_mode_rcq(nv, &qt->cmpl);
@@ -2052,22 +2298,18 @@ void fbnic_enable(struct fbnic_net *fbn)
 
 static void fbnic_nv_irq_enable(struct fbnic_napi_vector *nv)
 {
-	struct fbnic_dev *fbd = nv->fbd;
-	u32 val;
-
-	val = FBNIC_INTR_CQ_REARM_INTR_UNMASK;
-
-	fbnic_wr32(fbd, FBNIC_INTR_CQ_REARM(nv->v_idx), val);
+	fbnic_config_txrx_usecs(nv, FBNIC_INTR_CQ_REARM_INTR_UNMASK);
 }
 
 void fbnic_napi_enable(struct fbnic_net *fbn)
 {
 	u32 irqs[FBNIC_MAX_MSIX_VECS / 32] = {};
 	struct fbnic_dev *fbd = fbn->fbd;
-	struct fbnic_napi_vector *nv;
 	int i;
 
-	list_for_each_entry(nv, &fbn->napis, napis) {
+	for (i = 0; i < fbn->num_napi; i++) {
+		struct fbnic_napi_vector *nv = fbn->napi[i];
+
 		napi_enable(&nv->napi);
 
 		fbnic_nv_irq_enable(nv);
@@ -2096,17 +2338,18 @@ void fbnic_napi_depletion_check(struct net_device *netdev)
 	struct fbnic_net *fbn = netdev_priv(netdev);
 	u32 irqs[FBNIC_MAX_MSIX_VECS / 32] = {};
 	struct fbnic_dev *fbd = fbn->fbd;
-	struct fbnic_napi_vector *nv;
-	int i, j;
+	int i, j, t;
+
+	for (i = 0; i < fbn->num_napi; i++) {
+		struct fbnic_napi_vector *nv = fbn->napi[i];
 
-	list_for_each_entry(nv, &fbn->napis, napis) {
 		/* Find RQs which are completely out of pages */
-		for (i = nv->txt_count, j = 0; j < nv->rxt_count; j++, i++) {
+		for (t = nv->txt_count, j = 0; j < nv->rxt_count; j++, t++) {
 			/* Assume 4 pages is always enough to fit a packet
 			 * and therefore generate a completion and an IRQ.
 			 */
-			if (fbnic_desc_used(&nv->qt[i].sub0) < 4 ||
-			    fbnic_desc_used(&nv->qt[i].sub1) < 4)
+			if (fbnic_desc_used(&nv->qt[t].sub0) < 4 ||
+			    fbnic_desc_used(&nv->qt[t].sub1) < 4)
 				irqs[nv->v_idx / 32] |= BIT(nv->v_idx % 32);
 		}
 	}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index 8d626287c3f4..f46616af41ea 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -24,13 +24,29 @@ struct fbnic_net;
 #define FBNIC_TX_DESC_WAKEUP	(FBNIC_MAX_SKB_DESC * 2)
 #define FBNIC_TX_DESC_MIN	roundup_pow_of_two(FBNIC_TX_DESC_WAKEUP)
 
+/* To receive the worst case packet we need:
+ *	1 descriptor for primary metadata
+ *	+ 1 descriptor for optional metadata
+ *	+ 1 descriptor for headers
+ *	+ 4 descriptors for payload
+ */
+#define FBNIC_MAX_RX_PKT_DESC	7
+#define FBNIC_RX_DESC_MIN	roundup_pow_of_two(FBNIC_MAX_RX_PKT_DESC * 2)
+
 #define FBNIC_MAX_TXQS			128u
 #define FBNIC_MAX_RXQS			128u
 
+/* These apply to TWQs, TCQ, RCQ */
+#define FBNIC_QUEUE_SIZE_MIN		16u
+#define FBNIC_QUEUE_SIZE_MAX		SZ_64K
+
 #define FBNIC_TXQ_SIZE_DEFAULT		1024
 #define FBNIC_HPQ_SIZE_DEFAULT		256
 #define FBNIC_PPQ_SIZE_DEFAULT		256
 #define FBNIC_RCQ_SIZE_DEFAULT		1024
+#define FBNIC_TX_USECS_DEFAULT		35
+#define FBNIC_RX_USECS_DEFAULT		30
+#define FBNIC_RX_FRAMES_DEFAULT		0
 
 #define FBNIC_RX_TROOM \
 	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
@@ -56,9 +72,22 @@ struct fbnic_pkt_buff {
 struct fbnic_queue_stats {
 	u64 packets;
 	u64 bytes;
+	union {
+		struct {
+			u64 csum_partial;
+			u64 lso;
+			u64 ts_packets;
+			u64 ts_lost;
+			u64 stop;
+			u64 wake;
+		} twq;
+		struct {
+			u64 alloc_failed;
+			u64 csum_complete;
+			u64 csum_none;
+		} rx;
+	};
 	u64 dropped;
-	u64 ts_packets;
-	u64 ts_lost;
 	struct u64_stats_sync syncp;
 };
 
@@ -104,14 +133,11 @@ struct fbnic_napi_vector {
 	struct device *dev;		/* Device for DMA unmapping */
 	struct page_pool *page_pool;
 	struct fbnic_dev *fbd;
-	char name[IFNAMSIZ + 9];
 
 	u16 v_idx;
 	u8 txt_count;
 	u8 rxt_count;
 
-	struct list_head napis;
-
 	struct fbnic_q_triad qt[];
 };
 
@@ -123,10 +149,18 @@ netdev_features_t
 fbnic_features_check(struct sk_buff *skb, struct net_device *dev,
 		     netdev_features_t features);
 
+void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn,
+				      struct fbnic_ring *rxr);
+void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
+				      struct fbnic_ring *txr);
+
 int fbnic_alloc_napi_vectors(struct fbnic_net *fbn);
 void fbnic_free_napi_vectors(struct fbnic_net *fbn);
 int fbnic_alloc_resources(struct fbnic_net *fbn);
 void fbnic_free_resources(struct fbnic_net *fbn);
+int fbnic_set_netif_queues(struct fbnic_net *fbn);
+void fbnic_reset_netif_queues(struct fbnic_net *fbn);
+irqreturn_t fbnic_msix_clean_rings(int irq, void *data);
 void fbnic_napi_enable(struct fbnic_net *fbn);
 void fbnic_napi_disable(struct fbnic_net *fbn);
 void fbnic_enable(struct fbnic_net *fbn);
@@ -137,4 +171,9 @@ void fbnic_fill(struct fbnic_net *fbn);
 void fbnic_napi_depletion_check(struct net_device *netdev);
 int fbnic_wait_all_queues_idle(struct fbnic_dev *fbd, bool may_fail);
 
+static inline int fbnic_napi_idx(const struct fbnic_napi_vector *nv)
+{
+	return nv->v_idx - FBNIC_NON_NAPI_VECTORS;
+}
+
 #endif /* _FBNIC_TXRX_H_ */
diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c
index 3062cc0f9199..c862b13b447a 100644
--- a/drivers/net/ethernet/micrel/ks8851_spi.c
+++ b/drivers/net/ethernet/micrel/ks8851_spi.c
@@ -20,8 +20,6 @@
 #include <linux/regulator/consumer.h>
 
 #include <linux/spi/spi.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
 #include <linux/of_net.h>
 
 #include "ks8851.h"
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index dc1d9f774565..cdde19b8edc4 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -3951,7 +3951,7 @@ static void ksz_stop_timer(struct ksz_timer_info *info)
 {
 	if (info->max) {
 		info->max = 0;
-		del_timer_sync(&info->timer);
+		timer_delete_sync(&info->timer);
 	}
 }
 
@@ -6304,7 +6304,8 @@ static void mib_read_work(struct work_struct *work)
 
 static void mib_monitor(struct timer_list *t)
 {
-	struct dev_info *hw_priv = from_timer(hw_priv, t, mib_timer_info.timer);
+	struct dev_info *hw_priv = timer_container_of(hw_priv, t,
+						      mib_timer_info.timer);
 
 	mib_read_work(&hw_priv->mib_read);
 
@@ -6331,7 +6332,8 @@ static void mib_monitor(struct timer_list *t)
  */
 static void dev_monitor(struct timer_list *t)
 {
-	struct dev_priv *priv = from_timer(priv, t, monitor_timer_info.timer);
+	struct dev_priv *priv = timer_container_of(priv, t,
+						   monitor_timer_info.timer);
 	struct net_device *dev = priv->mii_if.dev;
 	struct dev_info *hw_priv = priv->adapter;
 	struct ksz_hw *hw = &hw_priv->hw;
diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index 73832fb2bc32..ee046468652c 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -59,7 +59,6 @@ config LAN743X
 
 source "drivers/net/ethernet/microchip/lan865x/Kconfig"
 source "drivers/net/ethernet/microchip/lan966x/Kconfig"
-source "drivers/net/ethernet/microchip/lan969x/Kconfig"
 source "drivers/net/ethernet/microchip/sparx5/Kconfig"
 source "drivers/net/ethernet/microchip/vcap/Kconfig"
 source "drivers/net/ethernet/microchip/fdma/Kconfig"
diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile
index 7770df82200f..3c65baed9fd8 100644
--- a/drivers/net/ethernet/microchip/Makefile
+++ b/drivers/net/ethernet/microchip/Makefile
@@ -11,7 +11,6 @@ lan743x-objs := lan743x_main.o lan743x_ethtool.o lan743x_ptp.o
 
 obj-$(CONFIG_LAN865X) += lan865x/
 obj-$(CONFIG_LAN966X_SWITCH) += lan966x/
-obj-$(CONFIG_LAN969X_SWITCH) += lan969x/
 obj-$(CONFIG_SPARX5_SWITCH) += sparx5/
 obj-$(CONFIG_VCAP) += vcap/
 obj-$(CONFIG_FDMA) += fdma/
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 1a1cbd034eda..64a3b953cc17 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -18,6 +18,8 @@
 #define EEPROM_MAC_OFFSET		    (0x01)
 #define MAX_EEPROM_SIZE			    (512)
 #define MAX_OTP_SIZE			    (1024)
+#define MAX_HS_OTP_SIZE			    (8 * 1024)
+#define MAX_HS_EEPROM_SIZE		    (64 * 1024)
 #define OTP_INDICATOR_1			    (0xF3)
 #define OTP_INDICATOR_2			    (0xF7)
 
@@ -272,6 +274,9 @@ static int lan743x_hs_otp_read(struct lan743x_adapter *adapter, u32 offset,
 	int ret;
 	int i;
 
+	if (offset + length > MAX_HS_OTP_SIZE)
+		return -EINVAL;
+
 	ret = lan743x_hs_syslock_acquire(adapter, LOCK_TIMEOUT_MAX_CNT);
 	if (ret < 0)
 		return ret;
@@ -320,6 +325,9 @@ static int lan743x_hs_otp_write(struct lan743x_adapter *adapter, u32 offset,
 	int ret;
 	int i;
 
+	if (offset + length > MAX_HS_OTP_SIZE)
+		return -EINVAL;
+
 	ret = lan743x_hs_syslock_acquire(adapter, LOCK_TIMEOUT_MAX_CNT);
 	if (ret < 0)
 		return ret;
@@ -497,6 +505,9 @@ static int lan743x_hs_eeprom_read(struct lan743x_adapter *adapter,
 	u32 val;
 	int i;
 
+	if (offset + length > MAX_HS_EEPROM_SIZE)
+		return -EINVAL;
+
 	retval = lan743x_hs_syslock_acquire(adapter, LOCK_TIMEOUT_MAX_CNT);
 	if (retval < 0)
 		return retval;
@@ -539,6 +550,9 @@ static int lan743x_hs_eeprom_write(struct lan743x_adapter *adapter,
 	u32 val;
 	int i;
 
+	if (offset + length > MAX_HS_EEPROM_SIZE)
+		return -EINVAL;
+
 	retval = lan743x_hs_syslock_acquire(adapter, LOCK_TIMEOUT_MAX_CNT);
 	if (retval < 0)
 		return retval;
@@ -604,9 +618,9 @@ static int lan743x_ethtool_get_eeprom_len(struct net_device *netdev)
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 
 	if (adapter->flags & LAN743X_ADAPTER_FLAG_OTP)
-		return MAX_OTP_SIZE;
+		return adapter->is_pci11x1x ? MAX_HS_OTP_SIZE : MAX_OTP_SIZE;
 
-	return MAX_EEPROM_SIZE;
+	return adapter->is_pci11x1x ? MAX_HS_EEPROM_SIZE : MAX_EEPROM_SIZE;
 }
 
 static int lan743x_ethtool_get_eeprom(struct net_device *netdev,
@@ -1055,9 +1069,6 @@ static int lan743x_ethtool_get_eee(struct net_device *netdev,
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 
-	eee->tx_lpi_timer = lan743x_csr_read(adapter,
-					     MAC_EEE_TX_LPI_REQ_DLY_CNT);
-
 	return phylink_ethtool_get_eee(adapter->phylink, eee);
 }
 
@@ -1065,24 +1076,6 @@ static int lan743x_ethtool_set_eee(struct net_device *netdev,
 				   struct ethtool_keee *eee)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
-	u32 tx_lpi_timer;
-
-	tx_lpi_timer = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT);
-	if (tx_lpi_timer != eee->tx_lpi_timer) {
-		u32 mac_cr = lan743x_csr_read(adapter, MAC_CR);
-
-		/* Software should only change this field when Energy Efficient
-		 * Ethernet Enable (EEEEN) is cleared.
-		 * This function will trigger an autonegotiation restart and
-		 * eee will be reenabled during link up if eee was negotiated.
-		 */
-		lan743x_mac_eee_enable(adapter, false);
-		lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT,
-				  eee->tx_lpi_timer);
-
-		if (mac_cr & MAC_CR_EEE_EN_)
-			lan743x_mac_eee_enable(adapter, true);
-	}
 
 	return phylink_ethtool_set_eee(adapter->phylink, eee);
 }
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 4dc5adcda6a3..9d70b51ca91d 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1330,7 +1330,7 @@ static int lan743x_mac_set_mtu(struct lan743x_adapter *adapter, int new_mtu)
 }
 
 /* PHY */
-static int lan743x_phy_reset(struct lan743x_adapter *adapter)
+static int lan743x_hw_reset_phy(struct lan743x_adapter *adapter)
 {
 	u32 data;
 
@@ -1346,11 +1346,6 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter)
 				  50000, 1000000);
 }
 
-static int lan743x_phy_init(struct lan743x_adapter *adapter)
-{
-	return lan743x_phy_reset(adapter);
-}
-
 static void lan743x_phy_interface_select(struct lan743x_adapter *adapter)
 {
 	u32 id_rev;
@@ -1729,6 +1724,7 @@ int lan743x_rx_set_tstamp_mode(struct lan743x_adapter *adapter,
 	default:
 			return -ERANGE;
 	}
+	adapter->rx_tstamp_filter = rx_filter;
 	return 0;
 }
 
@@ -1815,6 +1811,7 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
 	if (nr_frags <= 0) {
 		tx->frame_data0 |= TX_DESC_DATA0_LS_;
 		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+		tx->frame_last = tx->frame_first;
 	}
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
@@ -1884,6 +1881,7 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx,
 		tx->frame_first = 0;
 		tx->frame_data0 = 0;
 		tx->frame_tail = 0;
+		tx->frame_last = 0;
 		return -ENOMEM;
 	}
 
@@ -1924,16 +1922,18 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 	    TX_DESC_DATA0_DTYPE_DATA_) {
 		tx->frame_data0 |= TX_DESC_DATA0_LS_;
 		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+		tx->frame_last = tx->frame_tail;
 	}
 
-	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
-	buffer_info = &tx->buffer_info[tx->frame_tail];
+	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_last];
+	buffer_info = &tx->buffer_info[tx->frame_last];
 	buffer_info->skb = skb;
 	if (time_stamp)
 		buffer_info->flags |= TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED;
 	if (ignore_sync)
 		buffer_info->flags |= TX_BUFFER_INFO_FLAG_IGNORE_SYNC;
 
+	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
 	tx->frame_tail = lan743x_tx_next_index(tx, tx->frame_tail);
 	tx->last_tail = tx->frame_tail;
@@ -2495,8 +2495,7 @@ static int lan743x_rx_process_buffer(struct lan743x_rx *rx)
 
 	/* save existing skb, allocate new skb and map to dma */
 	skb = buffer_info->skb;
-	if (lan743x_rx_init_ring_element(rx, rx->last_head,
-					 GFP_ATOMIC | GFP_DMA)) {
+	if (lan743x_rx_init_ring_element(rx, rx->last_head, GFP_ATOMIC)) {
 		/* failed to allocate next skb.
 		 * Memory is very low.
 		 * Drop this packet and reuse buffer.
@@ -2966,7 +2965,7 @@ static int lan743x_phylink_2500basex_config(struct lan743x_adapter *adapter)
 	return lan743x_pcs_power_reset(adapter);
 }
 
-void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable)
+static void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable)
 {
 	u32 mac_cr;
 
@@ -3027,10 +3026,8 @@ static void lan743x_phylink_mac_link_down(struct phylink_config *config,
 					  phy_interface_t interface)
 {
 	struct net_device *netdev = to_net_dev(config->dev);
-	struct lan743x_adapter *adapter = netdev_priv(netdev);
 
-	netif_tx_stop_all_queues(to_net_dev(config->dev));
-	lan743x_mac_eee_enable(adapter, false);
+	netif_tx_stop_all_queues(netdev);
 }
 
 static void lan743x_phylink_mac_link_up(struct phylink_config *config,
@@ -3072,16 +3069,40 @@ static void lan743x_phylink_mac_link_up(struct phylink_config *config,
 					  cap & FLOW_CTRL_TX,
 					  cap & FLOW_CTRL_RX);
 
-	if (phydev)
-		lan743x_mac_eee_enable(adapter, phydev->enable_tx_lpi);
-
 	netif_tx_wake_all_queues(netdev);
 }
 
+static void lan743x_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	lan743x_mac_eee_enable(adapter, false);
+}
+
+static int lan743x_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				     bool tx_clk_stop)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	/* Software should only change this field when Energy Efficient
+	 * Ethernet Enable (EEEEN) is cleared. We ensure that by clearing
+	 * EEEEN during probe, and phylink itself guarantees that
+	 * mac_disable_tx_lpi() will have been previously called.
+	 */
+	lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, timer);
+	lan743x_mac_eee_enable(adapter, true);
+
+	return 0;
+}
+
 static const struct phylink_mac_ops lan743x_phylink_mac_ops = {
 	.mac_config = lan743x_phylink_mac_config,
 	.mac_link_down = lan743x_phylink_mac_link_down,
 	.mac_link_up = lan743x_phylink_mac_link_up,
+	.mac_disable_tx_lpi = lan743x_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = lan743x_mac_enable_tx_lpi,
 };
 
 static int lan743x_phylink_create(struct lan743x_adapter *adapter)
@@ -3095,6 +3116,9 @@ static int lan743x_phylink_create(struct lan743x_adapter *adapter)
 
 	adapter->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
 		MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD;
+	adapter->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD;
+	adapter->phylink_config.lpi_timer_default =
+		lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT);
 
 	lan743x_phy_interface_select(adapter);
 
@@ -3120,6 +3144,10 @@ static int lan743x_phylink_create(struct lan743x_adapter *adapter)
 		phy_interface_set_rgmii(adapter->phylink_config.supported_interfaces);
 	}
 
+	memcpy(adapter->phylink_config.lpi_interfaces,
+	       adapter->phylink_config.supported_interfaces,
+	       sizeof(adapter->phylink_config.lpi_interfaces));
+
 	pl = phylink_create(&adapter->phylink_config, NULL,
 			    adapter->phy_interface, &lan743x_phylink_mac_ops);
 
@@ -3319,8 +3347,6 @@ static int lan743x_netdev_ioctl(struct net_device *netdev,
 
 	if (!netif_running(netdev))
 		return -EINVAL;
-	if (cmd == SIOCSHWTSTAMP)
-		return lan743x_ptp_ioctl(netdev, ifr, cmd);
 
 	return phylink_mii_ioctl(adapter->phylink, ifr, cmd);
 }
@@ -3415,6 +3441,8 @@ static const struct net_device_ops lan743x_netdev_ops = {
 	.ndo_change_mtu		= lan743x_netdev_change_mtu,
 	.ndo_get_stats64	= lan743x_netdev_get_stats64,
 	.ndo_set_mac_address	= lan743x_netdev_set_mac_address,
+	.ndo_hwtstamp_get	= lan743x_ptp_hwtstamp_get,
+	.ndo_hwtstamp_set	= lan743x_ptp_hwtstamp_set,
 };
 
 static void lan743x_hardware_cleanup(struct lan743x_adapter *adapter)
@@ -3462,6 +3490,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 				 struct pci_dev *pdev)
 {
 	struct lan743x_tx *tx;
+	u32 sgmii_ctl;
 	int index;
 	int ret;
 
@@ -3474,6 +3503,15 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 		spin_lock_init(&adapter->eth_syslock_spinlock);
 		mutex_init(&adapter->sgmii_rw_lock);
 		pci11x1x_set_rfe_rd_fifo_threshold(adapter);
+		sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
+		if (adapter->is_sgmii_en) {
+			sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_;
+			sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_;
+		} else {
+			sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_;
+			sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_;
+		}
+		lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 	} else {
 		adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS;
 		adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS;
@@ -3491,10 +3529,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 	if (ret)
 		return ret;
 
-	ret = lan743x_phy_init(adapter);
-	if (ret)
-		return ret;
-
 	ret = lan743x_ptp_init(adapter);
 	if (ret)
 		return ret;
@@ -3517,12 +3551,14 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 		spin_lock_init(&tx->ring_lock);
 	}
 
+	/* Ensure EEEEN is clear */
+	lan743x_mac_eee_enable(adapter, false);
+
 	return 0;
 }
 
 static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 {
-	u32 sgmii_ctl;
 	int ret;
 
 	adapter->mdiobus = devm_mdiobus_alloc(&adapter->pdev->dev);
@@ -3534,10 +3570,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 	adapter->mdiobus->priv = (void *)adapter;
 	if (adapter->is_pci11x1x) {
 		if (adapter->is_sgmii_en) {
-			sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
-			sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_;
-			sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_;
-			lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "SGMII operation\n");
 			adapter->mdiobus->read = lan743x_mdiobus_read_c22;
@@ -3548,10 +3580,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "lan743x-mdiobus-c45\n");
 		} else {
-			sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
-			sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_;
-			sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_;
-			lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "RGMII operation\n");
 			// Only C22 support when RGMII I/F
@@ -3637,6 +3665,10 @@ static int lan743x_pcidev_probe(struct pci_dev *pdev,
 	if (ret)
 		goto cleanup_pci;
 
+	ret = lan743x_hw_reset_phy(adapter);
+	if (ret)
+		goto cleanup_pci;
+
 	ret = lan743x_hardware_init(adapter, pdev);
 	if (ret)
 		goto cleanup_pci;
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 8ef897c114d3..02a28b709163 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -980,6 +980,7 @@ struct lan743x_tx {
 	u32		frame_first;
 	u32		frame_data0;
 	u32		frame_tail;
+	u32		frame_last;
 
 	struct lan743x_tx_buffer_info *buffer_info;
 
@@ -1086,6 +1087,7 @@ struct lan743x_adapter {
 	phy_interface_t		phy_interface;
 	struct phylink		*phylink;
 	struct phylink_config	phylink_config;
+	int			rx_tstamp_filter;
 };
 
 #define LAN743X_COMPONENT_FLAG_RX(channel)  BIT(20 + (channel))
@@ -1206,6 +1208,5 @@ void lan743x_hs_syslock_release(struct lan743x_adapter *adapter);
 void lan743x_mac_flow_ctrl_set_enables(struct lan743x_adapter *adapter,
 				       bool tx_enable, bool rx_enable);
 int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr);
-void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable);
 
 #endif /* _LAN743X_H */
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
index 4a777b449ecd..a3b48388b3fd 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -463,10 +463,6 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on,
 	struct lan743x_ptp_perout *perout = &ptp->perout[index];
 	int ret = 0;
 
-	/* Reject requests with unsupported flags */
-	if (perout_request->flags & ~PTP_PEROUT_DUTY_CYCLE)
-		return -EOPNOTSUPP;
-
 	if (on) {
 		perout_pin = ptp_find_pin(ptp->ptp_clock, PTP_PF_PEROUT,
 					  perout_request->index);
@@ -1537,6 +1533,10 @@ int lan743x_ptp_open(struct lan743x_adapter *adapter)
 	ptp->ptp_clock_info.n_per_out = LAN743X_PTP_N_EVENT_CHAN;
 	ptp->ptp_clock_info.n_pins = n_pins;
 	ptp->ptp_clock_info.pps = LAN743X_PTP_N_PPS;
+	ptp->ptp_clock_info.supported_extts_flags = PTP_RISING_EDGE |
+						    PTP_FALLING_EDGE |
+						    PTP_STRICT_FLAGS;
+	ptp->ptp_clock_info.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE;
 	ptp->ptp_clock_info.pin_config = ptp->pin_config;
 	ptp->ptp_clock_info.adjfine = lan743x_ptpci_adjfine;
 	ptp->ptp_clock_info.adjtime = lan743x_ptpci_adjtime;
@@ -1736,23 +1736,32 @@ void lan743x_ptp_tx_timestamp_skb(struct lan743x_adapter *adapter,
 	lan743x_ptp_tx_ts_complete(adapter);
 }
 
-int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+int lan743x_ptp_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config config;
-	int ret = 0;
-	int index;
+	struct lan743x_tx *tx = &adapter->tx[0];
 
-	if (!ifr) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "SIOCSHWTSTAMP, ifr == NULL\n");
-		return -EINVAL;
-	}
+	if (tx->ts_flags & TX_TS_FLAG_ONE_STEP_SYNC)
+		config->tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
+	else if (tx->ts_flags & TX_TS_FLAG_TIMESTAMPING_ENABLED)
+		config->tx_type = HWTSTAMP_TX_ON;
+	else
+		config->tx_type = HWTSTAMP_TX_OFF;
+
+	config->rx_filter = adapter->rx_tstamp_filter;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	return 0;
+}
 
-	switch (config.tx_type) {
+int lan743x_ptp_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int index;
+
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		for (index = 0; index < adapter->used_tx_channels;
 		     index++)
@@ -1776,19 +1785,12 @@ int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 		lan743x_ptp_set_sync_ts_insert(adapter, true);
 		break;
 	case HWTSTAMP_TX_ONESTEP_P2P:
-		ret = -ERANGE;
-		break;
+		return -ERANGE;
 	default:
 		netif_warn(adapter, drv, adapter->netdev,
-			   "  tx_type = %d, UNKNOWN\n", config.tx_type);
-		ret = -EINVAL;
-		break;
+			   "  tx_type = %d, UNKNOWN\n", config->tx_type);
+		return -EINVAL;
 	}
 
-	ret = lan743x_rx_set_tstamp_mode(adapter, config.rx_filter);
-
-	if (!ret)
-		return copy_to_user(ifr->ifr_data, &config,
-			sizeof(config)) ? -EFAULT : 0;
-	return ret;
+	return lan743x_rx_set_tstamp_mode(adapter, config->rx_filter);
 }
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
index 0d29914cd460..f33dc83c5700 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.h
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -18,9 +18,9 @@
  */
 #define LAN743X_PTP_N_EVENT_CHAN	2
 #define LAN743X_PTP_N_PEROUT		LAN743X_PTP_N_EVENT_CHAN
-#define LAN743X_PTP_N_EXTTS		4
-#define LAN743X_PTP_N_PPS		0
 #define PCI11X1X_PTP_IO_MAX_CHANNELS	8
+#define LAN743X_PTP_N_EXTTS		PCI11X1X_PTP_IO_MAX_CHANNELS
+#define LAN743X_PTP_N_PPS		0
 #define PTP_CMD_CTL_TIMEOUT_CNT		50
 
 struct lan743x_adapter;
@@ -51,8 +51,11 @@ int lan743x_ptp_open(struct lan743x_adapter *adapter);
 void lan743x_ptp_close(struct lan743x_adapter *adapter);
 void lan743x_ptp_update_latency(struct lan743x_adapter *adapter,
 				u32 link_speed);
-
-int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
+int lan743x_ptp_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config);
+int lan743x_ptp_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack);
 
 #define LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS (4)
 
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 3234a960fcc3..7001584f1b7a 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -353,6 +353,11 @@ static void lan966x_ifh_set_rew_op(void *ifh, u64 rew_op)
 	lan966x_ifh_set(ifh, rew_op, IFH_POS_REW_CMD, IFH_WID_REW_CMD);
 }
 
+static void lan966x_ifh_set_oam_type(void *ifh, u64 oam_type)
+{
+	lan966x_ifh_set(ifh, oam_type, IFH_POS_PDU_TYPE, IFH_WID_PDU_TYPE);
+}
+
 static void lan966x_ifh_set_timestamp(void *ifh, u64 timestamp)
 {
 	lan966x_ifh_set(ifh, timestamp, IFH_POS_TIMESTAMP, IFH_WID_TIMESTAMP);
@@ -380,6 +385,7 @@ static netdev_tx_t lan966x_port_xmit(struct sk_buff *skb,
 			return err;
 
 		lan966x_ifh_set_rew_op(ifh, LAN966X_SKB_CB(skb)->rew_op);
+		lan966x_ifh_set_oam_type(ifh, LAN966X_SKB_CB(skb)->pdu_type);
 		lan966x_ifh_set_timestamp(ifh, LAN966X_SKB_CB(skb)->ts_id);
 	}
 
@@ -828,7 +834,6 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p,
 	port->phylink_config.type = PHYLINK_NETDEV;
 	port->phylink_pcs.poll = true;
 	port->phylink_pcs.ops = &lan966x_phylink_pcs_ops;
-	port->phylink_pcs.neg_mode = true;
 
 	port->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD;
@@ -874,6 +879,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p,
 	lan966x_vlan_port_set_vlan_aware(port, 0);
 	lan966x_vlan_port_set_vid(port, HOST_PVID, false, false);
 	lan966x_vlan_port_apply(port);
+	lan966x_vlan_port_rew_host(port);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 25cb2f61986f..4f75f0688369 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -75,6 +75,10 @@
 #define IFH_REW_OP_ONE_STEP_PTP		0x3
 #define IFH_REW_OP_TWO_STEP_PTP		0x4
 
+#define IFH_PDU_TYPE_NONE		0
+#define IFH_PDU_TYPE_IPV4		7
+#define IFH_PDU_TYPE_IPV6		8
+
 #define FDMA_RX_DCB_MAX_DBS		1
 #define FDMA_TX_DCB_MAX_DBS		1
 
@@ -254,6 +258,7 @@ struct lan966x_phc {
 
 struct lan966x_skb_cb {
 	u8 rew_op;
+	u8 pdu_type;
 	u16 ts_id;
 	unsigned long jiffies;
 };
@@ -443,7 +448,7 @@ int lan966x_stats_init(struct lan966x *lan966x);
 
 void lan966x_port_config_down(struct lan966x_port *port);
 void lan966x_port_config_up(struct lan966x_port *port);
-void lan966x_port_status_get(struct lan966x_port *port,
+void lan966x_port_status_get(struct lan966x_port *port, unsigned int neg_mode,
 			     struct phylink_link_state *state);
 int lan966x_port_pcs_set(struct lan966x_port *port,
 			 struct lan966x_port_config *config);
@@ -492,6 +497,7 @@ void lan966x_vlan_port_apply(struct lan966x_port *port);
 bool lan966x_vlan_cpu_member_cpu_vlan_mask(struct lan966x *lan966x, u16 vid);
 void lan966x_vlan_port_set_vlan_aware(struct lan966x_port *port,
 				      bool vlan_aware);
+void lan966x_vlan_port_rew_host(struct lan966x_port *port);
 int lan966x_vlan_port_set_vid(struct lan966x_port *port,
 			      u16 vid,
 			      bool pvid,
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c
index 1d63903f9006..75188b99e4e7 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c
@@ -88,11 +88,12 @@ static struct lan966x_port *lan966x_pcs_to_port(struct phylink_pcs *pcs)
 }
 
 static void lan966x_pcs_get_state(struct phylink_pcs *pcs,
+				  unsigned int neg_mode,
 				  struct phylink_link_state *state)
 {
 	struct lan966x_port *port = lan966x_pcs_to_port(pcs);
 
-	lan966x_port_status_get(port, state);
+	lan966x_port_status_get(port, neg_mode, state);
 }
 
 static int lan966x_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
index fdfa4040d9ee..cf7de0267c32 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
@@ -284,7 +284,7 @@ void lan966x_port_config_up(struct lan966x_port *port)
 	lan966x_port_link_up(port);
 }
 
-void lan966x_port_status_get(struct lan966x_port *port,
+void lan966x_port_status_get(struct lan966x_port *port, unsigned int neg_mode,
 			     struct phylink_link_state *state)
 {
 	struct lan966x *lan966x = port->lan966x;
@@ -314,7 +314,7 @@ void lan966x_port_status_get(struct lan966x_port *port,
 		bmsr |= BMSR_ANEGCOMPLETE;
 
 		lp_adv = DEV_PCS1G_ANEG_STATUS_LP_ADV_GET(val);
-		phylink_mii_c22_pcs_decode_state(state, bmsr, lp_adv);
+		phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lp_adv);
 	} else {
 		if (!state->link)
 			return;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
index 63905bb5a63a..b4377b8613c3 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
@@ -322,34 +322,55 @@ void lan966x_ptp_hwtstamp_get(struct lan966x_port *port,
 	*cfg = phc->hwtstamp_config;
 }
 
-static int lan966x_ptp_classify(struct lan966x_port *port, struct sk_buff *skb)
+static void lan966x_ptp_classify(struct lan966x_port *port, struct sk_buff *skb,
+				 u8 *rew_op, u8 *pdu_type)
 {
 	struct ptp_header *header;
 	u8 msgtype;
 	int type;
 
-	if (port->ptp_tx_cmd == IFH_REW_OP_NOOP)
-		return IFH_REW_OP_NOOP;
+	if (port->ptp_tx_cmd == IFH_REW_OP_NOOP) {
+		*rew_op = IFH_REW_OP_NOOP;
+		*pdu_type = IFH_PDU_TYPE_NONE;
+		return;
+	}
 
 	type = ptp_classify_raw(skb);
-	if (type == PTP_CLASS_NONE)
-		return IFH_REW_OP_NOOP;
+	if (type == PTP_CLASS_NONE) {
+		*rew_op = IFH_REW_OP_NOOP;
+		*pdu_type = IFH_PDU_TYPE_NONE;
+		return;
+	}
 
 	header = ptp_parse_header(skb, type);
-	if (!header)
-		return IFH_REW_OP_NOOP;
+	if (!header) {
+		*rew_op = IFH_REW_OP_NOOP;
+		*pdu_type = IFH_PDU_TYPE_NONE;
+		return;
+	}
 
-	if (port->ptp_tx_cmd == IFH_REW_OP_TWO_STEP_PTP)
-		return IFH_REW_OP_TWO_STEP_PTP;
+	if (type & PTP_CLASS_L2)
+		*pdu_type = IFH_PDU_TYPE_NONE;
+	if (type & PTP_CLASS_IPV4)
+		*pdu_type = IFH_PDU_TYPE_IPV4;
+	if (type & PTP_CLASS_IPV6)
+		*pdu_type = IFH_PDU_TYPE_IPV6;
+
+	if (port->ptp_tx_cmd == IFH_REW_OP_TWO_STEP_PTP) {
+		*rew_op = IFH_REW_OP_TWO_STEP_PTP;
+		return;
+	}
 
 	/* If it is sync and run 1 step then set the correct operation,
 	 * otherwise run as 2 step
 	 */
 	msgtype = ptp_get_msgtype(header, type);
-	if ((msgtype & 0xf) == 0)
-		return IFH_REW_OP_ONE_STEP_PTP;
+	if ((msgtype & 0xf) == 0) {
+		*rew_op = IFH_REW_OP_ONE_STEP_PTP;
+		return;
+	}
 
-	return IFH_REW_OP_TWO_STEP_PTP;
+	*rew_op = IFH_REW_OP_TWO_STEP_PTP;
 }
 
 static void lan966x_ptp_txtstamp_old_release(struct lan966x_port *port)
@@ -374,10 +395,12 @@ int lan966x_ptp_txtstamp_request(struct lan966x_port *port,
 {
 	struct lan966x *lan966x = port->lan966x;
 	unsigned long flags;
+	u8 pdu_type;
 	u8 rew_op;
 
-	rew_op = lan966x_ptp_classify(port, skb);
+	lan966x_ptp_classify(port, skb, &rew_op, &pdu_type);
 	LAN966X_SKB_CB(skb)->rew_op = rew_op;
+	LAN966X_SKB_CB(skb)->pdu_type = pdu_type;
 
 	if (rew_op != IFH_REW_OP_TWO_STEP_PTP)
 		return 0;
@@ -815,10 +838,6 @@ static int lan966x_ptp_perout(struct ptp_clock_info *ptp,
 	bool pps = false;
 	int pin;
 
-	if (rq->perout.flags & ~(PTP_PEROUT_DUTY_CYCLE |
-				 PTP_PEROUT_PHASE))
-		return -EOPNOTSUPP;
-
 	pin = ptp_find_pin(phc->clock, PTP_PF_PEROUT, rq->perout.index);
 	if (pin == -1 || pin >= LAN966X_PHC_PINS_NUM)
 		return -EINVAL;
@@ -917,12 +936,6 @@ static int lan966x_ptp_extts(struct ptp_clock_info *ptp,
 	if (lan966x->ptp_ext_irq <= 0)
 		return -EOPNOTSUPP;
 
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	pin = ptp_find_pin(phc->clock, PTP_PF_EXTTS, rq->extts.index);
 	if (pin == -1 || pin >= LAN966X_PHC_PINS_NUM)
 		return -EINVAL;
@@ -978,6 +991,10 @@ static struct ptp_clock_info lan966x_ptp_clock_info = {
 	.n_per_out	= LAN966X_PHC_PINS_NUM,
 	.n_ext_ts	= LAN966X_PHC_PINS_NUM,
 	.n_pins		= LAN966X_PHC_PINS_NUM,
+	.supported_extts_flags = PTP_RISING_EDGE |
+				 PTP_STRICT_FLAGS,
+	.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE |
+				  PTP_PEROUT_PHASE,
 };
 
 static int lan966x_ptp_phc_init(struct lan966x *lan966x,
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
index 1c88120eb291..bcb4db76b75c 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
@@ -297,6 +297,7 @@ static void lan966x_port_bridge_leave(struct lan966x_port *port,
 	lan966x_vlan_port_set_vlan_aware(port, false);
 	lan966x_vlan_port_set_vid(port, HOST_PVID, false, false);
 	lan966x_vlan_port_apply(port);
+	lan966x_vlan_port_rew_host(port);
 }
 
 int lan966x_port_changeupper(struct net_device *dev,
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
index fa34a739c748..7da22520724c 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
@@ -149,6 +149,27 @@ void lan966x_vlan_port_set_vlan_aware(struct lan966x_port *port,
 	port->vlan_aware = vlan_aware;
 }
 
+/* When the interface is in host mode, the interface should not be vlan aware
+ * but it should insert all the tags that it gets from the network stack.
+ * The tags are not in the data of the frame but actually in the skb and the ifh
+ * is configured already to get this tag. So what we need to do is to update the
+ * rewriter to insert the vlan tag for all frames which have a vlan tag
+ * different than 0.
+ */
+void lan966x_vlan_port_rew_host(struct lan966x_port *port)
+{
+	struct lan966x *lan966x = port->lan966x;
+	u32 val;
+
+	/* Tag all frames except when VID=0*/
+	val = REW_TAG_CFG_TAG_CFG_SET(2);
+
+	/* Update only some bits in the register */
+	lan_rmw(val,
+		REW_TAG_CFG_TAG_CFG,
+		lan966x, REW_TAG_CFG(port->chip_port));
+}
+
 void lan966x_vlan_port_apply(struct lan966x_port *port)
 {
 	struct lan966x *lan966x = port->lan966x;
diff --git a/drivers/net/ethernet/microchip/lan969x/Kconfig b/drivers/net/ethernet/microchip/lan969x/Kconfig
deleted file mode 100644
index c5c6122ae2ec..000000000000
--- a/drivers/net/ethernet/microchip/lan969x/Kconfig
+++ /dev/null
@@ -1,5 +0,0 @@
-config LAN969X_SWITCH
-	bool "Lan969x switch driver"
-	depends on SPARX5_SWITCH
-	help
-	  This driver supports the lan969x family of network switch devices.
diff --git a/drivers/net/ethernet/microchip/lan969x/Makefile b/drivers/net/ethernet/microchip/lan969x/Makefile
deleted file mode 100644
index 316405cbbc71..000000000000
--- a/drivers/net/ethernet/microchip/lan969x/Makefile
+++ /dev/null
@@ -1,13 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile for the Microchip lan969x network device drivers.
-#
-
-obj-$(CONFIG_SPARX5_SWITCH) += lan969x-switch.o
-
-lan969x-switch-y := lan969x_regs.o lan969x.o lan969x_calendar.o \
- lan969x_vcap_ag_api.o lan969x_vcap_impl.o
-
-# Provide include files
-ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/fdma
-ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap
diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig
index 3f04992eace6..35e1c0cf345e 100644
--- a/drivers/net/ethernet/microchip/sparx5/Kconfig
+++ b/drivers/net/ethernet/microchip/sparx5/Kconfig
@@ -24,3 +24,10 @@ config SPARX5_DCB
 	  DSCP and PCP.
 
 	  If unsure, set to Y.
+
+config LAN969X_SWITCH
+	bool "Lan969x switch driver"
+	depends on SPARX5_SWITCH
+	select PAGE_POOL
+	help
+	  This driver supports the lan969x family of network switch devices.
diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile
index 3435ca86dd70..d447f9e84d92 100644
--- a/drivers/net/ethernet/microchip/sparx5/Makefile
+++ b/drivers/net/ethernet/microchip/sparx5/Makefile
@@ -16,6 +16,14 @@ sparx5-switch-y  := sparx5_main.o sparx5_packet.o \
 sparx5-switch-$(CONFIG_SPARX5_DCB) += sparx5_dcb.o
 sparx5-switch-$(CONFIG_DEBUG_FS) += sparx5_vcap_debugfs.o
 
+sparx5-switch-$(CONFIG_LAN969X_SWITCH) += lan969x/lan969x_regs.o \
+					  lan969x/lan969x.o \
+					  lan969x/lan969x_calendar.o \
+					  lan969x/lan969x_vcap_ag_api.o \
+					  lan969x/lan969x_vcap_impl.o \
+					  lan969x/lan969x_rgmii.o \
+					  lan969x/lan969x_fdma.o
+
 # Provide include files
 ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap
 ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/fdma
diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c
index ac37d0f74ee3..f3a9c71bea36 100644
--- a/drivers/net/ethernet/microchip/lan969x/lan969x.c
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c
@@ -90,9 +90,12 @@ static const struct sparx5_main_io_resource lan969x_main_iomap[] =  {
 	{ TARGET_DEV2G5 + 27,         0x30d8000, 1 }, /* 0xe30d8000 */
 	{ TARGET_DEV10G +  9,         0x30dc000, 1 }, /* 0xe30dc000 */
 	{ TARGET_PCS10G_BR +  9,      0x30e0000, 1 }, /* 0xe30e0000 */
+	{ TARGET_DEVRGMII,            0x30e4000, 1 }, /* 0xe30e4000 */
+	{ TARGET_DEVRGMII +  1,       0x30e8000, 1 }, /* 0xe30e8000 */
 	{ TARGET_DSM,                 0x30ec000, 1 }, /* 0xe30ec000 */
 	{ TARGET_PORT_CONF,           0x30f0000, 1 }, /* 0xe30f0000 */
 	{ TARGET_ASM,                 0x3200000, 1 }, /* 0xe3200000 */
+	{ TARGET_HSIO_WRAP,           0x3408000, 1 }, /* 0xe3408000 */
 };
 
 static struct sparx5_sdlb_group lan969x_sdlb_groups[LAN969X_SDLB_GRP_CNT] = {
@@ -273,9 +276,9 @@ static irqreturn_t lan969x_ptp_irq_handler(int irq, void *args)
 		if (WARN_ON(!skb_match))
 			continue;
 
-		spin_lock(&sparx5->ptp_ts_id_lock);
+		spin_lock_irqsave(&sparx5->ptp_ts_id_lock, flags);
 		sparx5->ptp_skbs--;
-		spin_unlock(&sparx5->ptp_ts_id_lock);
+		spin_unlock_irqrestore(&sparx5->ptp_ts_id_lock, flags);
 
 		/* Get the h/w timestamp */
 		sparx5_get_hwtimestamp(sparx5, &ts, delay);
@@ -329,6 +332,7 @@ static const struct sparx5_ops lan969x_ops = {
 	.is_port_5g              = &lan969x_port_is_5g,
 	.is_port_10g             = &lan969x_port_is_10g,
 	.is_port_25g             = &lan969x_port_is_25g,
+	.is_port_rgmii           = &lan969x_port_is_rgmii,
 	.get_port_dev_index      = &lan969x_port_dev_mapping,
 	.get_port_dev_bit        = &lan969x_get_dev_mode_bit,
 	.get_hsch_max_group_rate = &lan969x_get_hsch_max_group_rate,
@@ -336,6 +340,11 @@ static const struct sparx5_ops lan969x_ops = {
 	.set_port_mux            = &lan969x_port_mux_set,
 	.ptp_irq_handler         = &lan969x_ptp_irq_handler,
 	.dsm_calendar_calc       = &lan969x_dsm_calendar_calc,
+	.port_config_rgmii       = &lan969x_port_config_rgmii,
+	.fdma_init               = &lan969x_fdma_init,
+	.fdma_deinit             = &lan969x_fdma_deinit,
+	.fdma_poll               = &lan969x_fdma_napi_poll,
+	.fdma_xmit               = &lan969x_fdma_xmit,
 };
 
 const struct sparx5_match_data lan969x_desc = {
@@ -346,8 +355,3 @@ const struct sparx5_match_data lan969x_desc = {
 	.consts     = &lan969x_consts,
 	.ops        = &lan969x_ops,
 };
-EXPORT_SYMBOL_GPL(lan969x_desc);
-
-MODULE_DESCRIPTION("Microchip lan969x switch driver");
-MODULE_AUTHOR("Daniel Machon <daniel.machon@microchip.com>");
-MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x.h b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h
index 2489d0d32dfd..529fde3d4deb 100644
--- a/drivers/net/ethernet/microchip/lan969x/lan969x.h
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h
@@ -59,7 +59,24 @@ static inline bool lan969x_port_is_25g(int portno)
 	return false;
 }
 
+static inline bool lan969x_port_is_rgmii(int portno)
+{
+	return portno == 28 || portno == 29;
+}
+
 /* lan969x_calendar.c */
 int lan969x_dsm_calendar_calc(struct sparx5 *sparx5, u32 taxi,
 			      struct sparx5_calendar_data *data);
+
+/* lan969x_rgmii.c */
+int lan969x_port_config_rgmii(struct sparx5_port *port,
+			      struct sparx5_port_config *conf);
+
+/* lan969x_fdma.c */
+int lan969x_fdma_init(struct sparx5 *sparx5);
+int lan969x_fdma_deinit(struct sparx5 *sparx5);
+int lan969x_fdma_napi_poll(struct napi_struct *napi, int weight);
+int lan969x_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb,
+		      struct net_device *dev);
+
 #endif
diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x_calendar.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_calendar.c
index e857640df185..e857640df185 100644
--- a/drivers/net/ethernet/microchip/lan969x/lan969x_calendar.c
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_calendar.c
diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c
new file mode 100644
index 000000000000..1282f5c3ee6d
--- /dev/null
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Microchip lan969x Switch driver
+ *
+ * Copyright (c) 2025 Microchip Technology Inc. and its subsidiaries.
+ */
+#include <net/page_pool/helpers.h>
+
+#include "../sparx5_main.h"
+#include "../sparx5_main_regs.h"
+#include "../sparx5_port.h"
+
+#include "fdma_api.h"
+#include "lan969x.h"
+
+#define FDMA_PRIV(fdma) ((struct sparx5 *)((fdma)->priv))
+
+static int lan969x_fdma_tx_dataptr_cb(struct fdma *fdma, int dcb, int db,
+				      u64 *dataptr)
+{
+	*dataptr = FDMA_PRIV(fdma)->tx.dbs[dcb].dma_addr;
+
+	return 0;
+}
+
+static int lan969x_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db,
+				      u64 *dataptr)
+{
+	struct sparx5_rx *rx = &FDMA_PRIV(fdma)->rx;
+	struct page *page;
+
+	page = page_pool_dev_alloc_pages(rx->page_pool);
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	rx->page[dcb][db] = page;
+
+	*dataptr = page_pool_get_dma_addr(page);
+
+	return 0;
+}
+
+static int lan969x_fdma_get_next_dcb(struct sparx5_tx *tx)
+{
+	struct fdma *fdma = &tx->fdma;
+
+	for (int i = 0; i < fdma->n_dcbs; ++i)
+		if (!tx->dbs[i].used && !fdma_is_last(fdma, &fdma->dcbs[i]))
+			return i;
+
+	return -ENOSPC;
+}
+
+static void lan969x_fdma_tx_clear_buf(struct sparx5 *sparx5, int weight)
+{
+	struct fdma *fdma = &sparx5->tx.fdma;
+	struct sparx5_tx_buf *db;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&sparx5->tx_lock, flags);
+
+	for (i = 0; i < fdma->n_dcbs; ++i) {
+		db = &sparx5->tx.dbs[i];
+
+		if (!db->used)
+			continue;
+
+		if (!fdma_db_is_done(fdma_db_get(fdma, i, 0)))
+			continue;
+
+		db->dev->stats.tx_bytes += db->skb->len;
+		db->dev->stats.tx_packets++;
+		sparx5->tx.packets++;
+
+		dma_unmap_single(sparx5->dev,
+				 db->dma_addr,
+				 db->skb->len,
+				 DMA_TO_DEVICE);
+
+		if (!db->ptp)
+			napi_consume_skb(db->skb, weight);
+
+		db->used = false;
+	}
+
+	spin_unlock_irqrestore(&sparx5->tx_lock, flags);
+}
+
+static void lan969x_fdma_free_pages(struct sparx5_rx *rx)
+{
+	struct fdma *fdma = &rx->fdma;
+
+	for (int i = 0; i < fdma->n_dcbs; ++i) {
+		for (int j = 0; j < fdma->n_dbs; ++j)
+			page_pool_put_full_page(rx->page_pool,
+						rx->page[i][j], false);
+	}
+}
+
+static struct sk_buff *lan969x_fdma_rx_get_frame(struct sparx5 *sparx5,
+						 struct sparx5_rx *rx)
+{
+	const struct sparx5_consts *consts = sparx5->data->consts;
+	struct fdma *fdma = &rx->fdma;
+	struct sparx5_port *port;
+	struct frame_info fi;
+	struct sk_buff *skb;
+	struct fdma_db *db;
+	struct page *page;
+
+	db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
+	page = rx->page[fdma->dcb_index][fdma->db_index];
+
+	sparx5_ifh_parse(sparx5, page_address(page), &fi);
+	port = fi.src_port < consts->n_ports ? sparx5->ports[fi.src_port] :
+					       NULL;
+	if (WARN_ON(!port))
+		goto free_page;
+
+	skb = build_skb(page_address(page), fdma->db_size);
+	if (unlikely(!skb))
+		goto free_page;
+
+	skb_mark_for_recycle(skb);
+	skb_put(skb, fdma_db_len_get(db));
+	skb_pull(skb, IFH_LEN * sizeof(u32));
+
+	skb->dev = port->ndev;
+
+	if (likely(!(skb->dev->features & NETIF_F_RXFCS)))
+		skb_trim(skb, skb->len - ETH_FCS_LEN);
+
+	sparx5_ptp_rxtstamp(sparx5, skb, fi.timestamp);
+	skb->protocol = eth_type_trans(skb, skb->dev);
+
+	if (test_bit(port->portno, sparx5->bridge_mask))
+		skb->offload_fwd_mark = 1;
+
+	skb->dev->stats.rx_bytes += skb->len;
+	skb->dev->stats.rx_packets++;
+
+	return skb;
+
+free_page:
+	page_pool_recycle_direct(rx->page_pool, page);
+
+	return NULL;
+}
+
+static int lan969x_fdma_rx_alloc(struct sparx5 *sparx5)
+{
+	struct sparx5_rx *rx = &sparx5->rx;
+	struct fdma *fdma = &rx->fdma;
+	int err;
+
+	struct page_pool_params pp_params = {
+		.order = 0,
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+		.pool_size = fdma->n_dcbs * fdma->n_dbs,
+		.nid = NUMA_NO_NODE,
+		.dev = sparx5->dev,
+		.dma_dir = DMA_FROM_DEVICE,
+		.offset = 0,
+		.max_len = fdma->db_size -
+			   SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+	};
+
+	rx->page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(rx->page_pool))
+		return PTR_ERR(rx->page_pool);
+
+	err = fdma_alloc_coherent(sparx5->dev, fdma);
+	if (err)
+		return err;
+
+	fdma_dcbs_init(fdma,
+		       FDMA_DCB_INFO_DATAL(fdma->db_size),
+		       FDMA_DCB_STATUS_INTR);
+
+	return 0;
+}
+
+static int lan969x_fdma_tx_alloc(struct sparx5 *sparx5)
+{
+	struct sparx5_tx *tx = &sparx5->tx;
+	struct fdma *fdma = &tx->fdma;
+	int err;
+
+	tx->dbs = kcalloc(fdma->n_dcbs,
+			  sizeof(struct sparx5_tx_buf),
+			  GFP_KERNEL);
+	if (!tx->dbs)
+		return -ENOMEM;
+
+	err = fdma_alloc_coherent(sparx5->dev, fdma);
+	if (err) {
+		kfree(tx->dbs);
+		return err;
+	}
+
+	fdma_dcbs_init(fdma,
+		       FDMA_DCB_INFO_DATAL(fdma->db_size),
+		       FDMA_DCB_STATUS_DONE);
+
+	return 0;
+}
+
+static void lan969x_fdma_rx_init(struct sparx5 *sparx5)
+{
+	struct fdma *fdma = &sparx5->rx.fdma;
+
+	fdma->channel_id = FDMA_XTR_CHANNEL;
+	fdma->n_dcbs = FDMA_DCB_MAX;
+	fdma->n_dbs = 1;
+	fdma->priv = sparx5;
+	fdma->size = fdma_get_size(fdma);
+	fdma->db_size = PAGE_SIZE;
+	fdma->ops.dataptr_cb = &lan969x_fdma_rx_dataptr_cb;
+	fdma->ops.nextptr_cb = &fdma_nextptr_cb;
+
+	/* Fetch a netdev for SKB and NAPI use, any will do */
+	for (int idx = 0; idx < sparx5->data->consts->n_ports; ++idx) {
+		struct sparx5_port *port = sparx5->ports[idx];
+
+		if (port && port->ndev) {
+			sparx5->rx.ndev = port->ndev;
+			break;
+		}
+	}
+}
+
+static void lan969x_fdma_tx_init(struct sparx5 *sparx5)
+{
+	struct fdma *fdma = &sparx5->tx.fdma;
+
+	fdma->channel_id = FDMA_INJ_CHANNEL;
+	fdma->n_dcbs = FDMA_DCB_MAX;
+	fdma->n_dbs = 1;
+	fdma->priv = sparx5;
+	fdma->size = fdma_get_size(fdma);
+	fdma->db_size = PAGE_SIZE;
+	fdma->ops.dataptr_cb = &lan969x_fdma_tx_dataptr_cb;
+	fdma->ops.nextptr_cb = &fdma_nextptr_cb;
+}
+
+int lan969x_fdma_napi_poll(struct napi_struct *napi, int weight)
+{
+	struct sparx5_rx *rx = container_of(napi, struct sparx5_rx, napi);
+	struct sparx5 *sparx5 = container_of(rx, struct sparx5, rx);
+	int old_dcb, dcb_reload, counter = 0;
+	struct fdma *fdma = &rx->fdma;
+	struct sk_buff *skb;
+
+	dcb_reload = fdma->dcb_index;
+
+	lan969x_fdma_tx_clear_buf(sparx5, weight);
+
+	/* Process RX data */
+	while (counter < weight) {
+		if (!fdma_has_frames(fdma))
+			break;
+
+		skb = lan969x_fdma_rx_get_frame(sparx5, rx);
+		if (!skb)
+			break;
+
+		napi_gro_receive(&rx->napi, skb);
+
+		fdma_db_advance(fdma);
+		counter++;
+		/* Check if the DCB can be reused */
+		if (fdma_dcb_is_reusable(fdma))
+			continue;
+
+		fdma_db_reset(fdma);
+		fdma_dcb_advance(fdma);
+	}
+
+	/* Allocate new pages and map them */
+	while (dcb_reload != fdma->dcb_index) {
+		old_dcb = dcb_reload;
+		dcb_reload++;
+		 /* n_dcbs must be a power of 2 */
+		dcb_reload &= fdma->n_dcbs - 1;
+
+		fdma_dcb_add(fdma,
+			     old_dcb,
+			     FDMA_DCB_INFO_DATAL(fdma->db_size),
+			     FDMA_DCB_STATUS_INTR);
+
+		sparx5_fdma_reload(sparx5, fdma);
+	}
+
+	if (counter < weight && napi_complete_done(napi, counter))
+		spx5_wr(0xff, sparx5, FDMA_INTR_DB_ENA);
+
+	return counter;
+}
+
+int lan969x_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb,
+		      struct net_device *dev)
+{
+	int next_dcb, needed_headroom, needed_tailroom, err;
+	struct sparx5_tx *tx = &sparx5->tx;
+	struct fdma *fdma = &tx->fdma;
+	struct sparx5_tx_buf *db_buf;
+	u64 status;
+
+	next_dcb = lan969x_fdma_get_next_dcb(tx);
+	if (next_dcb < 0)
+		return -EBUSY;
+
+	needed_headroom = max_t(int, IFH_LEN * 4 - skb_headroom(skb), 0);
+	needed_tailroom = max_t(int, ETH_FCS_LEN - skb_tailroom(skb), 0);
+	if (needed_headroom || needed_tailroom || skb_header_cloned(skb)) {
+		err = pskb_expand_head(skb, needed_headroom, needed_tailroom,
+				       GFP_ATOMIC);
+		if (unlikely(err))
+			return err;
+	}
+
+	skb_push(skb, IFH_LEN * 4);
+	memcpy(skb->data, ifh, IFH_LEN * 4);
+	skb_put(skb, ETH_FCS_LEN);
+
+	db_buf = &tx->dbs[next_dcb];
+	db_buf->dma_addr = dma_map_single(sparx5->dev,
+					  skb->data,
+					  skb->len,
+					  DMA_TO_DEVICE);
+	if (dma_mapping_error(sparx5->dev, db_buf->dma_addr))
+		return -ENOMEM;
+
+	db_buf->dev = dev;
+	db_buf->skb = skb;
+	db_buf->ptp = false;
+	db_buf->used = true;
+
+	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
+	    SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP)
+		db_buf->ptp = true;
+
+	status = FDMA_DCB_STATUS_SOF |
+		 FDMA_DCB_STATUS_EOF |
+		 FDMA_DCB_STATUS_BLOCKO(0) |
+		 FDMA_DCB_STATUS_BLOCKL(skb->len) |
+		 FDMA_DCB_STATUS_INTR;
+
+	fdma_dcb_advance(fdma);
+	fdma_dcb_add(fdma, next_dcb, 0, status);
+
+	sparx5_fdma_reload(sparx5, fdma);
+
+	return NETDEV_TX_OK;
+}
+
+int lan969x_fdma_init(struct sparx5 *sparx5)
+{
+	struct sparx5_rx *rx = &sparx5->rx;
+	int err;
+
+	lan969x_fdma_rx_init(sparx5);
+	lan969x_fdma_tx_init(sparx5);
+	sparx5_fdma_injection_mode(sparx5);
+
+	err = dma_set_mask_and_coherent(sparx5->dev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_err(sparx5->dev, "Failed to set 64-bit FDMA mask");
+		return err;
+	}
+
+	err = lan969x_fdma_rx_alloc(sparx5);
+	if (err) {
+		dev_err(sparx5->dev, "Failed to allocate RX buffers: %d\n",
+			err);
+		return err;
+	}
+
+	err = lan969x_fdma_tx_alloc(sparx5);
+	if (err) {
+		fdma_free_coherent(sparx5->dev, &rx->fdma);
+		dev_err(sparx5->dev, "Failed to allocate TX buffers: %d\n",
+			err);
+		return err;
+	}
+
+	/* Reset FDMA state */
+	spx5_wr(FDMA_CTRL_NRESET_SET(0), sparx5, FDMA_CTRL);
+	spx5_wr(FDMA_CTRL_NRESET_SET(1), sparx5, FDMA_CTRL);
+
+	return err;
+}
+
+int lan969x_fdma_deinit(struct sparx5 *sparx5)
+{
+	struct sparx5_rx *rx = &sparx5->rx;
+	struct sparx5_tx *tx = &sparx5->tx;
+
+	sparx5_fdma_stop(sparx5);
+	fdma_free_coherent(sparx5->dev, &tx->fdma);
+	fdma_free_coherent(sparx5->dev, &rx->fdma);
+	lan969x_fdma_free_pages(rx);
+	page_pool_destroy(rx->page_pool);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x_regs.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_regs.c
index ace4ba21eec4..ace4ba21eec4 100644
--- a/drivers/net/ethernet/microchip/lan969x/lan969x_regs.c
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_regs.c
diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_rgmii.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_rgmii.c
new file mode 100644
index 000000000000..4e422ca50828
--- /dev/null
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_rgmii.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Microchip lan969x Switch driver
+ *
+ * Copyright (c) 2024 Microchip Technology Inc. and its subsidiaries.
+ */
+
+#include "lan969x.h"
+
+/* Tx clock selectors */
+#define LAN969X_RGMII_TX_CLK_SEL_125MHZ 1  /* 1000Mbps */
+#define LAN969X_RGMII_TX_CLK_SEL_25MHZ  2  /* 100Mbps */
+#define LAN969X_RGMII_TX_CLK_SEL_2M5MHZ 3  /* 10Mbps */
+
+/* Port speed selectors */
+#define LAN969X_RGMII_SPEED_SEL_10 0   /* Select 10Mbps speed */
+#define LAN969X_RGMII_SPEED_SEL_100 1  /* Select 100Mbps speed */
+#define LAN969X_RGMII_SPEED_SEL_1000 2 /* Select 1000Mbps speed */
+
+/* Clock delay selectors */
+#define LAN969X_RGMII_CLK_DELAY_SEL_1_0_NS 2  /* Phase shift 45deg */
+#define LAN969X_RGMII_CLK_DELAY_SEL_1_7_NS 3  /* Phase shift 77deg */
+#define LAN969X_RGMII_CLK_DELAY_SEL_2_0_NS 4  /* Phase shift 90deg */
+#define LAN969X_RGMII_CLK_DELAY_SEL_2_5_NS 5  /* Phase shift 112deg */
+#define LAN969X_RGMII_CLK_DELAY_SEL_3_0_NS 6  /* Phase shift 135deg */
+#define LAN969X_RGMII_CLK_DELAY_SEL_3_3_NS 7  /* Phase shift 147deg */
+
+#define LAN969X_RGMII_PORT_START_IDX 28 /* Index of the first RGMII port */
+#define LAN969X_RGMII_IFG_TX 4          /* TX Inter Frame Gap value */
+#define LAN969X_RGMII_IFG_RX1 5         /* RX1 Inter Frame Gap value */
+#define LAN969X_RGMII_IFG_RX2 1         /* RX2 Inter Frame Gap value */
+
+#define RGMII_PORT_IDX(port) ((port)->portno - LAN969X_RGMII_PORT_START_IDX)
+
+/* Get the tx clock selector based on the port speed. */
+static int lan969x_rgmii_get_clk_sel(int speed)
+{
+	return (speed == SPEED_10  ? LAN969X_RGMII_TX_CLK_SEL_2M5MHZ :
+		speed == SPEED_100 ? LAN969X_RGMII_TX_CLK_SEL_25MHZ :
+				     LAN969X_RGMII_TX_CLK_SEL_125MHZ);
+}
+
+/* Get the port speed selector based on the port speed. */
+static int lan969x_rgmii_get_speed_sel(int speed)
+{
+	return (speed == SPEED_10  ? LAN969X_RGMII_SPEED_SEL_10 :
+		speed == SPEED_100 ? LAN969X_RGMII_SPEED_SEL_100 :
+				     LAN969X_RGMII_SPEED_SEL_1000);
+}
+
+/* Get the clock delay selector based on the clock delay in picoseconds. */
+static int lan969x_rgmii_get_clk_delay_sel(struct sparx5_port *port,
+					   u32 delay_ps, u32 *clk_delay_sel)
+{
+	switch (delay_ps) {
+	case 0:
+		/* Hardware default selector. */
+		*clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_2_5_NS;
+		break;
+	case 1000:
+		*clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_1_0_NS;
+		break;
+	case 1700:
+		*clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_1_7_NS;
+		break;
+	case 2000:
+		*clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_2_0_NS;
+		break;
+	case 2500:
+		*clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_2_5_NS;
+		break;
+	case 3000:
+		*clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_3_0_NS;
+		break;
+	case 3300:
+		*clk_delay_sel = LAN969X_RGMII_CLK_DELAY_SEL_3_3_NS;
+		break;
+	default:
+		dev_err(port->sparx5->dev, "Invalid RGMII delay: %u", delay_ps);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Configure the RGMII tx clock frequency. */
+static void lan969x_rgmii_tx_clk_config(struct sparx5_port *port,
+					struct sparx5_port_config *conf)
+{
+	u32 clk_sel = lan969x_rgmii_get_clk_sel(conf->speed);
+	u32 idx = RGMII_PORT_IDX(port);
+
+	/* Take the RGMII clock domain out of reset and set tx clock
+	 * frequency.
+	 */
+	spx5_rmw(HSIO_WRAP_RGMII_CFG_TX_CLK_CFG_SET(clk_sel) |
+		 HSIO_WRAP_RGMII_CFG_RGMII_TX_RST_SET(0) |
+		 HSIO_WRAP_RGMII_CFG_RGMII_RX_RST_SET(0),
+		 HSIO_WRAP_RGMII_CFG_TX_CLK_CFG |
+		 HSIO_WRAP_RGMII_CFG_RGMII_TX_RST |
+		 HSIO_WRAP_RGMII_CFG_RGMII_RX_RST,
+		 port->sparx5, HSIO_WRAP_RGMII_CFG(idx));
+}
+
+/* Configure the RGMII port device. */
+static void lan969x_rgmii_port_device_config(struct sparx5_port *port,
+					     struct sparx5_port_config *conf)
+{
+	u32 dtag, dotag, etype, speed_sel, idx = RGMII_PORT_IDX(port);
+
+	speed_sel = lan969x_rgmii_get_speed_sel(conf->speed);
+
+	etype = (port->vlan_type == SPX5_VLAN_PORT_TYPE_S_CUSTOM ?
+		 port->custom_etype :
+		 port->vlan_type == SPX5_VLAN_PORT_TYPE_C ?
+		 ETH_P_8021Q : ETH_P_8021AD);
+
+	dtag = port->max_vlan_tags == SPX5_PORT_MAX_TAGS_TWO;
+	dotag = port->max_vlan_tags != SPX5_PORT_MAX_TAGS_NONE;
+
+	/* Enable the MAC. */
+	spx5_wr(DEVRGMII_MAC_ENA_CFG_RX_ENA_SET(1) |
+		DEVRGMII_MAC_ENA_CFG_TX_ENA_SET(1),
+		port->sparx5, DEVRGMII_MAC_ENA_CFG(idx));
+
+	/* Configure the Inter Frame Gap. */
+	spx5_wr(DEVRGMII_MAC_IFG_CFG_TX_IFG_SET(LAN969X_RGMII_IFG_TX) |
+		DEVRGMII_MAC_IFG_CFG_RX_IFG1_SET(LAN969X_RGMII_IFG_RX1) |
+		DEVRGMII_MAC_IFG_CFG_RX_IFG2_SET(LAN969X_RGMII_IFG_RX2),
+		port->sparx5, DEVRGMII_MAC_IFG_CFG(idx));
+
+	/* Configure port data rate. */
+	spx5_wr(DEVRGMII_DEV_RST_CTRL_SPEED_SEL_SET(speed_sel),
+		port->sparx5, DEVRGMII_DEV_RST_CTRL(idx));
+
+	/* Configure VLAN awareness. */
+	spx5_wr(DEVRGMII_MAC_TAGS_CFG_TAG_ID_SET(etype) |
+		DEVRGMII_MAC_TAGS_CFG_PB_ENA_SET(dtag) |
+		DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(dotag) |
+		DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_SET(dotag),
+		port->sparx5,
+		DEVRGMII_MAC_TAGS_CFG(idx));
+}
+
+/* Configure the RGMII delay lines in the MAC.
+ *
+ * We use the rx-internal-delay-ps" and "tx-internal-delay-ps" properties to
+ * configure the rx and tx delays for the MAC. If these properties are missing
+ * or set to zero, the MAC will not apply any delay.
+ *
+ * The PHY side delays are determined by the PHY mode
+ * (e.g. PHY_INTERFACE_MODE_RGMII_{ID, RXID, TXID}), and ignored by the MAC side
+ * entirely.
+ */
+static int lan969x_rgmii_delay_config(struct sparx5_port *port,
+				      struct sparx5_port_config *conf)
+{
+	u32 tx_clk_sel, rx_clk_sel, tx_delay_ps = 0, rx_delay_ps = 0;
+	u32 idx = RGMII_PORT_IDX(port);
+	int err;
+
+	of_property_read_u32(port->of_node, "rx-internal-delay-ps",
+			     &rx_delay_ps);
+
+	of_property_read_u32(port->of_node, "tx-internal-delay-ps",
+			     &tx_delay_ps);
+
+	err = lan969x_rgmii_get_clk_delay_sel(port, rx_delay_ps, &rx_clk_sel);
+	if (err)
+		return err;
+
+	err = lan969x_rgmii_get_clk_delay_sel(port, tx_delay_ps, &tx_clk_sel);
+	if (err)
+		return err;
+
+	/* Configure rx delay. */
+	spx5_rmw(HSIO_WRAP_DLL_CFG_DLL_RST_SET(0) |
+		 HSIO_WRAP_DLL_CFG_DLL_ENA_SET(1) |
+		 HSIO_WRAP_DLL_CFG_DLL_CLK_ENA_SET(!!rx_delay_ps) |
+		 HSIO_WRAP_DLL_CFG_DLL_CLK_SEL_SET(rx_clk_sel),
+		 HSIO_WRAP_DLL_CFG_DLL_RST |
+		 HSIO_WRAP_DLL_CFG_DLL_ENA |
+		 HSIO_WRAP_DLL_CFG_DLL_CLK_ENA |
+		 HSIO_WRAP_DLL_CFG_DLL_CLK_SEL,
+		 port->sparx5, HSIO_WRAP_DLL_CFG(idx, 0));
+
+	/* Configure tx delay. */
+	spx5_rmw(HSIO_WRAP_DLL_CFG_DLL_RST_SET(0) |
+		 HSIO_WRAP_DLL_CFG_DLL_ENA_SET(1) |
+		 HSIO_WRAP_DLL_CFG_DLL_CLK_ENA_SET(!!tx_delay_ps) |
+		 HSIO_WRAP_DLL_CFG_DLL_CLK_SEL_SET(tx_clk_sel),
+		 HSIO_WRAP_DLL_CFG_DLL_RST |
+		 HSIO_WRAP_DLL_CFG_DLL_ENA |
+		 HSIO_WRAP_DLL_CFG_DLL_CLK_ENA |
+		 HSIO_WRAP_DLL_CFG_DLL_CLK_SEL,
+		 port->sparx5, HSIO_WRAP_DLL_CFG(idx, 1));
+
+	return 0;
+}
+
+/* Configure GPIO's to be used as RGMII interface. */
+static void lan969x_rgmii_gpio_config(struct sparx5_port *port)
+{
+	u32 idx = RGMII_PORT_IDX(port);
+
+	/* Enable the RGMII on the GPIOs. */
+	spx5_wr(HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG_SET(1), port->sparx5,
+		HSIO_WRAP_XMII_CFG(!idx));
+}
+
+int lan969x_port_config_rgmii(struct sparx5_port *port,
+			      struct sparx5_port_config *conf)
+{
+	int err;
+
+	err = lan969x_rgmii_delay_config(port, conf);
+	if (err)
+		return err;
+
+	lan969x_rgmii_tx_clk_config(port, conf);
+	lan969x_rgmii_gpio_config(port);
+	lan969x_rgmii_port_device_config(port, conf);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_ag_api.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_vcap_ag_api.c
index 7acc5bcf337a..7acc5bcf337a 100644
--- a/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_ag_api.c
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_vcap_ag_api.c
diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_vcap_impl.c
index 543a1f2bf6bd..543a1f2bf6bd 100644
--- a/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_impl.c
+++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_vcap_impl.c
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c b/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c
index 5fe941c66c17..5c46d81de530 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c
@@ -98,7 +98,6 @@ u32 sparx5_cal_speed_to_value(enum sparx5_cal_bw speed)
 	default: return 0;
 	}
 }
-EXPORT_SYMBOL_GPL(sparx5_cal_speed_to_value);
 
 static u32 sparx5_bandwidth_to_calendar(u32 bw)
 {
@@ -150,7 +149,6 @@ enum sparx5_cal_bw sparx5_get_port_cal_speed(struct sparx5 *sparx5, u32 portno)
 		return SPX5_CAL_SPEED_NONE;
 	return sparx5_bandwidth_to_calendar(port->conf.bandwidth);
 }
-EXPORT_SYMBOL_GPL(sparx5_get_port_cal_speed);
 
 /* Auto configure the QSYS calendar based on port configuration */
 int sparx5_config_auto_calendar(struct sparx5 *sparx5)
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 0027144a2af2..dbe86f937b21 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -18,9 +18,6 @@
 #include "sparx5_main.h"
 #include "sparx5_port.h"
 
-#define FDMA_XTR_CHANNEL		6
-#define FDMA_INJ_CHANNEL		0
-
 #define FDMA_XTR_BUFFER_SIZE		2048
 #define FDMA_WEIGHT			4
 
@@ -133,7 +130,7 @@ static void sparx5_fdma_tx_deactivate(struct sparx5 *sparx5, struct sparx5_tx *t
 		 sparx5, FDMA_CH_ACTIVATE);
 }
 
-static void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma)
+void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma)
 {
 	/* Reload the RX channel */
 	spx5_wr(BIT(fdma->channel_id), sparx5, FDMA_CH_RELOAD);
@@ -183,7 +180,7 @@ static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx
 	return true;
 }
 
-static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
+int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 {
 	struct sparx5_rx *rx = container_of(napi, struct sparx5_rx, napi);
 	struct sparx5 *sparx5 = container_of(rx, struct sparx5, rx);
@@ -213,11 +210,11 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 	return counter;
 }
 
-int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb)
+int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb,
+		     struct net_device *dev)
 {
 	struct sparx5_tx *tx = &sparx5->tx;
 	struct fdma *fdma = &tx->fdma;
-	static bool first_time = true;
 	void *virt_addr;
 
 	fdma_dcb_advance(fdma);
@@ -238,12 +235,8 @@ int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb)
 		     FDMA_DCB_STATUS_BLOCKO(0) |
 		     FDMA_DCB_STATUS_BLOCKL(skb->len + IFH_LEN * 4 + 4));
 
-	if (first_time) {
-		sparx5_fdma_tx_activate(sparx5, tx);
-		first_time = false;
-	} else {
-		sparx5_fdma_reload(sparx5, fdma);
-	}
+	sparx5_fdma_reload(sparx5, fdma);
+
 	return NETDEV_TX_OK;
 }
 
@@ -260,10 +253,6 @@ static int sparx5_fdma_rx_alloc(struct sparx5 *sparx5)
 	fdma_dcbs_init(fdma, FDMA_DCB_INFO_DATAL(fdma->db_size),
 		       FDMA_DCB_STATUS_INTR);
 
-	netif_napi_add_weight(rx->ndev, &rx->napi, sparx5_fdma_napi_callback,
-			      FDMA_WEIGHT);
-	napi_enable(&rx->napi);
-	sparx5_fdma_rx_activate(sparx5, rx);
 	return 0;
 }
 
@@ -348,7 +337,7 @@ irqreturn_t sparx5_fdma_handler(int irq, void *args)
 	return IRQ_HANDLED;
 }
 
-static void sparx5_fdma_injection_mode(struct sparx5 *sparx5)
+void sparx5_fdma_injection_mode(struct sparx5 *sparx5)
 {
 	const int byte_swap = 1;
 	int portno;
@@ -410,7 +399,7 @@ static void sparx5_fdma_injection_mode(struct sparx5 *sparx5)
 	}
 }
 
-int sparx5_fdma_start(struct sparx5 *sparx5)
+int sparx5_fdma_init(struct sparx5 *sparx5)
 {
 	int err;
 
@@ -443,24 +432,55 @@ int sparx5_fdma_start(struct sparx5 *sparx5)
 	return err;
 }
 
+int sparx5_fdma_deinit(struct sparx5 *sparx5)
+{
+	sparx5_fdma_stop(sparx5);
+	fdma_free_phys(&sparx5->rx.fdma);
+	fdma_free_phys(&sparx5->tx.fdma);
+
+	return 0;
+}
+
 static u32 sparx5_fdma_port_ctrl(struct sparx5 *sparx5)
 {
 	return spx5_rd(sparx5, FDMA_PORT_CTRL(0));
 }
 
+int sparx5_fdma_start(struct sparx5 *sparx5)
+{
+	const struct sparx5_ops *ops = sparx5->data->ops;
+	struct sparx5_rx *rx = &sparx5->rx;
+	struct sparx5_tx *tx = &sparx5->tx;
+
+	netif_napi_add_weight(rx->ndev,
+			      &rx->napi,
+			      ops->fdma_poll,
+			      FDMA_WEIGHT);
+
+	napi_enable(&rx->napi);
+
+	sparx5_fdma_rx_activate(sparx5, rx);
+	sparx5_fdma_tx_activate(sparx5, tx);
+
+	return 0;
+}
+
 int sparx5_fdma_stop(struct sparx5 *sparx5)
 {
+	struct sparx5_rx *rx = &sparx5->rx;
+	struct sparx5_tx *tx = &sparx5->tx;
 	u32 val;
 
-	napi_disable(&sparx5->rx.napi);
+	napi_disable(&rx->napi);
+
 	/* Stop the fdma and channel interrupts */
-	sparx5_fdma_rx_deactivate(sparx5, &sparx5->rx);
-	sparx5_fdma_tx_deactivate(sparx5, &sparx5->tx);
+	sparx5_fdma_rx_deactivate(sparx5, rx);
+	sparx5_fdma_tx_deactivate(sparx5, tx);
+
 	/* Wait for the RX channel to stop */
 	read_poll_timeout(sparx5_fdma_port_ctrl, val,
 			  FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY_GET(val) == 0,
 			  500, 10000, 0, sparx5);
-	fdma_free_phys(&sparx5->rx.fdma);
-	fdma_free_phys(&sparx5->tx.fdma);
+
 	return 0;
 }
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
index 2f1013f870fb..74ad1d73b465 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
@@ -24,7 +24,7 @@
 #include <linux/types.h>
 #include <linux/reset.h>
 
-#include "../lan969x/lan969x.h" /* for lan969x match data */
+#include "lan969x/lan969x.h" /* for lan969x match data */
 
 #include "sparx5_main_regs.h"
 #include "sparx5_main.h"
@@ -313,10 +313,13 @@ static int sparx5_create_port(struct sparx5 *sparx5,
 			      struct initial_port_config *config)
 {
 	struct sparx5_port *spx5_port;
+	const struct sparx5_ops *ops;
 	struct net_device *ndev;
 	struct phylink *phylink;
 	int err;
 
+	ops = sparx5->data->ops;
+
 	ndev = sparx5_create_netdev(sparx5, config->portno);
 	if (IS_ERR(ndev)) {
 		dev_err(sparx5->dev, "Could not create net device: %02u\n",
@@ -335,7 +338,6 @@ static int sparx5_create_port(struct sparx5 *sparx5,
 	spx5_port->custom_etype = 0x8880; /* Vitesse */
 	spx5_port->phylink_pcs.poll = true;
 	spx5_port->phylink_pcs.ops = &sparx5_phylink_pcs_ops;
-	spx5_port->phylink_pcs.neg_mode = true;
 	spx5_port->is_mrouter = false;
 	INIT_LIST_HEAD(&spx5_port->tc_templates);
 	sparx5->ports[config->portno] = spx5_port;
@@ -357,6 +359,9 @@ static int sparx5_create_port(struct sparx5 *sparx5,
 		MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD |
 		MAC_2500FD | MAC_5000FD | MAC_10000FD | MAC_25000FD;
 
+	if (ops->is_port_rgmii(spx5_port->portno))
+		phy_interface_set_rgmii(spx5_port->phylink_config.supported_interfaces);
+
 	__set_bit(PHY_INTERFACE_MODE_SGMII,
 		  spx5_port->phylink_config.supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_QSGMII,
@@ -778,16 +783,19 @@ static int sparx5_start(struct sparx5 *sparx5)
 
 	/* Start Frame DMA with fallback to register based INJ/XTR */
 	err = -ENXIO;
-	if (sparx5->fdma_irq >= 0 && is_sparx5(sparx5)) {
-		if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0)
-			err = devm_request_threaded_irq(sparx5->dev,
-							sparx5->fdma_irq,
-							NULL,
-							sparx5_fdma_handler,
-							IRQF_ONESHOT,
-							"sparx5-fdma", sparx5);
-		if (!err)
-			err = sparx5_fdma_start(sparx5);
+	if (sparx5->fdma_irq >= 0) {
+		if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0 ||
+		    !is_sparx5(sparx5))
+			err = devm_request_irq(sparx5->dev,
+					       sparx5->fdma_irq,
+					       sparx5_fdma_handler,
+					       0,
+					       "sparx5-fdma", sparx5);
+		if (!err) {
+			err = ops->fdma_init(sparx5);
+			if (!err)
+				sparx5_fdma_start(sparx5);
+		}
 		if (err)
 			sparx5->fdma_irq = -ENXIO;
 	} else {
@@ -831,6 +839,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
 	struct initial_port_config *configs, *config;
 	struct device_node *np = pdev->dev.of_node;
 	struct device_node *ports, *portnp;
+	const struct sparx5_ops *ops;
 	struct reset_control *reset;
 	struct sparx5 *sparx5;
 	int idx = 0, err = 0;
@@ -852,6 +861,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
 		return -EINVAL;
 
 	regs = sparx5->data->regs;
+	ops = sparx5->data->ops;
 
 	/* Do switch core reset if available */
 	reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch");
@@ -881,7 +891,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
 
 	for_each_available_child_of_node(ports, portnp) {
 		struct sparx5_port_config *conf;
-		struct phy *serdes;
+		struct phy *serdes = NULL;
 		u32 portno;
 
 		err = of_property_read_u32(portnp, "reg", &portno);
@@ -911,13 +921,17 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
 			conf->sd_sgpio = ~0;
 		else
 			sparx5->sd_sgpio_remapping = true;
-		serdes = devm_of_phy_get(sparx5->dev, portnp, NULL);
-		if (IS_ERR(serdes)) {
-			err = dev_err_probe(sparx5->dev, PTR_ERR(serdes),
-					    "port %u: missing serdes\n",
-					    portno);
-			of_node_put(portnp);
-			goto cleanup_config;
+		/* There is no SerDes node for RGMII ports. */
+		if (!ops->is_port_rgmii(portno)) {
+			serdes = devm_of_phy_get(sparx5->dev, portnp, NULL);
+			if (IS_ERR(serdes)) {
+				err = dev_err_probe(sparx5->dev,
+						    PTR_ERR(serdes),
+						    "port %u: missing serdes\n",
+						    portno);
+				of_node_put(portnp);
+				goto cleanup_config;
+			}
 		}
 		config->portno = portno;
 		config->node = portnp;
@@ -1015,6 +1029,7 @@ cleanup_pnode:
 static void mchp_sparx5_remove(struct platform_device *pdev)
 {
 	struct sparx5 *sparx5 = platform_get_drvdata(pdev);
+	const struct sparx5_ops *ops = sparx5->data->ops;
 
 	debugfs_remove_recursive(sparx5->debugfs_root);
 	if (sparx5->xtr_irq) {
@@ -1026,7 +1041,7 @@ static void mchp_sparx5_remove(struct platform_device *pdev)
 		sparx5->fdma_irq = -ENXIO;
 	}
 	sparx5_ptp_deinit(sparx5);
-	sparx5_fdma_stop(sparx5);
+	ops->fdma_deinit(sparx5);
 	sparx5_cleanup_ports(sparx5);
 	sparx5_vcap_destroy(sparx5);
 	/* Unregister netdevs */
@@ -1073,6 +1088,7 @@ static const struct sparx5_ops sparx5_ops = {
 	.is_port_5g              = &sparx5_port_is_5g,
 	.is_port_10g             = &sparx5_port_is_10g,
 	.is_port_25g             = &sparx5_port_is_25g,
+	.is_port_rgmii           = &sparx5_port_is_rgmii,
 	.get_port_dev_index      = &sparx5_port_dev_mapping,
 	.get_port_dev_bit        = &sparx5_port_dev_mapping,
 	.get_hsch_max_group_rate = &sparx5_get_hsch_max_group_rate,
@@ -1080,6 +1096,10 @@ static const struct sparx5_ops sparx5_ops = {
 	.set_port_mux            = &sparx5_port_mux_set,
 	.ptp_irq_handler         = &sparx5_ptp_irq_handler,
 	.dsm_calendar_calc       = &sparx5_dsm_calendar_calc,
+	.fdma_init               = &sparx5_fdma_init,
+	.fdma_deinit             = &sparx5_fdma_deinit,
+	.fdma_poll               = &sparx5_fdma_napi_callback,
+	.fdma_xmit               = &sparx5_fdma_xmit,
 };
 
 static const struct sparx5_match_data sparx5_desc = {
@@ -1093,7 +1113,7 @@ static const struct sparx5_match_data sparx5_desc = {
 
 static const struct of_device_id mchp_sparx5_match[] = {
 	{ .compatible = "microchip,sparx5-switch", .data = &sparx5_desc },
-#if IS_ENABLED(CONFIG_LAN969X_SWITCH)
+#ifdef CONFIG_LAN969X_SWITCH
 	{ .compatible = "microchip,lan9691-switch", .data = &lan969x_desc },
 #endif
 	{ }
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index d5dd953b0a71..fe7d8bcc0cd9 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -112,6 +112,8 @@ enum sparx5_feature {
 #define XTR_QUEUE     0
 #define INJ_QUEUE     0
 
+#define FDMA_XTR_CHANNEL		6
+#define FDMA_INJ_CHANNEL		0
 #define FDMA_DCB_MAX			64
 #define FDMA_RX_DCB_MAX_DBS		15
 #define FDMA_TX_DCB_MAX_DBS		1
@@ -157,11 +159,25 @@ struct sparx5_calendar_data {
  */
 struct sparx5_rx {
 	struct fdma fdma;
-	struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS];
+	struct page_pool *page_pool;
+	union {
+		struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS];
+		struct page *page[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS];
+	};
 	dma_addr_t dma;
 	struct napi_struct napi;
 	struct net_device *ndev;
 	u64 packets;
+	u8 page_order;
+};
+
+/* Used to store information about TX buffers. */
+struct sparx5_tx_buf {
+	struct net_device *dev;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	bool used;
+	bool ptp;
 };
 
 /* Frame DMA transmit state:
@@ -169,6 +185,7 @@ struct sparx5_rx {
  */
 struct sparx5_tx {
 	struct fdma fdma;
+	struct sparx5_tx_buf *dbs;
 	u64 packets;
 	u64 dropped;
 };
@@ -313,6 +330,7 @@ struct sparx5_ops {
 	bool (*is_port_5g)(int portno);
 	bool (*is_port_10g)(int portno);
 	bool (*is_port_25g)(int portno);
+	bool (*is_port_rgmii)(int portno);
 	u32  (*get_port_dev_index)(struct sparx5 *sparx5, int port);
 	u32  (*get_port_dev_bit)(struct sparx5 *sparx5, int port);
 	u32  (*get_hsch_max_group_rate)(int grp);
@@ -323,6 +341,13 @@ struct sparx5_ops {
 	irqreturn_t (*ptp_irq_handler)(int irq, void *args);
 	int (*dsm_calendar_calc)(struct sparx5 *sparx5, u32 taxi,
 				 struct sparx5_calendar_data *data);
+	int (*port_config_rgmii)(struct sparx5_port *port,
+				 struct sparx5_port_config *conf);
+	int (*fdma_init)(struct sparx5 *sparx5);
+	int (*fdma_deinit)(struct sparx5 *sparx5);
+	int (*fdma_poll)(struct napi_struct *napi, int weight);
+	int (*fdma_xmit)(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb,
+			 struct net_device *dev);
 };
 
 struct sparx5_main_io_resource {
@@ -433,10 +458,16 @@ int sparx5_manual_injection_mode(struct sparx5 *sparx5);
 void sparx5_port_inj_timer_setup(struct sparx5_port *port);
 
 /* sparx5_fdma.c */
+int sparx5_fdma_init(struct sparx5 *sparx5);
+int sparx5_fdma_deinit(struct sparx5 *sparx5);
 int sparx5_fdma_start(struct sparx5 *sparx5);
 int sparx5_fdma_stop(struct sparx5 *sparx5);
-int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb);
+int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight);
+int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb,
+		     struct net_device *dev);
 irqreturn_t sparx5_fdma_handler(int irq, void *args);
+void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma);
+void sparx5_fdma_injection_mode(struct sparx5 *sparx5);
 
 /* sparx5_mactable.c */
 void sparx5_mact_pull_work(struct work_struct *work);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
index 561344f19062..d9ef4ef137b8 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
@@ -37,6 +37,7 @@ enum sparx5_target {
 	TARGET_FDMA = 117,
 	TARGET_GCB = 118,
 	TARGET_HSCH = 119,
+	TARGET_HSIO_WRAP = 120,
 	TARGET_LRN = 122,
 	TARGET_PCEP = 129,
 	TARGET_PCS10G_BR = 132,
@@ -54,6 +55,7 @@ enum sparx5_target {
 	TARGET_VCAP_SUPER = 326,
 	TARGET_VOP = 327,
 	TARGET_XQS = 331,
+	TARGET_DEVRGMII = 392,
 	NUM_TARGETS = 517
 };
 
@@ -5367,6 +5369,69 @@ extern const struct sparx5_regs *regs;
 #define HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY_GET(x)\
 	FIELD_GET(HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY, x)
 
+/* LAN969X ONLY */
+/* HSIOWRAP:XMII_CFG:XMII_CFG */
+#define HSIO_WRAP_XMII_CFG(g)                                                  \
+	__REG(TARGET_HSIO_WRAP, 0, 1, 116, g, 2, 20, 0, 0, 1, 4)
+
+#define HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG         GENMASK(2, 1)
+#define HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG_SET(x)\
+	FIELD_PREP(HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG, x)
+#define HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG_GET(x)\
+	FIELD_GET(HSIO_WRAP_XMII_CFG_GPIO_XMII_CFG, x)
+
+/* LAN969X ONLY */
+/* HSIOWRAP:XMII_CFG:RGMII_CFG */
+#define HSIO_WRAP_RGMII_CFG(g)                                                 \
+	__REG(TARGET_HSIO_WRAP, 0, 1, 116, g, 2, 20, 4, 0, 1, 4)
+
+#define HSIO_WRAP_RGMII_CFG_TX_CLK_CFG           GENMASK(4, 2)
+#define HSIO_WRAP_RGMII_CFG_TX_CLK_CFG_SET(x)\
+	FIELD_PREP(HSIO_WRAP_RGMII_CFG_TX_CLK_CFG, x)
+#define HSIO_WRAP_RGMII_CFG_TX_CLK_CFG_GET(x)\
+	FIELD_GET(HSIO_WRAP_RGMII_CFG_TX_CLK_CFG, x)
+
+#define HSIO_WRAP_RGMII_CFG_RGMII_TX_RST         BIT(1)
+#define HSIO_WRAP_RGMII_CFG_RGMII_TX_RST_SET(x)\
+	FIELD_PREP(HSIO_WRAP_RGMII_CFG_RGMII_TX_RST, x)
+#define HSIO_WRAP_RGMII_CFG_RGMII_TX_RST_GET(x)\
+	FIELD_GET(HSIO_WRAP_RGMII_CFG_RGMII_TX_RST, x)
+
+#define HSIO_WRAP_RGMII_CFG_RGMII_RX_RST         BIT(0)
+#define HSIO_WRAP_RGMII_CFG_RGMII_RX_RST_SET(x)\
+	FIELD_PREP(HSIO_WRAP_RGMII_CFG_RGMII_RX_RST, x)
+#define HSIO_WRAP_RGMII_CFG_RGMII_RX_RST_GET(x)\
+	FIELD_GET(HSIO_WRAP_RGMII_CFG_RGMII_RX_RST, x)
+
+/* LAN969X ONLY */
+/* HSIOWRAP:XMII_CFG:DLL_CFG */
+#define HSIO_WRAP_DLL_CFG(g, r)                                                \
+	__REG(TARGET_HSIO_WRAP, 0, 1, 116, g, 2, 20, 12, r, 2, 4)
+
+#define HSIO_WRAP_DLL_CFG_DLL_ENA                BIT(19)
+#define HSIO_WRAP_DLL_CFG_DLL_ENA_SET(x)\
+	FIELD_PREP(HSIO_WRAP_DLL_CFG_DLL_ENA, x)
+#define HSIO_WRAP_DLL_CFG_DLL_ENA_GET(x)\
+	FIELD_GET(HSIO_WRAP_DLL_CFG_DLL_ENA, x)
+
+#define HSIO_WRAP_DLL_CFG_DLL_CLK_ENA            BIT(18)
+#define HSIO_WRAP_DLL_CFG_DLL_CLK_ENA_SET(x)\
+	FIELD_PREP(HSIO_WRAP_DLL_CFG_DLL_CLK_ENA, x)
+#define HSIO_WRAP_DLL_CFG_DLL_CLK_ENA_GET(x)\
+	FIELD_GET(HSIO_WRAP_DLL_CFG_DLL_CLK_ENA, x)
+
+#define HSIO_WRAP_DLL_CFG_DLL_CLK_SEL            GENMASK(17, 15)
+#define HSIO_WRAP_DLL_CFG_DLL_CLK_SEL_SET(x)\
+	FIELD_PREP(HSIO_WRAP_DLL_CFG_DLL_CLK_SEL, x)
+#define HSIO_WRAP_DLL_CFG_DLL_CLK_SEL_GET(x)\
+	FIELD_GET(HSIO_WRAP_DLL_CFG_DLL_CLK_SEL, x)
+
+#define HSIO_WRAP_DLL_CFG_DLL_RST                BIT(0)
+#define HSIO_WRAP_DLL_CFG_DLL_RST_SET(x)\
+	FIELD_PREP(HSIO_WRAP_DLL_CFG_DLL_RST, x)
+#define HSIO_WRAP_DLL_CFG_DLL_RST_GET(x)\
+	FIELD_GET(HSIO_WRAP_DLL_CFG_DLL_RST, x)
+
 /* LRN:COMMON:COMMON_ACCESS_CTRL */
 #define LRN_COMMON_ACCESS_CTRL                                                 \
 	__REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 0, 0, 1, 4)
@@ -8110,4 +8175,84 @@ extern const struct sparx5_regs *regs;
 #define XQS_CNT(g)                                                             \
 	__REG(TARGET_XQS, 0, 1, 0, g, 1024, 4, 0, 0, 1, 4)
 
+/* LAN969X ONLY */
+/* DEV1G:DEV_CFG_STATUS:DEV_RST_CTRL */
+#define DEVRGMII_DEV_RST_CTRL(t)                                               \
+	__REG(TARGET_DEVRGMII, t, 2, 0, 0, 1, 36, 0, 0, 1, 4)
+
+#define DEVRGMII_DEV_RST_CTRL_SPEED_SEL          GENMASK(22, 20)
+#define DEVRGMII_DEV_RST_CTRL_SPEED_SEL_SET(x)\
+	FIELD_PREP(DEVRGMII_DEV_RST_CTRL_SPEED_SEL, x)
+#define DEVRGMII_DEV_RST_CTRL_SPEED_SEL_GET(x)\
+	FIELD_GET(DEVRGMII_DEV_RST_CTRL_SPEED_SEL, x)
+
+/* LAN969X ONLY */
+/* DEV1G:MAC_CFG_STATUS:MAC_ENA_CFG */
+#define DEVRGMII_MAC_ENA_CFG(t)                                                \
+	__REG(TARGET_DEVRGMII, t, 2, 36, 0, 1, 36, 0, 0, 1, 4)
+
+#define DEVRGMII_MAC_ENA_CFG_RX_ENA              BIT(4)
+#define DEVRGMII_MAC_ENA_CFG_RX_ENA_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_ENA_CFG_RX_ENA, x)
+#define DEVRGMII_MAC_ENA_CFG_RX_ENA_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_ENA_CFG_RX_ENA, x)
+
+#define DEVRGMII_MAC_ENA_CFG_TX_ENA              BIT(0)
+#define DEVRGMII_MAC_ENA_CFG_TX_ENA_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_ENA_CFG_TX_ENA, x)
+#define DEVRGMII_MAC_ENA_CFG_TX_ENA_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_ENA_CFG_TX_ENA, x)
+
+/* LAN969X ONLY */
+/* DEV1G:MAC_CFG_STATUS:MAC_TAGS_CFG */
+#define DEVRGMII_MAC_TAGS_CFG(t)                                               \
+	__REG(TARGET_DEVRGMII, t, 2, 36, 0, 1, 36, 12, 0, 1, 4)
+
+#define DEVRGMII_MAC_TAGS_CFG_TAG_ID             GENMASK(31, 16)
+#define DEVRGMII_MAC_TAGS_CFG_TAG_ID_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_TAGS_CFG_TAG_ID, x)
+#define DEVRGMII_MAC_TAGS_CFG_TAG_ID_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_TAGS_CFG_TAG_ID, x)
+
+#define DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA   BIT(3)
+#define DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA, x)
+#define DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA, x)
+
+#define DEVRGMII_MAC_TAGS_CFG_PB_ENA             GENMASK(2, 1)
+#define DEVRGMII_MAC_TAGS_CFG_PB_ENA_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_TAGS_CFG_PB_ENA, x)
+#define DEVRGMII_MAC_TAGS_CFG_PB_ENA_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_TAGS_CFG_PB_ENA, x)
+
+#define DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA       BIT(0)
+#define DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA, x)
+#define DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_TAGS_CFG_VLAN_AWR_ENA, x)
+
+/* LAN969X ONLY */
+/* DEV1G:MAC_CFG_STATUS:MAC_IFG_CFG */
+#define DEVRGMII_MAC_IFG_CFG(t)                                                \
+	__REG(TARGET_DEVRGMII, t, 2, 36, 0, 1, 36, 24, 0, 1, 4)
+
+#define DEVRGMII_MAC_IFG_CFG_TX_IFG              GENMASK(12, 8)
+#define DEVRGMII_MAC_IFG_CFG_TX_IFG_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_IFG_CFG_TX_IFG, x)
+#define DEVRGMII_MAC_IFG_CFG_TX_IFG_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_IFG_CFG_TX_IFG, x)
+
+#define DEVRGMII_MAC_IFG_CFG_RX_IFG2             GENMASK(7, 4)
+#define DEVRGMII_MAC_IFG_CFG_RX_IFG2_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_IFG_CFG_RX_IFG2, x)
+#define DEVRGMII_MAC_IFG_CFG_RX_IFG2_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_IFG_CFG_RX_IFG2, x)
+
+#define DEVRGMII_MAC_IFG_CFG_RX_IFG1             GENMASK(3, 0)
+#define DEVRGMII_MAC_IFG_CFG_RX_IFG1_SET(x)\
+	FIELD_PREP(DEVRGMII_MAC_IFG_CFG_RX_IFG1, x)
+#define DEVRGMII_MAC_IFG_CFG_RX_IFG1_GET(x)\
+	FIELD_GET(DEVRGMII_MAC_IFG_CFG_RX_IFG1, x)
+
 #endif /* _SPARX5_MAIN_REGS_H_ */
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c
index 9806729e9c62..76097761fa97 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c
@@ -12,7 +12,6 @@
 #define SPX5_MIRROR_DISABLED 0
 #define SPX5_MIRROR_EGRESS 1
 #define SPX5_MIRROR_INGRESS 2
-#define SPX5_MIRROR_MONITOR_PORT_DEFAULT 65
 #define SPX5_QFWD_MP_OFFSET 9 /* Mirror port offset in the QFWD register */
 
 /* Convert from bool ingress/egress to mirror direction */
@@ -200,7 +199,7 @@ void sparx5_mirror_del(struct sparx5_mall_entry *entry)
 
 	sparx5_mirror_monitor_set(sparx5,
 				  mirror_idx,
-				  SPX5_MIRROR_MONITOR_PORT_DEFAULT);
+				  sparx5->data->consts->n_ports);
 }
 
 void sparx5_mirror_stats(struct sparx5_mall_entry *entry,
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index b6f635d85820..f713656f1fae 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -232,9 +232,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev)
 	struct net_device_stats *stats = &dev->stats;
 	struct sparx5_port *port = netdev_priv(dev);
 	struct sparx5 *sparx5 = port->sparx5;
+	const struct sparx5_ops *ops;
 	u32 ifh[IFH_LEN];
 	netdev_tx_t ret;
 
+	ops = sparx5->data->ops;
+
 	memset(ifh, 0, IFH_LEN * 4);
 	sparx5_set_port_ifh(sparx5, ifh, port->portno);
 
@@ -254,7 +257,7 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 	spin_lock(&sparx5->tx_lock);
 	if (sparx5->fdma_irq > 0)
-		ret = sparx5_fdma_xmit(sparx5, ifh, skb);
+		ret = ops->fdma_xmit(sparx5, ifh, skb, dev);
 	else
 		ret = sparx5_inject(sparx5, ifh, skb, dev);
 	spin_unlock(&sparx5->tx_lock);
@@ -264,6 +267,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev)
 	if (ret < 0)
 		goto drop;
 
+	if (!is_sparx5(sparx5))
+		/* When lan969x and TX_OK, stats and SKB consumption is handled
+		 * in the TX completion loop, so dont go any further.
+		 */
+		return NETDEV_TX_OK;
+
 	stats->tx_bytes += skb->len;
 	stats->tx_packets++;
 	sparx5->tx.packets++;
@@ -366,6 +375,6 @@ irqreturn_t sparx5_xtr_handler(int irq, void *_sparx5)
 
 void sparx5_port_inj_timer_setup(struct sparx5_port *port)
 {
-	hrtimer_init(&port->inj_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	port->inj_timer.function = sparx5_injection_timeout;
+	hrtimer_setup(&port->inj_timer, sparx5_injection_timeout, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 }
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c
index f8562c1a894d..cfb4b2e17ace 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c
@@ -32,7 +32,19 @@ sparx5_phylink_mac_select_pcs(struct phylink_config *config,
 {
 	struct sparx5_port *port = netdev_priv(to_net_dev(config->dev));
 
-	return &port->phylink_pcs;
+	/* Return the PCS for all the modes that require it. */
+	switch (interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
+	case PHY_INTERFACE_MODE_5GBASER:
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_25GBASER:
+		return &port->phylink_pcs;
+	default:
+		return NULL;
+	}
 }
 
 static void sparx5_phylink_mac_config(struct phylink_config *config,
@@ -77,7 +89,7 @@ static struct sparx5_port *sparx5_pcs_to_port(struct phylink_pcs *pcs)
 	return container_of(pcs, struct sparx5_port, phylink_pcs);
 }
 
-static void sparx5_pcs_get_state(struct phylink_pcs *pcs,
+static void sparx5_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
 				 struct phylink_link_state *state)
 {
 	struct sparx5_port *port = sparx5_pcs_to_port(pcs);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
index 1401761c6251..04bc8fffaf96 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
@@ -257,6 +257,15 @@ static int sparx5_port_verify_speed(struct sparx5 *sparx5,
 		     conf->speed != SPEED_25000))
 			return sparx5_port_error(port, conf, SPX5_PERR_SPEED);
 		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		if (conf->speed != SPEED_1000 &&
+		    conf->speed != SPEED_100 &&
+		    conf->speed != SPEED_10)
+			return sparx5_port_error(port, conf, SPX5_PERR_SPEED);
+		break;
 	default:
 		return sparx5_port_error(port, conf, SPX5_PERR_IFTYPE);
 	}
@@ -994,6 +1003,7 @@ int sparx5_port_config(struct sparx5 *sparx5,
 		       struct sparx5_port *port,
 		       struct sparx5_port_config *conf)
 {
+	bool rgmii = phy_interface_mode_is_rgmii(conf->phy_mode);
 	bool high_speed_dev = sparx5_is_baser(conf->portmode);
 	const struct sparx5_ops *ops = sparx5->data->ops;
 	int err, urgency, stop_wm;
@@ -1002,8 +1012,14 @@ int sparx5_port_config(struct sparx5 *sparx5,
 	if (err)
 		return err;
 
+	if (rgmii) {
+		err = ops->port_config_rgmii(port, conf);
+		if (err)
+			return err;
+	}
+
 	/* high speed device is already configured */
-	if (!high_speed_dev)
+	if (!rgmii && !high_speed_dev)
 		sparx5_port_config_low_set(sparx5, port, conf);
 
 	/* Configure flow control */
@@ -1067,24 +1083,6 @@ int sparx5_port_init(struct sparx5 *sparx5,
 	if (err)
 		return err;
 
-	/* Configure MAC vlan awareness */
-	err = sparx5_port_max_tags_set(sparx5, port);
-	if (err)
-		return err;
-
-	/* Set Max Length */
-	spx5_rmw(DEV2G5_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN),
-		 DEV2G5_MAC_MAXLEN_CFG_MAX_LEN,
-		 sparx5,
-		 DEV2G5_MAC_MAXLEN_CFG(port->portno));
-
-	/* 1G/2G5: Signal Detect configuration */
-	spx5_wr(DEV2G5_PCS1G_SD_CFG_SD_POL_SET(sd_pol) |
-		DEV2G5_PCS1G_SD_CFG_SD_SEL_SET(sd_sel) |
-		DEV2G5_PCS1G_SD_CFG_SD_ENA_SET(sd_ena),
-		sparx5,
-		DEV2G5_PCS1G_SD_CFG(port->portno));
-
 	/* Set Pause WM hysteresis */
 	spx5_rmw(QSYS_PAUSE_CFG_PAUSE_START_SET(pause_start) |
 		 QSYS_PAUSE_CFG_PAUSE_STOP_SET(pause_stop) |
@@ -1108,6 +1106,27 @@ int sparx5_port_init(struct sparx5 *sparx5,
 		 ANA_CL_FILTER_CTRL_FILTER_SMAC_MC_DIS,
 		 sparx5, ANA_CL_FILTER_CTRL(port->portno));
 
+	if (ops->is_port_rgmii(port->portno))
+		return 0; /* RGMII device - nothing more to configure */
+
+	/* Configure MAC vlan awareness */
+	err = sparx5_port_max_tags_set(sparx5, port);
+	if (err)
+		return err;
+
+	/* Set Max Length */
+	spx5_rmw(DEV2G5_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN),
+		 DEV2G5_MAC_MAXLEN_CFG_MAX_LEN,
+		 sparx5,
+		 DEV2G5_MAC_MAXLEN_CFG(port->portno));
+
+	/* 1G/2G5: Signal Detect configuration */
+	spx5_wr(DEV2G5_PCS1G_SD_CFG_SD_POL_SET(sd_pol) |
+		DEV2G5_PCS1G_SD_CFG_SD_SEL_SET(sd_sel) |
+		DEV2G5_PCS1G_SD_CFG_SD_ENA_SET(sd_ena),
+		sparx5,
+		DEV2G5_PCS1G_SD_CFG(port->portno));
+
 	if (conf->portmode == PHY_INTERFACE_MODE_QSGMII ||
 	    conf->portmode == PHY_INTERFACE_MODE_SGMII) {
 		err = sparx5_serdes_set(sparx5, port, conf);
@@ -1151,7 +1170,7 @@ int sparx5_port_init(struct sparx5 *sparx5,
 	spx5_inst_rmw(DEV10G_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN),
 		      DEV10G_MAC_MAXLEN_CFG_MAX_LEN,
 		      devinst,
-		      DEV10G_MAC_ENA_CFG(0));
+		      DEV10G_MAC_MAXLEN_CFG(0));
 
 	/* Handle Signal Detect in 10G PCS */
 	spx5_inst_wr(PCS10G_BR_PCS_SD_CFG_SD_POL_SET(sd_pol) |
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h
index 9b9bcc6834bc..c8a37468a3d1 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h
@@ -40,6 +40,11 @@ static inline bool sparx5_port_is_25g(int portno)
 	return portno >= 56 && portno <= 63;
 }
 
+static inline bool sparx5_port_is_rgmii(int portno)
+{
+	return false;
+}
+
 static inline u32 sparx5_to_high_dev(struct sparx5 *sparx5, int port)
 {
 	const struct sparx5_ops *ops = sparx5->data->ops;
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c
index 1c2903700a9c..2f168700f63c 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c
@@ -303,7 +303,6 @@ void sparx5_get_hwtimestamp(struct sparx5 *sparx5,
 
 	spin_unlock_irqrestore(&sparx5->ptp_clock_lock, flags);
 }
-EXPORT_SYMBOL_GPL(sparx5_get_hwtimestamp);
 
 irqreturn_t sparx5_ptp_irq_handler(int irq, void *args)
 {
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index e97af7ac2bb2..52cf7112762c 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -31,6 +31,9 @@ static void mana_gd_init_pf_regs(struct pci_dev *pdev)
 	gc->db_page_base = gc->bar0_va +
 				mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
 
+	gc->phys_db_page_base = gc->bar0_pa +
+				mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
+
 	sriov_base_off = mana_gd_r64(gc, GDMA_SRIOV_REG_CFG_BASE_OFF);
 
 	sriov_base_va = gc->bar0_va + sriov_base_off;
@@ -134,9 +137,10 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 	struct gdma_list_devices_resp resp = {};
 	struct gdma_general_req req = {};
 	struct gdma_dev_id dev;
-	u32 i, max_num_devs;
+	int found_dev = 0;
 	u16 dev_type;
 	int err;
+	u32 i;
 
 	mana_gd_init_req_hdr(&req.hdr, GDMA_LIST_DEVICES, sizeof(req),
 			     sizeof(resp));
@@ -148,12 +152,17 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 		return err ? err : -EPROTO;
 	}
 
-	max_num_devs = min_t(u32, MAX_NUM_GDMA_DEVICES, resp.num_of_devs);
-
-	for (i = 0; i < max_num_devs; i++) {
+	for (i = 0; i < GDMA_DEV_LIST_SIZE &&
+	     found_dev < resp.num_of_devs; i++) {
 		dev = resp.devs[i];
 		dev_type = dev.type;
 
+		/* Skip empty devices */
+		if (dev.as_uint32 == 0)
+			continue;
+
+		found_dev++;
+
 		/* HWC is already detected in mana_hwc_create_channel(). */
 		if (dev_type == GDMA_DEVICE_HWC)
 			continue;
@@ -177,7 +186,7 @@ int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req,
 
 	return mana_hwc_send_request(hwc, req_len, req, resp_len, resp);
 }
-EXPORT_SYMBOL_NS(mana_gd_send_request, NET_MANA);
+EXPORT_SYMBOL_NS(mana_gd_send_request, "NET_MANA");
 
 int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length,
 			 struct gdma_mem_info *gmi)
@@ -331,6 +340,7 @@ void mana_gd_wq_ring_doorbell(struct gdma_context *gc, struct gdma_queue *queue)
 	mana_gd_ring_doorbell(gc, queue->gdma_dev->doorbell, queue->type,
 			      queue->id, queue->head * GDMA_WQE_BU_SIZE, 0);
 }
+EXPORT_SYMBOL_NS(mana_gd_wq_ring_doorbell, "NET_MANA");
 
 void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
 {
@@ -343,6 +353,7 @@ void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
 	mana_gd_ring_doorbell(gc, cq->gdma_dev->doorbell, cq->type, cq->id,
 			      head, arm_bit);
 }
+EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA");
 
 static void mana_gd_process_eqe(struct gdma_queue *eq)
 {
@@ -383,6 +394,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
 	case GDMA_EQE_HWC_INIT_EQ_ID_DB:
 	case GDMA_EQE_HWC_INIT_DATA:
 	case GDMA_EQE_HWC_INIT_DONE:
+	case GDMA_EQE_HWC_SOC_SERVICE:
 	case GDMA_EQE_RNIC_QP_FATAL:
 		if (!eq->eq.callback)
 			break;
@@ -666,8 +678,11 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd,
 
 	gmi = &queue->mem_info;
 	err = mana_gd_alloc_memory(gc, spec->queue_size, gmi);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "GDMA queue type: %d, size: %u, gdma memory allocation err: %d\n",
+			spec->type, spec->queue_size, err);
 		goto free_q;
+	}
 
 	queue->head = 0;
 	queue->tail = 0;
@@ -688,6 +703,8 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd,
 	*queue_ptr = queue;
 	return 0;
 out:
+	dev_err(gc->dev, "Failed to create queue type %d of size %u, err: %d\n",
+		spec->type, spec->queue_size, err);
 	mana_gd_free_memory(gmi);
 free_q:
 	kfree(queue);
@@ -716,7 +733,7 @@ int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle)
 
 	return 0;
 }
-EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, NET_MANA);
+EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, "NET_MANA");
 
 static int mana_gd_create_dma_region(struct gdma_dev *gd,
 				     struct gdma_mem_info *gmi)
@@ -770,7 +787,13 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd,
 	}
 
 	gmi->dma_region_handle = resp.dma_region_handle;
+	dev_dbg(gc->dev, "Created DMA region handle 0x%llx\n",
+		gmi->dma_region_handle);
 out:
+	if (err)
+		dev_dbg(gc->dev,
+			"Failed to create DMA region of length: %u, page_type: %d, status: 0x%x, err: %d\n",
+			length, req->gdma_page_type, resp.hdr.status, err);
 	kfree(req);
 	return err;
 }
@@ -793,8 +816,11 @@ int mana_gd_create_mana_eq(struct gdma_dev *gd,
 
 	gmi = &queue->mem_info;
 	err = mana_gd_alloc_memory(gc, spec->queue_size, gmi);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "GDMA queue type: %d, size: %u, gdma memory allocation err: %d\n",
+			spec->type, spec->queue_size, err);
 		goto free_q;
+	}
 
 	err = mana_gd_create_dma_region(gd, gmi);
 	if (err)
@@ -815,12 +841,14 @@ int mana_gd_create_mana_eq(struct gdma_dev *gd,
 	*queue_ptr = queue;
 	return 0;
 out:
+	dev_err(gc->dev, "Failed to create queue type %d of size: %u, err: %d\n",
+		spec->type, spec->queue_size, err);
 	mana_gd_free_memory(gmi);
 free_q:
 	kfree(queue);
 	return err;
 }
-EXPORT_SYMBOL_NS(mana_gd_create_mana_eq, NET_MANA);
+EXPORT_SYMBOL_NS(mana_gd_create_mana_eq, "NET_MANA");
 
 int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
 			      const struct gdma_queue_spec *spec,
@@ -841,8 +869,11 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
 
 	gmi = &queue->mem_info;
 	err = mana_gd_alloc_memory(gc, spec->queue_size, gmi);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "GDMA queue type: %d, size: %u, memory allocation err: %d\n",
+			spec->type, spec->queue_size, err);
 		goto free_q;
+	}
 
 	err = mana_gd_create_dma_region(gd, gmi);
 	if (err)
@@ -862,11 +893,14 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
 	*queue_ptr = queue;
 	return 0;
 out:
+	dev_err(gc->dev, "Failed to create queue type %d of size: %u, err: %d\n",
+		spec->type, spec->queue_size, err);
 	mana_gd_free_memory(gmi);
 free_q:
 	kfree(queue);
 	return err;
 }
+EXPORT_SYMBOL_NS(mana_gd_create_mana_wq_cq, "NET_MANA");
 
 void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue)
 {
@@ -897,7 +931,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue)
 	mana_gd_free_memory(gmi);
 	kfree(queue);
 }
-EXPORT_SYMBOL_NS(mana_gd_destroy_queue, NET_MANA);
+EXPORT_SYMBOL_NS(mana_gd_destroy_queue, "NET_MANA");
 
 int mana_gd_verify_vf_version(struct pci_dev *pdev)
 {
@@ -934,6 +968,7 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
 			err, resp.hdr.status);
 		return err ? err : -EPROTO;
 	}
+	gc->pf_cap_flags1 = resp.pf_cap_flags1;
 	if (resp.pf_cap_flags1 & GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) {
 		err = mana_gd_query_hwc_timeout(pdev, &hwc->hwc_timeout);
 		if (err) {
@@ -974,7 +1009,6 @@ int mana_gd_register_device(struct gdma_dev *gd)
 
 	return 0;
 }
-EXPORT_SYMBOL_NS(mana_gd_register_device, NET_MANA);
 
 int mana_gd_deregister_device(struct gdma_dev *gd)
 {
@@ -1005,7 +1039,6 @@ int mana_gd_deregister_device(struct gdma_dev *gd)
 
 	return err;
 }
-EXPORT_SYMBOL_NS(mana_gd_deregister_device, NET_MANA);
 
 u32 mana_gd_wq_avail_space(struct gdma_queue *wq)
 {
@@ -1041,7 +1074,7 @@ static u32 mana_gd_write_client_oob(const struct gdma_wqe_request *wqe_req,
 	header->inline_oob_size_div4 = client_oob_size / sizeof(u32);
 
 	if (oob_in_sgl) {
-		WARN_ON_ONCE(!pad_data || wqe_req->num_sge < 2);
+		WARN_ON_ONCE(wqe_req->num_sge < 2);
 
 		header->client_oob_in_sgl = 1;
 
@@ -1148,6 +1181,7 @@ int mana_gd_post_work_request(struct gdma_queue *wq,
 
 	return 0;
 }
+EXPORT_SYMBOL_NS(mana_gd_post_work_request, "NET_MANA");
 
 int mana_gd_post_and_ring(struct gdma_queue *queue,
 			  const struct gdma_wqe_request *wqe_req,
@@ -1157,8 +1191,11 @@ int mana_gd_post_and_ring(struct gdma_queue *queue,
 	int err;
 
 	err = mana_gd_post_work_request(queue, wqe_req, wqe_info);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "Failed to post work req from queue type %d of size %u (err=%d)\n",
+			queue->type, queue->queue_size, err);
 		return err;
+	}
 
 	mana_gd_wq_ring_doorbell(gc, queue);
 
@@ -1218,6 +1255,7 @@ int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe)
 
 	return cqe_idx;
 }
+EXPORT_SYMBOL_NS(mana_gd_poll_cq, "NET_MANA");
 
 static irqreturn_t mana_gd_intr(int irq, void *arg)
 {
@@ -1318,7 +1356,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 				   GFP_KERNEL);
 	if (!gc->irq_contexts) {
 		err = -ENOMEM;
-		goto free_irq_vector;
+		goto free_irq_array;
 	}
 
 	for (i = 0; i < nvec; i++) {
@@ -1375,6 +1413,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 	gc->max_num_msix = nvec;
 	gc->num_msix_usable = nvec;
 	cpus_read_unlock();
+	kfree(irqs);
 	return 0;
 
 free_irq:
@@ -1387,8 +1426,9 @@ free_irq:
 	}
 
 	kfree(gc->irq_contexts);
-	kfree(irqs);
 	gc->irq_contexts = NULL;
+free_irq_array:
+	kfree(irqs);
 free_irq_vector:
 	cpus_read_unlock();
 	pci_free_irq_vectors(pdev);
@@ -1432,9 +1472,15 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	mana_gd_init_registers(pdev);
 	mana_smc_init(&gc->shm_channel, gc->dev, gc->shm_base);
 
+	gc->service_wq = alloc_ordered_workqueue("gdma_service_wq", 0);
+	if (!gc->service_wq)
+		return -ENOMEM;
+
 	err = mana_gd_setup_irqs(pdev);
-	if (err)
-		return err;
+	if (err) {
+		dev_err(gc->dev, "Failed to setup IRQs: %d\n", err);
+		goto free_workqueue;
+	}
 
 	err = mana_hwc_create_channel(gc);
 	if (err)
@@ -1452,12 +1498,16 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	if (err)
 		goto destroy_hwc;
 
+	dev_dbg(&pdev->dev, "mana gdma setup successful\n");
 	return 0;
 
 destroy_hwc:
 	mana_hwc_destroy_channel(gc);
 remove_irq:
 	mana_gd_remove_irqs(pdev);
+free_workqueue:
+	destroy_workqueue(gc->service_wq);
+	dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err);
 	return err;
 }
 
@@ -1468,6 +1518,9 @@ static void mana_gd_cleanup(struct pci_dev *pdev)
 	mana_hwc_destroy_channel(gc);
 
 	mana_gd_remove_irqs(pdev);
+
+	destroy_workqueue(gc->service_wq);
+	dev_dbg(&pdev->dev, "mana gdma cleanup successful\n");
 }
 
 static bool mana_is_pf(unsigned short dev_id)
@@ -1486,8 +1539,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	BUILD_BUG_ON(2 * MAX_PORTS_IN_MANA_DEV * GDMA_EQE_SIZE > EQ_SIZE);
 
 	err = pci_enable_device(pdev);
-	if (err)
+	if (err) {
+		dev_err(&pdev->dev, "Failed to enable pci device (err=%d)\n", err);
 		return -ENXIO;
+	}
 
 	pci_set_master(pdev);
 
@@ -1496,9 +1551,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto disable_dev;
 
 	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
-	if (err)
+	if (err) {
+		dev_err(&pdev->dev, "DMA set mask failed: %d\n", err);
 		goto release_region;
-
+	}
 	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 
 	err = -ENOMEM;
@@ -1533,8 +1589,14 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto cleanup_gd;
 
+	err = mana_rdma_probe(&gc->mana_ib);
+	if (err)
+		goto cleanup_mana;
+
 	return 0;
 
+cleanup_mana:
+	mana_remove(&gc->mana, false);
 cleanup_gd:
 	mana_gd_cleanup(pdev);
 unmap_bar:
@@ -1545,6 +1607,7 @@ unmap_bar:
 	 * adapter-MTU file and apc->mana_pci_debugfs folder.
 	 */
 	debugfs_remove_recursive(gc->mana_pci_debugfs);
+	gc->mana_pci_debugfs = NULL;
 	pci_iounmap(pdev, bar0_va);
 free_gc:
 	pci_set_drvdata(pdev, NULL);
@@ -1561,18 +1624,23 @@ static void mana_gd_remove(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 
+	mana_rdma_remove(&gc->mana_ib);
 	mana_remove(&gc->mana, false);
 
 	mana_gd_cleanup(pdev);
 
 	debugfs_remove_recursive(gc->mana_pci_debugfs);
 
+	gc->mana_pci_debugfs = NULL;
+
 	pci_iounmap(pdev, gc->bar0_va);
 
 	vfree(gc);
 
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+
+	dev_dbg(&pdev->dev, "mana gdma remove successful\n");
 }
 
 /* The 'state' parameter is not used. */
@@ -1580,6 +1648,7 @@ static int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 
+	mana_rdma_remove(&gc->mana_ib);
 	mana_remove(&gc->mana, true);
 
 	mana_gd_cleanup(pdev);
@@ -1604,6 +1673,10 @@ static int mana_gd_resume(struct pci_dev *pdev)
 	if (err)
 		return err;
 
+	err = mana_rdma_probe(&gc->mana_ib);
+	if (err)
+		return err;
+
 	return 0;
 }
 
@@ -1614,12 +1687,15 @@ static void mana_gd_shutdown(struct pci_dev *pdev)
 
 	dev_info(&pdev->dev, "Shutdown was called\n");
 
+	mana_rdma_remove(&gc->mana_ib);
 	mana_remove(&gc->mana, true);
 
 	mana_gd_cleanup(pdev);
 
 	debugfs_remove_recursive(gc->mana_pci_debugfs);
 
+	gc->mana_pci_debugfs = NULL;
+
 	pci_disable_device(pdev);
 }
 
@@ -1646,17 +1722,21 @@ static int __init mana_driver_init(void)
 	mana_debugfs_root = debugfs_create_dir("mana", NULL);
 
 	err = pci_register_driver(&mana_driver);
-	if (err)
+	if (err) {
 		debugfs_remove(mana_debugfs_root);
+		mana_debugfs_root = NULL;
+	}
 
 	return err;
 }
 
 static void __exit mana_driver_exit(void)
 {
+	pci_unregister_driver(&mana_driver);
+
 	debugfs_remove(mana_debugfs_root);
 
-	pci_unregister_driver(&mana_driver);
+	mana_debugfs_root = NULL;
 }
 
 module_init(mana_driver_init);
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index a00f915c5188..a8c4d8db75a5 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -112,11 +112,13 @@ out:
 static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
 					struct gdma_event *event)
 {
+	union hwc_init_soc_service_type service_data;
 	struct hw_channel_context *hwc = ctx;
 	struct gdma_dev *gd = hwc->gdma_dev;
 	union hwc_init_type_data type_data;
 	union hwc_init_eq_id_db eq_db;
 	u32 type, val;
+	int ret;
 
 	switch (event->type) {
 	case GDMA_EQE_HWC_INIT_EQ_ID_DB:
@@ -199,7 +201,24 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
 		}
 
 		break;
+	case GDMA_EQE_HWC_SOC_SERVICE:
+		service_data.as_uint32 = event->details[0];
+		type = service_data.type;
 
+		switch (type) {
+		case GDMA_SERVICE_TYPE_RDMA_SUSPEND:
+		case GDMA_SERVICE_TYPE_RDMA_RESUME:
+			ret = mana_rdma_service_event(gd->gdma_context, type);
+			if (ret)
+				dev_err(hwc->dev, "Failed to schedule adev service event: %d\n",
+					ret);
+			break;
+		default:
+			dev_warn(hwc->dev, "Received unknown SOC service type %u\n", type);
+			break;
+		}
+
+		break;
 	default:
 		dev_warn(hwc->dev, "Received unknown gdma event %u\n", event->type);
 		/* Ignore unknown events, which should never happen. */
@@ -440,7 +459,8 @@ static int mana_hwc_alloc_dma_buf(struct hw_channel_context *hwc, u16 q_depth,
 	gmi = &dma_buf->mem_info;
 	err = mana_gd_alloc_memory(gc, buf_size, gmi);
 	if (err) {
-		dev_err(hwc->dev, "Failed to allocate DMA buffer: %d\n", err);
+		dev_err(hwc->dev, "Failed to allocate DMA buffer size: %u, err %d\n",
+			buf_size, err);
 		goto out;
 	}
 
@@ -529,6 +549,9 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc,
 out:
 	if (err)
 		mana_hwc_destroy_wq(hwc, hwc_wq);
+
+	dev_err(hwc->dev, "Failed to create HWC queue size= %u type= %d err= %d\n",
+		queue_size, q_type, err);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
index 23b1521c0df9..d30721d4516f 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
@@ -91,7 +91,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq,
 		goto out;
 
 	xdp_init_buff(xdp, PAGE_SIZE, &rxq->xdp_rxq);
-	xdp_prepare_buff(xdp, buf_va, XDP_PACKET_HEADROOM, pkt_len, false);
+	xdp_prepare_buff(xdp, buf_va, XDP_PACKET_HEADROOM, pkt_len, true);
 
 	act = bpf_prog_run_xdp(prog, xdp);
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 57ac732e7707..ccd2885c939e 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -13,6 +13,7 @@
 
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
+#include <net/netdev_lock.h>
 #include <net/page_pool/helpers.h>
 #include <net/xdp.h>
 
@@ -52,10 +53,12 @@ static int mana_open(struct net_device *ndev)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
 	int err;
-
 	err = mana_alloc_queues(ndev);
-	if (err)
+
+	if (err) {
+		netdev_err(ndev, "%s failed to allocate queues: %d\n", __func__, err);
 		return err;
+	}
 
 	apc->port_is_up = true;
 
@@ -64,7 +67,7 @@ static int mana_open(struct net_device *ndev)
 
 	netif_carrier_on(ndev);
 	netif_tx_wake_all_queues(ndev);
-
+	netdev_dbg(ndev, "%s successful\n", __func__);
 	return 0;
 }
 
@@ -176,6 +179,9 @@ static int mana_map_skb(struct sk_buff *skb, struct mana_port_context *apc,
 	return 0;
 
 frag_err:
+	if (net_ratelimit())
+		netdev_err(apc->ndev, "Failed to map skb of size %u to DMA\n",
+			   skb->len);
 	for (i = sg_i - 1; i >= hsg; i--)
 		dma_unmap_page(dev, ash->dma_handle[i], ash->size[i],
 			       DMA_TO_DEVICE);
@@ -256,6 +262,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	if (skb_cow_head(skb, MANA_HEADROOM))
 		goto tx_drop_count;
 
+	if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
+		goto tx_drop_count;
+
 	txq = &apc->tx_qp[txq_idx].txq;
 	gdma_sq = txq->gdma_sq;
 	cq = &apc->tx_qp[txq_idx].tx_cq;
@@ -652,30 +661,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu
 	mpc->rxbpre_total = 0;
 
 	for (i = 0; i < num_rxb; i++) {
-		if (mpc->rxbpre_alloc_size > PAGE_SIZE) {
-			va = netdev_alloc_frag(mpc->rxbpre_alloc_size);
-			if (!va)
-				goto error;
-
-			page = virt_to_head_page(va);
-			/* Check if the frag falls back to single page */
-			if (compound_order(page) <
-			    get_order(mpc->rxbpre_alloc_size)) {
-				put_page(page);
-				goto error;
-			}
-		} else {
-			page = dev_alloc_page();
-			if (!page)
-				goto error;
+		page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size));
+		if (!page)
+			goto error;
 
-			va = page_to_virt(page);
-		}
+		va = page_to_virt(page);
 
 		da = dma_map_single(dev, va + mpc->rxbpre_headroom,
 				    mpc->rxbpre_datasize, DMA_FROM_DEVICE);
 		if (dma_mapping_error(dev, da)) {
-			put_page(virt_to_head_page(va));
+			put_page(page);
 			goto error;
 		}
 
@@ -687,6 +682,7 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu
 	return 0;
 
 error:
+	netdev_err(mpc->ndev, "Failed to pre-allocate RX buffers for %d queues\n", num_queues);
 	mana_pre_dealloc_rxbufs(mpc);
 	return -ENOMEM;
 }
@@ -738,12 +734,11 @@ static const struct net_device_ops mana_devops = {
 static void mana_cleanup_port_context(struct mana_port_context *apc)
 {
 	/*
-	 * at this point all dir/files under the vport directory
-	 * are already cleaned up.
-	 * We are sure the apc->mana_port_debugfs remove will not
-	 * cause any freed memory access issues
+	 * make sure subsequent cleanup attempts don't end up removing already
+	 * cleaned dentry pointer
 	 */
 	debugfs_remove(apc->mana_port_debugfs);
+	apc->mana_port_debugfs = NULL;
 	kfree(apc->rxqs);
 	apc->rxqs = NULL;
 }
@@ -926,7 +921,7 @@ static void mana_pf_deregister_filter(struct mana_port_context *apc)
 
 static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
 				 u32 proto_minor_ver, u32 proto_micro_ver,
-				 u16 *max_num_vports)
+				 u16 *max_num_vports, u8 *bm_hostmode)
 {
 	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 	struct mana_query_device_cfg_resp resp = {};
@@ -937,7 +932,7 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
 	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_DEV_CONFIG,
 			     sizeof(req), sizeof(resp));
 
-	req.hdr.resp.msg_version = GDMA_MESSAGE_V2;
+	req.hdr.resp.msg_version = GDMA_MESSAGE_V3;
 
 	req.proto_major_ver = proto_major_ver;
 	req.proto_minor_ver = proto_minor_ver;
@@ -961,11 +956,16 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
 
 	*max_num_vports = resp.max_num_vports;
 
-	if (resp.hdr.response.msg_version == GDMA_MESSAGE_V2)
+	if (resp.hdr.response.msg_version >= GDMA_MESSAGE_V2)
 		gc->adapter_mtu = resp.adapter_mtu;
 	else
 		gc->adapter_mtu = ETH_FRAME_LEN;
 
+	if (resp.hdr.response.msg_version >= GDMA_MESSAGE_V3)
+		*bm_hostmode = resp.bm_hostmode;
+	else
+		*bm_hostmode = 0;
+
 	debugfs_create_u16("adapter-MTU", 0400, gc->mana_pci_debugfs, &gc->adapter_mtu);
 
 	return 0;
@@ -1022,7 +1022,7 @@ void mana_uncfg_vport(struct mana_port_context *apc)
 	WARN_ON(apc->vport_use_count < 0);
 	mutex_unlock(&apc->vport_mutex);
 }
-EXPORT_SYMBOL_NS(mana_uncfg_vport, NET_MANA);
+EXPORT_SYMBOL_NS(mana_uncfg_vport, "NET_MANA");
 
 int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
 		   u32 doorbell_pg_id)
@@ -1092,7 +1092,7 @@ out:
 
 	return err;
 }
-EXPORT_SYMBOL_NS(mana_cfg_vport, NET_MANA);
+EXPORT_SYMBOL_NS(mana_cfg_vport, "NET_MANA");
 
 static int mana_cfg_vport_steering(struct mana_port_context *apc,
 				   enum TRI_STATE rx,
@@ -1214,7 +1214,7 @@ int mana_create_wq_obj(struct mana_port_context *apc,
 out:
 	return err;
 }
-EXPORT_SYMBOL_NS(mana_create_wq_obj, NET_MANA);
+EXPORT_SYMBOL_NS(mana_create_wq_obj, "NET_MANA");
 
 void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
 			 mana_handle_t wq_obj)
@@ -1242,7 +1242,7 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
 		netdev_err(ndev, "Failed to destroy WQ object: %d, 0x%x\n", err,
 			   resp.hdr.status);
 }
-EXPORT_SYMBOL_NS(mana_destroy_wq_obj, NET_MANA);
+EXPORT_SYMBOL_NS(mana_destroy_wq_obj, "NET_MANA");
 
 static void mana_destroy_eq(struct mana_context *ac)
 {
@@ -1254,6 +1254,7 @@ static void mana_destroy_eq(struct mana_context *ac)
 		return;
 
 	debugfs_remove_recursive(ac->mana_eqs_debugfs);
+	ac->mana_eqs_debugfs = NULL;
 
 	for (i = 0; i < gc->max_num_queues; i++) {
 		eq = ac->eqs[i].eq;
@@ -1304,8 +1305,10 @@ static int mana_create_eq(struct mana_context *ac)
 	for (i = 0; i < gc->max_num_queues; i++) {
 		spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
 		err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq);
-		if (err)
+		if (err) {
+			dev_err(gc->dev, "Failed to create EQ %d : %d\n", i, err);
 			goto out;
+		}
 		mana_create_eq_debugfs(ac, i);
 	}
 
@@ -1547,8 +1550,12 @@ static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va,
 		return NULL;
 
 	if (xdp->data_hard_start) {
+		u32 metasize = xdp->data - xdp->data_meta;
+
 		skb_reserve(skb, xdp->data - xdp->data_hard_start);
 		skb_put(skb, xdp->data_end - xdp->data);
+		if (metasize)
+			skb_metadata_set(skb, metasize);
 		return skb;
 	}
 
@@ -1660,7 +1667,7 @@ drop:
 }
 
 static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
-			     dma_addr_t *da, bool *from_pool, bool is_napi)
+			     dma_addr_t *da, bool *from_pool)
 {
 	struct page *page;
 	void *va;
@@ -1671,21 +1678,6 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
 	if (rxq->xdp_save_va) {
 		va = rxq->xdp_save_va;
 		rxq->xdp_save_va = NULL;
-	} else if (rxq->alloc_size > PAGE_SIZE) {
-		if (is_napi)
-			va = napi_alloc_frag(rxq->alloc_size);
-		else
-			va = netdev_alloc_frag(rxq->alloc_size);
-
-		if (!va)
-			return NULL;
-
-		page = virt_to_head_page(va);
-		/* Check if the frag falls back to single page */
-		if (compound_order(page) < get_order(rxq->alloc_size)) {
-			put_page(page);
-			return NULL;
-		}
 	} else {
 		page = page_pool_dev_alloc_pages(rxq->page_pool);
 		if (!page)
@@ -1718,7 +1710,7 @@ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq,
 	dma_addr_t da;
 	void *va;
 
-	va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true);
+	va = mana_get_rxfrag(rxq, dev, &da, &from_pool);
 	if (!va)
 		return;
 
@@ -1914,6 +1906,7 @@ static void mana_destroy_txq(struct mana_port_context *apc)
 
 	for (i = 0; i < apc->num_queues; i++) {
 		debugfs_remove_recursive(apc->tx_qp[i].mana_tx_debugfs);
+		apc->tx_qp[i].mana_tx_debugfs = NULL;
 
 		napi = &apc->tx_qp[i].tx_cq.napi;
 		if (apc->tx_qp[i].txq.napi_initialized) {
@@ -2080,6 +2073,8 @@ static int mana_create_txq(struct mana_port_context *apc,
 
 	return 0;
 out:
+	netdev_err(net, "Failed to create %d TX queues, %d\n",
+		   apc->num_queues, err);
 	mana_destroy_txq(apc);
 	return err;
 }
@@ -2099,6 +2094,7 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 		return;
 
 	debugfs_remove_recursive(rxq->mana_rx_debugfs);
+	rxq->mana_rx_debugfs = NULL;
 
 	napi = &rxq->rx_cq.napi;
 
@@ -2156,7 +2152,7 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key,
 	if (mpc->rxbufs_pre)
 		va = mana_get_rxbuf_pre(rxq, &da);
 	else
-		va = mana_get_rxfrag(rxq, dev, &da, &from_pool, false);
+		va = mana_get_rxfrag(rxq, dev, &da, &from_pool);
 
 	if (!va)
 		return -ENOMEM;
@@ -2242,6 +2238,7 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
 	pprm.netdev = rxq->ndev;
+	pprm.order = get_order(rxq->alloc_size);
 
 	rxq->page_pool = page_pool_create(&pprm);
 
@@ -2415,6 +2412,7 @@ static int mana_add_rx_queues(struct mana_port_context *apc,
 		rxq = mana_create_rxq(apc, i, &ac->eqs[i], ndev);
 		if (!rxq) {
 			err = -ENOMEM;
+			netdev_err(ndev, "Failed to create rxq %d : %d\n", i, err);
 			goto out;
 		}
 
@@ -2448,7 +2446,7 @@ static void mana_destroy_vport(struct mana_port_context *apc)
 	mana_destroy_txq(apc);
 	mana_uncfg_vport(apc);
 
-	if (gd->gdma_context->is_pf)
+	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode)
 		mana_pf_deregister_hw_vport(apc);
 }
 
@@ -2460,7 +2458,7 @@ static int mana_create_vport(struct mana_port_context *apc,
 
 	apc->default_rxobj = INVALID_MANA_HANDLE;
 
-	if (gd->gdma_context->is_pf) {
+	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) {
 		err = mana_pf_register_hw_vport(apc);
 		if (err)
 			return err;
@@ -2536,6 +2534,7 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 
 	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT,
 			     sizeof(req), sizeof(resp));
+	req.hdr.resp.msg_version = GDMA_MESSAGE_V2;
 	req.req_stats = STATISTICS_FLAGS_RX_DISCARDS_NO_WQE |
 			STATISTICS_FLAGS_RX_ERRORS_VPORT_DISABLED |
 			STATISTICS_FLAGS_HC_RX_BYTES |
@@ -2660,12 +2659,18 @@ int mana_alloc_queues(struct net_device *ndev)
 	int err;
 
 	err = mana_create_vport(apc, ndev);
-	if (err)
+	if (err) {
+		netdev_err(ndev, "Failed to create vPort %u : %d\n", apc->port_idx, err);
 		return err;
+	}
 
 	err = netif_set_real_num_tx_queues(ndev, apc->num_queues);
-	if (err)
+	if (err) {
+		netdev_err(ndev,
+			   "netif_set_real_num_tx_queues () failed for ndev with num_queues %u : %d\n",
+			   apc->num_queues, err);
 		goto destroy_vport;
+	}
 
 	err = mana_add_rx_queues(apc, ndev);
 	if (err)
@@ -2674,16 +2679,22 @@ int mana_alloc_queues(struct net_device *ndev)
 	apc->rss_state = apc->num_queues > 1 ? TRI_STATE_TRUE : TRI_STATE_FALSE;
 
 	err = netif_set_real_num_rx_queues(ndev, apc->num_queues);
-	if (err)
+	if (err) {
+		netdev_err(ndev,
+			   "netif_set_real_num_rx_queues () failed for ndev with num_queues %u : %d\n",
+			   apc->num_queues, err);
 		goto destroy_vport;
+	}
 
 	mana_rss_table_init(apc);
 
 	err = mana_config_rss(apc, TRI_STATE_TRUE, true, true);
-	if (err)
+	if (err) {
+		netdev_err(ndev, "Failed to configure RSS table: %d\n", err);
 		goto destroy_vport;
+	}
 
-	if (gd->gdma_context->is_pf) {
+	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) {
 		err = mana_pf_register_filter(apc);
 		if (err)
 			goto destroy_vport;
@@ -2745,7 +2756,7 @@ static int mana_dealloc_queues(struct net_device *ndev)
 
 	mana_chn_setxdp(apc, NULL);
 
-	if (gd->gdma_context->is_pf)
+	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode)
 		mana_pf_deregister_filter(apc);
 
 	/* No packet can be transmitted now since apc->port_is_up is false.
@@ -2822,8 +2833,10 @@ int mana_detach(struct net_device *ndev, bool from_close)
 
 	if (apc->port_st_save) {
 		err = mana_dealloc_queues(ndev);
-		if (err)
+		if (err) {
+			netdev_err(ndev, "%s failed to deallocate queues: %d\n", __func__, err);
 			return err;
+		}
 	}
 
 	if (!from_close) {
@@ -2872,6 +2885,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	ndev->dev_port = port_idx;
 	SET_NETDEV_DEV(ndev, gc->dev);
 
+	netif_set_tso_max_size(ndev, GSO_MAX_SIZE);
+
 	netif_carrier_off(ndev);
 
 	netdev_rss_key_fill(apc->hashkey, MANA_HASH_KEY_SIZE);
@@ -2935,7 +2950,7 @@ static void remove_adev(struct gdma_dev *gd)
 	gd->adev = NULL;
 }
 
-static int add_adev(struct gdma_dev *gd)
+static int add_adev(struct gdma_dev *gd, const char *name)
 {
 	struct auxiliary_device *adev;
 	struct mana_adev *madev;
@@ -2951,7 +2966,7 @@ static int add_adev(struct gdma_dev *gd)
 		goto idx_fail;
 	adev->id = ret;
 
-	adev->name = "rdma";
+	adev->name = name;
 	adev->dev.parent = gd->gdma_context->dev;
 	adev->dev.release = adev_release;
 	madev->mdev = gd;
@@ -2967,6 +2982,8 @@ static int add_adev(struct gdma_dev *gd)
 		goto add_fail;
 
 	gd->adev = adev;
+	dev_dbg(gd->gdma_context->dev,
+		"Auxiliary device added successfully\n");
 	return 0;
 
 add_fail:
@@ -2981,11 +2998,76 @@ idx_fail:
 	return ret;
 }
 
+static void mana_rdma_service_handle(struct work_struct *work)
+{
+	struct mana_service_work *serv_work =
+		container_of(work, struct mana_service_work, work);
+	struct gdma_dev *gd = serv_work->gdma_dev;
+	struct device *dev = gd->gdma_context->dev;
+	int ret;
+
+	if (READ_ONCE(gd->rdma_teardown))
+		goto out;
+
+	switch (serv_work->event) {
+	case GDMA_SERVICE_TYPE_RDMA_SUSPEND:
+		if (!gd->adev || gd->is_suspended)
+			break;
+
+		remove_adev(gd);
+		gd->is_suspended = true;
+		break;
+
+	case GDMA_SERVICE_TYPE_RDMA_RESUME:
+		if (!gd->is_suspended)
+			break;
+
+		ret = add_adev(gd, "rdma");
+		if (ret)
+			dev_err(dev, "Failed to add adev on resume: %d\n", ret);
+		else
+			gd->is_suspended = false;
+		break;
+
+	default:
+		dev_warn(dev, "unknown adev service event %u\n",
+			 serv_work->event);
+		break;
+	}
+
+out:
+	kfree(serv_work);
+}
+
+int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type event)
+{
+	struct gdma_dev *gd = &gc->mana_ib;
+	struct mana_service_work *serv_work;
+
+	if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) {
+		/* RDMA device is not detected on pci */
+		return 0;
+	}
+
+	serv_work = kzalloc(sizeof(*serv_work), GFP_ATOMIC);
+	if (!serv_work)
+		return -ENOMEM;
+
+	serv_work->event = event;
+	serv_work->gdma_dev = gd;
+
+	INIT_WORK(&serv_work->work, mana_rdma_service_handle);
+	queue_work(gc->service_wq, &serv_work->work);
+
+	return 0;
+}
+
 int mana_probe(struct gdma_dev *gd, bool resuming)
 {
 	struct gdma_context *gc = gd->gdma_context;
 	struct mana_context *ac = gd->driver_data;
 	struct device *dev = gc->dev;
+	u8 bm_hostmode = 0;
 	u16 num_ports = 0;
 	int err;
 	int i;
@@ -3008,14 +3090,18 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 	}
 
 	err = mana_create_eq(ac);
-	if (err)
+	if (err) {
+		dev_err(dev, "Failed to create EQs: %d\n", err);
 		goto out;
+	}
 
 	err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
-				    MANA_MICRO_VERSION, &num_ports);
+				    MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
 	if (err)
 		goto out;
 
+	ac->bm_hostmode = bm_hostmode;
+
 	if (!resuming) {
 		ac->num_ports = num_ports;
 	} else {
@@ -3063,10 +3149,16 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 		}
 	}
 
-	err = add_adev(gd);
+	err = add_adev(gd, "eth");
 out:
-	if (err)
+	if (err) {
 		mana_remove(gd, false);
+	} else {
+		dev_dbg(dev, "gd=%p, id=%u, num_ports=%d, type=%u, instance=%u\n",
+			gd, gd->dev_id.as_uint32, ac->num_ports,
+			gd->dev_id.type, gd->dev_id.instance);
+		dev_dbg(dev, "%s succeeded\n", __func__);
+	}
 
 	return err;
 }
@@ -3128,23 +3220,68 @@ out:
 	gd->driver_data = NULL;
 	gd->gdma_context = NULL;
 	kfree(ac);
+	dev_dbg(dev, "%s succeeded\n", __func__);
 }
 
-struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index)
+int mana_rdma_probe(struct gdma_dev *gd)
+{
+	int err = 0;
+
+	if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) {
+		/* RDMA device is not detected on pci */
+		return err;
+	}
+
+	err = mana_gd_register_device(gd);
+	if (err)
+		return err;
+
+	err = add_adev(gd, "rdma");
+	if (err)
+		mana_gd_deregister_device(gd);
+
+	return err;
+}
+
+void mana_rdma_remove(struct gdma_dev *gd)
+{
+	struct gdma_context *gc = gd->gdma_context;
+
+	if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) {
+		/* RDMA device is not detected on pci */
+		return;
+	}
+
+	WRITE_ONCE(gd->rdma_teardown, true);
+	flush_workqueue(gc->service_wq);
+
+	if (gd->adev)
+		remove_adev(gd);
+
+	mana_gd_deregister_device(gd);
+}
+
+struct net_device *mana_get_primary_netdev(struct mana_context *ac,
+					   u32 port_index,
+					   netdevice_tracker *tracker)
 {
 	struct net_device *ndev;
 
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
-			 "Taking primary netdev without holding the RCU read lock");
 	if (port_index >= ac->num_ports)
 		return NULL;
 
-	/* When mana is used in netvsc, the upper netdevice should be returned. */
-	if (ac->ports[port_index]->flags & IFF_SLAVE)
-		ndev = netdev_master_upper_dev_get_rcu(ac->ports[port_index]);
-	else
+	rcu_read_lock();
+
+	/* If mana is used in netvsc, the upper netdevice should be returned. */
+	ndev = netdev_master_upper_dev_get_rcu(ac->ports[port_index]);
+
+	/* If there is no upper device, use the parent Ethernet device */
+	if (!ndev)
 		ndev = ac->ports[port_index];
 
+	netdev_hold(ndev, tracker, GFP_ATOMIC);
+	rcu_read_unlock();
+
 	return ndev;
 }
-EXPORT_SYMBOL_NS(mana_get_primary_netdev_rcu, NET_MANA);
+EXPORT_SYMBOL_NS(mana_get_primary_netdev, "NET_MANA");
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 3d72aa7b1305..08bee56aea35 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -830,6 +830,7 @@ EXPORT_SYMBOL(ocelot_vlan_prepare);
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 		    bool untagged)
 {
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	int err;
 
 	/* Ignore VID 0 added to our RX filter by the 8021q module, since
@@ -849,6 +850,11 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 					   ocelot_bridge_vlan_find(ocelot, vid));
 		if (err)
 			return err;
+	} else if (ocelot_port->pvid_vlan &&
+		   ocelot_bridge_vlan_find(ocelot, vid) == ocelot_port->pvid_vlan) {
+		err = ocelot_port_set_pvid(ocelot, port, NULL);
+		if (err)
+			return err;
 	}
 
 	/* Untagged egress vlan clasification */
@@ -1432,7 +1438,7 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
 
 	memset(ifh, 0, OCELOT_TAG_LEN);
 	ocelot_ifh_set_bypass(ifh, 1);
-	ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports));
+	ocelot_ifh_set_src(ifh, ocelot->num_phys_ports);
 	ocelot_ifh_set_dest(ifh, BIT_ULL(port));
 	ocelot_ifh_set_qos_class(ifh, qos_class);
 	ocelot_ifh_set_tag_type(ifh, tag_type);
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 558e03301aa8..469784d3a1a6 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -758,12 +758,13 @@ static int ocelot_port_fdb_do_dump(const unsigned char *addr, u16 vid,
 				   bool is_static, void *data)
 {
 	struct ocelot_dump_ctx *dump = data;
+	struct ndo_fdb_dump_context *ctx = (void *)dump->cb->ctx;
 	u32 portid = NETLINK_CB(dump->cb->skb).portid;
 	u32 seq = dump->cb->nlh->nlmsg_seq;
 	struct nlmsghdr *nlh;
 	struct ndmsg *ndm;
 
-	if (dump->idx < dump->cb->args[2])
+	if (dump->idx < ctx->fdb_idx)
 		goto skip;
 
 	nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH,
@@ -869,23 +870,30 @@ static int ocelot_set_features(struct net_device *dev,
 
 static int ocelot_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
+	return phy_mii_ioctl(dev->phydev, ifr, cmd);
+}
+
+static int ocelot_port_hwtstamp_get(struct net_device *dev,
+				    struct kernel_hwtstamp_config *cfg)
+{
 	struct ocelot_port_private *priv = netdev_priv(dev);
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->port.index;
 
-	/* If the attached PHY device isn't capable of timestamping operations,
-	 * use our own (when possible).
-	 */
-	if (!phy_has_hwtstamp(dev->phydev) && ocelot->ptp) {
-		switch (cmd) {
-		case SIOCSHWTSTAMP:
-			return ocelot_hwstamp_set(ocelot, port, ifr);
-		case SIOCGHWTSTAMP:
-			return ocelot_hwstamp_get(ocelot, port, ifr);
-		}
-	}
+	ocelot_hwstamp_get(ocelot, port, cfg);
 
-	return phy_mii_ioctl(dev->phydev, ifr, cmd);
+	return 0;
+}
+
+static int ocelot_port_hwtstamp_set(struct net_device *dev,
+				    struct kernel_hwtstamp_config *cfg,
+				    struct netlink_ext_ack *extack)
+{
+	struct ocelot_port_private *priv = netdev_priv(dev);
+	struct ocelot *ocelot = priv->port.ocelot;
+	int port = priv->port.index;
+
+	return ocelot_hwstamp_set(ocelot, port, cfg, extack);
 }
 
 static int ocelot_change_mtu(struct net_device *dev, int new_mtu)
@@ -916,6 +924,8 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_set_features		= ocelot_set_features,
 	.ndo_setup_tc			= ocelot_setup_tc,
 	.ndo_eth_ioctl			= ocelot_ioctl,
+	.ndo_hwtstamp_get		= ocelot_port_hwtstamp_get,
+	.ndo_hwtstamp_set		= ocelot_port_hwtstamp_set,
 };
 
 struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port)
@@ -992,6 +1002,16 @@ static int ocelot_port_get_ts_info(struct net_device *dev,
 	return ocelot_get_ts_info(ocelot, port, info);
 }
 
+static void ocelot_port_ts_stats(struct net_device *dev,
+				 struct ethtool_ts_stats *ts_stats)
+{
+	struct ocelot_port_private *priv = netdev_priv(dev);
+	struct ocelot *ocelot = priv->port.ocelot;
+	int port = priv->port.index;
+
+	ocelot_port_get_ts_stats(ocelot, port, ts_stats);
+}
+
 static const struct ethtool_ops ocelot_ethtool_ops = {
 	.get_strings		= ocelot_port_get_strings,
 	.get_ethtool_stats	= ocelot_port_get_ethtool_stats,
@@ -999,6 +1019,7 @@ static const struct ethtool_ops ocelot_ethtool_ops = {
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 	.get_ts_info		= ocelot_port_get_ts_info,
+	.get_ts_stats		= ocelot_port_ts_stats,
 };
 
 static void ocelot_port_attr_stp_state_set(struct ocelot *ocelot, int port,
diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c
index e172638b0601..88b5422cc2a0 100644
--- a/drivers/net/ethernet/mscc/ocelot_ptp.c
+++ b/drivers/net/ethernet/mscc/ocelot_ptp.c
@@ -14,6 +14,8 @@
 #include <soc/mscc/ocelot.h>
 #include "ocelot.h"
 
+#define OCELOT_PTP_TX_TSTAMP_TIMEOUT		(5 * HZ)
+
 int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts)
 {
 	struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
@@ -209,11 +211,6 @@ int ocelot_ptp_enable(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_PEROUT:
-		/* Reject requests with unsupported flags */
-		if (rq->perout.flags & ~(PTP_PEROUT_DUTY_CYCLE |
-					 PTP_PEROUT_PHASE))
-			return -EOPNOTSUPP;
-
 		pin = ptp_find_pin(ocelot->ptp_clock, PTP_PF_PEROUT,
 				   rq->perout.index);
 		if (pin == 0)
@@ -495,58 +492,64 @@ static int ocelot_traps_to_ptp_rx_filter(unsigned int proto)
 	return HWTSTAMP_FILTER_NONE;
 }
 
-int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr)
+static int ocelot_ptp_tx_type_to_cmd(int tx_type, int *ptp_cmd)
+{
+	switch (tx_type) {
+	case HWTSTAMP_TX_ON:
+		*ptp_cmd = IFH_REW_OP_TWO_STEP_PTP;
+		break;
+	case HWTSTAMP_TX_ONESTEP_SYNC:
+		/* IFH_REW_OP_ONE_STEP_PTP updates the correctionField,
+		 * what we need to update is the originTimestamp.
+		 */
+		*ptp_cmd = IFH_REW_OP_ORIGIN_PTP;
+		break;
+	case HWTSTAMP_TX_OFF:
+		*ptp_cmd = 0;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+void ocelot_hwstamp_get(struct ocelot *ocelot, int port,
+			struct kernel_hwtstamp_config *cfg)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	struct hwtstamp_config cfg = {};
 
 	switch (ocelot_port->ptp_cmd) {
 	case IFH_REW_OP_TWO_STEP_PTP:
-		cfg.tx_type = HWTSTAMP_TX_ON;
+		cfg->tx_type = HWTSTAMP_TX_ON;
 		break;
 	case IFH_REW_OP_ORIGIN_PTP:
-		cfg.tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
+		cfg->tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
 		break;
 	default:
-		cfg.tx_type = HWTSTAMP_TX_OFF;
+		cfg->tx_type = HWTSTAMP_TX_OFF;
 		break;
 	}
 
-	cfg.rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto);
-
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	cfg->rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto);
 }
 EXPORT_SYMBOL(ocelot_hwstamp_get);
 
-int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
+int ocelot_hwstamp_set(struct ocelot *ocelot, int port,
+		       struct kernel_hwtstamp_config *cfg,
+		       struct netlink_ext_ack *extack)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	bool l2 = false, l4 = false;
-	struct hwtstamp_config cfg;
+	int ptp_cmd;
 	int err;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
 	/* Tx type sanity check */
-	switch (cfg.tx_type) {
-	case HWTSTAMP_TX_ON:
-		ocelot_port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP;
-		break;
-	case HWTSTAMP_TX_ONESTEP_SYNC:
-		/* IFH_REW_OP_ONE_STEP_PTP updates the correctional field, we
-		 * need to update the origin time.
-		 */
-		ocelot_port->ptp_cmd = IFH_REW_OP_ORIGIN_PTP;
-		break;
-	case HWTSTAMP_TX_OFF:
-		ocelot_port->ptp_cmd = 0;
-		break;
-	default:
-		return -ERANGE;
-	}
+	err = ocelot_ptp_tx_type_to_cmd(cfg->tx_type, &ptp_cmd);
+	if (err)
+		return err;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -573,9 +576,11 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
 	if (err)
 		return err;
 
-	cfg.rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto);
+	ocelot_port->ptp_cmd = ptp_cmd;
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	cfg->rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto);
+
+	return 0;
 }
 EXPORT_SYMBOL(ocelot_hwstamp_set);
 
@@ -603,34 +608,92 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 }
 EXPORT_SYMBOL(ocelot_get_ts_info);
 
-static int ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port,
-					struct sk_buff *clone)
+static struct sk_buff *ocelot_port_dequeue_ptp_tx_skb(struct ocelot *ocelot,
+						      int port, u8 ts_id,
+						      u32 seqid)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	unsigned long flags;
+	struct sk_buff *skb, *skb_tmp, *skb_match = NULL;
+	struct ptp_header *hdr;
 
-	spin_lock_irqsave(&ocelot->ts_id_lock, flags);
+	spin_lock(&ocelot->ts_id_lock);
 
-	if (ocelot_port->ptp_skbs_in_flight == OCELOT_MAX_PTP_ID ||
-	    ocelot->ptp_skbs_in_flight == OCELOT_PTP_FIFO_SIZE) {
-		spin_unlock_irqrestore(&ocelot->ts_id_lock, flags);
-		return -EBUSY;
+	skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) {
+		if (OCELOT_SKB_CB(skb)->ts_id != ts_id)
+			continue;
+
+		/* Check that the timestamp ID is for the expected PTP
+		 * sequenceId. We don't have to test ptp_parse_header() against
+		 * NULL, because we've pre-validated the packet's ptp_class.
+		 */
+		hdr = ptp_parse_header(skb, OCELOT_SKB_CB(skb)->ptp_class);
+		if (seqid != ntohs(hdr->sequence_id))
+			continue;
+
+		__skb_unlink(skb, &ocelot_port->tx_skbs);
+		ocelot->ptp_skbs_in_flight--;
+		skb_match = skb;
+		break;
 	}
 
-	skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS;
-	/* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */
-	OCELOT_SKB_CB(clone)->ts_id = ocelot_port->ts_id;
+	spin_unlock(&ocelot->ts_id_lock);
 
-	ocelot_port->ts_id++;
-	if (ocelot_port->ts_id == OCELOT_MAX_PTP_ID)
-		ocelot_port->ts_id = 0;
+	return skb_match;
+}
 
-	ocelot_port->ptp_skbs_in_flight++;
+static int ocelot_port_queue_ptp_tx_skb(struct ocelot *ocelot, int port,
+					struct sk_buff *clone)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	DECLARE_BITMAP(ts_id_in_flight, OCELOT_MAX_PTP_ID);
+	struct sk_buff *skb, *skb_tmp;
+	unsigned long n;
+
+	spin_lock(&ocelot->ts_id_lock);
+
+	/* To get a better chance of acquiring a timestamp ID, first flush the
+	 * stale packets still waiting in the TX timestamping queue. They are
+	 * probably lost.
+	 */
+	skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) {
+		if (time_before(OCELOT_SKB_CB(skb)->ptp_tx_time +
+				OCELOT_PTP_TX_TSTAMP_TIMEOUT, jiffies)) {
+			u64_stats_update_begin(&ocelot_port->ts_stats->syncp);
+			ocelot_port->ts_stats->lost++;
+			u64_stats_update_end(&ocelot_port->ts_stats->syncp);
+
+			dev_dbg_ratelimited(ocelot->dev,
+					    "port %d invalidating stale timestamp ID %u which seems lost\n",
+					    port, OCELOT_SKB_CB(skb)->ts_id);
+
+			__skb_unlink(skb, &ocelot_port->tx_skbs);
+			kfree_skb(skb);
+			ocelot->ptp_skbs_in_flight--;
+		} else {
+			__set_bit(OCELOT_SKB_CB(skb)->ts_id, ts_id_in_flight);
+		}
+	}
+
+	if (ocelot->ptp_skbs_in_flight == OCELOT_PTP_FIFO_SIZE) {
+		spin_unlock(&ocelot->ts_id_lock);
+		return -EBUSY;
+	}
+
+	n = find_first_zero_bit(ts_id_in_flight, OCELOT_MAX_PTP_ID);
+	if (n == OCELOT_MAX_PTP_ID) {
+		spin_unlock(&ocelot->ts_id_lock);
+		return -EBUSY;
+	}
+
+	/* Found an available timestamp ID, use it */
+	OCELOT_SKB_CB(clone)->ts_id = n;
+	OCELOT_SKB_CB(clone)->ptp_tx_time = jiffies;
 	ocelot->ptp_skbs_in_flight++;
+	__skb_queue_tail(&ocelot_port->tx_skbs, clone);
 
-	skb_queue_tail(&ocelot_port->tx_skbs, clone);
+	spin_unlock(&ocelot->ts_id_lock);
 
-	spin_unlock_irqrestore(&ocelot->ts_id_lock, flags);
+	dev_dbg_ratelimited(ocelot->dev, "port %d timestamp id %lu\n", port, n);
 
 	return 0;
 }
@@ -668,13 +731,20 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port,
 		return 0;
 
 	ptp_class = ptp_classify_raw(skb);
-	if (ptp_class == PTP_CLASS_NONE)
-		return -EINVAL;
+	if (ptp_class == PTP_CLASS_NONE) {
+		err = -EINVAL;
+		goto error;
+	}
 
 	/* Store ptp_cmd in OCELOT_SKB_CB(skb)->ptp_cmd */
 	if (ptp_cmd == IFH_REW_OP_ORIGIN_PTP) {
 		if (ocelot_ptp_is_onestep_sync(skb, ptp_class)) {
 			OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd;
+
+			u64_stats_update_begin(&ocelot_port->ts_stats->syncp);
+			ocelot_port->ts_stats->onestep_pkts_unconfirmed++;
+			u64_stats_update_end(&ocelot_port->ts_stats->syncp);
+
 			return 0;
 		}
 
@@ -684,18 +754,30 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port,
 
 	if (ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
 		*clone = skb_clone_sk(skb);
-		if (!(*clone))
-			return -ENOMEM;
+		if (!(*clone)) {
+			err = -ENOMEM;
+			goto error;
+		}
 
-		err = ocelot_port_add_txtstamp_skb(ocelot, port, *clone);
-		if (err)
-			return err;
+		/* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */
+		err = ocelot_port_queue_ptp_tx_skb(ocelot, port, *clone);
+		if (err) {
+			kfree_skb(*clone);
+			goto error;
+		}
 
+		skb_shinfo(*clone)->tx_flags |= SKBTX_IN_PROGRESS;
 		OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd;
 		OCELOT_SKB_CB(*clone)->ptp_class = ptp_class;
 	}
 
 	return 0;
+
+error:
+	u64_stats_update_begin(&ocelot_port->ts_stats->syncp);
+	ocelot_port->ts_stats->err++;
+	u64_stats_update_end(&ocelot_port->ts_stats->syncp);
+	return err;
 }
 EXPORT_SYMBOL(ocelot_port_txtstamp_request);
 
@@ -726,28 +808,16 @@ static void ocelot_get_hwtimestamp(struct ocelot *ocelot,
 	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
 }
 
-static bool ocelot_validate_ptp_skb(struct sk_buff *clone, u16 seqid)
-{
-	struct ptp_header *hdr;
-
-	hdr = ptp_parse_header(clone, OCELOT_SKB_CB(clone)->ptp_class);
-	if (WARN_ON(!hdr))
-		return false;
-
-	return seqid == ntohs(hdr->sequence_id);
-}
-
 void ocelot_get_txtstamp(struct ocelot *ocelot)
 {
 	int budget = OCELOT_PTP_QUEUE_SZ;
 
 	while (budget--) {
-		struct sk_buff *skb, *skb_tmp, *skb_match = NULL;
 		struct skb_shared_hwtstamps shhwtstamps;
+		struct ocelot_port *ocelot_port;
 		u32 val, id, seqid, txport;
-		struct ocelot_port *port;
+		struct sk_buff *skb_match;
 		struct timespec64 ts;
-		unsigned long flags;
 
 		val = ocelot_read(ocelot, SYS_PTP_STATUS);
 
@@ -761,38 +831,26 @@ void ocelot_get_txtstamp(struct ocelot *ocelot)
 		id = SYS_PTP_STATUS_PTP_MESS_ID_X(val);
 		txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val);
 		seqid = SYS_PTP_STATUS_PTP_MESS_SEQ_ID(val);
-
-		port = ocelot->ports[txport];
-
-		spin_lock(&ocelot->ts_id_lock);
-		port->ptp_skbs_in_flight--;
-		ocelot->ptp_skbs_in_flight--;
-		spin_unlock(&ocelot->ts_id_lock);
+		ocelot_port = ocelot->ports[txport];
 
 		/* Retrieve its associated skb */
-try_again:
-		spin_lock_irqsave(&port->tx_skbs.lock, flags);
-
-		skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) {
-			if (OCELOT_SKB_CB(skb)->ts_id != id)
-				continue;
-			__skb_unlink(skb, &port->tx_skbs);
-			skb_match = skb;
-			break;
+		skb_match = ocelot_port_dequeue_ptp_tx_skb(ocelot, txport, id,
+							   seqid);
+		if (!skb_match) {
+			u64_stats_update_begin(&ocelot_port->ts_stats->syncp);
+			ocelot_port->ts_stats->err++;
+			u64_stats_update_end(&ocelot_port->ts_stats->syncp);
+
+			dev_dbg_ratelimited(ocelot->dev,
+					    "port %d received TX timestamp (seqid %d, ts id %u) for packet previously declared stale\n",
+					    txport, seqid, id);
+
+			goto next_ts;
 		}
 
-		spin_unlock_irqrestore(&port->tx_skbs.lock, flags);
-
-		if (WARN_ON(!skb_match))
-			continue;
-
-		if (!ocelot_validate_ptp_skb(skb_match, seqid)) {
-			dev_err_ratelimited(ocelot->dev,
-					    "port %d received stale TX timestamp for seqid %d, discarding\n",
-					    txport, seqid);
-			dev_kfree_skb_any(skb);
-			goto try_again;
-		}
+		u64_stats_update_begin(&ocelot_port->ts_stats->syncp);
+		ocelot_port->ts_stats->pkts++;
+		u64_stats_update_end(&ocelot_port->ts_stats->syncp);
 
 		/* Get the h/w timestamp */
 		ocelot_get_hwtimestamp(ocelot, &ts);
@@ -802,7 +860,7 @@ try_again:
 		shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec);
 		skb_complete_tx_timestamp(skb_match, &shhwtstamps);
 
-		/* Next ts */
+next_ts:
 		ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT);
 	}
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c
index c018783757fb..545710dadcf5 100644
--- a/drivers/net/ethernet/mscc/ocelot_stats.c
+++ b/drivers/net/ethernet/mscc/ocelot_stats.c
@@ -821,6 +821,26 @@ void ocelot_port_get_eth_phy_stats(struct ocelot *ocelot, int port,
 }
 EXPORT_SYMBOL_GPL(ocelot_port_get_eth_phy_stats);
 
+void ocelot_port_get_ts_stats(struct ocelot *ocelot, int port,
+			      struct ethtool_ts_stats *ts_stats)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct ocelot_ts_stats *stats = ocelot_port->ts_stats;
+	unsigned int start;
+
+	if (!ocelot->ptp)
+		return;
+
+	do {
+		start = u64_stats_fetch_begin(&stats->syncp);
+		ts_stats->pkts = stats->pkts;
+		ts_stats->onestep_pkts_unconfirmed = stats->onestep_pkts_unconfirmed;
+		ts_stats->lost = stats->lost;
+		ts_stats->err = stats->err;
+	} while (u64_stats_fetch_retry(&stats->syncp, start));
+}
+EXPORT_SYMBOL_GPL(ocelot_port_get_ts_stats);
+
 void ocelot_port_get_stats64(struct ocelot *ocelot, int port,
 			     struct rtnl_link_stats64 *stats)
 {
@@ -960,6 +980,23 @@ int ocelot_stats_init(struct ocelot *ocelot)
 	if (!ocelot->stats)
 		return -ENOMEM;
 
+	if (ocelot->ptp) {
+		for (int port = 0; port < ocelot->num_phys_ports; port++) {
+			struct ocelot_port *ocelot_port = ocelot->ports[port];
+
+			if (!ocelot_port)
+				continue;
+
+			ocelot_port->ts_stats = devm_kzalloc(ocelot->dev,
+							     sizeof(*ocelot_port->ts_stats),
+							     GFP_KERNEL);
+			if (!ocelot_port->ts_stats)
+				return -ENOMEM;
+
+			u64_stats_init(&ocelot_port->ts_stats->syncp);
+		}
+	}
+
 	snprintf(queue_name, sizeof(queue_name), "%s-stats",
 		 dev_name(ocelot->dev));
 	ocelot->stats_queue = create_singlethread_workqueue(queue_name);
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 055b55651a49..498eec8ae61d 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -108,6 +108,8 @@ static struct ptp_clock_info ocelot_ptp_clock_info = {
 	.n_ext_ts	= 0,
 	.n_per_out	= OCELOT_PTP_PINS_NUM,
 	.n_pins		= OCELOT_PTP_PINS_NUM,
+	.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE |
+				  PTP_PEROUT_PHASE,
 	.pps		= 0,
 	.gettime64	= ocelot_ptp_gettime64,
 	.settime64	= ocelot_ptp_settime64,
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index b7d9657a7af3..e611ff7fa3fa 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -2482,7 +2482,7 @@ static int myri10ge_close(struct net_device *dev)
 	if (mgp->ss[0].tx.req_bytes == NULL)
 		return 0;
 
-	del_timer_sync(&mgp->watchdog_timer);
+	timer_delete_sync(&mgp->watchdog_timer);
 	mgp->running = MYRI10GE_ETH_STOPPING;
 	for (i = 0; i < mgp->num_slices; i++)
 		napi_disable(&mgp->ss[i].napi);
@@ -3478,7 +3478,7 @@ static void myri10ge_watchdog_timer(struct timer_list *t)
 	u32 rx_pause_cnt;
 	u16 cmd;
 
-	mgp = from_timer(mgp, t, watchdog_timer);
+	mgp = timer_container_of(mgp, t, watchdog_timer);
 
 	rx_pause_cnt = ntohl(mgp->ss[0].fw_stats->dropped_pause);
 	busy_slice_cnt = 0;
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index ad0c14849115..b253734dbc80 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -846,7 +846,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENOMEM;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
-	i = pci_request_regions(pdev, DRV_NAME);
+	i = pcim_request_all_regions(pdev, DRV_NAME);
 	if (i)
 		goto err_pci_request_regions;
 
@@ -1786,7 +1786,7 @@ static void init_registers(struct net_device *dev)
  */
 static void netdev_timer(struct timer_list *t)
 {
-	struct netdev_private *np = from_timer(np, t, timer);
+	struct netdev_private *np = timer_container_of(np, t, timer);
 	struct net_device *dev = np->dev;
 	void __iomem * ioaddr = ns_ioaddr(dev);
 	int next_tick = NATSEMI_TIMER_FREQ;
@@ -3179,7 +3179,7 @@ static int netdev_close(struct net_device *dev)
 	 * the final WOL settings?
 	 */
 
-	del_timer_sync(&np->timer);
+	timer_delete_sync(&np->timer);
 	disable_irq(irq);
 	spin_lock_irq(&np->lock);
 	natsemi_irq_disable(dev);
@@ -3278,7 +3278,7 @@ static int __maybe_unused natsemi_suspend(struct device *dev_d)
 	if (netif_running (dev)) {
 		const int irq = np->pci_dev->irq;
 
-		del_timer_sync(&np->timer);
+		timer_delete_sync(&np->timer);
 
 		disable_irq(irq);
 		spin_lock_irq(&np->lock);
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index bea969dfa536..56d5464222d9 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -1527,7 +1527,7 @@ static int ns83820_stop(struct net_device *ndev)
 	struct ns83820 *dev = PRIV(ndev);
 
 	/* FIXME: protect against interrupt handler? */
-	del_timer_sync(&dev->tx_watchdog);
+	timer_delete_sync(&dev->tx_watchdog);
 
 	ns83820_disable_interrupts(dev);
 
@@ -1587,7 +1587,7 @@ static void ns83820_tx_timeout(struct net_device *ndev, unsigned int txqueue)
 
 static void ns83820_tx_watch(struct timer_list *t)
 {
-	struct ns83820 *dev = from_timer(dev, t, tx_watchdog);
+	struct ns83820 *dev = timer_container_of(dev, t, tx_watchdog);
 	struct net_device *ndev = dev->ndev;
 
 #if defined(DEBUG)
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index f8016dc25e0a..27443e346f9f 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -4195,7 +4195,7 @@ pci_map_failed:
 static void
 s2io_alarm_handle(struct timer_list *t)
 {
-	struct s2io_nic *sp = from_timer(sp, t, alarm_timer);
+	struct s2io_nic *sp = timer_container_of(sp, t, alarm_timer);
 	struct net_device *dev = sp->dev;
 
 	s2io_handle_errors(dev);
@@ -7019,7 +7019,7 @@ static void do_s2io_card_down(struct s2io_nic *sp, int do_io)
 	if (!is_s2io_card_up(sp))
 		return;
 
-	del_timer_sync(&sp->alarm_timer);
+	timer_delete_sync(&sp->alarm_timer);
 	/* If s2io_set_link task is executing, wait till it completes. */
 	while (test_and_set_bit(__S2IO_STATE_LINK_TASK, &(sp->state)))
 		msleep(50);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index 2ec62c8d86e1..59486fe2ad18 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -20,6 +20,8 @@ nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size)
 	struct sk_buff *skb;
 
 	skb = nfp_app_ctrl_msg_alloc(bpf->app, size, GFP_KERNEL);
+	if (!skb)
+		return NULL;
 	skb_put(skb, size);
 
 	return skb;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 9d97cd281f18..c03558adda91 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -458,7 +458,8 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
 	map_id_full = be64_to_cpu(cbe->map_ptr);
 	map_id = map_id_full;
 
-	if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
+	if (size_add(pkt_size, data_size) > INT_MAX ||
+	    len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
 		return -EINVAL;
 	if (cbe->hdr.ver != NFP_CCM_ABI_VERSION)
 		return -EINVAL;
diff --git a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c
index 515069d5637b..9e7c285eaa6b 100644
--- a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c
+++ b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c
@@ -266,17 +266,17 @@ static void set_sha2_512hmac(struct nfp_ipsec_cfg_add_sa *cfg, int *trunc_len)
 	}
 }
 
-static int nfp_net_xfrm_add_state(struct xfrm_state *x,
+static int nfp_net_xfrm_add_state(struct net_device *dev,
+				  struct xfrm_state *x,
 				  struct netlink_ext_ack *extack)
 {
-	struct net_device *netdev = x->xso.real_dev;
 	struct nfp_ipsec_cfg_mssg msg = {};
 	int i, key_len, trunc_len, err = 0;
 	struct nfp_ipsec_cfg_add_sa *cfg;
 	struct nfp_net *nn;
 	unsigned int saidx;
 
-	nn = netdev_priv(netdev);
+	nn = netdev_priv(dev);
 	cfg = &msg.cfg_add_sa;
 
 	/* General */
@@ -546,17 +546,16 @@ static int nfp_net_xfrm_add_state(struct xfrm_state *x,
 	return 0;
 }
 
-static void nfp_net_xfrm_del_state(struct xfrm_state *x)
+static void nfp_net_xfrm_del_state(struct net_device *dev, struct xfrm_state *x)
 {
 	struct nfp_ipsec_cfg_mssg msg = {
 		.cmd = NFP_IPSEC_CFG_MSSG_INV_SA,
 		.sa_idx = x->xso.offload_handle - 1,
 	};
-	struct net_device *netdev = x->xso.real_dev;
 	struct nfp_net *nn;
 	int err;
 
-	nn = netdev_priv(netdev);
+	nn = netdev_priv(dev);
 	err = nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_IPSEC, &msg,
 					   sizeof(msg), nfp_net_ipsec_cfg);
 	if (err)
@@ -565,20 +564,9 @@ static void nfp_net_xfrm_del_state(struct xfrm_state *x)
 	xa_erase(&nn->xa_ipsec, x->xso.offload_handle - 1);
 }
 
-static bool nfp_net_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
-{
-	if (x->props.family == AF_INET)
-		/* Offload with IPv4 options is not supported yet */
-		return ip_hdr(skb)->ihl == 5;
-
-	/* Offload with IPv6 extension headers is not support yet */
-	return !(ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr));
-}
-
 static const struct xfrmdev_ops nfp_net_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_add = nfp_net_xfrm_add_state,
 	.xdo_dev_state_delete = nfp_net_xfrm_del_state,
-	.xdo_dev_offload_ok = nfp_net_ipsec_offload_ok,
 };
 
 void nfp_net_ipsec_init(struct nfp_net *nn)
diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
index f1c6c47564b1..08086eb76996 100644
--- a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
@@ -779,7 +779,7 @@ nfp_nfd3_parse_meta(struct net_device *netdev, struct nfp_meta_parsed *meta,
 		case NFP_NET_META_CSUM:
 			meta->csum_type = CHECKSUM_COMPLETE;
 			meta->csum =
-				(__force __wsum)__get_unaligned_cpu32(data);
+				(__force __wsum)get_unaligned((u32 *)data);
 			data += 4;
 			break;
 		case NFP_NET_META_RESYNC_INFO:
diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
index ebeb6ab4465c..ab3cd06ed63e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
@@ -779,7 +779,7 @@ nfp_nfdk_parse_meta(struct net_device *netdev, struct nfp_meta_parsed *meta,
 		case NFP_NET_META_CSUM:
 			meta->csum_type = CHECKSUM_COMPLETE;
 			meta->csum =
-				(__force __wsum)__get_unaligned_cpu32(data);
+				(__force __wsum)get_unaligned((u32 *)data);
 			data += 4;
 			break;
 		case NFP_NET_META_RESYNC_INFO:
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_hwmon.c b/drivers/net/ethernet/netronome/nfp/nfp_hwmon.c
index 0d6c59d6d4ae..ea6a288c0d5e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_hwmon.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_hwmon.c
@@ -83,42 +83,12 @@ nfp_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
 	return 0;
 }
 
-static u32 nfp_chip_config[] = {
-	HWMON_C_REGISTER_TZ,
-	0
-};
-
-static const struct hwmon_channel_info nfp_chip = {
-	.type = hwmon_chip,
-	.config = nfp_chip_config,
-};
-
-static u32 nfp_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT,
-	0
-};
-
-static const struct hwmon_channel_info nfp_temp = {
-	.type = hwmon_temp,
-	.config = nfp_temp_config,
-};
-
-static u32 nfp_power_config[] = {
-	HWMON_P_INPUT | HWMON_P_MAX,
-	HWMON_P_INPUT,
-	HWMON_P_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info nfp_power = {
-	.type = hwmon_power,
-	.config = nfp_power_config,
-};
-
 static const struct hwmon_channel_info * const nfp_hwmon_info[] = {
-	&nfp_chip,
-	&nfp_temp,
-	&nfp_power,
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT),
+	HWMON_CHANNEL_INFO(power, HWMON_P_INPUT | HWMON_P_MAX,
+			   HWMON_P_INPUT,
+			   HWMON_P_INPUT),
 	NULL
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 98e098c09c03..932f59d70f41 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -159,7 +159,7 @@ static int nfp_net_reconfig_wait(struct nfp_net *nn, unsigned long deadline)
 
 static void nfp_net_reconfig_timer(struct timer_list *t)
 {
-	struct nfp_net *nn = from_timer(nn, t, reconfig_timer);
+	struct nfp_net *nn = timer_container_of(nn, t, reconfig_timer);
 
 	spin_lock_bh(&nn->reconfig_lock);
 
@@ -227,7 +227,7 @@ static void nfp_net_reconfig_sync_enter(struct nfp_net *nn)
 	spin_unlock_bh(&nn->reconfig_lock);
 
 	if (cancelled_timer) {
-		del_timer_sync(&nn->reconfig_timer);
+		timer_delete_sync(&nn->reconfig_timer);
 		nfp_net_reconfig_wait(nn, nn->reconfig_timer.expires);
 	}
 
@@ -2538,7 +2538,7 @@ nfp_net_alloc(struct pci_dev *pdev, const struct nfp_dev_info *dev_info,
 				  nn->dp.num_r_vecs, num_online_cpus());
 	nn->max_r_vecs = nn->dp.num_r_vecs;
 
-	nn->dp.xsk_pools = kcalloc(nn->max_r_vecs, sizeof(nn->dp.xsk_pools),
+	nn->dp.xsk_pools = kcalloc(nn->max_r_vecs, sizeof(*nn->dp.xsk_pools),
 				   GFP_KERNEL);
 	if (!nn->dp.xsk_pools) {
 		err = -ENOMEM;
@@ -2779,7 +2779,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 		break;
 	}
 
-	netdev->watchdog_timeo = msecs_to_jiffies(5 * 1000);
+	netdev->watchdog_timeo = secs_to_jiffies(5);
 
 	/* MTU range: 68 - hw-specific max */
 	netdev->min_mtu = ETH_MIN_MTU;
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 720f577929db..19aa1f1538aa 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -1120,20 +1120,6 @@ static void nv_disable_hw_interrupts(struct net_device *dev, u32 mask)
 	}
 }
 
-static void nv_napi_enable(struct net_device *dev)
-{
-	struct fe_priv *np = get_nvpriv(dev);
-
-	napi_enable(&np->napi);
-}
-
-static void nv_napi_disable(struct net_device *dev)
-{
-	struct fe_priv *np = get_nvpriv(dev);
-
-	napi_disable(&np->napi);
-}
-
 #define MII_READ	(-1)
 /* mii_rw: read/write a register on the PHY.
  *
@@ -1905,7 +1891,7 @@ packet_dropped:
 /* If rx bufs are exhausted called after 50ms to attempt to refresh */
 static void nv_do_rx_refill(struct timer_list *t)
 {
-	struct fe_priv *np = from_timer(np, t, oom_kick);
+	struct fe_priv *np = timer_container_of(np, t, oom_kick);
 
 	/* Just reschedule NAPI rx processing */
 	napi_schedule(&np->napi);
@@ -3114,7 +3100,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu)
 		 * Changing the MTU is a rare event, it shouldn't matter.
 		 */
 		nv_disable_irq(dev);
-		nv_napi_disable(dev);
+		napi_disable(&np->napi);
 		netif_tx_lock_bh(dev);
 		netif_addr_lock(dev);
 		spin_lock(&np->lock);
@@ -3143,7 +3129,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu)
 		spin_unlock(&np->lock);
 		netif_addr_unlock(dev);
 		netif_tx_unlock_bh(dev);
-		nv_napi_enable(dev);
+		napi_enable(&np->napi);
 		nv_enable_irq(dev);
 	}
 	return 0;
@@ -4154,7 +4140,7 @@ static void nv_free_irq(struct net_device *dev)
 
 static void nv_do_nic_poll(struct timer_list *t)
 {
-	struct fe_priv *np = from_timer(np, t, nic_poll);
+	struct fe_priv *np = timer_container_of(np, t, nic_poll);
 	struct net_device *dev = np->dev;
 	u8 __iomem *base = get_hwbase(dev);
 	u32 mask = 0;
@@ -4273,7 +4259,7 @@ static void nv_do_stats_poll(struct timer_list *t)
 	__acquires(&netdev_priv(dev)->hwstats_lock)
 	__releases(&netdev_priv(dev)->hwstats_lock)
 {
-	struct fe_priv *np = from_timer(np, t, stats_poll);
+	struct fe_priv *np = timer_container_of(np, t, stats_poll);
 	struct net_device *dev = np->dev;
 
 	/* If lock is currently taken, the stats are being refreshed
@@ -4731,7 +4717,7 @@ static int nv_set_ringparam(struct net_device *dev,
 
 	if (netif_running(dev)) {
 		nv_disable_irq(dev);
-		nv_napi_disable(dev);
+		napi_disable(&np->napi);
 		netif_tx_lock_bh(dev);
 		netif_addr_lock(dev);
 		spin_lock(&np->lock);
@@ -4784,7 +4770,7 @@ static int nv_set_ringparam(struct net_device *dev,
 		spin_unlock(&np->lock);
 		netif_addr_unlock(dev);
 		netif_tx_unlock_bh(dev);
-		nv_napi_enable(dev);
+		napi_enable(&np->napi);
 		nv_enable_irq(dev);
 	}
 	return 0;
@@ -5277,7 +5263,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64
 	if (test->flags & ETH_TEST_FL_OFFLINE) {
 		if (netif_running(dev)) {
 			netif_stop_queue(dev);
-			nv_napi_disable(dev);
+			napi_disable(&np->napi);
 			netif_tx_lock_bh(dev);
 			netif_addr_lock(dev);
 			spin_lock_irq(&np->lock);
@@ -5334,7 +5320,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64
 			/* restart rx engine */
 			nv_start_rxtx(dev);
 			netif_start_queue(dev);
-			nv_napi_enable(dev);
+			napi_enable(&np->napi);
 			nv_enable_hw_interrupts(dev, np->irqmask);
 		}
 	}
@@ -5576,6 +5562,7 @@ static int nv_open(struct net_device *dev)
 	/* ask for interrupts */
 	nv_enable_hw_interrupts(dev, np->irqmask);
 
+	netdev_lock(dev);
 	spin_lock_irq(&np->lock);
 	writel(NVREG_MCASTADDRA_FORCE, base + NvRegMulticastAddrA);
 	writel(0, base + NvRegMulticastAddrB);
@@ -5594,7 +5581,7 @@ static int nv_open(struct net_device *dev)
 	ret = nv_update_linkspeed(dev);
 	nv_start_rxtx(dev);
 	netif_start_queue(dev);
-	nv_napi_enable(dev);
+	napi_enable_locked(&np->napi);
 
 	if (ret) {
 		netif_carrier_on(dev);
@@ -5611,6 +5598,7 @@ static int nv_open(struct net_device *dev)
 			round_jiffies(jiffies + STATS_INTERVAL));
 
 	spin_unlock_irq(&np->lock);
+	netdev_unlock(dev);
 
 	/* If the loopback feature was set while the device was down, make sure
 	 * that it's set correctly now.
@@ -5632,12 +5620,12 @@ static int nv_close(struct net_device *dev)
 	spin_lock_irq(&np->lock);
 	np->in_shutdown = 1;
 	spin_unlock_irq(&np->lock);
-	nv_napi_disable(dev);
+	napi_disable(&np->napi);
 	synchronize_irq(np->pci_dev->irq);
 
-	del_timer_sync(&np->oom_kick);
-	del_timer_sync(&np->nic_poll);
-	del_timer_sync(&np->stats_poll);
+	timer_delete_sync(&np->oom_kick);
+	timer_delete_sync(&np->nic_poll);
+	timer_delete_sync(&np->stats_poll);
 
 	netif_stop_queue(dev);
 	spin_lock_irq(&np->lock);
diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index f9c0dcd965c2..db200e4ec284 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -113,6 +113,7 @@ struct oa_tc6 {
 	struct mii_bus *mdiobus;
 	struct spi_device *spi;
 	struct mutex spi_ctrl_lock; /* Protects spi control transfer */
+	spinlock_t tx_skb_lock; /* Protects tx skb handling */
 	void *spi_ctrl_tx_buf;
 	void *spi_ctrl_rx_buf;
 	void *spi_data_tx_buf;
@@ -1004,8 +1005,10 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6)
 	for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits;
 	     used_tx_credits++) {
 		if (!tc6->ongoing_tx_skb) {
+			spin_lock_bh(&tc6->tx_skb_lock);
 			tc6->ongoing_tx_skb = tc6->waiting_tx_skb;
 			tc6->waiting_tx_skb = NULL;
+			spin_unlock_bh(&tc6->tx_skb_lock);
 		}
 		if (!tc6->ongoing_tx_skb)
 			break;
@@ -1111,8 +1114,9 @@ static int oa_tc6_spi_thread_handler(void *data)
 		/* This kthread will be waken up if there is a tx skb or mac-phy
 		 * interrupt to perform spi transfer with tx chunks.
 		 */
-		wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb ||
-					 tc6->int_flag ||
+		wait_event_interruptible(tc6->spi_wq, tc6->int_flag ||
+					 (tc6->waiting_tx_skb &&
+					 tc6->tx_credits) ||
 					 kthread_should_stop());
 
 		if (kthread_should_stop())
@@ -1209,7 +1213,9 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb)
 		return NETDEV_TX_OK;
 	}
 
+	spin_lock_bh(&tc6->tx_skb_lock);
 	tc6->waiting_tx_skb = skb;
+	spin_unlock_bh(&tc6->tx_skb_lock);
 
 	/* Wake spi kthread to perform spi transfer */
 	wake_up_interruptible(&tc6->spi_wq);
@@ -1239,6 +1245,7 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 	tc6->netdev = netdev;
 	SET_NETDEV_DEV(netdev, &spi->dev);
 	mutex_init(&tc6->spi_ctrl_lock);
+	spin_lock_init(&tc6->tx_skb_lock);
 
 	/* Set the SPI controller to pump at realtime priority */
 	tc6->spi->rt = true;
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 4ac29cd59f2b..e5a6f59af0b6 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -1014,8 +1014,8 @@ static void pch_gbe_set_mode(struct pch_gbe_adapter *adapter, u16 speed,
  */
 static void pch_gbe_watchdog(struct timer_list *t)
 {
-	struct pch_gbe_adapter *adapter = from_timer(adapter, t,
-						     watchdog_timer);
+	struct pch_gbe_adapter *adapter = timer_container_of(adapter, t,
+							     watchdog_timer);
 	struct net_device *netdev = adapter->netdev;
 	struct pch_gbe_hw *hw = &adapter->hw;
 
@@ -1916,7 +1916,7 @@ void pch_gbe_down(struct pch_gbe_adapter *adapter)
 	pch_gbe_irq_disable(adapter);
 	pch_gbe_free_irq(adapter);
 
-	del_timer_sync(&adapter->watchdog_timer);
+	timer_delete_sync(&adapter->watchdog_timer);
 
 	netdev->tx_queue_len = adapter->tx_queue_len;
 	netif_carrier_off(netdev);
diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c
index a36d422b5173..b0de7e9f12a5 100644
--- a/drivers/net/ethernet/packetengines/hamachi.c
+++ b/drivers/net/ethernet/packetengines/hamachi.c
@@ -1025,7 +1025,7 @@ static inline int hamachi_tx(struct net_device *dev)
 
 static void hamachi_timer(struct timer_list *t)
 {
-	struct hamachi_private *hmp = from_timer(hmp, t, timer);
+	struct hamachi_private *hmp = timer_container_of(hmp, t, timer);
 	struct net_device *dev = hmp->mii_if.dev;
 	void __iomem *ioaddr = hmp->base;
 	int next_tick = 10*HZ;
@@ -1712,7 +1712,7 @@ static int hamachi_close(struct net_device *dev)
 
 	free_irq(hmp->pci_dev->irq, dev);
 
-	del_timer_sync(&hmp->timer);
+	timer_delete_sync(&hmp->timer);
 
 	/* Free all the skbuffs in the Rx queue. */
 	for (i = 0; i < RX_RING_SIZE; i++) {
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index c0515dc63246..1e25ac13a7d8 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -652,7 +652,7 @@ err_free_irq:
 
 static void yellowfin_timer(struct timer_list *t)
 {
-	struct yellowfin_private *yp = from_timer(yp, t, timer);
+	struct yellowfin_private *yp = timer_container_of(yp, t, timer);
 	struct net_device *dev = pci_get_drvdata(yp->pci_dev);
 	void __iomem *ioaddr = yp->base;
 	int next_tick = 60*HZ;
@@ -1222,7 +1222,7 @@ static int yellowfin_close(struct net_device *dev)
 	iowrite32(0x80000000, ioaddr + RxCtrl);
 	iowrite32(0x80000000, ioaddr + TxCtrl);
 
-	del_timer(&yp->timer);
+	timer_delete(&yp->timer);
 
 #if defined(__i386__)
 	if (yellowfin_debug > 2) {
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c
index cb4e12df7719..fe58024b5901 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac.c
+++ b/drivers/net/ethernet/pasemi/pasemi_mac.c
@@ -934,7 +934,8 @@ static irqreturn_t pasemi_mac_rx_intr(int irq, void *data)
 
 static void pasemi_mac_tx_timer(struct timer_list *t)
 {
-	struct pasemi_mac_txring *txring = from_timer(txring, t, clean_timer);
+	struct pasemi_mac_txring *txring = timer_container_of(txring, t,
+							      clean_timer);
 	struct pasemi_mac *mac = txring->mac;
 
 	pasemi_mac_clean_tx(txring);
@@ -1288,7 +1289,7 @@ static int pasemi_mac_close(struct net_device *dev)
 		phy_disconnect(dev->phydev);
 	}
 
-	del_timer_sync(&mac->tx->clean_timer);
+	timer_delete_sync(&mac->tx->clean_timer);
 
 	netif_stop_queue(dev);
 	napi_disable(&mac->napi);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h
index 1c61390677f7..04f00ea94230 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic.h
@@ -18,8 +18,6 @@ struct ionic_lif;
 #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF	0x1002
 #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF	0x1003
 
-#define IONIC_ASIC_TYPE_ELBA	2
-
 #define DEVCMD_TIMEOUT			5
 #define IONIC_ADMINQ_TIME_SLICE		msecs_to_jiffies(100)
 
@@ -59,7 +57,6 @@ struct ionic {
 	DECLARE_BITMAP(intrs, IONIC_INTR_CTRL_REGS_MAX);
 	cpumask_var_t *affinity_masks;
 	struct delayed_work doorbell_check_dwork;
-	struct work_struct nb_work;
 	struct notifier_block nb;
 	struct rw_semaphore vf_op_lock;	/* lock for VF operations */
 	struct ionic_vf *vfs;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index f5dc876eb500..4c377bdc62c8 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -441,7 +441,7 @@ static void ionic_reset_prepare(struct pci_dev *pdev)
 
 	set_bit(IONIC_LIF_F_FW_RESET, lif->state);
 
-	del_timer_sync(&ionic->watchdog_timer);
+	timer_delete_sync(&ionic->watchdog_timer);
 	cancel_work_sync(&lif->deferred.work);
 
 	mutex_lock(&lif->queue_lock);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 9e42d599840d..18b9c8a810ae 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -13,7 +13,7 @@
 
 static void ionic_watchdog_cb(struct timer_list *t)
 {
-	struct ionic *ionic = from_timer(ionic, t, watchdog_timer);
+	struct ionic *ionic = timer_container_of(ionic, t, watchdog_timer);
 	struct ionic_lif *lif = ionic->lif;
 	struct ionic_deferred_work *work;
 	int hb;
@@ -277,7 +277,10 @@ void ionic_dev_teardown(struct ionic *ionic)
 	idev->phy_cmb_pages = 0;
 	idev->cmb_npages = 0;
 
-	destroy_workqueue(ionic->wq);
+	if (ionic->wq) {
+		destroy_workqueue(ionic->wq);
+		ionic->wq = NULL;
+	}
 	mutex_destroy(&idev->cmb_inuse_lock);
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index dda22fa4448c..92f30ff2d631 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -158,6 +158,20 @@ static int ionic_get_link_ksettings(struct net_device *netdev,
 						     25000baseCR_Full);
 		copper_seen++;
 		break;
+	case IONIC_XCVR_PID_QSFP_50G_CR2_FC:
+	case IONIC_XCVR_PID_QSFP_50G_CR2:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseCR2_Full);
+		copper_seen++;
+		break;
+	case IONIC_XCVR_PID_QSFP_200G_CR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, 200000baseCR4_Full);
+		copper_seen++;
+		break;
+	case IONIC_XCVR_PID_QSFP_400G_CR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, 400000baseCR4_Full);
+		copper_seen++;
+		break;
 	case IONIC_XCVR_PID_SFP_10GBASE_AOC:
 	case IONIC_XCVR_PID_SFP_10GBASE_CU:
 		ethtool_link_ksettings_add_link_mode(ks, supported,
@@ -196,6 +210,31 @@ static int ionic_get_link_ksettings(struct net_device *netdev,
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseSR_Full);
 		break;
+	case IONIC_XCVR_PID_QSFP_200G_AOC:
+	case IONIC_XCVR_PID_QSFP_200G_SR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     200000baseSR4_Full);
+		break;
+	case IONIC_XCVR_PID_QSFP_200G_FR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     200000baseLR4_ER4_FR4_Full);
+		break;
+	case IONIC_XCVR_PID_QSFP_200G_DR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     200000baseDR4_Full);
+		break;
+	case IONIC_XCVR_PID_QSFP_400G_FR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     400000baseLR4_ER4_FR4_Full);
+		break;
+	case IONIC_XCVR_PID_QSFP_400G_DR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     400000baseDR4_Full);
+		break;
+	case IONIC_XCVR_PID_QSFP_400G_SR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     400000baseSR4_Full);
+		break;
 	case IONIC_XCVR_PID_SFP_10GBASE_SR:
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseSR_Full);
@@ -909,63 +948,20 @@ static int ionic_get_tunable(struct net_device *netdev,
 	return 0;
 }
 
-static int ionic_get_module_info(struct net_device *netdev,
-				 struct ethtool_modinfo *modinfo)
-
+static int ionic_do_module_copy(u8 *dst, u8 *src, u32 len)
 {
-	struct ionic_lif *lif = netdev_priv(netdev);
-	struct ionic_dev *idev = &lif->ionic->idev;
-	struct ionic_xcvr_status *xcvr;
-	struct sfp_eeprom_base *sfp;
-
-	xcvr = &idev->port_info->status.xcvr;
-	sfp = (struct sfp_eeprom_base *) xcvr->sprom;
-
-	/* report the module data type and length */
-	switch (sfp->phys_id) {
-	case SFF8024_ID_SFP:
-		modinfo->type = ETH_MODULE_SFF_8079;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
-		break;
-	case SFF8024_ID_QSFP_8436_8636:
-	case SFF8024_ID_QSFP28_8636:
-		modinfo->type = ETH_MODULE_SFF_8436;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
-		break;
-	default:
-		netdev_info(netdev, "unknown xcvr type 0x%02x\n",
-			    xcvr->sprom[0]);
-		modinfo->type = 0;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
-		break;
-	}
-
-	return 0;
-}
-
-static int ionic_get_module_eeprom(struct net_device *netdev,
-				   struct ethtool_eeprom *ee,
-				   u8 *data)
-{
-	struct ionic_lif *lif = netdev_priv(netdev);
-	struct ionic_dev *idev = &lif->ionic->idev;
-	struct ionic_xcvr_status *xcvr;
-	char tbuf[sizeof(xcvr->sprom)];
+	char tbuf[sizeof_field(struct ionic_xcvr_status, sprom)];
 	int count = 10;
-	u32 len;
 
 	/* The NIC keeps the module prom up-to-date in the DMA space
 	 * so we can simply copy the module bytes into the data buffer.
 	 */
-	xcvr = &idev->port_info->status.xcvr;
-	len = min_t(u32, sizeof(xcvr->sprom), ee->len);
-
 	do {
-		memcpy(data, xcvr->sprom, len);
-		memcpy(tbuf, xcvr->sprom, len);
+		memcpy(dst, src, len);
+		memcpy(tbuf, src, len);
 
 		/* Let's make sure we got a consistent copy */
-		if (!memcmp(data, tbuf, len))
+		if (!memcmp(dst, tbuf, len))
 			break;
 
 	} while (--count);
@@ -976,6 +972,48 @@ static int ionic_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 
+static int ionic_get_module_eeprom_by_page(struct net_device *netdev,
+					   const struct ethtool_module_eeprom *page_data,
+					   struct netlink_ext_ack *extack)
+{
+	struct ionic_lif *lif = netdev_priv(netdev);
+	struct ionic_dev *idev = &lif->ionic->idev;
+	u32 err = -EINVAL;
+	u8 *src;
+
+	if (!page_data->length)
+		return -EINVAL;
+
+	if (page_data->bank != 0) {
+		NL_SET_ERR_MSG_MOD(extack, "Only bank 0 is supported");
+		return -EINVAL;
+	}
+
+	switch (page_data->page) {
+	case 0:
+		src = &idev->port_info->status.xcvr.sprom[page_data->offset];
+		break;
+	case 1:
+		src = &idev->port_info->sprom_page1[page_data->offset - 128];
+		break;
+	case 2:
+		src = &idev->port_info->sprom_page2[page_data->offset - 128];
+		break;
+	case 17:
+		src = &idev->port_info->sprom_page17[page_data->offset - 128];
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	memset(page_data->data, 0, page_data->length);
+	err = ionic_do_module_copy(page_data->data, src, page_data->length);
+	if (err)
+		return err;
+
+	return page_data->length;
+}
+
 static int ionic_get_ts_info(struct net_device *netdev,
 			     struct kernel_ethtool_ts_info *info)
 {
@@ -1121,8 +1159,7 @@ static const struct ethtool_ops ionic_ethtool_ops = {
 	.set_rxfh		= ionic_set_rxfh,
 	.get_tunable		= ionic_get_tunable,
 	.set_tunable		= ionic_set_tunable,
-	.get_module_info	= ionic_get_module_info,
-	.get_module_eeprom	= ionic_get_module_eeprom,
+	.get_module_eeprom_by_page	= ionic_get_module_eeprom_by_page,
 	.get_pauseparam		= ionic_get_pauseparam,
 	.set_pauseparam		= ionic_set_pauseparam,
 	.get_fecparam		= ionic_get_fecparam,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 9c85c0706c6e..f1ddbe9994a3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -1277,7 +1277,10 @@ enum ionic_xcvr_pid {
 	IONIC_XCVR_PID_SFP_25GBASE_CR_S  = 3,
 	IONIC_XCVR_PID_SFP_25GBASE_CR_L  = 4,
 	IONIC_XCVR_PID_SFP_25GBASE_CR_N  = 5,
-
+	IONIC_XCVR_PID_QSFP_50G_CR2_FC   = 6,
+	IONIC_XCVR_PID_QSFP_50G_CR2      = 7,
+	IONIC_XCVR_PID_QSFP_200G_CR4     = 8,
+	IONIC_XCVR_PID_QSFP_400G_CR4     = 9,
 	/* Fiber */
 	IONIC_XCVR_PID_QSFP_100G_AOC    = 50,
 	IONIC_XCVR_PID_QSFP_100G_ACC    = 51,
@@ -1303,6 +1306,15 @@ enum ionic_xcvr_pid {
 	IONIC_XCVR_PID_SFP_25GBASE_ACC  = 71,
 	IONIC_XCVR_PID_SFP_10GBASE_T    = 72,
 	IONIC_XCVR_PID_SFP_1000BASE_T   = 73,
+	IONIC_XCVR_PID_QSFP_200G_AOC    = 74,
+	IONIC_XCVR_PID_QSFP_200G_FR4    = 75,
+	IONIC_XCVR_PID_QSFP_200G_DR4    = 76,
+	IONIC_XCVR_PID_QSFP_200G_SR4    = 77,
+	IONIC_XCVR_PID_QSFP_200G_ACC    = 78,
+	IONIC_XCVR_PID_QSFP_400G_FR4    = 79,
+	IONIC_XCVR_PID_QSFP_400G_DR4    = 80,
+	IONIC_XCVR_PID_QSFP_400G_SR4    = 81,
+	IONIC_XCVR_PID_QSFP_400G_VR4    = 82,
 };
 
 /**
@@ -1404,6 +1416,8 @@ struct ionic_xcvr_status {
  */
 union ionic_port_config {
 	struct {
+#define IONIC_SPEED_400G	400000	/* 400G in Mbps */
+#define IONIC_SPEED_200G	200000	/* 200G in Mbps */
 #define IONIC_SPEED_100G	100000	/* 100G in Mbps */
 #define IONIC_SPEED_50G		50000	/* 50G in Mbps */
 #define IONIC_SPEED_40G		40000	/* 40G in Mbps */
@@ -2825,6 +2839,10 @@ union ionic_port_identity {
  * @status:          Port status data
  * @stats:           Port statistics data
  * @mgmt_stats:      Port management statistics data
+ * @sprom_epage:     Extended Transceiver sprom
+ * @sprom_page1:     Extended Transceiver sprom, page 1
+ * @sprom_page2:     Extended Transceiver sprom, page 2
+ * @sprom_page17:    Extended Transceiver sprom, page 17
  * @rsvd:            reserved byte(s)
  * @pb_stats:        uplink pb drop stats
  */
@@ -2835,8 +2853,17 @@ struct ionic_port_info {
 		struct ionic_port_stats      stats;
 		struct ionic_mgmt_port_stats mgmt_stats;
 	};
-	/* room for pb_stats to start at 2k offset */
-	u8                          rsvd[760];
+	union {
+		u8     sprom_epage[384];
+		struct {
+			u8 sprom_page1[128];
+			u8 sprom_page2[128];
+			u8 sprom_page17[128];
+		};
+	};
+	u8     rsvd[376];
+
+	/* pb_stats must start at 2k offset */
 	struct ionic_port_pb_stats  pb_stats;
 };
 
@@ -3209,7 +3236,11 @@ union ionic_adminq_comp {
 #define IONIC_BAR0_INTR_CTRL_OFFSET		0x2000
 #define IONIC_DEV_CMD_DONE			0x00000001
 
-#define IONIC_ASIC_TYPE_CAPRI			0
+#define IONIC_ASIC_TYPE_NONE			0
+#define IONIC_ASIC_TYPE_CAPRI			1
+#define IONIC_ASIC_TYPE_ELBA			2
+#define IONIC_ASIC_TYPE_GIGLIO			3
+#define IONIC_ASIC_TYPE_SALINA			4
 
 /**
  * struct ionic_doorbell - Doorbell register layout
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 40496587b2b3..7707a9e53c43 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3265,7 +3265,7 @@ int ionic_lif_alloc(struct ionic *ionic)
 	lif->netdev->min_mtu = max_t(unsigned int, ETH_MIN_MTU,
 				     le32_to_cpu(lif->identity->eth.min_frame_size));
 	lif->netdev->max_mtu =
-		le32_to_cpu(lif->identity->eth.max_frame_size) - ETH_HLEN - VLAN_HLEN;
+		le32_to_cpu(lif->identity->eth.max_frame_size) - VLAN_ETH_HLEN;
 
 	lif->neqs = ionic->neqs_per_lif;
 	lif->nxqs = ionic->ntxqs_per_lif;
@@ -3804,10 +3804,6 @@ err_out_adminq_deinit:
 	return err;
 }
 
-static void ionic_lif_notify_work(struct work_struct *ws)
-{
-}
-
 static void ionic_lif_set_netdev_info(struct ionic_lif *lif)
 {
 	struct ionic_admin_ctx ctx = {
@@ -3858,8 +3854,6 @@ int ionic_lif_register(struct ionic_lif *lif)
 
 	ionic_lif_register_phc(lif);
 
-	INIT_WORK(&lif->ionic->nb_work, ionic_lif_notify_work);
-
 	lif->ionic->nb.notifier_call = ionic_lif_notify;
 
 	err = register_netdevice_notifier(&lif->ionic->nb);
@@ -3869,8 +3863,8 @@ int ionic_lif_register(struct ionic_lif *lif)
 	/* only register LIF0 for now */
 	err = register_netdev(lif->netdev);
 	if (err) {
-		dev_err(lif->ionic->dev, "Cannot register net device, aborting\n");
-		ionic_lif_unregister_phc(lif);
+		dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err);
+		ionic_lif_unregister(lif);
 		return err;
 	}
 
@@ -3885,7 +3879,6 @@ void ionic_lif_unregister(struct ionic_lif *lif)
 {
 	if (lif->ionic->nb.notifier_call) {
 		unregister_netdevice_notifier(&lif->ionic->nb);
-		cancel_work_sync(&lif->ionic->nb_work);
 		lif->ionic->nb.notifier_call = NULL;
 	}
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 0f817c3f92d8..0e60a6bef99a 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -81,8 +81,9 @@ static int ionic_error_to_errno(enum ionic_status_code code)
 	case IONIC_RC_EQTYPE:
 	case IONIC_RC_EQID:
 	case IONIC_RC_EINVAL:
-	case IONIC_RC_ENOSUPP:
 		return -EINVAL;
+	case IONIC_RC_ENOSUPP:
+		return -EOPNOTSUPP;
 	case IONIC_RC_EPERM:
 		return -EPERM;
 	case IONIC_RC_ENOENT:
@@ -515,9 +516,9 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
 	unsigned long start_time;
 	unsigned long max_wait;
 	unsigned long duration;
-	int done = 0;
 	bool fw_up;
 	int opcode;
+	bool done;
 	int err;
 
 	/* Wait for dev cmd to complete, retrying if we get EAGAIN,
@@ -525,6 +526,7 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
 	 */
 	max_wait = jiffies + (max_seconds * HZ);
 try_again:
+	done = false;
 	opcode = idev->opcode;
 	start_time = jiffies;
 	for (fw_up = ionic_is_fw_running(idev);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 2ac59564ded1..d10b58ebf603 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -321,7 +321,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
 					   len, DMA_TO_DEVICE);
 	} else /* XDP_REDIRECT */ {
 		dma_addr = ionic_tx_map_single(q, frame->data, len);
-		if (!dma_addr)
+		if (dma_addr == DMA_MAPPING_ERROR)
 			return -EIO;
 	}
 
@@ -357,7 +357,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
 			} else {
 				dma_addr = ionic_tx_map_frag(q, frag, 0,
 							     skb_frag_size(frag));
-				if (dma_mapping_error(q->dev, dma_addr)) {
+				if (dma_addr == DMA_MAPPING_ERROR) {
 					ionic_tx_desc_unmap_bufs(q, desc_info);
 					return -EIO;
 				}
@@ -1083,7 +1083,7 @@ static dma_addr_t ionic_tx_map_single(struct ionic_queue *q,
 		net_warn_ratelimited("%s: DMA single map failed on %s!\n",
 				     dev_name(dev), q->name);
 		q_to_tx_stats(q)->dma_map_err++;
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 	return dma_addr;
 }
@@ -1100,7 +1100,7 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q,
 		net_warn_ratelimited("%s: DMA frag map failed on %s!\n",
 				     dev_name(dev), q->name);
 		q_to_tx_stats(q)->dma_map_err++;
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 	return dma_addr;
 }
@@ -1116,7 +1116,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb,
 	int frag_idx;
 
 	dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb));
-	if (!dma_addr)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return -EIO;
 	buf_info->dma_addr = dma_addr;
 	buf_info->len = skb_headlen(skb);
@@ -1126,7 +1126,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb,
 	nfrags = skb_shinfo(skb)->nr_frags;
 	for (frag_idx = 0; frag_idx < nfrags; frag_idx++, frag++) {
 		dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag));
-		if (!dma_addr)
+		if (dma_addr == DMA_MAPPING_ERROR)
 			goto dma_fail;
 		buf_info->dma_addr = dma_addr;
 		buf_info->len = skb_frag_size(frag);
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 9cff0a8ffb2c..3383ee1dad14 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -2832,7 +2832,7 @@ netxen_sysfs_validate_crb(struct netxen_adapter *adapter,
 
 static ssize_t
 netxen_sysfs_read_crb(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr,
+		const struct bin_attribute *attr,
 		char *buf, loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -2860,7 +2860,7 @@ netxen_sysfs_read_crb(struct file *filp, struct kobject *kobj,
 
 static ssize_t
 netxen_sysfs_write_crb(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr,
+		const struct bin_attribute *attr,
 		char *buf, loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -2901,7 +2901,7 @@ netxen_sysfs_validate_mem(struct netxen_adapter *adapter,
 
 static ssize_t
 netxen_sysfs_read_mem(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr,
+		const struct bin_attribute *attr,
 		char *buf, loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -2922,7 +2922,7 @@ netxen_sysfs_read_mem(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t netxen_sysfs_write_mem(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr, char *buf,
+		const struct bin_attribute *attr, char *buf,
 		loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -2946,20 +2946,20 @@ static ssize_t netxen_sysfs_write_mem(struct file *filp, struct kobject *kobj,
 static const struct bin_attribute bin_attr_crb = {
 	.attr = { .name = "crb", .mode = 0644 },
 	.size = 0,
-	.read = netxen_sysfs_read_crb,
-	.write = netxen_sysfs_write_crb,
+	.read_new = netxen_sysfs_read_crb,
+	.write_new = netxen_sysfs_write_crb,
 };
 
 static const struct bin_attribute bin_attr_mem = {
 	.attr = { .name = "mem", .mode = 0644 },
 	.size = 0,
-	.read = netxen_sysfs_read_mem,
-	.write = netxen_sysfs_write_mem,
+	.read_new = netxen_sysfs_read_mem,
+	.write_new = netxen_sysfs_write_mem,
 };
 
 static ssize_t
 netxen_sysfs_read_dimm(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr,
+		const struct bin_attribute *attr,
 		char *buf, loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -3082,7 +3082,7 @@ out:
 static const struct bin_attribute bin_attr_dimm = {
 	.attr = { .name = "dimm", .mode = 0644 },
 	.size = sizeof(struct netxen_dimm_cfg),
-	.read = netxen_sysfs_read_dimm,
+	.read_new = netxen_sysfs_read_dimm,
 };
 
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index b7def3b54937..016b575861b9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -939,7 +939,6 @@ u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
 /* doorbell recovery mechanism */
-void qed_db_recovery_dp(struct qed_hwfn *p_hwfn);
 void qed_db_recovery_execute(struct qed_hwfn *p_hwfn);
 bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dbg_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_dbg_hsi.h
index f6cd1b3efdfd..27e91d0d39f8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dbg_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dbg_hsi.h
@@ -1305,37 +1305,6 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn,
 					    char *results_buf);
 
 /**
- * qed_print_mcp_trace_results_cont(): Prints MCP Trace results, and
- * keeps the MCP trace meta data allocated, to support continuous MCP Trace
- * parsing. After the continuous parsing ends, mcp_trace_free_meta_data should
- * be called to free the meta data.
- *
- * @p_hwfn: HW device data.
- * @dump_buf: MVP trace dump buffer, starting from the header.
- * @results_buf: Buffer for printing the mcp trace results.
- *
- * Return: Error if the parsing fails, ok otherwise.
- */
-enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn,
-						 u32 *dump_buf,
-						 char *results_buf);
-
-/**
- * qed_print_mcp_trace_line(): Prints MCP Trace results for a single line
- *
- * @p_hwfn: HW device data.
- * @dump_buf: MCP trace dump buffer, starting from the header.
- * @num_dumped_bytes: Number of bytes that were dumped.
- * @results_buf: Buffer for printing the mcp trace results.
- *
- * Return: Error if the parsing fails, ok otherwise.
- */
-enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn,
-					 u8 *dump_buf,
-					 u32 num_dumped_bytes,
-					 char *results_buf);
-
-/**
  * qed_mcp_trace_free_meta_data(): Frees the MCP Trace meta data.
  * Should be called after continuous MCP Trace parsing.
  *
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 464a72afb758..9c3d3dd2f847 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -7614,31 +7614,6 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn,
 					results_buf, &parsed_buf_size, true);
 }
 
-enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn,
-						 u32 *dump_buf,
-						 char *results_buf)
-{
-	u32 parsed_buf_size;
-
-	return qed_parse_mcp_trace_dump(p_hwfn, dump_buf, results_buf,
-					&parsed_buf_size, false);
-}
-
-enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn,
-					 u8 *dump_buf,
-					 u32 num_dumped_bytes,
-					 char *results_buf)
-{
-	u32 parsed_results_bytes;
-
-	return qed_parse_mcp_trace_buf(p_hwfn,
-				       dump_buf,
-				       num_dumped_bytes,
-				       0,
-				       num_dumped_bytes,
-				       results_buf, &parsed_results_bytes);
-}
-
 /* Frees the specified MCP Trace meta data */
 void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn)
 {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 86a93cac2647..9659ce5b0712 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -255,25 +255,6 @@ static void qed_db_recovery_teardown(struct qed_hwfn *p_hwfn)
 	p_hwfn->db_recovery_info.db_recovery_counter = 0;
 }
 
-/* Print the content of the doorbell recovery mechanism */
-void qed_db_recovery_dp(struct qed_hwfn *p_hwfn)
-{
-	struct qed_db_recovery_entry *db_entry = NULL;
-
-	DP_NOTICE(p_hwfn,
-		  "Displaying doorbell recovery database. Counter was %d\n",
-		  p_hwfn->db_recovery_info.db_recovery_counter);
-
-	/* Protect the list */
-	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
-	list_for_each_entry(db_entry,
-			    &p_hwfn->db_recovery_info.list, list_entry) {
-		qed_db_recovery_dp_entry(p_hwfn, db_entry, "Printing");
-	}
-
-	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
-}
-
 /* Ring the doorbell of a single doorbell recovery entry */
 static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
 				 struct qed_db_recovery_entry *db_entry)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index ed1a84542ad2..10e355397cee 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -2666,58 +2666,6 @@ void qed_gft_config(struct qed_hwfn *p_hwfn,
 void qed_enable_context_validation(struct qed_hwfn *p_hwfn,
 				   struct qed_ptt *p_ptt);
 
-/**
- * qed_calc_session_ctx_validation(): Calcualte validation byte for
- *                                    session context.
- *
- * @p_ctx_mem: Pointer to context memory.
- * @ctx_size: Context size.
- * @ctx_type: Context type.
- * @cid: Context cid.
- *
- * Return: Void.
- */
-void qed_calc_session_ctx_validation(void *p_ctx_mem,
-				     u16 ctx_size, u8 ctx_type, u32 cid);
-
-/**
- * qed_calc_task_ctx_validation(): Calcualte validation byte for task
- *                                 context.
- *
- * @p_ctx_mem: Pointer to context memory.
- * @ctx_size: Context size.
- * @ctx_type: Context type.
- * @tid: Context tid.
- *
- * Return: Void.
- */
-void qed_calc_task_ctx_validation(void *p_ctx_mem,
-				  u16 ctx_size, u8 ctx_type, u32 tid);
-
-/**
- * qed_memset_session_ctx(): Memset session context to 0 while
- *                            preserving validation bytes.
- *
- * @p_ctx_mem: Pointer to context memory.
- * @ctx_size: Size to initialzie.
- * @ctx_type: Context type.
- *
- * Return: Void.
- */
-void qed_memset_session_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type);
-
-/**
- * qed_memset_task_ctx(): Memset task context to 0 while preserving
- *                        validation bytes.
- *
- * @p_ctx_mem: Pointer to context memory.
- * @ctx_size: size to initialzie.
- * @ctx_type: context type.
- *
- * Return: Void.
- */
-void qed_memset_task_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type);
-
 #define NUM_STORMS 6
 
 /**
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 9e5f0dbc8a07..9907973399dc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -69,17 +69,6 @@ int qed_ptt_pool_alloc(struct qed_hwfn *p_hwfn)
 	return 0;
 }
 
-void qed_ptt_invalidate(struct qed_hwfn *p_hwfn)
-{
-	struct qed_ptt *p_ptt;
-	int i;
-
-	for (i = 0; i < PXP_EXTERNAL_BAR_PF_WINDOW_NUM; i++) {
-		p_ptt = &p_hwfn->p_ptt_pool->ptts[i];
-		p_ptt->pxp.offset = QED_BAR_INVALID_OFFSET;
-	}
-}
-
 void qed_ptt_pool_free(struct qed_hwfn *p_hwfn)
 {
 	kfree(p_hwfn->p_ptt_pool);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h
index e535983ce21b..3c98f58a184f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h
@@ -62,15 +62,6 @@ enum _dmae_cmd_crc_mask {
 void qed_gtt_init(struct qed_hwfn *p_hwfn);
 
 /**
- * qed_ptt_invalidate(): Forces all ptt entries to be re-configured
- *
- * @p_hwfn: HW device data.
- *
- * Return: Void.
- */
-void qed_ptt_invalidate(struct qed_hwfn *p_hwfn);
-
-/**
  * qed_ptt_pool_alloc(): Allocate and initialize PTT pool.
  *
  * @p_hwfn: HW device data.
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index 407029a36fa1..aa20bb8caa9a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -18,16 +18,6 @@
 
 #define CDU_VALIDATION_DEFAULT_CFG CDU_CONTEXT_VALIDATION_DEFAULT_CFG
 
-static u16 con_region_offsets[3][NUM_OF_CONNECTION_TYPES] = {
-	{400, 336, 352, 368, 304, 384, 416, 352},	/* region 3 offsets */
-	{528, 496, 416, 512, 448, 512, 544, 480},	/* region 4 offsets */
-	{608, 544, 496, 576, 576, 592, 624, 560}	/* region 5 offsets */
-};
-
-static u16 task_region_offsets[1][NUM_OF_CONNECTION_TYPES] = {
-	{240, 240, 112, 0, 0, 0, 0, 96}	/* region 1 offsets */
-};
-
 /* General constants */
 #define QM_PQ_MEM_4KB(pq_size)	(pq_size ? DIV_ROUND_UP((pq_size + 1) *	\
 							QM_PQ_ELEMENT_SIZE, \
@@ -1576,134 +1566,6 @@ void qed_gft_config(struct qed_hwfn *p_hwfn,
 	qed_wr(p_hwfn, p_ptt, PRS_REG_SEARCH_GFT, 1);
 }
 
-DECLARE_CRC8_TABLE(cdu_crc8_table);
-
-/* Calculate and return CDU validation byte per connection type/region/cid */
-static u8 qed_calc_cdu_validation_byte(u8 conn_type, u8 region, u32 cid)
-{
-	const u8 validation_cfg = CDU_VALIDATION_DEFAULT_CFG;
-	u8 crc, validation_byte = 0;
-	static u8 crc8_table_valid; /* automatically initialized to 0 */
-	u32 validation_string = 0;
-	__be32 data_to_crc;
-
-	if (!crc8_table_valid) {
-		crc8_populate_msb(cdu_crc8_table, 0x07);
-		crc8_table_valid = 1;
-	}
-
-	/* The CRC is calculated on the String-to-compress:
-	 * [31:8]  = {CID[31:20],CID[11:0]}
-	 * [7:4]   = Region
-	 * [3:0]   = Type
-	 */
-	if ((validation_cfg >> CDU_CONTEXT_VALIDATION_CFG_USE_CID) & 1)
-		validation_string |= (cid & 0xFFF00000) | ((cid & 0xFFF) << 8);
-
-	if ((validation_cfg >> CDU_CONTEXT_VALIDATION_CFG_USE_REGION) & 1)
-		validation_string |= ((region & 0xF) << 4);
-
-	if ((validation_cfg >> CDU_CONTEXT_VALIDATION_CFG_USE_TYPE) & 1)
-		validation_string |= (conn_type & 0xF);
-
-	/* Convert to big-endian and calculate CRC8 */
-	data_to_crc = cpu_to_be32(validation_string);
-	crc = crc8(cdu_crc8_table, (u8 *)&data_to_crc, sizeof(data_to_crc),
-		   CRC8_INIT_VALUE);
-
-	/* The validation byte [7:0] is composed:
-	 * for type A validation
-	 * [7]          = active configuration bit
-	 * [6:0]        = crc[6:0]
-	 *
-	 * for type B validation
-	 * [7]          = active configuration bit
-	 * [6:3]        = connection_type[3:0]
-	 * [2:0]        = crc[2:0]
-	 */
-	validation_byte |=
-	    ((validation_cfg >>
-	      CDU_CONTEXT_VALIDATION_CFG_USE_ACTIVE) & 1) << 7;
-
-	if ((validation_cfg >>
-	     CDU_CONTEXT_VALIDATION_CFG_VALIDATION_TYPE_SHIFT) & 1)
-		validation_byte |= ((conn_type & 0xF) << 3) | (crc & 0x7);
-	else
-		validation_byte |= crc & 0x7F;
-
-	return validation_byte;
-}
-
-/* Calcualte and set validation bytes for session context */
-void qed_calc_session_ctx_validation(void *p_ctx_mem,
-				     u16 ctx_size, u8 ctx_type, u32 cid)
-{
-	u8 *x_val_ptr, *t_val_ptr, *u_val_ptr, *p_ctx;
-
-	p_ctx = (u8 * const)p_ctx_mem;
-	x_val_ptr = &p_ctx[con_region_offsets[0][ctx_type]];
-	t_val_ptr = &p_ctx[con_region_offsets[1][ctx_type]];
-	u_val_ptr = &p_ctx[con_region_offsets[2][ctx_type]];
-
-	memset(p_ctx, 0, ctx_size);
-
-	*x_val_ptr = qed_calc_cdu_validation_byte(ctx_type, 3, cid);
-	*t_val_ptr = qed_calc_cdu_validation_byte(ctx_type, 4, cid);
-	*u_val_ptr = qed_calc_cdu_validation_byte(ctx_type, 5, cid);
-}
-
-/* Calcualte and set validation bytes for task context */
-void qed_calc_task_ctx_validation(void *p_ctx_mem,
-				  u16 ctx_size, u8 ctx_type, u32 tid)
-{
-	u8 *p_ctx, *region1_val_ptr;
-
-	p_ctx = (u8 * const)p_ctx_mem;
-	region1_val_ptr = &p_ctx[task_region_offsets[0][ctx_type]];
-
-	memset(p_ctx, 0, ctx_size);
-
-	*region1_val_ptr = qed_calc_cdu_validation_byte(ctx_type, 1, tid);
-}
-
-/* Memset session context to 0 while preserving validation bytes */
-void qed_memset_session_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type)
-{
-	u8 *x_val_ptr, *t_val_ptr, *u_val_ptr, *p_ctx;
-	u8 x_val, t_val, u_val;
-
-	p_ctx = (u8 * const)p_ctx_mem;
-	x_val_ptr = &p_ctx[con_region_offsets[0][ctx_type]];
-	t_val_ptr = &p_ctx[con_region_offsets[1][ctx_type]];
-	u_val_ptr = &p_ctx[con_region_offsets[2][ctx_type]];
-
-	x_val = *x_val_ptr;
-	t_val = *t_val_ptr;
-	u_val = *u_val_ptr;
-
-	memset(p_ctx, 0, ctx_size);
-
-	*x_val_ptr = x_val;
-	*t_val_ptr = t_val;
-	*u_val_ptr = u_val;
-}
-
-/* Memset task context to 0 while preserving validation bytes */
-void qed_memset_task_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type)
-{
-	u8 *p_ctx, *region1_val_ptr;
-	u8 region1_val;
-
-	p_ctx = (u8 * const)p_ctx_mem;
-	region1_val_ptr = &p_ctx[task_region_offsets[0][ctx_type]];
-
-	region1_val = *region1_val_ptr;
-
-	memset(p_ctx, 0, ctx_size);
-
-	*region1_val_ptr = region1_val;
-}
-
 /* Enable and configure context validation */
 void qed_enable_context_validation(struct qed_hwfn *p_hwfn,
 				   struct qed_ptt *p_ptt)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index f915c423fe70..886061d7351a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -454,7 +454,7 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 
 static void qed_free_cdev(struct qed_dev *cdev)
 {
-	kfree((void *)cdev);
+	kfree(cdev);
 }
 
 static struct qed_dev *qed_alloc_cdev(struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 26a714bfad4e..c7f497c36f66 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -3301,7 +3301,9 @@ int qed_mcp_bist_nvm_get_num_images(struct qed_hwfn *p_hwfn,
 	if (rc)
 		return rc;
 
-	if (((rsp & FW_MSG_CODE_MASK) != FW_MSG_CODE_OK))
+	if (((rsp & FW_MSG_CODE_MASK) == FW_MSG_CODE_UNSUPPORTED))
+		rc = -EOPNOTSUPP;
+	else if (((rsp & FW_MSG_CODE_MASK) != FW_MSG_CODE_OK))
 		rc = -EINVAL;
 
 	return rc;
@@ -3356,6 +3358,7 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
 					     p_ptt, &nvm_info.num_images);
 	if (rc == -EOPNOTSUPP) {
 		DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n");
+		nvm_info.num_images = 0;
 		goto out;
 	} else if (rc || !nvm_info.num_images) {
 		DP_ERR(p_hwfn, "Failed getting number of images\n");
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
index f55eed092f25..7d78f072b0a1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
@@ -242,7 +242,7 @@ static int qed_mfw_get_tlv_group(u8 tlv_type, u8 *tlv_group)
 }
 
 /* Returns size of the data buffer or, -1 in case TLV data is not available. */
-static int
+static noinline_for_stack int
 qed_mfw_get_gen_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 			  struct qed_mfw_tlv_generic *p_drv_buf,
 			  struct qed_tlv_parsed_buf *p_buf)
@@ -304,7 +304,7 @@ qed_mfw_get_gen_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 	return -1;
 }
 
-static int
+static noinline_for_stack int
 qed_mfw_get_eth_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 			  struct qed_mfw_tlv_eth *p_drv_buf,
 			  struct qed_tlv_parsed_buf *p_buf)
@@ -438,7 +438,7 @@ qed_mfw_get_tlv_time_value(struct qed_mfw_tlv_time *p_time,
 	return QED_MFW_TLV_TIME_SIZE;
 }
 
-static int
+static noinline_for_stack int
 qed_mfw_get_fcoe_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 			   struct qed_mfw_tlv_fcoe *p_drv_buf,
 			   struct qed_tlv_parsed_buf *p_buf)
@@ -1073,7 +1073,7 @@ qed_mfw_get_fcoe_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 	return -1;
 }
 
-static int
+static noinline_for_stack int
 qed_mfw_get_iscsi_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 			    struct qed_mfw_tlv_iscsi *p_drv_buf,
 			    struct qed_tlv_parsed_buf *p_buf)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index fa167b1aa019..5222a035fd19 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -3033,7 +3033,7 @@ static void qed_iov_vf_mbx_vport_update(struct qed_hwfn *p_hwfn,
 	u16 length;
 	int rc;
 
-	/* Valiate PF can send such a request */
+	/* Validate PF can send such a request */
 	if (!vf->vport_instance) {
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_IOV,
@@ -3312,7 +3312,7 @@ static void qed_iov_vf_mbx_ucast_filter(struct qed_hwfn *p_hwfn,
 		goto out;
 	}
 
-	/* Determine if the unicast filtering is acceptible by PF */
+	/* Determine if the unicast filtering is acceptable by PF */
 	if ((p_bulletin->valid_bitmap & BIT(VLAN_ADDR_FORCED)) &&
 	    (params.type == QED_FILTER_VLAN ||
 	     params.type == QED_FILTER_MAC_VLAN)) {
@@ -3729,7 +3729,7 @@ qed_iov_execute_vf_flr_cleanup(struct qed_hwfn *p_hwfn,
 
 		rc = qed_iov_enable_vf_access(p_hwfn, p_ptt, p_vf);
 		if (rc) {
-			DP_ERR(p_hwfn, "Failed to re-enable VF[%d] acces\n",
+			DP_ERR(p_hwfn, "Failed to re-enable VF[%d] access\n",
 			       vfid);
 			return rc;
 		}
@@ -4480,7 +4480,7 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
 
 		/* Failure to acquire the ptt in 100g creates an odd error
-		 * where the first engine has already relased IOV.
+		 * where the first engine has already released IOV.
 		 */
 		if (!ptt) {
 			DP_ERR(hwfn, "Failed to acquire ptt\n");
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 99df00c30b8c..b5d744d2586f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -203,7 +203,7 @@ static struct pci_driver qede_pci_driver = {
 };
 
 static struct qed_eth_cb_ops qede_ll_ops = {
-	{
+	.common = {
 #ifdef CONFIG_RFS_ACCEL
 		.arfs_filter_op = qede_arfs_filter_op,
 #endif
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index fc78bc959ded..aee4e63b4b82 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -3420,7 +3420,7 @@ static int ql_adapter_down(struct ql3_adapter *qdev, int do_reset)
 		pci_disable_msi(qdev->pdev);
 	}
 
-	del_timer_sync(&qdev->adapter_timer);
+	timer_delete_sync(&qdev->adapter_timer);
 
 	napi_disable(&qdev->napi);
 
@@ -3735,7 +3735,7 @@ static void ql_get_board_info(struct ql3_adapter *qdev)
 
 static void ql3xxx_timer(struct timer_list *t)
 {
-	struct ql3_adapter *qdev = from_timer(qdev, t, adapter_timer);
+	struct ql3_adapter *qdev = timer_container_of(qdev, t, adapter_timer);
 	queue_delayed_work(qdev->workqueue, &qdev->link_state_work, 0);
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index f9dd50152b1e..d57b976b9040 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -454,8 +454,10 @@ static int qlcnic_sriov_set_guest_vlan_mode(struct qlcnic_adapter *adapter,
 
 	num_vlans = sriov->num_allowed_vlans;
 	sriov->allowed_vlans = kcalloc(num_vlans, sizeof(u16), GFP_KERNEL);
-	if (!sriov->allowed_vlans)
+	if (!sriov->allowed_vlans) {
+		qlcnic_sriov_free_vlans(adapter);
 		return -ENOMEM;
+	}
 
 	vlans = (u16 *)&cmd->rsp.arg[3];
 	for (i = 0; i < num_vlans; i++)
@@ -1482,8 +1484,11 @@ static int qlcnic_sriov_channel_cfg_cmd(struct qlcnic_adapter *adapter, u8 cmd_o
 	}
 
 	cmd_op = (cmd.rsp.arg[0] & 0xff);
-	if (cmd.rsp.arg[0] >> 25 == 2)
-		return 2;
+	if (cmd.rsp.arg[0] >> 25 == 2) {
+		ret = 2;
+		goto out;
+	}
+
 	if (cmd_op == QLCNIC_BC_CMD_CHANNEL_INIT)
 		set_bit(QLC_BC_VF_STATE, &vf->state);
 	else
@@ -2167,8 +2172,10 @@ int qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
 		vf = &sriov->vf_info[i];
 		vf->sriov_vlans = kcalloc(sriov->num_allowed_vlans,
 					  sizeof(*vf->sriov_vlans), GFP_KERNEL);
-		if (!vf->sriov_vlans)
+		if (!vf->sriov_vlans) {
+			qlcnic_sriov_free_vlans(adapter);
 			return -ENOMEM;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index 74125188beb8..c0f20464fd1e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -264,7 +264,7 @@ static int qlcnic_sysfs_validate_crb(struct qlcnic_adapter *adapter,
 }
 
 static ssize_t qlcnic_sysfs_read_crb(struct file *filp, struct kobject *kobj,
-				     struct bin_attribute *attr, char *buf,
+				     const struct bin_attribute *attr, char *buf,
 				     loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -281,7 +281,7 @@ static ssize_t qlcnic_sysfs_read_crb(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t qlcnic_sysfs_write_crb(struct file *filp, struct kobject *kobj,
-				      struct bin_attribute *attr, char *buf,
+				      const struct bin_attribute *attr, char *buf,
 				      loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -310,7 +310,7 @@ static int qlcnic_sysfs_validate_mem(struct qlcnic_adapter *adapter,
 }
 
 static ssize_t qlcnic_sysfs_read_mem(struct file *filp, struct kobject *kobj,
-				     struct bin_attribute *attr, char *buf,
+				     const struct bin_attribute *attr, char *buf,
 				     loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -332,7 +332,7 @@ static ssize_t qlcnic_sysfs_read_mem(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t qlcnic_sysfs_write_mem(struct file *filp, struct kobject *kobj,
-				      struct bin_attribute *attr, char *buf,
+				      const struct bin_attribute *attr, char *buf,
 				      loff_t offset, size_t size)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -396,7 +396,7 @@ static int validate_pm_config(struct qlcnic_adapter *adapter,
 
 static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp,
 					    struct kobject *kobj,
-					    struct bin_attribute *attr,
+					    const struct bin_attribute *attr,
 					    char *buf, loff_t offset,
 					    size_t size)
 {
@@ -446,7 +446,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp,
 
 static ssize_t qlcnic_sysfs_read_pm_config(struct file *filp,
 					   struct kobject *kobj,
-					   struct bin_attribute *attr,
+					   const struct bin_attribute *attr,
 					   char *buf, loff_t offset,
 					   size_t size)
 {
@@ -539,7 +539,7 @@ static int validate_esw_config(struct qlcnic_adapter *adapter,
 
 static ssize_t qlcnic_sysfs_write_esw_config(struct file *file,
 					     struct kobject *kobj,
-					     struct bin_attribute *attr,
+					     const struct bin_attribute *attr,
 					     char *buf, loff_t offset,
 					     size_t size)
 {
@@ -623,7 +623,7 @@ out:
 
 static ssize_t qlcnic_sysfs_read_esw_config(struct file *file,
 					    struct kobject *kobj,
-					    struct bin_attribute *attr,
+					    const struct bin_attribute *attr,
 					    char *buf, loff_t offset,
 					    size_t size)
 {
@@ -675,7 +675,7 @@ static int validate_npar_config(struct qlcnic_adapter *adapter,
 
 static ssize_t qlcnic_sysfs_write_npar_config(struct file *file,
 					      struct kobject *kobj,
-					      struct bin_attribute *attr,
+					      const struct bin_attribute *attr,
 					      char *buf, loff_t offset,
 					      size_t size)
 {
@@ -722,7 +722,7 @@ static ssize_t qlcnic_sysfs_write_npar_config(struct file *file,
 
 static ssize_t qlcnic_sysfs_read_npar_config(struct file *file,
 					     struct kobject *kobj,
-					     struct bin_attribute *attr,
+					     const struct bin_attribute *attr,
 					     char *buf, loff_t offset,
 					     size_t size)
 {
@@ -769,7 +769,7 @@ static ssize_t qlcnic_sysfs_read_npar_config(struct file *file,
 
 static ssize_t qlcnic_sysfs_get_port_stats(struct file *file,
 					   struct kobject *kobj,
-					   struct bin_attribute *attr,
+					   const struct bin_attribute *attr,
 					   char *buf, loff_t offset,
 					   size_t size)
 {
@@ -804,7 +804,7 @@ static ssize_t qlcnic_sysfs_get_port_stats(struct file *file,
 
 static ssize_t qlcnic_sysfs_get_esw_stats(struct file *file,
 					  struct kobject *kobj,
-					  struct bin_attribute *attr,
+					  const struct bin_attribute *attr,
 					  char *buf, loff_t offset,
 					  size_t size)
 {
@@ -839,7 +839,7 @@ static ssize_t qlcnic_sysfs_get_esw_stats(struct file *file,
 
 static ssize_t qlcnic_sysfs_clear_esw_stats(struct file *file,
 					    struct kobject *kobj,
-					    struct bin_attribute *attr,
+					    const struct bin_attribute *attr,
 					    char *buf, loff_t offset,
 					    size_t size)
 {
@@ -868,7 +868,7 @@ static ssize_t qlcnic_sysfs_clear_esw_stats(struct file *file,
 
 static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file,
 					     struct kobject *kobj,
-					     struct bin_attribute *attr,
+					     const struct bin_attribute *attr,
 					     char *buf, loff_t offset,
 					     size_t size)
 {
@@ -898,7 +898,7 @@ static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file,
 
 static ssize_t qlcnic_sysfs_read_pci_config(struct file *file,
 					    struct kobject *kobj,
-					    struct bin_attribute *attr,
+					    const struct bin_attribute *attr,
 					    char *buf, loff_t offset,
 					    size_t size)
 {
@@ -938,7 +938,7 @@ static ssize_t qlcnic_sysfs_read_pci_config(struct file *file,
 
 static ssize_t qlcnic_83xx_sysfs_flash_read_handler(struct file *filp,
 						    struct kobject *kobj,
-						    struct bin_attribute *attr,
+						    const struct bin_attribute *attr,
 						    char *buf, loff_t offset,
 						    size_t size)
 {
@@ -1115,7 +1115,7 @@ static int qlcnic_83xx_sysfs_flash_write(struct qlcnic_adapter *adapter,
 
 static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp,
 						     struct kobject *kobj,
-						     struct bin_attribute *attr,
+						     const struct bin_attribute *attr,
 						     char *buf, loff_t offset,
 						     size_t size)
 {
@@ -1195,64 +1195,63 @@ static const struct device_attribute dev_attr_beacon = {
 static const struct bin_attribute bin_attr_crb = {
 	.attr = { .name = "crb", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_sysfs_read_crb,
-	.write = qlcnic_sysfs_write_crb,
+	.read_new = qlcnic_sysfs_read_crb,
+	.write_new = qlcnic_sysfs_write_crb,
 };
 
 static const struct bin_attribute bin_attr_mem = {
 	.attr = { .name = "mem", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_sysfs_read_mem,
-	.write = qlcnic_sysfs_write_mem,
+	.read_new = qlcnic_sysfs_read_mem,
+	.write_new = qlcnic_sysfs_write_mem,
 };
 
 static const struct bin_attribute bin_attr_npar_config = {
 	.attr = { .name = "npar_config", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_sysfs_read_npar_config,
-	.write = qlcnic_sysfs_write_npar_config,
+	.read_new = qlcnic_sysfs_read_npar_config,
+	.write_new = qlcnic_sysfs_write_npar_config,
 };
 
 static const struct bin_attribute bin_attr_pci_config = {
 	.attr = { .name = "pci_config", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_sysfs_read_pci_config,
-	.write = NULL,
+	.read_new = qlcnic_sysfs_read_pci_config,
 };
 
 static const struct bin_attribute bin_attr_port_stats = {
 	.attr = { .name = "port_stats", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_sysfs_get_port_stats,
-	.write = qlcnic_sysfs_clear_port_stats,
+	.read_new = qlcnic_sysfs_get_port_stats,
+	.write_new = qlcnic_sysfs_clear_port_stats,
 };
 
 static const struct bin_attribute bin_attr_esw_stats = {
 	.attr = { .name = "esw_stats", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_sysfs_get_esw_stats,
-	.write = qlcnic_sysfs_clear_esw_stats,
+	.read_new = qlcnic_sysfs_get_esw_stats,
+	.write_new = qlcnic_sysfs_clear_esw_stats,
 };
 
 static const struct bin_attribute bin_attr_esw_config = {
 	.attr = { .name = "esw_config", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_sysfs_read_esw_config,
-	.write = qlcnic_sysfs_write_esw_config,
+	.read_new = qlcnic_sysfs_read_esw_config,
+	.write_new = qlcnic_sysfs_write_esw_config,
 };
 
 static const struct bin_attribute bin_attr_pm_config = {
 	.attr = { .name = "pm_config", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_sysfs_read_pm_config,
-	.write = qlcnic_sysfs_write_pm_config,
+	.read_new = qlcnic_sysfs_read_pm_config,
+	.write_new = qlcnic_sysfs_write_pm_config,
 };
 
 static const struct bin_attribute bin_attr_flash = {
 	.attr = { .name = "flash", .mode = 0644 },
 	.size = 0,
-	.read = qlcnic_83xx_sysfs_flash_read_handler,
-	.write = qlcnic_83xx_sysfs_flash_write_handler,
+	.read_new = qlcnic_83xx_sysfs_flash_read_handler,
+	.write_new = qlcnic_83xx_sysfs_flash_write_handler,
 };
 
 #ifdef CONFIG_QLCNIC_HWMON
diff --git a/drivers/net/ethernet/qualcomm/Kconfig b/drivers/net/ethernet/qualcomm/Kconfig
index 9210ff360fdc..a4434eb38950 100644
--- a/drivers/net/ethernet/qualcomm/Kconfig
+++ b/drivers/net/ethernet/qualcomm/Kconfig
@@ -52,7 +52,6 @@ config QCOM_EMAC
 	depends on HAS_DMA && HAS_IOMEM
 	select CRC32
 	select PHYLIB
-	select MDIO_DEVRES
 	help
 	  This driver supports the Qualcomm Technologies, Inc. Gigabit
 	  Ethernet Media Access Controller (EMAC). The controller
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index ef9c02b000e4..38a779f4b866 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -54,7 +54,7 @@ MODULE_PARM_DESC(qcaspi_burst_len, "Number of data bytes per burst. Use 1-5000."
 
 #define QCASPI_PLUGGABLE_MIN 0
 #define QCASPI_PLUGGABLE_MAX 1
-static int qcaspi_pluggable = QCASPI_PLUGGABLE_MIN;
+static int qcaspi_pluggable = QCASPI_PLUGGABLE_MAX;
 module_param(qcaspi_pluggable, int, 0);
 MODULE_PARM_DESC(qcaspi_pluggable, "Pluggable SPI connection (yes/no).");
 
@@ -818,7 +818,6 @@ qcaspi_netdev_init(struct net_device *dev)
 
 	dev->mtu = QCAFRM_MAX_MTU;
 	dev->type = ARPHRD_ETHER;
-	qca->clkspeed = qcaspi_clkspeed;
 	qca->burst_len = qcaspi_burst_len;
 	qca->spi_thread = NULL;
 	qca->buffer_size = (QCAFRM_MAX_MTU + VLAN_ETH_HLEN + QCAFRM_HEADER_LEN +
@@ -909,17 +908,15 @@ qca_spi_probe(struct spi_device *spi)
 	legacy_mode = of_property_read_bool(spi->dev.of_node,
 					    "qca,legacy-mode");
 
-	if (qcaspi_clkspeed == 0) {
-		if (spi->max_speed_hz)
-			qcaspi_clkspeed = spi->max_speed_hz;
-		else
-			qcaspi_clkspeed = QCASPI_CLK_SPEED;
-	}
+	if (qcaspi_clkspeed)
+		spi->max_speed_hz = qcaspi_clkspeed;
+	else if (!spi->max_speed_hz)
+		spi->max_speed_hz = QCASPI_CLK_SPEED;
 
-	if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) ||
-	    (qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) {
-		dev_err(&spi->dev, "Invalid clkspeed: %d\n",
-			qcaspi_clkspeed);
+	if (spi->max_speed_hz < QCASPI_CLK_SPEED_MIN ||
+	    spi->max_speed_hz > QCASPI_CLK_SPEED_MAX) {
+		dev_err(&spi->dev, "Invalid clkspeed: %u\n",
+			spi->max_speed_hz);
 		return -EINVAL;
 	}
 
@@ -944,14 +941,13 @@ qca_spi_probe(struct spi_device *spi)
 		return -EINVAL;
 	}
 
-	dev_info(&spi->dev, "ver=%s, clkspeed=%d, burst_len=%d, pluggable=%d\n",
+	dev_info(&spi->dev, "ver=%s, clkspeed=%u, burst_len=%d, pluggable=%d\n",
 		 QCASPI_DRV_VERSION,
-		 qcaspi_clkspeed,
+		 spi->max_speed_hz,
 		 qcaspi_burst_len,
 		 qcaspi_pluggable);
 
 	spi->mode = SPI_MODE_3;
-	spi->max_speed_hz = qcaspi_clkspeed;
 	if (spi_setup(spi) < 0) {
 		dev_err(&spi->dev, "Unable to setup SPI device\n");
 		return -EFAULT;
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h
index 7ba5c9e2f61c..90b290f94c27 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.h
+++ b/drivers/net/ethernet/qualcomm/qca_spi.h
@@ -89,7 +89,6 @@ struct qcaspi {
 #endif
 
 	/* user configurable options */
-	u32 clkspeed;
 	u8 legacy_mode;
 	u16 burst_len;
 };
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index f3bea196a8f9..ba8763cac9d9 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -117,11 +117,14 @@ static void rmnet_unregister_bridge(struct rmnet_port *port)
 	rmnet_unregister_real_device(bridge_dev);
 }
 
-static int rmnet_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
+static int rmnet_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	u32 data_format = RMNET_FLAGS_INGRESS_DEAGGREGATION;
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct net_device *real_dev;
 	int mode = RMNET_EPMODE_VND;
 	struct rmnet_endpoint *ep;
@@ -134,7 +137,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 	}
 
-	real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	real_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK]));
 	if (!real_dev) {
 		NL_SET_ERR_MSG_MOD(extack, "link does not exist");
 		return -ENODEV;
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
index a5e3d1a88305..8b4640c5d61e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
@@ -686,8 +686,8 @@ void rmnet_map_update_ul_agg_config(struct rmnet_port *port, u32 size,
 
 void rmnet_map_tx_aggregate_init(struct rmnet_port *port)
 {
-	hrtimer_init(&port->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	port->hrtimer.function = rmnet_map_flush_tx_packet_queue;
+	hrtimer_setup(&port->hrtimer, rmnet_map_flush_tx_packet_queue, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 	spin_lock_init(&port->agg_lock);
 	rmnet_map_update_ul_agg_config(port, 4096, 1, 800);
 	INIT_WORK(&port->agg_wq, rmnet_map_flush_tx_packet_work);
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 9ce0e8a64ba8..a73dcaffa8c5 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -1684,6 +1684,7 @@ static void rtl8139_tx_timeout_task (struct work_struct *work)
 	if (tmp8 & CmdTxEnb)
 		RTL_W8 (ChipCmd, CmdRxEnb);
 
+	netdev_lock(dev);
 	spin_lock_bh(&tp->rx_lock);
 	/* Disable interrupts by clearing the interrupt mask. */
 	RTL_W16 (IntrMask, 0x0000);
@@ -1694,11 +1695,12 @@ static void rtl8139_tx_timeout_task (struct work_struct *work)
 	spin_unlock_irq(&tp->lock);
 
 	/* ...and finally, reset everything */
-	napi_enable(&tp->napi);
+	napi_enable_locked(&tp->napi);
 	rtl8139_hw_start(dev);
 	netif_wake_queue(dev);
 
 	spin_unlock_bh(&tp->rx_lock);
+	netdev_unlock(dev);
 }
 
 static void rtl8139_tx_timeout(struct net_device *dev, unsigned int txqueue)
diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 8a8ea51c639e..fe136f61586f 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -114,7 +114,8 @@ config R8169
 	  will be called r8169.  This is recommended.
 
 config R8169_LEDS
-	def_bool R8169 && LEDS_TRIGGER_NETDEV
+	bool "Support for controlling the NIC LEDs"
+	depends on R8169 && LEDS_TRIGGER_NETDEV
 	depends on !(R8169=y && LEDS_CLASS=m)
 	help
 	  Optional support for controlling the NIC LED's with the netdev
diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c
index 6cbcb3164367..0d65434982a2 100644
--- a/drivers/net/ethernet/realtek/atp.c
+++ b/drivers/net/ethernet/realtek/atp.c
@@ -717,7 +717,7 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
    problem where the adapter forgets its ethernet address. */
 static void atp_timed_checker(struct timer_list *t)
 {
-	struct net_local *lp = from_timer(lp, t, timer);
+	struct net_local *lp = timer_container_of(lp, t, timer);
 	struct net_device *dev = lp->dev;
 	long ioaddr = dev->base_addr;
 	int tickssofar = jiffies - lp->last_rx_time;
@@ -832,7 +832,7 @@ net_close(struct net_device *dev)
 
 	netif_stop_queue(dev);
 
-	del_timer_sync(&lp->timer);
+	timer_delete_sync(&lp->timer);
 
 	/* Flush the Tx and disable Rx here. */
 	lp->addr_mode = CMR2h_OFF;
diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index be4c9622618d..2c1a0c21af8d 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -23,7 +23,7 @@ enum mac_version {
 	RTL_GIGA_MAC_VER_08,
 	RTL_GIGA_MAC_VER_09,
 	RTL_GIGA_MAC_VER_10,
-	RTL_GIGA_MAC_VER_11,
+	/* support for RTL_GIGA_MAC_VER_11 has been removed */
 	/* RTL_GIGA_MAC_VER_12 was handled the same as VER_17 */
 	/* RTL_GIGA_MAC_VER_13 was merged with VER_10 */
 	RTL_GIGA_MAC_VER_14,
@@ -64,14 +64,15 @@ enum mac_version {
 	/* support for RTL_GIGA_MAC_VER_50 has been removed */
 	RTL_GIGA_MAC_VER_51,
 	RTL_GIGA_MAC_VER_52,
-	RTL_GIGA_MAC_VER_53,
 	/* support for RTL_GIGA_MAC_VER_60 has been removed */
 	RTL_GIGA_MAC_VER_61,
 	RTL_GIGA_MAC_VER_63,
 	RTL_GIGA_MAC_VER_64,
-	RTL_GIGA_MAC_VER_65,
 	RTL_GIGA_MAC_VER_66,
-	RTL_GIGA_MAC_NONE
+	RTL_GIGA_MAC_VER_70,
+	RTL_GIGA_MAC_VER_80,
+	RTL_GIGA_MAC_NONE,
+	RTL_GIGA_MAC_VER_LAST = RTL_GIGA_MAC_NONE - 1
 };
 
 struct rtl8169_private;
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 739707a7b40f..43170500d566 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -16,7 +16,6 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/ethtool.h>
-#include <linux/hwmon.h>
 #include <linux/phy.h>
 #include <linux/if_vlan.h>
 #include <linux/in.h>
@@ -57,8 +56,11 @@
 #define FIRMWARE_8125A_3	"rtl_nic/rtl8125a-3.fw"
 #define FIRMWARE_8125B_2	"rtl_nic/rtl8125b-2.fw"
 #define FIRMWARE_8125D_1	"rtl_nic/rtl8125d-1.fw"
+#define FIRMWARE_8125D_2	"rtl_nic/rtl8125d-2.fw"
+#define FIRMWARE_8125BP_2	"rtl_nic/rtl8125bp-2.fw"
 #define FIRMWARE_8126A_2	"rtl_nic/rtl8126a-2.fw"
 #define FIRMWARE_8126A_3	"rtl_nic/rtl8126a-3.fw"
+#define FIRMWARE_8127A_1	"rtl_nic/rtl8127a-1.fw"
 
 #define TX_DMA_BURST	7	/* Maximum PCI burst, '7' is unlimited */
 #define InterFrameGap	0x03	/* 3 means InterFrameGap = the shortest one */
@@ -88,61 +90,119 @@
 #define JUMBO_6K	(6 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 #define JUMBO_7K	(7 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 #define JUMBO_9K	(9 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
+#define JUMBO_16K	(SZ_16K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 
-static const struct {
+static const struct rtl_chip_info {
+	u16 mask;
+	u16 val;
+	enum mac_version mac_version;
 	const char *name;
 	const char *fw_name;
 } rtl_chip_infos[] = {
-	/* PCI devices. */
-	[RTL_GIGA_MAC_VER_02] = {"RTL8169s"				},
-	[RTL_GIGA_MAC_VER_03] = {"RTL8110s"				},
-	[RTL_GIGA_MAC_VER_04] = {"RTL8169sb/8110sb"			},
-	[RTL_GIGA_MAC_VER_05] = {"RTL8169sc/8110sc"			},
-	[RTL_GIGA_MAC_VER_06] = {"RTL8169sc/8110sc"			},
-	/* PCI-E devices. */
-	[RTL_GIGA_MAC_VER_07] = {"RTL8102e"				},
-	[RTL_GIGA_MAC_VER_08] = {"RTL8102e"				},
-	[RTL_GIGA_MAC_VER_09] = {"RTL8102e/RTL8103e"			},
-	[RTL_GIGA_MAC_VER_10] = {"RTL8101e/RTL8100e"			},
-	[RTL_GIGA_MAC_VER_11] = {"RTL8168b/8111b"			},
-	[RTL_GIGA_MAC_VER_14] = {"RTL8401"				},
-	[RTL_GIGA_MAC_VER_17] = {"RTL8168b/8111b"			},
-	[RTL_GIGA_MAC_VER_18] = {"RTL8168cp/8111cp"			},
-	[RTL_GIGA_MAC_VER_19] = {"RTL8168c/8111c"			},
-	[RTL_GIGA_MAC_VER_20] = {"RTL8168c/8111c"			},
-	[RTL_GIGA_MAC_VER_21] = {"RTL8168c/8111c"			},
-	[RTL_GIGA_MAC_VER_22] = {"RTL8168c/8111c"			},
-	[RTL_GIGA_MAC_VER_23] = {"RTL8168cp/8111cp"			},
-	[RTL_GIGA_MAC_VER_24] = {"RTL8168cp/8111cp"			},
-	[RTL_GIGA_MAC_VER_25] = {"RTL8168d/8111d",	FIRMWARE_8168D_1},
-	[RTL_GIGA_MAC_VER_26] = {"RTL8168d/8111d",	FIRMWARE_8168D_2},
-	[RTL_GIGA_MAC_VER_28] = {"RTL8168dp/8111dp"			},
-	[RTL_GIGA_MAC_VER_29] = {"RTL8105e",		FIRMWARE_8105E_1},
-	[RTL_GIGA_MAC_VER_30] = {"RTL8105e",		FIRMWARE_8105E_1},
-	[RTL_GIGA_MAC_VER_31] = {"RTL8168dp/8111dp"			},
-	[RTL_GIGA_MAC_VER_32] = {"RTL8168e/8111e",	FIRMWARE_8168E_1},
-	[RTL_GIGA_MAC_VER_33] = {"RTL8168e/8111e",	FIRMWARE_8168E_2},
-	[RTL_GIGA_MAC_VER_34] = {"RTL8168evl/8111evl",	FIRMWARE_8168E_3},
-	[RTL_GIGA_MAC_VER_35] = {"RTL8168f/8111f",	FIRMWARE_8168F_1},
-	[RTL_GIGA_MAC_VER_36] = {"RTL8168f/8111f",	FIRMWARE_8168F_2},
-	[RTL_GIGA_MAC_VER_37] = {"RTL8402",		FIRMWARE_8402_1 },
-	[RTL_GIGA_MAC_VER_38] = {"RTL8411",		FIRMWARE_8411_1 },
-	[RTL_GIGA_MAC_VER_39] = {"RTL8106e",		FIRMWARE_8106E_1},
-	[RTL_GIGA_MAC_VER_40] = {"RTL8168g/8111g",	FIRMWARE_8168G_2},
-	[RTL_GIGA_MAC_VER_42] = {"RTL8168gu/8111gu",	FIRMWARE_8168G_3},
-	[RTL_GIGA_MAC_VER_43] = {"RTL8106eus",		FIRMWARE_8106E_2},
-	[RTL_GIGA_MAC_VER_44] = {"RTL8411b",		FIRMWARE_8411_2 },
-	[RTL_GIGA_MAC_VER_46] = {"RTL8168h/8111h",	FIRMWARE_8168H_2},
-	[RTL_GIGA_MAC_VER_48] = {"RTL8107e",		FIRMWARE_8107E_2},
-	[RTL_GIGA_MAC_VER_51] = {"RTL8168ep/8111ep"			},
-	[RTL_GIGA_MAC_VER_52] = {"RTL8168fp/RTL8117",  FIRMWARE_8168FP_3},
-	[RTL_GIGA_MAC_VER_53] = {"RTL8168fp/RTL8117",			},
-	[RTL_GIGA_MAC_VER_61] = {"RTL8125A",		FIRMWARE_8125A_3},
-	/* reserve 62 for CFG_METHOD_4 in the vendor driver */
-	[RTL_GIGA_MAC_VER_63] = {"RTL8125B",		FIRMWARE_8125B_2},
-	[RTL_GIGA_MAC_VER_64] = {"RTL8125D",		FIRMWARE_8125D_1},
-	[RTL_GIGA_MAC_VER_65] = {"RTL8126A",		FIRMWARE_8126A_2},
-	[RTL_GIGA_MAC_VER_66] = {"RTL8126A",		FIRMWARE_8126A_3},
+	/* 8127A family. */
+	{ 0x7cf, 0x6c9,	RTL_GIGA_MAC_VER_80, "RTL8127A", FIRMWARE_8127A_1 },
+
+	/* 8126A family. */
+	{ 0x7cf, 0x64a,	RTL_GIGA_MAC_VER_70, "RTL8126A", FIRMWARE_8126A_3 },
+	{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_70, "RTL8126A", FIRMWARE_8126A_2 },
+
+	/* 8125BP family. */
+	{ 0x7cf, 0x681,	RTL_GIGA_MAC_VER_66, "RTL8125BP", FIRMWARE_8125BP_2 },
+
+	/* 8125D family. */
+	{ 0x7cf, 0x689,	RTL_GIGA_MAC_VER_64, "RTL8125D", FIRMWARE_8125D_2 },
+	{ 0x7cf, 0x688,	RTL_GIGA_MAC_VER_64, "RTL8125D", FIRMWARE_8125D_1 },
+
+	/* 8125B family. */
+	{ 0x7cf, 0x641,	RTL_GIGA_MAC_VER_63, "RTL8125B", FIRMWARE_8125B_2 },
+
+	/* 8125A family. */
+	{ 0x7cf, 0x609,	RTL_GIGA_MAC_VER_61, "RTL8125A", FIRMWARE_8125A_3 },
+
+	/* RTL8117 */
+	{ 0x7cf, 0x54b,	RTL_GIGA_MAC_VER_52, "RTL8168fp/RTL8117" },
+	{ 0x7cf, 0x54a,	RTL_GIGA_MAC_VER_52, "RTL8168fp/RTL8117",
+	  FIRMWARE_8168FP_3 },
+
+	/* 8168EP family. */
+	{ 0x7cf, 0x502,	RTL_GIGA_MAC_VER_51, "RTL8168ep/8111ep" },
+
+	/* 8168H family. */
+	{ 0x7cf, 0x541,	RTL_GIGA_MAC_VER_46, "RTL8168h/8111h",
+	  FIRMWARE_8168H_2 },
+	/* Realtek calls it RTL8168M, but it's handled like RTL8168H */
+	{ 0x7cf, 0x6c0,	RTL_GIGA_MAC_VER_46, "RTL8168M", FIRMWARE_8168H_2 },
+
+	/* 8168G family. */
+	{ 0x7cf, 0x5c8,	RTL_GIGA_MAC_VER_44, "RTL8411b", FIRMWARE_8411_2 },
+	{ 0x7cf, 0x509,	RTL_GIGA_MAC_VER_42, "RTL8168gu/8111gu",
+	  FIRMWARE_8168G_3 },
+	{ 0x7cf, 0x4c0,	RTL_GIGA_MAC_VER_40, "RTL8168g/8111g",
+	  FIRMWARE_8168G_2 },
+
+	/* 8168F family. */
+	{ 0x7c8, 0x488,	RTL_GIGA_MAC_VER_38, "RTL8411", FIRMWARE_8411_1 },
+	{ 0x7cf, 0x481,	RTL_GIGA_MAC_VER_36, "RTL8168f/8111f",
+	  FIRMWARE_8168F_2 },
+	{ 0x7cf, 0x480,	RTL_GIGA_MAC_VER_35, "RTL8168f/8111f",
+	  FIRMWARE_8168F_1 },
+
+	/* 8168E family. */
+	{ 0x7c8, 0x2c8,	RTL_GIGA_MAC_VER_34, "RTL8168evl/8111evl",
+	  FIRMWARE_8168E_3 },
+	{ 0x7cf, 0x2c1,	RTL_GIGA_MAC_VER_32, "RTL8168e/8111e",
+	  FIRMWARE_8168E_1 },
+	{ 0x7c8, 0x2c0,	RTL_GIGA_MAC_VER_33, "RTL8168e/8111e",
+	  FIRMWARE_8168E_2 },
+
+	/* 8168D family. */
+	{ 0x7cf, 0x281,	RTL_GIGA_MAC_VER_25, "RTL8168d/8111d",
+	  FIRMWARE_8168D_1 },
+	{ 0x7c8, 0x280,	RTL_GIGA_MAC_VER_26, "RTL8168d/8111d",
+	  FIRMWARE_8168D_2 },
+
+	/* 8168DP family. */
+	{ 0x7cf, 0x28a,	RTL_GIGA_MAC_VER_28, "RTL8168dp/8111dp" },
+	{ 0x7cf, 0x28b,	RTL_GIGA_MAC_VER_31, "RTL8168dp/8111dp" },
+
+	/* 8168C family. */
+	{ 0x7cf, 0x3c9,	RTL_GIGA_MAC_VER_23, "RTL8168cp/8111cp" },
+	{ 0x7cf, 0x3c8,	RTL_GIGA_MAC_VER_18, "RTL8168cp/8111cp" },
+	{ 0x7c8, 0x3c8,	RTL_GIGA_MAC_VER_24, "RTL8168cp/8111cp" },
+	{ 0x7cf, 0x3c0,	RTL_GIGA_MAC_VER_19, "RTL8168c/8111c" },
+	{ 0x7cf, 0x3c2,	RTL_GIGA_MAC_VER_20, "RTL8168c/8111c" },
+	{ 0x7cf, 0x3c3,	RTL_GIGA_MAC_VER_21, "RTL8168c/8111c" },
+	{ 0x7c8, 0x3c0,	RTL_GIGA_MAC_VER_22, "RTL8168c/8111c" },
+
+	/* 8168B family. */
+	{ 0x7c8, 0x380,	RTL_GIGA_MAC_VER_17, "RTL8168b/8111b" },
+	/* This one is very old and rare, support has been removed.
+	 * { 0x7c8, 0x300, RTL_GIGA_MAC_VER_11, "RTL8168b/8111b" },
+	 */
+
+	/* 8101 family. */
+	{ 0x7c8, 0x448,	RTL_GIGA_MAC_VER_39, "RTL8106e", FIRMWARE_8106E_1 },
+	{ 0x7c8, 0x440,	RTL_GIGA_MAC_VER_37, "RTL8402", FIRMWARE_8402_1 },
+	{ 0x7cf, 0x409,	RTL_GIGA_MAC_VER_29, "RTL8105e", FIRMWARE_8105E_1 },
+	{ 0x7c8, 0x408,	RTL_GIGA_MAC_VER_30, "RTL8105e", FIRMWARE_8105E_1 },
+	{ 0x7cf, 0x349,	RTL_GIGA_MAC_VER_08, "RTL8102e" },
+	{ 0x7cf, 0x249,	RTL_GIGA_MAC_VER_08, "RTL8102e" },
+	{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07, "RTL8102e" },
+	{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07, "RTL8102e" },
+	{ 0x7cf, 0x240,	RTL_GIGA_MAC_VER_14, "RTL8401" },
+	{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09, "RTL8102e/RTL8103e" },
+	{ 0x7c8, 0x248,	RTL_GIGA_MAC_VER_09, "RTL8102e/RTL8103e" },
+	{ 0x7c8, 0x340,	RTL_GIGA_MAC_VER_10, "RTL8101e/RTL8100e" },
+
+	/* 8110 family. */
+	{ 0xfc8, 0x980,	RTL_GIGA_MAC_VER_06, "RTL8169sc/8110sc" },
+	{ 0xfc8, 0x180,	RTL_GIGA_MAC_VER_05, "RTL8169sc/8110sc" },
+	{ 0xfc8, 0x100,	RTL_GIGA_MAC_VER_04, "RTL8169sb/8110sb" },
+	{ 0xfc8, 0x040,	RTL_GIGA_MAC_VER_03, "RTL8110s" },
+	{ 0xfc8, 0x008,	RTL_GIGA_MAC_VER_02, "RTL8169s" },
+
+	/* Catch-all */
+	{ 0x000, 0x000,	RTL_GIGA_MAC_NONE }
 };
 
 static const struct pci_device_id rtl8169_pci_tbl[] = {
@@ -166,7 +226,10 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ 0x0001, 0x8168, PCI_ANY_ID, 0x2410 },
 	{ PCI_VDEVICE(REALTEK,	0x8125) },
 	{ PCI_VDEVICE(REALTEK,	0x8126) },
+	{ PCI_VDEVICE(REALTEK,	0x8127) },
 	{ PCI_VDEVICE(REALTEK,	0x3000) },
+	{ PCI_VDEVICE(REALTEK,	0x5000) },
+	{ PCI_VDEVICE(REALTEK,	0x0e10) },
 	{}
 };
 
@@ -623,7 +686,6 @@ struct rtl8169_tc_offsets {
 
 enum rtl_flag {
 	RTL_FLAG_TASK_RESET_PENDING,
-	RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE,
 	RTL_FLAG_TASK_TX_TIMEOUT,
 	RTL_FLAG_MAX
 };
@@ -632,6 +694,7 @@ enum rtl_dash_type {
 	RTL_DASH_NONE,
 	RTL_DASH_DP,
 	RTL_DASH_EP,
+	RTL_DASH_25_BP,
 };
 
 struct rtl8169_private {
@@ -708,8 +771,11 @@ MODULE_FIRMWARE(FIRMWARE_8107E_2);
 MODULE_FIRMWARE(FIRMWARE_8125A_3);
 MODULE_FIRMWARE(FIRMWARE_8125B_2);
 MODULE_FIRMWARE(FIRMWARE_8125D_1);
+MODULE_FIRMWARE(FIRMWARE_8125D_2);
+MODULE_FIRMWARE(FIRMWARE_8125BP_2);
 MODULE_FIRMWARE(FIRMWARE_8126A_2);
 MODULE_FIRMWARE(FIRMWARE_8126A_3);
+MODULE_FIRMWARE(FIRMWARE_8127A_1);
 
 static inline struct device *tp_to_dev(struct rtl8169_private *tp)
 {
@@ -771,7 +837,7 @@ static bool rtl_is_8168evl_up(struct rtl8169_private *tp)
 {
 	return tp->mac_version >= RTL_GIGA_MAC_VER_34 &&
 	       tp->mac_version != RTL_GIGA_MAC_VER_39 &&
-	       tp->mac_version <= RTL_GIGA_MAC_VER_53;
+	       tp->mac_version <= RTL_GIGA_MAC_VER_52;
 }
 
 static bool rtl_supports_eee(struct rtl8169_private *tp)
@@ -939,9 +1005,7 @@ void r8169_get_led_name(struct rtl8169_private *tp, int idx,
 static void r8168fp_adjust_ocp_cmd(struct rtl8169_private *tp, u32 *cmd, int type)
 {
 	/* based on RTL8168FP_OOBMAC_BASE in vendor driver */
-	if (type == ERIAR_OOB &&
-	    (tp->mac_version == RTL_GIGA_MAC_VER_52 ||
-	     tp->mac_version == RTL_GIGA_MAC_VER_53))
+	if (type == ERIAR_OOB && tp->mac_version == RTL_GIGA_MAC_VER_52)
 		*cmd |= 0xf70 << 18;
 }
 
@@ -1230,7 +1294,7 @@ static void rtl_writephy(struct rtl8169_private *tp, int location, int val)
 	case RTL_GIGA_MAC_VER_31:
 		r8168dp_2_mdio_write(tp, location, val);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		r8168g_mdio_write(tp, location, val);
 		break;
 	default:
@@ -1245,7 +1309,7 @@ static int rtl_readphy(struct rtl8169_private *tp, int location)
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
 		return r8168dp_2_mdio_read(tp, location);
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		return r8168g_mdio_read(tp, location);
 	default:
 		return r8169_mdio_read(tp, location);
@@ -1360,10 +1424,19 @@ static void rtl8168ep_driver_start(struct rtl8169_private *tp)
 		rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30);
 }
 
+static void rtl8125bp_driver_start(struct rtl8169_private *tp)
+{
+	r8168ep_ocp_write(tp, 0x01, 0x14, OOB_CMD_DRIVER_START);
+	r8168ep_ocp_write(tp, 0x01, 0x18, 0x00);
+	r8168ep_ocp_write(tp, 0x01, 0x10, 0x01);
+}
+
 static void rtl8168_driver_start(struct rtl8169_private *tp)
 {
 	if (tp->dash_type == RTL_DASH_DP)
 		rtl8168dp_driver_start(tp);
+	else if (tp->dash_type == RTL_DASH_25_BP)
+		rtl8125bp_driver_start(tp);
 	else
 		rtl8168ep_driver_start(tp);
 }
@@ -1384,10 +1457,19 @@ static void rtl8168ep_driver_stop(struct rtl8169_private *tp)
 		rtl_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10);
 }
 
+static void rtl8125bp_driver_stop(struct rtl8169_private *tp)
+{
+	r8168ep_ocp_write(tp, 0x01, 0x14, OOB_CMD_DRIVER_STOP);
+	r8168ep_ocp_write(tp, 0x01, 0x18, 0x00);
+	r8168ep_ocp_write(tp, 0x01, 0x10, 0x01);
+}
+
 static void rtl8168_driver_stop(struct rtl8169_private *tp)
 {
 	if (tp->dash_type == RTL_DASH_DP)
 		rtl8168dp_driver_stop(tp);
+	else if (tp->dash_type == RTL_DASH_25_BP)
+		rtl8125bp_driver_stop(tp);
 	else
 		rtl8168ep_driver_stop(tp);
 }
@@ -1410,6 +1492,7 @@ static bool rtl_dash_is_enabled(struct rtl8169_private *tp)
 	case RTL_DASH_DP:
 		return r8168dp_check_dash(tp);
 	case RTL_DASH_EP:
+	case RTL_DASH_25_BP:
 		return r8168ep_check_dash(tp);
 	default:
 		return false;
@@ -1422,8 +1505,10 @@ static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
 		return RTL_DASH_DP;
-	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53:
+	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_52:
 		return RTL_DASH_EP;
+	case RTL_GIGA_MAC_VER_66:
+		return RTL_DASH_25_BP;
 	default:
 		return RTL_DASH_NONE;
 	}
@@ -1576,7 +1661,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 		break;
 	case RTL_GIGA_MAC_VER_34:
 	case RTL_GIGA_MAC_VER_37:
-	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_LAST:
 		r8169_mod_reg8_cond(tp, Config2, PME_SIGNAL, wolopts);
 		break;
 	default:
@@ -2049,7 +2134,7 @@ static void rtl_set_eee_txidle_timer(struct rtl8169_private *tp)
 		tp->tx_lpi_timer = timer_val;
 		r8168_mac_ocp_write(tp, 0xe048, timer_val);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 		tp->tx_lpi_timer = timer_val;
 		RTL_W16(tp, EEE_TXIDLE_TIMER_8125, timer_val);
 		break;
@@ -2238,147 +2323,30 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_eth_ctrl_stats	= rtl8169_get_eth_ctrl_stats,
 };
 
-static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
+static const struct rtl_chip_info *rtl8169_get_chip_version(u16 xid, bool gmii)
 {
-	/*
-	 * The driver currently handles the 8168Bf and the 8168Be identically
-	 * but they can be identified more specifically through the test below
-	 * if needed:
-	 *
-	 * (RTL_R32(tp, TxConfig) & 0x700000) == 0x500000 ? 8168Bf : 8168Be
-	 *
-	 * Same thing for the 8101Eb and the 8101Ec:
-	 *
-	 * (RTL_R32(tp, TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec
-	 */
-	static const struct rtl_mac_info {
-		u16 mask;
-		u16 val;
-		enum mac_version ver;
-	} mac_info[] = {
-		/* 8126A family. */
-		{ 0x7cf, 0x64a,	RTL_GIGA_MAC_VER_66 },
-		{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_65 },
-
-		/* 8125D family. */
-		{ 0x7cf, 0x688,	RTL_GIGA_MAC_VER_64 },
-
-		/* 8125B family. */
-		{ 0x7cf, 0x641,	RTL_GIGA_MAC_VER_63 },
-
-		/* 8125A family. */
-		{ 0x7cf, 0x609,	RTL_GIGA_MAC_VER_61 },
-		/* It seems only XID 609 made it to the mass market.
-		 * { 0x7cf, 0x608,	RTL_GIGA_MAC_VER_60 },
-		 * { 0x7c8, 0x608,	RTL_GIGA_MAC_VER_61 },
-		 */
-
-		/* RTL8117 */
-		{ 0x7cf, 0x54b,	RTL_GIGA_MAC_VER_53 },
-		{ 0x7cf, 0x54a,	RTL_GIGA_MAC_VER_52 },
-
-		/* 8168EP family. */
-		{ 0x7cf, 0x502,	RTL_GIGA_MAC_VER_51 },
-		/* It seems this chip version never made it to
-		 * the wild. Let's disable detection.
-		 * { 0x7cf, 0x501,      RTL_GIGA_MAC_VER_50 },
-		 * { 0x7cf, 0x500,      RTL_GIGA_MAC_VER_49 },
-		 */
-
-		/* 8168H family. */
-		{ 0x7cf, 0x541,	RTL_GIGA_MAC_VER_46 },
-		/* It seems this chip version never made it to
-		 * the wild. Let's disable detection.
-		 * { 0x7cf, 0x540,	RTL_GIGA_MAC_VER_45 },
-		 */
-		/* Realtek calls it RTL8168M, but it's handled like RTL8168H */
-		{ 0x7cf, 0x6c0,	RTL_GIGA_MAC_VER_46 },
-
-		/* 8168G family. */
-		{ 0x7cf, 0x5c8,	RTL_GIGA_MAC_VER_44 },
-		{ 0x7cf, 0x509,	RTL_GIGA_MAC_VER_42 },
-		/* It seems this chip version never made it to
-		 * the wild. Let's disable detection.
-		 * { 0x7cf, 0x4c1,	RTL_GIGA_MAC_VER_41 },
-		 */
-		{ 0x7cf, 0x4c0,	RTL_GIGA_MAC_VER_40 },
-
-		/* 8168F family. */
-		{ 0x7c8, 0x488,	RTL_GIGA_MAC_VER_38 },
-		{ 0x7cf, 0x481,	RTL_GIGA_MAC_VER_36 },
-		{ 0x7cf, 0x480,	RTL_GIGA_MAC_VER_35 },
-
-		/* 8168E family. */
-		{ 0x7c8, 0x2c8,	RTL_GIGA_MAC_VER_34 },
-		{ 0x7cf, 0x2c1,	RTL_GIGA_MAC_VER_32 },
-		{ 0x7c8, 0x2c0,	RTL_GIGA_MAC_VER_33 },
-
-		/* 8168D family. */
-		{ 0x7cf, 0x281,	RTL_GIGA_MAC_VER_25 },
-		{ 0x7c8, 0x280,	RTL_GIGA_MAC_VER_26 },
-
-		/* 8168DP family. */
-		/* It seems this early RTL8168dp version never made it to
-		 * the wild. Support has been removed.
-		 * { 0x7cf, 0x288,      RTL_GIGA_MAC_VER_27 },
-		 */
-		{ 0x7cf, 0x28a,	RTL_GIGA_MAC_VER_28 },
-		{ 0x7cf, 0x28b,	RTL_GIGA_MAC_VER_31 },
-
-		/* 8168C family. */
-		{ 0x7cf, 0x3c9,	RTL_GIGA_MAC_VER_23 },
-		{ 0x7cf, 0x3c8,	RTL_GIGA_MAC_VER_18 },
-		{ 0x7c8, 0x3c8,	RTL_GIGA_MAC_VER_24 },
-		{ 0x7cf, 0x3c0,	RTL_GIGA_MAC_VER_19 },
-		{ 0x7cf, 0x3c2,	RTL_GIGA_MAC_VER_20 },
-		{ 0x7cf, 0x3c3,	RTL_GIGA_MAC_VER_21 },
-		{ 0x7c8, 0x3c0,	RTL_GIGA_MAC_VER_22 },
-
-		/* 8168B family. */
-		{ 0x7c8, 0x380,	RTL_GIGA_MAC_VER_17 },
-		/* This one is very old and rare, let's see if anybody complains.
-		 * { 0x7c8, 0x300,	RTL_GIGA_MAC_VER_11 },
-		 */
-
-		/* 8101 family. */
-		{ 0x7c8, 0x448,	RTL_GIGA_MAC_VER_39 },
-		{ 0x7c8, 0x440,	RTL_GIGA_MAC_VER_37 },
-		{ 0x7cf, 0x409,	RTL_GIGA_MAC_VER_29 },
-		{ 0x7c8, 0x408,	RTL_GIGA_MAC_VER_30 },
-		{ 0x7cf, 0x349,	RTL_GIGA_MAC_VER_08 },
-		{ 0x7cf, 0x249,	RTL_GIGA_MAC_VER_08 },
-		{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07 },
-		{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07 },
-		{ 0x7cf, 0x240,	RTL_GIGA_MAC_VER_14 },
-		{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09 },
-		{ 0x7c8, 0x248,	RTL_GIGA_MAC_VER_09 },
-		{ 0x7c8, 0x340,	RTL_GIGA_MAC_VER_10 },
-
-		/* 8110 family. */
-		{ 0xfc8, 0x980,	RTL_GIGA_MAC_VER_06 },
-		{ 0xfc8, 0x180,	RTL_GIGA_MAC_VER_05 },
-		{ 0xfc8, 0x100,	RTL_GIGA_MAC_VER_04 },
-		{ 0xfc8, 0x040,	RTL_GIGA_MAC_VER_03 },
-		{ 0xfc8, 0x008,	RTL_GIGA_MAC_VER_02 },
-
-		/* Catch-all */
-		{ 0x000, 0x000,	RTL_GIGA_MAC_NONE   }
+	/* Chips combining a 1Gbps MAC with a 100Mbps PHY */
+	static const struct rtl_chip_info rtl8106eus_info = {
+		.mac_version = RTL_GIGA_MAC_VER_43,
+		.name = "RTL8106eus",
+		.fw_name = FIRMWARE_8106E_2,
+	};
+	static const struct rtl_chip_info rtl8107e_info = {
+		.mac_version = RTL_GIGA_MAC_VER_48,
+		.name = "RTL8107e",
+		.fw_name = FIRMWARE_8107E_2,
 	};
-	const struct rtl_mac_info *p = mac_info;
-	enum mac_version ver;
+	const struct rtl_chip_info *p = rtl_chip_infos;
 
 	while ((xid & p->mask) != p->val)
 		p++;
-	ver = p->ver;
 
-	if (ver != RTL_GIGA_MAC_NONE && !gmii) {
-		if (ver == RTL_GIGA_MAC_VER_42)
-			ver = RTL_GIGA_MAC_VER_43;
-		else if (ver == RTL_GIGA_MAC_VER_46)
-			ver = RTL_GIGA_MAC_VER_48;
-	}
+	if (p->mac_version == RTL_GIGA_MAC_VER_42 && !gmii)
+		return &rtl8106eus_info;
+	if (p->mac_version == RTL_GIGA_MAC_VER_46 && !gmii)
+		return &rtl8107e_info;
 
-	return ver;
+	return p;
 }
 
 static void rtl_release_firmware(struct rtl8169_private *tp)
@@ -2522,13 +2490,13 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_38:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
 		break;
 	case RTL_GIGA_MAC_VER_61:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST);
 		break;
-	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_LAST:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST |
 			RX_PAUSE_SLOT_ON);
 		break;
@@ -2653,14 +2621,14 @@ DECLARE_RTL_COND(rtl_rxtx_empty_cond_2)
 static void rtl_wait_txrx_fifo_empty(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52:
 		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		break;
 	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_61:
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		break;
-	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_LAST:
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond_2, 100, 42);
@@ -2821,10 +2789,45 @@ static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
 		RTL_R32(tp, CSIDR) : ~0;
 }
 
+static void rtl_csi_mod(struct rtl8169_private *tp, int addr,
+			u32 mask, u32 set)
+{
+	u32 val;
+
+	WARN(addr % 4, "Invalid CSI address %#x\n", addr);
+
+	netdev_notice_once(tp->dev,
+		"No native access to PCI extended config space, falling back to CSI\n");
+
+	val = rtl_csi_read(tp, addr);
+	rtl_csi_write(tp, addr, (val & ~mask) | set);
+}
+
+static void rtl_disable_zrxdc_timeout(struct rtl8169_private *tp)
+{
+	struct pci_dev *pdev = tp->pci_dev;
+	int rc;
+	u8 val;
+
+#define RTL_GEN3_RELATED_OFF	0x0890
+#define RTL_GEN3_ZRXDC_NONCOMPL	0x1
+	if (pdev->cfg_size > RTL_GEN3_RELATED_OFF) {
+		rc = pci_read_config_byte(pdev, RTL_GEN3_RELATED_OFF, &val);
+		if (rc == PCIBIOS_SUCCESSFUL) {
+			val &= ~RTL_GEN3_ZRXDC_NONCOMPL;
+			rc = pci_write_config_byte(pdev, RTL_GEN3_RELATED_OFF,
+						   val);
+			if (rc == PCIBIOS_SUCCESSFUL)
+				return;
+		}
+	}
+
+	rtl_csi_mod(tp, RTL_GEN3_RELATED_OFF, RTL_GEN3_ZRXDC_NONCOMPL, 0);
+}
+
 static void rtl_set_aspm_entry_latency(struct rtl8169_private *tp, u8 val)
 {
 	struct pci_dev *pdev = tp->pci_dev;
-	u32 csi;
 
 	/* According to Realtek the value at config space address 0x070f
 	 * controls the L0s/L1 entrance latency. We try standard ECAM access
@@ -2836,10 +2839,7 @@ static void rtl_set_aspm_entry_latency(struct rtl8169_private *tp, u8 val)
 	    pci_write_config_byte(pdev, 0x070f, val) == PCIBIOS_SUCCESSFUL)
 		return;
 
-	netdev_notice_once(tp->dev,
-		"No native access to PCI extended config space, falling back to CSI\n");
-	csi = rtl_csi_read(tp, 0x070c) & 0x00ffffff;
-	rtl_csi_write(tp, 0x070c, csi | val << 24);
+	rtl_csi_mod(tp, 0x070c, 0xff000000, val << 24);
 }
 
 static void rtl_set_def_aspm_entry_latency(struct rtl8169_private *tp)
@@ -2903,7 +2903,7 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38:
 		rtl_eri_set_bits(tp, 0xd4, 0x0c00);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80);
 		break;
 	default:
@@ -2917,7 +2917,7 @@ static void rtl_disable_exit_l1(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
 		rtl_eri_clear_bits(tp, 0xd4, 0x1f00);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0);
 		break;
 	default:
@@ -2943,8 +2943,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 
 		rtl_mod_config5(tp, 0, ASPM_en);
 		switch (tp->mac_version) {
-		case RTL_GIGA_MAC_VER_65:
-		case RTL_GIGA_MAC_VER_66:
+		case RTL_GIGA_MAC_VER_70:
+		case RTL_GIGA_MAC_VER_80:
 			val8 = RTL_R8(tp, INT_CFG0_8125) | INT_CFG0_CLKREQEN;
 			RTL_W8(tp, INT_CFG0_8125, val8);
 			break;
@@ -2955,7 +2955,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
-		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 			/* reset ephy tx/rx disable timer */
 			r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0);
 			/* chip can trigger L1.2 */
@@ -2967,7 +2967,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 	} else {
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
-		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 			r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0);
 			break;
 		default:
@@ -2975,8 +2975,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 		}
 
 		switch (tp->mac_version) {
-		case RTL_GIGA_MAC_VER_65:
-		case RTL_GIGA_MAC_VER_66:
+		case RTL_GIGA_MAC_VER_70:
+		case RTL_GIGA_MAC_VER_80:
 			val8 = RTL_R8(tp, INT_CFG0_8125) & ~INT_CFG0_CLKREQEN;
 			RTL_W8(tp, INT_CFG0_8125, val8);
 			break;
@@ -3696,12 +3696,13 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	/* disable new tx descriptor format */
 	r8168_mac_ocp_modify(tp, 0xeb58, 0x0001, 0x0000);
 
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_66)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_70 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_80)
 		RTL_W8(tp, 0xD8, RTL_R8(tp, 0xD8) & ~0x02);
 
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_66)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_80)
+		r8168_mac_ocp_modify(tp, 0xe614, 0x0f00, 0x0f00);
+	else if (tp->mac_version == RTL_GIGA_MAC_VER_70)
 		r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0400);
 	else if (tp->mac_version == RTL_GIGA_MAC_VER_63)
 		r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0200);
@@ -3719,8 +3720,8 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0030);
 	r8168_mac_ocp_modify(tp, 0xe040, 0x1000, 0x0000);
 	r8168_mac_ocp_modify(tp, 0xea1c, 0x0003, 0x0001);
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_66)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_70 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_80)
 		r8168_mac_ocp_modify(tp, 0xea1c, 0x0300, 0x0000);
 	else
 		r8168_mac_ocp_modify(tp, 0xea1c, 0x0004, 0x0000);
@@ -3793,6 +3794,13 @@ static void rtl_hw_start_8125d(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8126a(struct rtl8169_private *tp)
 {
+	rtl_disable_zrxdc_timeout(tp);
+	rtl_set_def_aspm_entry_latency(tp);
+	rtl_hw_start_8125_common(tp);
+}
+
+static void rtl_hw_start_8127a(struct rtl8169_private *tp)
+{
 	rtl_set_def_aspm_entry_latency(tp);
 	rtl_hw_start_8125_common(tp);
 }
@@ -3804,7 +3812,6 @@ static void rtl_hw_config(struct rtl8169_private *tp)
 		[RTL_GIGA_MAC_VER_08] = rtl_hw_start_8102e_3,
 		[RTL_GIGA_MAC_VER_09] = rtl_hw_start_8102e_2,
 		[RTL_GIGA_MAC_VER_10] = NULL,
-		[RTL_GIGA_MAC_VER_11] = rtl_hw_start_8168b,
 		[RTL_GIGA_MAC_VER_14] = rtl_hw_start_8401,
 		[RTL_GIGA_MAC_VER_17] = rtl_hw_start_8168b,
 		[RTL_GIGA_MAC_VER_18] = rtl_hw_start_8168cp_1,
@@ -3836,12 +3843,12 @@ static void rtl_hw_config(struct rtl8169_private *tp)
 		[RTL_GIGA_MAC_VER_48] = rtl_hw_start_8168h_1,
 		[RTL_GIGA_MAC_VER_51] = rtl_hw_start_8168ep_3,
 		[RTL_GIGA_MAC_VER_52] = rtl_hw_start_8117,
-		[RTL_GIGA_MAC_VER_53] = rtl_hw_start_8117,
 		[RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2,
 		[RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b,
 		[RTL_GIGA_MAC_VER_64] = rtl_hw_start_8125d,
-		[RTL_GIGA_MAC_VER_65] = rtl_hw_start_8126a,
-		[RTL_GIGA_MAC_VER_66] = rtl_hw_start_8126a,
+		[RTL_GIGA_MAC_VER_66] = rtl_hw_start_8125d,
+		[RTL_GIGA_MAC_VER_70] = rtl_hw_start_8126a,
+		[RTL_GIGA_MAC_VER_80] = rtl_hw_start_8127a,
 	};
 
 	if (hw_configs[tp->mac_version])
@@ -3858,12 +3865,15 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp)
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_61:
 	case RTL_GIGA_MAC_VER_64:
+	case RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_80:
 		for (i = 0xa00; i < 0xb00; i += 4)
 			RTL_W32(tp, i, 0);
+		if (tp->mac_version == RTL_GIGA_MAC_VER_80)
+			RTL_W16(tp, INT_CFG1_8125, 0x0000);
 		break;
 	case RTL_GIGA_MAC_VER_63:
-	case RTL_GIGA_MAC_VER_65:
-	case RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_70:
 		for (i = 0xa00; i < 0xa80; i += 4)
 			RTL_W32(tp, i, 0);
 		RTL_W16(tp, INT_CFG1_8125, 0x0000);
@@ -4095,7 +4105,7 @@ static void rtl8169_cleanup(struct rtl8169_private *tp)
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		rtl_enable_rxdvgate(tp);
 		fsleep(2000);
 		break;
@@ -4252,7 +4262,7 @@ static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp,
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_34:
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 		padto = max_t(unsigned int, padto, ETH_ZLEN);
 		break;
 	default:
@@ -4680,12 +4690,6 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 	if (status & LinkChg)
 		phy_mac_interrupt(tp->phydev);
 
-	if (unlikely(status & RxFIFOOver &&
-	    tp->mac_version == RTL_GIGA_MAC_VER_11)) {
-		netif_stop_queue(tp->dev);
-		rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
-	}
-
 	rtl_irq_disable(tp);
 	napi_schedule(&tp->napi);
 out:
@@ -4723,8 +4727,6 @@ static void rtl_task(struct work_struct *work)
 reset:
 		rtl_reset_work(tp);
 		netif_wake_queue(tp->dev);
-	} else if (test_and_clear_bit(RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE, tp->wk.flags)) {
-		rtl_reset_work(tp);
 	}
 }
 
@@ -5048,10 +5050,8 @@ static void rtl_shutdown(struct pci_dev *pdev)
 	/* Restore original MAC address */
 	rtl_rar_set(tp, tp->dev->perm_addr);
 
-	if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled) {
-		pci_wake_from_d3(pdev, tp->saved_wolopts);
-		pci_set_power_state(pdev, PCI_D3hot);
-	}
+	if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled)
+		pci_prepare_to_sleep(pdev);
 }
 
 static void rtl_remove_one(struct pci_dev *pdev)
@@ -5103,9 +5103,6 @@ static void rtl_set_irq_mask(struct rtl8169_private *tp)
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
 		tp->irq_mask |= SYSErr | RxFIFOOver;
-	else if (tp->mac_version == RTL_GIGA_MAC_VER_11)
-		/* special workaround needed */
-		tp->irq_mask |= RxFIFOOver;
 }
 
 static int rtl_alloc_irq(struct rtl8169_private *tp)
@@ -5178,6 +5175,33 @@ static int r8169_mdio_write_reg(struct mii_bus *mii_bus, int phyaddr,
 	return 0;
 }
 
+static int r8169_mdio_read_reg_c45(struct mii_bus *mii_bus, int addr,
+				   int devnum, int regnum)
+{
+	struct rtl8169_private *tp = mii_bus->priv;
+
+	if (addr > 0)
+		return -ENODEV;
+
+	if (devnum == MDIO_MMD_VEND2 && regnum > MDIO_STAT2)
+		return r8168_phy_ocp_read(tp, regnum);
+
+	return 0;
+}
+
+static int r8169_mdio_write_reg_c45(struct mii_bus *mii_bus, int addr,
+				    int devnum, int regnum, u16 val)
+{
+	struct rtl8169_private *tp = mii_bus->priv;
+
+	if (addr > 0 || devnum != MDIO_MMD_VEND2 || regnum <= MDIO_STAT2)
+		return -ENODEV;
+
+	r8168_phy_ocp_write(tp, regnum, val);
+
+	return 0;
+}
+
 static int r8169_mdio_register(struct rtl8169_private *tp)
 {
 	struct pci_dev *pdev = tp->pci_dev;
@@ -5201,12 +5225,18 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->priv = tp;
 	new_bus->parent = &pdev->dev;
 	new_bus->irq[0] = PHY_MAC_INTERRUPT;
+	new_bus->phy_mask = GENMASK(31, 1);
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x",
 		 pci_domain_nr(pdev->bus), pci_dev_id(pdev));
 
 	new_bus->read = r8169_mdio_read_reg;
 	new_bus->write = r8169_mdio_write_reg;
 
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_40) {
+		new_bus->read_c45 = r8169_mdio_read_reg_c45;
+		new_bus->write_c45 = r8169_mdio_write_reg_c45;
+	}
+
 	ret = devm_mdiobus_register(&pdev->dev, new_bus);
 	if (ret)
 		return ret;
@@ -5230,9 +5260,9 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 
 	/* mimic behavior of r8125/r8126 vendor drivers */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_61)
-		phy_set_eee_broken(tp->phydev,
-				   ETHTOOL_LINK_MODE_2500baseT_Full_BIT);
-	phy_set_eee_broken(tp->phydev, ETHTOOL_LINK_MODE_5000baseT_Full_BIT);
+		phy_disable_eee_mode(tp->phydev,
+				     ETHTOOL_LINK_MODE_2500baseT_Full_BIT);
+	phy_disable_eee_mode(tp->phydev, ETHTOOL_LINK_MODE_5000baseT_Full_BIT);
 
 	/* PHY will be woken up in rtl_open() */
 	phy_suspend(tp->phydev);
@@ -5275,13 +5305,13 @@ static void rtl_hw_init_8125(struct rtl8169_private *tp)
 static void rtl_hw_initialize(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53:
+	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_52:
 		rtl8168ep_stop_cmac(tp);
 		fallthrough;
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48:
 		rtl_hw_init_8168g(tp);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 		rtl_hw_init_8125(tp);
 		break;
 	default:
@@ -5300,12 +5330,14 @@ static int rtl_jumbo_max(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
 		return JUMBO_7K;
 	/* RTL8168b */
-	case RTL_GIGA_MAC_VER_11:
 	case RTL_GIGA_MAC_VER_17:
 		return JUMBO_4K;
 	/* RTL8168c */
 	case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_24:
 		return JUMBO_6K;
+	/* RTL8125/8126 */
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
+		return JUMBO_16K;
 	default:
 		return JUMBO_9K;
 	}
@@ -5340,55 +5372,18 @@ done:
 /* register is set if system vendor successfully tested ASPM 1.2 */
 static bool rtl_aspm_is_safe(struct rtl8169_private *tp)
 {
-	if (tp->mac_version >= RTL_GIGA_MAC_VER_61 &&
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_46 &&
 	    r8168_mac_ocp_read(tp, 0xc0b2) & 0xf)
 		return true;
 
 	return false;
 }
 
-static umode_t r8169_hwmon_is_visible(const void *drvdata,
-				      enum hwmon_sensor_types type,
-				      u32 attr, int channel)
-{
-	return 0444;
-}
-
-static int r8169_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
-			    u32 attr, int channel, long *val)
-{
-	struct rtl8169_private *tp = dev_get_drvdata(dev);
-	int val_raw;
-
-	val_raw = phy_read_paged(tp->phydev, 0xbd8, 0x12) & 0x3ff;
-	if (val_raw >= 512)
-		val_raw -= 1024;
-
-	*val = 1000 * val_raw / 2;
-
-	return 0;
-}
-
-static const struct hwmon_ops r8169_hwmon_ops = {
-	.is_visible =  r8169_hwmon_is_visible,
-	.read = r8169_hwmon_read,
-};
-
-static const struct hwmon_channel_info * const r8169_hwmon_info[] = {
-	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
-	NULL
-};
-
-static const struct hwmon_chip_info r8169_hwmon_chip_info = {
-	.ops = &r8169_hwmon_ops,
-	.info = r8169_hwmon_info,
-};
-
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
+	const struct rtl_chip_info *chip;
 	struct rtl8169_private *tp;
 	int jumbo_max, region, rc;
-	enum mac_version chipset;
 	struct net_device *dev;
 	u32 txconfig;
 	u16 xid;
@@ -5426,11 +5421,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (region < 0)
 		return dev_err_probe(&pdev->dev, -ENODEV, "no MMIO resource found\n");
 
-	rc = pcim_iomap_regions(pdev, BIT(region), KBUILD_MODNAME);
-	if (rc < 0)
-		return dev_err_probe(&pdev->dev, rc, "cannot remap MMIO, aborting\n");
-
-	tp->mmio_addr = pcim_iomap_table(pdev)[region];
+	tp->mmio_addr = pcim_iomap_region(pdev, region, KBUILD_MODNAME);
+	if (IS_ERR(tp->mmio_addr))
+		return dev_err_probe(&pdev->dev, PTR_ERR(tp->mmio_addr),
+				     "cannot remap MMIO, aborting\n");
 
 	txconfig = RTL_R32(tp, TxConfig);
 	if (txconfig == ~0U)
@@ -5439,12 +5433,13 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	xid = (txconfig >> 20) & 0xfcf;
 
 	/* Identify chip attached to board */
-	chipset = rtl8169_get_mac_version(xid, tp->supports_gmii);
-	if (chipset == RTL_GIGA_MAC_NONE)
+	chip = rtl8169_get_chip_version(xid, tp->supports_gmii);
+	if (chip->mac_version == RTL_GIGA_MAC_NONE)
 		return dev_err_probe(&pdev->dev, -ENODEV,
 				     "unknown chip XID %03x, contact r8169 maintainers (see MAINTAINERS file)\n",
 				     xid);
-	tp->mac_version = chipset;
+	tp->mac_version = chip->mac_version;
+	tp->fw_name = chip->fw_name;
 
 	/* Disable ASPM L1 as that cause random device stop working
 	 * problems as well as full system hangs for some PCIe devices users.
@@ -5549,8 +5544,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	rtl_set_irq_mask(tp);
 
-	tp->fw_name = rtl_chip_infos[chipset].fw_name;
-
 	tp->counters = dmam_alloc_coherent (&pdev->dev, sizeof(*tp->counters),
 					    &tp->counters_phys_addr,
 					    GFP_KERNEL);
@@ -5563,12 +5556,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		return rc;
 
-	/* The temperature sensor is available from RTl8125B */
-	if (IS_REACHABLE(CONFIG_HWMON) && tp->mac_version >= RTL_GIGA_MAC_VER_63)
-		/* ignore errors */
-		devm_hwmon_device_register_with_info(&pdev->dev, "nic_temp", tp,
-						     &r8169_hwmon_chip_info,
-						     NULL);
 	rc = register_netdev(dev);
 	if (rc)
 		return rc;
@@ -5581,7 +5568,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	netdev_info(dev, "%s, %pM, XID %03x, IRQ %d\n",
-		    rtl_chip_infos[chipset].name, dev->dev_addr, xid, tp->irq);
+		    chip->name, dev->dev_addr, xid, tp->irq);
 
 	if (jumbo_max)
 		netdev_info(dev, "jumbo features [frames: %d bytes, tx checksumming: %s]\n",
diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
index 5307c6ff4e25..032d9d2cfa2a 100644
--- a/drivers/net/ethernet/realtek/r8169_phy_config.c
+++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
@@ -50,6 +50,15 @@ static void r8168g_phy_param(struct phy_device *phydev, u16 parm,
 	phy_restore_page(phydev, oldpage, 0);
 }
 
+static void rtl8125_phy_param(struct phy_device *phydev, u16 parm,
+			      u16 mask, u16 val)
+{
+	phy_lock_mdio_bus(phydev);
+	__phy_write_mmd(phydev, MDIO_MMD_VEND2, 0xb87c, parm);
+	__phy_modify_mmd(phydev, MDIO_MMD_VEND2, 0xb87e, mask, val);
+	phy_unlock_mdio_bus(phydev);
+}
+
 struct phy_reg {
 	u16 reg;
 	u16 val;
@@ -276,15 +285,6 @@ static void rtl8169sce_hw_phy_config(struct rtl8169_private *tp,
 	rtl_writephy_batch(phydev, phy_reg_init);
 }
 
-static void rtl8168bb_hw_phy_config(struct rtl8169_private *tp,
-				    struct phy_device *phydev)
-{
-	phy_write(phydev, 0x1f, 0x0001);
-	phy_set_bits(phydev, 0x16, BIT(0));
-	phy_write(phydev, 0x10, 0xf41b);
-	phy_write(phydev, 0x1f, 0x0000);
-}
-
 static void rtl8168bef_hw_phy_config(struct rtl8169_private *tp,
 				     struct phy_device *phydev)
 {
@@ -1013,12 +1013,8 @@ static void rtl8125a_2_hw_phy_config(struct rtl8169_private *tp,
 	phy_write_paged(phydev, 0xac5, 0x16, 0x01ff);
 	phy_modify_paged(phydev, 0xac8, 0x15, 0x00f0, 0x0030);
 
-	phy_write(phydev, 0x1f, 0x0b87);
-	phy_write(phydev, 0x16, 0x80a2);
-	phy_write(phydev, 0x17, 0x0153);
-	phy_write(phydev, 0x16, 0x809c);
-	phy_write(phydev, 0x17, 0x0153);
-	phy_write(phydev, 0x1f, 0x0000);
+	rtl8125_phy_param(phydev, 0x80a2, 0xffff, 0x0153);
+	rtl8125_phy_param(phydev, 0x809c, 0xffff, 0x0153);
 
 	phy_write(phydev, 0x1f, 0x0a43);
 	phy_write(phydev, 0x13, 0x81B3);
@@ -1070,14 +1066,9 @@ static void rtl8125b_hw_phy_config(struct rtl8169_private *tp,
 	phy_modify_paged(phydev, 0xac4, 0x13, 0x00f0, 0x0090);
 	phy_modify_paged(phydev, 0xad3, 0x10, 0x0003, 0x0001);
 
-	phy_write(phydev, 0x1f, 0x0b87);
-	phy_write(phydev, 0x16, 0x80f5);
-	phy_write(phydev, 0x17, 0x760e);
-	phy_write(phydev, 0x16, 0x8107);
-	phy_write(phydev, 0x17, 0x360e);
-	phy_write(phydev, 0x16, 0x8551);
-	phy_modify(phydev, 0x17, 0xff00, 0x0800);
-	phy_write(phydev, 0x1f, 0x0000);
+	rtl8125_phy_param(phydev, 0x80f5, 0xffff, 0x760e);
+	rtl8125_phy_param(phydev, 0x8107, 0xffff, 0x360e);
+	rtl8125_phy_param(phydev, 0x8551, 0xff00, 0x0800);
 
 	phy_modify_paged(phydev, 0xbf0, 0x10, 0xe000, 0xa000);
 	phy_modify_paged(phydev, 0xbf4, 0x13, 0x0f00, 0x0300);
@@ -1111,6 +1102,24 @@ static void rtl8125d_hw_phy_config(struct rtl8169_private *tp,
 	rtl8125_config_eee_phy(phydev);
 }
 
+static void rtl8125bp_hw_phy_config(struct rtl8169_private *tp,
+				    struct phy_device *phydev)
+{
+	r8169_apply_firmware(tp);
+	rtl8168g_enable_gphy_10m(phydev);
+
+	r8168g_phy_param(phydev, 0x8010, 0x0800, 0x0000);
+
+	rtl8125_phy_param(phydev, 0x8088, 0xff00, 0x9000);
+	rtl8125_phy_param(phydev, 0x808f, 0xff00, 0x9000);
+
+	r8168g_phy_param(phydev, 0x8174, 0x2000, 0x1800);
+
+	rtl8125_legacy_force_mode(phydev);
+	rtl8168g_disable_aldps(phydev);
+	rtl8125_config_eee_phy(phydev);
+}
+
 static void rtl8126a_hw_phy_config(struct rtl8169_private *tp,
 				   struct phy_device *phydev)
 {
@@ -1121,6 +1130,171 @@ static void rtl8126a_hw_phy_config(struct rtl8169_private *tp,
 	rtl8125_common_config_eee_phy(phydev);
 }
 
+static void rtl8127a_1_hw_phy_config(struct rtl8169_private *tp,
+				     struct phy_device *phydev)
+{
+	r8169_apply_firmware(tp);
+	rtl8168g_enable_gphy_10m(phydev);
+
+	r8168g_phy_param(phydev, 0x8415, 0xff00, 0x9300);
+	r8168g_phy_param(phydev, 0x81a3, 0xff00, 0x0f00);
+	r8168g_phy_param(phydev, 0x81ae, 0xff00, 0x0f00);
+	r8168g_phy_param(phydev, 0x81b9, 0xff00, 0xb900);
+	rtl8125_phy_param(phydev, 0x83b0, 0x0e00, 0x0000);
+	rtl8125_phy_param(phydev, 0x83C5, 0x0e00, 0x0000);
+	rtl8125_phy_param(phydev, 0x83da, 0x0e00, 0x0000);
+	rtl8125_phy_param(phydev, 0x83ef, 0x0e00, 0x0000);
+	phy_modify_paged(phydev, 0x0bf3, 0x14, 0x01f0, 0x0160);
+	phy_modify_paged(phydev, 0x0bf3, 0x15, 0x001f, 0x0014);
+	phy_modify_paged(phydev, 0x0bf2, 0x14, 0x6000, 0x0000);
+	phy_modify_paged(phydev, 0x0bf2, 0x16, 0xc000, 0x0000);
+	phy_modify_paged(phydev, 0x0bf2, 0x14, 0x1fff, 0x0187);
+	phy_modify_paged(phydev, 0x0bf2, 0x15, 0x003f, 0x0003);
+
+	r8168g_phy_param(phydev, 0x8173, 0xffff, 0x8620);
+	r8168g_phy_param(phydev, 0x8175, 0xffff, 0x8671);
+	r8168g_phy_param(phydev, 0x817c, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x8187, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x8192, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x819d, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x81a8, 0x2000, 0x0000);
+	r8168g_phy_param(phydev, 0x81b3, 0x2000, 0x0000);
+	r8168g_phy_param(phydev, 0x81be, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x817d, 0xff00, 0xa600);
+	r8168g_phy_param(phydev, 0x8188, 0xff00, 0xa600);
+	r8168g_phy_param(phydev, 0x8193, 0xff00, 0xa600);
+	r8168g_phy_param(phydev, 0x819e, 0xff00, 0xa600);
+	r8168g_phy_param(phydev, 0x81a9, 0xff00, 0x1400);
+	r8168g_phy_param(phydev, 0x81b4, 0xff00, 0x1400);
+	r8168g_phy_param(phydev, 0x81bf, 0xff00, 0xa600);
+
+	phy_modify_paged(phydev, 0x0aea, 0x15, 0x0028, 0x0000);
+
+	rtl8125_phy_param(phydev, 0x84f0, 0xffff, 0x201c);
+	rtl8125_phy_param(phydev, 0x84f2, 0xffff, 0x3117);
+
+	phy_write_paged(phydev, 0x0aec, 0x13, 0x0000);
+	phy_write_paged(phydev, 0x0ae2, 0x10, 0xffff);
+	phy_write_paged(phydev, 0x0aec, 0x17, 0xffff);
+	phy_write_paged(phydev, 0x0aed, 0x11, 0xffff);
+	phy_write_paged(phydev, 0x0aec, 0x14, 0x0000);
+	phy_modify_paged(phydev, 0x0aed, 0x10, 0x0001, 0x0000);
+	phy_write_paged(phydev, 0x0adb, 0x14, 0x0150);
+	rtl8125_phy_param(phydev, 0x8197, 0xff00, 0x5000);
+	rtl8125_phy_param(phydev, 0x8231, 0xff00, 0x5000);
+	rtl8125_phy_param(phydev, 0x82cb, 0xff00, 0x5000);
+	rtl8125_phy_param(phydev, 0x82cd, 0xff00, 0x5700);
+	rtl8125_phy_param(phydev, 0x8233, 0xff00, 0x5700);
+	rtl8125_phy_param(phydev, 0x8199, 0xff00, 0x5700);
+
+	rtl8125_phy_param(phydev, 0x815a, 0xffff, 0x0150);
+	rtl8125_phy_param(phydev, 0x81f4, 0xffff, 0x0150);
+	rtl8125_phy_param(phydev, 0x828e, 0xffff, 0x0150);
+	rtl8125_phy_param(phydev, 0x81b1, 0xffff, 0x0000);
+	rtl8125_phy_param(phydev, 0x824b, 0xffff, 0x0000);
+	rtl8125_phy_param(phydev, 0x82e5, 0xffff, 0x0000);
+
+	rtl8125_phy_param(phydev, 0x84f7, 0xff00, 0x2800);
+	phy_modify_paged(phydev, 0x0aec, 0x11, 0x0000, 0x1000);
+	rtl8125_phy_param(phydev, 0x81b3, 0xff00, 0xad00);
+	rtl8125_phy_param(phydev, 0x824d, 0xff00, 0xad00);
+	rtl8125_phy_param(phydev, 0x82e7, 0xff00, 0xad00);
+	phy_modify_paged(phydev, 0x0ae4, 0x17, 0x000f, 0x0001);
+	rtl8125_phy_param(phydev, 0x82ce, 0xf000, 0x4000);
+
+	rtl8125_phy_param(phydev, 0x84ac, 0xffff, 0x0000);
+	rtl8125_phy_param(phydev, 0x84ae, 0xffff, 0x0000);
+	rtl8125_phy_param(phydev, 0x84b0, 0xffff, 0xf818);
+	rtl8125_phy_param(phydev, 0x84b2, 0xff00, 0x6000);
+
+	rtl8125_phy_param(phydev, 0x8ffc, 0xffff, 0x6008);
+	rtl8125_phy_param(phydev, 0x8ffe, 0xffff, 0xf450);
+
+	rtl8125_phy_param(phydev, 0x8015, 0x0000, 0x0200);
+	rtl8125_phy_param(phydev, 0x8016, 0x0800, 0x0000);
+	rtl8125_phy_param(phydev, 0x8fe6, 0xff00, 0x0800);
+	rtl8125_phy_param(phydev, 0x8fe4, 0xffff, 0x2114);
+
+	rtl8125_phy_param(phydev, 0x8647, 0xffff, 0xa7b1);
+	rtl8125_phy_param(phydev, 0x8649, 0xffff, 0xbbca);
+	rtl8125_phy_param(phydev, 0x864b, 0xff00, 0xdc00);
+
+	rtl8125_phy_param(phydev, 0x8154, 0xc000, 0x4000);
+	rtl8125_phy_param(phydev, 0x8158, 0xc000, 0x0000);
+
+	rtl8125_phy_param(phydev, 0x826c, 0xffff, 0xffff);
+	rtl8125_phy_param(phydev, 0x826e, 0xffff, 0xffff);
+
+	rtl8125_phy_param(phydev, 0x8872, 0xff00, 0x0e00);
+	r8168g_phy_param(phydev, 0x8012, 0x0000, 0x0800);
+	r8168g_phy_param(phydev, 0x8012, 0x0000, 0x4000);
+	phy_modify_paged(phydev, 0x0b57, 0x13, 0x0000, 0x0001);
+	r8168g_phy_param(phydev, 0x834a, 0xff00, 0x0700);
+	rtl8125_phy_param(phydev, 0x8217, 0x3f00, 0x2a00);
+	r8168g_phy_param(phydev, 0x81b1, 0xff00, 0x0b00);
+	rtl8125_phy_param(phydev, 0x8fed, 0xff00, 0x4e00);
+
+	rtl8125_phy_param(phydev, 0x88ac, 0xff00, 0x2300);
+	phy_modify_paged(phydev, 0x0bf0, 0x16, 0x0000, 0x3800);
+	rtl8125_phy_param(phydev, 0x88de, 0xff00, 0x0000);
+	rtl8125_phy_param(phydev, 0x80b4, 0xffff, 0x5195);
+
+	r8168g_phy_param(phydev, 0x8370, 0xffff, 0x8671);
+	r8168g_phy_param(phydev, 0x8372, 0xffff, 0x86c8);
+
+	r8168g_phy_param(phydev, 0x8401, 0xffff, 0x86c8);
+	r8168g_phy_param(phydev, 0x8403, 0xffff, 0x86da);
+	r8168g_phy_param(phydev, 0x8406, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8408, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x840a, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x840c, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x840e, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8410, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8412, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8414, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8416, 0x1800, 0x1000);
+
+	r8168g_phy_param(phydev, 0x82bd, 0xffff, 0x1f40);
+
+	phy_modify_paged(phydev, 0x0bfb, 0x12, 0x07ff, 0x0328);
+	phy_write_paged(phydev, 0x0bfb, 0x13, 0x3e14);
+
+	r8168g_phy_param(phydev, 0x81c4, 0xffff, 0x003b);
+	r8168g_phy_param(phydev, 0x81c6, 0xffff, 0x0086);
+	r8168g_phy_param(phydev, 0x81c8, 0xffff, 0x00b7);
+	r8168g_phy_param(phydev, 0x81ca, 0xffff, 0x00db);
+	r8168g_phy_param(phydev, 0x81cc, 0xffff, 0x00fe);
+	r8168g_phy_param(phydev, 0x81ce, 0xffff, 0x00fe);
+	r8168g_phy_param(phydev, 0x81d0, 0xffff, 0x00fe);
+	r8168g_phy_param(phydev, 0x81d2, 0xffff, 0x00fe);
+	r8168g_phy_param(phydev, 0x81d4, 0xffff, 0x00c3);
+	r8168g_phy_param(phydev, 0x81d6, 0xffff, 0x0078);
+	r8168g_phy_param(phydev, 0x81d8, 0xffff, 0x0047);
+	r8168g_phy_param(phydev, 0x81da, 0xffff, 0x0023);
+
+	rtl8125_phy_param(phydev, 0x88d7, 0xffff, 0x01a0);
+	rtl8125_phy_param(phydev, 0x88d9, 0xffff, 0x01a0);
+	rtl8125_phy_param(phydev, 0x8ffa, 0xffff, 0x002a);
+
+	rtl8125_phy_param(phydev, 0x8fee, 0xffff, 0xffdf);
+	rtl8125_phy_param(phydev, 0x8ff0, 0xffff, 0xffff);
+	rtl8125_phy_param(phydev, 0x8ff2, 0xffff, 0x0a4a);
+	rtl8125_phy_param(phydev, 0x8ff4, 0xffff, 0xaa5a);
+	rtl8125_phy_param(phydev, 0x8ff6, 0xffff, 0x0a4a);
+
+	rtl8125_phy_param(phydev, 0x8ff8, 0xffff, 0xaa5a);
+	rtl8125_phy_param(phydev, 0x88d5, 0xff00, 0x0200);
+
+	r8168g_phy_param(phydev, 0x84bb, 0xff00, 0x0a00);
+	r8168g_phy_param(phydev, 0x84c0, 0xff00, 0x1600);
+
+	phy_modify_paged(phydev, 0x0a43, 0x10, 0x0000, 0x0003);
+
+	rtl8125_legacy_force_mode(phydev);
+	rtl8168g_disable_aldps(phydev);
+	rtl8125_common_config_eee_phy(phydev);
+}
+
 void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 			 enum mac_version ver)
 {
@@ -1136,7 +1310,6 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 		[RTL_GIGA_MAC_VER_08] = rtl8102e_hw_phy_config,
 		[RTL_GIGA_MAC_VER_09] = rtl8102e_hw_phy_config,
 		[RTL_GIGA_MAC_VER_10] = NULL,
-		[RTL_GIGA_MAC_VER_11] = rtl8168bb_hw_phy_config,
 		[RTL_GIGA_MAC_VER_14] = rtl8401_hw_phy_config,
 		[RTL_GIGA_MAC_VER_17] = rtl8168bef_hw_phy_config,
 		[RTL_GIGA_MAC_VER_18] = rtl8168cp_1_hw_phy_config,
@@ -1168,12 +1341,12 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 		[RTL_GIGA_MAC_VER_48] = rtl8168h_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_51] = rtl8168ep_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_52] = rtl8117_hw_phy_config,
-		[RTL_GIGA_MAC_VER_53] = rtl8117_hw_phy_config,
 		[RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config,
 		[RTL_GIGA_MAC_VER_64] = rtl8125d_hw_phy_config,
-		[RTL_GIGA_MAC_VER_65] = rtl8126a_hw_phy_config,
-		[RTL_GIGA_MAC_VER_66] = rtl8126a_hw_phy_config,
+		[RTL_GIGA_MAC_VER_66] = rtl8125bp_hw_phy_config,
+		[RTL_GIGA_MAC_VER_70] = rtl8126a_hw_phy_config,
+		[RTL_GIGA_MAC_VER_80] = rtl8127a_1_hw_phy_config,
 	};
 
 	if (phy_configs[ver])
diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h
index dbc3f92eebc4..498cfe4d0cac 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase.h
+++ b/drivers/net/ethernet/realtek/rtase/rtase.h
@@ -13,6 +13,7 @@
 #define RTASE_HW_VER_906X_7XA 0x00800000
 #define RTASE_HW_VER_906X_7XC 0x04000000
 #define RTASE_HW_VER_907XD_V1 0x04800000
+#define RTASE_HW_VER_907XD_VA 0x08000000
 
 #define RTASE_RX_DMA_BURST_256       4
 #define RTASE_TX_DMA_BURST_UNLIMITED 7
@@ -169,6 +170,7 @@ enum rtase_registers {
 #define RTASE_TC_MODE_MASK GENMASK(11, 10)
 
 	RTASE_TOKSEL      = 0x2046,
+	RTASE_TXQCRDT_0   = 0x2500,
 	RTASE_RFIFONFULL  = 0x4406,
 	RTASE_INT_MITI_TX = 0x0A00,
 	RTASE_INT_MITI_RX = 0x0A80,
@@ -258,6 +260,12 @@ union rtase_rx_desc {
 #define RTASE_VLAN_TAG_MASK     GENMASK(15, 0)
 #define RTASE_RX_PKT_SIZE_MASK  GENMASK(13, 0)
 
+/* txqos hardware definitions */
+#define RTASE_1T_CLOCK            64
+#define RTASE_1T_POWER            10000000
+#define RTASE_IDLESLOPE_INT_SHIFT 25
+#define RTASE_IDLESLOPE_INT_MASK  GENMASK(31, 25)
+
 #define RTASE_IVEC_NAME_SIZE (IFNAMSIZ + 10)
 
 struct rtase_int_vector {
@@ -293,6 +301,13 @@ struct rtase_ring {
 	u64 alloc_fail;
 };
 
+struct rtase_txqos {
+	int hicredit;
+	int locredit;
+	int idleslope;
+	int sendslope;
+};
+
 struct rtase_stats {
 	u64 tx_dropped;
 	u64 rx_dropped;
@@ -312,6 +327,7 @@ struct rtase_private {
 
 	struct page_pool *page_pool;
 	struct rtase_ring tx_ring[RTASE_NUM_TX_QUEUE];
+	struct rtase_txqos tx_qos[RTASE_NUM_TX_QUEUE];
 	struct rtase_ring rx_ring[RTASE_NUM_RX_QUEUE];
 	struct rtase_counters *tally_vaddr;
 	dma_addr_t tally_paddr;
diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index de7f11232593..4d37217e9a14 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1114,7 +1114,7 @@ static int rtase_open(struct net_device *dev)
 		/* request other interrupts to handle multiqueue */
 		for (i = 1; i < tp->int_nums; i++) {
 			ivec = &tp->int_vector[i];
-			snprintf(ivec->name, sizeof(ivec->name), "%s_int%i",
+			snprintf(ivec->name, sizeof(ivec->name), "%s_int%u",
 				 tp->dev->name, i);
 			ret = request_irq(ivec->irq, rtase_q_interrupt, 0,
 					  ivec->name, ivec);
@@ -1501,7 +1501,10 @@ static void rtase_wait_for_quiescence(const struct net_device *dev)
 static void rtase_sw_reset(struct net_device *dev)
 {
 	struct rtase_private *tp = netdev_priv(dev);
+	struct rtase_ring *ring, *tmp;
+	struct rtase_int_vector *ivec;
 	int ret;
+	u32 i;
 
 	netif_stop_queue(dev);
 	netif_carrier_off(dev);
@@ -1512,6 +1515,13 @@ static void rtase_sw_reset(struct net_device *dev)
 	rtase_tx_clear(tp);
 	rtase_rx_clear(tp);
 
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		list_for_each_entry_safe(ring, tmp, &ivec->ring_list,
+					 ring_entry)
+			list_del(&ring->ring_entry);
+	}
+
 	ret = rtase_init_ring(dev);
 	if (ret) {
 		netdev_err(dev, "unable to init ring\n");
@@ -1651,6 +1661,65 @@ static void rtase_get_stats64(struct net_device *dev,
 	stats->rx_length_errors = tp->stats.rx_length_errors;
 }
 
+static void rtase_set_hw_cbs(const struct rtase_private *tp, u32 queue)
+{
+	u32 idle = tp->tx_qos[queue].idleslope * RTASE_1T_CLOCK;
+	u32 val, i;
+
+	val = u32_encode_bits(idle / RTASE_1T_POWER, RTASE_IDLESLOPE_INT_MASK);
+	idle %= RTASE_1T_POWER;
+
+	for (i = 1; i <= RTASE_IDLESLOPE_INT_SHIFT; i++) {
+		idle *= 2;
+		if ((idle / RTASE_1T_POWER) == 1)
+			val |= BIT(RTASE_IDLESLOPE_INT_SHIFT - i);
+
+		idle %= RTASE_1T_POWER;
+	}
+
+	rtase_w32(tp, RTASE_TXQCRDT_0 + queue * 4, val);
+}
+
+static int rtase_setup_tc_cbs(struct rtase_private *tp,
+			      const struct tc_cbs_qopt_offload *qopt)
+{
+	int queue = qopt->queue;
+
+	if (queue < 0 || queue >= tp->func_tx_queue_num)
+		return -EINVAL;
+
+	if (!qopt->enable) {
+		tp->tx_qos[queue].hicredit = 0;
+		tp->tx_qos[queue].locredit = 0;
+		tp->tx_qos[queue].idleslope = 0;
+		tp->tx_qos[queue].sendslope = 0;
+
+		rtase_w32(tp, RTASE_TXQCRDT_0 + queue * 4, 0);
+	} else {
+		tp->tx_qos[queue].hicredit = qopt->hicredit;
+		tp->tx_qos[queue].locredit = qopt->locredit;
+		tp->tx_qos[queue].idleslope = qopt->idleslope;
+		tp->tx_qos[queue].sendslope = qopt->sendslope;
+
+		rtase_set_hw_cbs(tp, queue);
+	}
+
+	return 0;
+}
+
+static int rtase_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			  void *type_data)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_CBS:
+		return rtase_setup_tc_cbs(tp, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static netdev_features_t rtase_fix_features(struct net_device *dev,
 					    netdev_features_t features)
 {
@@ -1686,6 +1755,7 @@ static const struct net_device_ops rtase_netdev_ops = {
 	.ndo_change_mtu = rtase_change_mtu,
 	.ndo_tx_timeout = rtase_tx_timeout,
 	.ndo_get_stats64 = rtase_get_stats64,
+	.ndo_setup_tc = rtase_setup_tc,
 	.ndo_fix_features = rtase_fix_features,
 	.ndo_set_features = rtase_set_features,
 };
@@ -1725,6 +1795,7 @@ static int rtase_get_settings(struct net_device *dev,
 		cmd->base.speed = SPEED_5000;
 		break;
 	case RTASE_HW_VER_907XD_V1:
+	case RTASE_HW_VER_907XD_VA:
 		cmd->base.speed = SPEED_10000;
 		break;
 	}
@@ -1827,7 +1898,7 @@ static int rtase_alloc_msix(struct pci_dev *pdev, struct rtase_private *tp)
 
 	for (i = 0; i < tp->int_nums; i++) {
 		irq = pci_irq_vector(pdev, i);
-		if (!irq) {
+		if (irq < 0) {
 			pci_disable_msix(pdev);
 			return irq;
 		}
@@ -1912,10 +1983,10 @@ static u16 rtase_calc_time_mitigation(u32 time_us)
 	u8 msb, time_count, time_unit;
 	u16 int_miti;
 
-	time_us = min_t(int, time_us, RTASE_MITI_MAX_TIME);
+	time_us = min(time_us, RTASE_MITI_MAX_TIME);
 
-	msb = fls(time_us);
-	if (msb >= RTASE_MITI_COUNT_BIT_NUM) {
+	if (time_us > RTASE_MITI_TIME_COUNT_MASK) {
+		msb = fls(time_us);
 		time_unit = msb - RTASE_MITI_COUNT_BIT_NUM;
 		time_count = time_us >> (msb - RTASE_MITI_COUNT_BIT_NUM);
 	} else {
@@ -1934,7 +2005,7 @@ static u16 rtase_calc_packet_num_mitigation(u16 pkt_num)
 	u8 msb, pkt_num_count, pkt_num_unit;
 	u16 int_miti;
 
-	pkt_num = min_t(int, pkt_num, RTASE_MITI_MAX_PKT_NUM);
+	pkt_num = min(pkt_num, RTASE_MITI_MAX_PKT_NUM);
 
 	if (pkt_num > 60) {
 		pkt_num_unit = RTASE_MITI_MAX_PKT_NUM_IDX;
@@ -1993,6 +2064,7 @@ static int rtase_check_mac_version_valid(struct rtase_private *tp)
 	case RTASE_HW_VER_906X_7XA:
 	case RTASE_HW_VER_906X_7XC:
 	case RTASE_HW_VER_907XD_V1:
+	case RTASE_HW_VER_907XD_VA:
 		ret = 0;
 		break;
 	}
@@ -2016,7 +2088,7 @@ static int rtase_init_board(struct pci_dev *pdev, struct net_device **dev_out,
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	ret = pci_enable_device(pdev);
-	if (ret < 0)
+	if (ret)
 		goto err_out_free_dev;
 
 	/* make sure PCI base addr 1 is MMIO */
@@ -2032,7 +2104,7 @@ static int rtase_init_board(struct pci_dev *pdev, struct net_device **dev_out,
 	}
 
 	ret = pci_request_regions(pdev, KBUILD_MODNAME);
-	if (ret < 0)
+	if (ret)
 		goto err_out_disable;
 
 	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
@@ -2108,7 +2180,7 @@ static int rtase_init_one(struct pci_dev *pdev,
 	dev_dbg(&pdev->dev, "Automotive Switch Ethernet driver loaded\n");
 
 	ret = rtase_init_board(pdev, &dev, &ioaddr);
-	if (ret != 0)
+	if (ret)
 		return ret;
 
 	tp = netdev_priv(dev);
@@ -2118,7 +2190,7 @@ static int rtase_init_one(struct pci_dev *pdev,
 
 	/* identify chip attached to board */
 	ret = rtase_check_mac_version_valid(tp);
-	if (ret != 0) {
+	if (ret) {
 		dev_err(&pdev->dev,
 			"unknown chip version: 0x%08x, contact rtase maintainers (see MAINTAINERS file)\n",
 			tp->hw_ver);
@@ -2129,7 +2201,7 @@ static int rtase_init_one(struct pci_dev *pdev,
 	rtase_init_hardware(tp);
 
 	ret = rtase_alloc_interrupt(pdev, tp);
-	if (ret < 0) {
+	if (ret) {
 		dev_err(&pdev->dev, "unable to alloc MSIX/MSI\n");
 		goto err_out_del_napi;
 	}
@@ -2174,7 +2246,7 @@ static int rtase_init_one(struct pci_dev *pdev,
 	netif_carrier_off(dev);
 
 	ret = register_netdev(dev);
-	if (ret != 0)
+	if (ret)
 		goto err_out_free_dma;
 
 	netdev_dbg(dev, "%pM, IRQ %d\n", dev->dev_addr, dev->irq);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index ac0f093f647a..c9f4976a3527 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -2763,6 +2763,7 @@ static const struct ravb_hw_info ravb_rzv2m_hw_info = {
 	.net_features = NETIF_F_RXCSUM,
 	.stats_len = ARRAY_SIZE(ravb_gstrings_stats),
 	.tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3,
+	.tx_max_frame_size = SZ_2K,
 	.rx_max_frame_size = SZ_2K,
 	.rx_buffer_size = SZ_2K +
 			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
@@ -3216,10 +3217,15 @@ static int ravb_suspend(struct device *dev)
 
 	netif_device_detach(ndev);
 
-	if (priv->wol_enabled)
-		return ravb_wol_setup(ndev);
+	rtnl_lock();
+	if (priv->wol_enabled) {
+		ret = ravb_wol_setup(ndev);
+		rtnl_unlock();
+		return ret;
+	}
 
 	ret = ravb_close(ndev);
+	rtnl_unlock();
 	if (ret)
 		return ret;
 
@@ -3244,19 +3250,20 @@ static int ravb_resume(struct device *dev)
 	if (!netif_running(ndev))
 		return 0;
 
+	rtnl_lock();
 	/* If WoL is enabled restore the interface. */
-	if (priv->wol_enabled) {
+	if (priv->wol_enabled)
 		ret = ravb_wol_restore(ndev);
-		if (ret)
-			return ret;
-	} else {
+	else
 		ret = pm_runtime_force_resume(dev);
-		if (ret)
-			return ret;
+	if (ret) {
+		rtnl_unlock();
+		return ret;
 	}
 
 	/* Reopening the interface will restore the device to the working state. */
 	ret = ravb_open(ndev);
+	rtnl_unlock();
 	if (ret < 0)
 		goto out_rpm_put;
 
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index 6e4ef7af27bf..226c6c0ab945 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -176,13 +176,6 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp,
 	struct net_device *ndev = priv->ndev;
 	unsigned long flags;
 
-	/* Reject requests with unsupported flags */
-	if (req->flags & ~(PTP_ENABLE_FEATURE |
-			   PTP_RISING_EDGE |
-			   PTP_FALLING_EDGE |
-			   PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	if (req->index)
 		return -EINVAL;
 
@@ -213,10 +206,6 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp,
 	unsigned long flags;
 	int error = 0;
 
-	/* Reject requests with unsupported flags */
-	if (req->flags)
-		return -EOPNOTSUPP;
-
 	if (req->index)
 		return -EINVAL;
 
@@ -288,6 +277,7 @@ static const struct ptp_clock_info ravb_ptp_info = {
 	.max_adj	= 50000000,
 	.n_ext_ts	= N_EXT_TS,
 	.n_per_out	= N_PER_OUT,
+	.supported_extts_flags = PTP_RISING_EDGE | PTP_FALLING_EDGE,
 	.adjfine	= ravb_ptp_adjfine,
 	.adjtime	= ravb_ptp_adjtime,
 	.gettime64	= ravb_ptp_gettime64,
diff --git a/drivers/net/ethernet/renesas/rcar_gen4_ptp.c b/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
index 72e7fcc56693..4c3e8cc5046f 100644
--- a/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
+++ b/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
@@ -29,8 +29,8 @@ static const struct rcar_gen4_ptp_reg_offset gen4_offs = {
 static int rcar_gen4_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 {
 	struct rcar_gen4_ptp_private *ptp_priv = ptp_to_priv(ptp);
-	bool neg_adj = scaled_ppm < 0 ? true : false;
 	s64 addend = ptp_priv->default_addend;
+	bool neg_adj = scaled_ppm < 0;
 	s64 diff;
 
 	if (neg_adj)
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 8d18dae4d8fb..aba772e14555 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -111,25 +111,35 @@ static void rswitch_top_init(struct rswitch_private *priv)
 /* Forwarding engine block (MFWD) */
 static void rswitch_fwd_init(struct rswitch_private *priv)
 {
+	u32 all_ports_mask = GENMASK(RSWITCH_NUM_AGENTS - 1, 0);
 	unsigned int i;
 
-	/* For ETHA */
-	for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
-		iowrite32(FWPC0_DEFAULT, priv->addr + FWPC0(i));
+	/* Start with empty configuration */
+	for (i = 0; i < RSWITCH_NUM_AGENTS; i++) {
+		/* Disable all port features */
+		iowrite32(0, priv->addr + FWPC0(i));
+		/* Disallow L3 forwarding and direct descriptor forwarding */
+		iowrite32(FIELD_PREP(FWCP1_LTHFW, all_ports_mask),
+			  priv->addr + FWPC1(i));
+		/* Disallow L2 forwarding */
+		iowrite32(FIELD_PREP(FWCP2_LTWFW, all_ports_mask),
+			  priv->addr + FWPC2(i));
+		/* Disallow port based forwarding */
 		iowrite32(0, priv->addr + FWPBFC(i));
 	}
 
-	for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
+	/* For enabled ETHA ports, setup port based forwarding */
+	rswitch_for_each_enabled_port(priv, i) {
+		/* Port based forwarding from port i to GWCA port */
+		rswitch_modify(priv->addr, FWPBFC(i), FWPBFC_PBDV,
+			       FIELD_PREP(FWPBFC_PBDV, BIT(priv->gwca.index)));
+		/* Within GWCA port, forward to Rx queue for port i */
 		iowrite32(priv->rdev[i]->rx_queue->index,
 			  priv->addr + FWPBFCSDC(GWCA_INDEX, i));
-		iowrite32(BIT(priv->gwca.index), priv->addr + FWPBFC(i));
 	}
 
-	/* For GWCA */
-	iowrite32(FWPC0_DEFAULT, priv->addr + FWPC0(priv->gwca.index));
-	iowrite32(FWPC1_DDE, priv->addr + FWPC1(priv->gwca.index));
-	iowrite32(0, priv->addr + FWPBFC(priv->gwca.index));
-	iowrite32(GENMASK(RSWITCH_NUM_PORTS - 1, 0), priv->addr + FWPBFC(priv->gwca.index));
+	/* For GWCA port, allow direct descriptor forwarding */
+	rswitch_modify(priv->addr, FWPC1(priv->gwca.index), FWPC1_DDE, FWPC1_DDE);
 }
 
 /* Gateway CPU agent block (GWCA) */
@@ -547,7 +557,6 @@ static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv)
 	desc = &gq->ts_ring[gq->ring_size];
 	desc->desc.die_dt = DT_LINKFIX;
 	rswitch_desc_set_dptr(&desc->desc, gq->ring_dma);
-	INIT_LIST_HEAD(&priv->gwca.ts_info_list);
 
 	return 0;
 }
@@ -862,13 +871,10 @@ static void rswitch_tx_free(struct net_device *ndev)
 	struct rswitch_ext_desc *desc;
 	struct sk_buff *skb;
 
-	for (; rswitch_get_num_cur_queues(gq) > 0;
-	     gq->dirty = rswitch_next_queue_index(gq, false, 1)) {
-		desc = &gq->tx_ring[gq->dirty];
-		if ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY)
-			break;
-
+	desc = &gq->tx_ring[gq->dirty];
+	while ((desc->desc.die_dt & DT_MASK) == DT_FEMPTY) {
 		dma_rmb();
+
 		skb = gq->skbs[gq->dirty];
 		if (skb) {
 			rdev->ndev->stats.tx_packets++;
@@ -879,7 +885,10 @@ static void rswitch_tx_free(struct net_device *ndev)
 			dev_kfree_skb_any(gq->skbs[gq->dirty]);
 			gq->skbs[gq->dirty] = NULL;
 		}
+
 		desc->desc.die_dt = DT_EEMPTY;
+		gq->dirty = rswitch_next_queue_index(gq, false, 1);
+		desc = &gq->tx_ring[gq->dirty];
 	}
 }
 
@@ -908,8 +917,10 @@ retry:
 
 	if (napi_complete_done(napi, budget - quota)) {
 		spin_lock_irqsave(&priv->lock, flags);
-		rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true);
-		rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true);
+		if (test_bit(rdev->port, priv->opened_ports)) {
+			rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true);
+			rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true);
+		}
 		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
@@ -1001,9 +1012,10 @@ static int rswitch_gwca_request_irqs(struct rswitch_private *priv)
 static void rswitch_ts(struct rswitch_private *priv)
 {
 	struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue;
-	struct rswitch_gwca_ts_info *ts_info, *ts_info2;
 	struct skb_shared_hwtstamps shhwtstamps;
 	struct rswitch_ts_desc *desc;
+	struct rswitch_device *rdev;
+	struct sk_buff *ts_skb;
 	struct timespec64 ts;
 	unsigned int num;
 	u32 tag, port;
@@ -1013,23 +1025,28 @@ static void rswitch_ts(struct rswitch_private *priv)
 		dma_rmb();
 
 		port = TS_DESC_DPN(__le32_to_cpu(desc->desc.dptrl));
-		tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl));
-
-		list_for_each_entry_safe(ts_info, ts_info2, &priv->gwca.ts_info_list, list) {
-			if (!(ts_info->port == port && ts_info->tag == tag))
-				continue;
-
-			memset(&shhwtstamps, 0, sizeof(shhwtstamps));
-			ts.tv_sec = __le32_to_cpu(desc->ts_sec);
-			ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff));
-			shhwtstamps.hwtstamp = timespec64_to_ktime(ts);
-			skb_tstamp_tx(ts_info->skb, &shhwtstamps);
-			dev_consume_skb_irq(ts_info->skb);
-			list_del(&ts_info->list);
-			kfree(ts_info);
-			break;
-		}
+		if (unlikely(port >= RSWITCH_NUM_PORTS))
+			goto next;
+		rdev = priv->rdev[port];
 
+		tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl));
+		if (unlikely(tag >= TS_TAGS_PER_PORT))
+			goto next;
+		ts_skb = xchg(&rdev->ts_skb[tag], NULL);
+		smp_mb(); /* order rdev->ts_skb[] read before bitmap update */
+		clear_bit(tag, rdev->ts_skb_used);
+
+		if (unlikely(!ts_skb))
+			goto next;
+
+		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+		ts.tv_sec = __le32_to_cpu(desc->ts_sec);
+		ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff));
+		shhwtstamps.hwtstamp = timespec64_to_ktime(ts);
+		skb_tstamp_tx(ts_skb, &shhwtstamps);
+		dev_consume_skb_irq(ts_skb);
+
+next:
 		gq->cur = rswitch_next_queue_index(gq, true, 1);
 		desc = &gq->ts_ring[gq->cur];
 	}
@@ -1114,32 +1131,47 @@ static int rswitch_etha_wait_link_verification(struct rswitch_etha *etha)
 
 static void rswitch_rmac_setting(struct rswitch_etha *etha, const u8 *mac)
 {
-	u32 val;
+	u32 pis, lsc;
 
 	rswitch_etha_write_mac_address(etha, mac);
 
+	switch (etha->phy_interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+		pis = MPIC_PIS_GMII;
+		break;
+	case PHY_INTERFACE_MODE_USXGMII:
+	case PHY_INTERFACE_MODE_5GBASER:
+		pis = MPIC_PIS_XGMII;
+		break;
+	default:
+		pis = FIELD_GET(MPIC_PIS, ioread32(etha->addr + MPIC));
+		break;
+	}
+
 	switch (etha->speed) {
 	case 100:
-		val = MPIC_LSC_100M;
+		lsc = MPIC_LSC_100M;
 		break;
 	case 1000:
-		val = MPIC_LSC_1G;
+		lsc = MPIC_LSC_1G;
 		break;
 	case 2500:
-		val = MPIC_LSC_2_5G;
+		lsc = MPIC_LSC_2_5G;
 		break;
 	default:
-		return;
+		lsc = FIELD_GET(MPIC_LSC, ioread32(etha->addr + MPIC));
+		break;
 	}
 
-	iowrite32(MPIC_PIS_GMII | val, etha->addr + MPIC);
+	rswitch_modify(etha->addr, MPIC, MPIC_PIS | MPIC_LSC,
+		       FIELD_PREP(MPIC_PIS, pis) | FIELD_PREP(MPIC_LSC, lsc));
 }
 
 static void rswitch_etha_enable_mii(struct rswitch_etha *etha)
 {
-	rswitch_modify(etha->addr, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK,
-		       MPIC_PSMCS(etha->psmcs) | MPIC_PSMHT(0x06));
-	rswitch_modify(etha->addr, MPSM, 0, MPSM_MFF_C45);
+	rswitch_modify(etha->addr, MPIC, MPIC_PSMCS | MPIC_PSMHT,
+		       FIELD_PREP(MPIC_PSMCS, etha->psmcs) |
+		       FIELD_PREP(MPIC_PSMHT, 0x06));
 }
 
 static int rswitch_etha_hw_init(struct rswitch_etha *etha, const u8 *mac)
@@ -1168,42 +1200,29 @@ static int rswitch_etha_hw_init(struct rswitch_etha *etha, const u8 *mac)
 	return rswitch_etha_change_mode(etha, EAMC_OPC_OPERATION);
 }
 
-static int rswitch_etha_set_access(struct rswitch_etha *etha, bool read,
-				   int phyad, int devad, int regad, int data)
+static int rswitch_etha_mpsm_op(struct rswitch_etha *etha, bool read,
+				unsigned int mmf, unsigned int pda,
+				unsigned int pra, unsigned int pop,
+				unsigned int prd)
 {
-	int pop = read ? MDIO_READ_C45 : MDIO_WRITE_C45;
 	u32 val;
 	int ret;
 
-	if (devad == 0xffffffff)
-		return -ENODEV;
-
-	writel(MMIS1_CLEAR_FLAGS, etha->addr + MMIS1);
-
-	val = MPSM_PSME | MPSM_MFF_C45;
-	iowrite32((regad << 16) | (devad << 8) | (phyad << 3) | val, etha->addr + MPSM);
+	val = MPSM_PSME |
+	      FIELD_PREP(MPSM_MFF, mmf) |
+	      FIELD_PREP(MPSM_PDA, pda) |
+	      FIELD_PREP(MPSM_PRA, pra) |
+	      FIELD_PREP(MPSM_POP, pop) |
+	      FIELD_PREP(MPSM_PRD, prd);
+	iowrite32(val, etha->addr + MPSM);
 
-	ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PAACS, MMIS1_PAACS);
+	ret = rswitch_reg_wait(etha->addr, MPSM, MPSM_PSME, 0);
 	if (ret)
 		return ret;
 
-	rswitch_modify(etha->addr, MMIS1, MMIS1_PAACS, MMIS1_PAACS);
-
 	if (read) {
-		writel((pop << 13) | (devad << 8) | (phyad << 3) | val, etha->addr + MPSM);
-
-		ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PRACS, MMIS1_PRACS);
-		if (ret)
-			return ret;
-
-		ret = (ioread32(etha->addr + MPSM) & MPSM_PRD_MASK) >> 16;
-
-		rswitch_modify(etha->addr, MMIS1, MMIS1_PRACS, MMIS1_PRACS);
-	} else {
-		iowrite32((data << 16) | (pop << 13) | (devad << 8) | (phyad << 3) | val,
-			  etha->addr + MPSM);
-
-		ret = rswitch_reg_wait(etha->addr, MMIS1, MMIS1_PWACS, MMIS1_PWACS);
+		val = ioread32(etha->addr + MPSM);
+		ret = FIELD_GET(MPSM_PRD, val);
 	}
 
 	return ret;
@@ -1213,16 +1232,47 @@ static int rswitch_etha_mii_read_c45(struct mii_bus *bus, int addr, int devad,
 				     int regad)
 {
 	struct rswitch_etha *etha = bus->priv;
+	int ret;
 
-	return rswitch_etha_set_access(etha, true, addr, devad, regad, 0);
+	ret = rswitch_etha_mpsm_op(etha, false, MPSM_MMF_C45, addr, devad,
+				   MPSM_POP_ADDRESS, regad);
+	if (ret)
+		return ret;
+
+	return rswitch_etha_mpsm_op(etha, true, MPSM_MMF_C45, addr, devad,
+				    MPSM_POP_READ_C45, 0);
 }
 
 static int rswitch_etha_mii_write_c45(struct mii_bus *bus, int addr, int devad,
 				      int regad, u16 val)
 {
 	struct rswitch_etha *etha = bus->priv;
+	int ret;
+
+	ret = rswitch_etha_mpsm_op(etha, false, MPSM_MMF_C45, addr, devad,
+				   MPSM_POP_ADDRESS, regad);
+	if (ret)
+		return ret;
+
+	return rswitch_etha_mpsm_op(etha, false, MPSM_MMF_C45, addr, devad,
+				    MPSM_POP_WRITE, val);
+}
+
+static int rswitch_etha_mii_read_c22(struct mii_bus *bus, int phyad, int regad)
+{
+	struct rswitch_etha *etha = bus->priv;
+
+	return rswitch_etha_mpsm_op(etha, true, MPSM_MMF_C22, phyad, regad,
+				    MPSM_POP_READ_C22, 0);
+}
+
+static int rswitch_etha_mii_write_c22(struct mii_bus *bus, int phyad,
+				      int regad, u16 val)
+{
+	struct rswitch_etha *etha = bus->priv;
 
-	return rswitch_etha_set_access(etha, false, addr, devad, regad, val);
+	return rswitch_etha_mpsm_op(etha, false, MPSM_MMF_C22, phyad, regad,
+				    MPSM_POP_WRITE, val);
 }
 
 /* Call of_node_put(port) after done */
@@ -1237,17 +1287,14 @@ static struct device_node *rswitch_get_port_node(struct rswitch_device *rdev)
 	if (!ports)
 		return NULL;
 
-	for_each_child_of_node(ports, port) {
+	for_each_available_child_of_node(ports, port) {
 		err = of_property_read_u32(port, "reg", &index);
 		if (err < 0) {
 			port = NULL;
 			goto out;
 		}
-		if (index == rdev->etha->index) {
-			if (!of_device_is_available(port))
-				port = NULL;
+		if (index == rdev->etha->index)
 			break;
-		}
 	}
 
 out:
@@ -1307,6 +1354,8 @@ static int rswitch_mii_register(struct rswitch_device *rdev)
 	mii_bus->priv = rdev->etha;
 	mii_bus->read_c45 = rswitch_etha_mii_read_c45;
 	mii_bus->write_c45 = rswitch_etha_mii_write_c45;
+	mii_bus->read = rswitch_etha_mii_read_c22;
+	mii_bus->write = rswitch_etha_mii_write_c22;
 	mii_bus->parent = &rdev->priv->pdev->dev;
 
 	mdio_np = of_get_child_by_name(rdev->np_port, "mdio");
@@ -1527,7 +1576,7 @@ static void rswitch_ether_port_deinit_all(struct rswitch_private *priv)
 {
 	unsigned int i;
 
-	for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
+	rswitch_for_each_enabled_port(priv, i) {
 		phy_exit(priv->rdev[i]->serdes);
 		rswitch_ether_port_deinit_one(priv->rdev[i]);
 	}
@@ -1538,20 +1587,20 @@ static int rswitch_open(struct net_device *ndev)
 	struct rswitch_device *rdev = netdev_priv(ndev);
 	unsigned long flags;
 
-	phy_start(ndev->phydev);
+	if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS))
+		iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE);
 
 	napi_enable(&rdev->napi);
-	netif_start_queue(ndev);
 
 	spin_lock_irqsave(&rdev->priv->lock, flags);
+	bitmap_set(rdev->priv->opened_ports, rdev->port, 1);
 	rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, true);
 	rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, true);
 	spin_unlock_irqrestore(&rdev->priv->lock, flags);
 
-	if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS))
-		iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE);
+	phy_start(ndev->phydev);
 
-	bitmap_set(rdev->priv->opened_ports, rdev->port, 1);
+	netif_start_queue(ndev);
 
 	return 0;
 };
@@ -1559,31 +1608,34 @@ static int rswitch_open(struct net_device *ndev)
 static int rswitch_stop(struct net_device *ndev)
 {
 	struct rswitch_device *rdev = netdev_priv(ndev);
-	struct rswitch_gwca_ts_info *ts_info, *ts_info2;
+	struct sk_buff *ts_skb;
 	unsigned long flags;
+	unsigned int tag;
 
 	netif_tx_stop_all_queues(ndev);
-	bitmap_clear(rdev->priv->opened_ports, rdev->port, 1);
-
-	if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS))
-		iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID);
 
-	list_for_each_entry_safe(ts_info, ts_info2, &rdev->priv->gwca.ts_info_list, list) {
-		if (ts_info->port != rdev->port)
-			continue;
-		dev_kfree_skb_irq(ts_info->skb);
-		list_del(&ts_info->list);
-		kfree(ts_info);
-	}
+	phy_stop(ndev->phydev);
 
 	spin_lock_irqsave(&rdev->priv->lock, flags);
 	rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false);
 	rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false);
+	bitmap_clear(rdev->priv->opened_ports, rdev->port, 1);
 	spin_unlock_irqrestore(&rdev->priv->lock, flags);
 
-	phy_stop(ndev->phydev);
 	napi_disable(&rdev->napi);
 
+	if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS))
+		iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID);
+
+	for (tag = find_first_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT);
+	     tag < TS_TAGS_PER_PORT;
+	     tag = find_next_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT, tag + 1)) {
+		ts_skb = xchg(&rdev->ts_skb[tag], NULL);
+		clear_bit(tag, rdev->ts_skb_used);
+		if (ts_skb)
+			dev_kfree_skb(ts_skb);
+	}
+
 	return 0;
 };
 
@@ -1594,20 +1646,17 @@ static bool rswitch_ext_desc_set_info1(struct rswitch_device *rdev,
 	desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) |
 				  INFO1_IPV(GWCA_IPV_NUM) | INFO1_FMT);
 	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
-		struct rswitch_gwca_ts_info *ts_info;
+		unsigned int tag;
 
-		ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC);
-		if (!ts_info)
+		tag = find_first_zero_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT);
+		if (tag == TS_TAGS_PER_PORT)
 			return false;
+		smp_mb(); /* order bitmap read before rdev->ts_skb[] write */
+		rdev->ts_skb[tag] = skb_get(skb);
+		set_bit(tag, rdev->ts_skb_used);
 
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-		rdev->ts_tag++;
-		desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC);
-
-		ts_info->skb = skb_get(skb);
-		ts_info->port = rdev->port;
-		ts_info->tag = rdev->ts_tag;
-		list_add_tail(&ts_info->list, &rdev->priv->gwca.ts_info_list);
+		desc->info1 |= cpu_to_le64(INFO1_TSUN(tag) | INFO1_TXC);
 
 		skb_tx_timestamp(skb);
 	}
@@ -1681,8 +1730,11 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
 	if (dma_mapping_error(ndev->dev.parent, dma_addr_orig))
 		goto err_kfree;
 
-	gq->skbs[gq->cur] = skb;
-	gq->unmap_addrs[gq->cur] = dma_addr_orig;
+	/* Stored the skb at the last descriptor to avoid skb free before hardware completes send */
+	gq->skbs[(gq->cur + nr_desc - 1) % gq->ring_size] = skb;
+	gq->unmap_addrs[(gq->cur + nr_desc - 1) % gq->ring_size] = dma_addr_orig;
+
+	dma_wmb();
 
 	/* DT_FSTART should be set at last. So, this is reverse order. */
 	for (i = nr_desc; i-- > 0; ) {
@@ -1694,14 +1746,13 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
 			goto err_unmap;
 	}
 
-	wmb();	/* gq->cur must be incremented after die_dt was set */
-
 	gq->cur = rswitch_next_queue_index(gq, true, nr_desc);
 	rswitch_modify(rdev->addr, GWTRC(gq->index), 0, BIT(gq->index % 32));
 
 	return ret;
 
 err_unmap:
+	gq->skbs[(gq->cur + nr_desc - 1) % gq->ring_size] = NULL;
 	dma_unmap_single(ndev->dev.parent, dma_addr_orig, skb->len, DMA_TO_DEVICE);
 
 err_kfree:
@@ -1889,7 +1940,6 @@ static int rswitch_device_alloc(struct rswitch_private *priv, unsigned int index
 	rdev->np_port = rswitch_get_port_node(rdev);
 	rdev->disabled = !rdev->np_port;
 	err = of_get_ethdev_address(rdev->np_port, ndev);
-	of_node_put(rdev->np_port);
 	if (err) {
 		if (is_valid_ether_addr(rdev->etha->mac_addr))
 			eth_hw_addr_set(ndev, rdev->etha->mac_addr);
@@ -1901,9 +1951,6 @@ static int rswitch_device_alloc(struct rswitch_private *priv, unsigned int index
 	if (err < 0)
 		goto out_get_params;
 
-	if (rdev->priv->gwca.speed < rdev->etha->speed)
-		rdev->priv->gwca.speed = rdev->etha->speed;
-
 	err = rswitch_rxdmac_alloc(ndev);
 	if (err < 0)
 		goto out_rxdmac;
@@ -1919,6 +1966,7 @@ out_txdmac:
 
 out_rxdmac:
 out_get_params:
+	of_node_put(rdev->np_port);
 	netif_napi_del(&rdev->napi);
 	free_netdev(ndev);
 
@@ -1932,6 +1980,7 @@ static void rswitch_device_free(struct rswitch_private *priv, unsigned int index
 
 	rswitch_txdmac_free(ndev);
 	rswitch_rxdmac_free(ndev);
+	of_node_put(rdev->np_port);
 	netif_napi_del(&rdev->napi);
 	free_netdev(ndev);
 }
diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h
index 72e3ff596d31..532192cbca4b 100644
--- a/drivers/net/ethernet/renesas/rswitch.h
+++ b/drivers/net/ethernet/renesas/rswitch.h
@@ -12,6 +12,7 @@
 
 #define RSWITCH_MAX_NUM_QUEUES	128
 
+#define RSWITCH_NUM_AGENTS	5
 #define RSWITCH_NUM_PORTS	3
 #define rswitch_for_each_enabled_port(priv, i)		\
 	for (i = 0; i < RSWITCH_NUM_PORTS; i++)		\
@@ -724,35 +725,28 @@ enum rswitch_etha_mode {
 
 #define EAVCC_VEM_SC_TAG	(0x3 << 16)
 
-#define MPIC_PIS_MII		0x00
-#define MPIC_PIS_GMII		0x02
-#define MPIC_PIS_XGMII		0x04
-#define MPIC_LSC_SHIFT		3
-#define MPIC_LSC_100M		(1 << MPIC_LSC_SHIFT)
-#define MPIC_LSC_1G		(2 << MPIC_LSC_SHIFT)
-#define MPIC_LSC_2_5G		(3 << MPIC_LSC_SHIFT)
-
-#define MDIO_READ_C45		0x03
-#define MDIO_WRITE_C45		0x01
+#define MPIC_PIS		GENMASK(2, 0)
+#define MPIC_PIS_GMII		2
+#define MPIC_PIS_XGMII		4
+#define MPIC_LSC		GENMASK(5, 3)
+#define MPIC_LSC_100M		1
+#define MPIC_LSC_1G		2
+#define MPIC_LSC_2_5G		3
+#define MPIC_PSMCS		GENMASK(22, 16)
+#define MPIC_PSMHT		GENMASK(26, 24)
 
 #define MPSM_PSME		BIT(0)
-#define MPSM_MFF_C45		BIT(2)
-#define MPSM_PRD_SHIFT		16
-#define MPSM_PRD_MASK		GENMASK(31, MPSM_PRD_SHIFT)
-
-/* Completion flags */
-#define MMIS1_PAACS             BIT(2) /* Address */
-#define MMIS1_PWACS             BIT(1) /* Write */
-#define MMIS1_PRACS             BIT(0) /* Read */
-#define MMIS1_CLEAR_FLAGS       0xf
-
-#define MPIC_PSMCS_SHIFT	16
-#define MPIC_PSMCS_MASK		GENMASK(22, MPIC_PSMCS_SHIFT)
-#define MPIC_PSMCS(val)		((val) << MPIC_PSMCS_SHIFT)
-
-#define MPIC_PSMHT_SHIFT	24
-#define MPIC_PSMHT_MASK		GENMASK(26, MPIC_PSMHT_SHIFT)
-#define MPIC_PSMHT(val)		((val) << MPIC_PSMHT_SHIFT)
+#define MPSM_MFF		BIT(2)
+#define MPSM_MMF_C22		0
+#define MPSM_MMF_C45		1
+#define MPSM_PDA		GENMASK(7, 3)
+#define MPSM_PRA		GENMASK(12, 8)
+#define MPSM_POP		GENMASK(14, 13)
+#define MPSM_POP_ADDRESS	0
+#define MPSM_POP_WRITE		1
+#define MPSM_POP_READ_C22	2
+#define MPSM_POP_READ_C45	3
+#define MPSM_PRD		GENMASK(31, 16)
 
 #define MLVC_PLV		BIT(16)
 
@@ -806,6 +800,7 @@ enum rswitch_gwca_mode {
 #define CABPPFLC_INIT_VALUE	0x00800080
 
 /* MFWD */
+#define FWPC0(i)		(FWPC00 + (i) * 0x10)
 #define FWPC0_LTHTA		BIT(0)
 #define FWPC0_IP4UE		BIT(3)
 #define FWPC0_IP4TE		BIT(4)
@@ -819,15 +814,15 @@ enum rswitch_gwca_mode {
 #define FWPC0_MACHMA		BIT(27)
 #define FWPC0_VLANSA		BIT(28)
 
-#define FWPC0(i)		(FWPC00 + (i) * 0x10)
-#define FWPC0_DEFAULT		(FWPC0_LTHTA | FWPC0_IP4UE | FWPC0_IP4TE | \
-				 FWPC0_IP4OE | FWPC0_L2SE | FWPC0_IP4EA | \
-				 FWPC0_IPDSA | FWPC0_IPHLA | FWPC0_MACSDA | \
-				 FWPC0_MACHLA |	FWPC0_MACHMA | FWPC0_VLANSA)
 #define FWPC1(i)		(FWPC10 + (i) * 0x10)
+#define FWCP1_LTHFW		GENMASK(16 + (RSWITCH_NUM_AGENTS - 1), 16)
 #define FWPC1_DDE		BIT(0)
 
-#define	FWPBFC(i)		(FWPBFC0 + (i) * 0x10)
+#define FWPC2(i)		(FWPC20 + (i) * 0x10)
+#define FWCP2_LTWFW		GENMASK(16 + (RSWITCH_NUM_AGENTS - 1), 16)
+
+#define FWPBFC(i)		(FWPBFC0 + (i) * 0x10)
+#define FWPBFC_PBDV		GENMASK(RSWITCH_NUM_AGENTS - 1, 0)
 
 #define FWPBFCSDC(j, i)         (FWPBFCSDC00 + (i) * 0x10 + (j) * 0x04)
 
@@ -972,14 +967,6 @@ struct rswitch_gwca_queue {
 	};
 };
 
-struct rswitch_gwca_ts_info {
-	struct sk_buff *skb;
-	struct list_head list;
-
-	int port;
-	u8 tag;
-};
-
 #define RSWITCH_NUM_IRQ_REGS	(RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32))
 struct rswitch_gwca {
 	unsigned int index;
@@ -989,14 +976,13 @@ struct rswitch_gwca {
 	struct rswitch_gwca_queue *queues;
 	int num_queues;
 	struct rswitch_gwca_queue ts_queue;
-	struct list_head ts_info_list;
 	DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES);
 	u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS];
 	u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS];
-	int speed;
 };
 
 #define NUM_QUEUES_PER_NDEV	2
+#define TS_TAGS_PER_PORT	256
 struct rswitch_device {
 	struct rswitch_private *priv;
 	struct net_device *ndev;
@@ -1004,7 +990,8 @@ struct rswitch_device {
 	void __iomem *addr;
 	struct rswitch_gwca_queue *tx_queue;
 	struct rswitch_gwca_queue *rx_queue;
-	u8 ts_tag;
+	struct sk_buff *ts_skb[TS_TAGS_PER_PORT];
+	DECLARE_BITMAP(ts_skb_used, TS_TAGS_PER_PORT);
 	bool disabled;
 
 	int port;
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 8887b8921009..5fc8027c92c7 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3494,10 +3494,12 @@ static int sh_eth_suspend(struct device *dev)
 
 	netif_device_detach(ndev);
 
+	rtnl_lock();
 	if (mdp->wol_enabled)
 		ret = sh_eth_wol_setup(ndev);
 	else
 		ret = sh_eth_close(ndev);
+	rtnl_unlock();
 
 	return ret;
 }
@@ -3511,10 +3513,12 @@ static int sh_eth_resume(struct device *dev)
 	if (!netif_running(ndev))
 		return 0;
 
+	rtnl_lock();
 	if (mdp->wol_enabled)
 		ret = sh_eth_wol_restore(ndev);
 	else
 		ret = sh_eth_open(ndev);
+	rtnl_unlock();
 
 	if (ret < 0)
 		return ret;
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index fe0bf1d3217a..36af94a2e062 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2576,7 +2576,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 	rocker_carrier_init(rocker_port);
 
 	dev->features |= NETIF_F_SG;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	/* MTU range: 68 - 9000 */
 	dev->min_mtu = ROCKER_PORT_MIN_MTU;
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 826990459fa4..61e50517c05b 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -1933,7 +1933,7 @@ static int ofdpa_port_fdb(struct ofdpa_port *ofdpa_port,
 	spin_unlock_irqrestore(&ofdpa->fdb_tbl_lock, lock_flags);
 
 	/* Check if adding and already exists, or removing and can't find */
-	if (!found != !removing) {
+	if (!found == removing) {
 		kfree(fdb);
 		if (!found && removing)
 			return 0;
@@ -1982,7 +1982,7 @@ err_out:
 
 static void ofdpa_fdb_cleanup(struct timer_list *t)
 {
-	struct ofdpa *ofdpa = from_timer(ofdpa, t, fdb_cleanup_timer);
+	struct ofdpa *ofdpa = timer_container_of(ofdpa, t, fdb_cleanup_timer);
 	struct ofdpa_port *ofdpa_port;
 	struct ofdpa_fdb_tbl_entry *entry;
 	struct hlist_node *tmp;
@@ -2386,7 +2386,7 @@ static void ofdpa_fini(struct rocker *rocker)
 	struct hlist_node *tmp;
 	int bkt;
 
-	del_timer_sync(&ofdpa->fdb_cleanup_timer);
+	timer_delete_sync(&ofdpa->fdb_cleanup_timer);
 	flush_workqueue(rocker->rocker_owq);
 
 	spin_lock_irqsave(&ofdpa->flow_tbl_lock, flags);
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 12c8396b6942..75bad561b352 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -91,7 +91,7 @@ void sxgbe_disable_eee_mode(struct sxgbe_priv_data * const priv)
 {
 	/* Exit and disable EEE in case of we are in LPI state. */
 	priv->hw->mac->reset_eee_mode(priv->ioaddr);
-	del_timer_sync(&priv->eee_ctrl_timer);
+	timer_delete_sync(&priv->eee_ctrl_timer);
 	priv->tx_path_in_lpi_mode = false;
 }
 
@@ -104,7 +104,8 @@ void sxgbe_disable_eee_mode(struct sxgbe_priv_data * const priv)
  */
 static void sxgbe_eee_ctrl_timer(struct timer_list *t)
 {
-	struct sxgbe_priv_data *priv = from_timer(priv, t, eee_ctrl_timer);
+	struct sxgbe_priv_data *priv = timer_container_of(priv, t,
+							  eee_ctrl_timer);
 
 	sxgbe_enable_eee_mode(priv);
 	mod_timer(&priv->eee_ctrl_timer, SXGBE_LPI_TIMER(eee_timer));
@@ -1012,7 +1013,7 @@ static void sxgbe_disable_mtl_engine(struct sxgbe_priv_data *priv)
  */
 static void sxgbe_tx_timer(struct timer_list *t)
 {
-	struct sxgbe_tx_queue *p = from_timer(p, t, txtimer);
+	struct sxgbe_tx_queue *p = timer_container_of(p, t, txtimer);
 	sxgbe_tx_queue_clean(p);
 }
 
@@ -1044,7 +1045,7 @@ static void sxgbe_tx_del_timer(struct sxgbe_priv_data *priv)
 
 	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
 		struct sxgbe_tx_queue *p = priv->txq[queue_num];
-		del_timer_sync(&p->txtimer);
+		timer_delete_sync(&p->txtimer);
 	}
 }
 
@@ -1208,7 +1209,7 @@ static int sxgbe_release(struct net_device *dev)
 	struct sxgbe_priv_data *priv = netdev_priv(dev);
 
 	if (priv->eee_enabled)
-		del_timer_sync(&priv->eee_ctrl_timer);
+		timer_delete_sync(&priv->eee_ctrl_timer);
 
 	/* Stop and disconnect the PHY */
 	if (dev->phydev) {
diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c
index 9319a2675e7b..20dad39b5ab9 100644
--- a/drivers/net/ethernet/seeq/ether3.c
+++ b/drivers/net/ethernet/seeq/ether3.c
@@ -170,7 +170,7 @@ ether3_setbuffer(struct net_device *dev, buffer_rw_t read, int start)
  */
 static void ether3_ledoff(struct timer_list *t)
 {
-	struct dev_priv *private = from_timer(private, t, timer);
+	struct dev_priv *private = timer_container_of(private, t, timer);
 	struct net_device *dev = private->dev;
 
 	ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2);
@@ -181,7 +181,7 @@ static void ether3_ledoff(struct timer_list *t)
  */
 static inline void ether3_ledon(struct net_device *dev)
 {
-	del_timer(&priv(dev)->timer);
+	timer_delete(&priv(dev)->timer);
 	priv(dev)->timer.expires = jiffies + HZ / 50; /* leave on for 1/50th second */
 	add_timer(&priv(dev)->timer);
 	if (priv(dev)->regs.config2 & CFG2_CTRLO)
@@ -454,7 +454,7 @@ static void ether3_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	unsigned long flags;
 
-	del_timer(&priv(dev)->timer);
+	timer_delete(&priv(dev)->timer);
 
 	local_irq_save(flags);
 	printk(KERN_ERR "%s: transmit timed out, network cable problem?\n", dev->name);
@@ -851,7 +851,7 @@ static void ether3_remove(struct expansion_card *ec)
 	ecard_set_drvdata(ec, NULL);
 
 	unregister_netdev(dev);
-	del_timer_sync(&priv(dev)->timer);
+	timer_delete_sync(&priv(dev)->timer);
 	free_netdev(dev);
 	ecard_release_resources(ec);
 }
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 3eb55dcfa8a6..c4c43434f314 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -38,8 +38,9 @@ config SFC_MTD
 	default y
 	help
 	  This exposes the on-board flash and/or EEPROM as MTD devices
-	  (e.g. /dev/mtd1).  This is required to update the firmware or
-	  the boot configuration under Linux.
+	  (e.g. /dev/mtd1).  This is required to update the boot
+	  configuration under Linux, or use some older userland tools to
+	  update the firmware.
 config SFC_MCDI_MON
 	bool "Solarflare SFC9100-family hwmon support"
 	depends on SFC && HWMON && !(SFC=y && HWMON=m)
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index 8f446b9bd5ee..d99039ec468d 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -7,7 +7,7 @@ sfc-y			+= efx.o efx_common.o efx_channels.o nic.o \
 			   mcdi_functions.o mcdi_filters.o mcdi_mon.o \
 			   ef100.o ef100_nic.o ef100_netdev.o \
 			   ef100_ethtool.o ef100_rx.o ef100_tx.o \
-			   efx_devlink.o
+			   efx_devlink.o efx_reflash.o
 sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o ef10_sriov.o ef100_sriov.o ef100_rep.o \
                            mae.o tc.o tc_bindings.o tc_counters.o \
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 452009ed7a43..47349c148c0c 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3501,7 +3501,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_METADATA_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_METADATA_OUT_LENMAX);
 	const struct efx_ef10_nvram_type_info *info;
-	size_t size, erase_size, outlen;
+	size_t size, erase_size, write_size, outlen;
 	int type_idx = 0;
 	bool protected;
 	int rc;
@@ -3516,7 +3516,8 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	if (info->port != efx_port_num(efx))
 		return -ENODEV;
 
-	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected);
+	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &write_size,
+				 &protected);
 	if (rc)
 		return rc;
 	if (protected &&
@@ -3561,6 +3562,8 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	if (!erase_size)
 		part->common.mtd.flags |= MTD_NO_ERASE;
 
+	part->common.mtd.writesize = write_size;
+
 	return 0;
 }
 
@@ -4416,6 +4419,7 @@ const struct efx_nic_type efx_x4_nic_type = {
 	.can_rx_scatter = true,
 	.always_rx_scatter = true,
 	.option_descriptors = true,
+	.flash_auto_partition = true,
 	.min_interrupt_mode = EFX_INT_MODE_MSIX,
 	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
 	.offload_features = EF10_OFFLOAD_FEATURES,
diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c
index 7f7d560cb2b4..3a06e3b1bd6b 100644
--- a/drivers/net/ethernet/sfc/ef100_netdev.c
+++ b/drivers/net/ethernet/sfc/ef100_netdev.c
@@ -450,9 +450,9 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data)
 	net_dev->hw_enc_features |= efx->type->offload_features;
 	net_dev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_SG |
 				  NETIF_F_HIGHDMA | NETIF_F_ALL_TSO;
-	netif_set_tso_max_segs(net_dev,
-			       ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS_DEFAULT);
-	efx->mdio.dev = net_dev;
+	nic_data = efx->nic_data;
+	netif_set_tso_max_size(efx->net_dev, nic_data->tso_max_payload_len);
+	netif_set_tso_max_segs(efx->net_dev, nic_data->tso_max_payload_num_segs);
 
 	rc = efx_ef100_init_datapath_caps(efx);
 	if (rc < 0)
@@ -478,7 +478,6 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data)
 	/* Don't fail init if RSS setup doesn't work. */
 	efx_mcdi_push_default_indir_table(efx, efx->n_rx_channels);
 
-	nic_data = efx->nic_data;
 	rc = ef100_get_mac_address(efx, net_dev->perm_addr, CLIENT_HANDLE_SELF,
 				   efx->type->is_vf);
 	if (rc)
diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c
index 62e674d6ff60..3ad95a4c8af2 100644
--- a/drivers/net/ethernet/sfc/ef100_nic.c
+++ b/drivers/net/ethernet/sfc/ef100_nic.c
@@ -887,8 +887,7 @@ static int ef100_process_design_param(struct efx_nic *efx,
 	case ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS:
 		/* We always put HDR_NUM_SEGS=1 in our TSO descriptors */
 		if (!reader->value) {
-			netif_err(efx, probe, efx->net_dev,
-				  "TSO_MAX_HDR_NUM_SEGS < 1\n");
+			pci_err(efx->pci_dev, "TSO_MAX_HDR_NUM_SEGS < 1\n");
 			return -EOPNOTSUPP;
 		}
 		return 0;
@@ -901,32 +900,28 @@ static int ef100_process_design_param(struct efx_nic *efx,
 		 */
 		if (!reader->value || reader->value > EFX_MIN_DMAQ_SIZE ||
 		    EFX_MIN_DMAQ_SIZE % (u32)reader->value) {
-			netif_err(efx, probe, efx->net_dev,
-				  "%s size granularity is %llu, can't guarantee safety\n",
-				  reader->type == ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY ? "RXQ" : "TXQ",
-				  reader->value);
+			pci_err(efx->pci_dev,
+				"%s size granularity is %llu, can't guarantee safety\n",
+				reader->type == ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY ? "RXQ" : "TXQ",
+				reader->value);
 			return -EOPNOTSUPP;
 		}
 		return 0;
 	case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN:
 		nic_data->tso_max_payload_len = min_t(u64, reader->value,
 						      GSO_LEGACY_MAX_SIZE);
-		netif_set_tso_max_size(efx->net_dev,
-				       nic_data->tso_max_payload_len);
 		return 0;
 	case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS:
 		nic_data->tso_max_payload_num_segs = min_t(u64, reader->value, 0xffff);
-		netif_set_tso_max_segs(efx->net_dev,
-				       nic_data->tso_max_payload_num_segs);
 		return 0;
 	case ESE_EF100_DP_GZ_TSO_MAX_NUM_FRAMES:
 		nic_data->tso_max_frames = min_t(u64, reader->value, 0xffff);
 		return 0;
 	case ESE_EF100_DP_GZ_COMPAT:
 		if (reader->value) {
-			netif_err(efx, probe, efx->net_dev,
-				  "DP_COMPAT has unknown bits %#llx, driver not compatible with this hw\n",
-				  reader->value);
+			pci_err(efx->pci_dev,
+				"DP_COMPAT has unknown bits %#llx, driver not compatible with this hw\n",
+				reader->value);
 			return -EOPNOTSUPP;
 		}
 		return 0;
@@ -946,10 +941,10 @@ static int ef100_process_design_param(struct efx_nic *efx,
 		 * So the value of this shouldn't matter.
 		 */
 		if (reader->value != ESE_EF100_DP_GZ_VI_STRIDES_DEFAULT)
-			netif_dbg(efx, probe, efx->net_dev,
-				  "NIC has other than default VI_STRIDES (mask "
-				  "%#llx), early probing might use wrong one\n",
-				  reader->value);
+			pci_dbg(efx->pci_dev,
+				"NIC has other than default VI_STRIDES (mask "
+				"%#llx), early probing might use wrong one\n",
+				reader->value);
 		return 0;
 	case ESE_EF100_DP_GZ_RX_MAX_RUNT:
 		/* Driver doesn't look at L2_STATUS:LEN_ERR bit, so we don't
@@ -961,9 +956,9 @@ static int ef100_process_design_param(struct efx_nic *efx,
 		/* Host interface says "Drivers should ignore design parameters
 		 * that they do not recognise."
 		 */
-		netif_dbg(efx, probe, efx->net_dev,
-			  "Ignoring unrecognised design parameter %u\n",
-			  reader->type);
+		pci_dbg(efx->pci_dev,
+			"Ignoring unrecognised design parameter %u\n",
+			reader->type);
 		return 0;
 	}
 }
@@ -999,13 +994,13 @@ static int ef100_check_design_params(struct efx_nic *efx)
 	 */
 	if (reader.state != EF100_TLV_TYPE) {
 		if (reader.state == EF100_TLV_TYPE_CONT)
-			netif_err(efx, probe, efx->net_dev,
-				  "truncated design parameter (incomplete type %u)\n",
-				  reader.type);
+			pci_err(efx->pci_dev,
+				"truncated design parameter (incomplete type %u)\n",
+				reader.type);
 		else
-			netif_err(efx, probe, efx->net_dev,
-				  "truncated design parameter %u\n",
-				  reader.type);
+			pci_err(efx->pci_dev,
+				"truncated design parameter %u\n",
+				reader.type);
 		rc = -EIO;
 	}
 out:
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 650136dfc642..112e55b98ed3 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -476,28 +476,6 @@ void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
 
 /**************************************************************************
  *
- * ioctls
- *
- *************************************************************************/
-
-/* Net device ioctl
- * Context: process, rtnl_lock() held.
- */
-static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	struct mii_ioctl_data *data = if_mii(ifr);
-
-	/* Convert phy_id from older PRTAD/DEVAD format */
-	if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
-	    (data->phy_id & 0xfc00) == 0x0400)
-		data->phy_id ^= MDIO_PHY_ID_C45 | 0x0400;
-
-	return mdio_mii_ioctl(&efx->mdio, data, cmd);
-}
-
-/**************************************************************************
- *
  * Kernel net device interface
  *
  *************************************************************************/
@@ -593,7 +571,6 @@ static const struct net_device_ops efx_netdev_ops = {
 	.ndo_tx_timeout		= efx_watchdog,
 	.ndo_start_xmit		= efx_hard_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_eth_ioctl		= efx_ioctl,
 	.ndo_change_mtu		= efx_change_mtu,
 	.ndo_set_mac_address	= efx_set_mac_address,
 	.ndo_set_rx_mode	= efx_set_rx_mode,
@@ -1201,7 +1178,6 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	rc = efx_init_struct(efx, pci_dev);
 	if (rc)
 		goto fail1;
-	efx->mdio.dev = net_dev;
 
 	pci_info(pci_dev, "Solarflare NIC detected\n");
 
diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index c88ec3e24836..5a14d94163b1 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -1003,6 +1003,7 @@ int efx_init_struct(struct efx_nic *efx, struct pci_dev *pci_dev)
 	INIT_LIST_HEAD(&efx->vf_reps);
 	INIT_WORK(&efx->mac_work, efx_mac_work);
 	init_waitqueue_head(&efx->flush_wq);
+	mutex_init(&efx->reflash_mutex);
 
 	efx->tx_queues_per_channel = 1;
 	efx->rxq_entries = EFX_DEFAULT_DMAQ_SIZE;
diff --git a/drivers/net/ethernet/sfc/efx_devlink.c b/drivers/net/ethernet/sfc/efx_devlink.c
index 3cd750820fdd..d842c60dfc10 100644
--- a/drivers/net/ethernet/sfc/efx_devlink.c
+++ b/drivers/net/ethernet/sfc/efx_devlink.c
@@ -19,6 +19,7 @@
 #include "mae.h"
 #include "ef100_rep.h"
 #endif
+#include "efx_reflash.h"
 
 struct efx_devlink {
 	struct efx_nic *efx;
@@ -615,7 +616,19 @@ static int efx_devlink_info_get(struct devlink *devlink,
 	return 0;
 }
 
+static int efx_devlink_flash_update(struct devlink *devlink,
+				    struct devlink_flash_update_params *params,
+				    struct netlink_ext_ack *extack)
+{
+	struct efx_devlink *devlink_private = devlink_priv(devlink);
+	struct efx_nic *efx = devlink_private->efx;
+
+	return efx_reflash_flash_firmware(efx, params->fw, extack);
+}
+
 static const struct devlink_ops sfc_devlink_ops = {
+	.supported_flash_update_params	= 0,
+	.flash_update			= efx_devlink_flash_update,
 	.info_get			= efx_devlink_info_get,
 };
 
diff --git a/drivers/net/ethernet/sfc/efx_reflash.c b/drivers/net/ethernet/sfc/efx_reflash.c
new file mode 100644
index 000000000000..b12e95f1c80a
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_reflash.c
@@ -0,0 +1,522 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for AMD network controllers and boards
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include <linux/crc32.h>
+#include <net/devlink.h>
+#include "efx_reflash.h"
+#include "net_driver.h"
+#include "fw_formats.h"
+#include "mcdi_pcol.h"
+#include "mcdi.h"
+
+/* Try to parse a Reflash header at the specified offset */
+static bool efx_reflash_parse_reflash_header(const struct firmware *fw,
+					     size_t header_offset, u32 *type,
+					     u32 *subtype, const u8 **data,
+					     size_t *data_size)
+{
+	size_t header_end, trailer_offset, trailer_end;
+	u32 magic, version, payload_size, header_len;
+	const u8 *header, *trailer;
+	u32 expected_crc, crc;
+
+	if (check_add_overflow(header_offset, EFX_REFLASH_HEADER_LENGTH_OFST +
+					      EFX_REFLASH_HEADER_LENGTH_LEN,
+			       &header_end))
+		return false;
+	if (fw->size < header_end)
+		return false;
+
+	header = fw->data + header_offset;
+	magic = get_unaligned_le32(header + EFX_REFLASH_HEADER_MAGIC_OFST);
+	if (magic != EFX_REFLASH_HEADER_MAGIC_VALUE)
+		return false;
+
+	version = get_unaligned_le32(header + EFX_REFLASH_HEADER_VERSION_OFST);
+	if (version != EFX_REFLASH_HEADER_VERSION_VALUE)
+		return false;
+
+	payload_size = get_unaligned_le32(header + EFX_REFLASH_HEADER_PAYLOAD_SIZE_OFST);
+	header_len = get_unaligned_le32(header + EFX_REFLASH_HEADER_LENGTH_OFST);
+	if (check_add_overflow(header_offset, header_len, &trailer_offset) ||
+	    check_add_overflow(trailer_offset, payload_size, &trailer_offset) ||
+	    check_add_overflow(trailer_offset, EFX_REFLASH_TRAILER_LEN,
+			       &trailer_end))
+		return false;
+	if (fw->size < trailer_end)
+		return false;
+
+	trailer = fw->data + trailer_offset;
+	expected_crc = get_unaligned_le32(trailer + EFX_REFLASH_TRAILER_CRC_OFST);
+	/* Addition could overflow u32, but not size_t since we already
+	 * checked trailer_offset didn't overflow.  So cast to size_t first.
+	 */
+	crc = crc32_le(0, header, (size_t)header_len + payload_size);
+	if (crc != expected_crc)
+		return false;
+
+	*type = get_unaligned_le32(header + EFX_REFLASH_HEADER_FIRMWARE_TYPE_OFST);
+	*subtype = get_unaligned_le32(header + EFX_REFLASH_HEADER_FIRMWARE_SUBTYPE_OFST);
+	if (*type == EFX_REFLASH_FIRMWARE_TYPE_BUNDLE) {
+		/* All the bundle data is written verbatim to NVRAM */
+		*data = fw->data;
+		*data_size = fw->size;
+	} else {
+		/* Other payload types strip the reflash header and trailer
+		 * from the data written to NVRAM
+		 */
+		*data = header + header_len;
+		*data_size = payload_size;
+	}
+
+	return true;
+}
+
+/* Map from FIRMWARE_TYPE to NVRAM_PARTITION_TYPE */
+static int efx_reflash_partition_type(u32 type, u32 subtype,
+				      u32 *partition_type,
+				      u32 *partition_subtype)
+{
+	int rc = 0;
+
+	switch (type) {
+	case EFX_REFLASH_FIRMWARE_TYPE_BOOTROM:
+		*partition_type = NVRAM_PARTITION_TYPE_EXPANSION_ROM;
+		*partition_subtype = subtype;
+		break;
+	case EFX_REFLASH_FIRMWARE_TYPE_BUNDLE:
+		*partition_type = NVRAM_PARTITION_TYPE_BUNDLE;
+		*partition_subtype = subtype;
+		break;
+	default:
+		/* Not supported */
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+/* Try to parse a SmartNIC image header at the specified offset */
+static bool efx_reflash_parse_snic_header(const struct firmware *fw,
+					  size_t header_offset,
+					  u32 *partition_type,
+					  u32 *partition_subtype,
+					  const u8 **data, size_t *data_size)
+{
+	u32 magic, version, payload_size, header_len, expected_crc, crc;
+	size_t header_end, payload_end;
+	const u8 *header;
+
+	if (check_add_overflow(header_offset, EFX_SNICIMAGE_HEADER_MINLEN,
+			       &header_end) ||
+	    fw->size < header_end)
+		return false;
+
+	header = fw->data + header_offset;
+	magic = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_MAGIC_OFST);
+	if (magic != EFX_SNICIMAGE_HEADER_MAGIC_VALUE)
+		return false;
+
+	version = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_VERSION_OFST);
+	if (version != EFX_SNICIMAGE_HEADER_VERSION_VALUE)
+		return false;
+
+	header_len = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_LENGTH_OFST);
+	if (check_add_overflow(header_offset, header_len, &header_end))
+		return false;
+	payload_size = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_PAYLOAD_SIZE_OFST);
+	if (check_add_overflow(header_end, payload_size, &payload_end) ||
+	    fw->size < payload_end)
+		return false;
+
+	expected_crc = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_CRC_OFST);
+
+	/* Calculate CRC omitting the expected CRC field itself */
+	crc = crc32_le(~0, header, EFX_SNICIMAGE_HEADER_CRC_OFST);
+	crc = ~crc32_le(crc,
+			header + EFX_SNICIMAGE_HEADER_CRC_OFST +
+			EFX_SNICIMAGE_HEADER_CRC_LEN,
+			header_len + payload_size - EFX_SNICIMAGE_HEADER_CRC_OFST -
+			EFX_SNICIMAGE_HEADER_CRC_LEN);
+	if (crc != expected_crc)
+		return false;
+
+	*partition_type =
+		get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_PARTITION_TYPE_OFST);
+	*partition_subtype =
+		get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_PARTITION_SUBTYPE_OFST);
+	*data = fw->data;
+	*data_size = fw->size;
+	return true;
+}
+
+/* Try to parse a SmartNIC bundle header at the specified offset */
+static bool efx_reflash_parse_snic_bundle_header(const struct firmware *fw,
+						 size_t header_offset,
+						 u32 *partition_type,
+						 u32 *partition_subtype,
+						 const u8 **data,
+						 size_t *data_size)
+{
+	u32 magic, version, bundle_type, header_len, expected_crc, crc;
+	size_t header_end;
+	const u8 *header;
+
+	if (check_add_overflow(header_offset, EFX_SNICBUNDLE_HEADER_LEN,
+			       &header_end))
+		return false;
+	if (fw->size < header_end)
+		return false;
+
+	header = fw->data + header_offset;
+	magic = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_MAGIC_OFST);
+	if (magic != EFX_SNICBUNDLE_HEADER_MAGIC_VALUE)
+		return false;
+
+	version = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_VERSION_OFST);
+	if (version != EFX_SNICBUNDLE_HEADER_VERSION_VALUE)
+		return false;
+
+	bundle_type = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_BUNDLE_TYPE_OFST);
+	if (bundle_type != NVRAM_PARTITION_TYPE_BUNDLE)
+		return false;
+
+	header_len = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_LENGTH_OFST);
+	if (header_len != EFX_SNICBUNDLE_HEADER_LEN)
+		return false;
+
+	expected_crc = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_CRC_OFST);
+	crc = ~crc32_le(~0, header, EFX_SNICBUNDLE_HEADER_CRC_OFST);
+	if (crc != expected_crc)
+		return false;
+
+	*partition_type = NVRAM_PARTITION_TYPE_BUNDLE;
+	*partition_subtype = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_BUNDLE_SUBTYPE_OFST);
+	*data = fw->data;
+	*data_size = fw->size;
+	return true;
+}
+
+/* Try to find a valid firmware payload in the firmware data.
+ * When we recognise a valid header, we parse it for the partition type
+ * (so we know where to ask the MC to write it to) and the location of
+ * the data blob to write.
+ */
+static int efx_reflash_parse_firmware_data(const struct firmware *fw,
+					   u32 *partition_type,
+					   u32 *partition_subtype,
+					   const u8 **data, size_t *data_size)
+{
+	size_t header_offset;
+	u32 type, subtype;
+
+	/* Some packaging formats (such as CMS/PKCS#7 signed images)
+	 * prepend a header for which finding the size is a non-trivial
+	 * task, so step through the firmware data until we find a valid
+	 * header.
+	 *
+	 * The checks are intended to reject firmware data that is clearly not
+	 * in the expected format.  They do not need to be exhaustive as the
+	 * running firmware will perform its own comprehensive validity and
+	 * compatibility checks during the update procedure.
+	 *
+	 * Firmware packages may contain multiple reflash images, e.g. a
+	 * bundle containing one or more other images.  Only check the
+	 * outermost container by stopping after the first candidate image
+	 * found even it is for an unsupported partition type.
+	 */
+	for (header_offset = 0; header_offset < fw->size; header_offset++) {
+		if (efx_reflash_parse_snic_bundle_header(fw, header_offset,
+							 partition_type,
+							 partition_subtype,
+							 data, data_size))
+			return 0;
+
+		if (efx_reflash_parse_snic_header(fw, header_offset,
+						  partition_type,
+						  partition_subtype, data,
+						  data_size))
+			return 0;
+
+		if (efx_reflash_parse_reflash_header(fw, header_offset, &type,
+						     &subtype, data, data_size))
+			return efx_reflash_partition_type(type, subtype,
+							  partition_type,
+							  partition_subtype);
+	}
+
+	return -EINVAL;
+}
+
+/* Limit the number of status updates during the erase or write phases */
+#define EFX_DEVLINK_STATUS_UPDATE_COUNT		50
+
+/* Expected timeout for the efx_mcdi_nvram_update_finish_polled() */
+#define EFX_DEVLINK_UPDATE_FINISH_TIMEOUT	900
+
+/* Ideal erase chunk size.  This is a balance between minimising the number of
+ * MCDI requests to erase an entire partition whilst avoiding tripping the MCDI
+ * RPC timeout.
+ */
+#define EFX_NVRAM_ERASE_IDEAL_CHUNK_SIZE	(64 * 1024)
+
+static int efx_reflash_erase_partition(struct efx_nic *efx,
+				       struct netlink_ext_ack *extack,
+				       struct devlink *devlink, u32 type,
+				       size_t partition_size,
+				       size_t align)
+{
+	size_t chunk, offset, next_update;
+	int rc;
+
+	/* Partitions that cannot be erased or do not require erase before
+	 * write are advertised with a erase alignment/sector size of zero.
+	 */
+	if (align == 0)
+		/* Nothing to do */
+		return 0;
+
+	if (partition_size % align)
+		return -EINVAL;
+
+	/* Erase the entire NVRAM partition a chunk at a time to avoid
+	 * potentially tripping the MCDI RPC timeout.
+	 */
+	if (align >= EFX_NVRAM_ERASE_IDEAL_CHUNK_SIZE)
+		chunk = align;
+	else
+		chunk = rounddown(EFX_NVRAM_ERASE_IDEAL_CHUNK_SIZE, align);
+
+	for (offset = 0, next_update = 0; offset < partition_size; offset += chunk) {
+		if (offset >= next_update) {
+			devlink_flash_update_status_notify(devlink, "Erasing",
+							   NULL, offset,
+							   partition_size);
+			next_update += partition_size / EFX_DEVLINK_STATUS_UPDATE_COUNT;
+		}
+
+		chunk = min_t(size_t, partition_size - offset, chunk);
+		rc = efx_mcdi_nvram_erase(efx, type, offset, chunk);
+		if (rc) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Erase failed for NVRAM partition %#x at %#zx-%#zx",
+					       type, offset, offset + chunk - 1);
+			return rc;
+		}
+	}
+
+	devlink_flash_update_status_notify(devlink, "Erasing", NULL,
+					   partition_size, partition_size);
+
+	return 0;
+}
+
+static int efx_reflash_write_partition(struct efx_nic *efx,
+				       struct netlink_ext_ack *extack,
+				       struct devlink *devlink, u32 type,
+				       const u8 *data, size_t data_size,
+				       size_t align)
+{
+	size_t write_max, chunk, offset, next_update;
+	int rc;
+
+	if (align == 0)
+		return -EINVAL;
+
+	/* Write the NVRAM partition in chunks that are the largest multiple
+	 * of the partition's required write alignment that will fit into the
+	 * MCDI NVRAM_WRITE RPC payload.
+	 */
+	if (efx->type->mcdi_max_ver < 2)
+		write_max = MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_LEN *
+			    MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM;
+	else
+		write_max = MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_LEN *
+			    MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM_MCDI2;
+	chunk = rounddown(write_max, align);
+
+	for (offset = 0, next_update = 0; offset + chunk <= data_size; offset += chunk) {
+		if (offset >= next_update) {
+			devlink_flash_update_status_notify(devlink, "Writing",
+							   NULL, offset,
+							   data_size);
+			next_update += data_size / EFX_DEVLINK_STATUS_UPDATE_COUNT;
+		}
+
+		rc = efx_mcdi_nvram_write(efx, type, offset, data + offset, chunk);
+		if (rc) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Write failed for NVRAM partition %#x at %#zx-%#zx",
+					       type, offset, offset + chunk - 1);
+			return rc;
+		}
+	}
+
+	/* Round up left over data to satisfy write alignment */
+	if (offset < data_size) {
+		size_t remaining = data_size - offset;
+		u8 *buf;
+
+		if (offset >= next_update)
+			devlink_flash_update_status_notify(devlink, "Writing",
+							   NULL, offset,
+							   data_size);
+
+		chunk = roundup(remaining, align);
+		buf = kmalloc(chunk, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		memcpy(buf, data + offset, remaining);
+		memset(buf + remaining, 0xFF, chunk - remaining);
+		rc = efx_mcdi_nvram_write(efx, type, offset, buf, chunk);
+		kfree(buf);
+		if (rc) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Write failed for NVRAM partition %#x at %#zx-%#zx",
+					       type, offset, offset + chunk - 1);
+			return rc;
+		}
+	}
+
+	devlink_flash_update_status_notify(devlink, "Writing", NULL, data_size,
+					   data_size);
+
+	return 0;
+}
+
+int efx_reflash_flash_firmware(struct efx_nic *efx, const struct firmware *fw,
+			       struct netlink_ext_ack *extack)
+{
+	size_t data_size, size, erase_align, write_align;
+	struct devlink *devlink = efx->devlink;
+	u32 type, data_subtype, subtype;
+	const u8 *data;
+	bool protected;
+	int rc;
+
+	if (!efx_has_cap(efx, BUNDLE_UPDATE)) {
+		NL_SET_ERR_MSG_MOD(extack, "NVRAM bundle updates are not supported by the firmware");
+		return -EOPNOTSUPP;
+	}
+
+	mutex_lock(&efx->reflash_mutex);
+
+	devlink_flash_update_status_notify(devlink, "Checking update", NULL, 0, 0);
+
+	if (efx->type->flash_auto_partition) {
+		/* NIC wants entire FW file including headers;
+		 * FW will validate 'subtype' if there is one
+		 */
+		type = NVRAM_PARTITION_TYPE_AUTO;
+		data = fw->data;
+		data_size = fw->size;
+	} else {
+		rc = efx_reflash_parse_firmware_data(fw, &type, &data_subtype, &data,
+						     &data_size);
+		if (rc) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Firmware image validation check failed");
+			goto out_unlock;
+		}
+
+		rc = efx_mcdi_nvram_metadata(efx, type, &subtype, NULL, NULL, 0);
+		if (rc) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Metadata query for NVRAM partition %#x failed",
+					       type);
+			goto out_unlock;
+		}
+
+		if (subtype != data_subtype) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Firmware image is not appropriate for this adapter");
+			rc = -EINVAL;
+			goto out_unlock;
+		}
+	}
+
+	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_align, &write_align,
+				 &protected);
+	if (rc) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Info query for NVRAM partition %#x failed",
+				       type);
+		goto out_unlock;
+	}
+
+	if (protected) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "NVRAM partition %#x is protected",
+				       type);
+		rc = -EPERM;
+		goto out_unlock;
+	}
+
+	if (write_align == 0) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "NVRAM partition %#x is not writable",
+				       type);
+		rc = -EACCES;
+		goto out_unlock;
+	}
+
+	if (erase_align != 0 && size % erase_align) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "NVRAM partition %#x has a bad partition table entry, can't erase it",
+				       type);
+		rc = -EACCES;
+		goto out_unlock;
+	}
+
+	if (data_size > size) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Firmware image is too big for NVRAM partition %#x",
+				       type);
+		rc = -EFBIG;
+		goto out_unlock;
+	}
+
+	devlink_flash_update_status_notify(devlink, "Starting update", NULL, 0, 0);
+
+	rc = efx_mcdi_nvram_update_start(efx, type);
+	if (rc) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Update start request for NVRAM partition %#x failed",
+				       type);
+		goto out_unlock;
+	}
+
+	rc = efx_reflash_erase_partition(efx, extack, devlink, type, size,
+					 erase_align);
+	if (rc)
+		goto out_update_finish;
+
+	rc = efx_reflash_write_partition(efx, extack, devlink, type, data,
+					 data_size, write_align);
+	if (rc)
+		goto out_update_finish;
+
+	devlink_flash_update_timeout_notify(devlink, "Finishing update", NULL,
+					    EFX_DEVLINK_UPDATE_FINISH_TIMEOUT);
+
+out_update_finish:
+	if (rc)
+		/* Don't obscure the return code from an earlier failure */
+		efx_mcdi_nvram_update_finish(efx, type, EFX_UPDATE_FINISH_ABORT);
+	else
+		rc = efx_mcdi_nvram_update_finish_polled(efx, type);
+out_unlock:
+	mutex_unlock(&efx->reflash_mutex);
+	devlink_flash_update_status_notify(devlink, rc ? "Update failed" :
+							 "Update complete",
+					   NULL, 0, 0);
+	return rc;
+}
diff --git a/drivers/net/ethernet/sfc/efx_reflash.h b/drivers/net/ethernet/sfc/efx_reflash.h
new file mode 100644
index 000000000000..3dffac565161
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_reflash.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for AMD network controllers and boards
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef _EFX_REFLASH_H
+#define _EFX_REFLASH_H
+
+#include "net_driver.h"
+#include <linux/firmware.h>
+
+int efx_reflash_flash_firmware(struct efx_nic *efx, const struct firmware *fw,
+			       struct netlink_ext_ack *extack);
+
+#endif /* _EFX_REFLASH_H */
diff --git a/drivers/net/ethernet/sfc/falcon/falcon.c b/drivers/net/ethernet/sfc/falcon/falcon.c
index 4af56333ea49..c44df8e4dd30 100644
--- a/drivers/net/ethernet/sfc/falcon/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon/falcon.c
@@ -1453,8 +1453,8 @@ static void falcon_stats_complete(struct ef4_nic *efx)
 
 static void falcon_stats_timer_func(struct timer_list *t)
 {
-	struct falcon_nic_data *nic_data = from_timer(nic_data, t,
-						      stats_timer);
+	struct falcon_nic_data *nic_data = timer_container_of(nic_data, t,
+							      stats_timer);
 	struct ef4_nic *efx = nic_data->efx;
 
 	spin_lock(&efx->stats_lock);
@@ -2657,7 +2657,7 @@ void falcon_stop_nic_stats(struct ef4_nic *efx)
 	++nic_data->stats_disable_count;
 	spin_unlock_bh(&efx->stats_lock);
 
-	del_timer_sync(&nic_data->stats_timer);
+	timer_delete_sync(&nic_data->stats_timer);
 
 	/* Wait enough time for the most recent transfer to
 	 * complete. */
diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 6bbdb5d2eebf..f69fcf6caca8 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -382,7 +382,8 @@ void ef4_fast_push_rx_descriptors(struct ef4_rx_queue *rx_queue, bool atomic)
 
 void ef4_rx_slow_fill(struct timer_list *t)
 {
-	struct ef4_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
+	struct ef4_rx_queue *rx_queue = timer_container_of(rx_queue, t,
+							   slow_fill);
 
 	/* Post an event to cause NAPI to run and refill the queue */
 	ef4_nic_generate_fill_event(rx_queue);
@@ -791,7 +792,7 @@ void ef4_fini_rx_queue(struct ef4_rx_queue *rx_queue)
 	netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
 		  "shutting down RX queue %d\n", ef4_rx_queue_index(rx_queue));
 
-	del_timer_sync(&rx_queue->slow_fill);
+	timer_delete_sync(&rx_queue->slow_fill);
 
 	/* Release RX buffers from the current read ptr to the write ptr */
 	if (rx_queue->buffer) {
diff --git a/drivers/net/ethernet/sfc/fw_formats.h b/drivers/net/ethernet/sfc/fw_formats.h
new file mode 100644
index 000000000000..cbc350c96013
--- /dev/null
+++ b/drivers/net/ethernet/sfc/fw_formats.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for AMD network controllers and boards
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef _EFX_FW_FORMATS_H
+#define _EFX_FW_FORMATS_H
+
+/* Header layouts of firmware update images recognised by Efx NICs.
+ * The sources-of-truth for these layouts are AMD internal documents
+ * and sfregistry headers, neither of which are available externally
+ * nor usable directly by the driver.
+ *
+ * While each format includes a 'magic number', these are at different
+ * offsets in the various formats, and a legal header for one format
+ * could have the right value in whichever field occupies that offset
+ * to match another format's magic.
+ * Besides, some packaging formats (such as CMS/PKCS#7 signed images)
+ * prepend a header for which finding the size is a non-trivial task;
+ * rather than trying to parse those headers, we search byte-by-byte
+ * through the provided firmware image looking for a valid header.
+ * Thus, format recognition has to include validation of the checksum
+ * field, even though the firmware will validate that itself before
+ * applying the image.
+ */
+
+/* EF10 (Medford2, X2) "reflash" header format.  Defined in SF-121352-AN */
+#define EFX_REFLASH_HEADER_MAGIC_OFST 0
+#define EFX_REFLASH_HEADER_MAGIC_LEN 4
+#define EFX_REFLASH_HEADER_MAGIC_VALUE 0x106F1A5
+
+#define EFX_REFLASH_HEADER_VERSION_OFST 4
+#define EFX_REFLASH_HEADER_VERSION_LEN 4
+#define EFX_REFLASH_HEADER_VERSION_VALUE 4
+
+#define EFX_REFLASH_HEADER_FIRMWARE_TYPE_OFST 8
+#define EFX_REFLASH_HEADER_FIRMWARE_TYPE_LEN 4
+#define EFX_REFLASH_FIRMWARE_TYPE_BOOTROM 0x2
+#define EFX_REFLASH_FIRMWARE_TYPE_BUNDLE 0xd
+
+#define EFX_REFLASH_HEADER_FIRMWARE_SUBTYPE_OFST 12
+#define EFX_REFLASH_HEADER_FIRMWARE_SUBTYPE_LEN 4
+
+#define EFX_REFLASH_HEADER_PAYLOAD_SIZE_OFST 16
+#define EFX_REFLASH_HEADER_PAYLOAD_SIZE_LEN 4
+
+#define EFX_REFLASH_HEADER_LENGTH_OFST 20
+#define EFX_REFLASH_HEADER_LENGTH_LEN 4
+
+/* Reflash trailer */
+#define EFX_REFLASH_TRAILER_CRC_OFST 0
+#define EFX_REFLASH_TRAILER_CRC_LEN 4
+
+#define EFX_REFLASH_TRAILER_LEN	\
+	(EFX_REFLASH_TRAILER_CRC_OFST + EFX_REFLASH_TRAILER_CRC_LEN)
+
+/* EF100 "SmartNIC image" header format.
+ * Defined in sfregistry "src/layout/snic_image_hdr.h".
+ */
+#define EFX_SNICIMAGE_HEADER_MAGIC_OFST 16
+#define EFX_SNICIMAGE_HEADER_MAGIC_LEN 4
+#define EFX_SNICIMAGE_HEADER_MAGIC_VALUE 0x541C057A
+
+#define EFX_SNICIMAGE_HEADER_VERSION_OFST 20
+#define EFX_SNICIMAGE_HEADER_VERSION_LEN 4
+#define EFX_SNICIMAGE_HEADER_VERSION_VALUE 1
+
+#define EFX_SNICIMAGE_HEADER_LENGTH_OFST 24
+#define EFX_SNICIMAGE_HEADER_LENGTH_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_PARTITION_TYPE_OFST 36
+#define EFX_SNICIMAGE_HEADER_PARTITION_TYPE_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_PARTITION_SUBTYPE_OFST 40
+#define EFX_SNICIMAGE_HEADER_PARTITION_SUBTYPE_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_PAYLOAD_SIZE_OFST 60
+#define EFX_SNICIMAGE_HEADER_PAYLOAD_SIZE_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_CRC_OFST 64
+#define EFX_SNICIMAGE_HEADER_CRC_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_MINLEN 256
+
+/* EF100 "SmartNIC bundle" header format.  Defined in SF-122606-TC */
+#define EFX_SNICBUNDLE_HEADER_MAGIC_OFST 0
+#define EFX_SNICBUNDLE_HEADER_MAGIC_LEN 4
+#define EFX_SNICBUNDLE_HEADER_MAGIC_VALUE 0xB1001001
+
+#define EFX_SNICBUNDLE_HEADER_VERSION_OFST 4
+#define EFX_SNICBUNDLE_HEADER_VERSION_LEN 4
+#define EFX_SNICBUNDLE_HEADER_VERSION_VALUE 1
+
+#define EFX_SNICBUNDLE_HEADER_BUNDLE_TYPE_OFST 8
+#define EFX_SNICBUNDLE_HEADER_BUNDLE_TYPE_LEN 4
+
+#define EFX_SNICBUNDLE_HEADER_BUNDLE_SUBTYPE_OFST 12
+#define EFX_SNICBUNDLE_HEADER_BUNDLE_SUBTYPE_LEN 4
+
+#define EFX_SNICBUNDLE_HEADER_LENGTH_OFST 20
+#define EFX_SNICBUNDLE_HEADER_LENGTH_LEN 4
+
+#define EFX_SNICBUNDLE_HEADER_CRC_OFST 224
+#define EFX_SNICBUNDLE_HEADER_CRC_LEN 4
+
+#define EFX_SNICBUNDLE_HEADER_LEN	\
+	(EFX_SNICBUNDLE_HEADER_CRC_OFST + EFX_SNICBUNDLE_HEADER_CRC_LEN)
+
+#endif /* _EFX_FW_FORMATS_H */
diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 4cc7b501135f..ef374a8e05c3 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -217,28 +217,4 @@ _efx_writed_page(struct efx_nic *efx, const efx_dword_t *value,
 					   (reg) != 0xa1c),		\
 			 page)
 
-/* Write TIMER_COMMAND.  This is a page-mapped 32-bit CSR, but a bug
- * in the BIU means that writes to TIMER_COMMAND[0] invalidate the
- * collector register.
- */
-static inline void _efx_writed_page_locked(struct efx_nic *efx,
-					   const efx_dword_t *value,
-					   unsigned int reg,
-					   unsigned int page)
-{
-	unsigned long flags __attribute__ ((unused));
-
-	if (page == 0) {
-		spin_lock_irqsave(&efx->biu_lock, flags);
-		efx_writed(efx, value, efx_paged_reg(efx, page, reg));
-		spin_unlock_irqrestore(&efx->biu_lock, flags);
-	} else {
-		efx_writed(efx, value, efx_paged_reg(efx, page, reg));
-	}
-}
-#define efx_writed_page_locked(efx, value, reg, page)			\
-	_efx_writed_page_locked(efx, value,				\
-				reg + BUILD_BUG_ON_ZERO((reg) != 0x420), \
-				page)
-
 #endif /* EFX_IO_H */
diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c
index 50f097487b14..6fd0c1e9a7d5 100644
--- a/drivers/net/ethernet/sfc/mae.c
+++ b/drivers/net/ethernet/sfc/mae.c
@@ -755,7 +755,7 @@ int efx_mae_match_check_caps_lhs(struct efx_nic *efx,
 	rc = efx_mae_match_check_cap_typ(supported_fields[MAE_FIELD_INGRESS_PORT],
 					 ingress_port_mask_type);
 	if (rc) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "No support for %s mask in field %s\n",
+		NL_SET_ERR_MSG_FMT_MOD(extack, "No support for %s mask in field %s",
 				       mask_type_name(ingress_port_mask_type),
 				       "ingress_port");
 		return rc;
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index d461b1a6ce81..5e9b8def5e42 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -530,7 +530,7 @@ static bool efx_mcdi_complete_async(struct efx_mcdi_iface *mcdi, bool timeout)
 	 * of it aborting the next request.
 	 */
 	if (!timeout)
-		del_timer_sync(&mcdi->async_timer);
+		timer_delete_sync(&mcdi->async_timer);
 
 	spin_lock(&mcdi->async_lock);
 	async = list_first_entry(&mcdi->async_list,
@@ -605,7 +605,7 @@ static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno,
 
 static void efx_mcdi_timeout_async(struct timer_list *t)
 {
-	struct efx_mcdi_iface *mcdi = from_timer(mcdi, t, async_timer);
+	struct efx_mcdi_iface *mcdi = timer_container_of(mcdi, t, async_timer);
 
 	efx_mcdi_complete_async(mcdi, true);
 }
@@ -1122,7 +1122,7 @@ void efx_mcdi_flush_async(struct efx_nic *efx)
 	/* We must be in poll or fail mode so no more requests can be queued */
 	BUG_ON(mcdi->mode == MCDI_MODE_EVENTS);
 
-	del_timer_sync(&mcdi->async_timer);
+	timer_delete_sync(&mcdi->async_timer);
 
 	/* If a request is still running, make sure we give the MC
 	 * time to complete it so that the response won't overwrite our
@@ -1625,12 +1625,15 @@ fail:
 	return rc;
 }
 
+#define EFX_MCDI_NVRAM_DEFAULT_WRITE_LEN 128
+
 int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
 			size_t *size_out, size_t *erase_size_out,
-			bool *protected_out)
+			size_t *write_size_out, bool *protected_out)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_INFO_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_INFO_OUT_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_INFO_V2_OUT_LEN);
+	size_t write_size = 0;
 	size_t outlen;
 	int rc;
 
@@ -1645,6 +1648,12 @@ int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
 		goto fail;
 	}
 
+	if (outlen >= MC_CMD_NVRAM_INFO_V2_OUT_LEN)
+		write_size = MCDI_DWORD(outbuf, NVRAM_INFO_V2_OUT_WRITESIZE);
+	else
+		write_size = EFX_MCDI_NVRAM_DEFAULT_WRITE_LEN;
+
+	*write_size_out = write_size;
 	*size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_SIZE);
 	*erase_size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_ERASESIZE);
 	*protected_out = !!(MCDI_DWORD(outbuf, NVRAM_INFO_OUT_FLAGS) &
@@ -2163,11 +2172,9 @@ out_free:
 	return rc;
 }
 
-#ifdef CONFIG_SFC_MTD
-
 #define EFX_MCDI_NVRAM_LEN_MAX 128
 
-static int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
+int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_START_V2_IN_LEN);
 	int rc;
@@ -2185,6 +2192,8 @@ static int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
 	return rc;
 }
 
+#ifdef CONFIG_SFC_MTD
+
 static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
 			       loff_t offset, u8 *buffer, size_t length)
 {
@@ -2209,13 +2218,20 @@ static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
 	return 0;
 }
 
-static int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
-				loff_t offset, const u8 *buffer, size_t length)
+#endif /* CONFIG_SFC_MTD */
+
+int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
+			 loff_t offset, const u8 *buffer, size_t length)
 {
-	MCDI_DECLARE_BUF(inbuf,
-			 MC_CMD_NVRAM_WRITE_IN_LEN(EFX_MCDI_NVRAM_LEN_MAX));
+	efx_dword_t *inbuf;
+	size_t inlen;
 	int rc;
 
+	inlen = ALIGN(MC_CMD_NVRAM_WRITE_IN_LEN(length), 4);
+	inbuf = kzalloc(inlen, GFP_KERNEL);
+	if (!inbuf)
+		return -ENOMEM;
+
 	MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_TYPE, type);
 	MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_OFFSET, offset);
 	MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_LENGTH, length);
@@ -2223,14 +2239,14 @@ static int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
 
 	BUILD_BUG_ON(MC_CMD_NVRAM_WRITE_OUT_LEN != 0);
 
-	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_WRITE, inbuf,
-			  ALIGN(MC_CMD_NVRAM_WRITE_IN_LEN(length), 4),
-			  NULL, 0, NULL);
+	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_WRITE, inbuf, inlen, NULL, 0, NULL);
+	kfree(inbuf);
+
 	return rc;
 }
 
-static int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
-				loff_t offset, size_t length)
+int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type, loff_t offset,
+			 size_t length)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_ERASE_IN_LEN);
 	int rc;
@@ -2246,7 +2262,8 @@ static int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
 	return rc;
 }
 
-static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
+int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type,
+				 enum efx_update_finish_mode mode)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN);
@@ -2254,22 +2271,41 @@ static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
 	int rc, rc2;
 
 	MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_FINISH_IN_TYPE, type);
-	/* Always set this flag. Old firmware ignores it */
-	MCDI_POPULATE_DWORD_1(inbuf, NVRAM_UPDATE_FINISH_V2_IN_FLAGS,
+
+	/* Old firmware doesn't support background update finish and abort
+	 * operations. Fallback to waiting if the requested mode is not
+	 * supported.
+	 */
+	if (!efx_has_cap(efx, NVRAM_UPDATE_POLL_VERIFY_RESULT) ||
+	    (!efx_has_cap(efx, NVRAM_UPDATE_ABORT_SUPPORTED) &&
+	     mode == EFX_UPDATE_FINISH_ABORT))
+		mode = EFX_UPDATE_FINISH_WAIT;
+
+	MCDI_POPULATE_DWORD_4(inbuf, NVRAM_UPDATE_FINISH_V2_IN_FLAGS,
 			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_REPORT_VERIFY_RESULT,
-			      1);
+			      (mode != EFX_UPDATE_FINISH_ABORT),
+			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_RUN_IN_BACKGROUND,
+			      (mode == EFX_UPDATE_FINISH_BACKGROUND),
+			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_POLL_VERIFY_RESULT,
+			      (mode == EFX_UPDATE_FINISH_POLL),
+			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_ABORT,
+			      (mode == EFX_UPDATE_FINISH_ABORT));
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_FINISH, inbuf, sizeof(inbuf),
 			  outbuf, sizeof(outbuf), &outlen);
 	if (!rc && outlen >= MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN) {
 		rc2 = MCDI_DWORD(outbuf, NVRAM_UPDATE_FINISH_V2_OUT_RESULT_CODE);
-		if (rc2 != MC_CMD_NVRAM_VERIFY_RC_SUCCESS)
+		if (rc2 != MC_CMD_NVRAM_VERIFY_RC_SUCCESS &&
+		    rc2 != MC_CMD_NVRAM_VERIFY_RC_PENDING)
 			netif_err(efx, drv, efx->net_dev,
 				  "NVRAM update failed verification with code 0x%x\n",
 				  rc2);
 		switch (rc2) {
 		case MC_CMD_NVRAM_VERIFY_RC_SUCCESS:
 			break;
+		case MC_CMD_NVRAM_VERIFY_RC_PENDING:
+			rc = -EAGAIN;
+			break;
 		case MC_CMD_NVRAM_VERIFY_RC_CMS_CHECK_FAILED:
 		case MC_CMD_NVRAM_VERIFY_RC_MESSAGE_DIGEST_CHECK_FAILED:
 		case MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHECK_FAILED:
@@ -2284,6 +2320,8 @@ static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
 		case MC_CMD_NVRAM_VERIFY_RC_NO_VALID_SIGNATURES:
 		case MC_CMD_NVRAM_VERIFY_RC_NO_TRUSTED_APPROVERS:
 		case MC_CMD_NVRAM_VERIFY_RC_NO_SIGNATURE_MATCH:
+		case MC_CMD_NVRAM_VERIFY_RC_REJECT_TEST_SIGNED:
+		case MC_CMD_NVRAM_VERIFY_RC_SECURITY_LEVEL_DOWNGRADE:
 			rc = -EPERM;
 			break;
 		default:
@@ -2296,6 +2334,42 @@ static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
 	return rc;
 }
 
+#define	EFX_MCDI_NVRAM_UPDATE_FINISH_INITIAL_POLL_DELAY_MS 5
+#define	EFX_MCDI_NVRAM_UPDATE_FINISH_MAX_POLL_DELAY_MS 5000
+#define	EFX_MCDI_NVRAM_UPDATE_FINISH_RETRIES 185
+
+int efx_mcdi_nvram_update_finish_polled(struct efx_nic *efx, unsigned int type)
+{
+	unsigned int delay = EFX_MCDI_NVRAM_UPDATE_FINISH_INITIAL_POLL_DELAY_MS;
+	unsigned int retry = 0;
+	int rc;
+
+	/* NVRAM updates can take a long time (e.g. up to 1 minute for bundle
+	 * images). Polling for NVRAM update completion ensures that other MCDI
+	 * commands can be issued before the background NVRAM update completes.
+	 *
+	 * The initial call either completes the update synchronously, or
+	 * returns -EAGAIN to indicate processing is continuing. In the latter
+	 * case, we poll for at least 900 seconds, at increasing intervals
+	 * (5ms, 50ms, 500ms, 5s).
+	 */
+	rc = efx_mcdi_nvram_update_finish(efx, type, EFX_UPDATE_FINISH_BACKGROUND);
+	while (rc == -EAGAIN) {
+		if (retry > EFX_MCDI_NVRAM_UPDATE_FINISH_RETRIES)
+			return -ETIMEDOUT;
+		retry++;
+
+		msleep(delay);
+		if (delay < EFX_MCDI_NVRAM_UPDATE_FINISH_MAX_POLL_DELAY_MS)
+			delay *= 10;
+
+		rc = efx_mcdi_nvram_update_finish(efx, type, EFX_UPDATE_FINISH_POLL);
+	}
+	return rc;
+}
+
+#ifdef CONFIG_SFC_MTD
+
 int efx_mcdi_mtd_read(struct mtd_info *mtd, loff_t start,
 		      size_t len, size_t *retlen, u8 *buffer)
 {
@@ -2389,7 +2463,8 @@ int efx_mcdi_mtd_sync(struct mtd_info *mtd)
 
 	if (part->updating) {
 		part->updating = false;
-		rc = efx_mcdi_nvram_update_finish(efx, part->nvram_type);
+		rc = efx_mcdi_nvram_update_finish(efx, part->nvram_type,
+						  EFX_UPDATE_FINISH_WAIT);
 	}
 
 	return rc;
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index cdb17d7c147f..3755cd3fe1e6 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -392,7 +392,7 @@ int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, u32 dest_evq);
 int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out);
 int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
 			size_t *size_out, size_t *erase_size_out,
-			bool *protected_out);
+			size_t *write_size_out, bool *protected_out);
 int efx_new_mcdi_nvram_test_all(struct efx_nic *efx);
 int efx_mcdi_nvram_metadata(struct efx_nic *efx, unsigned int type,
 			    u32 *subtype, u16 version[4], char *desc,
@@ -424,6 +424,26 @@ static inline int efx_mcdi_mon_probe(struct efx_nic *efx) { return 0; }
 static inline void efx_mcdi_mon_remove(struct efx_nic *efx) {}
 #endif
 
+int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type);
+int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
+			 loff_t offset, const u8 *buffer, size_t length);
+int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
+			 loff_t offset, size_t length);
+int efx_mcdi_nvram_metadata(struct efx_nic *efx, unsigned int type,
+			    u32 *subtype, u16 version[4], char *desc,
+			    size_t descsize);
+
+enum efx_update_finish_mode {
+	EFX_UPDATE_FINISH_WAIT,
+	EFX_UPDATE_FINISH_BACKGROUND,
+	EFX_UPDATE_FINISH_POLL,
+	EFX_UPDATE_FINISH_ABORT,
+};
+
+int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type,
+				 enum efx_update_finish_mode mode);
+int efx_mcdi_nvram_update_finish_polled(struct efx_nic *efx, unsigned int type);
+
 #ifdef CONFIG_SFC_MTD
 int efx_mcdi_mtd_read(struct mtd_info *mtd, loff_t start, size_t len,
 		      size_t *retlen, u8 *buffer);
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index cd297e19cddc..9cb339c461fb 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -72,19 +72,19 @@
  *               |                      \------- Error
  *               \------------------------------ Resync (always set)
  *
- * The client writes it's request into MC shared memory, and rings the
- * doorbell. Each request is completed by either by the MC writing
+ * The client writes its request into MC shared memory, and rings the
+ * doorbell. Each request is completed either by the MC writing
  * back into shared memory, or by writing out an event.
  *
  * All MCDI commands support completion by shared memory response. Each
  * request may also contain additional data (accounted for by HEADER.LEN),
- * and some response's may also contain additional data (again, accounted
+ * and some responses may also contain additional data (again, accounted
  * for by HEADER.LEN).
  *
  * Some MCDI commands support completion by event, in which any associated
  * response data is included in the event.
  *
- * The protocol requires one response to be delivered for every request, a
+ * The protocol requires one response to be delivered for every request; a
  * request should not be sent unless the response for the previous request
  * has been received (either by polling shared memory, or by receiving
  * an event).
@@ -165,6 +165,7 @@
 #define FSE_AZ_EV_CODE_MCDI_EVRESPONSE 0xc
 
 
+
 #define MC_CMD_ERR_CODE_OFST 0
 #define MC_CMD_ERR_PROXY_PENDING_HANDLE_OFST 4
 
@@ -321,7 +322,7 @@
 /* enum: The requesting client is not a function */
 #define          MC_CMD_ERR_CLIENT_NOT_FN 0x100c
 /* enum: The requested operation might require the command to be passed between
- * MCs, and thetransport doesn't support that. Should only ever been seen over
+ * MCs, and the transport doesn't support that. Should only ever been seen over
  * the UART.
  */
 #define          MC_CMD_ERR_TRANSPORT_NOPROXY 0x100d
@@ -358,7 +359,7 @@
  * sub-variant switching.
  */
 #define          MC_CMD_ERR_FILTERS_PRESENT 0x1014
-/* enum: The clock whose frequency you've attempted to set set doesn't exist on
+/* enum: The clock whose frequency you've attempted to set doesn't exist on
  * this NIC
  */
 #define          MC_CMD_ERR_NO_CLOCK 0x1015
@@ -387,25 +388,6 @@
  */
 #define          MC_CMD_ERR_PIOBUFS_PRESENT 0x101b
 
-/* MC_CMD_RESOURCE_SPECIFIER enum */
-/* enum: Any */
-#define          MC_CMD_RESOURCE_INSTANCE_ANY 0xffffffff
-#define          MC_CMD_RESOURCE_INSTANCE_NONE 0xfffffffe /* enum */
-
-/* MC_CMD_FPGA_FLASH_INDEX enum */
-#define          MC_CMD_FPGA_FLASH_PRIMARY 0x0 /* enum */
-#define          MC_CMD_FPGA_FLASH_SECONDARY 0x1 /* enum */
-
-/* MC_CMD_EXTERNAL_MAE_LINK_MODE enum */
-/* enum: Legacy mode as described in XN-200039-TC. */
-#define          MC_CMD_EXTERNAL_MAE_LINK_MODE_LEGACY 0x0
-/* enum: Switchdev mode as described in XN-200039-TC. */
-#define          MC_CMD_EXTERNAL_MAE_LINK_MODE_SWITCHDEV 0x1
-/* enum: Bootstrap mode as described in XN-200039-TC. */
-#define          MC_CMD_EXTERNAL_MAE_LINK_MODE_BOOTSTRAP 0x2
-/* enum: Link-mode change is in-progress as described in XN-200039-TC. */
-#define          MC_CMD_EXTERNAL_MAE_LINK_MODE_PENDING 0xf
-
 /* PCIE_INTERFACE enum: From EF100 onwards, SFC products can have multiple PCIe
  * interfaces. There is a need to refer to interfaces explicitly from drivers
  * (for example, a management driver on one interface administering a function
@@ -424,6 +406,14 @@
  * an on-NIC ARM module is expected to be connected.
  */
 #define          PCIE_INTERFACE_NIC_EMBEDDED 0x1
+/* enum: The PCIe logical interface 0. It is an alias for HOST_PRIMARY. */
+#define          PCIE_INTERFACE_PCIE_HOST_INTF_0 0x0
+/* enum: The PCIe logical interface 1. */
+#define          PCIE_INTERFACE_PCIE_HOST_INTF_1 0x2
+/* enum: The PCIe logical interface 2. */
+#define          PCIE_INTERFACE_PCIE_HOST_INTF_2 0x3
+/* enum: The PCIe logical interface 3. */
+#define          PCIE_INTERFACE_PCIE_HOST_INTF_3 0x4
 /* enum: For MCDI commands issued over a PCIe interface, this value is
  * translated into the interface over which the command was issued. Not
  * meaningful for other MCDI transports.
@@ -640,7 +630,11 @@
  * be allocated by different counter blocks, so e.g. AR counter 42 is different
  * from CT counter 42. Generation counts are also type-specific. This value is
  * also present in the header of streaming counter packets, in the IDENTIFIER
- * field (see packetiser packet format definitions).
+ * field (see packetiser packet format definitions). Also note that LACP
+ * counter IDs are not allocated individually, instead the counter IDs are
+ * directly tied to the LACP balance table indices. These in turn are allocated
+ * in large contiguous blocks as a LAG config. Calling MAE_COUNTER_ALLOC/FREE
+ * with an LACP counter type will return EPERM.
  */
 /* enum: Action Rule counters - can be referenced in AR response. */
 #define          MAE_COUNTER_TYPE_AR 0x0
@@ -648,6 +642,14 @@
 #define          MAE_COUNTER_TYPE_CT 0x1
 /* enum: Outer Rule counters - can be referenced in OR response. */
 #define          MAE_COUNTER_TYPE_OR 0x2
+/* enum: LACP counters - linked to LACP balance table entries. */
+#define          MAE_COUNTER_TYPE_LACP 0x3
+
+/* MAE_COUNTER_ID enum: ID of allocated counter or counter list. */
+/* enum: A counter ID that is guaranteed never to represent a real counter or
+ * counter list.
+ */
+#define          MAE_COUNTER_ID_NULL 0xffffffff
 
 /* TABLE_ID enum: Unique IDs for tables. The 32-bit ID values have been
  * structured with bits [31:24] reserved (0), [23:16] indicating which major
@@ -656,7 +658,9 @@
  * variations of the same table. (All of the tables currently defined within
  * the streaming engines are listed here, but this does not imply that they are
  * all supported - MC_CMD_TABLE_LIST returns the list of actually supported
- * tables.)
+ * tables.) The DPU offload engines' enumerators follow a deliberate pattern:
+ * 0x01010000 + is_dpu_net * 0x10000 + is_wr_or_tx * 0x8000 + is_lite_pipe *
+ * 0x1000 + oe_engine_type * 0x100 + oe_instance_within_pipe * 0x10
  */
 /* enum: Outer_Rule_Table in the MAE - refer to SF-123102-TC. */
 #define          TABLE_ID_OUTER_RULE_TABLE 0x10000
@@ -694,45 +698,70 @@
 #define          TABLE_ID_RSS_CONTEXT_TABLE 0x20200
 /* enum: Indirection_Table in VNIC Rx - refer to SF-123102-TC. */
 #define          TABLE_ID_INDIRECTION_TABLE 0x20300
-
-/* TABLE_COMPRESSED_VLAN enum: Compressed VLAN TPID as used by some field
- * types; can be calculated by (((ether_type_msb >> 2) & 0x4) ^ 0x4) |
- * (ether_type_msb & 0x3);
- */
-#define          TABLE_COMPRESSED_VLAN_TPID_8100 0x5 /* enum */
-#define          TABLE_COMPRESSED_VLAN_TPID_88A8 0x4 /* enum */
-#define          TABLE_COMPRESSED_VLAN_TPID_9100 0x1 /* enum */
-#define          TABLE_COMPRESSED_VLAN_TPID_9200 0x2 /* enum */
-#define          TABLE_COMPRESSED_VLAN_TPID_9300 0x3 /* enum */
-
-/* TABLE_NAT_DIR enum: NAT direction. */
-#define          TABLE_NAT_DIR_SOURCE 0x0 /* enum */
-#define          TABLE_NAT_DIR_DEST 0x1 /* enum */
-
-/* TABLE_RSS_KEY_MODE enum: Defines how the value for Toeplitz hashing for RSS
- * is constructed as a concatenation (indicated here by "++") of packet header
- * fields.
- */
-/* enum: IP src addr ++ IP dst addr */
-#define          TABLE_RSS_KEY_MODE_SA_DA 0x0
-/* enum: IP src addr ++ IP dst addr ++ TCP/UDP src port ++ TCP/UDP dst port */
-#define          TABLE_RSS_KEY_MODE_SA_DA_SP_DP 0x1
-/* enum: IP src addr */
-#define          TABLE_RSS_KEY_MODE_SA 0x2
-/* enum: IP dst addr */
-#define          TABLE_RSS_KEY_MODE_DA 0x3
-/* enum: IP src addr ++ TCP/UDP src port */
-#define          TABLE_RSS_KEY_MODE_SA_SP 0x4
-/* enum: IP dest addr ++ TCP dest port */
-#define          TABLE_RSS_KEY_MODE_DA_DP 0x5
-/* enum: Nothing (produces input of 0, resulting in output hash of 0) */
-#define          TABLE_RSS_KEY_MODE_NONE 0x7
-
-/* TABLE_RSS_SPREAD_MODE enum: RSS spreading mode. */
-/* enum: RSS uses Indirection_Table lookup. */
-#define          TABLE_RSS_SPREAD_MODE_INDIRECTION 0x0
-/* enum: RSS uses even spreading calculation. */
-#define          TABLE_RSS_SPREAD_MODE_EVEN 0x1
+/* enum: DPU.host read pipe first CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_HOST_RD_CRC0_OE_PROFILE 0x1010000
+/* enum: DPU.host read pipe second CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_HOST_RD_CRC1_OE_PROFILE 0x1010010
+/* enum: DPU.host write pipe first CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_HOST_WR_CRC0_OE_PROFILE 0x1018000
+/* enum: DPU.host write pipe second CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_HOST_WR_CRC1_OE_PROFILE 0x1018010
+/* enum: DPU.net 'full' receive pipe CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RX_CRC0_OE_PROFILE 0x1020000
+/* enum: DPU.net 'full' receive pipe first checksum offload engine profiles -
+ * refer to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RX_CSUM0_OE_PROFILE 0x1020100
+/* enum: DPU.net 'full' receive pipe second checksum offload engine profiles -
+ * refer to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RX_CSUM1_OE_PROFILE 0x1020110
+/* enum: DPU.net 'full' receive pipe AES-GCM offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RX_AES_GCM0_OE_PROFILE 0x1020200
+/* enum: DPU.net 'lite' receive pipe CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RXLITE_CRC0_OE_PROFILE 0x1021000
+/* enum: DPU.net 'lite' receive pipe checksum offload engine profiles - refer
+ * to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RXLITE_CSUM0_OE_PROFILE 0x1021100
+/* enum: DPU.net 'full' transmit pipe CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TX_CRC0_OE_PROFILE 0x1028000
+/* enum: DPU.net 'full' transmit pipe first checksum offload engine profiles -
+ * refer to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TX_CSUM0_OE_PROFILE 0x1028100
+/* enum: DPU.net 'full' transmit pipe second checksum offload engine profiles -
+ * refer to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TX_CSUM1_OE_PROFILE 0x1028110
+/* enum: DPU.net 'full' transmit pipe AES-GCM offload engine profiles - refer
+ * to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TX_AES_GCM0_OE_PROFILE 0x1028200
+/* enum: DPU.net 'lite' transmit pipe CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TXLITE_CRC0_OE_PROFILE 0x1029000
+/* enum: DPU.net 'lite' transmit pipe checksum offload engine profiles - refer
+ * to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TXLITE_CSUM0_OE_PROFILE 0x1029100
 
 /* TABLE_FIELD_ID enum: Unique IDs for fields. Related concepts have been
  * loosely grouped together into blocks with gaps for expansion, but the values
@@ -1026,6 +1055,16 @@
 #define          TABLE_FIELD_ID_BAL_TBL_BASE_DIV64 0xde
 /* enum: Length of balance table region: 0=>64, 1=>128, 2=>256. */
 #define          TABLE_FIELD_ID_BAL_TBL_LEN_ID 0xdf
+/* enum: LACP LAG ID (i.e. the low 3 bits of LACP LAG mport ID), indexing
+ * LACP_LAG_Config_Table. Refer to SF-123102-TC.
+ */
+#define          TABLE_FIELD_ID_LACP_LAG_ID 0xe0
+/* enum: Address in LACP_Balance_Table. The balance table is partitioned
+ * between LAGs according to the settings in LACP_LAG_Config_Table and then
+ * indexed by the LACP hash, providing the mapping to destination mports. Refer
+ * to SF-123102-TC.
+ */
+#define          TABLE_FIELD_ID_BAL_TBL_ADDR 0xe1
 /* enum: UDP port to match for UDP-based encapsulations; required to be 0 for
  * other encapsulation types.
  */
@@ -1082,6 +1121,55 @@
 #define          TABLE_FIELD_ID_INDIR_TBL_LEN_ID 0x105
 /* enum: An offset to be applied to the base destination queue ID. */
 #define          TABLE_FIELD_ID_INDIR_OFFSET 0x106
+/* enum: DPU offload engine profile ID to address. */
+#define          TABLE_FIELD_ID_OE_PROFILE 0x3e8
+/* enum: Width of the CRC to calculate - see CRC_VARIANT enum. */
+#define          TABLE_FIELD_ID_CRC_VARIANT 0x3f2
+/* enum: If set, reflect the bits of each input byte, bit 7 is LSB, bit 0 is
+ * MSB. If clear, bit 7 is MSB, bit 0 is LSB.
+ */
+#define          TABLE_FIELD_ID_CRC_REFIN 0x3f3
+/* enum: If set, reflect the bits of each output byte, bit 7 is LSB, bit 0 is
+ * MSB. If clear, bit 7 is MSB, bit 0 is LSB.
+ */
+#define          TABLE_FIELD_ID_CRC_REFOUT 0x3f4
+/* enum: If set, invert every bit of the output value. */
+#define          TABLE_FIELD_ID_CRC_INVOUT 0x3f5
+/* enum: The CRC polynomial to use for checksumming, in normal form. */
+#define          TABLE_FIELD_ID_CRC_POLY 0x3f6
+/* enum: Operation for the checksum engine to perform - see DPU_CSUM_OP enum.
+ */
+#define          TABLE_FIELD_ID_CSUM_OP 0x410
+/* enum: Byte offset of checksum relative to region_start (for VALIDATE_*
+ * operations only).
+ */
+#define          TABLE_FIELD_ID_CSUM_OFFSET 0x411
+/* enum: Indicates there is additional data on OPR bus that needs to be
+ * incorporated into the payload checksum.
+ */
+#define          TABLE_FIELD_ID_CSUM_OPR_ADDITIONAL_DATA 0x412
+/* enum: Log2 data size of additional data on OPR bus. */
+#define          TABLE_FIELD_ID_CSUM_OPR_DATA_SIZE_LOG2 0x413
+/* enum: 4 byte offset of where to find the additional data on the OPR bus. */
+#define          TABLE_FIELD_ID_CSUM_OPR_4B_OFF 0x414
+/* enum: Operation type for the AES-GCM core - see GCM_OP_CODE enum. */
+#define          TABLE_FIELD_ID_GCM_OP_CODE 0x41a
+/* enum: Key length - AES_KEY_LEN enum. */
+#define          TABLE_FIELD_ID_GCM_KEY_LEN 0x41b
+/* enum: OPR 4 byte offset for ICV or GHASH output (only in BULK_* mode) or
+ * IPSEC descrypt output.
+ */
+#define          TABLE_FIELD_ID_GCM_OPR_4B_OFFSET 0x41c
+/* enum: If OP_CODE is BULK_*, indicates Emit GHASH (Fragment mode). Else,
+ * indicates IPSEC-ESN mode.
+ */
+#define          TABLE_FIELD_ID_GCM_EMIT_GHASH_ISESN 0x41d
+/* enum: Replay Protection Enable. */
+#define          TABLE_FIELD_ID_GCM_REPLAY_PROTECT_EN 0x41e
+/* enum: IPSEC Encrypt ESP trailer NEXT_HEADER byte. */
+#define          TABLE_FIELD_ID_GCM_NEXT_HDR 0x41f
+/* enum: Replay Window Size. */
+#define          TABLE_FIELD_ID_GCM_REPLAY_WIN_SIZE 0x420
 
 /* MCDI_EVENT structuredef: The structure of an MCDI_EVENT on Siena/EF10/EF100
  * platforms
@@ -1138,6 +1226,24 @@
 #define        MCDI_EVENT_LINKCHANGE_LINK_FLAGS_OFST 0
 #define        MCDI_EVENT_LINKCHANGE_LINK_FLAGS_LBN 24
 #define        MCDI_EVENT_LINKCHANGE_LINK_FLAGS_WIDTH 8
+#define        MCDI_EVENT_PORT_LINKCHANGE_PORT_HANDLE_OFST 0
+#define        MCDI_EVENT_PORT_LINKCHANGE_PORT_HANDLE_LBN 0
+#define        MCDI_EVENT_PORT_LINKCHANGE_PORT_HANDLE_WIDTH 24
+#define        MCDI_EVENT_PORT_LINKCHANGE_SEQ_NUM_OFST 0
+#define        MCDI_EVENT_PORT_LINKCHANGE_SEQ_NUM_LBN 24
+#define        MCDI_EVENT_PORT_LINKCHANGE_SEQ_NUM_WIDTH 7
+#define        MCDI_EVENT_PORT_LINKCHANGE_LINK_UP_OFST 0
+#define        MCDI_EVENT_PORT_LINKCHANGE_LINK_UP_LBN 31
+#define        MCDI_EVENT_PORT_LINKCHANGE_LINK_UP_WIDTH 1
+#define        MCDI_EVENT_PORT_MODULECHANGE_PORT_HANDLE_OFST 0
+#define        MCDI_EVENT_PORT_MODULECHANGE_PORT_HANDLE_LBN 0
+#define        MCDI_EVENT_PORT_MODULECHANGE_PORT_HANDLE_WIDTH 24
+#define        MCDI_EVENT_PORT_MODULECHANGE_SEQ_NUM_OFST 0
+#define        MCDI_EVENT_PORT_MODULECHANGE_SEQ_NUM_LBN 24
+#define        MCDI_EVENT_PORT_MODULECHANGE_SEQ_NUM_WIDTH 7
+#define        MCDI_EVENT_PORT_MODULECHANGE_MDI_CONNECTED_OFST 0
+#define        MCDI_EVENT_PORT_MODULECHANGE_MDI_CONNECTED_LBN 31
+#define        MCDI_EVENT_PORT_MODULECHANGE_MDI_CONNECTED_WIDTH 1
 #define        MCDI_EVENT_SENSOREVT_MONITOR_OFST 0
 #define        MCDI_EVENT_SENSOREVT_MONITOR_LBN 0
 #define        MCDI_EVENT_SENSOREVT_MONITOR_WIDTH 8
@@ -1237,7 +1343,7 @@
 #define          MCDI_EVENT_AOE_FPGA_LOAD_FAILED 0xe
 /* enum: Notify that invalid flash type detected */
 #define          MCDI_EVENT_AOE_INVALID_FPGA_FLASH_TYPE 0xf
-/* enum: Notify that the attempt to run FPGA Controller firmware timedout */
+/* enum: Notify that the attempt to run FPGA Controller firmware timed out */
 #define          MCDI_EVENT_AOE_FC_RUN_TIMEDOUT 0x10
 /* enum: Failure to probe one or more FPGA boot flash chips */
 #define          MCDI_EVENT_AOE_FPGA_BOOT_FLASH_INVALID 0x11
@@ -1255,7 +1361,7 @@
 #define        MCDI_EVENT_AOE_ERR_FC_ASSERT_INFO_WIDTH 8
 /* enum: FC Assert happened, but the register information is not available */
 #define          MCDI_EVENT_AOE_ERR_FC_ASSERT_SEEN 0x0
-/* enum: The register information for FC Assert is ready for readinng by driver
+/* enum: The register information for FC Assert is ready for reading by driver
  */
 #define          MCDI_EVENT_AOE_ERR_FC_ASSERT_DATA_READY 0x1
 #define        MCDI_EVENT_AOE_ERR_CODE_FPGA_HEADER_VERIFY_FAILED_OFST 0
@@ -1364,6 +1470,12 @@
 #define        MCDI_EVENT_MODULECHANGE_SEQ_OFST 0
 #define        MCDI_EVENT_MODULECHANGE_SEQ_LBN 30
 #define        MCDI_EVENT_MODULECHANGE_SEQ_WIDTH 2
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_VI_ID_OFST 0
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_VI_ID_LBN 0
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_VI_ID_WIDTH 16
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_ID_OFST 0
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_ID_LBN 16
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_ID_WIDTH 16
 #define       MCDI_EVENT_DATA_LBN 0
 #define       MCDI_EVENT_DATA_WIDTH 32
 /* Alias for PTP_DATA. */
@@ -1500,6 +1612,31 @@
  * change to the journal.
  */
 #define          MCDI_EVENT_CODE_MPORT_JOURNAL_CHANGE 0x27
+/* enum: Notification that a source queue is enabled and attached to its proxy
+ * sink queue. SRC field contains the handle of the affected descriptor proxy
+ * function. DATA field contains the relative source queue number and absolute
+ * VI ID.
+ */
+#define          MCDI_EVENT_CODE_DESC_PROXY_FUNC_QUEUE_START 0x28
+/* enum: Notification of a change in link state and/or link speed of a network
+ * port link. This event applies to a network port identified by a handle,
+ * PORT_HANDLE, which is discovered by the driver using the MC_CMD_ENUM_PORTS
+ * command.
+ */
+#define          MCDI_EVENT_CODE_PORT_LINKCHANGE 0x29
+/* enum: Notification of a change in the state of an MDI (external connector)
+ * of a network port. This typically corresponds to module plug/unplug for
+ * modular interfaces (e.g., SFP/QSFP and similar) or cable connect/disconnect.
+ * This event applies to a network port identified by a handle, PORT_HANDLE,
+ * which is discovered by the driver using the MC_CMD_ENUM_PORTS command.
+ */
+#define          MCDI_EVENT_CODE_PORT_MODULECHANGE 0x2a
+/* enum: Notification that the port enumeration journal has changed since it
+ * was last read and updates can be read using the MC_CMD_ENUM_PORTS command.
+ * The firmware may moderate the events so that an event is not sent for every
+ * change to the journal.
+ */
+#define          MCDI_EVENT_CODE_ENUM_PORTS_CHANGE 0x2b
 /* enum: Artificial event generated by host and posted via MC for test
  * purposes.
  */
@@ -1512,6 +1649,14 @@
 #define       MCDI_EVENT_LINKCHANGE_DATA_LEN 4
 #define       MCDI_EVENT_LINKCHANGE_DATA_LBN 0
 #define       MCDI_EVENT_LINKCHANGE_DATA_WIDTH 32
+#define       MCDI_EVENT_PORT_LINKCHANGE_DATA_OFST 0
+#define       MCDI_EVENT_PORT_LINKCHANGE_DATA_LEN 4
+#define       MCDI_EVENT_PORT_LINKCHANGE_DATA_LBN 0
+#define       MCDI_EVENT_PORT_LINKCHANGE_DATA_WIDTH 32
+#define       MCDI_EVENT_PORT_MODULECHANGE_DATA_OFST 0
+#define       MCDI_EVENT_PORT_MODULECHANGE_DATA_LEN 4
+#define       MCDI_EVENT_PORT_MODULECHANGE_DATA_LBN 0
+#define       MCDI_EVENT_PORT_MODULECHANGE_DATA_WIDTH 32
 #define       MCDI_EVENT_SENSOREVT_DATA_OFST 0
 #define       MCDI_EVENT_SENSOREVT_DATA_LEN 4
 #define       MCDI_EVENT_SENSOREVT_DATA_LBN 0
@@ -1668,247 +1813,6 @@
 #define       MCDI_EVENT_DESC_PROXY_VIRTIO_FEATURES_LBN 0
 #define       MCDI_EVENT_DESC_PROXY_VIRTIO_FEATURES_WIDTH 32
 
-/* FCDI_EVENT structuredef */
-#define    FCDI_EVENT_LEN 8
-#define       FCDI_EVENT_CONT_LBN 32
-#define       FCDI_EVENT_CONT_WIDTH 1
-#define       FCDI_EVENT_LEVEL_LBN 33
-#define       FCDI_EVENT_LEVEL_WIDTH 3
-/* enum: Info. */
-#define          FCDI_EVENT_LEVEL_INFO 0x0
-/* enum: Warning. */
-#define          FCDI_EVENT_LEVEL_WARN 0x1
-/* enum: Error. */
-#define          FCDI_EVENT_LEVEL_ERR 0x2
-/* enum: Fatal. */
-#define          FCDI_EVENT_LEVEL_FATAL 0x3
-#define       FCDI_EVENT_DATA_OFST 0
-#define       FCDI_EVENT_DATA_LEN 4
-#define        FCDI_EVENT_LINK_STATE_STATUS_OFST 0
-#define        FCDI_EVENT_LINK_STATE_STATUS_LBN 0
-#define        FCDI_EVENT_LINK_STATE_STATUS_WIDTH 1
-#define          FCDI_EVENT_LINK_DOWN 0x0 /* enum */
-#define          FCDI_EVENT_LINK_UP 0x1 /* enum */
-#define       FCDI_EVENT_DATA_LBN 0
-#define       FCDI_EVENT_DATA_WIDTH 32
-#define       FCDI_EVENT_SRC_LBN 36
-#define       FCDI_EVENT_SRC_WIDTH 8
-#define       FCDI_EVENT_EV_CODE_LBN 60
-#define       FCDI_EVENT_EV_CODE_WIDTH 4
-#define       FCDI_EVENT_CODE_LBN 44
-#define       FCDI_EVENT_CODE_WIDTH 8
-/* enum: The FC was rebooted. */
-#define          FCDI_EVENT_CODE_REBOOT 0x1
-/* enum: Bad assert. */
-#define          FCDI_EVENT_CODE_ASSERT 0x2
-/* enum: DDR3 test result. */
-#define          FCDI_EVENT_CODE_DDR_TEST_RESULT 0x3
-/* enum: Link status. */
-#define          FCDI_EVENT_CODE_LINK_STATE 0x4
-/* enum: A timed read is ready to be serviced. */
-#define          FCDI_EVENT_CODE_TIMED_READ 0x5
-/* enum: One or more PPS IN events */
-#define          FCDI_EVENT_CODE_PPS_IN 0x6
-/* enum: Tick event from PTP clock */
-#define          FCDI_EVENT_CODE_PTP_TICK 0x7
-/* enum: ECC error counters */
-#define          FCDI_EVENT_CODE_DDR_ECC_STATUS 0x8
-/* enum: Current status of PTP */
-#define          FCDI_EVENT_CODE_PTP_STATUS 0x9
-/* enum: Port id config to map MC-FC port idx */
-#define          FCDI_EVENT_CODE_PORT_CONFIG 0xa
-/* enum: Boot result or error code */
-#define          FCDI_EVENT_CODE_BOOT_RESULT 0xb
-#define       FCDI_EVENT_REBOOT_SRC_LBN 36
-#define       FCDI_EVENT_REBOOT_SRC_WIDTH 8
-#define          FCDI_EVENT_REBOOT_FC_FW 0x0 /* enum */
-#define          FCDI_EVENT_REBOOT_FC_BOOTLOADER 0x1 /* enum */
-#define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_OFST 0
-#define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_LEN 4
-#define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_LBN 0
-#define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_WIDTH 32
-#define       FCDI_EVENT_ASSERT_TYPE_LBN 36
-#define       FCDI_EVENT_ASSERT_TYPE_WIDTH 8
-#define       FCDI_EVENT_DDR_TEST_RESULT_STATUS_CODE_LBN 36
-#define       FCDI_EVENT_DDR_TEST_RESULT_STATUS_CODE_WIDTH 8
-#define       FCDI_EVENT_DDR_TEST_RESULT_RESULT_OFST 0
-#define       FCDI_EVENT_DDR_TEST_RESULT_RESULT_LEN 4
-#define       FCDI_EVENT_DDR_TEST_RESULT_RESULT_LBN 0
-#define       FCDI_EVENT_DDR_TEST_RESULT_RESULT_WIDTH 32
-#define       FCDI_EVENT_LINK_STATE_DATA_OFST 0
-#define       FCDI_EVENT_LINK_STATE_DATA_LEN 4
-#define       FCDI_EVENT_LINK_STATE_DATA_LBN 0
-#define       FCDI_EVENT_LINK_STATE_DATA_WIDTH 32
-#define       FCDI_EVENT_PTP_STATE_OFST 0
-#define       FCDI_EVENT_PTP_STATE_LEN 4
-#define          FCDI_EVENT_PTP_UNDEFINED 0x0 /* enum */
-#define          FCDI_EVENT_PTP_SETUP_FAILED 0x1 /* enum */
-#define          FCDI_EVENT_PTP_OPERATIONAL 0x2 /* enum */
-#define       FCDI_EVENT_PTP_STATE_LBN 0
-#define       FCDI_EVENT_PTP_STATE_WIDTH 32
-#define       FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_LBN 36
-#define       FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_WIDTH 8
-#define       FCDI_EVENT_DDR_ECC_STATUS_STATUS_OFST 0
-#define       FCDI_EVENT_DDR_ECC_STATUS_STATUS_LEN 4
-#define       FCDI_EVENT_DDR_ECC_STATUS_STATUS_LBN 0
-#define       FCDI_EVENT_DDR_ECC_STATUS_STATUS_WIDTH 32
-/* Index of MC port being referred to */
-#define       FCDI_EVENT_PORT_CONFIG_SRC_LBN 36
-#define       FCDI_EVENT_PORT_CONFIG_SRC_WIDTH 8
-/* FC Port index that matches the MC port index in SRC */
-#define       FCDI_EVENT_PORT_CONFIG_DATA_OFST 0
-#define       FCDI_EVENT_PORT_CONFIG_DATA_LEN 4
-#define       FCDI_EVENT_PORT_CONFIG_DATA_LBN 0
-#define       FCDI_EVENT_PORT_CONFIG_DATA_WIDTH 32
-#define       FCDI_EVENT_BOOT_RESULT_OFST 0
-#define       FCDI_EVENT_BOOT_RESULT_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_AOE/MC_CMD_AOE_OUT_INFO/FC_BOOT_RESULT */
-#define       FCDI_EVENT_BOOT_RESULT_LBN 0
-#define       FCDI_EVENT_BOOT_RESULT_WIDTH 32
-
-/* FCDI_EXTENDED_EVENT_PPS structuredef: Extended FCDI event to send PPS events
- * to the MC. Note that this structure | is overlayed over a normal FCDI event
- * such that bits 32-63 containing | event code, level, source etc remain the
- * same. In this case the data | field of the header is defined to be the
- * number of timestamps
- */
-#define    FCDI_EXTENDED_EVENT_PPS_LENMIN 16
-#define    FCDI_EXTENDED_EVENT_PPS_LENMAX 248
-#define    FCDI_EXTENDED_EVENT_PPS_LENMAX_MCDI2 1016
-#define    FCDI_EXTENDED_EVENT_PPS_LEN(num) (8+8*(num))
-#define    FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_NUM(len) (((len)-8)/8)
-/* Number of timestamps following */
-#define       FCDI_EXTENDED_EVENT_PPS_COUNT_OFST 0
-#define       FCDI_EXTENDED_EVENT_PPS_COUNT_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_COUNT_LBN 0
-#define       FCDI_EXTENDED_EVENT_PPS_COUNT_WIDTH 32
-/* Seconds field of a timestamp record */
-#define       FCDI_EXTENDED_EVENT_PPS_SECONDS_OFST 8
-#define       FCDI_EXTENDED_EVENT_PPS_SECONDS_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_SECONDS_LBN 64
-#define       FCDI_EXTENDED_EVENT_PPS_SECONDS_WIDTH 32
-/* Nanoseconds field of a timestamp record */
-#define       FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_OFST 12
-#define       FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_LBN 96
-#define       FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_WIDTH 32
-/* Timestamp records comprising the event */
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_OFST 8
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LEN 8
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_OFST 8
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_LBN 64
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_WIDTH 32
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_OFST 12
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_LBN 96
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_WIDTH 32
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MINNUM 1
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MAXNUM 30
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MAXNUM_MCDI2 126
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LBN 64
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_WIDTH 64
-
-/* MUM_EVENT structuredef */
-#define    MUM_EVENT_LEN 8
-#define       MUM_EVENT_CONT_LBN 32
-#define       MUM_EVENT_CONT_WIDTH 1
-#define       MUM_EVENT_LEVEL_LBN 33
-#define       MUM_EVENT_LEVEL_WIDTH 3
-/* enum: Info. */
-#define          MUM_EVENT_LEVEL_INFO 0x0
-/* enum: Warning. */
-#define          MUM_EVENT_LEVEL_WARN 0x1
-/* enum: Error. */
-#define          MUM_EVENT_LEVEL_ERR 0x2
-/* enum: Fatal. */
-#define          MUM_EVENT_LEVEL_FATAL 0x3
-#define       MUM_EVENT_DATA_OFST 0
-#define       MUM_EVENT_DATA_LEN 4
-#define        MUM_EVENT_SENSOR_ID_OFST 0
-#define        MUM_EVENT_SENSOR_ID_LBN 0
-#define        MUM_EVENT_SENSOR_ID_WIDTH 8
-/*             Enum values, see field(s): */
-/*                MC_CMD_SENSOR_INFO/MC_CMD_SENSOR_INFO_OUT/MASK */
-#define        MUM_EVENT_SENSOR_STATE_OFST 0
-#define        MUM_EVENT_SENSOR_STATE_LBN 8
-#define        MUM_EVENT_SENSOR_STATE_WIDTH 8
-#define        MUM_EVENT_PORT_PHY_READY_OFST 0
-#define        MUM_EVENT_PORT_PHY_READY_LBN 0
-#define        MUM_EVENT_PORT_PHY_READY_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_LINK_UP_OFST 0
-#define        MUM_EVENT_PORT_PHY_LINK_UP_LBN 1
-#define        MUM_EVENT_PORT_PHY_LINK_UP_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_TX_LOL_OFST 0
-#define        MUM_EVENT_PORT_PHY_TX_LOL_LBN 2
-#define        MUM_EVENT_PORT_PHY_TX_LOL_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_RX_LOL_OFST 0
-#define        MUM_EVENT_PORT_PHY_RX_LOL_LBN 3
-#define        MUM_EVENT_PORT_PHY_RX_LOL_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_TX_LOS_OFST 0
-#define        MUM_EVENT_PORT_PHY_TX_LOS_LBN 4
-#define        MUM_EVENT_PORT_PHY_TX_LOS_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_RX_LOS_OFST 0
-#define        MUM_EVENT_PORT_PHY_RX_LOS_LBN 5
-#define        MUM_EVENT_PORT_PHY_RX_LOS_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_TX_FAULT_OFST 0
-#define        MUM_EVENT_PORT_PHY_TX_FAULT_LBN 6
-#define        MUM_EVENT_PORT_PHY_TX_FAULT_WIDTH 1
-#define       MUM_EVENT_DATA_LBN 0
-#define       MUM_EVENT_DATA_WIDTH 32
-#define       MUM_EVENT_SRC_LBN 36
-#define       MUM_EVENT_SRC_WIDTH 8
-#define       MUM_EVENT_EV_CODE_LBN 60
-#define       MUM_EVENT_EV_CODE_WIDTH 4
-#define       MUM_EVENT_CODE_LBN 44
-#define       MUM_EVENT_CODE_WIDTH 8
-/* enum: The MUM was rebooted. */
-#define          MUM_EVENT_CODE_REBOOT 0x1
-/* enum: Bad assert. */
-#define          MUM_EVENT_CODE_ASSERT 0x2
-/* enum: Sensor failure. */
-#define          MUM_EVENT_CODE_SENSOR 0x3
-/* enum: Link fault has been asserted, or has cleared. */
-#define          MUM_EVENT_CODE_QSFP_LASI_INTERRUPT 0x4
-#define       MUM_EVENT_SENSOR_DATA_OFST 0
-#define       MUM_EVENT_SENSOR_DATA_LEN 4
-#define       MUM_EVENT_SENSOR_DATA_LBN 0
-#define       MUM_EVENT_SENSOR_DATA_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_FLAGS_OFST 0
-#define       MUM_EVENT_PORT_PHY_FLAGS_LEN 4
-#define       MUM_EVENT_PORT_PHY_FLAGS_LBN 0
-#define       MUM_EVENT_PORT_PHY_FLAGS_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_COPPER_LEN_OFST 0
-#define       MUM_EVENT_PORT_PHY_COPPER_LEN_LEN 4
-#define       MUM_EVENT_PORT_PHY_COPPER_LEN_LBN 0
-#define       MUM_EVENT_PORT_PHY_COPPER_LEN_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_CAPS_OFST 0
-#define       MUM_EVENT_PORT_PHY_CAPS_LEN 4
-#define       MUM_EVENT_PORT_PHY_CAPS_LBN 0
-#define       MUM_EVENT_PORT_PHY_CAPS_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_TECH_OFST 0
-#define       MUM_EVENT_PORT_PHY_TECH_LEN 4
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_UNKNOWN 0x0 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_OPTICAL 0x1 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_PASSIVE 0x2 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_PASSIVE_EQUALIZED 0x3 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_ACTIVE_LIMITING 0x4 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_ACTIVE_LINEAR 0x5 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_BASE_T 0x6 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_LOOPBACK_PASSIVE 0x7 /* enum */
-#define       MUM_EVENT_PORT_PHY_TECH_LBN 0
-#define       MUM_EVENT_PORT_PHY_TECH_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_SRC_DATA_ID_LBN 36
-#define       MUM_EVENT_PORT_PHY_SRC_DATA_ID_WIDTH 4
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_FLAGS 0x0 /* enum */
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_COPPER_LEN 0x1 /* enum */
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_CAPS 0x2 /* enum */
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_TECH 0x3 /* enum */
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_MAX 0x4 /* enum */
-#define       MUM_EVENT_PORT_PHY_SRC_PORT_NO_LBN 40
-#define       MUM_EVENT_PORT_PHY_SRC_PORT_NO_WIDTH 4
-
 
 /***********************************/
 /* MC_CMD_READ32
@@ -1969,90 +1873,6 @@
 
 
 /***********************************/
-/* MC_CMD_COPYCODE
- * Copy MC code between two locations and jump. Note - this command really
- * belongs to INSECURE category but is required by shmboot. The command handler
- * has additional checks to reject insecure calls.
- */
-#define MC_CMD_COPYCODE 0x3
-#undef MC_CMD_0x3_PRIVILEGE_CTG
-
-#define MC_CMD_0x3_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_COPYCODE_IN msgrequest */
-#define    MC_CMD_COPYCODE_IN_LEN 16
-/* Source address
- *
- * The main image should be entered via a copy of a single word from and to a
- * magic address, which controls various aspects of the boot. The magic address
- * is a bitfield, with each bit as documented below.
- */
-#define       MC_CMD_COPYCODE_IN_SRC_ADDR_OFST 0
-#define       MC_CMD_COPYCODE_IN_SRC_ADDR_LEN 4
-/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT (see below) */
-#define          MC_CMD_COPYCODE_HUNT_NO_MAGIC_ADDR 0x10000
-/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT and
- * BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED (see below)
- */
-#define          MC_CMD_COPYCODE_HUNT_NO_DATAPATH_MAGIC_ADDR 0x1d0d0
-/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT,
- * BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED and BOOT_MAGIC_IGNORE_CONFIG (see
- * below)
- */
-#define          MC_CMD_COPYCODE_HUNT_IGNORE_CONFIG_MAGIC_ADDR 0x1badc
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_PRESENT_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_PRESENT_LBN 17
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_PRESENT_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED_LBN 2
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_IGNORE_CONFIG_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_IGNORE_CONFIG_LBN 3
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_IGNORE_CONFIG_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_LBN 4
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_LBN 5
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_DISABLE_XIP_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_DISABLE_XIP_LBN 6
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_DISABLE_XIP_WIDTH 1
-/* Destination address */
-#define       MC_CMD_COPYCODE_IN_DEST_ADDR_OFST 4
-#define       MC_CMD_COPYCODE_IN_DEST_ADDR_LEN 4
-#define       MC_CMD_COPYCODE_IN_NUMWORDS_OFST 8
-#define       MC_CMD_COPYCODE_IN_NUMWORDS_LEN 4
-/* Address of where to jump after copy. */
-#define       MC_CMD_COPYCODE_IN_JUMP_OFST 12
-#define       MC_CMD_COPYCODE_IN_JUMP_LEN 4
-/* enum: Control should return to the caller rather than jumping */
-#define          MC_CMD_COPYCODE_JUMP_NONE 0x1
-
-/* MC_CMD_COPYCODE_OUT msgresponse */
-#define    MC_CMD_COPYCODE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_SET_FUNC
- * Select function for function-specific commands.
- */
-#define MC_CMD_SET_FUNC 0x4
-#undef MC_CMD_0x4_PRIVILEGE_CTG
-
-#define MC_CMD_0x4_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SET_FUNC_IN msgrequest */
-#define    MC_CMD_SET_FUNC_IN_LEN 4
-/* Set function */
-#define       MC_CMD_SET_FUNC_IN_FUNC_OFST 0
-#define       MC_CMD_SET_FUNC_IN_FUNC_LEN 4
-
-/* MC_CMD_SET_FUNC_OUT msgresponse */
-#define    MC_CMD_SET_FUNC_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_GET_BOOT_STATUS
  * Get the instruction address from which the MC booted.
  */
@@ -2259,6 +2079,7 @@
 /* Log destination */
 #define       MC_CMD_LOG_CTRL_IN_LOG_DEST_OFST 0
 #define       MC_CMD_LOG_CTRL_IN_LOG_DEST_LEN 4
+/* enum property: bitmask */
 /* enum: UART. */
 #define          MC_CMD_LOG_CTRL_IN_LOG_DEST_UART 0x1
 /* enum: Event queue. */
@@ -2304,6 +2125,9 @@
 
 /* MC_CMD_GET_VERSION_OUT msgresponse */
 #define    MC_CMD_GET_VERSION_OUT_LEN 32
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2326,6 +2150,9 @@
 
 /* MC_CMD_GET_VERSION_EXT_OUT msgresponse */
 #define    MC_CMD_GET_VERSION_EXT_OUT_LEN 48
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2356,6 +2183,9 @@
  * (depending on which components exist on a particular adapter)
  */
 #define    MC_CMD_GET_VERSION_V2_OUT_LEN 304
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2495,6 +2325,9 @@
  * (depending on which components exist on a particular adapter)
  */
 #define    MC_CMD_GET_VERSION_V3_OUT_LEN 328
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2641,6 +2474,9 @@
  * version information
  */
 #define    MC_CMD_GET_VERSION_V4_OUT_LEN 392
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2803,6 +2639,9 @@
  * and board version information
  */
 #define    MC_CMD_GET_VERSION_V5_OUT_LEN 424
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -3065,8 +2904,18 @@
  * subscribers.
  */
 #define          MC_CMD_PTP_OP_SET_SYNC_STATUS 0x1b
-/* enum: Above this for future use. */
-#define          MC_CMD_PTP_OP_MAX 0x1c
+/* enum: X4 and later adapters should use this instead of
+ * PTP_OP_TIME_EVENT_SUBSCRIBE. Subscribe to receive periodic time events
+ * indicating the current NIC time
+ */
+#define          MC_CMD_PTP_OP_TIME_EVENT_SUBSCRIBE_V2 0x1c
+/* enum: For X4 and later NICs. Packet timestamps and time sync events have
+ * IS_SET and IN_SYNC flags, that indicates whether time is updated and if it
+ * is in sync with host. Once set, IN_SYNC flag is cleared by hardware after a
+ * software configurable time out. Host driver need to query what is set and
+ * what is maximum supported interval, this MCDI can be used to query these.
+ */
+#define          MC_CMD_PTP_OP_GET_SYNC_TIMEOUT 0x1d
 
 /* MC_CMD_PTP_IN_ENABLE msgrequest */
 #define    MC_CMD_PTP_IN_ENABLE_LEN 16
@@ -3507,6 +3356,22 @@
 #define       MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE_OFST 12
 #define       MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE_LEN 4
 
+/* MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2 msgrequest */
+#define    MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_LEN 16
+/*            MC_CMD_PTP_IN_CMD_OFST 0 */
+/*            MC_CMD_PTP_IN_CMD_LEN 4 */
+/*            MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/*            MC_CMD_PTP_IN_PERIPH_ID_LEN 4 */
+/* Event queue ID */
+#define       MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_QUEUE_ID_OFST 8
+#define       MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_QUEUE_ID_LEN 4
+/* Space for flags. */
+#define       MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_FLAGS_OFST 12
+#define       MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_FLAGS_LEN 4
+#define        MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_REPORT_SYNC_STATUS_OFST 12
+#define        MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_REPORT_SYNC_STATUS_LBN 31
+#define        MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_REPORT_SYNC_STATUS_WIDTH 1
+
 /* MC_CMD_PTP_IN_MANFTEST_PPS msgrequest */
 #define    MC_CMD_PTP_IN_MANFTEST_PPS_LEN 12
 /*            MC_CMD_PTP_IN_CMD_OFST 0 */
@@ -3540,6 +3405,13 @@
 #define       MC_CMD_PTP_IN_SET_SYNC_STATUS_RESERVED1_OFST 20
 #define       MC_CMD_PTP_IN_SET_SYNC_STATUS_RESERVED1_LEN 4
 
+/* MC_CMD_PTP_IN_GET_SYNC_TIMEOUT msgrequest */
+#define    MC_CMD_PTP_IN_GET_SYNC_TIMEOUT_LEN 8
+/*            MC_CMD_PTP_IN_CMD_OFST 0 */
+/*            MC_CMD_PTP_IN_CMD_LEN 4 */
+/*            MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/*            MC_CMD_PTP_IN_PERIPH_ID_LEN 4 */
+
 /* MC_CMD_PTP_OUT msgresponse */
 #define    MC_CMD_PTP_OUT_LEN 0
 
@@ -3939,416 +3811,14 @@
 /* MC_CMD_PTP_OUT_SET_SYNC_STATUS msgresponse */
 #define    MC_CMD_PTP_OUT_SET_SYNC_STATUS_LEN 0
 
-
-/***********************************/
-/* MC_CMD_CSR_READ32
- * Read 32bit words from the indirect memory map.
- */
-#define MC_CMD_CSR_READ32 0xc
-#undef MC_CMD_0xc_PRIVILEGE_CTG
-
-#define MC_CMD_0xc_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_CSR_READ32_IN msgrequest */
-#define    MC_CMD_CSR_READ32_IN_LEN 12
-/* Address */
-#define       MC_CMD_CSR_READ32_IN_ADDR_OFST 0
-#define       MC_CMD_CSR_READ32_IN_ADDR_LEN 4
-#define       MC_CMD_CSR_READ32_IN_STEP_OFST 4
-#define       MC_CMD_CSR_READ32_IN_STEP_LEN 4
-#define       MC_CMD_CSR_READ32_IN_NUMWORDS_OFST 8
-#define       MC_CMD_CSR_READ32_IN_NUMWORDS_LEN 4
-
-/* MC_CMD_CSR_READ32_OUT msgresponse */
-#define    MC_CMD_CSR_READ32_OUT_LENMIN 4
-#define    MC_CMD_CSR_READ32_OUT_LENMAX 252
-#define    MC_CMD_CSR_READ32_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_CSR_READ32_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_CSR_READ32_OUT_BUFFER_NUM(len) (((len)-0)/4)
-/* The last dword is the status, not a value read */
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_OFST 0
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_LEN 4
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_MINNUM 1
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_MAXNUM 63
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_MAXNUM_MCDI2 255
-
-
-/***********************************/
-/* MC_CMD_CSR_WRITE32
- * Write 32bit dwords to the indirect memory map.
- */
-#define MC_CMD_CSR_WRITE32 0xd
-#undef MC_CMD_0xd_PRIVILEGE_CTG
-
-#define MC_CMD_0xd_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_CSR_WRITE32_IN msgrequest */
-#define    MC_CMD_CSR_WRITE32_IN_LENMIN 12
-#define    MC_CMD_CSR_WRITE32_IN_LENMAX 252
-#define    MC_CMD_CSR_WRITE32_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_CSR_WRITE32_IN_LEN(num) (8+4*(num))
-#define    MC_CMD_CSR_WRITE32_IN_BUFFER_NUM(len) (((len)-8)/4)
-/* Address */
-#define       MC_CMD_CSR_WRITE32_IN_ADDR_OFST 0
-#define       MC_CMD_CSR_WRITE32_IN_ADDR_LEN 4
-#define       MC_CMD_CSR_WRITE32_IN_STEP_OFST 4
-#define       MC_CMD_CSR_WRITE32_IN_STEP_LEN 4
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_OFST 8
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_LEN 4
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_MINNUM 1
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_MAXNUM 61
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_MAXNUM_MCDI2 253
-
-/* MC_CMD_CSR_WRITE32_OUT msgresponse */
-#define    MC_CMD_CSR_WRITE32_OUT_LEN 4
-#define       MC_CMD_CSR_WRITE32_OUT_STATUS_OFST 0
-#define       MC_CMD_CSR_WRITE32_OUT_STATUS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_HP
- * These commands are used for HP related features. They are grouped under one
- * MCDI command to avoid creating too many MCDI commands.
- */
-#define MC_CMD_HP 0x54
-#undef MC_CMD_0x54_PRIVILEGE_CTG
-
-#define MC_CMD_0x54_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_HP_IN msgrequest */
-#define    MC_CMD_HP_IN_LEN 16
-/* HP OCSD sub-command. When address is not NULL, request activation of OCSD at
- * the specified address with the specified interval.When address is NULL,
- * INTERVAL is interpreted as a command: 0: stop OCSD / 1: Report OCSD current
- * state / 2: (debug) Show temperature reported by one of the supported
- * sensors.
- */
-#define       MC_CMD_HP_IN_SUBCMD_OFST 0
-#define       MC_CMD_HP_IN_SUBCMD_LEN 4
-/* enum: OCSD (Option Card Sensor Data) sub-command. */
-#define          MC_CMD_HP_IN_OCSD_SUBCMD 0x0
-/* enum: Last known valid HP sub-command. */
-#define          MC_CMD_HP_IN_LAST_SUBCMD 0x0
-/* The address to the array of sensor fields. (Or NULL to use a sub-command.)
- */
-#define       MC_CMD_HP_IN_OCSD_ADDR_OFST 4
-#define       MC_CMD_HP_IN_OCSD_ADDR_LEN 8
-#define       MC_CMD_HP_IN_OCSD_ADDR_LO_OFST 4
-#define       MC_CMD_HP_IN_OCSD_ADDR_LO_LEN 4
-#define       MC_CMD_HP_IN_OCSD_ADDR_LO_LBN 32
-#define       MC_CMD_HP_IN_OCSD_ADDR_LO_WIDTH 32
-#define       MC_CMD_HP_IN_OCSD_ADDR_HI_OFST 8
-#define       MC_CMD_HP_IN_OCSD_ADDR_HI_LEN 4
-#define       MC_CMD_HP_IN_OCSD_ADDR_HI_LBN 64
-#define       MC_CMD_HP_IN_OCSD_ADDR_HI_WIDTH 32
-/* The requested update interval, in seconds. (Or the sub-command if ADDR is
- * NULL.)
- */
-#define       MC_CMD_HP_IN_OCSD_INTERVAL_OFST 12
-#define       MC_CMD_HP_IN_OCSD_INTERVAL_LEN 4
-
-/* MC_CMD_HP_OUT msgresponse */
-#define    MC_CMD_HP_OUT_LEN 4
-#define       MC_CMD_HP_OUT_OCSD_STATUS_OFST 0
-#define       MC_CMD_HP_OUT_OCSD_STATUS_LEN 4
-/* enum: OCSD stopped for this card. */
-#define          MC_CMD_HP_OUT_OCSD_STOPPED 0x1
-/* enum: OCSD was successfully started with the address provided. */
-#define          MC_CMD_HP_OUT_OCSD_STARTED 0x2
-/* enum: OCSD was already started for this card. */
-#define          MC_CMD_HP_OUT_OCSD_ALREADY_STARTED 0x3
-
-
-/***********************************/
-/* MC_CMD_STACKINFO
- * Get stack information.
- */
-#define MC_CMD_STACKINFO 0xf
-#undef MC_CMD_0xf_PRIVILEGE_CTG
-
-#define MC_CMD_0xf_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_STACKINFO_IN msgrequest */
-#define    MC_CMD_STACKINFO_IN_LEN 0
-
-/* MC_CMD_STACKINFO_OUT msgresponse */
-#define    MC_CMD_STACKINFO_OUT_LENMIN 12
-#define    MC_CMD_STACKINFO_OUT_LENMAX 252
-#define    MC_CMD_STACKINFO_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_STACKINFO_OUT_LEN(num) (0+12*(num))
-#define    MC_CMD_STACKINFO_OUT_THREAD_INFO_NUM(len) (((len)-0)/12)
-/* (thread ptr, stack size, free space) for each thread in system */
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_OFST 0
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_LEN 12
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_MINNUM 1
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_MAXNUM 21
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_MAXNUM_MCDI2 85
-
-
-/***********************************/
-/* MC_CMD_MDIO_READ
- * MDIO register read.
- */
-#define MC_CMD_MDIO_READ 0x10
-#undef MC_CMD_0x10_PRIVILEGE_CTG
-
-#define MC_CMD_0x10_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_MDIO_READ_IN msgrequest */
-#define    MC_CMD_MDIO_READ_IN_LEN 16
-/* Bus number; there are two MDIO buses: one for the internal PHY, and one for
- * external devices.
- */
-#define       MC_CMD_MDIO_READ_IN_BUS_OFST 0
-#define       MC_CMD_MDIO_READ_IN_BUS_LEN 4
-/* enum: Internal. */
-#define          MC_CMD_MDIO_BUS_INTERNAL 0x0
-/* enum: External. */
-#define          MC_CMD_MDIO_BUS_EXTERNAL 0x1
-/* Port address */
-#define       MC_CMD_MDIO_READ_IN_PRTAD_OFST 4
-#define       MC_CMD_MDIO_READ_IN_PRTAD_LEN 4
-/* Device Address or clause 22. */
-#define       MC_CMD_MDIO_READ_IN_DEVAD_OFST 8
-#define       MC_CMD_MDIO_READ_IN_DEVAD_LEN 4
-/* enum: By default all the MCDI MDIO operations perform clause45 mode. If you
- * want to use clause22 then set DEVAD = MC_CMD_MDIO_CLAUSE22.
- */
-#define          MC_CMD_MDIO_CLAUSE22 0x20
-/* Address */
-#define       MC_CMD_MDIO_READ_IN_ADDR_OFST 12
-#define       MC_CMD_MDIO_READ_IN_ADDR_LEN 4
-
-/* MC_CMD_MDIO_READ_OUT msgresponse */
-#define    MC_CMD_MDIO_READ_OUT_LEN 8
-/* Value */
-#define       MC_CMD_MDIO_READ_OUT_VALUE_OFST 0
-#define       MC_CMD_MDIO_READ_OUT_VALUE_LEN 4
-/* Status the MDIO commands return the raw status bits from the MDIO block. A
- * "good" transaction should have the DONE bit set and all other bits clear.
- */
-#define       MC_CMD_MDIO_READ_OUT_STATUS_OFST 4
-#define       MC_CMD_MDIO_READ_OUT_STATUS_LEN 4
-/* enum: Good. */
-#define          MC_CMD_MDIO_STATUS_GOOD 0x8
-
-
-/***********************************/
-/* MC_CMD_MDIO_WRITE
- * MDIO register write.
- */
-#define MC_CMD_MDIO_WRITE 0x11
-#undef MC_CMD_0x11_PRIVILEGE_CTG
-
-#define MC_CMD_0x11_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_MDIO_WRITE_IN msgrequest */
-#define    MC_CMD_MDIO_WRITE_IN_LEN 20
-/* Bus number; there are two MDIO buses: one for the internal PHY, and one for
- * external devices.
- */
-#define       MC_CMD_MDIO_WRITE_IN_BUS_OFST 0
-#define       MC_CMD_MDIO_WRITE_IN_BUS_LEN 4
-/* enum: Internal. */
-/*               MC_CMD_MDIO_BUS_INTERNAL 0x0 */
-/* enum: External. */
-/*               MC_CMD_MDIO_BUS_EXTERNAL 0x1 */
-/* Port address */
-#define       MC_CMD_MDIO_WRITE_IN_PRTAD_OFST 4
-#define       MC_CMD_MDIO_WRITE_IN_PRTAD_LEN 4
-/* Device Address or clause 22. */
-#define       MC_CMD_MDIO_WRITE_IN_DEVAD_OFST 8
-#define       MC_CMD_MDIO_WRITE_IN_DEVAD_LEN 4
-/* enum: By default all the MCDI MDIO operations perform clause45 mode. If you
- * want to use clause22 then set DEVAD = MC_CMD_MDIO_CLAUSE22.
- */
-/*               MC_CMD_MDIO_CLAUSE22 0x20 */
-/* Address */
-#define       MC_CMD_MDIO_WRITE_IN_ADDR_OFST 12
-#define       MC_CMD_MDIO_WRITE_IN_ADDR_LEN 4
-/* Value */
-#define       MC_CMD_MDIO_WRITE_IN_VALUE_OFST 16
-#define       MC_CMD_MDIO_WRITE_IN_VALUE_LEN 4
-
-/* MC_CMD_MDIO_WRITE_OUT msgresponse */
-#define    MC_CMD_MDIO_WRITE_OUT_LEN 4
-/* Status; the MDIO commands return the raw status bits from the MDIO block. A
- * "good" transaction should have the DONE bit set and all other bits clear.
- */
-#define       MC_CMD_MDIO_WRITE_OUT_STATUS_OFST 0
-#define       MC_CMD_MDIO_WRITE_OUT_STATUS_LEN 4
-/* enum: Good. */
-/*               MC_CMD_MDIO_STATUS_GOOD 0x8 */
-
-
-/***********************************/
-/* MC_CMD_DBI_WRITE
- * Write DBI register(s).
- */
-#define MC_CMD_DBI_WRITE 0x12
-#undef MC_CMD_0x12_PRIVILEGE_CTG
-
-#define MC_CMD_0x12_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_DBI_WRITE_IN msgrequest */
-#define    MC_CMD_DBI_WRITE_IN_LENMIN 12
-#define    MC_CMD_DBI_WRITE_IN_LENMAX 252
-#define    MC_CMD_DBI_WRITE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_DBI_WRITE_IN_LEN(num) (0+12*(num))
-#define    MC_CMD_DBI_WRITE_IN_DBIWROP_NUM(len) (((len)-0)/12)
-/* Each write op consists of an address (offset 0), byte enable/VF/CS2 (offset
- * 32) and value (offset 64). See MC_CMD_DBIWROP_TYPEDEF.
- */
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_OFST 0
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_LEN 12
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_MINNUM 1
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_MAXNUM 21
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_MAXNUM_MCDI2 85
-
-/* MC_CMD_DBI_WRITE_OUT msgresponse */
-#define    MC_CMD_DBI_WRITE_OUT_LEN 0
-
-/* MC_CMD_DBIWROP_TYPEDEF structuredef */
-#define    MC_CMD_DBIWROP_TYPEDEF_LEN 12
-#define       MC_CMD_DBIWROP_TYPEDEF_ADDRESS_OFST 0
-#define       MC_CMD_DBIWROP_TYPEDEF_ADDRESS_LEN 4
-#define       MC_CMD_DBIWROP_TYPEDEF_ADDRESS_LBN 0
-#define       MC_CMD_DBIWROP_TYPEDEF_ADDRESS_WIDTH 32
-#define       MC_CMD_DBIWROP_TYPEDEF_PARMS_OFST 4
-#define       MC_CMD_DBIWROP_TYPEDEF_PARMS_LEN 4
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_NUM_OFST 4
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_NUM_LBN 16
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_NUM_WIDTH 16
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_ACTIVE_OFST 4
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_ACTIVE_LBN 15
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_ACTIVE_WIDTH 1
-#define        MC_CMD_DBIWROP_TYPEDEF_CS2_OFST 4
-#define        MC_CMD_DBIWROP_TYPEDEF_CS2_LBN 14
-#define        MC_CMD_DBIWROP_TYPEDEF_CS2_WIDTH 1
-#define       MC_CMD_DBIWROP_TYPEDEF_PARMS_LBN 32
-#define       MC_CMD_DBIWROP_TYPEDEF_PARMS_WIDTH 32
-#define       MC_CMD_DBIWROP_TYPEDEF_VALUE_OFST 8
-#define       MC_CMD_DBIWROP_TYPEDEF_VALUE_LEN 4
-#define       MC_CMD_DBIWROP_TYPEDEF_VALUE_LBN 64
-#define       MC_CMD_DBIWROP_TYPEDEF_VALUE_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_PORT_READ32
- * Read a 32-bit register from the indirect port register map. The port to
- * access is implied by the Shared memory channel used.
- */
-#define MC_CMD_PORT_READ32 0x14
-
-/* MC_CMD_PORT_READ32_IN msgrequest */
-#define    MC_CMD_PORT_READ32_IN_LEN 4
-/* Address */
-#define       MC_CMD_PORT_READ32_IN_ADDR_OFST 0
-#define       MC_CMD_PORT_READ32_IN_ADDR_LEN 4
-
-/* MC_CMD_PORT_READ32_OUT msgresponse */
-#define    MC_CMD_PORT_READ32_OUT_LEN 8
-/* Value */
-#define       MC_CMD_PORT_READ32_OUT_VALUE_OFST 0
-#define       MC_CMD_PORT_READ32_OUT_VALUE_LEN 4
-/* Status */
-#define       MC_CMD_PORT_READ32_OUT_STATUS_OFST 4
-#define       MC_CMD_PORT_READ32_OUT_STATUS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PORT_WRITE32
- * Write a 32-bit register to the indirect port register map. The port to
- * access is implied by the Shared memory channel used.
- */
-#define MC_CMD_PORT_WRITE32 0x15
-
-/* MC_CMD_PORT_WRITE32_IN msgrequest */
-#define    MC_CMD_PORT_WRITE32_IN_LEN 8
-/* Address */
-#define       MC_CMD_PORT_WRITE32_IN_ADDR_OFST 0
-#define       MC_CMD_PORT_WRITE32_IN_ADDR_LEN 4
-/* Value */
-#define       MC_CMD_PORT_WRITE32_IN_VALUE_OFST 4
-#define       MC_CMD_PORT_WRITE32_IN_VALUE_LEN 4
-
-/* MC_CMD_PORT_WRITE32_OUT msgresponse */
-#define    MC_CMD_PORT_WRITE32_OUT_LEN 4
-/* Status */
-#define       MC_CMD_PORT_WRITE32_OUT_STATUS_OFST 0
-#define       MC_CMD_PORT_WRITE32_OUT_STATUS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PORT_READ128
- * Read a 128-bit register from the indirect port register map. The port to
- * access is implied by the Shared memory channel used.
- */
-#define MC_CMD_PORT_READ128 0x16
-
-/* MC_CMD_PORT_READ128_IN msgrequest */
-#define    MC_CMD_PORT_READ128_IN_LEN 4
-/* Address */
-#define       MC_CMD_PORT_READ128_IN_ADDR_OFST 0
-#define       MC_CMD_PORT_READ128_IN_ADDR_LEN 4
-
-/* MC_CMD_PORT_READ128_OUT msgresponse */
-#define    MC_CMD_PORT_READ128_OUT_LEN 20
-/* Value */
-#define       MC_CMD_PORT_READ128_OUT_VALUE_OFST 0
-#define       MC_CMD_PORT_READ128_OUT_VALUE_LEN 16
-/* Status */
-#define       MC_CMD_PORT_READ128_OUT_STATUS_OFST 16
-#define       MC_CMD_PORT_READ128_OUT_STATUS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PORT_WRITE128
- * Write a 128-bit register to the indirect port register map. The port to
- * access is implied by the Shared memory channel used.
- */
-#define MC_CMD_PORT_WRITE128 0x17
-
-/* MC_CMD_PORT_WRITE128_IN msgrequest */
-#define    MC_CMD_PORT_WRITE128_IN_LEN 20
-/* Address */
-#define       MC_CMD_PORT_WRITE128_IN_ADDR_OFST 0
-#define       MC_CMD_PORT_WRITE128_IN_ADDR_LEN 4
-/* Value */
-#define       MC_CMD_PORT_WRITE128_IN_VALUE_OFST 4
-#define       MC_CMD_PORT_WRITE128_IN_VALUE_LEN 16
-
-/* MC_CMD_PORT_WRITE128_OUT msgresponse */
-#define    MC_CMD_PORT_WRITE128_OUT_LEN 4
-/* Status */
-#define       MC_CMD_PORT_WRITE128_OUT_STATUS_OFST 0
-#define       MC_CMD_PORT_WRITE128_OUT_STATUS_LEN 4
-
-/* MC_CMD_CAPABILITIES structuredef */
-#define    MC_CMD_CAPABILITIES_LEN 4
-/* Small buf table. */
-#define       MC_CMD_CAPABILITIES_SMALL_BUF_TBL_LBN 0
-#define       MC_CMD_CAPABILITIES_SMALL_BUF_TBL_WIDTH 1
-/* Turbo mode (for Maranello). */
-#define       MC_CMD_CAPABILITIES_TURBO_LBN 1
-#define       MC_CMD_CAPABILITIES_TURBO_WIDTH 1
-/* Turbo mode active (for Maranello). */
-#define       MC_CMD_CAPABILITIES_TURBO_ACTIVE_LBN 2
-#define       MC_CMD_CAPABILITIES_TURBO_ACTIVE_WIDTH 1
-/* PTP offload. */
-#define       MC_CMD_CAPABILITIES_PTP_LBN 3
-#define       MC_CMD_CAPABILITIES_PTP_WIDTH 1
-/* AOE mode. */
-#define       MC_CMD_CAPABILITIES_AOE_LBN 4
-#define       MC_CMD_CAPABILITIES_AOE_WIDTH 1
-/* AOE mode active. */
-#define       MC_CMD_CAPABILITIES_AOE_ACTIVE_LBN 5
-#define       MC_CMD_CAPABILITIES_AOE_ACTIVE_WIDTH 1
-/* AOE mode active. */
-#define       MC_CMD_CAPABILITIES_FC_ACTIVE_LBN 6
-#define       MC_CMD_CAPABILITIES_FC_ACTIVE_WIDTH 1
-#define       MC_CMD_CAPABILITIES_RESERVED_LBN 7
-#define       MC_CMD_CAPABILITIES_RESERVED_WIDTH 25
+/* MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT msgresponse */
+#define    MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_LEN 8
+/* Current value set in NIC, in seconds */
+#define       MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_CURRENT_OFST 0
+#define       MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_CURRENT_LEN 4
+/* Maximum supported by NIC, in seconds */
+#define       MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_MAXIMUM_OFST 4
+#define       MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_MAXIMUM_LEN 4
 
 
 /***********************************/
@@ -4427,112 +3897,6 @@
 
 
 /***********************************/
-/* MC_CMD_DBI_READX
- * Read DBI register(s) -- extended functionality
- */
-#define MC_CMD_DBI_READX 0x19
-#undef MC_CMD_0x19_PRIVILEGE_CTG
-
-#define MC_CMD_0x19_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_DBI_READX_IN msgrequest */
-#define    MC_CMD_DBI_READX_IN_LENMIN 8
-#define    MC_CMD_DBI_READX_IN_LENMAX 248
-#define    MC_CMD_DBI_READX_IN_LENMAX_MCDI2 1016
-#define    MC_CMD_DBI_READX_IN_LEN(num) (0+8*(num))
-#define    MC_CMD_DBI_READX_IN_DBIRDOP_NUM(len) (((len)-0)/8)
-/* Each Read op consists of an address (offset 0), VF/CS2) */
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_OFST 0
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LEN 8
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LO_OFST 0
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LO_LEN 4
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LO_LBN 0
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LO_WIDTH 32
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_HI_OFST 4
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_HI_LEN 4
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_HI_LBN 32
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_HI_WIDTH 32
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_MINNUM 1
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_MAXNUM 31
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_MAXNUM_MCDI2 127
-
-/* MC_CMD_DBI_READX_OUT msgresponse */
-#define    MC_CMD_DBI_READX_OUT_LENMIN 4
-#define    MC_CMD_DBI_READX_OUT_LENMAX 252
-#define    MC_CMD_DBI_READX_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_DBI_READX_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_DBI_READX_OUT_VALUE_NUM(len) (((len)-0)/4)
-/* Value */
-#define       MC_CMD_DBI_READX_OUT_VALUE_OFST 0
-#define       MC_CMD_DBI_READX_OUT_VALUE_LEN 4
-#define       MC_CMD_DBI_READX_OUT_VALUE_MINNUM 1
-#define       MC_CMD_DBI_READX_OUT_VALUE_MAXNUM 63
-#define       MC_CMD_DBI_READX_OUT_VALUE_MAXNUM_MCDI2 255
-
-/* MC_CMD_DBIRDOP_TYPEDEF structuredef */
-#define    MC_CMD_DBIRDOP_TYPEDEF_LEN 8
-#define       MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_OFST 0
-#define       MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_LEN 4
-#define       MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_LBN 0
-#define       MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_WIDTH 32
-#define       MC_CMD_DBIRDOP_TYPEDEF_PARMS_OFST 4
-#define       MC_CMD_DBIRDOP_TYPEDEF_PARMS_LEN 4
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_NUM_OFST 4
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_NUM_LBN 16
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_NUM_WIDTH 16
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_ACTIVE_OFST 4
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_ACTIVE_LBN 15
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_ACTIVE_WIDTH 1
-#define        MC_CMD_DBIRDOP_TYPEDEF_CS2_OFST 4
-#define        MC_CMD_DBIRDOP_TYPEDEF_CS2_LBN 14
-#define        MC_CMD_DBIRDOP_TYPEDEF_CS2_WIDTH 1
-#define       MC_CMD_DBIRDOP_TYPEDEF_PARMS_LBN 32
-#define       MC_CMD_DBIRDOP_TYPEDEF_PARMS_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_SET_RAND_SEED
- * Set the 16byte seed for the MC pseudo-random generator.
- */
-#define MC_CMD_SET_RAND_SEED 0x1a
-#undef MC_CMD_0x1a_PRIVILEGE_CTG
-
-#define MC_CMD_0x1a_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SET_RAND_SEED_IN msgrequest */
-#define    MC_CMD_SET_RAND_SEED_IN_LEN 16
-/* Seed value. */
-#define       MC_CMD_SET_RAND_SEED_IN_SEED_OFST 0
-#define       MC_CMD_SET_RAND_SEED_IN_SEED_LEN 16
-
-/* MC_CMD_SET_RAND_SEED_OUT msgresponse */
-#define    MC_CMD_SET_RAND_SEED_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_LTSSM_HIST
- * Retrieve the history of the LTSSM, if the build supports it.
- */
-#define MC_CMD_LTSSM_HIST 0x1b
-
-/* MC_CMD_LTSSM_HIST_IN msgrequest */
-#define    MC_CMD_LTSSM_HIST_IN_LEN 0
-
-/* MC_CMD_LTSSM_HIST_OUT msgresponse */
-#define    MC_CMD_LTSSM_HIST_OUT_LENMIN 0
-#define    MC_CMD_LTSSM_HIST_OUT_LENMAX 252
-#define    MC_CMD_LTSSM_HIST_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_LTSSM_HIST_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_LTSSM_HIST_OUT_DATA_NUM(len) (((len)-0)/4)
-/* variable number of LTSSM values, as bytes. The history is read-to-clear. */
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_OFST 0
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_LEN 4
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_MINNUM 0
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_MAXNUM 63
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_MAXNUM_MCDI2 255
-
-
-/***********************************/
 /* MC_CMD_DRV_ATTACH
  * Inform MCPU that this port is managed on the host (i.e. driver active). For
  * Huntington, also request the preferred datapath firmware to use if possible
@@ -4705,6 +4069,7 @@
 /* Flags associated with this function */
 #define       MC_CMD_DRV_ATTACH_EXT_OUT_FUNC_FLAGS_OFST 4
 #define       MC_CMD_DRV_ATTACH_EXT_OUT_FUNC_FLAGS_LEN 4
+/* enum property: bitshift */
 /* enum: Labels the lowest-numbered function visible to the OS */
 #define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY 0x0
 /* enum: The function can control the link state of the physical port it is
@@ -4732,22 +4097,6 @@
 
 
 /***********************************/
-/* MC_CMD_SHMUART
- * Route UART output to circular buffer in shared memory instead.
- */
-#define MC_CMD_SHMUART 0x1f
-
-/* MC_CMD_SHMUART_IN msgrequest */
-#define    MC_CMD_SHMUART_IN_LEN 4
-/* ??? */
-#define       MC_CMD_SHMUART_IN_FLAG_OFST 0
-#define       MC_CMD_SHMUART_IN_FLAG_LEN 4
-
-/* MC_CMD_SHMUART_OUT msgresponse */
-#define    MC_CMD_SHMUART_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_PORT_RESET
  * Generic per-port reset. There is no equivalent for per-board reset. Locks
  * required: None; Return code: 0, ETIME. NOTE: This command is deprecated -
@@ -4790,100 +4139,6 @@
 
 
 /***********************************/
-/* MC_CMD_PCIE_CREDITS
- * Read instantaneous and minimum flow control thresholds.
- */
-#define MC_CMD_PCIE_CREDITS 0x21
-
-/* MC_CMD_PCIE_CREDITS_IN msgrequest */
-#define    MC_CMD_PCIE_CREDITS_IN_LEN 8
-/* poll period. 0 is disabled */
-#define       MC_CMD_PCIE_CREDITS_IN_POLL_PERIOD_OFST 0
-#define       MC_CMD_PCIE_CREDITS_IN_POLL_PERIOD_LEN 4
-/* wipe statistics */
-#define       MC_CMD_PCIE_CREDITS_IN_WIPE_OFST 4
-#define       MC_CMD_PCIE_CREDITS_IN_WIPE_LEN 4
-
-/* MC_CMD_PCIE_CREDITS_OUT msgresponse */
-#define    MC_CMD_PCIE_CREDITS_OUT_LEN 16
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_HDR_OFST 0
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_HDR_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_DATA_OFST 2
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_DATA_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_HDR_OFST 4
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_HDR_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_DATA_OFST 6
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_DATA_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_HDR_OFST 8
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_HDR_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_DATA_OFST 10
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_DATA_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_HDR_OFST 12
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_HDR_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_DATA_OFST 14
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_DATA_LEN 2
-
-
-/***********************************/
-/* MC_CMD_RXD_MONITOR
- * Get histogram of RX queue fill level.
- */
-#define MC_CMD_RXD_MONITOR 0x22
-
-/* MC_CMD_RXD_MONITOR_IN msgrequest */
-#define    MC_CMD_RXD_MONITOR_IN_LEN 12
-#define       MC_CMD_RXD_MONITOR_IN_QID_OFST 0
-#define       MC_CMD_RXD_MONITOR_IN_QID_LEN 4
-#define       MC_CMD_RXD_MONITOR_IN_POLL_PERIOD_OFST 4
-#define       MC_CMD_RXD_MONITOR_IN_POLL_PERIOD_LEN 4
-#define       MC_CMD_RXD_MONITOR_IN_WIPE_OFST 8
-#define       MC_CMD_RXD_MONITOR_IN_WIPE_LEN 4
-
-/* MC_CMD_RXD_MONITOR_OUT msgresponse */
-#define    MC_CMD_RXD_MONITOR_OUT_LEN 80
-#define       MC_CMD_RXD_MONITOR_OUT_QID_OFST 0
-#define       MC_CMD_RXD_MONITOR_OUT_QID_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_FILL_OFST 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_FILL_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_FILL_OFST 8
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_FILL_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_1_OFST 12
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_1_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_2_OFST 16
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_2_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_4_OFST 20
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_4_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_8_OFST 24
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_8_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_16_OFST 28
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_16_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_32_OFST 32
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_32_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_64_OFST 36
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_64_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_128_OFST 40
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_128_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_256_OFST 44
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_256_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_GE_256_OFST 48
-#define       MC_CMD_RXD_MONITOR_OUT_RING_GE_256_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_1_OFST 52
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_1_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_2_OFST 56
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_2_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_4_OFST 60
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_4_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_8_OFST 64
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_8_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_16_OFST 68
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_16_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_32_OFST 72
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_32_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_GE_32_OFST 76
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_GE_32_LEN 4
-
-
-/***********************************/
 /* MC_CMD_PUTS
  * Copy the given ASCII string out onto UART and/or out of the network port.
  */
@@ -4931,6 +4186,54 @@
 /* MC_CMD_GET_PHY_CFG_IN msgrequest */
 #define    MC_CMD_GET_PHY_CFG_IN_LEN 0
 
+/* MC_CMD_GET_PHY_CFG_IN_V2 msgrequest */
+#define    MC_CMD_GET_PHY_CFG_IN_V2_LEN 8
+/* Target port to request PHY state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
+ */
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LO_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LO_LBN 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_HI_OFST 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_HI_LBN 32
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 3
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 20
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 16
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 2
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LINK_END_OFST 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LO_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LO_LBN 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_HI_OFST 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_HI_LBN 32
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_PHY_CFG_OUT msgresponse */
 #define    MC_CMD_GET_PHY_CFG_OUT_LEN 72
 /* flags */
@@ -5026,6 +4329,9 @@
 #define        MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_OFST 8
 #define        MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_LBN 21
 #define        MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_WIDTH 1
+#define        MC_CMD_PHY_CAP_200000FDX_OFST 8
+#define        MC_CMD_PHY_CAP_200000FDX_LBN 22
+#define        MC_CMD_PHY_CAP_200000FDX_WIDTH 1
 /* ?? */
 #define       MC_CMD_GET_PHY_CFG_OUT_CHANNEL_OFST 12
 #define       MC_CMD_GET_PHY_CFG_OUT_CHANNEL_LEN 4
@@ -5059,6 +4365,7 @@
 #define          MC_CMD_MEDIA_DSFP 0x8
 #define       MC_CMD_GET_PHY_CFG_OUT_MMD_MASK_OFST 48
 #define       MC_CMD_GET_PHY_CFG_OUT_MMD_MASK_LEN 4
+/* enum property: bitshift */
 /* enum: Native clause 22 */
 #define          MC_CMD_MMD_CLAUSE22 0x0
 #define          MC_CMD_MMD_CLAUSE45_PMAPMD 0x1 /* enum */
@@ -5084,7 +4391,7 @@
 #define MC_CMD_START_BIST 0x25
 #undef MC_CMD_0x25_PRIVILEGE_CTG
 
-#define MC_CMD_0x25_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0x25_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_START_BIST_IN msgrequest */
 #define    MC_CMD_START_BIST_IN_LEN 4
@@ -5124,7 +4431,7 @@
 #define MC_CMD_POLL_BIST 0x26
 #undef MC_CMD_0x26_PRIVILEGE_CTG
 
-#define MC_CMD_0x26_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0x26_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_POLL_BIST_IN msgrequest */
 #define    MC_CMD_POLL_BIST_IN_LEN 0
@@ -5282,33 +4589,6 @@
 
 
 /***********************************/
-/* MC_CMD_FLUSH_RX_QUEUES
- * Flush receive queue(s). If SRIOV is enabled (via MC_CMD_SRIOV), then RXQ
- * flushes should be initiated via this MCDI operation, rather than via
- * directly writing FLUSH_CMD.
- *
- * The flush is completed (either done/fail) asynchronously (after this command
- * returns). The driver must still wait for flush done/failure events as usual.
- */
-#define MC_CMD_FLUSH_RX_QUEUES 0x27
-
-/* MC_CMD_FLUSH_RX_QUEUES_IN msgrequest */
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_LENMIN 4
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_LENMAX 252
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_LEN(num) (0+4*(num))
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_NUM(len) (((len)-0)/4)
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_OFST 0
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_LEN 4
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MINNUM 1
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM 63
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM_MCDI2 255
-
-/* MC_CMD_FLUSH_RX_QUEUES_OUT msgresponse */
-#define    MC_CMD_FLUSH_RX_QUEUES_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_GET_LOOPBACK_MODES
  * Returns a bitmask of loopback modes available at each speed.
  */
@@ -5320,6 +4600,54 @@
 /* MC_CMD_GET_LOOPBACK_MODES_IN msgrequest */
 #define    MC_CMD_GET_LOOPBACK_MODES_IN_LEN 0
 
+/* MC_CMD_GET_LOOPBACK_MODES_IN_V2 msgrequest */
+#define    MC_CMD_GET_LOOPBACK_MODES_IN_V2_LEN 8
+/* Target port to request loopback modes for. Uses MAE_LINK_ENDPOINT_SELECTOR
+ * which identifies a real or virtual network port by MAE port and link end.
+ * See the structure definition for more details
+ */
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LO_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LO_LBN 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_HI_OFST 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_HI_LBN 32
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 3
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 20
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 16
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 2
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LINK_END_OFST 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LO_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LO_LBN 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_HI_OFST 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_HI_LBN 32
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_LOOPBACK_MODES_OUT msgresponse */
 #define    MC_CMD_GET_LOOPBACK_MODES_OUT_LEN 40
 /* Supported loopbacks. */
@@ -5333,6 +4661,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_100M_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_100M_HI_LBN 32
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_100M_HI_WIDTH 32
+/* enum property: bitshift */
 /* enum: None. */
 #define          MC_CMD_LOOPBACK_NONE 0x0
 /* enum: Data. */
@@ -5422,6 +4751,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_1G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_1G_HI_LBN 96
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_1G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5435,6 +4765,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_10G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_10G_HI_LBN 160
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_10G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5448,6 +4779,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_HI_LBN 224
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5461,6 +4793,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_40G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_40G_HI_LBN 288
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_40G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 
@@ -5479,6 +4812,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100M_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100M_HI_LBN 32
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100M_HI_WIDTH 32
+/* enum property: bitshift */
 /* enum: None. */
 /*               MC_CMD_LOOPBACK_NONE 0x0 */
 /* enum: Data. */
@@ -5568,6 +4902,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_1G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_1G_HI_LBN 96
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_1G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5581,6 +4916,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_10G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_10G_HI_LBN 160
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_10G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5594,6 +4930,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_SUGGESTED_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_SUGGESTED_HI_LBN 224
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_SUGGESTED_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5607,6 +4944,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_40G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_40G_HI_LBN 288
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_40G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported 25G loopbacks. */
@@ -5620,6 +4958,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_25G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_25G_HI_LBN 352
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_25G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported 50 loopbacks. */
@@ -5633,6 +4972,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_50G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_50G_HI_LBN 416
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_50G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported 100G loopbacks. */
@@ -5646,6 +4986,214 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100G_HI_LBN 480
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+
+/* MC_CMD_GET_LOOPBACK_MODES_OUT_V3 msgresponse: Supported loopback modes for
+ * newer NICs with 200G support
+ */
+#define    MC_CMD_GET_LOOPBACK_MODES_OUT_V3_LEN 72
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LO_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LO_LBN 0
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_HI_OFST 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_HI_LBN 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_HI_WIDTH 32
+/* enum property: bitshift */
+/* enum: None. */
+/*               MC_CMD_LOOPBACK_NONE 0x0 */
+/* enum: Data. */
+/*               MC_CMD_LOOPBACK_DATA 0x1 */
+/* enum: GMAC. */
+/*               MC_CMD_LOOPBACK_GMAC 0x2 */
+/* enum: XGMII. */
+/*               MC_CMD_LOOPBACK_XGMII 0x3 */
+/* enum: XGXS. */
+/*               MC_CMD_LOOPBACK_XGXS 0x4 */
+/* enum: XAUI. */
+/*               MC_CMD_LOOPBACK_XAUI 0x5 */
+/* enum: GMII. */
+/*               MC_CMD_LOOPBACK_GMII 0x6 */
+/* enum: SGMII. */
+/*               MC_CMD_LOOPBACK_SGMII 0x7 */
+/* enum: XGBR. */
+/*               MC_CMD_LOOPBACK_XGBR 0x8 */
+/* enum: XFI. */
+/*               MC_CMD_LOOPBACK_XFI 0x9 */
+/* enum: XAUI Far. */
+/*               MC_CMD_LOOPBACK_XAUI_FAR 0xa */
+/* enum: GMII Far. */
+/*               MC_CMD_LOOPBACK_GMII_FAR 0xb */
+/* enum: SGMII Far. */
+/*               MC_CMD_LOOPBACK_SGMII_FAR 0xc */
+/* enum: XFI Far. */
+/*               MC_CMD_LOOPBACK_XFI_FAR 0xd */
+/* enum: GPhy. */
+/*               MC_CMD_LOOPBACK_GPHY 0xe */
+/* enum: PhyXS. */
+/*               MC_CMD_LOOPBACK_PHYXS 0xf */
+/* enum: PCS. */
+/*               MC_CMD_LOOPBACK_PCS 0x10 */
+/* enum: PMA-PMD. */
+/*               MC_CMD_LOOPBACK_PMAPMD 0x11 */
+/* enum: Cross-Port. */
+/*               MC_CMD_LOOPBACK_XPORT 0x12 */
+/* enum: XGMII-Wireside. */
+/*               MC_CMD_LOOPBACK_XGMII_WS 0x13 */
+/* enum: XAUI Wireside. */
+/*               MC_CMD_LOOPBACK_XAUI_WS 0x14 */
+/* enum: XAUI Wireside Far. */
+/*               MC_CMD_LOOPBACK_XAUI_WS_FAR 0x15 */
+/* enum: XAUI Wireside near. */
+/*               MC_CMD_LOOPBACK_XAUI_WS_NEAR 0x16 */
+/* enum: GMII Wireside. */
+/*               MC_CMD_LOOPBACK_GMII_WS 0x17 */
+/* enum: XFI Wireside. */
+/*               MC_CMD_LOOPBACK_XFI_WS 0x18 */
+/* enum: XFI Wireside Far. */
+/*               MC_CMD_LOOPBACK_XFI_WS_FAR 0x19 */
+/* enum: PhyXS Wireside. */
+/*               MC_CMD_LOOPBACK_PHYXS_WS 0x1a */
+/* enum: PMA lanes MAC-Serdes. */
+/*               MC_CMD_LOOPBACK_PMA_INT 0x1b */
+/* enum: KR Serdes Parallel (Encoder). */
+/*               MC_CMD_LOOPBACK_SD_NEAR 0x1c */
+/* enum: KR Serdes Serial. */
+/*               MC_CMD_LOOPBACK_SD_FAR 0x1d */
+/* enum: PMA lanes MAC-Serdes Wireside. */
+/*               MC_CMD_LOOPBACK_PMA_INT_WS 0x1e */
+/* enum: KR Serdes Parallel Wireside (Full PCS). */
+/*               MC_CMD_LOOPBACK_SD_FEP2_WS 0x1f */
+/* enum: KR Serdes Parallel Wireside (Sym Aligner to TX). */
+/*               MC_CMD_LOOPBACK_SD_FEP1_5_WS 0x20 */
+/* enum: KR Serdes Parallel Wireside (Deserializer to Serializer). */
+/*               MC_CMD_LOOPBACK_SD_FEP_WS 0x21 */
+/* enum: KR Serdes Serial Wireside. */
+/*               MC_CMD_LOOPBACK_SD_FES_WS 0x22 */
+/* enum: Near side of AOE Siena side port */
+/*               MC_CMD_LOOPBACK_AOE_INT_NEAR 0x23 */
+/* enum: Medford Wireside datapath loopback */
+/*               MC_CMD_LOOPBACK_DATA_WS 0x24 */
+/* enum: Force link up without setting up any physical loopback (snapper use
+ * only)
+ */
+/*               MC_CMD_LOOPBACK_FORCE_EXT_LINK 0x25 */
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_OFST 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LO_OFST 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LO_LBN 64
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_HI_OFST 12
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_HI_LBN 96
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_OFST 16
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LO_OFST 16
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LO_LBN 128
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_HI_OFST 20
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_HI_LBN 160
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_OFST 24
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LO_OFST 24
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LO_LBN 192
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_HI_OFST 28
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_HI_LBN 224
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_OFST 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LO_OFST 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LO_LBN 256
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_HI_OFST 36
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_HI_LBN 288
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported 25G loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_OFST 40
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LO_OFST 40
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LO_LBN 320
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_HI_OFST 44
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_HI_LBN 352
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported 50 loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_OFST 48
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LO_OFST 48
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LO_LBN 384
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_HI_OFST 52
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_HI_LBN 416
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported 100G loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_OFST 56
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LO_OFST 56
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LO_LBN 448
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_HI_OFST 60
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_HI_LBN 480
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported 200G loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_OFST 64
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LO_OFST 64
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LO_LBN 512
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_HI_OFST 68
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_HI_LBN 544
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 
@@ -5673,13 +5221,835 @@
 #define       FEC_TYPE_TYPE_LEN 4
 /* enum: No FEC */
 #define          MC_CMD_FEC_NONE 0x0
-/* enum: Clause 74 BASE-R FEC (a.k.a Firecode) */
+/* enum: IEEE 802.3, Clause 74 BASE-R FEC (a.k.a Firecode) */
 #define          MC_CMD_FEC_BASER 0x1
-/* enum: Clause 91/Clause 108 Reed-Solomon FEC */
+/* enum: IEEE 802.3, Clause 91/Clause 108 Reed-Solomon FEC */
 #define          MC_CMD_FEC_RS 0x2
+/* enum: IEEE 802.3, Clause 161, interleaved RS-FEC sublayer for 100GBASE-R
+ * PHYs
+ */
+#define          MC_CMD_FEC_IEEE_RS_INT 0x3
+/* enum: Ethernet Consortium, Low Latency RS-FEC. RS(272, 258). Replaces FEC
+ * specified in Clause 119 for 100/200G PHY. Replaces FEC specified in Clause
+ * 134 for 50G PHY.
+ */
+#define          MC_CMD_FEC_ETCS_RS_LL 0x4
+/* enum: FEC mode selected automatically */
+#define          MC_CMD_FEC_AUTO 0x5
 #define       FEC_TYPE_TYPE_LBN 0
 #define       FEC_TYPE_TYPE_WIDTH 32
 
+/* MC_CMD_ETH_TECH structuredef: Ethernet technology as defined by IEEE802.3,
+ * Ethernet Technology Consortium, proprietary technologies. The driver must
+ * not use technologies labelled NONE and AUTO.
+ */
+#define    MC_CMD_ETH_TECH_LEN 16
+/* The enums in this field can be used either as bitwise indices into a tech
+ * mask (e.g. see MC_CMD_ETH_AN_FIELDS/TECH_MASK for example) or as regular
+ * enums (e.g. see MC_CMD_LINK_CTRL_IN/ADVERTISED_TECH_ABILITIES_MASK). This
+ * structure must be updated to add new technologies when projects that need
+ * them arise. An incomplete list of possible expansion in the future include:
+ * 100GBASE_KP4, 800GBASE_CR8, 800GBASE_KR8, 800GBASE_DR8, 800GBASE_SR8
+ * 800GBASE_VR8
+ */
+#define       MC_CMD_ETH_TECH_TECH_OFST 0
+#define       MC_CMD_ETH_TECH_TECH_LEN 16
+/* enum: 1000BASE-KX - 1000BASE-X PCS/PMA over an electrical backplane PMD. See
+ * IEEE 802.3 Clause 70
+ */
+#define          MC_CMD_ETH_TECH_1000BASEKX 0x0
+/* enum: 10GBASE-R - PCS/PMA over an electrical backplane PMD. Refer to IEEE
+ * 802.3 Clause 72
+ */
+#define          MC_CMD_ETH_TECH_10GBASE_KR 0x1
+/* enum: 40GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 84.
+ */
+#define          MC_CMD_ETH_TECH_40GBASE_KR4 0x2
+/* enum: 40GBASE-R PCS/PMA over 4 lane shielded copper balanced cable PMD. See
+ * IEEE 802.3 Clause 85
+ */
+#define          MC_CMD_ETH_TECH_40GBASE_CR4 0x3
+/* enum: 40GBASE-R PCS/PMA over 4 lane multimode fiber PMD as specified in
+ * Clause 86
+ */
+#define          MC_CMD_ETH_TECH_40GBASE_SR4 0x4
+/* enum: 40GBASE-R PCS/PMA over 4 WDM lane single mode fiber PMD with long
+ * reach. See IEEE 802.3 Clause 87
+ */
+#define          MC_CMD_ETH_TECH_40GBASE_LR4 0x5
+/* enum: 25GBASE-R PCS/PMA over shielded balanced copper cable PMD. See IEEE
+ * 802.3 Clause 110
+ */
+#define          MC_CMD_ETH_TECH_25GBASE_CR 0x6
+/* enum: 25GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 111
+ */
+#define          MC_CMD_ETH_TECH_25GBASE_KR 0x7
+/* enum: 25GBASE-R PCS/PMA over multimode fiber PMD. Refer to IEEE 802.3 Clause
+ * 112
+ */
+#define          MC_CMD_ETH_TECH_25GBASE_SR 0x8
+/* enum: An Ethernet Physical layer operating at 50 Gb/s on twin-axial copper
+ * cable. Refer to Ethernet Technology Consortium 25/50G Ethernet Spec.
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_CR2 0x9
+/* enum: An Ethernet Physical layer operating at 50 Gb/s on copper backplane.
+ * Refer to Ethernet Technology Consortium 25/50G Ethernet Spec.
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_KR2 0xa
+/* enum: 100GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 93
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_KR4 0xb
+/* enum: 100GBASE-R PCS/PMA over 4 lane multimode fiber PMD. See IEEE 802.3
+ * Clause 95
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_SR4 0xc
+/* enum: 100GBASE-R PCS/PMA over 4 lane shielded copper balanced cable PMD. See
+ * IEEE 802.3 Clause 92
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_CR4 0xd
+/* enum: 100GBASE-R PCS/PMA over 4 WDM lane single mode fiber PMD, with
+ * long/extended reach,. See IEEE 802.3 Clause 88
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_LR4_ER4 0xe
+/* enum: An Ethernet Physical layer operating at 50 Gb/s on short reach fiber.
+ * Refer to Ethernet Technology Consortium 25/50G Ethernet Spec.
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_SR2 0xf
+/* enum: 1000BASEX PCS/PMA. See IEEE 802.3 Clause 36 over undefined PMD, duplex
+ * mode unknown
+ */
+#define          MC_CMD_ETH_TECH_1000BASEX 0x10
+/* enum: Non-standardised. 10G direct attach */
+#define          MC_CMD_ETH_TECH_10GBASE_CR 0x11
+/* enum: 10GBASE-SR fiber over 850nm optics. See IEEE 802.3 Clause 52 */
+#define          MC_CMD_ETH_TECH_10GBASE_SR 0x12
+/* enum: 10GBASE-LR fiber over 1310nm optics. See IEEE 802.3 Clause 52 */
+#define          MC_CMD_ETH_TECH_10GBASE_LR 0x13
+/* enum: 10GBASE-LRM fiber over 1310 nm optics. See IEEE 802.3 Clause 68 */
+#define          MC_CMD_ETH_TECH_10GBASE_LRM 0x14
+/* enum: 10GBASE-ER fiber over 1550nm optics. See IEEE 802.3 Clause 52 */
+#define          MC_CMD_ETH_TECH_10GBASE_ER 0x15
+/* enum: 50GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 137
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_KR 0x16
+/* enum: 50GBASE-SR PCS/PMA over multimode fiber PMD as specified in Clause 138
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_SR 0x17
+/* enum: 50GBASE-CR PCS/PMA over shielded copper balanced cable PMD. See IEEE
+ * 802.3 Clause 136
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_CR 0x18
+/* enum: 50GBASE-R PCS/PMA over single mode fiber PMD as specified in Clause
+ * 139.
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_LR_ER_FR 0x19
+/* enum: 100 Gb/s PHY using 100GBASE-R encoding over single-mode fiber with
+ * reach up to at least 500 m (see IEEE 802.3 Clause 140)
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_DR 0x1a
+/* enum: 100GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 137
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_KR2 0x1b
+/* enum: 100GBASE-R PCS/PMA over 2 lane multimode fiber PMD. See IEEE 802.3
+ * Clause 138
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_SR2 0x1c
+/* enum: 100GBASE-R PCS/PMA over 2 lane shielded copper balanced cable PMD. See
+ * IEEE 802.3 Clause 136
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_CR2 0x1d
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_100GBASE_LR2_ER2_FR2 0x1e
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_100GBASE_DR2 0x1f
+/* enum: 200GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 137
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_KR4 0x20
+/* enum: 200GBASE-R PCS/PMA over 4 lane multimode fiber PMD. See IEEE 802.3
+ * Clause 138
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_SR4 0x21
+/* enum: 200GBASE-R PCS/PMA over 4 WDM lane single-mode fiber PMD as specified
+ * in Clause 122
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_LR4_ER4_FR4 0x22
+/* enum: 200GBASE-R PCS/PMA over 4-lane single-mode fiber PMD. See IEEE 802.3
+ * Clause 121
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_DR4 0x23
+/* enum: 200GBASE-R PCS/PMA over 4 lane shielded copper balanced cable PMD as
+ * specified in Clause 136
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_CR4 0x24
+/* enum: Ethernet Technology Consortium 400G AN Spec. 400GBASE-KR8 PMD uses
+ * 802.3 Clause 137, but the number PMD lanes is 8.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_KR8 0x25
+/* enum: 400GBASE-R PCS/PMA over 8-lane multimode fiber PMD. See IEEE 802.3
+ * Clause 138
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_SR8 0x26
+/* enum: 400GBASE-R PCS/PMA over 8 WDM lane single-mode fiber PMD. See IEEE
+ * 802.3 Clause 122
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_LR8_ER8_FR8 0x27
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_400GBASE_DR8 0x28
+/* enum: Ethernet Technology Consortium 400G AN Spec. 400GBASE-CR8 PMD uses
+ * IEEE 802.3 Clause 136, but the number PMD lanes is 8.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_CR8 0x29
+/* enum: 100GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3ck
+ * Clause 163.
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_KR 0x2a
+/* enum: IEEE 802.3ck. 100G PHY with PMD as specified in Clause 167 over short
+ * reach fiber
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_SR 0x2b
+/* enum: 100G PMD together with single-mode fiber medium. See IEEE 802.3 Clause
+ * 140
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_LR_ER_FR 0x2c
+/* enum: 100GBASE-R PCS/PMA over shielded balanced copper cable PMD. See IEEE
+ * 802.3 in Clause 162 IEEE 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_CR 0x2d
+/* enum: 100G PMD together with single-mode fiber medium. See IEEE 802.3 Clause
+ * 140
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_DR 0x2e
+/* enum: 200GBASE-R PCS/PMA over an electrical backplane PMD as specified in
+ * Clause 163 IEEE 802.3ck
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_KR2 0x2f
+/* enum: 200G PHY with PMD as specified in Clause 167 over short reach fiber
+ * IEEE 802.3ck
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_SR2 0x30
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_200GBASE_LR2_ER2_FR2 0x31
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_200GBASE_DR2 0x32
+/* enum: 200GBASE-R PCS/PMA over 2 lane shielded balanced copper cable PMD as
+ * specified in Clause 162 IEEE 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_CR2 0x33
+/* enum: 400GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 163 IEEE 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_KR4 0x34
+/* enum: 400G PHY with PMD over short reach fiber. See Clause 167 of IEEE
+ * 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_SR4 0x35
+/* enum: 400GBASE-R PCS/PMA over 4 WDM lane single-mode fiber PMD. See IEEE
+ * 802.3 Clause 151
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_LR4_ER4_FR4 0x36
+/* enum: 400GBASE-R PCS/PMA over 4-lane single-mode fiber PMD as specified in
+ * Clause 124
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_DR4 0x37
+/* enum: 400GBASE-R PCS/PMA over 4 lane shielded balanced copper cable PMD as
+ * specified in Clause 162 of IEEE 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_CR4 0x38
+/* enum: Automatic tech mode. The driver must not use this. */
+#define          MC_CMD_ETH_TECH_AUTO 0x39
+/* enum: See IEEE 802.3cc-2017 Clause 114 */
+#define          MC_CMD_ETH_TECH_25GBASE_LR_ER 0x3a
+/* enum: Up to 7 m over twinaxial copper cable assembly (10 lanes, 10 Gbit/s
+ * each) See IEEE 802.3ba-2010 Clause 85
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_CR10 0x3b
+/* enum: Invalid tech mode. The driver must not use this. */
+#define          MC_CMD_ETH_TECH_NONE 0x7f
+#define       MC_CMD_ETH_TECH_TECH_LBN 0
+#define       MC_CMD_ETH_TECH_TECH_WIDTH 128
+
+/* MC_CMD_LINK_STATUS_FLAGS structuredef */
+#define    MC_CMD_LINK_STATUS_FLAGS_LEN 8
+/* Flags used to report the current configuration/state of the link. */
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_OFST 0
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LEN 8
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LO_OFST 0
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LO_LEN 4
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LO_LBN 0
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LO_WIDTH 32
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_HI_OFST 4
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_HI_LEN 4
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_HI_LBN 32
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_HI_WIDTH 32
+/* enum property: bitshift */
+/* enum: Whether we have overall link up */
+#define          MC_CMD_LINK_STATUS_FLAGS_LINK_UP 0x0
+/* enum: If set, the PHY has no external RX link synchronisation */
+#define          MC_CMD_LINK_STATUS_FLAGS_NO_PHY_LINK 0x1
+/* enum: If set, PMD/MDI is not connected (e.g. cable disconnected, module cage
+ * empty)
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_MDI_DISCONNECTED 0x2
+/* enum: Set on error while decoding module data (e.g. module EEPROM does not
+ * contain valid values, has checksum errors, etc.)
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_BAD 0x3
+/* enum: Set when module unsupported (e.g. unsupported link rate or link
+ * technology)
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_UNSUPPORTED 0x4
+/* enum: Set on error while communicating with the module (e.g. I2C errors
+ * while reading EEPROM)
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_COMMS_FAULT 0x5
+/* enum: Set on module overcurrent/overvoltage condition */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_POWER_FAULT 0x6
+/* enum: Set on module overtemperature condition */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_THERMAL_FAULT 0x7
+/* enum: If set, the module is indicating Loss of Signal */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_LOS 0x8
+/* enum: If set, PMA is indicating loss of CDR lock (clock sync) */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMA_NO_CDR_LOCK 0x9
+/* enum: If set, PMA is indicating loss of analog signal */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMA_LOS 0xa
+/* enum: If set, PCS is indicating loss of block lock */
+#define          MC_CMD_LINK_STATUS_FLAGS_PCS_NO_BLOCK_LOCK 0xb
+/* enum: If set, PCS is indicating loss of alignment marker lock on one or more
+ * lanes
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PCS_NO_AM_LOCK 0xc
+/* enum: If set, PCS is indicating loss of overall alignment lock */
+#define          MC_CMD_LINK_STATUS_FLAGS_PCS_NO_ALIGN_LOCK 0xd
+/* enum: If set, PCS is indicating high bit error rate condition. */
+#define          MC_CMD_LINK_STATUS_FLAGS_PCS_HI_BER 0xe
+/* enum: If set, FEC is indicating loss of FEC lock */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_NO_LOCK 0xf
+/* enum: If set, indicates that the number of symbol errors in a 8192-codeword
+ * window has exceeded the threshold K (417).
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_HI_SER 0x10
+/* enum: If set, the receiver has detected the local FEC has degraded. */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_LOCAL_DEGRADED 0x11
+/* enum: If set, the receiver has detected the remote FEC has degraded. */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_RM_DEGRADED 0x12
+/* enum: If set, the number of symbol errors is over an internal threshold. */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_DEGRADED_SER 0x13
+/* enum: If set, autonegotiation has detected an auto-negotiation capable link
+ * partner
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_AN_ABLE 0x14
+/* enum: If set, autonegotiation base page exchange has failed */
+#define          MC_CMD_LINK_STATUS_FLAGS_AN_BP_FAILED 0x15
+/* enum: If set, autonegotiation next page exchange has failed */
+#define          MC_CMD_LINK_STATUS_FLAGS_AN_NP_FAILED 0x16
+/* enum: If set, autonegotiation has failed to negotiate a common set of
+ * capabilities
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_AN_NO_HCD 0x17
+/* enum: If set, local end link training has failed to establish link training
+ * frame lock on one or more lanes
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_LT_NO_LOCAL_FRAME_LOCK 0x18
+/* enum: If set, remote end link training has failed to establish link training
+ * frame lock on one or more lanes
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_LT_NO_RM_FRAME_LOCK 0x19
+/* enum: If set, remote end has failed to assert Receiver Ready (link training
+ * success) within the designated timeout
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_LT_NO_RX_READY 0x1a
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LBN 0
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_WIDTH 64
+
+/* MC_CMD_PAUSE_MODE structuredef */
+#define    MC_CMD_PAUSE_MODE_LEN 1
+#define       MC_CMD_PAUSE_MODE_TYPE_OFST 0
+#define       MC_CMD_PAUSE_MODE_TYPE_LEN 1
+/* enum: See IEEE 802.3 Clause 73.6.6 */
+#define          MC_CMD_PAUSE_MODE_AN_PAUSE 0x0
+/* enum: See IEEE 802.3 Clause 73.6.6 */
+#define          MC_CMD_PAUSE_MODE_AN_ASYM_DIR 0x1
+#define       MC_CMD_PAUSE_MODE_TYPE_LBN 0
+#define       MC_CMD_PAUSE_MODE_TYPE_WIDTH 8
+
+/* MC_CMD_ETH_AN_FIELDS structuredef: Fields used for IEEE 802.3 Clause 73
+ * Auto-Negotiation. Warning - This is fixed size and cannot be extended. This
+ * structure is used to define autonegotiable abilities (advertised, link
+ * partner and supported abilities).
+ */
+#define    MC_CMD_ETH_AN_FIELDS_LEN 25
+/* Mask of Ethernet technologies. The bit indices in this mask are taken from
+ * the TECH field in the MC_CMD_ETH_TECH structure.
+ */
+#define       MC_CMD_ETH_AN_FIELDS_TECH_MASK_OFST 0
+#define       MC_CMD_ETH_AN_FIELDS_TECH_MASK_LEN 16
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+#define       MC_CMD_ETH_AN_FIELDS_TECH_MASK_LBN 0
+#define       MC_CMD_ETH_AN_FIELDS_TECH_MASK_WIDTH 128
+/* Mask of supported FEC modes */
+#define       MC_CMD_ETH_AN_FIELDS_FEC_MASK_OFST 16
+#define       MC_CMD_ETH_AN_FIELDS_FEC_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+#define       MC_CMD_ETH_AN_FIELDS_FEC_MASK_LBN 128
+#define       MC_CMD_ETH_AN_FIELDS_FEC_MASK_WIDTH 32
+/* Mask of requested FEC modes */
+#define       MC_CMD_ETH_AN_FIELDS_FEC_REQ_OFST 20
+#define       MC_CMD_ETH_AN_FIELDS_FEC_REQ_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+#define       MC_CMD_ETH_AN_FIELDS_FEC_REQ_LBN 160
+#define       MC_CMD_ETH_AN_FIELDS_FEC_REQ_WIDTH 32
+/* Bitmask of negotiated pause modes */
+#define       MC_CMD_ETH_AN_FIELDS_PAUSE_MASK_OFST 24
+#define       MC_CMD_ETH_AN_FIELDS_PAUSE_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+#define       MC_CMD_ETH_AN_FIELDS_PAUSE_MASK_LBN 192
+#define       MC_CMD_ETH_AN_FIELDS_PAUSE_MASK_WIDTH 8
+
+/* MC_CMD_LOOPBACK_V2 structuredef: Loopback modes for use with the new
+ * MC_CMD_LINK_CTRL and MC_CMD_LINK_STATE. These loopback modes are not
+ * supported in other getlink/setlink commands.
+ */
+#define    MC_CMD_LOOPBACK_V2_LEN 4
+#define       MC_CMD_LOOPBACK_V2_MODE_OFST 0
+#define       MC_CMD_LOOPBACK_V2_MODE_LEN 4
+/* enum: No loopback */
+#define          MC_CMD_LOOPBACK_V2_NONE 0x0
+/* enum: Let firmware choose a supported loopback mode */
+#define          MC_CMD_LOOPBACK_V2_AUTO 0x1
+/* enum: Loopback after the MAC */
+#define          MC_CMD_LOOPBACK_V2_POST_MAC 0x2
+/* enum: Loopback after the PCS */
+#define          MC_CMD_LOOPBACK_V2_POST_PCS 0x3
+/* enum: Loopback after the PMA */
+#define          MC_CMD_LOOPBACK_V2_POST_PMA 0x4
+/* enum: Loopback after the MDI Wireside */
+#define          MC_CMD_LOOPBACK_V2_POST_MDI_WS 0x5
+/* enum: Loopback after the PMA Wireside */
+#define          MC_CMD_LOOPBACK_V2_POST_PMA_WS 0x6
+/* enum: Loopback after the PCS Wireside */
+#define          MC_CMD_LOOPBACK_V2_POST_PCS_WS 0x7
+/* enum: Loopback after the MAC Wireside */
+#define          MC_CMD_LOOPBACK_V2_POST_MAC_WS 0x8
+/* enum: Loopback after the MAC FIFOs (before the MAC) */
+#define          MC_CMD_LOOPBACK_V2_PRE_MAC 0x9
+#define       MC_CMD_LOOPBACK_V2_MODE_LBN 0
+#define       MC_CMD_LOOPBACK_V2_MODE_WIDTH 32
+
+/* MC_CMD_FCNTL structuredef */
+#define    MC_CMD_FCNTL_LEN 4
+#define       MC_CMD_FCNTL_MASK_OFST 0
+#define       MC_CMD_FCNTL_MASK_LEN 4
+/* enum: Flow control is off. */
+#define          MC_CMD_FCNTL_OFF 0x0
+/* enum: Respond to flow control. */
+#define          MC_CMD_FCNTL_RESPOND 0x1
+/* enum: Respond to and Issue flow control. */
+#define          MC_CMD_FCNTL_BIDIR 0x2
+/* enum: Auto negotiate flow control. */
+#define          MC_CMD_FCNTL_AUTO 0x3
+/* enum: Priority flow control. This is only supported on KSB. */
+#define          MC_CMD_FCNTL_QBB 0x4
+/* enum: Issue flow control. */
+#define          MC_CMD_FCNTL_GENERATE 0x5
+#define       MC_CMD_FCNTL_MASK_LBN 0
+#define       MC_CMD_FCNTL_MASK_WIDTH 32
+
+/* MC_CMD_LINK_FLAGS structuredef */
+#define    MC_CMD_LINK_FLAGS_LEN 4
+/* The enums defined in this field are used as indices into the
+ * MC_CMD_LINK_FLAGS bitmask.
+ */
+#define       MC_CMD_LINK_FLAGS_MASK_OFST 0
+#define       MC_CMD_LINK_FLAGS_MASK_LEN 4
+/* enum property: bitshift */
+/* enum: Enable auto-negotiation. If AN is enabled, link technology and FEC
+ * mode are determined by advertised capabilities and requested FEC modes,
+ * combined with link partner capabilities. If AN is disabled, link technology
+ * is forced to LINK_TECHNOLOGY and FEC mode is forced to FEC_MODE. Not valid
+ * if loopback is enabled
+ */
+#define          MC_CMD_LINK_FLAGS_AUTONEG_EN 0x0
+/* enum: Enable parallel detect. In addition to AN, try to sense partner forced
+ * speed/FEC mode (when partner AN disabled). Only valid if AN is enabled.
+ */
+#define          MC_CMD_LINK_FLAGS_PARALLEL_DETECT_EN 0x1
+/* enum: Force link down, in electrical idle. */
+#define          MC_CMD_LINK_FLAGS_LINK_DISABLE 0x2
+/* enum: Ignore the sequence number and always apply. */
+#define          MC_CMD_LINK_FLAGS_IGNORE_MODULE_SEQ 0x3
+#define       MC_CMD_LINK_FLAGS_MASK_LBN 0
+#define       MC_CMD_LINK_FLAGS_MASK_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_LINK_CTRL
+ * Write the unified MAC/PHY link configuration. Locks required: None. Return
+ * code: 0, EINVAL, ETIME, EAGAIN
+ */
+#define MC_CMD_LINK_CTRL 0x6b
+#undef MC_CMD_0x6b_PRIVILEGE_CTG
+
+#define MC_CMD_0x6b_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_LINK_CTRL_IN msgrequest */
+#define    MC_CMD_LINK_CTRL_IN_LEN 40
+/* Handle to the port to set link state for. */
+#define       MC_CMD_LINK_CTRL_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_LINK_CTRL_IN_PORT_HANDLE_LEN 4
+/* Control flags */
+#define       MC_CMD_LINK_CTRL_IN_CONTROL_FLAGS_OFST 4
+#define       MC_CMD_LINK_CTRL_IN_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_FLAGS/MASK */
+/* Reserved for future expansion, and included to provide padding for alignment
+ * purposes.
+ */
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_OFST 8
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LEN 8
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LO_OFST 8
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LO_LEN 4
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LO_LBN 64
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LO_WIDTH 32
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_HI_OFST 12
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_HI_LEN 4
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_HI_LBN 96
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_HI_WIDTH 32
+/* Technology abilities to advertise during auto-negotiation */
+#define       MC_CMD_LINK_CTRL_IN_ADVERTISED_TECH_ABILITIES_MASK_OFST 16
+#define       MC_CMD_LINK_CTRL_IN_ADVERTISED_TECH_ABILITIES_MASK_LEN 16
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Pause abilities to advertise during auto-negotiation. Valid when auto-
+ * negotation is enabled and MC_CMD_SET_MAC_IN/FCTL is set to
+ * MC_CMD_FCNTL_AUTO. If auto-negotiation is disabled the driver must
+ * explicitly configure pause mode with MC_CMD_SET_MAC.
+ */
+#define       MC_CMD_LINK_CTRL_IN_ADVERTISED_PAUSE_ABILITIES_MASK_OFST 32
+#define       MC_CMD_LINK_CTRL_IN_ADVERTISED_PAUSE_ABILITIES_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+/* When auto-negotiation is enabled, this is the FEC mode to request. Note that
+ * a weaker FEC mode may get negotiated, depending on what the link partner
+ * supports. The driver should subsequently use MC_CMD_GET_LINK to check the
+ * actual negotiated FEC mode. When auto-negotiation is disabled, this is the
+ * forced FEC mode.
+ */
+#define       MC_CMD_LINK_CTRL_IN_FEC_MODE_OFST 33
+#define       MC_CMD_LINK_CTRL_IN_FEC_MODE_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* This is only to be used when auto-negotiation is disabled (forced speed or
+ * loopback mode). If the specified value does not align with the values
+ * defined in the enum MC_CMD_ETH_TECH/TECH, it is considered invalid.
+ */
+#define       MC_CMD_LINK_CTRL_IN_LINK_TECHNOLOGY_OFST 36
+#define       MC_CMD_LINK_CTRL_IN_LINK_TECHNOLOGY_LEN 2
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* The sequence number of the last MODULECHANGE event. If this doesn't match,
+ * fail with EAGAIN.
+ */
+#define       MC_CMD_LINK_CTRL_IN_MODULE_SEQ_OFST 38
+#define       MC_CMD_LINK_CTRL_IN_MODULE_SEQ_LEN 1
+/* Loopback Mode. Only valid when auto-negotiation is disabled. */
+#define       MC_CMD_LINK_CTRL_IN_LOOPBACK_OFST 39
+#define       MC_CMD_LINK_CTRL_IN_LOOPBACK_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+
+/* MC_CMD_LINK_CTRL_OUT msgresponse */
+#define    MC_CMD_LINK_CTRL_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_LINK_STATE
+ */
+#define MC_CMD_LINK_STATE 0x6c
+#undef MC_CMD_0x6c_PRIVILEGE_CTG
+
+#define MC_CMD_0x6c_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_LINK_STATE_IN msgrequest */
+#define    MC_CMD_LINK_STATE_IN_LEN 4
+/* Handle to the port to get link state for. */
+#define       MC_CMD_LINK_STATE_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_LINK_STATE_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_LINK_STATE_OUT msgresponse */
+#define    MC_CMD_LINK_STATE_OUT_LEN 114
+/* Flags used to report the current configuration/state of the link. */
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LEN 8
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LO_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LO_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LO_LBN 0
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LO_WIDTH 32
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_HI_OFST 4
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_HI_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_HI_LBN 32
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_HI_WIDTH 32
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_STATUS_FLAGS/STATUS_FLAGS */
+/* Configured technology. If the specified value does not align with the values
+ * defined in the enum MC_CMD_ETH_TECH/TECH, it is considered invalid.
+ */
+#define       MC_CMD_LINK_STATE_OUT_LINK_TECHNOLOGY_OFST 8
+#define       MC_CMD_LINK_STATE_OUT_LINK_TECHNOLOGY_LEN 2
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Configured FEC mode */
+#define       MC_CMD_LINK_STATE_OUT_FEC_MODE_OFST 10
+#define       MC_CMD_LINK_STATE_OUT_FEC_MODE_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* Bitmask of auto-negotiated pause modes */
+#define       MC_CMD_LINK_STATE_OUT_PAUSE_MASK_OFST 11
+#define       MC_CMD_LINK_STATE_OUT_PAUSE_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+/* Configured loopback mode */
+#define       MC_CMD_LINK_STATE_OUT_LOOPBACK_OFST 12
+#define       MC_CMD_LINK_STATE_OUT_LOOPBACK_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* Abilities requested by the driver to advertise during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_OFST 16
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_LEN 32
+/* See structuredef: MC_CMD_ETH_AN_FIELDS */
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_TECH_MASK_OFST 16
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_TECH_MASK_LEN 16
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_FEC_MASK_OFST 32
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_FEC_MASK_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_FEC_REQ_OFST 36
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_FEC_REQ_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_PAUSE_MASK_OFST 40
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_PAUSE_MASK_LEN 1
+/* Abilities advertised by the link partner during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_OFST 48
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_LEN 32
+/* See structuredef: MC_CMD_ETH_AN_FIELDS */
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_TECH_MASK_OFST 48
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_TECH_MASK_LEN 16
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_FEC_MASK_OFST 64
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_FEC_MASK_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_FEC_REQ_OFST 68
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_FEC_REQ_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_PAUSE_MASK_OFST 72
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_PAUSE_MASK_LEN 1
+/* Abilities supported by the local device (including cable abilities) For
+ * fixed local device capbilities see MC_CMD_GET_LOCAL_DEVICE_INFO
+ */
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_OFST 80
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_LEN 28
+/* See structuredef: MC_CMD_ETH_AN_FIELDS */
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_TECH_MASK_OFST 80
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_TECH_MASK_LEN 16
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_FEC_MASK_OFST 96
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_FEC_MASK_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_FEC_REQ_OFST 100
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_FEC_REQ_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_PAUSE_MASK_OFST 104
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_PAUSE_MASK_LEN 1
+/* Control flags */
+#define       MC_CMD_LINK_STATE_OUT_CONTROL_FLAGS_OFST 108
+#define       MC_CMD_LINK_STATE_OUT_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_FLAGS/MASK */
+/* Sequence number to synchronize link change events */
+#define       MC_CMD_LINK_STATE_OUT_PORT_LINKCHANGE_SEQ_NUM_OFST 112
+#define       MC_CMD_LINK_STATE_OUT_PORT_LINKCHANGE_SEQ_NUM_LEN 1
+/* Sequence number to synchronize module change events */
+#define       MC_CMD_LINK_STATE_OUT_PORT_MODULECHANGE_SEQ_NUM_OFST 113
+#define       MC_CMD_LINK_STATE_OUT_PORT_MODULECHANGE_SEQ_NUM_LEN 1
+
+/* MC_CMD_LINK_STATE_OUT_V2 msgresponse: Updated LINK_STATE_OUT with
+ * LOCAL_AN_SUPPORT
+ */
+#define    MC_CMD_LINK_STATE_OUT_V2_LEN 120
+/* Flags used to report the current configuration/state of the link. */
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LEN 8
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LO_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LO_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LO_LBN 0
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LO_WIDTH 32
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_HI_OFST 4
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_HI_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_HI_LBN 32
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_HI_WIDTH 32
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_STATUS_FLAGS/STATUS_FLAGS */
+/* Configured technology. If the specified value does not align with the values
+ * defined in the enum MC_CMD_ETH_TECH/TECH, it is considered invalid.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V2_LINK_TECHNOLOGY_OFST 8
+#define       MC_CMD_LINK_STATE_OUT_V2_LINK_TECHNOLOGY_LEN 2
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Configured FEC mode */
+#define       MC_CMD_LINK_STATE_OUT_V2_FEC_MODE_OFST 10
+#define       MC_CMD_LINK_STATE_OUT_V2_FEC_MODE_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* Bitmask of auto-negotiated pause modes */
+#define       MC_CMD_LINK_STATE_OUT_V2_PAUSE_MASK_OFST 11
+#define       MC_CMD_LINK_STATE_OUT_V2_PAUSE_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+/* Configured loopback mode */
+#define       MC_CMD_LINK_STATE_OUT_V2_LOOPBACK_OFST 12
+#define       MC_CMD_LINK_STATE_OUT_V2_LOOPBACK_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* Abilities requested by the driver to advertise during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_V2_ADVERTISED_ABILITIES_OFST 16
+#define       MC_CMD_LINK_STATE_OUT_V2_ADVERTISED_ABILITIES_LEN 32
+/* Abilities advertised by the link partner during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_V2_LINK_PARTNER_ABILITIES_OFST 48
+#define       MC_CMD_LINK_STATE_OUT_V2_LINK_PARTNER_ABILITIES_LEN 32
+/* Abilities supported by the local device (including cable abilities) For
+ * fixed local device capbilities see MC_CMD_GET_LOCAL_DEVICE_INFO
+ */
+#define       MC_CMD_LINK_STATE_OUT_V2_SUPPORTED_ABILITIES_OFST 80
+#define       MC_CMD_LINK_STATE_OUT_V2_SUPPORTED_ABILITIES_LEN 28
+/* Control flags */
+#define       MC_CMD_LINK_STATE_OUT_V2_CONTROL_FLAGS_OFST 108
+#define       MC_CMD_LINK_STATE_OUT_V2_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_FLAGS/MASK */
+/* Sequence number to synchronize link change events */
+#define       MC_CMD_LINK_STATE_OUT_V2_PORT_LINKCHANGE_SEQ_NUM_OFST 112
+#define       MC_CMD_LINK_STATE_OUT_V2_PORT_LINKCHANGE_SEQ_NUM_LEN 1
+/* Sequence number to synchronize module change events */
+#define       MC_CMD_LINK_STATE_OUT_V2_PORT_MODULECHANGE_SEQ_NUM_OFST 113
+#define       MC_CMD_LINK_STATE_OUT_V2_PORT_MODULECHANGE_SEQ_NUM_LEN 1
+/* Reports the auto-negotiation supported by the local device. This depends on
+ * the port and module properties.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V2_LOCAL_AN_SUPPORT_OFST 116
+#define       MC_CMD_LINK_STATE_OUT_V2_LOCAL_AN_SUPPORT_LEN 4
+/*            Enum values, see field(s): */
+/*               AN_TYPE/TYPE */
+
+/* MC_CMD_LINK_STATE_OUT_V3 msgresponse: Updated LINK_STATE_OUT_V2 for explicit
+ * reporting of the link speed and duplex mode.
+ */
+#define    MC_CMD_LINK_STATE_OUT_V3_LEN 128
+/* Flags used to report the current configuration/state of the link. */
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LEN 8
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LO_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LO_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LO_LBN 0
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LO_WIDTH 32
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_HI_OFST 4
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_HI_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_HI_LBN 32
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_HI_WIDTH 32
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_STATUS_FLAGS/STATUS_FLAGS */
+/* Configured technology. If the specified value does not align with the values
+ * defined in the enum MC_CMD_ETH_TECH/TECH, it is considered invalid.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_TECHNOLOGY_OFST 8
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_TECHNOLOGY_LEN 2
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Configured FEC mode */
+#define       MC_CMD_LINK_STATE_OUT_V3_FEC_MODE_OFST 10
+#define       MC_CMD_LINK_STATE_OUT_V3_FEC_MODE_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* Bitmask of auto-negotiated pause modes */
+#define       MC_CMD_LINK_STATE_OUT_V3_PAUSE_MASK_OFST 11
+#define       MC_CMD_LINK_STATE_OUT_V3_PAUSE_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+/* Configured loopback mode */
+#define       MC_CMD_LINK_STATE_OUT_V3_LOOPBACK_OFST 12
+#define       MC_CMD_LINK_STATE_OUT_V3_LOOPBACK_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* Abilities requested by the driver to advertise during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_V3_ADVERTISED_ABILITIES_OFST 16
+#define       MC_CMD_LINK_STATE_OUT_V3_ADVERTISED_ABILITIES_LEN 32
+/* Abilities advertised by the link partner during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_PARTNER_ABILITIES_OFST 48
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_PARTNER_ABILITIES_LEN 32
+/* Abilities supported by the local device (including cable abilities) For
+ * fixed local device capbilities see MC_CMD_GET_LOCAL_DEVICE_INFO
+ */
+#define       MC_CMD_LINK_STATE_OUT_V3_SUPPORTED_ABILITIES_OFST 80
+#define       MC_CMD_LINK_STATE_OUT_V3_SUPPORTED_ABILITIES_LEN 28
+/* Control flags */
+#define       MC_CMD_LINK_STATE_OUT_V3_CONTROL_FLAGS_OFST 108
+#define       MC_CMD_LINK_STATE_OUT_V3_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_FLAGS/MASK */
+/* Sequence number to synchronize link change events */
+#define       MC_CMD_LINK_STATE_OUT_V3_PORT_LINKCHANGE_SEQ_NUM_OFST 112
+#define       MC_CMD_LINK_STATE_OUT_V3_PORT_LINKCHANGE_SEQ_NUM_LEN 1
+/* Sequence number to synchronize module change events */
+#define       MC_CMD_LINK_STATE_OUT_V3_PORT_MODULECHANGE_SEQ_NUM_OFST 113
+#define       MC_CMD_LINK_STATE_OUT_V3_PORT_MODULECHANGE_SEQ_NUM_LEN 1
+/* Reports the auto-negotiation supported by the local device. This depends on
+ * the port and module properties.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V3_LOCAL_AN_SUPPORT_OFST 116
+#define       MC_CMD_LINK_STATE_OUT_V3_LOCAL_AN_SUPPORT_LEN 4
+/*            Enum values, see field(s): */
+/*               AN_TYPE/TYPE */
+/* Autonegotiated speed in mbit/s. The link may still be down even if this
+ * reads non-zero. LINK_SPEED field is intended to be used by drivers without
+ * the most up-to-date MCDI definitions, unable to deduce the link speed from
+ * the reported LINK_TECHNOLOGY field.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_SPEED_OFST 120
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_SPEED_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V3_FLAGS_OFST 124
+#define       MC_CMD_LINK_STATE_OUT_V3_FLAGS_LEN 4
+#define        MC_CMD_LINK_STATE_OUT_V3_FULL_DUPLEX_OFST 124
+#define        MC_CMD_LINK_STATE_OUT_V3_FULL_DUPLEX_LBN 0
+#define        MC_CMD_LINK_STATE_OUT_V3_FULL_DUPLEX_WIDTH 1
+
 
 /***********************************/
 /* MC_CMD_GET_LINK
@@ -5694,6 +6064,54 @@
 /* MC_CMD_GET_LINK_IN msgrequest */
 #define    MC_CMD_GET_LINK_IN_LEN 0
 
+/* MC_CMD_GET_LINK_IN_V2 msgrequest */
+#define    MC_CMD_GET_LINK_IN_V2_LEN 8
+/* Target port to request link state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details.
+ */
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LO_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LO_LBN 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_HI_OFST 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_HI_LBN 32
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 3
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 20
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 16
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 2
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LINK_END_OFST 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LO_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LO_LBN 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_HI_OFST 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_HI_LBN 32
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_LINK_OUT msgresponse */
 #define    MC_CMD_GET_LINK_OUT_LEN 28
 /* Near-side advertised capabilities. Refer to
@@ -5745,6 +6163,7 @@
 /* This returns the negotiated flow control value. */
 #define       MC_CMD_GET_LINK_OUT_FCNTL_OFST 20
 #define       MC_CMD_GET_LINK_OUT_FCNTL_LEN 4
+/* enum property: value */
 /*            Enum values, see field(s): */
 /*               MC_CMD_SET_MAC/MC_CMD_SET_MAC_IN/FCNTL */
 #define       MC_CMD_GET_LINK_OUT_MAC_FAULT_OFST 24
@@ -5813,6 +6232,7 @@
 /* This returns the negotiated flow control value. */
 #define       MC_CMD_GET_LINK_OUT_V2_FCNTL_OFST 20
 #define       MC_CMD_GET_LINK_OUT_V2_FCNTL_LEN 4
+/* enum property: value */
 /*            Enum values, see field(s): */
 /*               MC_CMD_SET_MAC/MC_CMD_SET_MAC_IN/FCNTL */
 #define       MC_CMD_GET_LINK_OUT_V2_MAC_FAULT_OFST 24
@@ -5969,6 +6389,95 @@
 #define        MC_CMD_SET_LINK_IN_V2_MODULE_SEQ_IGNORE_LBN 7
 #define        MC_CMD_SET_LINK_IN_V2_MODULE_SEQ_IGNORE_WIDTH 1
 
+/* MC_CMD_SET_LINK_IN_V3 msgrequest */
+#define    MC_CMD_SET_LINK_IN_V3_LEN 28
+/* Near-side advertised capabilities. Refer to
+ * MC_CMD_GET_PHY_CFG_OUT/SUPPORTED_CAP for bit definitions.
+ */
+#define       MC_CMD_SET_LINK_IN_V3_CAP_OFST 0
+#define       MC_CMD_SET_LINK_IN_V3_CAP_LEN 4
+/* Flags */
+#define       MC_CMD_SET_LINK_IN_V3_FLAGS_OFST 4
+#define       MC_CMD_SET_LINK_IN_V3_FLAGS_LEN 4
+#define        MC_CMD_SET_LINK_IN_V3_LOWPOWER_OFST 4
+#define        MC_CMD_SET_LINK_IN_V3_LOWPOWER_LBN 0
+#define        MC_CMD_SET_LINK_IN_V3_LOWPOWER_WIDTH 1
+#define        MC_CMD_SET_LINK_IN_V3_POWEROFF_OFST 4
+#define        MC_CMD_SET_LINK_IN_V3_POWEROFF_LBN 1
+#define        MC_CMD_SET_LINK_IN_V3_POWEROFF_WIDTH 1
+#define        MC_CMD_SET_LINK_IN_V3_TXDIS_OFST 4
+#define        MC_CMD_SET_LINK_IN_V3_TXDIS_LBN 2
+#define        MC_CMD_SET_LINK_IN_V3_TXDIS_WIDTH 1
+#define        MC_CMD_SET_LINK_IN_V3_LINKDOWN_OFST 4
+#define        MC_CMD_SET_LINK_IN_V3_LINKDOWN_LBN 3
+#define        MC_CMD_SET_LINK_IN_V3_LINKDOWN_WIDTH 1
+/* Loopback mode. */
+#define       MC_CMD_SET_LINK_IN_V3_LOOPBACK_MODE_OFST 8
+#define       MC_CMD_SET_LINK_IN_V3_LOOPBACK_MODE_LEN 4
+/*            Enum values, see field(s): */
+/*               MC_CMD_GET_LOOPBACK_MODES/MC_CMD_GET_LOOPBACK_MODES_OUT/100M */
+/* A loopback speed of "0" is supported, and means (choose any available
+ * speed).
+ */
+#define       MC_CMD_SET_LINK_IN_V3_LOOPBACK_SPEED_OFST 12
+#define       MC_CMD_SET_LINK_IN_V3_LOOPBACK_SPEED_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_OFST 16
+#define       MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_LEN 1
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_NUMBER_OFST 16
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_NUMBER_LBN 0
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_NUMBER_WIDTH 7
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_IGNORE_OFST 16
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_IGNORE_LBN 7
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_IGNORE_WIDTH 1
+/* Padding */
+#define       MC_CMD_SET_LINK_IN_V3_RESERVED_OFST 17
+#define       MC_CMD_SET_LINK_IN_V3_RESERVED_LEN 3
+/* Target port to set link state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
+ */
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LEN 8
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LO_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LO_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LO_LBN 160
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LO_WIDTH 32
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_HI_OFST 24
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_HI_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_HI_LBN 192
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FLAT_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_TYPE_OFST 23
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 160
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 180
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 176
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 22
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LINK_END_OFST 24
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LINK_END_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LEN 8
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LO_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LO_LBN 160
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_HI_OFST 24
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_HI_LBN 192
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_SET_LINK_OUT msgresponse */
 #define    MC_CMD_SET_LINK_OUT_LEN 0
 
@@ -6034,17 +6543,17 @@
 #define       MC_CMD_SET_MAC_IN_FCNTL_OFST 20
 #define       MC_CMD_SET_MAC_IN_FCNTL_LEN 4
 /* enum: Flow control is off. */
-#define          MC_CMD_FCNTL_OFF 0x0
+/*               MC_CMD_FCNTL_OFF 0x0 */
 /* enum: Respond to flow control. */
-#define          MC_CMD_FCNTL_RESPOND 0x1
+/*               MC_CMD_FCNTL_RESPOND 0x1 */
 /* enum: Respond to and Issue flow control. */
-#define          MC_CMD_FCNTL_BIDIR 0x2
-/* enum: Auto neg flow control. */
-#define          MC_CMD_FCNTL_AUTO 0x3
-/* enum: Priority flow control (eftest builds only). */
-#define          MC_CMD_FCNTL_QBB 0x4
+/*               MC_CMD_FCNTL_BIDIR 0x2 */
+/* enum: Auto negotiate flow control. */
+/*               MC_CMD_FCNTL_AUTO 0x3 */
+/* enum: Priority flow control. This is only supported on KSB. */
+/*               MC_CMD_FCNTL_QBB 0x4 */
 /* enum: Issue flow control. */
-#define          MC_CMD_FCNTL_GENERATE 0x5
+/*               MC_CMD_FCNTL_GENERATE 0x5 */
 #define       MC_CMD_SET_MAC_IN_FLAGS_OFST 24
 #define       MC_CMD_SET_MAC_IN_FLAGS_LEN 4
 #define        MC_CMD_SET_MAC_IN_FLAG_INCLUDE_FCS_OFST 24
@@ -6086,9 +6595,9 @@
 /*               MC_CMD_FCNTL_RESPOND 0x1 */
 /* enum: Respond to and Issue flow control. */
 /*               MC_CMD_FCNTL_BIDIR 0x2 */
-/* enum: Auto neg flow control. */
+/* enum: Auto negotiate flow control. */
 /*               MC_CMD_FCNTL_AUTO 0x3 */
-/* enum: Priority flow control (eftest builds only). */
+/* enum: Priority flow control. This is only supported on KSB. */
 /*               MC_CMD_FCNTL_QBB 0x4 */
 /* enum: Issue flow control. */
 /*               MC_CMD_FCNTL_GENERATE 0x5 */
@@ -6155,9 +6664,9 @@
 /*               MC_CMD_FCNTL_RESPOND 0x1 */
 /* enum: Respond to and Issue flow control. */
 /*               MC_CMD_FCNTL_BIDIR 0x2 */
-/* enum: Auto neg flow control. */
+/* enum: Auto negotiate flow control. */
 /*               MC_CMD_FCNTL_AUTO 0x3 */
-/* enum: Priority flow control (eftest builds only). */
+/* enum: Priority flow control. This is only supported on KSB. */
 /*               MC_CMD_FCNTL_QBB 0x4 */
 /* enum: Issue flow control. */
 /*               MC_CMD_FCNTL_GENERATE 0x5 */
@@ -6188,19 +6697,9 @@
 #define        MC_CMD_SET_MAC_V3_IN_CFG_FCS_OFST 28
 #define        MC_CMD_SET_MAC_V3_IN_CFG_FCS_LBN 4
 #define        MC_CMD_SET_MAC_V3_IN_CFG_FCS_WIDTH 1
-/* Identifies the MAC to update by the specifying the end of a logical MAE
- * link. Setting TARGET to MAE_LINK_ENDPOINT_COMPAT is equivalent to using the
- * previous version of the command (MC_CMD_SET_MAC_EXT). Not all possible
- * combinations of MPORT_END and MPORT_SELECTOR in TARGET will work in all
- * circumstances. 1. Some will always work (e.g. a VF can always address its
- * logical MAC using MPORT_SELECTOR=ASSIGNED,LINK_END=VNIC), 2. Some are not
- * meaningful and will always fail with EINVAL (e.g. attempting to address the
- * VNIC end of a link to a physical port), 3. Some are meaningful but require
- * the MCDI client to have the required permission and fail with EPERM
- * otherwise (e.g. trying to set the MAC on a VF the caller cannot administer),
- * and 4. Some could be implementation-specific and fail with ENOTSUP if not
- * available (no examples exist right now). See SF-123581-TC section 4.3 for
- * more details.
+/* Target port to set mac state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
  */
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_OFST 32
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_LEN 8
@@ -6212,6 +6711,7 @@
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_HI_LEN 4
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_HI_LBN 288
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_MPORT_SELECTOR_OFST 32
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_MPORT_SELECTOR_LEN 4
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_MPORT_SELECTOR_FLAT_OFST 32
@@ -6405,6 +6905,98 @@
 #define       MC_CMD_MAC_STATS_IN_PORT_ID_OFST 16
 #define       MC_CMD_MAC_STATS_IN_PORT_ID_LEN 4
 
+/* MC_CMD_MAC_STATS_V2_IN msgrequest */
+#define    MC_CMD_MAC_STATS_V2_IN_LEN 28
+/* ??? */
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_OFST 0
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LEN 8
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LO_OFST 0
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LO_LBN 0
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_HI_OFST 4
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_HI_LBN 32
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_HI_WIDTH 32
+#define       MC_CMD_MAC_STATS_V2_IN_CMD_OFST 8
+#define       MC_CMD_MAC_STATS_V2_IN_CMD_LEN 4
+#define        MC_CMD_MAC_STATS_V2_IN_DMA_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_DMA_LBN 0
+#define        MC_CMD_MAC_STATS_V2_IN_DMA_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_CLEAR_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_CLEAR_LBN 1
+#define        MC_CMD_MAC_STATS_V2_IN_CLEAR_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CHANGE_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CHANGE_LBN 2
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CHANGE_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_ENABLE_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_ENABLE_LBN 3
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_ENABLE_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CLEAR_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CLEAR_LBN 4
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CLEAR_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_NOEVENT_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_NOEVENT_LBN 5
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_NOEVENT_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIOD_MS_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIOD_MS_LBN 16
+#define        MC_CMD_MAC_STATS_V2_IN_PERIOD_MS_WIDTH 16
+/* DMA length. Should be set to MAC_STATS_NUM_STATS * sizeof(uint64_t), as
+ * returned by MC_CMD_GET_CAPABILITIES_V4_OUT. For legacy firmware not
+ * supporting MC_CMD_GET_CAPABILITIES_V4_OUT, DMA_LEN should be set to
+ * MC_CMD_MAC_NSTATS * sizeof(uint64_t)
+ */
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_LEN_OFST 12
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_LEN_LEN 4
+/* port id so vadapter stats can be provided */
+#define       MC_CMD_MAC_STATS_V2_IN_PORT_ID_OFST 16
+#define       MC_CMD_MAC_STATS_V2_IN_PORT_ID_LEN 4
+/* Target port to request statistics for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
+ */
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LEN 8
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LO_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LO_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LO_LBN 160
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LO_WIDTH 32
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_HI_OFST 24
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_HI_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_HI_LBN 192
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FLAT_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_TYPE_OFST 23
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 160
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 180
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 176
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 22
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LINK_END_OFST 24
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LINK_END_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LEN 8
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LO_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LO_LBN 160
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_HI_OFST 24
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_HI_LBN 192
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_MAC_STATS_OUT_DMA msgresponse */
 #define    MC_CMD_MAC_STATS_OUT_DMA_LEN 0
 
@@ -6421,6 +7013,7 @@
 #define       MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_HI_LBN 32
 #define       MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
 #define       MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS
+/* enum property: index */
 #define          MC_CMD_MAC_GENERATION_START 0x0 /* enum */
 #define          MC_CMD_MAC_DMABUF_START 0x1 /* enum */
 #define          MC_CMD_MAC_TX_PKTS 0x1 /* enum */
@@ -6583,6 +7176,7 @@
 #define       MC_CMD_MAC_STATS_V2_OUT_NO_DMA_STATISTICS_HI_LBN 32
 #define       MC_CMD_MAC_STATS_V2_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
 #define       MC_CMD_MAC_STATS_V2_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS_V2
+/* enum property: index */
 /* enum: Start of FEC stats buffer space, Medford2 and up */
 #define          MC_CMD_MAC_FEC_DMABUF_START 0x61
 /* enum: Number of uncorrected FEC codewords on link (RS-FEC only for Medford2)
@@ -6622,6 +7216,7 @@
 #define       MC_CMD_MAC_STATS_V3_OUT_NO_DMA_STATISTICS_HI_LBN 32
 #define       MC_CMD_MAC_STATS_V3_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
 #define       MC_CMD_MAC_STATS_V3_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS_V3
+/* enum property: index */
 /* enum: Start of CTPIO stats buffer space, Medford2 and up */
 #define          MC_CMD_MAC_CTPIO_DMABUF_START 0x68
 /* enum: Number of CTPIO fallbacks because a DMA packet was in progress on the
@@ -6702,6 +7297,7 @@
 #define       MC_CMD_MAC_STATS_V4_OUT_NO_DMA_STATISTICS_HI_LBN 32
 #define       MC_CMD_MAC_STATS_V4_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
 #define       MC_CMD_MAC_STATS_V4_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS_V4
+/* enum property: index */
 /* enum: Start of V4 stats buffer space */
 #define          MC_CMD_MAC_V4_DMABUF_START 0x79
 /* enum: RXDP counter: Number of packets truncated because scattering was
@@ -6723,112 +7319,35 @@
 /*            Other enum values, see field(s): */
 /*               MC_CMD_MAC_STATS_V3_OUT_NO_DMA/STATISTICS */
 
-
-/***********************************/
-/* MC_CMD_SRIOV
- * to be documented
- */
-#define MC_CMD_SRIOV 0x30
-
-/* MC_CMD_SRIOV_IN msgrequest */
-#define    MC_CMD_SRIOV_IN_LEN 12
-#define       MC_CMD_SRIOV_IN_ENABLE_OFST 0
-#define       MC_CMD_SRIOV_IN_ENABLE_LEN 4
-#define       MC_CMD_SRIOV_IN_VI_BASE_OFST 4
-#define       MC_CMD_SRIOV_IN_VI_BASE_LEN 4
-#define       MC_CMD_SRIOV_IN_VF_COUNT_OFST 8
-#define       MC_CMD_SRIOV_IN_VF_COUNT_LEN 4
-
-/* MC_CMD_SRIOV_OUT msgresponse */
-#define    MC_CMD_SRIOV_OUT_LEN 8
-#define       MC_CMD_SRIOV_OUT_VI_SCALE_OFST 0
-#define       MC_CMD_SRIOV_OUT_VI_SCALE_LEN 4
-#define       MC_CMD_SRIOV_OUT_VF_TOTAL_OFST 4
-#define       MC_CMD_SRIOV_OUT_VF_TOTAL_LEN 4
-
-/* MC_CMD_MEMCPY_RECORD_TYPEDEF structuredef */
-#define    MC_CMD_MEMCPY_RECORD_TYPEDEF_LEN 32
-/* this is only used for the first record */
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_OFST 0
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_LBN 0
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_OFST 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_LBN 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_OFST 8
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LEN 8
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_OFST 8
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_LBN 64
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_OFST 12
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_LBN 96
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LBN 64
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_WIDTH 64
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_OFST 16
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_LEN 4
-#define          MC_CMD_MEMCPY_RECORD_TYPEDEF_RID_INLINE 0x100 /* enum */
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_LBN 128
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_OFST 20
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LEN 8
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_OFST 20
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_LBN 160
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_OFST 24
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_LBN 192
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LBN 160
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_WIDTH 64
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_OFST 28
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_LBN 224
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_MEMCPY
- * DMA write data into (Rid,Addr), either by dma reading (Rid,Addr), or by data
- * embedded directly in the command.
- *
- * A common pattern is for a client to use generation counts to signal a dma
- * update of a datastructure. To facilitate this, this MCDI operation can
- * contain multiple requests which are executed in strict order. Requests take
- * the form of duplicating the entire MCDI request continuously (including the
- * requests record, which is ignored in all but the first structure)
- *
- * The source data can either come from a DMA from the host, or it can be
- * embedded within the request directly, thereby eliminating a DMA read. To
- * indicate this, the client sets FROM_RID=%RID_INLINE, ADDR_HI=0, and
- * ADDR_LO=offset, and inserts the data at %offset from the start of the
- * payload. It's the callers responsibility to ensure that the embedded data
- * doesn't overlap the records.
- *
- * Returns: 0, EINVAL (invalid RID)
- */
-#define MC_CMD_MEMCPY 0x31
-
-/* MC_CMD_MEMCPY_IN msgrequest */
-#define    MC_CMD_MEMCPY_IN_LENMIN 32
-#define    MC_CMD_MEMCPY_IN_LENMAX 224
-#define    MC_CMD_MEMCPY_IN_LENMAX_MCDI2 992
-#define    MC_CMD_MEMCPY_IN_LEN(num) (0+32*(num))
-#define    MC_CMD_MEMCPY_IN_RECORD_NUM(len) (((len)-0)/32)
-/* see MC_CMD_MEMCPY_RECORD_TYPEDEF */
-#define       MC_CMD_MEMCPY_IN_RECORD_OFST 0
-#define       MC_CMD_MEMCPY_IN_RECORD_LEN 32
-#define       MC_CMD_MEMCPY_IN_RECORD_MINNUM 1
-#define       MC_CMD_MEMCPY_IN_RECORD_MAXNUM 7
-#define       MC_CMD_MEMCPY_IN_RECORD_MAXNUM_MCDI2 31
-
-/* MC_CMD_MEMCPY_OUT msgresponse */
-#define    MC_CMD_MEMCPY_OUT_LEN 0
+/* MC_CMD_MAC_STATS_V5_OUT_DMA msgresponse */
+#define    MC_CMD_MAC_STATS_V5_OUT_DMA_LEN 0
+
+/* MC_CMD_MAC_STATS_V5_OUT_NO_DMA msgresponse */
+#define    MC_CMD_MAC_STATS_V5_OUT_NO_DMA_LEN (((MC_CMD_MAC_NSTATS_V5*64))>>3)
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_OFST 0
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LEN 8
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LO_OFST 0
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LO_LEN 4
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LO_LBN 0
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LO_WIDTH 32
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_HI_OFST 4
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_HI_LEN 4
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_HI_LBN 32
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS_V5
+/* enum property: index */
+/* enum: Start of V5 stats buffer space */
+#define          MC_CMD_MAC_V5_DMABUF_START 0x7c
+/* enum: Link toggle counter: Number of times the link has toggled between
+ * up/down and down/up
+ */
+#define          MC_CMD_MAC_LINK_TOGGLES 0x7c
+/* enum: This includes the space at offset 125 which is the final
+ * GENERATION_END in a MAC_STATS_V5 response and otherwise unused.
+ */
+#define          MC_CMD_MAC_NSTATS_V5 0x7e
+/*            Other enum values, see field(s): */
+/*               MC_CMD_MAC_STATS_V4_OUT_NO_DMA/STATISTICS */
 
 
 /***********************************/
@@ -6984,6 +7503,7 @@
 #define    MC_CMD_WOL_FILTER_RESET_IN_LEN 4
 #define       MC_CMD_WOL_FILTER_RESET_IN_MASK_OFST 0
 #define       MC_CMD_WOL_FILTER_RESET_IN_MASK_LEN 4
+/* enum property: bitmask */
 #define          MC_CMD_WOL_FILTER_RESET_IN_WAKE_FILTERS 0x1 /* enum */
 #define          MC_CMD_WOL_FILTER_RESET_IN_LIGHTSOUT_OFFLOADS 0x2 /* enum */
 
@@ -6992,23 +7512,6 @@
 
 
 /***********************************/
-/* MC_CMD_SET_MCAST_HASH
- * Set the MCAST hash value without otherwise reconfiguring the MAC
- */
-#define MC_CMD_SET_MCAST_HASH 0x35
-
-/* MC_CMD_SET_MCAST_HASH_IN msgrequest */
-#define    MC_CMD_SET_MCAST_HASH_IN_LEN 32
-#define       MC_CMD_SET_MCAST_HASH_IN_HASH0_OFST 0
-#define       MC_CMD_SET_MCAST_HASH_IN_HASH0_LEN 16
-#define       MC_CMD_SET_MCAST_HASH_IN_HASH1_OFST 16
-#define       MC_CMD_SET_MCAST_HASH_IN_HASH1_LEN 16
-
-/* MC_CMD_SET_MCAST_HASH_OUT msgresponse */
-#define    MC_CMD_SET_MCAST_HASH_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_NVRAM_TYPES
  * Return bitfield indicating available types of virtual NVRAM partitions.
  * Locks required: none. Returns: 0
@@ -7026,6 +7529,7 @@
 /* Bit mask of supported types. */
 #define       MC_CMD_NVRAM_TYPES_OUT_TYPES_OFST 0
 #define       MC_CMD_NVRAM_TYPES_OUT_TYPES_LEN 4
+/* enum property: bitshift */
 /* enum: Disabled callisto. */
 #define          MC_CMD_NVRAM_TYPE_DISABLED_CALLISTO 0x0
 /* enum: MC firmware. */
@@ -7152,6 +7656,12 @@
 #define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_OFST 12
 #define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_LBN 7
 #define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_WIDTH 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_WRITE_ONLY_OFST 12
+#define        MC_CMD_NVRAM_INFO_V2_OUT_WRITE_ONLY_LBN 8
+#define        MC_CMD_NVRAM_INFO_V2_OUT_WRITE_ONLY_WIDTH 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_SEQUENTIAL_WRITE_OFST 12
+#define        MC_CMD_NVRAM_INFO_V2_OUT_SEQUENTIAL_WRITE_LBN 9
+#define        MC_CMD_NVRAM_INFO_V2_OUT_SEQUENTIAL_WRITE_WIDTH 1
 #define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSDEV_OFST 16
 #define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSDEV_LEN 4
 #define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSADDR_OFST 20
@@ -7499,6 +8009,128 @@
 #define          MC_CMD_NVRAM_VERIFY_RC_BUNDLE_COMPONENT_COPY_FAILED 0x19
 /* enum: The update operation is in-progress. */
 #define          MC_CMD_NVRAM_VERIFY_RC_PENDING 0x1a
+/* enum: The update was an invalid user configuration file. */
+#define          MC_CMD_NVRAM_VERIFY_RC_BAD_CONFIG 0x1b
+/* enum: The write was to the AUTO partition but the data was not recognised as
+ * a valid partition.
+ */
+#define          MC_CMD_NVRAM_VERIFY_RC_UNKNOWN_TYPE 0x1c
+
+/* MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT msgresponse */
+#define    MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_LEN 88
+/* Result of nvram update completion processing. Result codes that indicate an
+ * internal build failure and therefore not expected to be seen by customers in
+ * the field are marked with a prefix 'Internal-error'.
+ */
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_RESULT_CODE_OFST 0
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_RESULT_CODE_LEN 4
+/* enum: Invalid return code; only non-zero values are defined. Defined as
+ * unknown for backwards compatibility with NVRAM_UPDATE_FINISH_OUT.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_UNKNOWN 0x0 */
+/* enum: Verify succeeded without any errors. */
+/*               MC_CMD_NVRAM_VERIFY_RC_SUCCESS 0x1 */
+/* enum: CMS format verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_CMS_CHECK_FAILED 0x2 */
+/* enum: Invalid CMS format in image metadata. */
+/*               MC_CMD_NVRAM_VERIFY_RC_INVALID_CMS_FORMAT 0x3 */
+/* enum: Message digest verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_MESSAGE_DIGEST_CHECK_FAILED 0x4 */
+/* enum: Error in message digest calculated over the reflash-header, payload
+ * and reflash-trailer.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BAD_MESSAGE_DIGEST 0x5 */
+/* enum: Signature verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHECK_FAILED 0x6 */
+/* enum: There are no valid signatures in the image. */
+/*               MC_CMD_NVRAM_VERIFY_RC_NO_VALID_SIGNATURES 0x7 */
+/* enum: Trusted approvers verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_TRUSTED_APPROVERS_CHECK_FAILED 0x8 */
+/* enum: The Trusted approver's list is empty. */
+/*               MC_CMD_NVRAM_VERIFY_RC_NO_TRUSTED_APPROVERS 0x9 */
+/* enum: Signature chain verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHAIN_CHECK_FAILED 0xa */
+/* enum: The signers of the signatures in the image are not listed in the
+ * Trusted approver's list.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_NO_SIGNATURE_MATCH 0xb */
+/* enum: The image contains a test-signed certificate, but the adapter accepts
+ * only production signed images.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_REJECT_TEST_SIGNED 0xc */
+/* enum: The image has a lower security level than the current firmware. */
+/*               MC_CMD_NVRAM_VERIFY_RC_SECURITY_LEVEL_DOWNGRADE 0xd */
+/* enum: Internal-error. The signed image is missing the 'contents' section,
+ * where the 'contents' section holds the actual image payload to be applied.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_CONTENT_NOT_FOUND 0xe */
+/* enum: Internal-error. The bundle header is invalid. */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_CONTENT_HEADER_INVALID 0xf */
+/* enum: Internal-error. The bundle does not have a valid reflash image layout.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_REFLASH_IMAGE_INVALID 0x10 */
+/* enum: Internal-error. The bundle has an inconsistent layout of components or
+ * incorrect checksum.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_IMAGE_LAYOUT_INVALID 0x11 */
+/* enum: Internal-error. The bundle manifest is inconsistent with components in
+ * the bundle.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_INVALID 0x12 */
+/* enum: Internal-error. The number of components in a bundle do not match the
+ * number of components advertised by the bundle manifest.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_NUM_COMPONENTS_MISMATCH 0x13 */
+/* enum: Internal-error. The bundle contains too many components for the MC
+ * firmware to process
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_TOO_MANY_COMPONENTS 0x14 */
+/* enum: Internal-error. The bundle manifest has an invalid/inconsistent
+ * component.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_COMPONENT_INVALID 0x15 */
+/* enum: Internal-error. The hash of a component does not match the hash stored
+ * in the bundle manifest.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_COMPONENT_HASH_MISMATCH 0x16 */
+/* enum: Internal-error. Component hash calculation failed. */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_COMPONENT_HASH_FAILED 0x17 */
+/* enum: Internal-error. The component does not have a valid reflash image
+ * layout.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_COMPONENT_REFLASH_IMAGE_INVALID 0x18 */
+/* enum: The bundle processing code failed to copy a component to its target
+ * partition.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_COMPONENT_COPY_FAILED 0x19 */
+/* enum: The update operation is in-progress. */
+/*               MC_CMD_NVRAM_VERIFY_RC_PENDING 0x1a */
+/* enum: The update was an invalid user configuration file. */
+/*               MC_CMD_NVRAM_VERIFY_RC_BAD_CONFIG 0x1b */
+/* enum: The write was to the AUTO partition but the data was not recognised as
+ * a valid partition.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_UNKNOWN_TYPE 0x1c */
+/* If the update was a user configuration, what action(s) the user must take to
+ * apply the new configuration.
+ */
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_ACTIONS_REQUIRED_OFST 4
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_ACTIONS_REQUIRED_LEN 4
+/* enum: No action required. */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_NONE 0x0
+/* enum: The MC firmware must be rebooted (eg with MC_CMD_REBOOT). */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_FIRMWARE_REBOOT 0x1
+/* enum: The host must be rebooted. */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_HOST_REBOOT 0x2
+/* enum: The firmware and host must be rebooted (in either order). */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_FIRMWARE_AND_HOST_REBOOT 0x3
+/* enum: The host must be fully powered off. */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_HOST_POWERCYCLE 0x4
+/* If the update failed with MC_CMD_NVRAM_VERIFY_RC_BAD_CONFIG, a null-
+ * terminated US-ASCII string suitable for showing to the user.
+ */
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_ERROR_STRING_OFST 8
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_ERROR_STRING_LEN 80
 
 
 /***********************************/
@@ -7522,7 +8154,7 @@
 #define MC_CMD_REBOOT 0x3d
 #undef MC_CMD_0x3d_PRIVILEGE_CTG
 
-#define MC_CMD_0x3d_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0x3d_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_REBOOT_IN msgrequest */
 #define    MC_CMD_REBOOT_IN_LEN 4
@@ -7535,65 +8167,6 @@
 
 
 /***********************************/
-/* MC_CMD_SCHEDINFO
- * Request scheduler info. Locks required: NONE. Returns: An array of
- * (timeslice,maximum overrun), one for each thread, in ascending order of
- * thread address.
- */
-#define MC_CMD_SCHEDINFO 0x3e
-#undef MC_CMD_0x3e_PRIVILEGE_CTG
-
-#define MC_CMD_0x3e_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SCHEDINFO_IN msgrequest */
-#define    MC_CMD_SCHEDINFO_IN_LEN 0
-
-/* MC_CMD_SCHEDINFO_OUT msgresponse */
-#define    MC_CMD_SCHEDINFO_OUT_LENMIN 4
-#define    MC_CMD_SCHEDINFO_OUT_LENMAX 252
-#define    MC_CMD_SCHEDINFO_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_SCHEDINFO_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_SCHEDINFO_OUT_DATA_NUM(len) (((len)-0)/4)
-#define       MC_CMD_SCHEDINFO_OUT_DATA_OFST 0
-#define       MC_CMD_SCHEDINFO_OUT_DATA_LEN 4
-#define       MC_CMD_SCHEDINFO_OUT_DATA_MINNUM 1
-#define       MC_CMD_SCHEDINFO_OUT_DATA_MAXNUM 63
-#define       MC_CMD_SCHEDINFO_OUT_DATA_MAXNUM_MCDI2 255
-
-
-/***********************************/
-/* MC_CMD_REBOOT_MODE
- * Set the mode for the next MC reboot. Locks required: NONE. Sets the reboot
- * mode to the specified value. Returns the old mode.
- */
-#define MC_CMD_REBOOT_MODE 0x3f
-#undef MC_CMD_0x3f_PRIVILEGE_CTG
-
-#define MC_CMD_0x3f_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_REBOOT_MODE_IN msgrequest */
-#define    MC_CMD_REBOOT_MODE_IN_LEN 4
-#define       MC_CMD_REBOOT_MODE_IN_VALUE_OFST 0
-#define       MC_CMD_REBOOT_MODE_IN_VALUE_LEN 4
-/* enum: Normal. */
-#define          MC_CMD_REBOOT_MODE_NORMAL 0x0
-/* enum: Power-on Reset. */
-#define          MC_CMD_REBOOT_MODE_POR 0x2
-/* enum: Snapper. */
-#define          MC_CMD_REBOOT_MODE_SNAPPER 0x3
-/* enum: snapper fake POR */
-#define          MC_CMD_REBOOT_MODE_SNAPPER_POR 0x4
-#define        MC_CMD_REBOOT_MODE_IN_FAKE_OFST 0
-#define        MC_CMD_REBOOT_MODE_IN_FAKE_LBN 7
-#define        MC_CMD_REBOOT_MODE_IN_FAKE_WIDTH 1
-
-/* MC_CMD_REBOOT_MODE_OUT msgresponse */
-#define    MC_CMD_REBOOT_MODE_OUT_LEN 4
-#define       MC_CMD_REBOOT_MODE_OUT_VALUE_OFST 0
-#define       MC_CMD_REBOOT_MODE_OUT_VALUE_LEN 4
-
-
-/***********************************/
 /* MC_CMD_SENSOR_INFO
  * Returns information about every available sensor.
  *
@@ -8061,6 +8634,54 @@
 /* MC_CMD_GET_PHY_STATE_IN msgrequest */
 #define    MC_CMD_GET_PHY_STATE_IN_LEN 0
 
+/* MC_CMD_GET_PHY_STATE_IN_V2 msgrequest */
+#define    MC_CMD_GET_PHY_STATE_IN_V2_LEN 8
+/* Target port to request PHY state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details.
+ */
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LO_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LO_LBN 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_HI_OFST 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_HI_LBN 32
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 3
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 20
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 16
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 2
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LINK_END_OFST 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LO_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LO_LBN 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_HI_OFST 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_HI_LBN 32
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_PHY_STATE_OUT msgresponse */
 #define    MC_CMD_GET_PHY_STATE_OUT_LEN 4
 #define       MC_CMD_GET_PHY_STATE_OUT_STATE_OFST 0
@@ -8072,22 +8693,6 @@
 
 
 /***********************************/
-/* MC_CMD_SETUP_8021QBB
- * 802.1Qbb control. 8 Tx queues that map to priorities 0 - 7. Use all 1s to
- * disable 802.Qbb for a given priority.
- */
-#define MC_CMD_SETUP_8021QBB 0x44
-
-/* MC_CMD_SETUP_8021QBB_IN msgrequest */
-#define    MC_CMD_SETUP_8021QBB_IN_LEN 32
-#define       MC_CMD_SETUP_8021QBB_IN_TXQS_OFST 0
-#define       MC_CMD_SETUP_8021QBB_IN_TXQS_LEN 32
-
-/* MC_CMD_SETUP_8021QBB_OUT msgresponse */
-#define    MC_CMD_SETUP_8021QBB_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_WOL_FILTER_GET
  * Retrieve ID of any WoL filters. Locks required: None. Returns: 0, ENOSYS
  */
@@ -8106,133 +8711,6 @@
 
 
 /***********************************/
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD
- * Add a protocol offload to NIC for lights-out state. Locks required: None.
- * Returns: 0, ENOSYS
- */
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD 0x46
-#undef MC_CMD_0x46_PRIVILEGE_CTG
-
-#define MC_CMD_0x46_PRIVILEGE_CTG SRIOV_CTG_LINK
-
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN msgrequest */
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMIN 8
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMAX 252
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LEN(num) (4+4*(num))
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_NUM(len) (((len)-4)/4)
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_LEN 4
-#define          MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_ARP 0x1 /* enum */
-#define          MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_NS 0x2 /* enum */
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_OFST 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_LEN 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_MINNUM 1
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_MAXNUM 62
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_MAXNUM_MCDI2 254
-
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP msgrequest */
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_LEN 14
-/*            MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0 */
-/*            MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_LEN 4 */
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_MAC_OFST 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_MAC_LEN 6
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_IP_OFST 10
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_IP_LEN 4
-
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS msgrequest */
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_LEN 42
-/*            MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0 */
-/*            MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_LEN 4 */
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_MAC_OFST 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_MAC_LEN 6
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_SNIPV6_OFST 10
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_SNIPV6_LEN 16
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_IPV6_OFST 26
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_IPV6_LEN 16
-
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT msgresponse */
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_LEN 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_FILTER_ID_OFST 0
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_FILTER_ID_LEN 4
-
-
-/***********************************/
-/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD
- * Remove a protocol offload from NIC for lights-out state. Locks required:
- * None. Returns: 0, ENOSYS
- */
-#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD 0x47
-#undef MC_CMD_0x47_PRIVILEGE_CTG
-
-#define MC_CMD_0x47_PRIVILEGE_CTG SRIOV_CTG_LINK
-
-/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN msgrequest */
-#define    MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_LEN 8
-#define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
-#define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_LEN 4
-#define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_FILTER_ID_OFST 4
-#define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_FILTER_ID_LEN 4
-
-/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_OUT msgresponse */
-#define    MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_MAC_RESET_RESTORE
- * Restore MAC after block reset. Locks required: None. Returns: 0.
- */
-#define MC_CMD_MAC_RESET_RESTORE 0x48
-
-/* MC_CMD_MAC_RESET_RESTORE_IN msgrequest */
-#define    MC_CMD_MAC_RESET_RESTORE_IN_LEN 0
-
-/* MC_CMD_MAC_RESET_RESTORE_OUT msgresponse */
-#define    MC_CMD_MAC_RESET_RESTORE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_TESTASSERT
- * Deliberately trigger an assert-detonation in the firmware for testing
- * purposes (i.e. to allow tests that the driver copes gracefully). Locks
- * required: None Returns: 0
- */
-#define MC_CMD_TESTASSERT 0x49
-#undef MC_CMD_0x49_PRIVILEGE_CTG
-
-#define MC_CMD_0x49_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_TESTASSERT_IN msgrequest */
-#define    MC_CMD_TESTASSERT_IN_LEN 0
-
-/* MC_CMD_TESTASSERT_OUT msgresponse */
-#define    MC_CMD_TESTASSERT_OUT_LEN 0
-
-/* MC_CMD_TESTASSERT_V2_IN msgrequest */
-#define    MC_CMD_TESTASSERT_V2_IN_LEN 4
-/* How to provoke the assertion */
-#define       MC_CMD_TESTASSERT_V2_IN_TYPE_OFST 0
-#define       MC_CMD_TESTASSERT_V2_IN_TYPE_LEN 4
-/* enum: Assert using the FAIL_ASSERTION_WITH_USEFUL_VALUES macro. Unless
- * you're testing firmware, this is what you want.
- */
-#define          MC_CMD_TESTASSERT_V2_IN_FAIL_ASSERTION_WITH_USEFUL_VALUES 0x0
-/* enum: Assert using assert(0); */
-#define          MC_CMD_TESTASSERT_V2_IN_ASSERT_FALSE 0x1
-/* enum: Deliberately trigger a watchdog */
-#define          MC_CMD_TESTASSERT_V2_IN_WATCHDOG 0x2
-/* enum: Deliberately trigger a trap by loading from an invalid address */
-#define          MC_CMD_TESTASSERT_V2_IN_LOAD_TRAP 0x3
-/* enum: Deliberately trigger a trap by storing to an invalid address */
-#define          MC_CMD_TESTASSERT_V2_IN_STORE_TRAP 0x4
-/* enum: Jump to an invalid address */
-#define          MC_CMD_TESTASSERT_V2_IN_JUMP_TRAP 0x5
-
-/* MC_CMD_TESTASSERT_V2_OUT msgresponse */
-#define    MC_CMD_TESTASSERT_V2_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_WORKAROUND
  * Enable/Disable a given workaround. The mcfw will return EINVAL if it doesn't
  * understand the given workaround number - which should not be treated as a
@@ -8324,6 +8802,62 @@
 #define        MC_CMD_GET_PHY_MEDIA_INFO_IN_DSFP_BANK_LBN 16
 #define        MC_CMD_GET_PHY_MEDIA_INFO_IN_DSFP_BANK_WIDTH 16
 
+/* MC_CMD_GET_PHY_MEDIA_INFO_IN_V2 msgrequest */
+#define    MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_LEN 12
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_PAGE_OFST 0
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_PAGE_LEN 4
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_PAGE_OFST 0
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_PAGE_LBN 0
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_PAGE_WIDTH 16
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_BANK_OFST 0
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_BANK_LBN 16
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_BANK_WIDTH 16
+/* Target port to request PHY state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
+ */
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LO_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LO_LBN 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_HI_OFST 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_HI_LBN 64
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 7
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 52
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 48
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 6
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LINK_END_OFST 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LO_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LO_LBN 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_HI_OFST 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_HI_LBN 64
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_PHY_MEDIA_INFO_OUT msgresponse */
 #define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMIN 5
 #define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 252
@@ -8348,7 +8882,7 @@
 #define MC_CMD_NVRAM_TEST 0x4c
 #undef MC_CMD_0x4c_PRIVILEGE_CTG
 
-#define MC_CMD_0x4c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0x4c_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_NVRAM_TEST_IN msgrequest */
 #define    MC_CMD_NVRAM_TEST_IN_LEN 4
@@ -8370,103 +8904,6 @@
 
 
 /***********************************/
-/* MC_CMD_MRSFP_TWEAK
- * Read status and/or set parameters for the 'mrsfp' driver in mr_rusty builds.
- * I2C I/O expander bits are always read; if equaliser parameters are supplied,
- * they are configured first. Locks required: None. Return code: 0, EINVAL.
- */
-#define MC_CMD_MRSFP_TWEAK 0x4d
-
-/* MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG msgrequest */
-#define    MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_LEN 16
-/* 0-6 low->high de-emph. */
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_LEVEL_OFST 0
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_LEVEL_LEN 4
-/* 0-8 low->high ref.V */
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_DT_CFG_OFST 4
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_DT_CFG_LEN 4
-/* 0-8 0-8 low->high boost */
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_BOOST_OFST 8
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_BOOST_LEN 4
-/* 0-8 low->high ref.V */
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_DT_CFG_OFST 12
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_DT_CFG_LEN 4
-
-/* MC_CMD_MRSFP_TWEAK_IN_READ_ONLY msgrequest */
-#define    MC_CMD_MRSFP_TWEAK_IN_READ_ONLY_LEN 0
-
-/* MC_CMD_MRSFP_TWEAK_OUT msgresponse */
-#define    MC_CMD_MRSFP_TWEAK_OUT_LEN 12
-/* input bits */
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_INPUTS_OFST 0
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_INPUTS_LEN 4
-/* output bits */
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_OUTPUTS_OFST 4
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_OUTPUTS_LEN 4
-/* direction */
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_OFST 8
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_LEN 4
-/* enum: Out. */
-#define          MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_OUT 0x0
-/* enum: In. */
-#define          MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_IN 0x1
-
-
-/***********************************/
-/* MC_CMD_SENSOR_SET_LIMS
- * Adjusts the sensor limits. This is a warranty-voiding operation. Returns:
- * ENOENT if the sensor specified does not exist, EINVAL if the limits are out
- * of range.
- */
-#define MC_CMD_SENSOR_SET_LIMS 0x4e
-#undef MC_CMD_0x4e_PRIVILEGE_CTG
-
-#define MC_CMD_0x4e_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SENSOR_SET_LIMS_IN msgrequest */
-#define    MC_CMD_SENSOR_SET_LIMS_IN_LEN 20
-#define       MC_CMD_SENSOR_SET_LIMS_IN_SENSOR_OFST 0
-#define       MC_CMD_SENSOR_SET_LIMS_IN_SENSOR_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_SENSOR_INFO/MC_CMD_SENSOR_INFO_OUT/MASK */
-/* interpretation is is sensor-specific. */
-#define       MC_CMD_SENSOR_SET_LIMS_IN_LOW0_OFST 4
-#define       MC_CMD_SENSOR_SET_LIMS_IN_LOW0_LEN 4
-/* interpretation is is sensor-specific. */
-#define       MC_CMD_SENSOR_SET_LIMS_IN_HI0_OFST 8
-#define       MC_CMD_SENSOR_SET_LIMS_IN_HI0_LEN 4
-/* interpretation is is sensor-specific. */
-#define       MC_CMD_SENSOR_SET_LIMS_IN_LOW1_OFST 12
-#define       MC_CMD_SENSOR_SET_LIMS_IN_LOW1_LEN 4
-/* interpretation is is sensor-specific. */
-#define       MC_CMD_SENSOR_SET_LIMS_IN_HI1_OFST 16
-#define       MC_CMD_SENSOR_SET_LIMS_IN_HI1_LEN 4
-
-/* MC_CMD_SENSOR_SET_LIMS_OUT msgresponse */
-#define    MC_CMD_SENSOR_SET_LIMS_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_RESOURCE_LIMITS
- */
-#define MC_CMD_GET_RESOURCE_LIMITS 0x4f
-
-/* MC_CMD_GET_RESOURCE_LIMITS_IN msgrequest */
-#define    MC_CMD_GET_RESOURCE_LIMITS_IN_LEN 0
-
-/* MC_CMD_GET_RESOURCE_LIMITS_OUT msgresponse */
-#define    MC_CMD_GET_RESOURCE_LIMITS_OUT_LEN 16
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_BUFTBL_OFST 0
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_BUFTBL_LEN 4
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_EVQ_OFST 4
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_EVQ_LEN 4
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_RXQ_OFST 8
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_RXQ_LEN 4
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_TXQ_OFST 12
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_TXQ_LEN 4
-
-
-/***********************************/
 /* MC_CMD_NVRAM_PARTITIONS
  * Reads the list of available virtual NVRAM partition types. Locks required:
  * none. Returns: 0, EINVAL (bad type).
@@ -8582,806 +9019,6 @@
 #define       MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_STRIDE_OFST 12
 #define       MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_STRIDE_LEN 4
 
-
-/***********************************/
-/* MC_CMD_CLP
- * Perform a CLP related operation, see SF-110495-PS for details of CLP
- * processing. This command has been extended to accomodate the requirements of
- * different manufacturers which are to be found in SF-119187-TC, SF-119186-TC,
- * SF-120509-TC and SF-117282-PS.
- */
-#define MC_CMD_CLP 0x56
-#undef MC_CMD_0x56_PRIVILEGE_CTG
-
-#define MC_CMD_0x56_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_CLP_IN msgrequest */
-#define    MC_CMD_CLP_IN_LEN 4
-/* Sub operation */
-#define       MC_CMD_CLP_IN_OP_OFST 0
-#define       MC_CMD_CLP_IN_OP_LEN 4
-/* enum: Return to factory default settings */
-#define          MC_CMD_CLP_OP_DEFAULT 0x1
-/* enum: Set MAC address */
-#define          MC_CMD_CLP_OP_SET_MAC 0x2
-/* enum: Get MAC address */
-#define          MC_CMD_CLP_OP_GET_MAC 0x3
-/* enum: Set UEFI/GPXE boot mode */
-#define          MC_CMD_CLP_OP_SET_BOOT 0x4
-/* enum: Get UEFI/GPXE boot mode */
-#define          MC_CMD_CLP_OP_GET_BOOT 0x5
-
-/* MC_CMD_CLP_OUT msgresponse */
-#define    MC_CMD_CLP_OUT_LEN 0
-
-/* MC_CMD_CLP_IN_DEFAULT msgrequest */
-#define    MC_CMD_CLP_IN_DEFAULT_LEN 4
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-
-/* MC_CMD_CLP_OUT_DEFAULT msgresponse */
-#define    MC_CMD_CLP_OUT_DEFAULT_LEN 0
-
-/* MC_CMD_CLP_IN_SET_MAC msgrequest */
-#define    MC_CMD_CLP_IN_SET_MAC_LEN 12
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-/* The MAC address assigned to port. A zero MAC address of 00:00:00:00:00:00
- * restores the permanent (factory-programmed) MAC address associated with the
- * port. A non-zero MAC address persists until a PCIe reset or a power cycle.
- */
-#define       MC_CMD_CLP_IN_SET_MAC_ADDR_OFST 4
-#define       MC_CMD_CLP_IN_SET_MAC_ADDR_LEN 6
-/* Padding */
-#define       MC_CMD_CLP_IN_SET_MAC_RESERVED_OFST 10
-#define       MC_CMD_CLP_IN_SET_MAC_RESERVED_LEN 2
-
-/* MC_CMD_CLP_OUT_SET_MAC msgresponse */
-#define    MC_CMD_CLP_OUT_SET_MAC_LEN 0
-
-/* MC_CMD_CLP_IN_SET_MAC_V2 msgrequest */
-#define    MC_CMD_CLP_IN_SET_MAC_V2_LEN 16
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-/* The MAC address assigned to port. A zero MAC address of 00:00:00:00:00:00
- * restores the permanent (factory-programmed) MAC address associated with the
- * port. A non-zero MAC address persists until a PCIe reset or a power cycle.
- */
-#define       MC_CMD_CLP_IN_SET_MAC_V2_ADDR_OFST 4
-#define       MC_CMD_CLP_IN_SET_MAC_V2_ADDR_LEN 6
-/* Padding */
-#define       MC_CMD_CLP_IN_SET_MAC_V2_RESERVED_OFST 10
-#define       MC_CMD_CLP_IN_SET_MAC_V2_RESERVED_LEN 2
-#define       MC_CMD_CLP_IN_SET_MAC_V2_FLAGS_OFST 12
-#define       MC_CMD_CLP_IN_SET_MAC_V2_FLAGS_LEN 4
-#define        MC_CMD_CLP_IN_SET_MAC_V2_VIRTUAL_OFST 12
-#define        MC_CMD_CLP_IN_SET_MAC_V2_VIRTUAL_LBN 0
-#define        MC_CMD_CLP_IN_SET_MAC_V2_VIRTUAL_WIDTH 1
-
-/* MC_CMD_CLP_IN_GET_MAC msgrequest */
-#define    MC_CMD_CLP_IN_GET_MAC_LEN 4
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-
-/* MC_CMD_CLP_IN_GET_MAC_V2 msgrequest */
-#define    MC_CMD_CLP_IN_GET_MAC_V2_LEN 8
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-#define       MC_CMD_CLP_IN_GET_MAC_V2_FLAGS_OFST 4
-#define       MC_CMD_CLP_IN_GET_MAC_V2_FLAGS_LEN 4
-#define        MC_CMD_CLP_IN_GET_MAC_V2_PERMANENT_OFST 4
-#define        MC_CMD_CLP_IN_GET_MAC_V2_PERMANENT_LBN 0
-#define        MC_CMD_CLP_IN_GET_MAC_V2_PERMANENT_WIDTH 1
-
-/* MC_CMD_CLP_OUT_GET_MAC msgresponse */
-#define    MC_CMD_CLP_OUT_GET_MAC_LEN 8
-/* MAC address assigned to port */
-#define       MC_CMD_CLP_OUT_GET_MAC_ADDR_OFST 0
-#define       MC_CMD_CLP_OUT_GET_MAC_ADDR_LEN 6
-/* Padding */
-#define       MC_CMD_CLP_OUT_GET_MAC_RESERVED_OFST 6
-#define       MC_CMD_CLP_OUT_GET_MAC_RESERVED_LEN 2
-
-/* MC_CMD_CLP_IN_SET_BOOT msgrequest */
-#define    MC_CMD_CLP_IN_SET_BOOT_LEN 5
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-/* Boot flag */
-#define       MC_CMD_CLP_IN_SET_BOOT_FLAG_OFST 4
-#define       MC_CMD_CLP_IN_SET_BOOT_FLAG_LEN 1
-
-/* MC_CMD_CLP_OUT_SET_BOOT msgresponse */
-#define    MC_CMD_CLP_OUT_SET_BOOT_LEN 0
-
-/* MC_CMD_CLP_IN_GET_BOOT msgrequest */
-#define    MC_CMD_CLP_IN_GET_BOOT_LEN 4
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-
-/* MC_CMD_CLP_OUT_GET_BOOT msgresponse */
-#define    MC_CMD_CLP_OUT_GET_BOOT_LEN 4
-/* Boot flag */
-#define       MC_CMD_CLP_OUT_GET_BOOT_FLAG_OFST 0
-#define       MC_CMD_CLP_OUT_GET_BOOT_FLAG_LEN 1
-/* Padding */
-#define       MC_CMD_CLP_OUT_GET_BOOT_RESERVED_OFST 1
-#define       MC_CMD_CLP_OUT_GET_BOOT_RESERVED_LEN 3
-
-
-/***********************************/
-/* MC_CMD_MUM
- * Perform a MUM operation
- */
-#define MC_CMD_MUM 0x57
-#undef MC_CMD_0x57_PRIVILEGE_CTG
-
-#define MC_CMD_0x57_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_MUM_IN msgrequest */
-#define    MC_CMD_MUM_IN_LEN 4
-#define       MC_CMD_MUM_IN_OP_HDR_OFST 0
-#define       MC_CMD_MUM_IN_OP_HDR_LEN 4
-#define        MC_CMD_MUM_IN_OP_OFST 0
-#define        MC_CMD_MUM_IN_OP_LBN 0
-#define        MC_CMD_MUM_IN_OP_WIDTH 8
-/* enum: NULL MCDI command to MUM */
-#define          MC_CMD_MUM_OP_NULL 0x1
-/* enum: Get MUM version */
-#define          MC_CMD_MUM_OP_GET_VERSION 0x2
-/* enum: Issue raw I2C command to MUM */
-#define          MC_CMD_MUM_OP_RAW_CMD 0x3
-/* enum: Read from registers on devices connected to MUM. */
-#define          MC_CMD_MUM_OP_READ 0x4
-/* enum: Write to registers on devices connected to MUM. */
-#define          MC_CMD_MUM_OP_WRITE 0x5
-/* enum: Control UART logging. */
-#define          MC_CMD_MUM_OP_LOG 0x6
-/* enum: Operations on MUM GPIO lines */
-#define          MC_CMD_MUM_OP_GPIO 0x7
-/* enum: Get sensor readings from MUM */
-#define          MC_CMD_MUM_OP_READ_SENSORS 0x8
-/* enum: Initiate clock programming on the MUM */
-#define          MC_CMD_MUM_OP_PROGRAM_CLOCKS 0x9
-/* enum: Initiate FPGA load from flash on the MUM */
-#define          MC_CMD_MUM_OP_FPGA_LOAD 0xa
-/* enum: Request sensor reading from MUM ADC resulting from earlier request via
- * MUM ATB
- */
-#define          MC_CMD_MUM_OP_READ_ATB_SENSOR 0xb
-/* enum: Send commands relating to the QSFP ports via the MUM for PHY
- * operations
- */
-#define          MC_CMD_MUM_OP_QSFP 0xc
-/* enum: Request discrete and SODIMM DDR info (type, size, speed grade, voltage
- * level) from MUM
- */
-#define          MC_CMD_MUM_OP_READ_DDR_INFO 0xd
-
-/* MC_CMD_MUM_IN_NULL msgrequest */
-#define    MC_CMD_MUM_IN_NULL_LEN 4
-/* MUM cmd header */
-#define       MC_CMD_MUM_IN_CMD_OFST 0
-#define       MC_CMD_MUM_IN_CMD_LEN 4
-
-/* MC_CMD_MUM_IN_GET_VERSION msgrequest */
-#define    MC_CMD_MUM_IN_GET_VERSION_LEN 4
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-
-/* MC_CMD_MUM_IN_READ msgrequest */
-#define    MC_CMD_MUM_IN_READ_LEN 16
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* ID of (device connected to MUM) to read from registers of */
-#define       MC_CMD_MUM_IN_READ_DEVICE_OFST 4
-#define       MC_CMD_MUM_IN_READ_DEVICE_LEN 4
-/* enum: Hittite HMC1035 clock generator on Sorrento board */
-#define          MC_CMD_MUM_DEV_HITTITE 0x1
-/* enum: Hittite HMC1035 clock generator for NIC-side on Sorrento board */
-#define          MC_CMD_MUM_DEV_HITTITE_NIC 0x2
-/* 32-bit address to read from */
-#define       MC_CMD_MUM_IN_READ_ADDR_OFST 8
-#define       MC_CMD_MUM_IN_READ_ADDR_LEN 4
-/* Number of words to read. */
-#define       MC_CMD_MUM_IN_READ_NUMWORDS_OFST 12
-#define       MC_CMD_MUM_IN_READ_NUMWORDS_LEN 4
-
-/* MC_CMD_MUM_IN_WRITE msgrequest */
-#define    MC_CMD_MUM_IN_WRITE_LENMIN 16
-#define    MC_CMD_MUM_IN_WRITE_LENMAX 252
-#define    MC_CMD_MUM_IN_WRITE_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_IN_WRITE_LEN(num) (12+4*(num))
-#define    MC_CMD_MUM_IN_WRITE_BUFFER_NUM(len) (((len)-12)/4)
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* ID of (device connected to MUM) to write to registers of */
-#define       MC_CMD_MUM_IN_WRITE_DEVICE_OFST 4
-#define       MC_CMD_MUM_IN_WRITE_DEVICE_LEN 4
-/* enum: Hittite HMC1035 clock generator on Sorrento board */
-/*               MC_CMD_MUM_DEV_HITTITE 0x1 */
-/* 32-bit address to write to */
-#define       MC_CMD_MUM_IN_WRITE_ADDR_OFST 8
-#define       MC_CMD_MUM_IN_WRITE_ADDR_LEN 4
-/* Words to write */
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_OFST 12
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_LEN 4
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_MINNUM 1
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_MAXNUM 60
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_MAXNUM_MCDI2 252
-
-/* MC_CMD_MUM_IN_RAW_CMD msgrequest */
-#define    MC_CMD_MUM_IN_RAW_CMD_LENMIN 17
-#define    MC_CMD_MUM_IN_RAW_CMD_LENMAX 252
-#define    MC_CMD_MUM_IN_RAW_CMD_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_IN_RAW_CMD_LEN(num) (16+1*(num))
-#define    MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_NUM(len) (((len)-16)/1)
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* MUM I2C cmd code */
-#define       MC_CMD_MUM_IN_RAW_CMD_CMD_CODE_OFST 4
-#define       MC_CMD_MUM_IN_RAW_CMD_CMD_CODE_LEN 4
-/* Number of bytes to write */
-#define       MC_CMD_MUM_IN_RAW_CMD_NUM_WRITE_OFST 8
-#define       MC_CMD_MUM_IN_RAW_CMD_NUM_WRITE_LEN 4
-/* Number of bytes to read */
-#define       MC_CMD_MUM_IN_RAW_CMD_NUM_READ_OFST 12
-#define       MC_CMD_MUM_IN_RAW_CMD_NUM_READ_LEN 4
-/* Bytes to write */
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_OFST 16
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_LEN 1
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_MINNUM 1
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_MAXNUM 236
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_MAXNUM_MCDI2 1004
-
-/* MC_CMD_MUM_IN_LOG msgrequest */
-#define    MC_CMD_MUM_IN_LOG_LEN 8
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_LOG_OP_OFST 4
-#define       MC_CMD_MUM_IN_LOG_OP_LEN 4
-#define          MC_CMD_MUM_IN_LOG_OP_UART 0x1 /* enum */
-
-/* MC_CMD_MUM_IN_LOG_OP_UART msgrequest */
-#define    MC_CMD_MUM_IN_LOG_OP_UART_LEN 12
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/*            MC_CMD_MUM_IN_LOG_OP_OFST 4 */
-/*            MC_CMD_MUM_IN_LOG_OP_LEN 4 */
-/* Enable/disable debug output to UART */
-#define       MC_CMD_MUM_IN_LOG_OP_UART_ENABLE_OFST 8
-#define       MC_CMD_MUM_IN_LOG_OP_UART_ENABLE_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_LEN 8
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OPCODE_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OPCODE_LBN 0
-#define        MC_CMD_MUM_IN_GPIO_OPCODE_WIDTH 8
-#define          MC_CMD_MUM_IN_GPIO_IN_READ 0x0 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OUT_WRITE 0x1 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OUT_READ 0x2 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE 0x3 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ 0x4 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OP 0x5 /* enum */
-
-/* MC_CMD_MUM_IN_GPIO_IN_READ msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_IN_READ_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_IN_READ_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_IN_READ_HDR_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OUT_WRITE msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OUT_WRITE_LEN 16
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_HDR_LEN 4
-/* The first 32-bit word to be written to the GPIO OUT register. */
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK1_OFST 8
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK1_LEN 4
-/* The second 32-bit word to be written to the GPIO OUT register. */
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK2_OFST 12
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OUT_READ msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OUT_READ_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OUT_READ_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OUT_READ_HDR_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_LEN 16
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_HDR_LEN 4
-/* The first 32-bit word to be written to the GPIO OUT ENABLE register. */
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK1_OFST 8
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK1_LEN 4
-/* The second 32-bit word to be written to the GPIO OUT ENABLE register. */
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK2_OFST 12
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ_HDR_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OP msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OP_BITWISE_OP_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_BITWISE_OP_LBN 8
-#define        MC_CMD_MUM_IN_GPIO_OP_BITWISE_OP_WIDTH 8
-#define          MC_CMD_MUM_IN_GPIO_OP_OUT_READ 0x0 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE 0x1 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG 0x2 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE 0x3 /* enum */
-#define        MC_CMD_MUM_IN_GPIO_OP_GPIO_NUMBER_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_GPIO_NUMBER_LBN 16
-#define        MC_CMD_MUM_IN_GPIO_OP_GPIO_NUMBER_WIDTH 8
-
-/* MC_CMD_MUM_IN_GPIO_OP_OUT_READ msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_OUT_READ_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_READ_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_READ_HDR_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_WRITEBIT_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_WRITEBIT_LBN 24
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_WRITEBIT_WIDTH 8
-
-/* MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_CFG_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_CFG_LBN 24
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_CFG_WIDTH 8
-
-/* MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_ENABLEBIT_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_ENABLEBIT_LBN 24
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_ENABLEBIT_WIDTH 8
-
-/* MC_CMD_MUM_IN_READ_SENSORS msgrequest */
-#define    MC_CMD_MUM_IN_READ_SENSORS_LEN 8
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_READ_SENSORS_PARAMS_OFST 4
-#define       MC_CMD_MUM_IN_READ_SENSORS_PARAMS_LEN 4
-#define        MC_CMD_MUM_IN_READ_SENSORS_SENSOR_ID_OFST 4
-#define        MC_CMD_MUM_IN_READ_SENSORS_SENSOR_ID_LBN 0
-#define        MC_CMD_MUM_IN_READ_SENSORS_SENSOR_ID_WIDTH 8
-#define        MC_CMD_MUM_IN_READ_SENSORS_NUM_SENSORS_OFST 4
-#define        MC_CMD_MUM_IN_READ_SENSORS_NUM_SENSORS_LBN 8
-#define        MC_CMD_MUM_IN_READ_SENSORS_NUM_SENSORS_WIDTH 8
-
-/* MC_CMD_MUM_IN_PROGRAM_CLOCKS msgrequest */
-#define    MC_CMD_MUM_IN_PROGRAM_CLOCKS_LEN 12
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* Bit-mask of clocks to be programmed */
-#define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_MASK_OFST 4
-#define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_MASK_LEN 4
-#define          MC_CMD_MUM_CLOCK_ID_FPGA 0x0 /* enum */
-#define          MC_CMD_MUM_CLOCK_ID_DDR 0x1 /* enum */
-#define          MC_CMD_MUM_CLOCK_ID_NIC 0x2 /* enum */
-/* Control flags for clock programming */
-#define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_FLAGS_OFST 8
-#define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_FLAGS_LEN 4
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_OFST 8
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_LBN 0
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_WIDTH 1
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_OFST 8
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_LBN 1
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_WIDTH 1
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_OFST 8
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_LBN 2
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_WIDTH 1
-
-/* MC_CMD_MUM_IN_FPGA_LOAD msgrequest */
-#define    MC_CMD_MUM_IN_FPGA_LOAD_LEN 8
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* Enable/Disable FPGA config from flash */
-#define       MC_CMD_MUM_IN_FPGA_LOAD_ENABLE_OFST 4
-#define       MC_CMD_MUM_IN_FPGA_LOAD_ENABLE_LEN 4
-
-/* MC_CMD_MUM_IN_READ_ATB_SENSOR msgrequest */
-#define    MC_CMD_MUM_IN_READ_ATB_SENSOR_LEN 4
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-
-/* MC_CMD_MUM_IN_QSFP msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_LEN 12
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_HDR_LEN 4
-#define        MC_CMD_MUM_IN_QSFP_OPCODE_OFST 4
-#define        MC_CMD_MUM_IN_QSFP_OPCODE_LBN 0
-#define        MC_CMD_MUM_IN_QSFP_OPCODE_WIDTH 4
-#define          MC_CMD_MUM_IN_QSFP_INIT 0x0 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_RECONFIGURE 0x1 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP 0x2 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO 0x3 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_FILL_STATS 0x4 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_POLL_BIST 0x5 /* enum */
-#define       MC_CMD_MUM_IN_QSFP_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_IDX_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_INIT msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_INIT_LEN 16
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_INIT_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_INIT_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_INIT_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_INIT_IDX_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_INIT_CAGE_OFST 12
-#define       MC_CMD_MUM_IN_QSFP_INIT_CAGE_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_RECONFIGURE msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_RECONFIGURE_LEN 24
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_IDX_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_TX_DISABLE_OFST 12
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_TX_DISABLE_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LANES_OFST 16
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LANES_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LINK_SPEED_OFST 20
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LINK_SPEED_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_LEN 12
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_IDX_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_LEN 16
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_IDX_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_PAGE_OFST 12
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_PAGE_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_FILL_STATS msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_FILL_STATS_LEN 12
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_FILL_STATS_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_FILL_STATS_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_FILL_STATS_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_FILL_STATS_IDX_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_POLL_BIST msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_POLL_BIST_LEN 12
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_POLL_BIST_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_POLL_BIST_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_POLL_BIST_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_POLL_BIST_IDX_LEN 4
-
-/* MC_CMD_MUM_IN_READ_DDR_INFO msgrequest */
-#define    MC_CMD_MUM_IN_READ_DDR_INFO_LEN 4
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-
-/* MC_CMD_MUM_OUT msgresponse */
-#define    MC_CMD_MUM_OUT_LEN 0
-
-/* MC_CMD_MUM_OUT_NULL msgresponse */
-#define    MC_CMD_MUM_OUT_NULL_LEN 0
-
-/* MC_CMD_MUM_OUT_GET_VERSION msgresponse */
-#define    MC_CMD_MUM_OUT_GET_VERSION_LEN 12
-#define       MC_CMD_MUM_OUT_GET_VERSION_FIRMWARE_OFST 0
-#define       MC_CMD_MUM_OUT_GET_VERSION_FIRMWARE_LEN 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_OFST 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LEN 8
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_OFST 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_LEN 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_LBN 32
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_WIDTH 32
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_OFST 8
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_LEN 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_LBN 64
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_WIDTH 32
-
-/* MC_CMD_MUM_OUT_RAW_CMD msgresponse */
-#define    MC_CMD_MUM_OUT_RAW_CMD_LENMIN 1
-#define    MC_CMD_MUM_OUT_RAW_CMD_LENMAX 252
-#define    MC_CMD_MUM_OUT_RAW_CMD_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_OUT_RAW_CMD_LEN(num) (0+1*(num))
-#define    MC_CMD_MUM_OUT_RAW_CMD_DATA_NUM(len) (((len)-0)/1)
-/* returned data */
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_OFST 0
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_LEN 1
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_MINNUM 1
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_MAXNUM 252
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_MAXNUM_MCDI2 1020
-
-/* MC_CMD_MUM_OUT_READ msgresponse */
-#define    MC_CMD_MUM_OUT_READ_LENMIN 4
-#define    MC_CMD_MUM_OUT_READ_LENMAX 252
-#define    MC_CMD_MUM_OUT_READ_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_OUT_READ_LEN(num) (0+4*(num))
-#define    MC_CMD_MUM_OUT_READ_BUFFER_NUM(len) (((len)-0)/4)
-#define       MC_CMD_MUM_OUT_READ_BUFFER_OFST 0
-#define       MC_CMD_MUM_OUT_READ_BUFFER_LEN 4
-#define       MC_CMD_MUM_OUT_READ_BUFFER_MINNUM 1
-#define       MC_CMD_MUM_OUT_READ_BUFFER_MAXNUM 63
-#define       MC_CMD_MUM_OUT_READ_BUFFER_MAXNUM_MCDI2 255
-
-/* MC_CMD_MUM_OUT_WRITE msgresponse */
-#define    MC_CMD_MUM_OUT_WRITE_LEN 0
-
-/* MC_CMD_MUM_OUT_LOG msgresponse */
-#define    MC_CMD_MUM_OUT_LOG_LEN 0
-
-/* MC_CMD_MUM_OUT_LOG_OP_UART msgresponse */
-#define    MC_CMD_MUM_OUT_LOG_OP_UART_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_IN_READ msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_IN_READ_LEN 8
-/* The first 32-bit word read from the GPIO IN register. */
-#define       MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK1_OFST 0
-#define       MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK1_LEN 4
-/* The second 32-bit word read from the GPIO IN register. */
-#define       MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK2_OFST 4
-#define       MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_OUT_GPIO_OUT_WRITE msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OUT_WRITE_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_OUT_READ msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OUT_READ_LEN 8
-/* The first 32-bit word read from the GPIO OUT register. */
-#define       MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK1_OFST 0
-#define       MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK1_LEN 4
-/* The second 32-bit word read from the GPIO OUT register. */
-#define       MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK2_OFST 4
-#define       MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_WRITE msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_WRITE_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_LEN 8
-#define       MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK1_OFST 0
-#define       MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK1_LEN 4
-#define       MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK2_OFST 4
-#define       MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_OUT_GPIO_OP_OUT_READ msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OP_OUT_READ_LEN 4
-#define       MC_CMD_MUM_OUT_GPIO_OP_OUT_READ_BIT_READ_OFST 0
-#define       MC_CMD_MUM_OUT_GPIO_OP_OUT_READ_BIT_READ_LEN 4
-
-/* MC_CMD_MUM_OUT_GPIO_OP_OUT_WRITE msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OP_OUT_WRITE_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_OP_OUT_CONFIG msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OP_OUT_CONFIG_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_OP_OUT_ENABLE msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OP_OUT_ENABLE_LEN 0
-
-/* MC_CMD_MUM_OUT_READ_SENSORS msgresponse */
-#define    MC_CMD_MUM_OUT_READ_SENSORS_LENMIN 4
-#define    MC_CMD_MUM_OUT_READ_SENSORS_LENMAX 252
-#define    MC_CMD_MUM_OUT_READ_SENSORS_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_OUT_READ_SENSORS_LEN(num) (0+4*(num))
-#define    MC_CMD_MUM_OUT_READ_SENSORS_DATA_NUM(len) (((len)-0)/4)
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_OFST 0
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_LEN 4
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_MINNUM 1
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_MAXNUM 63
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_MAXNUM_MCDI2 255
-#define        MC_CMD_MUM_OUT_READ_SENSORS_READING_OFST 0
-#define        MC_CMD_MUM_OUT_READ_SENSORS_READING_LBN 0
-#define        MC_CMD_MUM_OUT_READ_SENSORS_READING_WIDTH 16
-#define        MC_CMD_MUM_OUT_READ_SENSORS_STATE_OFST 0
-#define        MC_CMD_MUM_OUT_READ_SENSORS_STATE_LBN 16
-#define        MC_CMD_MUM_OUT_READ_SENSORS_STATE_WIDTH 8
-#define        MC_CMD_MUM_OUT_READ_SENSORS_TYPE_OFST 0
-#define        MC_CMD_MUM_OUT_READ_SENSORS_TYPE_LBN 24
-#define        MC_CMD_MUM_OUT_READ_SENSORS_TYPE_WIDTH 8
-
-/* MC_CMD_MUM_OUT_PROGRAM_CLOCKS msgresponse */
-#define    MC_CMD_MUM_OUT_PROGRAM_CLOCKS_LEN 4
-#define       MC_CMD_MUM_OUT_PROGRAM_CLOCKS_OK_MASK_OFST 0
-#define       MC_CMD_MUM_OUT_PROGRAM_CLOCKS_OK_MASK_LEN 4
-
-/* MC_CMD_MUM_OUT_FPGA_LOAD msgresponse */
-#define    MC_CMD_MUM_OUT_FPGA_LOAD_LEN 0
-
-/* MC_CMD_MUM_OUT_READ_ATB_SENSOR msgresponse */
-#define    MC_CMD_MUM_OUT_READ_ATB_SENSOR_LEN 4
-#define       MC_CMD_MUM_OUT_READ_ATB_SENSOR_RESULT_OFST 0
-#define       MC_CMD_MUM_OUT_READ_ATB_SENSOR_RESULT_LEN 4
-
-/* MC_CMD_MUM_OUT_QSFP_INIT msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_INIT_LEN 0
-
-/* MC_CMD_MUM_OUT_QSFP_RECONFIGURE msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_RECONFIGURE_LEN 8
-#define       MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LP_CAP_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LP_CAP_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_FLAGS_OFST 4
-#define       MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_FLAGS_LEN 4
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_READY_OFST 4
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_READY_LBN 0
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_READY_WIDTH 1
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LINK_UP_OFST 4
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LINK_UP_LBN 1
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LINK_UP_WIDTH 1
-
-/* MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP_PORT_PHY_LP_CAP_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP_PORT_PHY_LP_CAP_LEN 4
-
-/* MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LENMIN 5
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LENMAX 252
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LEN(num) (4+1*(num))
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_NUM(len) (((len)-4)/1)
-/* in bytes */
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATALEN_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATALEN_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_OFST 4
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_LEN 1
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_MINNUM 1
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_MAXNUM 248
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_MAXNUM_MCDI2 1016
-
-/* MC_CMD_MUM_OUT_QSFP_FILL_STATS msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_FILL_STATS_LEN 8
-#define       MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PMA_PMD_LINK_UP_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PMA_PMD_LINK_UP_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PCS_LINK_UP_OFST 4
-#define       MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PCS_LINK_UP_LEN 4
-
-/* MC_CMD_MUM_OUT_QSFP_POLL_BIST msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_POLL_BIST_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_POLL_BIST_TEST_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_POLL_BIST_TEST_LEN 4
-
-/* MC_CMD_MUM_OUT_READ_DDR_INFO msgresponse */
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMIN 24
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMAX 248
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMAX_MCDI2 1016
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LEN(num) (8+8*(num))
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_NUM(len) (((len)-8)/8)
-/* Discrete (soldered) DDR resistor strap info */
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_DISCRETE_DDR_INFO_OFST 0
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_DISCRETE_DDR_INFO_LEN 4
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_OFST 0
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_LBN 0
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_WIDTH 16
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_OFST 0
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_LBN 16
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_WIDTH 16
-/* Number of SODIMM info records */
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_RECORDS_OFST 4
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_RECORDS_LEN 4
-/* Array of SODIMM info records */
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_OFST 8
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LEN 8
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_OFST 8
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_LEN 4
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_LBN 64
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_WIDTH 32
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_OFST 12
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_LEN 4
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_LBN 96
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_WIDTH 32
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MINNUM 2
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MAXNUM 30
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MAXNUM_MCDI2 126
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_LBN 0
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_WIDTH 8
-/* enum: SODIMM bank 1 (Top SODIMM for Sorrento) */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_BANK1 0x0
-/* enum: SODIMM bank 2 (Bottom SODDIMM for Sorrento) */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_BANK2 0x1
-/* enum: Total number of SODIMM banks */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_BANKS 0x2
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_LBN 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_WIDTH 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_LBN 16
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_WIDTH 4
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_LBN 20
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_WIDTH 4
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NOT_POWERED 0x0 /* enum */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V25 0x1 /* enum */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V35 0x2 /* enum */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V5 0x3 /* enum */
-/* enum: Values 5-15 are reserved for future usage */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V8 0x4
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_LBN 24
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_WIDTH 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_LBN 32
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_WIDTH 16
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_LBN 48
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_WIDTH 4
-/* enum: No module present */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_ABSENT 0x0
-/* enum: Module present supported and powered on */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_POWERED 0x1
-/* enum: Module present but bad type */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_TYPE 0x2
-/* enum: Module present but incompatible voltage */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_VOLTAGE 0x3
-/* enum: Module present but unknown SPD */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_SPD 0x4
-/* enum: Module present but slot cannot support it */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_SLOT 0x5
-/* enum: Modules may or may not be present, but cannot establish contact by I2C
- */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NOT_REACHABLE 0x6
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_LBN 52
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_WIDTH 12
-
 /* MC_CMD_DYNAMIC_SENSORS_LIMITS structuredef: Set of sensor limits. This
  * should match the equivalent structure in the sensor_query SPHINX service.
  */
@@ -9500,27 +9137,22 @@
  * and a generation count for this version of the sensor table. On systems
  * advertising the DYNAMIC_SENSORS capability bit, this replaces the
  * MC_CMD_READ_SENSORS command. On multi-MC systems this may include sensors
- * added by the NMC.
- *
- * Sensor handles are persistent for the lifetime of the sensor and are used to
- * identify sensors in MC_CMD_DYNAMIC_SENSORS_GET_DESCRIPTIONS and
- * MC_CMD_DYNAMIC_SENSORS_GET_VALUES.
- *
- * The generation count is maintained by the MC, is persistent across reboots
- * and will be incremented each time the sensor table is modified. When the
- * table is modified, a CODE_DYNAMIC_SENSORS_CHANGE event will be generated
- * containing the new generation count. The driver should compare this against
- * the current generation count, and if it is different, call
- * MC_CMD_DYNAMIC_SENSORS_LIST again to update it's copy of the sensor table.
- *
- * The sensor count is provided to allow a future path to supporting more than
+ * added by the NMC. Sensor handles are persistent for the lifetime of the
+ * sensor and are used to identify sensors in
+ * MC_CMD_DYNAMIC_SENSORS_GET_DESCRIPTIONS and
+ * MC_CMD_DYNAMIC_SENSORS_GET_VALUES. The generation count is maintained by the
+ * MC, is persistent across reboots and will be incremented each time the
+ * sensor table is modified. When the table is modified, a
+ * CODE_DYNAMIC_SENSORS_CHANGE event will be generated containing the new
+ * generation count. The driver should compare this against the current
+ * generation count, and if it is different, call MC_CMD_DYNAMIC_SENSORS_LIST
+ * again to update it's copy of the sensor table. The sensor count is provided
+ * to allow a future path to supporting more than
  * MC_CMD_DYNAMIC_SENSORS_GET_READINGS_IN_HANDLES_MAXNUM_MCDI2 sensors, i.e.
  * the maximum number that will fit in a single response. As this is a fairly
  * large number (253) it is not anticipated that this will be needed in the
- * near future, so can currently be ignored.
- *
- * On Riverhead this command is implemented as a wrapper for `list` in the
- * sensor_query SPHINX service.
+ * near future, so can currently be ignored. On Riverhead this command is
+ * implemented as a wrapper for `list` in the sensor_query SPHINX service.
  */
 #define MC_CMD_DYNAMIC_SENSORS_LIST 0x66
 #undef MC_CMD_0x66_PRIVILEGE_CTG
@@ -9557,15 +9189,13 @@
 /***********************************/
 /* MC_CMD_DYNAMIC_SENSORS_GET_DESCRIPTIONS
  * Get descriptions for a set of sensors, specified as an array of sensor
- * handles as returned by MC_CMD_DYNAMIC_SENSORS_LIST
- *
- * Any handles which do not correspond to a sensor currently managed by the MC
- * will be dropped from from the response. This may happen when a sensor table
- * update is in progress, and effectively means the set of usable sensors is
- * the intersection between the sets of sensors known to the driver and the MC.
- *
- * On Riverhead this command is implemented as a wrapper for
- * `get_descriptions` in the sensor_query SPHINX service.
+ * handles as returned by MC_CMD_DYNAMIC_SENSORS_LIST. Any handles which do not
+ * correspond to a sensor currently managed by the MC will be dropped from from
+ * the response. This may happen when a sensor table update is in progress, and
+ * effectively means the set of usable sensors is the intersection between the
+ * sets of sensors known to the driver and the MC. On Riverhead this command is
+ * implemented as a wrapper for `get_descriptions` in the sensor_query SPHINX
+ * service.
  */
 #define MC_CMD_DYNAMIC_SENSORS_GET_DESCRIPTIONS 0x67
 #undef MC_CMD_0x67_PRIVILEGE_CTG
@@ -9602,19 +9232,15 @@
 /***********************************/
 /* MC_CMD_DYNAMIC_SENSORS_GET_READINGS
  * Read the state and value for a set of sensors, specified as an array of
- * sensor handles as returned by MC_CMD_DYNAMIC_SENSORS_LIST.
- *
- * In the case of a broken sensor, then the state of the response's
- * MC_CMD_DYNAMIC_SENSORS_VALUE entry will be set to BROKEN, and any value
- * provided should be treated as erroneous.
- *
- * Any handles which do not correspond to a sensor currently managed by the MC
- * will be dropped from from the response. This may happen when a sensor table
- * update is in progress, and effectively means the set of usable sensors is
- * the intersection between the sets of sensors known to the driver and the MC.
- *
- * On Riverhead this command is implemented as a wrapper for `get_readings`
- * in the sensor_query SPHINX service.
+ * sensor handles as returned by MC_CMD_DYNAMIC_SENSORS_LIST. In the case of a
+ * broken sensor, then the state of the response's MC_CMD_DYNAMIC_SENSORS_VALUE
+ * entry will be set to BROKEN, and any value provided should be treated as
+ * erroneous. Any handles which do not correspond to a sensor currently managed
+ * by the MC will be dropped from from the response. This may happen when a
+ * sensor table update is in progress, and effectively means the set of usable
+ * sensors is the intersection between the sets of sensors known to the driver
+ * and the MC. On Riverhead this command is implemented as a wrapper for
+ * `get_readings` in the sensor_query SPHINX service.
  */
 #define MC_CMD_DYNAMIC_SENSORS_GET_READINGS 0x68
 #undef MC_CMD_0x68_PRIVILEGE_CTG
@@ -9647,45 +9273,1286 @@
 #define       MC_CMD_DYNAMIC_SENSORS_GET_READINGS_OUT_VALUES_MAXNUM 21
 #define       MC_CMD_DYNAMIC_SENSORS_GET_READINGS_OUT_VALUES_MAXNUM_MCDI2 85
 
+/* MC_CMD_MAC_FLAGS structuredef */
+#define    MC_CMD_MAC_FLAGS_LEN 4
+/* The enums defined in this field are used as indices into the
+ * MC_CMD_MAC_FLAGS bitmask.
+ */
+#define       MC_CMD_MAC_FLAGS_MASK_OFST 0
+#define       MC_CMD_MAC_FLAGS_MASK_LEN 4
+/* enum property: bitshift */
+/* enum: Include the FCS in the packet data delivered to the host. Ignored if
+ * RX_INCLUDE_FCS not set in capabilities.
+ */
+#define          MC_CMD_MAC_FLAGS_FLAG_INCLUDE_FCS 0x0
+#define       MC_CMD_MAC_FLAGS_MASK_LBN 0
+#define       MC_CMD_MAC_FLAGS_MASK_WIDTH 32
+
+/* MC_CMD_TRANSMISSION_MODE structuredef */
+#define    MC_CMD_TRANSMISSION_MODE_LEN 4
+#define       MC_CMD_TRANSMISSION_MODE_MASK_OFST 0
+#define       MC_CMD_TRANSMISSION_MODE_MASK_LEN 4
+/* enum property: value */
+#define          MC_CMD_TRANSMISSION_MODE_PROMSC_MODE 0x0 /* enum */
+#define          MC_CMD_TRANSMISSION_MODE_UNCST_MODE 0x1 /* enum */
+#define          MC_CMD_TRANSMISSION_MODE_BRDCST_MODE 0x2 /* enum */
+#define       MC_CMD_TRANSMISSION_MODE_MASK_LBN 0
+#define       MC_CMD_TRANSMISSION_MODE_MASK_WIDTH 32
+
+/* MC_CMD_MAC_CONFIG_OPTIONS structuredef */
+#define    MC_CMD_MAC_CONFIG_OPTIONS_LEN 4
+#define       MC_CMD_MAC_CONFIG_OPTIONS_MASK_OFST 0
+#define       MC_CMD_MAC_CONFIG_OPTIONS_MASK_LEN 4
+/* enum property: bitmask */
+/* enum: Configure the MAC address. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_ADDR 0x0
+/* enum: Configure the maximum frame length. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_MAX_FRAME_LEN 0x1
+/* enum: Configure flow control. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_FCNTL 0x2
+/* enum: Configure the transmission mode. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_TRANSMISSION_MODE 0x3
+/* enum: Configure FCS. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_INCLUDE_FCS 0x4
+#define       MC_CMD_MAC_CONFIG_OPTIONS_MASK_LBN 0
+#define       MC_CMD_MAC_CONFIG_OPTIONS_MASK_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_MAC_CTRL
+ * Set MAC configuration. Return code: 0, EINVAL, ENOTSUP
+ */
+#define MC_CMD_MAC_CTRL 0x1df
+#undef MC_CMD_0x1df_PRIVILEGE_CTG
+
+#define MC_CMD_0x1df_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_MAC_CTRL_IN msgrequest */
+#define    MC_CMD_MAC_CTRL_IN_LEN 32
+/* Handle for selected network port. */
+#define       MC_CMD_MAC_CTRL_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_CTRL_IN_PORT_HANDLE_LEN 4
+/* Select which parameters to configure. A parameter will only be modified if
+ * the corresponding control flag is set.
+ */
+#define       MC_CMD_MAC_CTRL_IN_CONTROL_FLAGS_OFST 4
+#define       MC_CMD_MAC_CTRL_IN_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_CONFIG_OPTIONS/MASK */
+/* MAC address of the device. */
+#define       MC_CMD_MAC_CTRL_IN_ADDR_OFST 8
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LEN 8
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LO_OFST 8
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LO_LBN 64
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_CTRL_IN_ADDR_HI_OFST 12
+#define       MC_CMD_MAC_CTRL_IN_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_CTRL_IN_ADDR_HI_LBN 96
+#define       MC_CMD_MAC_CTRL_IN_ADDR_HI_WIDTH 32
+/* Includes the ethernet header, optional VLAN tags, payload and FCS. */
+#define       MC_CMD_MAC_CTRL_IN_MAX_FRAME_LEN_OFST 16
+#define       MC_CMD_MAC_CTRL_IN_MAX_FRAME_LEN_LEN 4
+/* Settings for flow control. */
+#define       MC_CMD_MAC_CTRL_IN_FCNTL_OFST 20
+#define       MC_CMD_MAC_CTRL_IN_FCNTL_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_FCNTL/MASK */
+/* Configure the MAC to transmit in one of promiscuous, unicast or broadcast
+ * mode.
+ */
+#define       MC_CMD_MAC_CTRL_IN_TRANSMISSION_MODE_OFST 24
+#define       MC_CMD_MAC_CTRL_IN_TRANSMISSION_MODE_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_TRANSMISSION_MODE/MASK */
+/* Flags to control and expand the configuration of the MAC. */
+#define       MC_CMD_MAC_CTRL_IN_FLAGS_OFST 28
+#define       MC_CMD_MAC_CTRL_IN_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_FLAGS/MASK */
+
+/* MC_CMD_MAC_CTRL_IN_V2 msgrequest: Updated MAC_CTRL with QBB mask */
+#define    MC_CMD_MAC_CTRL_IN_V2_LEN 33
+/* Handle for selected network port. */
+#define       MC_CMD_MAC_CTRL_IN_V2_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_CTRL_IN_V2_PORT_HANDLE_LEN 4
+/* Select which parameters to configure. A parameter will only be modified if
+ * the corresponding control flag is set.
+ */
+#define       MC_CMD_MAC_CTRL_IN_V2_CONTROL_FLAGS_OFST 4
+#define       MC_CMD_MAC_CTRL_IN_V2_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_CONFIG_OPTIONS/MASK */
+/* MAC address of the device. */
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_OFST 8
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LEN 8
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LO_OFST 8
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LO_LBN 64
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_HI_OFST 12
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_HI_LBN 96
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_HI_WIDTH 32
+/* Includes the ethernet header, optional VLAN tags, payload and FCS. */
+#define       MC_CMD_MAC_CTRL_IN_V2_MAX_FRAME_LEN_OFST 16
+#define       MC_CMD_MAC_CTRL_IN_V2_MAX_FRAME_LEN_LEN 4
+/* Settings for flow control. */
+#define       MC_CMD_MAC_CTRL_IN_V2_FCNTL_OFST 20
+#define       MC_CMD_MAC_CTRL_IN_V2_FCNTL_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_FCNTL/MASK */
+/* Configure the MAC to transmit in one of promiscuous, unicast or broadcast
+ * mode.
+ */
+#define       MC_CMD_MAC_CTRL_IN_V2_TRANSMISSION_MODE_OFST 24
+#define       MC_CMD_MAC_CTRL_IN_V2_TRANSMISSION_MODE_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_TRANSMISSION_MODE/MASK */
+/* Flags to control and expand the configuration of the MAC. */
+#define       MC_CMD_MAC_CTRL_IN_V2_FLAGS_OFST 28
+#define       MC_CMD_MAC_CTRL_IN_V2_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_FLAGS/MASK */
+/* Priority-based flow control mask (QBB). PRIO7 corresponds to the highest
+ * priority, and PRIO0 to the lowest. This field is only used when CFG_FCNTL is
+ * set and FCNTL is QBB
+ */
+#define       MC_CMD_MAC_CTRL_IN_V2_PRIO_FCNTL_MASK_OFST 32
+#define       MC_CMD_MAC_CTRL_IN_V2_PRIO_FCNTL_MASK_LEN 1
+/* enum property: bitmask */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO0 0x0 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO1 0x1 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO2 0x2 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO3 0x3 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO4 0x4 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO5 0x5 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO6 0x6 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO7 0x7 /* enum */
+
+/* MC_CMD_MAC_CTRL_OUT msgresponse */
+#define    MC_CMD_MAC_CTRL_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_MAC_STATE
+ * Read the MAC state. Return code: 0, ETIME.
+ */
+#define MC_CMD_MAC_STATE 0x1e0
+#undef MC_CMD_0x1e0_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e0_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_MAC_STATE_IN msgrequest */
+#define    MC_CMD_MAC_STATE_IN_LEN 4
+/* Handle for selected network port. */
+#define       MC_CMD_MAC_STATE_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_STATE_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_MAC_STATE_OUT msgresponse */
+#define    MC_CMD_MAC_STATE_OUT_LEN 32
+/* The configured maximum frame length of the MAC. */
+#define       MC_CMD_MAC_STATE_OUT_MAX_FRAME_LEN_OFST 0
+#define       MC_CMD_MAC_STATE_OUT_MAX_FRAME_LEN_LEN 4
+/* This returns the negotiated flow control value. */
+#define       MC_CMD_MAC_STATE_OUT_FCNTL_OFST 4
+#define       MC_CMD_MAC_STATE_OUT_FCNTL_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_FCNTL/MASK */
+/* MAC address of the device. */
+#define       MC_CMD_MAC_STATE_OUT_ADDR_OFST 8
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LEN 8
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LO_OFST 8
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LO_LBN 64
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_STATE_OUT_ADDR_HI_OFST 12
+#define       MC_CMD_MAC_STATE_OUT_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_STATE_OUT_ADDR_HI_LBN 96
+#define       MC_CMD_MAC_STATE_OUT_ADDR_HI_WIDTH 32
+/* Flags indicating MAC faults. */
+#define       MC_CMD_MAC_STATE_OUT_MAC_FAULT_FLAGS_OFST 16
+#define       MC_CMD_MAC_STATE_OUT_MAC_FAULT_FLAGS_LEN 4
+/* enum property: bitshift */
+/* enum: Indicates a local MAC fault. */
+#define          MC_CMD_MAC_STATE_OUT_LOCAL 0x0
+/* enum: Indicates a remote MAC fault. */
+#define          MC_CMD_MAC_STATE_OUT_REMOTE 0x1
+/* enum: Indicates a pending reconfiguration of the MAC. */
+#define          MC_CMD_MAC_STATE_OUT_PENDING_RECONFIG 0x2
+/* The flags that were used to configure the MAC. This is a copy of the FLAGS
+ * field in the MC_CMD_MAC_CTRL_IN command.
+ */
+#define       MC_CMD_MAC_STATE_OUT_FLAGS_OFST 20
+#define       MC_CMD_MAC_STATE_OUT_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_FLAGS/MASK */
+/* The transmission mode that was used to configure the MAC. This is a copy of
+ * the TRANSMISSION_MODE field in the MC_CMD_MAC_CTRL_IN command.
+ */
+#define       MC_CMD_MAC_STATE_OUT_TRANSMISSION_MODE_OFST 24
+#define       MC_CMD_MAC_STATE_OUT_TRANSMISSION_MODE_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_TRANSMISSION_MODE/MASK */
+/* The control flags that were used to configure the MAC. This is a copy of the
+ * CONTROL field in the MC_CMD_MAC_CTRL_IN command.
+ */
+#define       MC_CMD_MAC_STATE_OUT_CONTROL_FLAGS_OFST 28
+#define       MC_CMD_MAC_STATE_OUT_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_CONFIG_OPTIONS/MASK */
+
+
+/***********************************/
+/* MC_CMD_GET_ASSIGNED_PORT_HANDLE
+ * Obtain a handle that can be operated on to configure and query the status of
+ * the link. ENOENT is returned when no port is assigned to the client. Return
+ * code: 0, ENOENT
+ */
+#define MC_CMD_GET_ASSIGNED_PORT_HANDLE 0x1e2
+#undef MC_CMD_0x1e2_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_ASSIGNED_PORT_HANDLE_IN msgrequest */
+#define    MC_CMD_GET_ASSIGNED_PORT_HANDLE_IN_LEN 0
+
+/* MC_CMD_GET_ASSIGNED_PORT_HANDLE_OUT msgresponse */
+#define    MC_CMD_GET_ASSIGNED_PORT_HANDLE_OUT_LEN 4
+/* Handle for assigned port. */
+#define       MC_CMD_GET_ASSIGNED_PORT_HANDLE_OUT_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_ASSIGNED_PORT_HANDLE_OUT_PORT_HANDLE_LEN 4
+
+/* MC_CMD_STAT_ID structuredef */
+#define    MC_CMD_STAT_ID_LEN 4
+#define       MC_CMD_STAT_ID_SOURCE_ID_OFST 0
+#define       MC_CMD_STAT_ID_SOURCE_ID_LEN 2
+/* enum property: index */
+/* enum: Internal markers (generation start and end markers) */
+#define          MC_CMD_STAT_ID_MARKER 0x1
+/* enum: Network port MAC statistics. */
+#define          MC_CMD_STAT_ID_MAC 0x2
+/* enum: Network port PHY statistics. */
+#define          MC_CMD_STAT_ID_PHY 0x3
+#define       MC_CMD_STAT_ID_SOURCE_ID_LBN 0
+#define       MC_CMD_STAT_ID_SOURCE_ID_WIDTH 16
+#define       MC_CMD_STAT_ID_MARKER_STAT_ID_OFST 2
+#define       MC_CMD_STAT_ID_MARKER_STAT_ID_LEN 2
+/* enum property: index */
+/* enum: This value is used to mark the start of a generation of statistics for
+ * DMA synchronization. It is incremented whenever a new set of statistics is
+ * transferred. Always the first entry in the DMA buffer.
+ */
+#define          MC_CMD_STAT_ID_GENERATION_START 0x1
+/* enum: This value is used to mark the end of a generation of statistics for
+ * DMA synchronizaion. Always the last entry in the DMA buffer and set to the
+ * same value as GENERATION_START. The host driver must compare the
+ * GENERATION_START and GENERATION_END values to verify that the DMA buffer is
+ * consistent upon copying the the DMA buffer. If they do not match, it means
+ * that new DMA transfer has started while the host driver was copying the DMA
+ * buffer. In this case, the host driver must repeat the copy operation.
+ */
+#define          MC_CMD_STAT_ID_GENERATION_END 0x2
+#define       MC_CMD_STAT_ID_MARKER_STAT_ID_LBN 16
+#define       MC_CMD_STAT_ID_MARKER_STAT_ID_WIDTH 16
+#define       MC_CMD_STAT_ID_MAC_STAT_ID_OFST 2
+#define       MC_CMD_STAT_ID_MAC_STAT_ID_LEN 2
+/* enum property: index */
+/* enum: Total number of packets transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_PKTS 0x1
+/* enum: Pause frames transmitted. */
+#define          MC_CMD_STAT_ID_TX_PAUSE_PKTS 0x2
+/* enum: Control frames transmitted. */
+#define          MC_CMD_STAT_ID_TX_CONTROL_PKTS 0x3
+/* enum: Unicast packets transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_UNICAST_PKTS 0x4
+/* enum: Multicast packets transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_MULTICAST_PKTS 0x5
+/* enum: Broadcast packets transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_BROADCAST_PKTS 0x6
+/* enum: Bytes transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_BYTES 0x7
+/* enum: Bytes transmitted with bad CRC. */
+#define          MC_CMD_STAT_ID_TX_BAD_BYTES 0x8
+/* enum: Bytes transmitted with good CRC. */
+#define          MC_CMD_STAT_ID_TX_GOOD_BYTES 0x9
+/* enum: Packets transmitted with length less than 64 bytes. */
+#define          MC_CMD_STAT_ID_TX_LT64_PKTS 0xa
+/* enum: Packets transmitted with length equal to 64 bytes. */
+#define          MC_CMD_STAT_ID_TX_64_PKTS 0xb
+/* enum: Packets transmitted with length between 65 and 127 bytes. */
+#define          MC_CMD_STAT_ID_TX_65_TO_127_PKTS 0xc
+/* enum: Packets transmitted with length between 128 and 255 bytes. */
+#define          MC_CMD_STAT_ID_TX_128_TO_255_PKTS 0xd
+/* enum: Packets transmitted with length between 256 and 511 bytes. */
+#define          MC_CMD_STAT_ID_TX_256_TO_511_PKTS 0xe
+/* enum: Packets transmitted with length between 512 and 1023 bytes. */
+#define          MC_CMD_STAT_ID_TX_512_TO_1023_PKTS 0xf
+/* enum: Packets transmitted with length between 1024 and 1518 bytes. */
+#define          MC_CMD_STAT_ID_TX_1024_TO_15XX_PKTS 0x10
+/* enum: Packets transmitted with length between 1519 and 9216 bytes. */
+#define          MC_CMD_STAT_ID_TX_15XX_TO_JUMBO_PKTS 0x11
+/* enum: Packets transmitted with length greater than 9216 bytes. */
+#define          MC_CMD_STAT_ID_TX_GTJUMBO_PKTS 0x12
+/* enum: Packets transmitted with bad FCS. */
+#define          MC_CMD_STAT_ID_TX_BAD_FCS_PKTS 0x13
+/* enum: Packets transmitted with good FCS. */
+#define          MC_CMD_STAT_ID_TX_GOOD_FCS_PKTS 0x14
+/* enum: Packets received. */
+#define          MC_CMD_STAT_ID_RX_PKTS 0x15
+/* enum: Pause frames received. */
+#define          MC_CMD_STAT_ID_RX_PAUSE_PKTS 0x16
+/* enum: Total number of good packets received. */
+#define          MC_CMD_STAT_ID_RX_GOOD_PKTS 0x17
+/* enum: Total number of BAD packets received. */
+#define          MC_CMD_STAT_ID_RX_BAD_PKTS 0x18
+/* enum: Total number of control frames received. */
+#define          MC_CMD_STAT_ID_RX_CONTROL_PKTS 0x19
+/* enum: Total number of unicast packets received. */
+#define          MC_CMD_STAT_ID_RX_UNICAST_PKTS 0x1a
+/* enum: Total number of multicast packets received. */
+#define          MC_CMD_STAT_ID_RX_MULTICAST_PKTS 0x1b
+/* enum: Total number of broadcast packets received. */
+#define          MC_CMD_STAT_ID_RX_BROADCAST_PKTS 0x1c
+/* enum: Total number of bytes received. */
+#define          MC_CMD_STAT_ID_RX_BYTES 0x1d
+/* enum: Total number of bytes received with bad CRC. */
+#define          MC_CMD_STAT_ID_RX_BAD_BYTES 0x1e
+/* enum: Total number of bytes received with GOOD CRC. */
+#define          MC_CMD_STAT_ID_RX_GOOD_BYTES 0x1f
+/* enum: Packets received with length equal to 64 bytes. */
+#define          MC_CMD_STAT_ID_RX_64_PKTS 0x20
+/* enum: Packets received with length between 65 and 127 bytes. */
+#define          MC_CMD_STAT_ID_RX_65_TO_127_PKTS 0x21
+/* enum: Packets received with length between 128 and 255 bytes. */
+#define          MC_CMD_STAT_ID_RX_128_TO_255_PKTS 0x22
+/* enum: Packets received with length between 256 and 511 bytes. */
+#define          MC_CMD_STAT_ID_RX_256_TO_511_PKTS 0x23
+/* enum: Packets received with length between 512 and 1023 bytes. */
+#define          MC_CMD_STAT_ID_RX_512_TO_1023_PKTS 0x24
+/* enum: Packets received with length between 1024 and 1518 bytes. */
+#define          MC_CMD_STAT_ID_RX_1024_TO_15XX_PKTS 0x25
+/* enum: Packets received with length between 1519 and 9216 bytes. */
+#define          MC_CMD_STAT_ID_RX_15XX_TO_JUMBO_PKTS 0x26
+/* enum: Packets received with length greater than 9216 bytes. */
+#define          MC_CMD_STAT_ID_RX_GTJUMBO_PKTS 0x27
+/* enum: Packets received with length less than 64 bytes. */
+#define          MC_CMD_STAT_ID_RX_UNDERSIZE_PKTS 0x28
+/* enum: Packets received with bad FCS. */
+#define          MC_CMD_STAT_ID_RX_BAD_FCS_PKTS 0x29
+/* enum: Packets received with GOOD FCS. */
+#define          MC_CMD_STAT_ID_RX_GOOD_FCS_PKTS 0x2a
+/* enum: Packets received with overflow. */
+#define          MC_CMD_STAT_ID_RX_OVERFLOW_PKTS 0x2b
+/* enum: Packets received with symbol error. */
+#define          MC_CMD_STAT_ID_RX_SYMBOL_ERROR_PKTS 0x2c
+/* enum: Packets received with alignment error. */
+#define          MC_CMD_STAT_ID_RX_ALIGN_ERROR_PKTS 0x2d
+/* enum: Packets received with length error. */
+#define          MC_CMD_STAT_ID_RX_LENGTH_ERROR_PKTS 0x2e
+/* enum: Packets received with internal error. */
+#define          MC_CMD_STAT_ID_RX_INTERNAL_ERROR_PKTS 0x2f
+/* enum: Packets received with jabber. These packets are larger than the
+ * allowed maximum receive unit (MRU). This indicates that a packet either has
+ * a bad CRC or has an RX error.
+ */
+#define          MC_CMD_STAT_ID_RX_JABBER_PKTS 0x30
+/* enum: Packets dropped due to having no descriptor. This is a datapath stat
+ */
+#define          MC_CMD_STAT_ID_RX_NODESC_DROPS 0x31
+/* enum: Packets received with lanes 0 and 1 character error. */
+#define          MC_CMD_STAT_ID_RX_LANES01_CHAR_ERR 0x32
+/* enum: Packets received with lanes 2 and 3 character error. */
+#define          MC_CMD_STAT_ID_RX_LANES23_CHAR_ERR 0x33
+/* enum: Packets received with lanes 0 and 1 disparity error. */
+#define          MC_CMD_STAT_ID_RX_LANES01_DISP_ERR 0x34
+/* enum: Packets received with lanes 2 and 3 disparity error. */
+#define          MC_CMD_STAT_ID_RX_LANES23_DISP_ERR 0x35
+/* enum: Packets received with match fault. */
+#define          MC_CMD_STAT_ID_RX_MATCH_FAULT 0x36
+#define       MC_CMD_STAT_ID_MAC_STAT_ID_LBN 16
+#define       MC_CMD_STAT_ID_MAC_STAT_ID_WIDTH 16
+/* Include FEC stats. */
+#define       MC_CMD_STAT_ID_PHY_STAT_ID_OFST 2
+#define       MC_CMD_STAT_ID_PHY_STAT_ID_LEN 2
+/* enum property: index */
+/* enum: Number of uncorrected FEC codewords on link (RS-FEC only from Medford2
+ * onwards)
+ */
+#define          MC_CMD_STAT_ID_FEC_UNCORRECTED_ERRORS 0x1
+/* enum: Number of corrected FEC codewords on link (RS-FEC only from Medford2
+ * onwards)
+ */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_ERRORS 0x2
+/* enum: Number of corrected 10-bit symbol errors, lane 0 (RS-FEC only) */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_SYMBOLS_LANE0 0x3
+/* enum: Number of corrected 10-bit symbol errors, lane 1 (RS-FEC only) */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_SYMBOLS_LANE1 0x4
+/* enum: Number of corrected 10-bit symbol errors, lane 2 (RS-FEC only) */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_SYMBOLS_LANE2 0x5
+/* enum: Number of corrected 10-bit symbol errors, lane 3 (RS-FEC only) */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_SYMBOLS_LANE3 0x6
+#define       MC_CMD_STAT_ID_PHY_STAT_ID_LBN 16
+#define       MC_CMD_STAT_ID_PHY_STAT_ID_WIDTH 16
+
+/* MC_CMD_STAT_DESC structuredef: Structure describing the layout and size of
+ * the stats DMA buffer descriptor.
+ */
+#define    MC_CMD_STAT_DESC_LEN 8
+/* Unique identifier of the statistic. Formatted as MC_CMD_STAT_ID */
+#define       MC_CMD_STAT_DESC_STAT_ID_OFST 0
+#define       MC_CMD_STAT_DESC_STAT_ID_LEN 4
+#define       MC_CMD_STAT_DESC_STAT_ID_LBN 0
+#define       MC_CMD_STAT_DESC_STAT_ID_WIDTH 32
+/* See structuredef: MC_CMD_STAT_ID */
+#define       MC_CMD_STAT_DESC_STAT_ID_SOURCE_ID_OFST 0
+#define       MC_CMD_STAT_DESC_STAT_ID_SOURCE_ID_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_ID_SOURCE_ID_LBN 0
+#define       MC_CMD_STAT_DESC_STAT_ID_SOURCE_ID_WIDTH 16
+#define       MC_CMD_STAT_DESC_STAT_ID_MARKER_STAT_ID_OFST 2
+#define       MC_CMD_STAT_DESC_STAT_ID_MARKER_STAT_ID_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_ID_MARKER_STAT_ID_LBN 16
+#define       MC_CMD_STAT_DESC_STAT_ID_MARKER_STAT_ID_WIDTH 16
+#define       MC_CMD_STAT_DESC_STAT_ID_MAC_STAT_ID_OFST 2
+#define       MC_CMD_STAT_DESC_STAT_ID_MAC_STAT_ID_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_ID_MAC_STAT_ID_LBN 16
+#define       MC_CMD_STAT_DESC_STAT_ID_MAC_STAT_ID_WIDTH 16
+#define       MC_CMD_STAT_DESC_STAT_ID_PHY_STAT_ID_OFST 2
+#define       MC_CMD_STAT_DESC_STAT_ID_PHY_STAT_ID_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_ID_PHY_STAT_ID_LBN 16
+#define       MC_CMD_STAT_DESC_STAT_ID_PHY_STAT_ID_WIDTH 16
+/* Index of the statistic in the DMA buffer. */
+#define       MC_CMD_STAT_DESC_STAT_INDEX_OFST 4
+#define       MC_CMD_STAT_DESC_STAT_INDEX_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_INDEX_LBN 32
+#define       MC_CMD_STAT_DESC_STAT_INDEX_WIDTH 16
+/* Reserved for future extension (e.g. flags field) - currently always 0. */
+#define       MC_CMD_STAT_DESC_RESERVED_OFST 6
+#define       MC_CMD_STAT_DESC_RESERVED_LEN 2
+#define       MC_CMD_STAT_DESC_RESERVED_LBN 48
+#define       MC_CMD_STAT_DESC_RESERVED_WIDTH 16
+
+
+/***********************************/
+/* MC_CMD_MAC_STATISTICS_DESCRIPTOR
+ * Get a list of descriptors that describe the layout and size of the stats
+ * buffer required for retrieving statistics for a given port. Each entry in
+ * the list is formatted as MC_CMD_STAT_DESC and provides the ID of each stat
+ * and its location and size in the buffer. It also gives the overall minimum
+ * size of the DMA buffer required when DMA mode is used. Note that the first
+ * and last entries in the list are reserved for the generation start
+ * (MC_CMD_MARKER_STAT_GENERATION_START) and end
+ * (MC_CMD_MARKER_STAT_GENERATION_END) markers respectively, to be used for DMA
+ * synchronisation as described in the documentation for the relevant enum
+ * entries. The entries are present in the buffer even if DMA mode is not used.
+ * Provisions are made (but currently unused) for extending the size of the
+ * descriptors, extending the size of the list beyond the maximum MCDI response
+ * size, as well as the dynamic runtime updates of the list. Returns: 0 on
+ * success, ENOENT on non-existent port handle
+ */
+#define MC_CMD_MAC_STATISTICS_DESCRIPTOR 0x1e3
+#undef MC_CMD_0x1e3_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN msgrequest */
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_LEN 8
+/* Handle of port to get MAC statitstics descriptors for. */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_PORT_HANDLE_LEN 4
+/* Offset of the first entry to return, for cases where not all entries fit in
+ * the MCDI response. Should be set to 0 on initial request, and on subsequent
+ * requests updated by the number of entries already returned, as long as the
+ * MORE_ENTRIES flag is set.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_OFFSET_OFST 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_OFFSET_LEN 4
+
+/* MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT msgresponse */
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_LENMIN 28
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_LENMAX 252
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_LEN(num) (20+8*(num))
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_NUM(len) (((len)-20)/8)
+/* Generation number of the stats buffer. This is incremented each time the
+ * buffer is updated, and is used to verify the consistency of the buffer
+ * contents. Reserved for future extension (dynamic list updates). Currently
+ * always set to 0.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_GENERATION_OFST 0
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_GENERATION_LEN 4
+/* Minimum size of the DMA buffer required to retrieve all statistics for the
+ * port. This is the sum of the sizes of all the statistics, plus the size of
+ * the generation markers. Minimum buffer size in bytes required to fit all
+ * statistics. Drivers will typically round up this value to the granularity of
+ * the host DMA allocation units.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_DMA_BUFFER_SIZE_OFST 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_DMA_BUFFER_SIZE_LEN 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_FLAGS_OFST 8
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_FLAGS_LEN 4
+#define        MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_MORE_ENTRIES_OFST 8
+#define        MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_MORE_ENTRIES_LBN 0
+#define        MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_MORE_ENTRIES_WIDTH 1
+/* Size of the individual descriptor entry in the list. Determines the entry
+ * stride in the list. Currently always set to size of MC_CMD_STAT_DESC, larger
+ * values can be used in the future for extending the descriptor, by appending
+ * new data to the end of the existing structure.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRY_SIZE_OFST 12
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRY_SIZE_LEN 4
+/* Number of entries returned in the descriptor list. */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRY_COUNT_OFST 16
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRY_COUNT_LEN 4
+/* List of descriptors. Each entry is formatted as MC_CMD_STAT_DESC and
+ * provides the ID of each stat and its location and size in the buffer. The
+ * first and last entries are reserved for the generation start and end markers
+ * respectively.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_OFST 20
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LEN 8
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LO_OFST 20
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LO_LEN 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LO_LBN 160
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LO_WIDTH 32
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_HI_OFST 24
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_HI_LEN 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_HI_LBN 192
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_HI_WIDTH 32
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_MINNUM 1
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_MAXNUM 29
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_MAXNUM_MCDI2 125
+
+
+/***********************************/
+/* MC_CMD_MAC_STATISTICS
+ * Get generic MAC statistics. This call retrieves unified statistics managed
+ * by the MC. The MC will populate and provide all supported statistics in the
+ * format as returned by MC_CMD_MAC_STATISTICS_DESCRIPTOR. Refer to the
+ * aforementioned command for the format and contents of the stats DMA buffer.
+ * To ensure consistent and accurate results, it is essential for the driver to
+ * initialize the DMA buffer with zeros when DMA mode is used. Returns: 0 on
+ * success, ETIME if the DMA buffer is not ready, ENOENT on non-existent port
+ * handle, and EINVAL on invalid parameters (DMA buffer too small)
+ */
+#define MC_CMD_MAC_STATISTICS 0x1e4
+#undef MC_CMD_0x1e4_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_MAC_STATISTICS_IN msgrequest */
+#define    MC_CMD_MAC_STATISTICS_IN_LEN 20
+/* Handle of port to get MAC statistics for. */
+#define       MC_CMD_MAC_STATISTICS_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_STATISTICS_IN_PORT_HANDLE_LEN 4
+/* Contains options for querying the MAC statistics. */
+#define       MC_CMD_MAC_STATISTICS_IN_CMD_OFST 4
+#define       MC_CMD_MAC_STATISTICS_IN_CMD_LEN 4
+#define        MC_CMD_MAC_STATISTICS_IN_DMA_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_DMA_LBN 0
+#define        MC_CMD_MAC_STATISTICS_IN_DMA_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_CLEAR_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_CLEAR_LBN 1
+#define        MC_CMD_MAC_STATISTICS_IN_CLEAR_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_CHANGE_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_CHANGE_LBN 2
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_CHANGE_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_ENABLE_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_ENABLE_LBN 3
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_ENABLE_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_NOEVENT_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_NOEVENT_LBN 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_NOEVENT_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_PERIOD_MS_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIOD_MS_LBN 16
+#define        MC_CMD_MAC_STATISTICS_IN_PERIOD_MS_WIDTH 16
+/* This is the address of the DMA buffer to use for transfer of the statistics.
+ * Only valid if the DMA flag is set to 1.
+ */
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_OFST 8
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LEN 8
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LO_OFST 8
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LO_LBN 64
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_HI_OFST 12
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_HI_LBN 96
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_HI_WIDTH 32
+/* This is the length of the DMA buffer to use for the transfer of the
+ * statistics. The buffer should be at least DMA_BUFFER_SIZE long, as returned
+ * by MC_CMD_MAC_STATISTICS_DESCRIPTOR. If the supplied buffer is too small,
+ * the command will fail with EINVAL. Only valid if the DMA flag is set to 1.
+ */
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_LEN_OFST 16
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_LEN_LEN 4
+
+/* MC_CMD_MAC_STATISTICS_OUT msgresponse */
+#define    MC_CMD_MAC_STATISTICS_OUT_LENMIN 5
+#define    MC_CMD_MAC_STATISTICS_OUT_LENMAX 252
+#define    MC_CMD_MAC_STATISTICS_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_MAC_STATISTICS_OUT_LEN(num) (4+1*(num))
+#define    MC_CMD_MAC_STATISTICS_OUT_DATA_NUM(len) (((len)-4)/1)
+/* length of the data in bytes */
+#define       MC_CMD_MAC_STATISTICS_OUT_DATALEN_OFST 0
+#define       MC_CMD_MAC_STATISTICS_OUT_DATALEN_LEN 4
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_OFST 4
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_LEN 1
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_MINNUM 1
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_MAXNUM 248
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_MAXNUM_MCDI2 1016
+
+/* NET_PORT_HANDLE_DESC structuredef: Network port descriptor containing a port
+ * handle and attributes used, for example, in MC_CMD_ENUM_PORTS.
+ */
+#define    NET_PORT_HANDLE_DESC_LEN 53
+/* The handle to identify the port */
+#define       NET_PORT_HANDLE_DESC_PORT_HANDLE_OFST 0
+#define       NET_PORT_HANDLE_DESC_PORT_HANDLE_LEN 4
+#define       NET_PORT_HANDLE_DESC_PORT_HANDLE_LBN 0
+#define       NET_PORT_HANDLE_DESC_PORT_HANDLE_WIDTH 32
+/* Includes the type of port e.g. physical, virtual or MAE MPORT and other
+ * properties relevant to the port.
+ */
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_OFST 4
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LEN 8
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LO_OFST 4
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LO_LEN 4
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LO_LBN 32
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LO_WIDTH 32
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_HI_OFST 8
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_HI_LEN 4
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_HI_LBN 64
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_HI_WIDTH 32
+#define        NET_PORT_HANDLE_DESC_PORT_TYPE_OFST 4
+#define        NET_PORT_HANDLE_DESC_PORT_TYPE_LBN 0
+#define        NET_PORT_HANDLE_DESC_PORT_TYPE_WIDTH 3
+#define          NET_PORT_HANDLE_DESC_PHYSICAL 0x0 /* enum */
+#define          NET_PORT_HANDLE_DESC_VIRTUAL 0x1 /* enum */
+#define          NET_PORT_HANDLE_DESC_MPORT 0x2 /* enum */
+#define        NET_PORT_HANDLE_DESC_IS_ZOMBIE_OFST 4
+#define        NET_PORT_HANDLE_DESC_IS_ZOMBIE_LBN 8
+#define        NET_PORT_HANDLE_DESC_IS_ZOMBIE_WIDTH 1
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LBN 32
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_WIDTH 64
+/* The dynamic change that led to the port enumeration */
+#define       NET_PORT_HANDLE_DESC_ENTRY_SRC_OFST 12
+#define       NET_PORT_HANDLE_DESC_ENTRY_SRC_LEN 1
+/* enum: Indicates that the ENTRY_SRC field has not been initialized. */
+#define          NET_PORT_HANDLE_DESC_UNKNOWN 0x0
+/* enum: The port was enumerated at start of day. */
+#define          NET_PORT_HANDLE_DESC_PRESENT 0x1
+/* enum: The port was dynamically added. */
+#define          NET_PORT_HANDLE_DESC_ADDED 0x2
+/* enum: The port was dynamically deleted. */
+#define          NET_PORT_HANDLE_DESC_DELETED 0x3
+#define       NET_PORT_HANDLE_DESC_ENTRY_SRC_LBN 96
+#define       NET_PORT_HANDLE_DESC_ENTRY_SRC_WIDTH 8
+/* This is an opaque 40 byte label exposed to users as a unique identifier of
+ * the port. It is represented as a zero-terminated ASCII string and assigned
+ * by the port administrator which is typically either the firmware for a
+ * physical port or the host software responsible for creating the virtual
+ * port. The label is conveyed to the driver after assignment, which, unlike
+ * the port administrator, does not need to know how to interpret the label.
+ */
+#define       NET_PORT_HANDLE_DESC_PORT_LABEL_OFST 13
+#define       NET_PORT_HANDLE_DESC_PORT_LABEL_LEN 40
+#define       NET_PORT_HANDLE_DESC_PORT_LABEL_LBN 104
+#define       NET_PORT_HANDLE_DESC_PORT_LABEL_WIDTH 320
+
+
+/***********************************/
+/* MC_CMD_ENUM_PORTS
+ * This command returns handles for all ports present in the system. The PCIe
+ * function type of each port (either physical or virtual) is also reported.
+ * After a start-of-day port enumeration, firmware keeps track of all available
+ * ports upon creation or deletion and updates the ports if there is a change.
+ * This command is cleared after a control interface reset (e.g. FLR,
+ * ENTITY_RESET), in which case it must be called again to reenumerate the
+ * ports. The command is also clear-on-read and repeated calls will drain the
+ * buffer.
+ */
+#define MC_CMD_ENUM_PORTS 0x1e5
+#undef MC_CMD_0x1e5_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e5_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_ENUM_PORTS_IN msgrequest */
+#define    MC_CMD_ENUM_PORTS_IN_LEN 0
+
+/* MC_CMD_ENUM_PORTS_OUT msgresponse */
+#define    MC_CMD_ENUM_PORTS_OUT_LENMIN 12
+#define    MC_CMD_ENUM_PORTS_OUT_LENMAX 252
+#define    MC_CMD_ENUM_PORTS_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_ENUM_PORTS_OUT_LEN(num) (12+1*(num))
+#define    MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_NUM(len) (((len)-12)/1)
+/* Any unused flags are reserved and must be ignored. */
+#define       MC_CMD_ENUM_PORTS_OUT_FLAGS_OFST 0
+#define       MC_CMD_ENUM_PORTS_OUT_FLAGS_LEN 4
+#define        MC_CMD_ENUM_PORTS_OUT_MORE_OFST 0
+#define        MC_CMD_ENUM_PORTS_OUT_MORE_LBN 0
+#define        MC_CMD_ENUM_PORTS_OUT_MORE_WIDTH 1
+/* The number of NET_PORT_HANDLE_DESC structures in PORT_HANDLES. */
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_COUNT_OFST 4
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_COUNT_LEN 4
+#define       MC_CMD_ENUM_PORTS_OUT_SIZEOF_NET_PORT_HANDLE_DESC_OFST 8
+#define       MC_CMD_ENUM_PORTS_OUT_SIZEOF_NET_PORT_HANDLE_DESC_LEN 4
+/* Array of NET_PORT_HANDLE_DESC structures. Callers must use must use the
+ * SIZEOF_NET_PORT_HANDLE_DESC field field as the array stride between entries.
+ * This may also allow for tail padding for alignment. Fields beyond
+ * SIZEOF_NET_PORT_HANDLE_DESC are not present.
+ */
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_OFST 12
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_LEN 1
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_MINNUM 0
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_MAXNUM 240
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_MAXNUM_MCDI2 1008
+/* See structuredef: NET_PORT_HANDLE_DESC */
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_HANDLE_OFST 12
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_HANDLE_LEN 4
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_OFST 16
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LEN 8
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LO_OFST 16
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LO_LEN 4
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LO_LBN 128
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LO_WIDTH 32
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_HI_OFST 20
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_HI_LEN 4
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_HI_LBN 160
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_HI_WIDTH 32
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_TYPE_LBN 128
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_TYPE_WIDTH 3
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_IS_ZOMBIE_LBN 136
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_IS_ZOMBIE_WIDTH 1
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_ENTRY_SRC_OFST 24
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_ENTRY_SRC_LEN 1
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_LABEL_OFST 25
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_LABEL_LEN 40
+
+
+/***********************************/
+/* MC_CMD_GET_TRANSCEIVER_PROPERTIES
+ * Read properties of the transceiver associated with the port. Can be either
+ * for a fixed onboard transceiver or an inserted module. The returned data is
+ * interpreted from the transceiver hardware and may be fixed up by the
+ * firmware. Use MC_CMD_GET_MODULE_DATA to get raw undecoded data.
+ */
+#define MC_CMD_GET_TRANSCEIVER_PROPERTIES 0x1e6
+#undef MC_CMD_0x1e6_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e6_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_TRANSCEIVER_PROPERTIES_IN msgrequest */
+#define    MC_CMD_GET_TRANSCEIVER_PROPERTIES_IN_LEN 4
+/* Handle to port to get transceiver properties from. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT msgresponse */
+#define    MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_LEN 89
+/* Supported technology abilities. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_TECH_ABILITIES_MASK_OFST 0
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_TECH_ABILITIES_MASK_LEN 16
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Reserved for future expansion to accommodate future Ethernet technology
+ * expansion.
+ */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_RESERVED_OFST 16
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_RESERVED_LEN 16
+/* Preferred FEC modes. This is a function of the cable type and length. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_PREFERRED_FEC_MASK_OFST 32
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_PREFERRED_FEC_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* SFF-8042 code reported by the module. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_CODE_OFST 36
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_CODE_LEN 2
+/* Medium. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_MEDIUM_OFST 38
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_MEDIUM_LEN 1
+/* enum property: value */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_UNKNOWN 0x0 /* enum */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_COPPER 0x1 /* enum */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_OPTICAL 0x2 /* enum */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_BACKPLANE 0x3 /* enum */
+/* Identifies the tech */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_MEDIA_SUBTYPE_OFST 39
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_MEDIA_SUBTYPE_LEN 1
+/* enum property: value */
+/*               MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_UNKNOWN 0x0 */
+/* enum: Ethernet over twisted-pair copper cables for distances up to 100
+ * meters.
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_BASET 0x1
+/* enum: Ethernet over twin-axial, balanced copper cable. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_CR 0x2
+/* enum: Ethernet over backplane for connections on the same board. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_KX 0x3
+/* enum: Ethernet over a single backplane lane for connections between
+ * different boards.
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_KR 0x4
+/* enum: Ethernet over copper backplane. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_KP 0x5
+/* enum: Ethernet over fiber optic. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_BASEX 0x6
+/* enum: Short range ethernet over multimode fiber optic (See IEEE 802.3 Clause
+ * 49 and 52).
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_SR 0x7
+/* enum: Long range, extended range or far reach ethernet used with single mode
+ * fiber optics.
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_LR_ER_FR 0x8
+/* enum: Long reach multimode ethernet over multimode optical fiber. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_LRM 0x9
+/* enum: Very short reach PAM4 ethernet over multimode optical fiber (see IEEE
+ * 802.3db).
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VR 0xa
+/* enum: BASE-R encoding and PAM4 over single-mode fiber with reach up to at
+ * least 500 meters (803.2 Clause 121 and 124)
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_DR 0xb
+/* String of the vendor name as intepreted by NMC firmware. NMC firmware
+ * applies workarounds for known buggy transceivers. The vendor name is
+ * presented as 16 bytes of ASCII characters padded with spaces. It can also be
+ * represented as 16 bytes of zeros if the field is unspecified for the
+ * connected module. See SFF-8472/CMIS specifications for details.
+ */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_NAME_OFST 40
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_NAME_LEN 1
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_NAME_NUM 16
+/* The vendor part number as intepreted by NMC firmware. The field is presented
+ * as 16 bytes of ASCII chars padded with spaces. It can also be 16 bytes of
+ * zeros if the field is unspecified for the connected module.
+ */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_PN_OFST 56
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_PN_LEN 1
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_PN_NUM 16
+/* Serial number of the module presented as 16 bytes of ASCII characters padded
+ * with spaces. It can also be 16 bytes of zeros if the field is unspecified
+ * for the connected module. See SFF-8472/CMIS specifications for details.
+ */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_SERIAL_NUMBER_OFST 72
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_SERIAL_NUMBER_LEN 1
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_SERIAL_NUMBER_NUM 16
+/* This reports the number of module changes detected by the NMC firmware. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_PORT_MODULECHANGE_SEQ_NUM_OFST 88
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_PORT_MODULECHANGE_SEQ_NUM_LEN 1
+
+
+/***********************************/
+/* MC_CMD_GET_FIXED_PORT_PROPERTIES
+ */
+#define MC_CMD_GET_FIXED_PORT_PROPERTIES 0x1e7
+#undef MC_CMD_0x1e7_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e7_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_FIXED_PORT_PROPERTIES_IN msgrequest: In this context, the port
+ * consists of the MAC and the PHY, and excludes any modules inserted into the
+ * cage. This information is fixed for a given board but not for a given ASIC.
+ * This command reports properties for the port as it is currently configured,
+ * and not its hardware capabilities, which can be better than the current
+ * configuration.
+ */
+#define    MC_CMD_GET_FIXED_PORT_PROPERTIES_IN_LEN 4
+/* Handle to the port to from which to retreive properties */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT msgresponse */
+#define    MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_LEN 36
+/* Supported capabilities of the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_OFST 0
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_LEN 25
+/* See structuredef: MC_CMD_ETH_AN_FIELDS */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_TECH_MASK_OFST 0
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_TECH_MASK_LEN 16
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_FEC_MASK_OFST 16
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_FEC_MASK_LEN 4
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_FEC_REQ_OFST 20
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_FEC_REQ_LEN 4
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_PAUSE_MASK_OFST 24
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_PAUSE_MASK_LEN 1
+/* Number of lanes supported by the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_NUM_LANES_OFST 25
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_NUM_LANES_LEN 1
+/* Bitmask of supported loopback modes. Where the response to this command
+ * includes the LOOPBACK_MODES_MASK_V2 field, that field should be used in
+ * preference to ensure that all available loopback modes are seen.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_LOOPBACK_MODES_MASK_OFST 26
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_LOOPBACK_MODES_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* This field serves as a cage index that uniquely identifies the cage to which
+ * the module is connected. This is useful when splitter cables that have
+ * multiple ports on a single cage are used.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MDI_INDEX_OFST 27
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MDI_INDEX_LEN 1
+/* This bitmask is used to specify the lanes within the cage identified by
+ * MDI_INDEX that are allocated to the port.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MDI_LANE_MASK_OFST 28
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MDI_LANE_MASK_LEN 1
+/* Maximum frame length supported by the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MAX_FRAME_LEN_OFST 32
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MAX_FRAME_LEN_LEN 4
+
+/* MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2 msgresponse */
+#define    MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LEN 48
+/* Supported capabilities of the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_ABILITIES_OFST 0
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_ABILITIES_LEN 25
+/* Number of lanes supported by the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_NUM_LANES_OFST 25
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_NUM_LANES_LEN 1
+/* Bitmask of supported loopback modes. Where the response to this command
+ * includes the LOOPBACK_MODES_MASK_V2 field, that field should be used in
+ * preference to ensure that all available loopback modes are seen.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_OFST 26
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* This field serves as a cage index that uniquely identifies the cage to which
+ * the module is connected. This is useful when splitter cables that have
+ * multiple ports on a single cage are used.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MDI_INDEX_OFST 27
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MDI_INDEX_LEN 1
+/* This bitmask is used to specify the lanes within the cage identified by
+ * MDI_INDEX that are allocated to the port.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MDI_LANE_MASK_OFST 28
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MDI_LANE_MASK_LEN 1
+/* Maximum frame length supported by the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MAX_FRAME_LEN_OFST 32
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MAX_FRAME_LEN_LEN 4
+/* Bitmask of supported loopback modes. This field replaces the
+ * LOOPBACK_MODES_MASK field which is defined under version 1 of this command.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_OFST 40
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LEN 8
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LO_OFST 40
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LO_LEN 4
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LO_LBN 320
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LO_WIDTH 32
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_HI_OFST 44
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_HI_LEN 4
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_HI_LBN 352
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+
+
+/***********************************/
+/* MC_CMD_GET_MODULE_DATA
+ * Read media-specific data from the PHY (e.g. SFP/SFP+ module ID information
+ * for SFP+ PHYs). This command returns raw data from the module's EEPROM and
+ * it is not interpreted by the MC. Use MC_CMD_GET_TRANSCEIVER_PROPERTIES to
+ * get interpreted data. Return code: 0, ENOENT
+ */
+#define MC_CMD_GET_MODULE_DATA 0x1e8
+#undef MC_CMD_0x1e8_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e8_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_MODULE_DATA_IN msgrequest */
+#define    MC_CMD_GET_MODULE_DATA_IN_LEN 16
+/* Handle to identify the port from which to request module properties. */
+#define       MC_CMD_GET_MODULE_DATA_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_MODULE_DATA_IN_PORT_HANDLE_LEN 4
+/* 7 bit I2C address of the device. DEPRECATED: This field is replaced by
+ * MODULE_ADDR in V2. Use V2 of this command for proper alignment and easier
+ * access.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_DEVADDR_LBN 32
+#define       MC_CMD_GET_MODULE_DATA_IN_DEVADDR_WIDTH 7
+/* 0 if the page does not support banked access, non-zero otherwise. Non-zero
+ * BANK is valid if OFFSET is in the range 80h - ffh, i.e. in the Upper Memory
+ * region.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_BANK_OFST 6
+#define       MC_CMD_GET_MODULE_DATA_IN_BANK_LEN 2
+/* 0 if paged access is not supported, non-zero otherwise. Non-zero PAGE is
+ * valid if OFFSET is in the range 80h - ffh.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_PAGE_OFST 8
+#define       MC_CMD_GET_MODULE_DATA_IN_PAGE_LEN 2
+/* Offset in the range 00h - 7fh to access lower memory. Offset in the range
+ * 80h - ffh to access upper memory
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_OFFSET_OFST 10
+#define       MC_CMD_GET_MODULE_DATA_IN_OFFSET_LEN 1
+#define       MC_CMD_GET_MODULE_DATA_IN_LENGTH_OFST 12
+#define       MC_CMD_GET_MODULE_DATA_IN_LENGTH_LEN 4
+
+/* MC_CMD_GET_MODULE_DATA_IN_V2 msgrequest: Updated MC_CMD_GET_MODULE_DATA with
+ * 8-bit wide ADDRESSING field. This new field provides a correctly aligned
+ * container for the 7-bit DEVADDR field from V1, now renamed MODULE_ADDR, to
+ * ensure proper alignment.
+ */
+#define    MC_CMD_GET_MODULE_DATA_IN_V2_LEN 16
+/* Handle to identify the port from which to request module properties. */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_PORT_HANDLE_LEN 4
+/* 7 bit I2C address of the device. DEPRECATED: This field is replaced by
+ * MODULE_ADDR in V2. Use V2 of this command for proper alignment and easier
+ * access.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_DEVADDR_LBN 32
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_DEVADDR_WIDTH 7
+/* 0 if the page does not support banked access, non-zero otherwise. Non-zero
+ * BANK is valid if OFFSET is in the range 80h - ffh, i.e. in the Upper Memory
+ * region.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_BANK_OFST 6
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_BANK_LEN 2
+/* 0 if paged access is not supported, non-zero otherwise. Non-zero PAGE is
+ * valid if OFFSET is in the range 80h - ffh.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_PAGE_OFST 8
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_PAGE_LEN 2
+/* Offset in the range 00h - 7fh to access lower memory. Offset in the range
+ * 80h - ffh to access upper memory
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_OFFSET_OFST 10
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_OFFSET_LEN 1
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_LENGTH_OFST 12
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_LENGTH_LEN 4
+/* Container for 7 bit I2C addresses. */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_ADDRESSING_OFST 4
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_ADDRESSING_LEN 1
+#define        MC_CMD_GET_MODULE_DATA_IN_V2_MODULE_ADDR_OFST 4
+#define        MC_CMD_GET_MODULE_DATA_IN_V2_MODULE_ADDR_LBN 0
+#define        MC_CMD_GET_MODULE_DATA_IN_V2_MODULE_ADDR_WIDTH 7
+
+/* MC_CMD_GET_MODULE_DATA_OUT msgresponse */
+#define    MC_CMD_GET_MODULE_DATA_OUT_LENMIN 5
+#define    MC_CMD_GET_MODULE_DATA_OUT_LENMAX 252
+#define    MC_CMD_GET_MODULE_DATA_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_GET_MODULE_DATA_OUT_LEN(num) (4+1*(num))
+#define    MC_CMD_GET_MODULE_DATA_OUT_DATA_NUM(len) (((len)-4)/1)
+/* length of the data in bytes */
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATALEN_OFST 0
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATALEN_LEN 4
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_OFST 4
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_LEN 1
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_MINNUM 1
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_MAXNUM 248
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_MAXNUM_MCDI2 1016
+
+/* EVENT_MASK structuredef */
+#define    EVENT_MASK_LEN 4
+#define       EVENT_MASK_TYPE_OFST 0
+#define       EVENT_MASK_TYPE_LEN 4
+/* enum: PORT_LINKCHANGE event is enabled */
+#define          EVENT_MASK_PORT_LINKCHANGE 0x0
+/* enum: PORT_MODULECHANGE event is enabled */
+#define          EVENT_MASK_PORT_MODULECHANGE 0x1
+#define       EVENT_MASK_TYPE_LBN 0
+#define       EVENT_MASK_TYPE_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_SET_NETPORT_EVENTS_MASK
+ */
+#define MC_CMD_SET_NETPORT_EVENTS_MASK 0x1e9
+#undef MC_CMD_0x1e9_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e9_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_SET_NETPORT_EVENTS_MASK_IN msgrequest: Enable or disable delivery of
+ * specified network port events for a given port identified by PORT_HANDLE. At
+ * start of day, or after any control interface reset (FLR, ENTITY_RESET,
+ * etc.), all event delivery is disabled for all ports associated with the
+ * control interface.
+ */
+#define    MC_CMD_SET_NETPORT_EVENTS_MASK_IN_LEN 8
+/* Handle to port to set event delivery mask. */
+#define       MC_CMD_SET_NETPORT_EVENTS_MASK_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_SET_NETPORT_EVENTS_MASK_IN_PORT_HANDLE_LEN 4
+/* Bitmask of events to enable. Event delivery is enabled when corresponding
+ * bit is 1, disabled when 0.
+ */
+#define       MC_CMD_SET_NETPORT_EVENTS_MASK_IN_EVENT_MASK_OFST 4
+#define       MC_CMD_SET_NETPORT_EVENTS_MASK_IN_EVENT_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               EVENT_MASK/TYPE */
+
+/* MC_CMD_SET_NETPORT_EVENTS_MASK_OUT msgresponse */
+#define    MC_CMD_SET_NETPORT_EVENTS_MASK_OUT_LEN 0
+
 
 /***********************************/
-/* MC_CMD_EVENT_CTRL
- * Configure which categories of unsolicited events the driver expects to
- * receive (Riverhead).
- */
-#define MC_CMD_EVENT_CTRL 0x69
-#undef MC_CMD_0x69_PRIVILEGE_CTG
-
-#define MC_CMD_0x69_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_EVENT_CTRL_IN msgrequest */
-#define    MC_CMD_EVENT_CTRL_IN_LENMIN 0
-#define    MC_CMD_EVENT_CTRL_IN_LENMAX 252
-#define    MC_CMD_EVENT_CTRL_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_EVENT_CTRL_IN_LEN(num) (0+4*(num))
-#define    MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_NUM(len) (((len)-0)/4)
-/* Array of event categories for which the driver wishes to receive events. */
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_OFST 0
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_LEN 4
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_MINNUM 0
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_MAXNUM 63
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_MAXNUM_MCDI2 255
-/* enum: Driver wishes to receive LINKCHANGE events. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_LINKCHANGE 0x0
-/* enum: Driver wishes to receive SENSOR_CHANGE and SENSOR_STATE_CHANGE events.
- */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_SENSOREVT 0x1
-/* enum: Driver wishes to receive receive errors. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_RX_ERR 0x2
-/* enum: Driver wishes to receive transmit errors. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_TX_ERR 0x3
-/* enum: Driver wishes to receive firmware alerts. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_FWALERT 0x4
-/* enum: Driver wishes to receive reboot events. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_MC_REBOOT 0x5
-
-/* MC_CMD_EVENT_CTRL_OUT msgrequest */
-#define    MC_CMD_EVENT_CTRL_OUT_LEN 0
+/* MC_CMD_GET_NETPORT_EVENTS_MASK
+ */
+#define MC_CMD_GET_NETPORT_EVENTS_MASK 0x1ea
+#undef MC_CMD_0x1ea_PRIVILEGE_CTG
+
+#define MC_CMD_0x1ea_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_NETPORT_EVENTS_MASK_IN msgrequest: Get event delivery mask a
+ * given port identified by PORT_HANDLE.
+ */
+#define    MC_CMD_GET_NETPORT_EVENTS_MASK_IN_LEN 4
+/* Handle to port to get event deliver mask for. */
+#define       MC_CMD_GET_NETPORT_EVENTS_MASK_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_NETPORT_EVENTS_MASK_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_GET_NETPORT_EVENTS_MASK_OUT msgresponse */
+#define    MC_CMD_GET_NETPORT_EVENTS_MASK_OUT_LEN 4
+/* Bitmask of events enabled. Event delivery is enabled when corresponding bit
+ * is 1, disabled when 0.
+ */
+#define       MC_CMD_GET_NETPORT_EVENTS_MASK_OUT_EVENT_MASK_OFST 0
+#define       MC_CMD_GET_NETPORT_EVENTS_MASK_OUT_EVENT_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               EVENT_MASK/TYPE */
+
+
+/***********************************/
+/* MC_CMD_GET_SUPPORTED_NETPORT_EVENTS
+ */
+#define MC_CMD_GET_SUPPORTED_NETPORT_EVENTS 0x1eb
+#undef MC_CMD_0x1eb_PRIVILEGE_CTG
+
+#define MC_CMD_0x1eb_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_IN msgrequest: Get network port events
+ * supported by the platform. Information returned is fixed for a given NIC
+ * platform.
+ */
+#define    MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_IN_LEN 0
+
+/* MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_OUT msgresponse */
+#define    MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_OUT_LEN 4
+/* Bitmask of events enabled. Event delivery is enabled when corresponding bit
+ * is 1, disabled when 0.
+ */
+#define       MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_OUT_EVENT_MASK_OFST 0
+#define       MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_OUT_EVENT_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               EVENT_MASK/TYPE */
+
+
+/***********************************/
+/* MC_CMD_GET_NETPORT_STATISTICS
+ * Get generic MAC statistics. This call retrieves unified statistics managed
+ * by the MC. The MC will populate and provide all supported statistics in the
+ * format as returned by MC_CMD_MAC_STATISTICS_DESCRIPTOR. Refer to the
+ * aforementioned command for the format and contents of the stats DMA buffer.
+ * To ensure consistent and accurate results, it is essential for the driver to
+ * initialize the DMA buffer with zeros when DMA mode is used. Returns: 0 on
+ * success, ETIME if the DMA buffer is not ready, ENOENT on non-existent port
+ * handle, and EINVAL on invalid parameters (DMA buffer too small)
+ */
+#define MC_CMD_GET_NETPORT_STATISTICS 0x1fa
+#undef MC_CMD_0x1fa_PRIVILEGE_CTG
+
+#define MC_CMD_0x1fa_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_NETPORT_STATISTICS_IN msgrequest */
+#define    MC_CMD_GET_NETPORT_STATISTICS_IN_LEN 20
+/* Handle of port to get MAC statistics for. */
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_PORT_HANDLE_LEN 4
+/* Contains options for querying the MAC statistics. */
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_CMD_OFST 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_CMD_LEN 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_LBN 0
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_CLEAR_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_CLEAR_LBN 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_CLEAR_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_CHANGE_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_CHANGE_LBN 2
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_CHANGE_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_ENABLE_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_ENABLE_LBN 3
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_ENABLE_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_NOEVENT_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_NOEVENT_LBN 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_NOEVENT_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIOD_MS_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIOD_MS_LBN 15
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIOD_MS_WIDTH 17
+/* Specifies the physical address of the DMA buffer to use for statistics
+ * transfer. This field must contain a valid address under either of these
+ * conditions: 1. DMA flag is set (immediate DMA requested) 2. Both
+ * PERIODIC_CHANGE and PERIODIC_ENABLE are set (periodic DMA configured)
+ */
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_OFST 8
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LEN 8
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LO_OFST 8
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LO_LEN 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LO_LBN 64
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LO_WIDTH 32
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_HI_OFST 12
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_HI_LEN 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_HI_LBN 96
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_HI_WIDTH 32
+/* Specifies the length of the DMA buffer in bytes for statistics transfer. The
+ * buffer size must be at least DMA_BUFFER_SIZE bytes (as returned by
+ * MC_CMD_MAC_STATISTICS_DESCRIPTOR). Providing an insufficient buffer size
+ * will result in an EINVAL error. This field must contain a valid length under
+ * either of these conditions: 1. DMA flag is set (immediate DMA requested) 2.
+ * Both PERIODIC_CHANGE and PERIODIC_ENABLE are set (periodic DMA configured)
+ */
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_LEN_OFST 16
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_LEN_LEN 4
+
+/* MC_CMD_GET_NETPORT_STATISTICS_OUT msgresponse */
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_LENMIN 0
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_LENMAX 248
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_LENMAX_MCDI2 1016
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_LEN(num) (0+8*(num))
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_NUM(len) (((len)-0)/8)
+/* Statistics buffer. Zero-length if DMA mode is used. The statistics buffer is
+ * an array of 8-byte counter values, containing the generation start marker,
+ * stats counters, and generation end marker. The index of each counter in the
+ * array is reported by the MAC_STATISTICS_DESCRIPTOR command. The same layout
+ * is used for the DMA buffer for DMA mode stats.
+ */
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_OFST 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LEN 8
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LO_OFST 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LO_LEN 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LO_LBN 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LO_WIDTH 32
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_HI_OFST 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_HI_LEN 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_HI_LBN 32
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_HI_WIDTH 32
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_MINNUM 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_MAXNUM 31
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_MAXNUM_MCDI2 127
 
 /* EVB_PORT_ID structuredef */
 #define    EVB_PORT_ID_LEN 4
@@ -9706,44 +10573,6 @@
 #define       EVB_PORT_ID_PORT_ID_LBN 0
 #define       EVB_PORT_ID_PORT_ID_WIDTH 32
 
-/* EVB_VLAN_TAG structuredef */
-#define    EVB_VLAN_TAG_LEN 2
-/* The VLAN tag value */
-#define       EVB_VLAN_TAG_VLAN_ID_LBN 0
-#define       EVB_VLAN_TAG_VLAN_ID_WIDTH 12
-#define       EVB_VLAN_TAG_MODE_LBN 12
-#define       EVB_VLAN_TAG_MODE_WIDTH 4
-/* enum: Insert the VLAN. */
-#define          EVB_VLAN_TAG_INSERT 0x0
-/* enum: Replace the VLAN if already present. */
-#define          EVB_VLAN_TAG_REPLACE 0x1
-
-/* BUFTBL_ENTRY structuredef */
-#define    BUFTBL_ENTRY_LEN 12
-/* the owner ID */
-#define       BUFTBL_ENTRY_OID_OFST 0
-#define       BUFTBL_ENTRY_OID_LEN 2
-#define       BUFTBL_ENTRY_OID_LBN 0
-#define       BUFTBL_ENTRY_OID_WIDTH 16
-/* the page parameter as one of ESE_DZ_SMC_PAGE_SIZE_ */
-#define       BUFTBL_ENTRY_PGSZ_OFST 2
-#define       BUFTBL_ENTRY_PGSZ_LEN 2
-#define       BUFTBL_ENTRY_PGSZ_LBN 16
-#define       BUFTBL_ENTRY_PGSZ_WIDTH 16
-/* the raw 64-bit address field from the SMC, not adjusted for page size */
-#define       BUFTBL_ENTRY_RAWADDR_OFST 4
-#define       BUFTBL_ENTRY_RAWADDR_LEN 8
-#define       BUFTBL_ENTRY_RAWADDR_LO_OFST 4
-#define       BUFTBL_ENTRY_RAWADDR_LO_LEN 4
-#define       BUFTBL_ENTRY_RAWADDR_LO_LBN 32
-#define       BUFTBL_ENTRY_RAWADDR_LO_WIDTH 32
-#define       BUFTBL_ENTRY_RAWADDR_HI_OFST 8
-#define       BUFTBL_ENTRY_RAWADDR_HI_LEN 4
-#define       BUFTBL_ENTRY_RAWADDR_HI_LBN 64
-#define       BUFTBL_ENTRY_RAWADDR_HI_WIDTH 32
-#define       BUFTBL_ENTRY_RAWADDR_LBN 32
-#define       BUFTBL_ENTRY_RAWADDR_WIDTH 64
-
 /* NVRAM_PARTITION_TYPE structuredef */
 #define    NVRAM_PARTITION_TYPE_LEN 2
 #define       NVRAM_PARTITION_TYPE_ID_OFST 0
@@ -9787,6 +10616,8 @@
 #define          NVRAM_PARTITION_TYPE_NMC_LOG 0x700
 /* enum: Non-volatile log output of second core on dual-core device */
 #define          NVRAM_PARTITION_TYPE_LOG_SLAVE 0x701
+/* enum: RAM (volatile) log output partition */
+#define          NVRAM_PARTITION_TYPE_RAM_LOG 0x702
 /* enum: Device state dump output partition */
 #define          NVRAM_PARTITION_TYPE_DUMP 0x800
 /* enum: Crash log partition for NMC firmware */
@@ -9923,6 +10754,16 @@
 #define          NVRAM_PARTITION_TYPE_SUC_SOC_CONFIG 0x1f07
 /* enum: System-on-Chip update information. */
 #define          NVRAM_PARTITION_TYPE_SOC_UPDATE 0x2003
+/* enum: Virtual partition. Write-only. Writes will actually be sent to an
+ * appropriate partition (for instance BUNDLE if the data starts with the magic
+ * number for a bundle update), or discarded with an error if not recognised as
+ * a supported type.
+ */
+#define          NVRAM_PARTITION_TYPE_AUTO 0x2100
+/* enum: MC/NMC (first stage) bootloader firmware. (For X4, see XN-202072-PS
+ * and XN-202084-SW section 3.1).
+ */
+#define          NVRAM_PARTITION_TYPE_BOOTLOADER 0x2200
 /* enum: Start of reserved value range (firmware may use for any purpose) */
 #define          NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN 0xff00
 /* enum: End of reserved value range (firmware may use for any purpose) */
@@ -9981,116 +10822,6 @@
 #define       LICENSED_APP_ID_ID_LBN 0
 #define       LICENSED_APP_ID_ID_WIDTH 32
 
-/* LICENSED_FEATURES structuredef */
-#define    LICENSED_FEATURES_LEN 8
-/* Bitmask of licensed firmware features */
-#define       LICENSED_FEATURES_MASK_OFST 0
-#define       LICENSED_FEATURES_MASK_LEN 8
-#define       LICENSED_FEATURES_MASK_LO_OFST 0
-#define       LICENSED_FEATURES_MASK_LO_LEN 4
-#define       LICENSED_FEATURES_MASK_LO_LBN 0
-#define       LICENSED_FEATURES_MASK_LO_WIDTH 32
-#define       LICENSED_FEATURES_MASK_HI_OFST 4
-#define       LICENSED_FEATURES_MASK_HI_LEN 4
-#define       LICENSED_FEATURES_MASK_HI_LBN 32
-#define       LICENSED_FEATURES_MASK_HI_WIDTH 32
-#define        LICENSED_FEATURES_RX_CUT_THROUGH_OFST 0
-#define        LICENSED_FEATURES_RX_CUT_THROUGH_LBN 0
-#define        LICENSED_FEATURES_RX_CUT_THROUGH_WIDTH 1
-#define        LICENSED_FEATURES_PIO_OFST 0
-#define        LICENSED_FEATURES_PIO_LBN 1
-#define        LICENSED_FEATURES_PIO_WIDTH 1
-#define        LICENSED_FEATURES_EVQ_TIMER_OFST 0
-#define        LICENSED_FEATURES_EVQ_TIMER_LBN 2
-#define        LICENSED_FEATURES_EVQ_TIMER_WIDTH 1
-#define        LICENSED_FEATURES_CLOCK_OFST 0
-#define        LICENSED_FEATURES_CLOCK_LBN 3
-#define        LICENSED_FEATURES_CLOCK_WIDTH 1
-#define        LICENSED_FEATURES_RX_TIMESTAMPS_OFST 0
-#define        LICENSED_FEATURES_RX_TIMESTAMPS_LBN 4
-#define        LICENSED_FEATURES_RX_TIMESTAMPS_WIDTH 1
-#define        LICENSED_FEATURES_TX_TIMESTAMPS_OFST 0
-#define        LICENSED_FEATURES_TX_TIMESTAMPS_LBN 5
-#define        LICENSED_FEATURES_TX_TIMESTAMPS_WIDTH 1
-#define        LICENSED_FEATURES_RX_SNIFF_OFST 0
-#define        LICENSED_FEATURES_RX_SNIFF_LBN 6
-#define        LICENSED_FEATURES_RX_SNIFF_WIDTH 1
-#define        LICENSED_FEATURES_TX_SNIFF_OFST 0
-#define        LICENSED_FEATURES_TX_SNIFF_LBN 7
-#define        LICENSED_FEATURES_TX_SNIFF_WIDTH 1
-#define        LICENSED_FEATURES_PROXY_FILTER_OPS_OFST 0
-#define        LICENSED_FEATURES_PROXY_FILTER_OPS_LBN 8
-#define        LICENSED_FEATURES_PROXY_FILTER_OPS_WIDTH 1
-#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_OFST 0
-#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_LBN 9
-#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_WIDTH 1
-#define       LICENSED_FEATURES_MASK_LBN 0
-#define       LICENSED_FEATURES_MASK_WIDTH 64
-
-/* LICENSED_V3_APPS structuredef */
-#define    LICENSED_V3_APPS_LEN 8
-/* Bitmask of licensed applications */
-#define       LICENSED_V3_APPS_MASK_OFST 0
-#define       LICENSED_V3_APPS_MASK_LEN 8
-#define       LICENSED_V3_APPS_MASK_LO_OFST 0
-#define       LICENSED_V3_APPS_MASK_LO_LEN 4
-#define       LICENSED_V3_APPS_MASK_LO_LBN 0
-#define       LICENSED_V3_APPS_MASK_LO_WIDTH 32
-#define       LICENSED_V3_APPS_MASK_HI_OFST 4
-#define       LICENSED_V3_APPS_MASK_HI_LEN 4
-#define       LICENSED_V3_APPS_MASK_HI_LBN 32
-#define       LICENSED_V3_APPS_MASK_HI_WIDTH 32
-#define        LICENSED_V3_APPS_ONLOAD_OFST 0
-#define        LICENSED_V3_APPS_ONLOAD_LBN 0
-#define        LICENSED_V3_APPS_ONLOAD_WIDTH 1
-#define        LICENSED_V3_APPS_PTP_OFST 0
-#define        LICENSED_V3_APPS_PTP_LBN 1
-#define        LICENSED_V3_APPS_PTP_WIDTH 1
-#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_OFST 0
-#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_LBN 2
-#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_WIDTH 1
-#define        LICENSED_V3_APPS_SOLARSECURE_OFST 0
-#define        LICENSED_V3_APPS_SOLARSECURE_LBN 3
-#define        LICENSED_V3_APPS_SOLARSECURE_WIDTH 1
-#define        LICENSED_V3_APPS_PERF_MONITOR_OFST 0
-#define        LICENSED_V3_APPS_PERF_MONITOR_LBN 4
-#define        LICENSED_V3_APPS_PERF_MONITOR_WIDTH 1
-#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_OFST 0
-#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_LBN 5
-#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_WIDTH 1
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_OFST 0
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_LBN 6
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_WIDTH 1
-#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_OFST 0
-#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_LBN 7
-#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_WIDTH 1
-#define        LICENSED_V3_APPS_TCP_DIRECT_OFST 0
-#define        LICENSED_V3_APPS_TCP_DIRECT_LBN 8
-#define        LICENSED_V3_APPS_TCP_DIRECT_WIDTH 1
-#define        LICENSED_V3_APPS_LOW_LATENCY_OFST 0
-#define        LICENSED_V3_APPS_LOW_LATENCY_LBN 9
-#define        LICENSED_V3_APPS_LOW_LATENCY_WIDTH 1
-#define        LICENSED_V3_APPS_SOLARCAPTURE_TAP_OFST 0
-#define        LICENSED_V3_APPS_SOLARCAPTURE_TAP_LBN 10
-#define        LICENSED_V3_APPS_SOLARCAPTURE_TAP_WIDTH 1
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_40G_OFST 0
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_40G_LBN 11
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_40G_WIDTH 1
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_1G_OFST 0
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_1G_LBN 12
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_1G_WIDTH 1
-#define        LICENSED_V3_APPS_SCALEOUT_ONLOAD_OFST 0
-#define        LICENSED_V3_APPS_SCALEOUT_ONLOAD_LBN 13
-#define        LICENSED_V3_APPS_SCALEOUT_ONLOAD_WIDTH 1
-#define        LICENSED_V3_APPS_DSHBRD_OFST 0
-#define        LICENSED_V3_APPS_DSHBRD_LBN 14
-#define        LICENSED_V3_APPS_DSHBRD_WIDTH 1
-#define        LICENSED_V3_APPS_SCATRD_OFST 0
-#define        LICENSED_V3_APPS_SCATRD_LBN 15
-#define        LICENSED_V3_APPS_SCATRD_WIDTH 1
-#define       LICENSED_V3_APPS_MASK_LBN 0
-#define       LICENSED_V3_APPS_MASK_WIDTH 64
-
 /* LICENSED_V3_FEATURES structuredef */
 #define    LICENSED_V3_FEATURES_LEN 8
 /* Bitmask of licensed firmware features */
@@ -10199,44 +10930,6 @@
 #define       RSS_MODE_HASH_SELECTOR_LBN 0
 #define       RSS_MODE_HASH_SELECTOR_WIDTH 8
 
-/* CTPIO_STATS_MAP structuredef */
-#define    CTPIO_STATS_MAP_LEN 4
-/* The (function relative) VI number */
-#define       CTPIO_STATS_MAP_VI_OFST 0
-#define       CTPIO_STATS_MAP_VI_LEN 2
-#define       CTPIO_STATS_MAP_VI_LBN 0
-#define       CTPIO_STATS_MAP_VI_WIDTH 16
-/* The target bucket for the VI */
-#define       CTPIO_STATS_MAP_BUCKET_OFST 2
-#define       CTPIO_STATS_MAP_BUCKET_LEN 2
-#define       CTPIO_STATS_MAP_BUCKET_LBN 16
-#define       CTPIO_STATS_MAP_BUCKET_WIDTH 16
-
-
-/***********************************/
-/* MC_CMD_READ_REGS
- * Get a dump of the MCPU registers
- */
-#define MC_CMD_READ_REGS 0x50
-#undef MC_CMD_0x50_PRIVILEGE_CTG
-
-#define MC_CMD_0x50_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_READ_REGS_IN msgrequest */
-#define    MC_CMD_READ_REGS_IN_LEN 0
-
-/* MC_CMD_READ_REGS_OUT msgresponse */
-#define    MC_CMD_READ_REGS_OUT_LEN 308
-/* Whether the corresponding register entry contains a valid value */
-#define       MC_CMD_READ_REGS_OUT_MASK_OFST 0
-#define       MC_CMD_READ_REGS_OUT_MASK_LEN 16
-/* Same order as MIPS GDB (r0-r31, sr, lo, hi, bad, cause, 32 x float, fsr,
- * fir, fp)
- */
-#define       MC_CMD_READ_REGS_OUT_REGS_OFST 16
-#define       MC_CMD_READ_REGS_OUT_REGS_LEN 4
-#define       MC_CMD_READ_REGS_OUT_REGS_NUM 73
-
 
 /***********************************/
 /* MC_CMD_INIT_EVQ
@@ -10640,25 +11333,6 @@
 #define        MC_CMD_INIT_EVQ_V3_OUT_FLAG_RXQ_FORCE_EV_MERGING_LBN 3
 #define        MC_CMD_INIT_EVQ_V3_OUT_FLAG_RXQ_FORCE_EV_MERGING_WIDTH 1
 
-/* QUEUE_CRC_MODE structuredef */
-#define    QUEUE_CRC_MODE_LEN 1
-#define       QUEUE_CRC_MODE_MODE_LBN 0
-#define       QUEUE_CRC_MODE_MODE_WIDTH 4
-/* enum: No CRC. */
-#define          QUEUE_CRC_MODE_NONE 0x0
-/* enum: CRC Fiber channel over ethernet. */
-#define          QUEUE_CRC_MODE_FCOE 0x1
-/* enum: CRC (digest) iSCSI header only. */
-#define          QUEUE_CRC_MODE_ISCSI_HDR 0x2
-/* enum: CRC (digest) iSCSI header and payload. */
-#define          QUEUE_CRC_MODE_ISCSI 0x3
-/* enum: CRC Fiber channel over IP over ethernet. */
-#define          QUEUE_CRC_MODE_FCOIPOE 0x4
-/* enum: CRC MPA. */
-#define          QUEUE_CRC_MODE_MPA 0x5
-#define       QUEUE_CRC_MODE_SPARE_LBN 4
-#define       QUEUE_CRC_MODE_SPARE_WIDTH 4
-
 
 /***********************************/
 /* MC_CMD_INIT_RXQ
@@ -10827,6 +11501,9 @@
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_NO_CONT_EV_OFST 16
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_NO_CONT_EV_LBN 20
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_SUPPRESS_RX_EVENTS_OFST 16
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_SUPPRESS_RX_EVENTS_LBN 21
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_SUPPRESS_RX_EVENTS_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_EXT_IN_OWNER_ID_OFST 20
 #define       MC_CMD_INIT_RXQ_EXT_IN_OWNER_ID_LEN 4
@@ -10933,6 +11610,9 @@
 #define        MC_CMD_INIT_RXQ_V3_IN_FLAG_NO_CONT_EV_OFST 16
 #define        MC_CMD_INIT_RXQ_V3_IN_FLAG_NO_CONT_EV_LBN 20
 #define        MC_CMD_INIT_RXQ_V3_IN_FLAG_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_INIT_RXQ_V3_IN_FLAG_SUPPRESS_RX_EVENTS_OFST 16
+#define        MC_CMD_INIT_RXQ_V3_IN_FLAG_SUPPRESS_RX_EVENTS_LBN 21
+#define        MC_CMD_INIT_RXQ_V3_IN_FLAG_SUPPRESS_RX_EVENTS_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_V3_IN_OWNER_ID_OFST 20
 #define       MC_CMD_INIT_RXQ_V3_IN_OWNER_ID_LEN 4
@@ -11068,6 +11748,9 @@
 #define        MC_CMD_INIT_RXQ_V4_IN_FLAG_NO_CONT_EV_OFST 16
 #define        MC_CMD_INIT_RXQ_V4_IN_FLAG_NO_CONT_EV_LBN 20
 #define        MC_CMD_INIT_RXQ_V4_IN_FLAG_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_INIT_RXQ_V4_IN_FLAG_SUPPRESS_RX_EVENTS_OFST 16
+#define        MC_CMD_INIT_RXQ_V4_IN_FLAG_SUPPRESS_RX_EVENTS_LBN 21
+#define        MC_CMD_INIT_RXQ_V4_IN_FLAG_SUPPRESS_RX_EVENTS_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_V4_IN_OWNER_ID_OFST 20
 #define       MC_CMD_INIT_RXQ_V4_IN_OWNER_ID_LEN 4
@@ -11216,6 +11899,9 @@
 #define        MC_CMD_INIT_RXQ_V5_IN_FLAG_NO_CONT_EV_OFST 16
 #define        MC_CMD_INIT_RXQ_V5_IN_FLAG_NO_CONT_EV_LBN 20
 #define        MC_CMD_INIT_RXQ_V5_IN_FLAG_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_INIT_RXQ_V5_IN_FLAG_SUPPRESS_RX_EVENTS_OFST 16
+#define        MC_CMD_INIT_RXQ_V5_IN_FLAG_SUPPRESS_RX_EVENTS_LBN 21
+#define        MC_CMD_INIT_RXQ_V5_IN_FLAG_SUPPRESS_RX_EVENTS_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_V5_IN_OWNER_ID_OFST 20
 #define       MC_CMD_INIT_RXQ_V5_IN_OWNER_ID_LEN 4
@@ -11610,320 +12296,6 @@
 /* MC_CMD_PROXY_CMD_OUT msgresponse */
 #define    MC_CMD_PROXY_CMD_OUT_LEN 0
 
-/* MC_PROXY_STATUS_BUFFER structuredef: Host memory status buffer used to
- * manage proxied requests
- */
-#define    MC_PROXY_STATUS_BUFFER_LEN 16
-/* Handle allocated by the firmware for this proxy transaction */
-#define       MC_PROXY_STATUS_BUFFER_HANDLE_OFST 0
-#define       MC_PROXY_STATUS_BUFFER_HANDLE_LEN 4
-/* enum: An invalid handle. */
-#define          MC_PROXY_STATUS_BUFFER_HANDLE_INVALID 0x0
-#define       MC_PROXY_STATUS_BUFFER_HANDLE_LBN 0
-#define       MC_PROXY_STATUS_BUFFER_HANDLE_WIDTH 32
-/* The requesting physical function number */
-#define       MC_PROXY_STATUS_BUFFER_PF_OFST 4
-#define       MC_PROXY_STATUS_BUFFER_PF_LEN 2
-#define       MC_PROXY_STATUS_BUFFER_PF_LBN 32
-#define       MC_PROXY_STATUS_BUFFER_PF_WIDTH 16
-/* The requesting virtual function number. Set to VF_NULL if the target is a
- * PF.
- */
-#define       MC_PROXY_STATUS_BUFFER_VF_OFST 6
-#define       MC_PROXY_STATUS_BUFFER_VF_LEN 2
-#define       MC_PROXY_STATUS_BUFFER_VF_LBN 48
-#define       MC_PROXY_STATUS_BUFFER_VF_WIDTH 16
-/* The target function RID. */
-#define       MC_PROXY_STATUS_BUFFER_RID_OFST 8
-#define       MC_PROXY_STATUS_BUFFER_RID_LEN 2
-#define       MC_PROXY_STATUS_BUFFER_RID_LBN 64
-#define       MC_PROXY_STATUS_BUFFER_RID_WIDTH 16
-/* The status of the proxy as described in MC_CMD_PROXY_COMPLETE. */
-#define       MC_PROXY_STATUS_BUFFER_STATUS_OFST 10
-#define       MC_PROXY_STATUS_BUFFER_STATUS_LEN 2
-#define       MC_PROXY_STATUS_BUFFER_STATUS_LBN 80
-#define       MC_PROXY_STATUS_BUFFER_STATUS_WIDTH 16
-/* If a request is authorized rather than carried out by the host, this is the
- * elevated privilege mask granted to the requesting function.
- */
-#define       MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_OFST 12
-#define       MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_LEN 4
-#define       MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_LBN 96
-#define       MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_PROXY_CONFIGURE
- * Enable/disable authorization of MCDI requests from unprivileged functions by
- * a designated admin function
- */
-#define MC_CMD_PROXY_CONFIGURE 0x58
-#undef MC_CMD_0x58_PRIVILEGE_CTG
-
-#define MC_CMD_0x58_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PROXY_CONFIGURE_IN msgrequest */
-#define    MC_CMD_PROXY_CONFIGURE_IN_LEN 108
-#define       MC_CMD_PROXY_CONFIGURE_IN_FLAGS_OFST 0
-#define       MC_CMD_PROXY_CONFIGURE_IN_FLAGS_LEN 4
-#define        MC_CMD_PROXY_CONFIGURE_IN_ENABLE_OFST 0
-#define        MC_CMD_PROXY_CONFIGURE_IN_ENABLE_LBN 0
-#define        MC_CMD_PROXY_CONFIGURE_IN_ENABLE_WIDTH 1
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size REQUEST_BLOCK_SIZE.
- */
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_OFST 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_OFST 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_LBN 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_OFST 8
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_LBN 64
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2 */
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BLOCK_SIZE_OFST 12
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BLOCK_SIZE_LEN 4
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size REPLY_BLOCK_SIZE.
- */
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_OFST 16
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_OFST 16
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_LBN 128
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_OFST 20
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_LBN 160
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2 */
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BLOCK_SIZE_OFST 24
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BLOCK_SIZE_LEN 4
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size STATUS_BLOCK_SIZE. This buffer is only needed if
- * host intends to complete proxied operations by using MC_CMD_PROXY_CMD.
- */
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_OFST 28
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_OFST 28
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_LBN 224
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_OFST 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_LBN 256
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2, or zero if this buffer is not provided */
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BLOCK_SIZE_OFST 36
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BLOCK_SIZE_LEN 4
-/* Applies to all three buffers */
-#define       MC_CMD_PROXY_CONFIGURE_IN_NUM_BLOCKS_OFST 40
-#define       MC_CMD_PROXY_CONFIGURE_IN_NUM_BLOCKS_LEN 4
-/* A bit mask defining which MCDI operations may be proxied */
-#define       MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_OFST 44
-#define       MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_LEN 64
-
-/* MC_CMD_PROXY_CONFIGURE_EXT_IN msgrequest */
-#define    MC_CMD_PROXY_CONFIGURE_EXT_IN_LEN 112
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_FLAGS_OFST 0
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_FLAGS_LEN 4
-#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_OFST 0
-#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_LBN 0
-#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_WIDTH 1
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size REQUEST_BLOCK_SIZE.
- */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_OFST 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_OFST 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_LBN 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_OFST 8
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_LBN 64
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2 */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BLOCK_SIZE_OFST 12
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BLOCK_SIZE_LEN 4
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size REPLY_BLOCK_SIZE.
- */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_OFST 16
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_OFST 16
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_LBN 128
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_OFST 20
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_LBN 160
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2 */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BLOCK_SIZE_OFST 24
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BLOCK_SIZE_LEN 4
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size STATUS_BLOCK_SIZE. This buffer is only needed if
- * host intends to complete proxied operations by using MC_CMD_PROXY_CMD.
- */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_OFST 28
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_OFST 28
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_LBN 224
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_OFST 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_LBN 256
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2, or zero if this buffer is not provided */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BLOCK_SIZE_OFST 36
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BLOCK_SIZE_LEN 4
-/* Applies to all three buffers */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_NUM_BLOCKS_OFST 40
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_NUM_BLOCKS_LEN 4
-/* A bit mask defining which MCDI operations may be proxied */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_ALLOWED_MCDI_MASK_OFST 44
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_ALLOWED_MCDI_MASK_LEN 64
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_RESERVED_OFST 108
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_RESERVED_LEN 4
-
-/* MC_CMD_PROXY_CONFIGURE_OUT msgresponse */
-#define    MC_CMD_PROXY_CONFIGURE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_PROXY_COMPLETE
- * Tells FW that a requested proxy operation has either been completed (by
- * using MC_CMD_PROXY_CMD) or authorized/declined. May only be sent by the
- * function that enabled proxying/authorization (by using
- * MC_CMD_PROXY_CONFIGURE).
- */
-#define MC_CMD_PROXY_COMPLETE 0x5f
-#undef MC_CMD_0x5f_PRIVILEGE_CTG
-
-#define MC_CMD_0x5f_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PROXY_COMPLETE_IN msgrequest */
-#define    MC_CMD_PROXY_COMPLETE_IN_LEN 12
-#define       MC_CMD_PROXY_COMPLETE_IN_BLOCK_INDEX_OFST 0
-#define       MC_CMD_PROXY_COMPLETE_IN_BLOCK_INDEX_LEN 4
-#define       MC_CMD_PROXY_COMPLETE_IN_STATUS_OFST 4
-#define       MC_CMD_PROXY_COMPLETE_IN_STATUS_LEN 4
-/* enum: The operation has been completed by using MC_CMD_PROXY_CMD, the reply
- * is stored in the REPLY_BUFF.
- */
-#define          MC_CMD_PROXY_COMPLETE_IN_COMPLETE 0x0
-/* enum: The operation has been authorized. The originating function may now
- * try again.
- */
-#define          MC_CMD_PROXY_COMPLETE_IN_AUTHORIZED 0x1
-/* enum: The operation has been declined. */
-#define          MC_CMD_PROXY_COMPLETE_IN_DECLINED 0x2
-/* enum: The authorization failed because the relevant application did not
- * respond in time.
- */
-#define          MC_CMD_PROXY_COMPLETE_IN_TIMEDOUT 0x3
-#define       MC_CMD_PROXY_COMPLETE_IN_HANDLE_OFST 8
-#define       MC_CMD_PROXY_COMPLETE_IN_HANDLE_LEN 4
-
-/* MC_CMD_PROXY_COMPLETE_OUT msgresponse */
-#define    MC_CMD_PROXY_COMPLETE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_ALLOC_BUFTBL_CHUNK
- * Allocate a set of buffer table entries using the specified owner ID. This
- * operation allocates the required buffer table entries (and fails if it
- * cannot do so). The buffer table entries will initially be zeroed.
- */
-#define MC_CMD_ALLOC_BUFTBL_CHUNK 0x87
-#undef MC_CMD_0x87_PRIVILEGE_CTG
-
-#define MC_CMD_0x87_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_ALLOC_BUFTBL_CHUNK_IN msgrequest */
-#define    MC_CMD_ALLOC_BUFTBL_CHUNK_IN_LEN 8
-/* Owner ID to use */
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_IN_OWNER_OFST 0
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_IN_OWNER_LEN 4
-/* Size of buffer table pages to use, in bytes (note that only a few values are
- * legal on any specific hardware).
- */
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_IN_PAGE_SIZE_OFST 4
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_IN_PAGE_SIZE_LEN 4
-
-/* MC_CMD_ALLOC_BUFTBL_CHUNK_OUT msgresponse */
-#define    MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_LEN 12
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_HANDLE_OFST 0
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_HANDLE_LEN 4
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_NUMENTRIES_OFST 4
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_NUMENTRIES_LEN 4
-/* Buffer table IDs for use in DMA descriptors. */
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_ID_OFST 8
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_ID_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PROGRAM_BUFTBL_ENTRIES
- * Reprogram a set of buffer table entries in the specified chunk.
- */
-#define MC_CMD_PROGRAM_BUFTBL_ENTRIES 0x88
-#undef MC_CMD_0x88_PRIVILEGE_CTG
-
-#define MC_CMD_0x88_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN msgrequest */
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMIN 20
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMAX 268
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMAX_MCDI2 268
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LEN(num) (12+8*(num))
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_NUM(len) (((len)-12)/8)
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_HANDLE_OFST 0
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_HANDLE_LEN 4
-/* ID */
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_FIRSTID_OFST 4
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_FIRSTID_LEN 4
-/* Num entries */
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_NUMENTRIES_OFST 8
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_NUMENTRIES_LEN 4
-/* Buffer table entry address */
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_OFST 12
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LEN 8
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_OFST 12
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_LEN 4
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_LBN 96
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_WIDTH 32
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_OFST 16
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_LEN 4
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_LBN 128
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_WIDTH 32
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MINNUM 1
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MAXNUM 32
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MAXNUM_MCDI2 32
-
-/* MC_CMD_PROGRAM_BUFTBL_ENTRIES_OUT msgresponse */
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_FREE_BUFTBL_CHUNK
- */
-#define MC_CMD_FREE_BUFTBL_CHUNK 0x89
-#undef MC_CMD_0x89_PRIVILEGE_CTG
-
-#define MC_CMD_0x89_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_FREE_BUFTBL_CHUNK_IN msgrequest */
-#define    MC_CMD_FREE_BUFTBL_CHUNK_IN_LEN 4
-#define       MC_CMD_FREE_BUFTBL_CHUNK_IN_HANDLE_OFST 0
-#define       MC_CMD_FREE_BUFTBL_CHUNK_IN_HANDLE_LEN 4
-
-/* MC_CMD_FREE_BUFTBL_CHUNK_OUT msgresponse */
-#define    MC_CMD_FREE_BUFTBL_CHUNK_OUT_LEN 0
-
 
 /***********************************/
 /* MC_CMD_FILTER_OP
@@ -12822,6 +13194,10 @@
 #define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_VNIC_ENCAP_MATCHES 0x5
 /* enum: read the supported encapsulation types for the VNIC */
 #define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_VNIC_ENCAP_TYPES 0x6
+/* enum: read the supported RX filter matches for low-latency queues (as
+ * allocated by MC_CMD_ALLOC_LL_QUEUES)
+ */
+#define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_LL_RX_MATCHES 0x7
 
 /* MC_CMD_GET_PARSER_DISP_INFO_OUT msgresponse */
 #define    MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMIN 8
@@ -12860,6 +13236,48 @@
 #define        MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_DST_IP_MCAST_ONLY_LBN 0
 #define        MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_DST_IP_MCAST_ONLY_WIDTH 1
 
+/* MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT msgresponse:
+ * GET_PARSER_DISP_INFO response format for OP_GET_SECURITY_RULE_INFO.
+ * (Medford-only; for use by SolarSecure apps, not directly by drivers. See
+ * SF-114946-SW.) NOTE - this message definition is provisional. It has not yet
+ * been used in any released code and may change during development. This note
+ * will be removed once it is regarded as stable.
+ */
+#define    MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_LEN 36
+/* identifies the type of operation requested */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_OP_OFST 0
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_OP_LEN 4
+/*            Enum values, see field(s): */
+/*               MC_CMD_GET_PARSER_DISP_INFO_IN/OP */
+/* a version number representing the set of rule lookups that are implemented
+ * by the currently running firmware
+ */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_RULES_VERSION_OFST 4
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_RULES_VERSION_LEN 4
+/* enum: implements lookup sequences described in SF-114946-SW draft C */
+#define          MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_RULES_VERSION_SF_114946_SW_C 0x0
+/* the number of nodes in the subnet map */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_MAP_NUM_NODES_OFST 8
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_MAP_NUM_NODES_LEN 4
+/* the number of entries in one subnet map node */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_MAP_NUM_ENTRIES_PER_NODE_OFST 12
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_MAP_NUM_ENTRIES_PER_NODE_LEN 4
+/* minimum valid value for a subnet ID in a subnet map leaf */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_ID_MIN_OFST 16
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_ID_MIN_LEN 4
+/* maximum valid value for a subnet ID in a subnet map leaf */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_ID_MAX_OFST 20
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_ID_MAX_LEN 4
+/* the number of entries in the local and remote port range maps */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_TREE_NUM_ENTRIES_OFST 24
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_TREE_NUM_ENTRIES_LEN 4
+/* minimum valid value for a portrange ID in a port range map leaf */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_ID_MIN_OFST 28
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_ID_MIN_LEN 4
+/* maximum valid value for a portrange ID in a port range map leaf */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_ID_MAX_OFST 32
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_ID_MAX_LEN 4
+
 /* MC_CMD_GET_PARSER_DISP_VNIC_ENCAP_MATCHES_OUT msgresponse: This response is
  * returned if a MC_CMD_GET_PARSER_DISP_INFO_IN request is sent with OP value
  * OP_GET_SUPPORTED_VNIC_ENCAP_MATCHES. It contains information about the
@@ -12914,136 +13332,6 @@
 
 
 /***********************************/
-/* MC_CMD_PARSER_DISP_RW
- * Direct read/write of parser-dispatcher state (DICPUs and LUE) for debugging.
- * Please note that this interface is only of use to debug tools which have
- * knowledge of firmware and hardware data structures; nothing here is intended
- * for use by normal driver code. Note that although this command is in the
- * Admin privilege group, in tamperproof adapters, only read operations are
- * permitted.
- */
-#define MC_CMD_PARSER_DISP_RW 0xe5
-#undef MC_CMD_0xe5_PRIVILEGE_CTG
-
-#define MC_CMD_0xe5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PARSER_DISP_RW_IN msgrequest */
-#define    MC_CMD_PARSER_DISP_RW_IN_LEN 32
-/* identifies the target of the operation */
-#define       MC_CMD_PARSER_DISP_RW_IN_TARGET_OFST 0
-#define       MC_CMD_PARSER_DISP_RW_IN_TARGET_LEN 4
-/* enum: RX dispatcher CPU */
-#define          MC_CMD_PARSER_DISP_RW_IN_RX_DICPU 0x0
-/* enum: TX dispatcher CPU */
-#define          MC_CMD_PARSER_DISP_RW_IN_TX_DICPU 0x1
-/* enum: Lookup engine (with original metadata format). Deprecated; used only
- * by cmdclient as a fallback for very old Huntington firmware, and not
- * supported in firmware beyond v6.4.0.1005. Use LUE_VERSIONED_METADATA
- * instead.
- */
-#define          MC_CMD_PARSER_DISP_RW_IN_LUE 0x2
-/* enum: Lookup engine (with requested metadata format) */
-#define          MC_CMD_PARSER_DISP_RW_IN_LUE_VERSIONED_METADATA 0x3
-/* enum: RX0 dispatcher CPU (alias for RX_DICPU; Medford has 2 RX DICPUs) */
-#define          MC_CMD_PARSER_DISP_RW_IN_RX0_DICPU 0x0
-/* enum: RX1 dispatcher CPU (only valid for Medford) */
-#define          MC_CMD_PARSER_DISP_RW_IN_RX1_DICPU 0x4
-/* enum: Miscellaneous other state (only valid for Medford) */
-#define          MC_CMD_PARSER_DISP_RW_IN_MISC_STATE 0x5
-/* identifies the type of operation requested */
-#define       MC_CMD_PARSER_DISP_RW_IN_OP_OFST 4
-#define       MC_CMD_PARSER_DISP_RW_IN_OP_LEN 4
-/* enum: Read a word of DICPU DMEM or a LUE entry */
-#define          MC_CMD_PARSER_DISP_RW_IN_READ 0x0
-/* enum: Write a word of DICPU DMEM or a LUE entry. Not permitted on
- * tamperproof adapters.
- */
-#define          MC_CMD_PARSER_DISP_RW_IN_WRITE 0x1
-/* enum: Read-modify-write a word of DICPU DMEM (not valid for LUE). Not
- * permitted on tamperproof adapters.
- */
-#define          MC_CMD_PARSER_DISP_RW_IN_RMW 0x2
-/* data memory address (DICPU targets) or LUE index (LUE targets) */
-#define       MC_CMD_PARSER_DISP_RW_IN_ADDRESS_OFST 8
-#define       MC_CMD_PARSER_DISP_RW_IN_ADDRESS_LEN 4
-/* selector (for MISC_STATE target) */
-#define       MC_CMD_PARSER_DISP_RW_IN_SELECTOR_OFST 8
-#define       MC_CMD_PARSER_DISP_RW_IN_SELECTOR_LEN 4
-/* enum: Port to datapath mapping */
-#define          MC_CMD_PARSER_DISP_RW_IN_PORT_DP_MAPPING 0x1
-/* value to write (for DMEM writes) */
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_WRITE_VALUE_OFST 12
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_WRITE_VALUE_LEN 4
-/* XOR value (for DMEM read-modify-writes: new = (old & mask) ^ value) */
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_XOR_VALUE_OFST 12
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_XOR_VALUE_LEN 4
-/* AND mask (for DMEM read-modify-writes: new = (old & mask) ^ value) */
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_AND_MASK_OFST 16
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_AND_MASK_LEN 4
-/* metadata format (for LUE reads using LUE_VERSIONED_METADATA) */
-#define       MC_CMD_PARSER_DISP_RW_IN_LUE_READ_METADATA_VERSION_OFST 12
-#define       MC_CMD_PARSER_DISP_RW_IN_LUE_READ_METADATA_VERSION_LEN 4
-/* value to write (for LUE writes) */
-#define       MC_CMD_PARSER_DISP_RW_IN_LUE_WRITE_VALUE_OFST 12
-#define       MC_CMD_PARSER_DISP_RW_IN_LUE_WRITE_VALUE_LEN 20
-
-/* MC_CMD_PARSER_DISP_RW_OUT msgresponse */
-#define    MC_CMD_PARSER_DISP_RW_OUT_LEN 52
-/* value read (for DMEM reads) */
-#define       MC_CMD_PARSER_DISP_RW_OUT_DMEM_READ_VALUE_OFST 0
-#define       MC_CMD_PARSER_DISP_RW_OUT_DMEM_READ_VALUE_LEN 4
-/* value read (for LUE reads) */
-#define       MC_CMD_PARSER_DISP_RW_OUT_LUE_READ_VALUE_OFST 0
-#define       MC_CMD_PARSER_DISP_RW_OUT_LUE_READ_VALUE_LEN 20
-/* up to 8 32-bit words of additional soft state from the LUE manager (the
- * exact content is firmware-dependent and intended only for debug use)
- */
-#define       MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_OFST 20
-#define       MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_LEN 32
-/* datapath(s) used for each port (for MISC_STATE PORT_DP_MAPPING selector) */
-#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_OFST 0
-#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_LEN 4
-#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_NUM 4
-#define          MC_CMD_PARSER_DISP_RW_OUT_DP0 0x1 /* enum */
-#define          MC_CMD_PARSER_DISP_RW_OUT_DP1 0x2 /* enum */
-
-
-/***********************************/
-/* MC_CMD_GET_PF_COUNT
- * Get number of PFs on the device.
- */
-#define MC_CMD_GET_PF_COUNT 0xb6
-#undef MC_CMD_0xb6_PRIVILEGE_CTG
-
-#define MC_CMD_0xb6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PF_COUNT_IN msgrequest */
-#define    MC_CMD_GET_PF_COUNT_IN_LEN 0
-
-/* MC_CMD_GET_PF_COUNT_OUT msgresponse */
-#define    MC_CMD_GET_PF_COUNT_OUT_LEN 1
-/* Identifies the number of PFs on the device. */
-#define       MC_CMD_GET_PF_COUNT_OUT_PF_COUNT_OFST 0
-#define       MC_CMD_GET_PF_COUNT_OUT_PF_COUNT_LEN 1
-
-
-/***********************************/
-/* MC_CMD_SET_PF_COUNT
- * Set number of PFs on the device.
- */
-#define MC_CMD_SET_PF_COUNT 0xb7
-
-/* MC_CMD_SET_PF_COUNT_IN msgrequest */
-#define    MC_CMD_SET_PF_COUNT_IN_LEN 4
-/* New number of PFs on the device. */
-#define       MC_CMD_SET_PF_COUNT_IN_PF_COUNT_OFST 0
-#define       MC_CMD_SET_PF_COUNT_IN_PF_COUNT_LEN 4
-
-/* MC_CMD_SET_PF_COUNT_OUT msgresponse */
-#define    MC_CMD_SET_PF_COUNT_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_GET_PORT_ASSIGNMENT
  * Get port assignment for current PCI function.
  */
@@ -13069,25 +13357,6 @@
 
 
 /***********************************/
-/* MC_CMD_SET_PORT_ASSIGNMENT
- * Set port assignment for current PCI function.
- */
-#define MC_CMD_SET_PORT_ASSIGNMENT 0xb9
-#undef MC_CMD_0xb9_PRIVILEGE_CTG
-
-#define MC_CMD_0xb9_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_PORT_ASSIGNMENT_IN msgrequest */
-#define    MC_CMD_SET_PORT_ASSIGNMENT_IN_LEN 4
-/* Identifies the port assignment for this function. */
-#define       MC_CMD_SET_PORT_ASSIGNMENT_IN_PORT_OFST 0
-#define       MC_CMD_SET_PORT_ASSIGNMENT_IN_PORT_LEN 4
-
-/* MC_CMD_SET_PORT_ASSIGNMENT_OUT msgresponse */
-#define    MC_CMD_SET_PORT_ASSIGNMENT_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_ALLOC_VIS
  * Allocate VIs for current PCI function.
  */
@@ -13184,263 +13453,6 @@
 
 
 /***********************************/
-/* MC_CMD_SET_SRIOV_CFG
- * Set SRIOV config for this PF.
- */
-#define MC_CMD_SET_SRIOV_CFG 0xbb
-#undef MC_CMD_0xbb_PRIVILEGE_CTG
-
-#define MC_CMD_0xbb_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_SRIOV_CFG_IN msgrequest */
-#define    MC_CMD_SET_SRIOV_CFG_IN_LEN 20
-/* Number of VFs currently enabled. */
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_CURRENT_OFST 0
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_CURRENT_LEN 4
-/* Max number of VFs before sriov stride and offset may need to be changed. */
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_MAX_OFST 4
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_MAX_LEN 4
-#define       MC_CMD_SET_SRIOV_CFG_IN_FLAGS_OFST 8
-#define       MC_CMD_SET_SRIOV_CFG_IN_FLAGS_LEN 4
-#define        MC_CMD_SET_SRIOV_CFG_IN_VF_ENABLED_OFST 8
-#define        MC_CMD_SET_SRIOV_CFG_IN_VF_ENABLED_LBN 0
-#define        MC_CMD_SET_SRIOV_CFG_IN_VF_ENABLED_WIDTH 1
-/* RID offset of first VF from PF, or 0 for no change, or
- * MC_CMD_RESOURCE_INSTANCE_ANY to allow the system to allocate an offset.
- */
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_OFFSET_OFST 12
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_OFFSET_LEN 4
-/* RID offset of each subsequent VF from the previous, 0 for no change, or
- * MC_CMD_RESOURCE_INSTANCE_ANY to allow the system to allocate a stride.
- */
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_STRIDE_OFST 16
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_STRIDE_LEN 4
-
-/* MC_CMD_SET_SRIOV_CFG_OUT msgresponse */
-#define    MC_CMD_SET_SRIOV_CFG_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_VI_ALLOC_INFO
- * Get information about number of VI's and base VI number allocated to this
- * function. This message is not available to dynamic clients created by
- * MC_CMD_CLIENT_ALLOC.
- */
-#define MC_CMD_GET_VI_ALLOC_INFO 0x8d
-#undef MC_CMD_0x8d_PRIVILEGE_CTG
-
-#define MC_CMD_0x8d_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_VI_ALLOC_INFO_IN msgrequest */
-#define    MC_CMD_GET_VI_ALLOC_INFO_IN_LEN 0
-
-/* MC_CMD_GET_VI_ALLOC_INFO_OUT msgresponse */
-#define    MC_CMD_GET_VI_ALLOC_INFO_OUT_LEN 12
-/* The number of VIs allocated on this function */
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_COUNT_OFST 0
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_COUNT_LEN 4
-/* The base absolute VI number allocated to this function. Required to
- * correctly interpret wakeup events.
- */
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_BASE_OFST 4
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_BASE_LEN 4
-/* Function's port vi_shift value (always 0 on Huntington) */
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_SHIFT_OFST 8
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_SHIFT_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DUMP_VI_STATE
- * For CmdClient use. Dump pertinent information on a specific absolute VI. The
- * VI must be owned by the calling client or one of its ancestors; usership of
- * the VI (as set by MC_CMD_SET_VI_USER) is not sufficient.
- */
-#define MC_CMD_DUMP_VI_STATE 0x8e
-#undef MC_CMD_0x8e_PRIVILEGE_CTG
-
-#define MC_CMD_0x8e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_DUMP_VI_STATE_IN msgrequest */
-#define    MC_CMD_DUMP_VI_STATE_IN_LEN 4
-/* The VI number to query. */
-#define       MC_CMD_DUMP_VI_STATE_IN_VI_NUMBER_OFST 0
-#define       MC_CMD_DUMP_VI_STATE_IN_VI_NUMBER_LEN 4
-
-/* MC_CMD_DUMP_VI_STATE_OUT msgresponse */
-#define    MC_CMD_DUMP_VI_STATE_OUT_LEN 100
-/* The PF part of the function owning this VI. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_OWNER_PF_OFST 0
-#define       MC_CMD_DUMP_VI_STATE_OUT_OWNER_PF_LEN 2
-/* The VF part of the function owning this VI. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_OWNER_VF_OFST 2
-#define       MC_CMD_DUMP_VI_STATE_OUT_OWNER_VF_LEN 2
-/* Base of VIs allocated to this function. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_BASE_OFST 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_BASE_LEN 2
-/* Count of VIs allocated to the owner function. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_COUNT_OFST 6
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_COUNT_LEN 2
-/* Base interrupt vector allocated to this function. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_BASE_OFST 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_BASE_LEN 2
-/* Number of interrupt vectors allocated to this function. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_COUNT_OFST 10
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_COUNT_LEN 2
-/* Raw evq ptr table data. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_OFST 12
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_OFST 12
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_LBN 96
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_OFST 16
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_LBN 128
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_WIDTH 32
-/* Raw evq timer table data. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_OFST 20
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_OFST 20
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_LBN 160
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_OFST 24
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_LBN 192
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_WIDTH 32
-/* Combined metadata field. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_OFST 28
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_LEN 4
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_BASE_OFST 28
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_BASE_LBN 0
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_BASE_WIDTH 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_NPAGES_OFST 28
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_NPAGES_LBN 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_NPAGES_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_WKUP_REF_OFST 28
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_WKUP_REF_LBN 24
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_WKUP_REF_WIDTH 8
-/* TXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_OFST 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_OFST 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_LBN 256
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_OFST 36
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_LBN 288
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_WIDTH 32
-/* TXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_OFST 40
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_OFST 40
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_LBN 320
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_OFST 44
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_LBN 352
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_WIDTH 32
-/* TXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_OFST 48
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_OFST 48
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_LBN 384
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_OFST 52
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_LBN 416
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_WIDTH 32
-/* Combined metadata field. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_OFST 56
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_OFST 56
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_LBN 448
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_OFST 60
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_LBN 480
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_WIDTH 32
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_BASE_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_BASE_LBN 0
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_BASE_WIDTH 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_NPAGES_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_NPAGES_LBN 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_NPAGES_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_QSTATE_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_QSTATE_LBN 24
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_QSTATE_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_WAITCOUNT_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_WAITCOUNT_LBN 32
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_WAITCOUNT_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_PADDING_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_PADDING_LBN 40
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_PADDING_WIDTH 24
-/* RXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_OFST 64
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_OFST 64
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_LBN 512
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_OFST 68
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_LBN 544
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_WIDTH 32
-/* RXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_OFST 72
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_OFST 72
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_LBN 576
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_OFST 76
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_LBN 608
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_WIDTH 32
-/* Reserved, currently 0. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_OFST 80
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_OFST 80
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_LBN 640
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_OFST 84
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_LBN 672
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_WIDTH 32
-/* Combined metadata field. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_OFST 88
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_OFST 88
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_LBN 704
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_OFST 92
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_LBN 736
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_WIDTH 32
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_BASE_OFST 88
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_BASE_LBN 0
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_BASE_WIDTH 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_NPAGES_OFST 88
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_NPAGES_LBN 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_NPAGES_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_QSTATE_OFST 88
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_QSTATE_LBN 24
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_QSTATE_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_WAITCOUNT_OFST 88
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_WAITCOUNT_LBN 32
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_WAITCOUNT_WIDTH 8
-/* Current user, as assigned by MC_CMD_SET_VI_USER. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_USER_CLIENT_ID_OFST 96
-#define       MC_CMD_DUMP_VI_STATE_OUT_USER_CLIENT_ID_LEN 4
-
-
-/***********************************/
 /* MC_CMD_ALLOC_PIOBUF
  * Allocate a push I/O buffer for later use with a tx queue.
  */
@@ -13491,354 +13503,102 @@
 
 /* MC_CMD_GET_VI_TLP_PROCESSING_IN msgrequest */
 #define    MC_CMD_GET_VI_TLP_PROCESSING_IN_LEN 4
-/* VI number to get information for. */
+/* Queue handle, encodes queue type and VI number to get information for. */
 #define       MC_CMD_GET_VI_TLP_PROCESSING_IN_INSTANCE_OFST 0
 #define       MC_CMD_GET_VI_TLP_PROCESSING_IN_INSTANCE_LEN 4
 
-/* MC_CMD_GET_VI_TLP_PROCESSING_OUT msgresponse */
-#define    MC_CMD_GET_VI_TLP_PROCESSING_OUT_LEN 4
-/* Transaction processing steering hint 1 for use with the Rx Queue. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG1_RX_OFST 0
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG1_RX_LEN 1
-/* Transaction processing steering hint 2 for use with the Ev Queue. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG2_EV_OFST 1
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG2_EV_LEN 1
-/* Use Relaxed ordering model for TLPs on this VI. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_RELAXED_ORDERING_LBN 16
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_RELAXED_ORDERING_WIDTH 1
-/* Use ID based ordering for TLPs on this VI. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_ID_BASED_ORDERING_LBN 17
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_ID_BASED_ORDERING_WIDTH 1
-/* Set no snoop bit for TLPs on this VI. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_NO_SNOOP_LBN 18
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_NO_SNOOP_WIDTH 1
-/* Enable TPH for TLPs on this VI. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_ON_LBN 19
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_ON_WIDTH 1
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_DATA_OFST 0
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_DATA_LEN 4
+/* MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT msgresponse: This message has the same
+ * layout as GET_VI_TLP_PROCESSING_OUT, but with corrected field ordering to
+ * simplify use in drivers
+ */
+#define    MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_LEN 4
+#define       MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_DATA_OFST 0
+#define       MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_DATA_LEN 4
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG1_RX_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG1_RX_LBN 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG1_RX_WIDTH 8
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG2_EV_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG2_EV_LBN 8
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG2_EV_WIDTH 8
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_LBN 16
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_PACKET_DATA_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_PACKET_DATA_LBN 16
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_PACKET_DATA_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_ID_BASED_ORDERING_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_ID_BASED_ORDERING_LBN 17
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_ID_BASED_ORDERING_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_NO_SNOOP_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_NO_SNOOP_LBN 18
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_NO_SNOOP_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_ON_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_ON_LBN 19
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_ON_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_SYNC_DATA_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_SYNC_DATA_LBN 20
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_SYNC_DATA_WIDTH 1
 
 
 /***********************************/
 /* MC_CMD_SET_VI_TLP_PROCESSING
  * Set TLP steering and ordering information for a VI. The caller must have the
  * GRP_FUNC_DMA privilege and must be the currently-assigned user of this VI or
- * an ancestor of the current user (see MC_CMD_SET_VI_USER).
+ * an ancestor of the current user (see MC_CMD_SET_VI_USER). Note that LL
+ * queues require this to be called after allocation but before initialisation
+ * of the queue. TLP options of a queue are fixed after queue is initialised,
+ * with the values set to current global value or they can be overriden using
+ * this command. At LL queue allocation, all overrides are cleared.
  */
 #define MC_CMD_SET_VI_TLP_PROCESSING 0xb1
 #undef MC_CMD_0xb1_PRIVILEGE_CTG
 
 #define MC_CMD_0xb1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
 
-/* MC_CMD_SET_VI_TLP_PROCESSING_IN msgrequest */
-#define    MC_CMD_SET_VI_TLP_PROCESSING_IN_LEN 8
-/* VI number to set information for. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_INSTANCE_OFST 0
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_INSTANCE_LEN 4
-/* Transaction processing steering hint 1 for use with the Rx Queue. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG1_RX_OFST 4
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG1_RX_LEN 1
-/* Transaction processing steering hint 2 for use with the Ev Queue. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG2_EV_OFST 5
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG2_EV_LEN 1
-/* Use Relaxed ordering model for TLPs on this VI. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_RELAXED_ORDERING_LBN 48
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_RELAXED_ORDERING_WIDTH 1
-/* Use ID based ordering for TLPs on this VI. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_ID_BASED_ORDERING_LBN 49
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_ID_BASED_ORDERING_WIDTH 1
-/* Set the no snoop bit for TLPs on this VI. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_NO_SNOOP_LBN 50
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_NO_SNOOP_WIDTH 1
-/* Enable TPH for TLPs on this VI. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_ON_LBN 51
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_ON_WIDTH 1
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_DATA_OFST 4
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_DATA_LEN 4
+/* MC_CMD_SET_VI_TLP_PROCESSING_V2_IN msgrequest: This message has the same
+ * layout as SET_VI_TLP_PROCESSING_OUT, but with corrected field ordering to
+ * simplify use in drivers.
+ */
+#define    MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_LEN 8
+/* Queue handle, encodes queue type and VI number to set information for. */
+#define       MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_INSTANCE_OFST 0
+#define       MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_INSTANCE_LEN 4
+#define       MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_DATA_OFST 4
+#define       MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_DATA_LEN 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG1_RX_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG1_RX_LBN 0
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG1_RX_WIDTH 8
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG2_EV_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG2_EV_LBN 8
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG2_EV_WIDTH 8
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_LBN 16
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_PACKET_DATA_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_PACKET_DATA_LBN 16
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_PACKET_DATA_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_ID_BASED_ORDERING_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_ID_BASED_ORDERING_LBN 17
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_ID_BASED_ORDERING_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_NO_SNOOP_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_NO_SNOOP_LBN 18
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_NO_SNOOP_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_ON_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_ON_LBN 19
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_ON_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_SYNC_DATA_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_SYNC_DATA_LBN 20
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_SYNC_DATA_WIDTH 1
 
 /* MC_CMD_SET_VI_TLP_PROCESSING_OUT msgresponse */
 #define    MC_CMD_SET_VI_TLP_PROCESSING_OUT_LEN 0
 
 
 /***********************************/
-/* MC_CMD_GET_TLP_PROCESSING_GLOBALS
- * Get global PCIe steering and transaction processing configuration.
- */
-#define MC_CMD_GET_TLP_PROCESSING_GLOBALS 0xbc
-#undef MC_CMD_0xbc_PRIVILEGE_CTG
-
-#define MC_CMD_0xbc_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN msgrequest */
-#define    MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_LEN 4
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_OFST 0
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_LEN 4
-/* enum: MISC. */
-#define          MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_MISC 0x0
-/* enum: IDO. */
-#define          MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_IDO 0x1
-/* enum: RO. */
-#define          MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_RO 0x2
-/* enum: TPH Type. */
-#define          MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_TPH_TYPE 0x3
-
-/* MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT msgresponse */
-#define    MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_LEN 8
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_GLOBAL_CATEGORY_OFST 0
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_GLOBAL_CATEGORY_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN/TLP_GLOBAL_CATEGORY */
-/* Amalgamated TLP info word. */
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_WORD_OFST 4
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_WORD_LEN 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_WTAG_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_WTAG_EN_LBN 0
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_WTAG_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_SPARE_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_SPARE_LBN 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_SPARE_WIDTH 31
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_DL_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_DL_EN_LBN 0
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_DL_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_TX_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_TX_EN_LBN 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_TX_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_EV_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_EV_EN_LBN 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_EV_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_RX_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_RX_EN_LBN 3
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_RX_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_SPARE_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_SPARE_LBN 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_SPARE_WIDTH 28
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_RXDMA_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_RXDMA_EN_LBN 0
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_RXDMA_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_TXDMA_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_TXDMA_EN_LBN 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_TXDMA_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_DL_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_DL_EN_LBN 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_DL_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_SPARE_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_SPARE_LBN 3
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_SPARE_WIDTH 29
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_MSIX_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_MSIX_LBN 0
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_MSIX_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_DL_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_DL_LBN 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_DL_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_TX_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_TX_LBN 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_TX_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_EV_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_EV_LBN 6
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_EV_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_RX_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_RX_LBN 8
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_RX_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TLP_TYPE_SPARE_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TLP_TYPE_SPARE_LBN 9
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TLP_TYPE_SPARE_WIDTH 23
-
-
-/***********************************/
-/* MC_CMD_SET_TLP_PROCESSING_GLOBALS
- * Set global PCIe steering and transaction processing configuration.
- */
-#define MC_CMD_SET_TLP_PROCESSING_GLOBALS 0xbd
-#undef MC_CMD_0xbd_PRIVILEGE_CTG
-
-#define MC_CMD_0xbd_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN msgrequest */
-#define    MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_LEN 8
-#define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_OFST 0
-#define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_GET_TLP_PROCESSING_GLOBALS/MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN/TLP_GLOBAL_CATEGORY */
-/* Amalgamated TLP info word. */
-#define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_WORD_OFST 4
-#define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_WORD_LEN 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_MISC_WTAG_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_MISC_WTAG_EN_LBN 0
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_MISC_WTAG_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_DL_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_DL_EN_LBN 0
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_DL_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_TX_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_TX_EN_LBN 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_TX_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_EV_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_EV_EN_LBN 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_EV_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_RX_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_RX_EN_LBN 3
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_RX_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_RXDMA_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_RXDMA_EN_LBN 0
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_RXDMA_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_TXDMA_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_TXDMA_EN_LBN 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_TXDMA_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_DL_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_DL_EN_LBN 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_DL_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_MSIX_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_MSIX_LBN 0
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_MSIX_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_DL_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_DL_LBN 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_DL_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_TX_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_TX_LBN 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_TX_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_EV_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_EV_LBN 6
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_EV_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_RX_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_RX_LBN 8
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_RX_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_SPARE_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_SPARE_LBN 10
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_SPARE_WIDTH 22
-
-/* MC_CMD_SET_TLP_PROCESSING_GLOBALS_OUT msgresponse */
-#define    MC_CMD_SET_TLP_PROCESSING_GLOBALS_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_SATELLITE_DOWNLOAD
- * Download a new set of images to the satellite CPUs from the host.
- */
-#define MC_CMD_SATELLITE_DOWNLOAD 0x91
-#undef MC_CMD_0x91_PRIVILEGE_CTG
-
-#define MC_CMD_0x91_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SATELLITE_DOWNLOAD_IN msgrequest: The reset requirements for the CPUs
- * are subtle, and so downloads must proceed in a number of phases.
- *
- * 1) PHASE_RESET with a target of TARGET_ALL and chunk ID/length of 0.
- *
- * 2) PHASE_IMEMS for each of the IMEM targets (target IDs 0-11). Each download
- * may consist of multiple chunks. The final chunk (with CHUNK_ID_LAST) should
- * be a checksum (a simple 32-bit sum) of the transferred data. An individual
- * download may be aborted using CHUNK_ID_ABORT.
- *
- * 3) PHASE_VECTORS for each of the vector table targets (target IDs 12-15),
- * similar to PHASE_IMEMS.
- *
- * 4) PHASE_READY with a target of TARGET_ALL and chunk ID/length of 0.
- *
- * After any error (a requested abort is not considered to be an error) the
- * sequence must be restarted from PHASE_RESET.
- */
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_LENMIN 20
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_LENMAX 252
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_LEN(num) (16+4*(num))
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_NUM(len) (((len)-16)/4)
-/* Download phase. (Note: the IDLE phase is used internally and is never valid
- * in a command from the host.)
- */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_OFST 0
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_LEN 4
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_IDLE 0x0 /* enum */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_RESET 0x1 /* enum */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_IMEMS 0x2 /* enum */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_VECTORS 0x3 /* enum */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_READY 0x4 /* enum */
-/* Target for download. (These match the blob numbers defined in
- * mc_flash_layout.h.)
- */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_OFST 4
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_LEN 4
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_TEXT 0x0
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_TEXT 0x1
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDP_TEXT 0x2
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDP_TEXT 0x3
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_LUT 0x4
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_LUT_CFG 0x5
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_LUT 0x6
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_LUT_CFG 0x7
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_PGM 0x8
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_SL_PGM 0x9
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_PGM 0xa
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_SL_PGM 0xb
-/* enum: Valid in phase 3 (PHASE_VECTORS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_VTBL0 0xc
-/* enum: Valid in phase 3 (PHASE_VECTORS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_VTBL0 0xd
-/* enum: Valid in phase 3 (PHASE_VECTORS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_VTBL1 0xe
-/* enum: Valid in phase 3 (PHASE_VECTORS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_VTBL1 0xf
-/* enum: Valid in phases 1 (PHASE_RESET) and 4 (PHASE_READY) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_ALL 0xffffffff
-/* Chunk ID, or CHUNK_ID_LAST or CHUNK_ID_ABORT */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_OFST 8
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_LEN 4
-/* enum: Last chunk, containing checksum rather than data */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_LAST 0xffffffff
-/* enum: Abort download of this item */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_ABORT 0xfffffffe
-/* Length of this chunk in bytes */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_LEN_OFST 12
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_LEN_LEN 4
-/* Data for this chunk */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_OFST 16
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_LEN 4
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_MINNUM 1
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_MAXNUM 59
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_MAXNUM_MCDI2 251
-
-/* MC_CMD_SATELLITE_DOWNLOAD_OUT msgresponse */
-#define    MC_CMD_SATELLITE_DOWNLOAD_OUT_LEN 8
-/* Same as MC_CMD_ERR field, but included as 0 in success cases */
-#define       MC_CMD_SATELLITE_DOWNLOAD_OUT_RESULT_OFST 0
-#define       MC_CMD_SATELLITE_DOWNLOAD_OUT_RESULT_LEN 4
-/* Extra status information */
-#define       MC_CMD_SATELLITE_DOWNLOAD_OUT_INFO_OFST 4
-#define       MC_CMD_SATELLITE_DOWNLOAD_OUT_INFO_LEN 4
-/* enum: Code download OK, completed. */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_COMPLETE 0x0
-/* enum: Code download aborted as requested. */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_ABORTED 0x1
-/* enum: Code download OK so far, send next chunk. */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_NEXT_CHUNK 0x2
-/* enum: Download phases out of sequence */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_PHASE 0x100
-/* enum: Bad target for this phase */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_TARGET 0x101
-/* enum: Chunk ID out of sequence */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHUNK_ID 0x200
-/* enum: Chunk length zero or too large */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHUNK_LEN 0x201
-/* enum: Checksum was incorrect */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHECKSUM 0x300
-
-
-/***********************************/
 /* MC_CMD_GET_CAPABILITIES
- * Get device capabilities.
- *
- * This is supplementary to the MC_CMD_GET_BOARD_CFG command, and intended to
- * reference inherent device capabilities as opposed to current NVRAM config.
+ * Get device capabilities. This is supplementary to the MC_CMD_GET_BOARD_CFG
+ * command, and intended to reference inherent device capabilities as opposed
+ * to current NVRAM config.
  */
 #define MC_CMD_GET_CAPABILITIES 0xbe
 #undef MC_CMD_0xbe_PRIVILEGE_CTG
@@ -14490,7 +14250,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -14900,7 +14663,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V3_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V3_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -15335,7 +15101,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V4_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V4_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -15778,7 +15547,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V5_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V5_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -16226,7 +15998,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V6_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V6_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -16685,7 +16460,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V7_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V7_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -16796,9 +16574,21 @@
 #define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
 #define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
 #define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
 #define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
 #define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CXL_CONFIG_ENABLE_WIDTH 1
 
 /* MC_CMD_GET_CAPABILITIES_V8_OUT msgresponse */
 #define    MC_CMD_GET_CAPABILITIES_V8_OUT_LEN 160
@@ -17189,7 +16979,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V8_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V8_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -17300,9 +17093,21 @@
 #define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
 #define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
 #define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
 #define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
 #define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CXL_CONFIG_ENABLE_WIDTH 1
 /* These bits are reserved for communicating test-specific capabilities to
  * host-side test software. All production drivers should treat this field as
  * opaque.
@@ -17707,7 +17512,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V9_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V9_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -17818,9 +17626,21 @@
 #define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
 #define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
 #define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
 #define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
 #define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CXL_CONFIG_ENABLE_WIDTH 1
 /* These bits are reserved for communicating test-specific capabilities to
  * host-side test software. All production drivers should treat this field as
  * opaque.
@@ -18260,7 +18080,10 @@
 /*               MC_CMD_GET_CAPABILITIES_V10_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
 /*               MC_CMD_GET_CAPABILITIES_V10_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
 #define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_OFST 58
 #define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_LEN 2
 #define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_NUM 4
@@ -18371,9 +18194,21 @@
 #define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
 #define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
 #define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
 #define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
 #define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CXL_CONFIG_ENABLE_WIDTH 1
 /* These bits are reserved for communicating test-specific capabilities to
  * host-side test software. All production drivers should treat this field as
  * opaque.
@@ -18438,6 +18273,1182 @@
 #define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_QUEUE_SIZES_OFST 188
 #define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_QUEUE_SIZES_LEN 4
 
+/* MC_CMD_GET_CAPABILITIES_V11_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V11_OUT_LEN 196
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VXLAN_NVGRE_WIDTH 1
+/* RxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DPCPU_FW_ID_LEN 2
+/* enum: Standard RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP 0x0
+/* enum: Low latency RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_LOW_LATENCY 0x1
+/* enum: Packed stream RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_PACKED_STREAM 0x2
+/* enum: Rules engine RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_RULES_ENGINE 0x5
+/* enum: DPDK RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_DPDK 0x6
+/* enum: BIST RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_BIST 0x10a
+/* enum: RXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+/* enum: RXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+/* enum: RXDP Test firmware image 3 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+/* enum: RXDP Test firmware image 4 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+/* enum: RXDP Test firmware image 5 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_BACKPRESSURE 0x105
+/* enum: RXDP Test firmware image 6 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+/* enum: RXDP Test firmware image 7 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+/* enum: RXDP Test firmware image 8 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+/* enum: RXDP Test firmware image 9 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+/* enum: RXDP Test firmware image 10 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_SLOW 0x10c
+/* TxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_DPCPU_FW_ID_LEN 2
+/* enum: Standard TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP 0x0
+/* enum: Low latency TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_LOW_LATENCY 0x1
+/* enum: High packet rate TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_HIGH_PACKET_RATE 0x3
+/* enum: Rules engine TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_RULES_ENGINE 0x5
+/* enum: DPDK TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_DPDK 0x6
+/* enum: BIST TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_BIST 0x12d
+/* enum: TXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+/* enum: TXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+/* enum: TXDP CSR bus test firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial RX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: RX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant RX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+/* enum: Low latency RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+/* enum: Packed stream RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+/* enum: RX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* enum: RX PD firmware parsing but not filtering network overlay tunnel
+ * encapsulations (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial TX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: TX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant TX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+/* enum: TX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* Hardware capabilities of NIC */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_HW_CAPABILITIES_LEN 4
+/* Licensed capabilities */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_LICENSE_CAPABILITIES_LEN 4
+/* Second word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+/* Number of FATSOv2 contexts per datapath supported by this NIC (when
+ * TX_TSO_V2 == 1). Not present on older firmware (check the length).
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+/* One byte per PF containing the number of the external port assigned to this
+ * PF, indexed by PF number. Special values indicate that a PF is either not
+ * present or not assigned.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_ACCESS_NOT_PERMITTED 0xff
+/* enum: PF does not exist. */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_PF_NOT_PRESENT 0xfe
+/* enum: PF does exist but is not assigned to any external port. */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_PF_NOT_ASSIGNED 0xfd
+/* enum: This value indicates that PF is assigned, but it cannot be expressed
+ * in this field. It is intended for a possible future situation where a more
+ * complex scheme of PFs to ports mapping is being used. The future driver
+ * should look for a new field supporting the new scheme. The current/old
+ * driver should treat this value as PF_NOT_ASSIGNED.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+/* One byte per PF containing the number of its VFs, indexed by PF number. A
+ * special value indicates that a PF is not present.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VFS_PER_PF_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+/*               MC_CMD_GET_CAPABILITIES_V11_OUT_ACCESS_NOT_PERMITTED 0xff */
+/* enum: PF does not exist. */
+/*               MC_CMD_GET_CAPABILITIES_V11_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VIS_PER_PORT_NUM 4
+/* Size of RX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ RX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DESC_CACHE_SIZE_LEN 1
+/* Size of TX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ TX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_DESC_CACHE_SIZE_LEN 1
+/* Total number of available PIO buffers */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_PIO_BUFFS_LEN 2
+/* Size of a single PIO buffer */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_SIZE_PIO_BUFF_LEN 2
+/* On chips later than Medford the amount of address space assigned to each VI
+ * is configurable. This is a global setting that the driver must query to
+ * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
+ * with 8k VI windows.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_LEN 1
+/* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
+ * CTPIO is not mapped.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_8K 0x0
+/* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_16K 0x1
+/* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_64K 0x2
+/* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+/* Number of buffers per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+/* Entry count in the MAC stats array, including the final GENERATION_END
+ * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
+ * hold at least this many 64-bit stats values, if they wish to receive all
+ * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
+ * stats array returned will be truncated.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_NUM_STATS_LEN 2
+/* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
+ * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+/* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
+ * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
+ * they create an RX queue. Due to hardware limitations, only a small number of
+ * different buffer sizes may be available concurrently. Nonzero entries in
+ * this array are the sizes of buffers which the system guarantees will be
+ * available for use. If the list is empty, there are no limitations on
+ * concurrent buffer sizes.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
+/* Third word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS3_OFST 148
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS3_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_WOL_ETHERWAKE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_WOL_ETHERWAKE_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_WOL_ETHERWAKE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_EVEN_SPREADING_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_EVEN_SPREADING_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_EVEN_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_SUPPORTED_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VDPA_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VDPA_SUPPORTED_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VDPA_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CXL_CONFIG_ENABLE_WIDTH 1
+/* These bits are reserved for communicating test-specific capabilities to
+ * host-side test software. All production drivers should treat this field as
+ * opaque.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LEN 8
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LO_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LO_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LO_LBN 1216
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LO_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_HI_OFST 156
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_HI_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_HI_LBN 1248
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_HI_WIDTH 32
+/* The minimum size (in table entries) of indirection table to be allocated
+ * from the pool for an RSS context. Note that the table size used must be a
+ * power of 2.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_OFST 160
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_LEN 4
+/* The maximum size (in table entries) of indirection table to be allocated
+ * from the pool for an RSS context. Note that the table size used must be a
+ * power of 2.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_OFST 164
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_LEN 4
+/* The maximum number of queues that can be used by an RSS context in exclusive
+ * mode. In exclusive mode the context has a configurable indirection table and
+ * a configurable RSS key.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_INDIRECTION_QUEUES_OFST 168
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_INDIRECTION_QUEUES_LEN 4
+/* The maximum number of queues that can be used by an RSS context in even-
+ * spreading mode. In even-spreading mode the context has no indirection table
+ * but it does have a configurable RSS key.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_OFST 172
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_LEN 4
+/* The total number of RSS contexts supported. Note that the number of
+ * available contexts using indirection tables is also limited by the
+ * availability of indirection table space allocated from a common pool.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_NUM_CONTEXTS_OFST 176
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_NUM_CONTEXTS_LEN 4
+/* The total amount of indirection table space that can be shared between RSS
+ * contexts.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_TABLE_POOL_SIZE_OFST 180
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_TABLE_POOL_SIZE_LEN 4
+/* A bitmap of the queue sizes the device can provide, where bit N being set
+ * indicates that 2**N is a valid size. The device may be limited in the number
+ * of different queue sizes that can exist simultaneously, so a bit being set
+ * here does not guarantee that an attempt to create a queue of that size will
+ * succeed.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_SUPPORTED_QUEUE_SIZES_OFST 184
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_SUPPORTED_QUEUE_SIZES_LEN 4
+/* A bitmap of queue sizes that are always available, in the same format as
+ * SUPPORTED_QUEUE_SIZES. Attempting to create a queue with one of these sizes
+ * will never fail due to unavailability of the requested size.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_QUEUE_SIZES_OFST 188
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_QUEUE_SIZES_LEN 4
+/* Number of available indirect memory maps. */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_INDIRECT_MAP_INDEX_COUNT_OFST 192
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_INDIRECT_MAP_INDEX_COUNT_LEN 4
+
+/* MC_CMD_GET_CAPABILITIES_V12_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V12_OUT_LEN 204
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VXLAN_NVGRE_WIDTH 1
+/* RxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DPCPU_FW_ID_LEN 2
+/* enum: Standard RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP 0x0
+/* enum: Low latency RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_LOW_LATENCY 0x1
+/* enum: Packed stream RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_PACKED_STREAM 0x2
+/* enum: Rules engine RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_RULES_ENGINE 0x5
+/* enum: DPDK RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_DPDK 0x6
+/* enum: BIST RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_BIST 0x10a
+/* enum: RXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+/* enum: RXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+/* enum: RXDP Test firmware image 3 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+/* enum: RXDP Test firmware image 4 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+/* enum: RXDP Test firmware image 5 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_BACKPRESSURE 0x105
+/* enum: RXDP Test firmware image 6 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+/* enum: RXDP Test firmware image 7 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+/* enum: RXDP Test firmware image 8 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+/* enum: RXDP Test firmware image 9 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+/* enum: RXDP Test firmware image 10 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_SLOW 0x10c
+/* TxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_DPCPU_FW_ID_LEN 2
+/* enum: Standard TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP 0x0
+/* enum: Low latency TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_LOW_LATENCY 0x1
+/* enum: High packet rate TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_HIGH_PACKET_RATE 0x3
+/* enum: Rules engine TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_RULES_ENGINE 0x5
+/* enum: DPDK TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_DPDK 0x6
+/* enum: BIST TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_BIST 0x12d
+/* enum: TXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+/* enum: TXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+/* enum: TXDP CSR bus test firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial RX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: RX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant RX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+/* enum: Low latency RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+/* enum: Packed stream RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+/* enum: RX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* enum: RX PD firmware parsing but not filtering network overlay tunnel
+ * encapsulations (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial TX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: TX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant TX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+/* enum: TX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* Hardware capabilities of NIC */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_HW_CAPABILITIES_LEN 4
+/* Licensed capabilities */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_LICENSE_CAPABILITIES_LEN 4
+/* Second word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+/* Number of FATSOv2 contexts per datapath supported by this NIC (when
+ * TX_TSO_V2 == 1). Not present on older firmware (check the length).
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+/* One byte per PF containing the number of the external port assigned to this
+ * PF, indexed by PF number. Special values indicate that a PF is either not
+ * present or not assigned.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_ACCESS_NOT_PERMITTED 0xff
+/* enum: PF does not exist. */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_PF_NOT_PRESENT 0xfe
+/* enum: PF does exist but is not assigned to any external port. */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_PF_NOT_ASSIGNED 0xfd
+/* enum: This value indicates that PF is assigned, but it cannot be expressed
+ * in this field. It is intended for a possible future situation where a more
+ * complex scheme of PFs to ports mapping is being used. The future driver
+ * should look for a new field supporting the new scheme. The current/old
+ * driver should treat this value as PF_NOT_ASSIGNED.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+/* One byte per PF containing the number of its VFs, indexed by PF number. A
+ * special value indicates that a PF is not present.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VFS_PER_PF_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+/*               MC_CMD_GET_CAPABILITIES_V12_OUT_ACCESS_NOT_PERMITTED 0xff */
+/* enum: PF does not exist. */
+/*               MC_CMD_GET_CAPABILITIES_V12_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT_NUM 4
+/* Size of RX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ RX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DESC_CACHE_SIZE_LEN 1
+/* Size of TX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ TX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_DESC_CACHE_SIZE_LEN 1
+/* Total number of available PIO buffers */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_PIO_BUFFS_LEN 2
+/* Size of a single PIO buffer */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_SIZE_PIO_BUFF_LEN 2
+/* On chips later than Medford the amount of address space assigned to each VI
+ * is configurable. This is a global setting that the driver must query to
+ * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
+ * with 8k VI windows.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_LEN 1
+/* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
+ * CTPIO is not mapped.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_8K 0x0
+/* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_16K 0x1
+/* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_64K 0x2
+/* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+/* Number of buffers per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+/* Entry count in the MAC stats array, including the final GENERATION_END
+ * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
+ * hold at least this many 64-bit stats values, if they wish to receive all
+ * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
+ * stats array returned will be truncated.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_NUM_STATS_LEN 2
+/* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
+ * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+/* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
+ * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
+ * they create an RX queue. Due to hardware limitations, only a small number of
+ * different buffer sizes may be available concurrently. Nonzero entries in
+ * this array are the sizes of buffers which the system guarantees will be
+ * available for use. If the list is empty, there are no limitations on
+ * concurrent buffer sizes.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
+/* Third word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS3_OFST 148
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS3_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_WOL_ETHERWAKE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_WOL_ETHERWAKE_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_WOL_ETHERWAKE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_EVEN_SPREADING_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_EVEN_SPREADING_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_EVEN_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_SUPPORTED_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VDPA_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VDPA_SUPPORTED_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VDPA_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CXL_CONFIG_ENABLE_WIDTH 1
+/* These bits are reserved for communicating test-specific capabilities to
+ * host-side test software. All production drivers should treat this field as
+ * opaque.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LEN 8
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LO_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LO_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LO_LBN 1216
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LO_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_HI_OFST 156
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_HI_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_HI_LBN 1248
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_HI_WIDTH 32
+/* The minimum size (in table entries) of indirection table to be allocated
+ * from the pool for an RSS context. Note that the table size used must be a
+ * power of 2.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_OFST 160
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_LEN 4
+/* The maximum size (in table entries) of indirection table to be allocated
+ * from the pool for an RSS context. Note that the table size used must be a
+ * power of 2.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_OFST 164
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_LEN 4
+/* The maximum number of queues that can be used by an RSS context in exclusive
+ * mode. In exclusive mode the context has a configurable indirection table and
+ * a configurable RSS key.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_INDIRECTION_QUEUES_OFST 168
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_INDIRECTION_QUEUES_LEN 4
+/* The maximum number of queues that can be used by an RSS context in even-
+ * spreading mode. In even-spreading mode the context has no indirection table
+ * but it does have a configurable RSS key.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_OFST 172
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_LEN 4
+/* The total number of RSS contexts supported. Note that the number of
+ * available contexts using indirection tables is also limited by the
+ * availability of indirection table space allocated from a common pool.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_NUM_CONTEXTS_OFST 176
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_NUM_CONTEXTS_LEN 4
+/* The total amount of indirection table space that can be shared between RSS
+ * contexts.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_TABLE_POOL_SIZE_OFST 180
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_TABLE_POOL_SIZE_LEN 4
+/* A bitmap of the queue sizes the device can provide, where bit N being set
+ * indicates that 2**N is a valid size. The device may be limited in the number
+ * of different queue sizes that can exist simultaneously, so a bit being set
+ * here does not guarantee that an attempt to create a queue of that size will
+ * succeed.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_SUPPORTED_QUEUE_SIZES_OFST 184
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_SUPPORTED_QUEUE_SIZES_LEN 4
+/* A bitmap of queue sizes that are always available, in the same format as
+ * SUPPORTED_QUEUE_SIZES. Attempting to create a queue with one of these sizes
+ * will never fail due to unavailability of the requested size.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_QUEUE_SIZES_OFST 188
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_QUEUE_SIZES_LEN 4
+/* Number of available indirect memory maps. */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_INDIRECT_MAP_INDEX_COUNT_OFST 192
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_INDIRECT_MAP_INDEX_COUNT_LEN 4
+/* Number of VIs available for external ports 4-7. Information for ports 0-3 is
+ * in NUM_VIS_PER_PORT in GET_CAPABILITIES_V2_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT2_OFST 196
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT2_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT2_NUM 4
+
 
 /***********************************/
 /* MC_CMD_V2_EXTN
@@ -18468,168 +19479,13 @@
  * are not defined.
  */
 #define          MC_CMD_V2_EXTN_IN_MCDI_MESSAGE_TYPE_TSA 0x1
-
-
-/***********************************/
-/* MC_CMD_TCM_BUCKET_ALLOC
- * Allocate a pacer bucket (for qau rp or a snapper test)
+/* enum: MCDI command used for platform management. Typically, these commands
+ * are used for low-level operations directed at the platform as a whole (e.g.
+ * MMIO device enumeration) rather than individual functions and use a
+ * dedicated comms channel (e.g. RPmsg/IPI). May be handled by the same or
+ * different CPU as MCDI_MESSAGE_TYPE_MC.
  */
-#define MC_CMD_TCM_BUCKET_ALLOC 0xb2
-#undef MC_CMD_0xb2_PRIVILEGE_CTG
-
-#define MC_CMD_0xb2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TCM_BUCKET_ALLOC_IN msgrequest */
-#define    MC_CMD_TCM_BUCKET_ALLOC_IN_LEN 0
-
-/* MC_CMD_TCM_BUCKET_ALLOC_OUT msgresponse */
-#define    MC_CMD_TCM_BUCKET_ALLOC_OUT_LEN 4
-/* the bucket id */
-#define       MC_CMD_TCM_BUCKET_ALLOC_OUT_BUCKET_OFST 0
-#define       MC_CMD_TCM_BUCKET_ALLOC_OUT_BUCKET_LEN 4
-
-
-/***********************************/
-/* MC_CMD_TCM_BUCKET_FREE
- * Free a pacer bucket
- */
-#define MC_CMD_TCM_BUCKET_FREE 0xb3
-#undef MC_CMD_0xb3_PRIVILEGE_CTG
-
-#define MC_CMD_0xb3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TCM_BUCKET_FREE_IN msgrequest */
-#define    MC_CMD_TCM_BUCKET_FREE_IN_LEN 4
-/* the bucket id */
-#define       MC_CMD_TCM_BUCKET_FREE_IN_BUCKET_OFST 0
-#define       MC_CMD_TCM_BUCKET_FREE_IN_BUCKET_LEN 4
-
-/* MC_CMD_TCM_BUCKET_FREE_OUT msgresponse */
-#define    MC_CMD_TCM_BUCKET_FREE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_TCM_BUCKET_INIT
- * Initialise pacer bucket with a given rate
- */
-#define MC_CMD_TCM_BUCKET_INIT 0xb4
-#undef MC_CMD_0xb4_PRIVILEGE_CTG
-
-#define MC_CMD_0xb4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TCM_BUCKET_INIT_IN msgrequest */
-#define    MC_CMD_TCM_BUCKET_INIT_IN_LEN 8
-/* the bucket id */
-#define       MC_CMD_TCM_BUCKET_INIT_IN_BUCKET_OFST 0
-#define       MC_CMD_TCM_BUCKET_INIT_IN_BUCKET_LEN 4
-/* the rate in mbps */
-#define       MC_CMD_TCM_BUCKET_INIT_IN_RATE_OFST 4
-#define       MC_CMD_TCM_BUCKET_INIT_IN_RATE_LEN 4
-
-/* MC_CMD_TCM_BUCKET_INIT_EXT_IN msgrequest */
-#define    MC_CMD_TCM_BUCKET_INIT_EXT_IN_LEN 12
-/* the bucket id */
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_BUCKET_OFST 0
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_BUCKET_LEN 4
-/* the rate in mbps */
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_RATE_OFST 4
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_RATE_LEN 4
-/* the desired maximum fill level */
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_MAX_FILL_OFST 8
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_MAX_FILL_LEN 4
-
-/* MC_CMD_TCM_BUCKET_INIT_OUT msgresponse */
-#define    MC_CMD_TCM_BUCKET_INIT_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_TCM_TXQ_INIT
- * Initialise txq in pacer with given options or set options
- */
-#define MC_CMD_TCM_TXQ_INIT 0xb5
-#undef MC_CMD_0xb5_PRIVILEGE_CTG
-
-#define MC_CMD_0xb5_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TCM_TXQ_INIT_IN msgrequest */
-#define    MC_CMD_TCM_TXQ_INIT_IN_LEN 28
-/* the txq id */
-#define       MC_CMD_TCM_TXQ_INIT_IN_QID_OFST 0
-#define       MC_CMD_TCM_TXQ_INIT_IN_QID_LEN 4
-/* the static priority associated with the txq */
-#define       MC_CMD_TCM_TXQ_INIT_IN_LABEL_OFST 4
-#define       MC_CMD_TCM_TXQ_INIT_IN_LABEL_LEN 4
-/* bitmask of the priority queues this txq is inserted into when inserted. */
-#define       MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAGS_OFST 8
-#define       MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAGS_LEN 4
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_GUARANTEED_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_GUARANTEED_LBN 0
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_GUARANTEED_WIDTH 1
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_NORMAL_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_NORMAL_LBN 1
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_NORMAL_WIDTH 1
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_LOW_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_LOW_LBN 2
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_LOW_WIDTH 1
-/* the reaction point (RP) bucket */
-#define       MC_CMD_TCM_TXQ_INIT_IN_RP_BKT_OFST 12
-#define       MC_CMD_TCM_TXQ_INIT_IN_RP_BKT_LEN 4
-/* an already reserved bucket (typically set to bucket associated with outer
- * vswitch)
- */
-#define       MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT1_OFST 16
-#define       MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT1_LEN 4
-/* an already reserved bucket (typically set to bucket associated with inner
- * vswitch)
- */
-#define       MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT2_OFST 20
-#define       MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT2_LEN 4
-/* the min bucket (typically for ETS/minimum bandwidth) */
-#define       MC_CMD_TCM_TXQ_INIT_IN_MIN_BKT_OFST 24
-#define       MC_CMD_TCM_TXQ_INIT_IN_MIN_BKT_LEN 4
-
-/* MC_CMD_TCM_TXQ_INIT_EXT_IN msgrequest */
-#define    MC_CMD_TCM_TXQ_INIT_EXT_IN_LEN 32
-/* the txq id */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_QID_OFST 0
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_QID_LEN 4
-/* the static priority associated with the txq */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_NORMAL_OFST 4
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_NORMAL_LEN 4
-/* bitmask of the priority queues this txq is inserted into when inserted. */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAGS_OFST 8
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAGS_LEN 4
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_GUARANTEED_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_GUARANTEED_LBN 0
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_GUARANTEED_WIDTH 1
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_NORMAL_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_NORMAL_LBN 1
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_NORMAL_WIDTH 1
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_LOW_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_LOW_LBN 2
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_LOW_WIDTH 1
-/* the reaction point (RP) bucket */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_RP_BKT_OFST 12
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_RP_BKT_LEN 4
-/* an already reserved bucket (typically set to bucket associated with outer
- * vswitch)
- */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT1_OFST 16
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT1_LEN 4
-/* an already reserved bucket (typically set to bucket associated with inner
- * vswitch)
- */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT2_OFST 20
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT2_LEN 4
-/* the min bucket (typically for ETS/minimum bandwidth) */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MIN_BKT_OFST 24
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MIN_BKT_LEN 4
-/* the static priority associated with the txq */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_GUARANTEED_OFST 28
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_GUARANTEED_LEN 4
-
-/* MC_CMD_TCM_TXQ_INIT_OUT msgresponse */
-#define    MC_CMD_TCM_TXQ_INIT_OUT_LEN 0
+#define          MC_CMD_V2_EXTN_IN_MCDI_MESSAGE_TYPE_PLATFORM 0x2
 
 
 /***********************************/
@@ -18740,27 +19596,6 @@
 
 
 /***********************************/
-/* MC_CMD_VSWITCH_QUERY
- * read some config of v-switch. For now this command is an empty placeholder.
- * It may be used to check if a v-switch is connected to a given EVB port (if
- * not, then the command returns ENOENT).
- */
-#define MC_CMD_VSWITCH_QUERY 0x63
-#undef MC_CMD_0x63_PRIVILEGE_CTG
-
-#define MC_CMD_0x63_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VSWITCH_QUERY_IN msgrequest */
-#define    MC_CMD_VSWITCH_QUERY_IN_LEN 4
-/* The port to which the v-switch is connected. */
-#define       MC_CMD_VSWITCH_QUERY_IN_UPSTREAM_PORT_ID_OFST 0
-#define       MC_CMD_VSWITCH_QUERY_IN_UPSTREAM_PORT_ID_LEN 4
-
-/* MC_CMD_VSWITCH_QUERY_OUT msgresponse */
-#define    MC_CMD_VSWITCH_QUERY_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_VPORT_ALLOC
  * allocate a v-port.
  */
@@ -18936,28 +19771,6 @@
 
 
 /***********************************/
-/* MC_CMD_VADAPTOR_GET_MAC
- * read the MAC address assigned to a v-adaptor.
- */
-#define MC_CMD_VADAPTOR_GET_MAC 0x5e
-#undef MC_CMD_0x5e_PRIVILEGE_CTG
-
-#define MC_CMD_0x5e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VADAPTOR_GET_MAC_IN msgrequest */
-#define    MC_CMD_VADAPTOR_GET_MAC_IN_LEN 4
-/* The port to which the v-adaptor is connected. */
-#define       MC_CMD_VADAPTOR_GET_MAC_IN_UPSTREAM_PORT_ID_OFST 0
-#define       MC_CMD_VADAPTOR_GET_MAC_IN_UPSTREAM_PORT_ID_LEN 4
-
-/* MC_CMD_VADAPTOR_GET_MAC_OUT msgresponse */
-#define    MC_CMD_VADAPTOR_GET_MAC_OUT_LEN 6
-/* The MAC address assigned to this v-adaptor */
-#define       MC_CMD_VADAPTOR_GET_MAC_OUT_MACADDR_OFST 0
-#define       MC_CMD_VADAPTOR_GET_MAC_OUT_MACADDR_LEN 6
-
-
-/***********************************/
 /* MC_CMD_VADAPTOR_QUERY
  * read some config of v-adaptor.
  */
@@ -19014,86 +19827,6 @@
 
 
 /***********************************/
-/* MC_CMD_RDWR_A64_REGIONS
- * Assign the 64 bit region addresses.
- */
-#define MC_CMD_RDWR_A64_REGIONS 0x9b
-#undef MC_CMD_0x9b_PRIVILEGE_CTG
-
-#define MC_CMD_0x9b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_RDWR_A64_REGIONS_IN msgrequest */
-#define    MC_CMD_RDWR_A64_REGIONS_IN_LEN 17
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION0_OFST 0
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION0_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION1_OFST 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION1_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION2_OFST 8
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION2_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION3_OFST 12
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION3_LEN 4
-/* Write enable bits 0-3, set to write, clear to read. */
-#define       MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_LBN 128
-#define       MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_WIDTH 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_BYTE_OFST 16
-#define       MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_BYTE_LEN 1
-
-/* MC_CMD_RDWR_A64_REGIONS_OUT msgresponse: This data always included
- * regardless of state of write bits in the request.
- */
-#define    MC_CMD_RDWR_A64_REGIONS_OUT_LEN 16
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION0_OFST 0
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION0_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION1_OFST 4
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION1_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION2_OFST 8
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION2_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION3_OFST 12
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION3_LEN 4
-
-
-/***********************************/
-/* MC_CMD_ONLOAD_STACK_ALLOC
- * Allocate an Onload stack ID.
- */
-#define MC_CMD_ONLOAD_STACK_ALLOC 0x9c
-#undef MC_CMD_0x9c_PRIVILEGE_CTG
-
-#define MC_CMD_0x9c_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_ONLOAD_STACK_ALLOC_IN msgrequest */
-#define    MC_CMD_ONLOAD_STACK_ALLOC_IN_LEN 4
-/* The handle of the owning upstream port */
-#define       MC_CMD_ONLOAD_STACK_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
-#define       MC_CMD_ONLOAD_STACK_ALLOC_IN_UPSTREAM_PORT_ID_LEN 4
-
-/* MC_CMD_ONLOAD_STACK_ALLOC_OUT msgresponse */
-#define    MC_CMD_ONLOAD_STACK_ALLOC_OUT_LEN 4
-/* The handle of the new Onload stack */
-#define       MC_CMD_ONLOAD_STACK_ALLOC_OUT_ONLOAD_STACK_ID_OFST 0
-#define       MC_CMD_ONLOAD_STACK_ALLOC_OUT_ONLOAD_STACK_ID_LEN 4
-
-
-/***********************************/
-/* MC_CMD_ONLOAD_STACK_FREE
- * Free an Onload stack ID.
- */
-#define MC_CMD_ONLOAD_STACK_FREE 0x9d
-#undef MC_CMD_0x9d_PRIVILEGE_CTG
-
-#define MC_CMD_0x9d_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_ONLOAD_STACK_FREE_IN msgrequest */
-#define    MC_CMD_ONLOAD_STACK_FREE_IN_LEN 4
-/* The handle of the Onload stack */
-#define       MC_CMD_ONLOAD_STACK_FREE_IN_ONLOAD_STACK_ID_OFST 0
-#define       MC_CMD_ONLOAD_STACK_FREE_IN_ONLOAD_STACK_ID_LEN 4
-
-/* MC_CMD_ONLOAD_STACK_FREE_OUT msgresponse */
-#define    MC_CMD_ONLOAD_STACK_FREE_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_RSS_CONTEXT_ALLOC
  * Allocate an RSS context.
  */
@@ -19305,93 +20038,6 @@
 
 
 /***********************************/
-/* MC_CMD_RSS_CONTEXT_WRITE_TABLE
- * Write a portion of a selectable-size indirection table for an RSS context.
- * This command must be used instead of MC_CMD_RSS_CONTEXT_SET_TABLE if the
- * RSS_SELECTABLE_TABLE_SIZE bit is set in MC_CMD_GET_CAPABILITIES.
- */
-#define MC_CMD_RSS_CONTEXT_WRITE_TABLE 0x13e
-#undef MC_CMD_0x13e_PRIVILEGE_CTG
-
-#define MC_CMD_0x13e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN msgrequest */
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_LENMIN 8
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_LENMAX 252
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_LEN(num) (4+4*(num))
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_NUM(len) (((len)-4)/4)
-/* The handle of the RSS context */
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_RSS_CONTEXT_ID_OFST 0
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_RSS_CONTEXT_ID_LEN 4
-/* An array of index-value pairs to be written to the table. Structure is
- * MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY.
- */
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_OFST 4
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_LEN 4
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_MINNUM 1
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_MAXNUM 62
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_MAXNUM_MCDI2 254
-
-/* MC_CMD_RSS_CONTEXT_WRITE_TABLE_OUT msgresponse */
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_OUT_LEN 0
-
-/* MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY structuredef */
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_LEN 4
-/* The index of the table entry to be written. */
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_INDEX_OFST 0
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_INDEX_LEN 2
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_INDEX_LBN 0
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_INDEX_WIDTH 16
-/* The value to write into the table entry. */
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_VALUE_OFST 2
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_VALUE_LEN 2
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_VALUE_LBN 16
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_VALUE_WIDTH 16
-
-
-/***********************************/
-/* MC_CMD_RSS_CONTEXT_READ_TABLE
- * Read a portion of a selectable-size indirection table for an RSS context.
- * This command must be used instead of MC_CMD_RSS_CONTEXT_GET_TABLE if the
- * RSS_SELECTABLE_TABLE_SIZE bit is set in MC_CMD_GET_CAPABILITIES.
- */
-#define MC_CMD_RSS_CONTEXT_READ_TABLE 0x13f
-#undef MC_CMD_0x13f_PRIVILEGE_CTG
-
-#define MC_CMD_0x13f_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_RSS_CONTEXT_READ_TABLE_IN msgrequest */
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_LENMIN 6
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_LENMAX 252
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_LEN(num) (4+2*(num))
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_NUM(len) (((len)-4)/2)
-/* The handle of the RSS context */
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_RSS_CONTEXT_ID_OFST 0
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_RSS_CONTEXT_ID_LEN 4
-/* An array containing the indices of the entries to be read. */
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_OFST 4
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_LEN 2
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_MINNUM 1
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_MAXNUM 124
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_MAXNUM_MCDI2 508
-
-/* MC_CMD_RSS_CONTEXT_READ_TABLE_OUT msgresponse */
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_LENMIN 2
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_LENMAX 252
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_LEN(num) (0+2*(num))
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_NUM(len) (((len)-0)/2)
-/* A buffer containing the requested entries read from the table. */
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_OFST 0
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_LEN 2
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_MINNUM 1
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_MAXNUM 126
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_MAXNUM_MCDI2 510
-
-
-/***********************************/
 /* MC_CMD_RSS_CONTEXT_SET_FLAGS
  * Set various control flags for an RSS context.
  */
@@ -19525,158 +20171,6 @@
 
 
 /***********************************/
-/* MC_CMD_DOT1P_MAPPING_ALLOC
- * Allocate a .1p mapping.
- */
-#define MC_CMD_DOT1P_MAPPING_ALLOC 0xa4
-#undef MC_CMD_0xa4_PRIVILEGE_CTG
-
-#define MC_CMD_0xa4_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DOT1P_MAPPING_ALLOC_IN msgrequest */
-#define    MC_CMD_DOT1P_MAPPING_ALLOC_IN_LEN 8
-/* The handle of the owning upstream port */
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_IN_UPSTREAM_PORT_ID_LEN 4
-/* Number of queues spanned by this mapping, in the range 1-64; valid fixed
- * offsets in the mapping table will be in the range 0 to NUM_QUEUES-1, and
- * referenced RSS contexts must span no more than this number.
- */
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_IN_NUM_QUEUES_OFST 4
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_IN_NUM_QUEUES_LEN 4
-
-/* MC_CMD_DOT1P_MAPPING_ALLOC_OUT msgresponse */
-#define    MC_CMD_DOT1P_MAPPING_ALLOC_OUT_LEN 4
-/* The handle of the new .1p mapping. This should be considered opaque to the
- * host, although a value of 0xFFFFFFFF is guaranteed never to be a valid
- * handle.
- */
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_LEN 4
-/* enum: guaranteed invalid .1p mapping handle value */
-#define          MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_INVALID 0xffffffff
-
-
-/***********************************/
-/* MC_CMD_DOT1P_MAPPING_FREE
- * Free a .1p mapping.
- */
-#define MC_CMD_DOT1P_MAPPING_FREE 0xa5
-#undef MC_CMD_0xa5_PRIVILEGE_CTG
-
-#define MC_CMD_0xa5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DOT1P_MAPPING_FREE_IN msgrequest */
-#define    MC_CMD_DOT1P_MAPPING_FREE_IN_LEN 4
-/* The handle of the .1p mapping */
-#define       MC_CMD_DOT1P_MAPPING_FREE_IN_DOT1P_MAPPING_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_FREE_IN_DOT1P_MAPPING_ID_LEN 4
-
-/* MC_CMD_DOT1P_MAPPING_FREE_OUT msgresponse */
-#define    MC_CMD_DOT1P_MAPPING_FREE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DOT1P_MAPPING_SET_TABLE
- * Set the mapping table for a .1p mapping.
- */
-#define MC_CMD_DOT1P_MAPPING_SET_TABLE 0xa6
-#undef MC_CMD_0xa6_PRIVILEGE_CTG
-
-#define MC_CMD_0xa6_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DOT1P_MAPPING_SET_TABLE_IN msgrequest */
-#define    MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_LEN 36
-/* The handle of the .1p mapping */
-#define       MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_DOT1P_MAPPING_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_DOT1P_MAPPING_ID_LEN 4
-/* Per-priority mappings (1 32-bit word per entry - an offset or RSS context
- * handle)
- */
-#define       MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_MAPPING_TABLE_OFST 4
-#define       MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_MAPPING_TABLE_LEN 32
-
-/* MC_CMD_DOT1P_MAPPING_SET_TABLE_OUT msgresponse */
-#define    MC_CMD_DOT1P_MAPPING_SET_TABLE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DOT1P_MAPPING_GET_TABLE
- * Get the mapping table for a .1p mapping.
- */
-#define MC_CMD_DOT1P_MAPPING_GET_TABLE 0xa7
-#undef MC_CMD_0xa7_PRIVILEGE_CTG
-
-#define MC_CMD_0xa7_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DOT1P_MAPPING_GET_TABLE_IN msgrequest */
-#define    MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_LEN 4
-/* The handle of the .1p mapping */
-#define       MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_DOT1P_MAPPING_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_DOT1P_MAPPING_ID_LEN 4
-
-/* MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT msgresponse */
-#define    MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_LEN 36
-/* Per-priority mappings (1 32-bit word per entry - an offset or RSS context
- * handle)
- */
-#define       MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_MAPPING_TABLE_OFST 4
-#define       MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_MAPPING_TABLE_LEN 32
-
-
-/***********************************/
-/* MC_CMD_GET_VECTOR_CFG
- * Get Interrupt Vector config for this PF.
- */
-#define MC_CMD_GET_VECTOR_CFG 0xbf
-#undef MC_CMD_0xbf_PRIVILEGE_CTG
-
-#define MC_CMD_0xbf_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_VECTOR_CFG_IN msgrequest */
-#define    MC_CMD_GET_VECTOR_CFG_IN_LEN 0
-
-/* MC_CMD_GET_VECTOR_CFG_OUT msgresponse */
-#define    MC_CMD_GET_VECTOR_CFG_OUT_LEN 12
-/* Base absolute interrupt vector number. */
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VEC_BASE_OFST 0
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VEC_BASE_LEN 4
-/* Number of interrupt vectors allocate to this PF. */
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_PF_OFST 4
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_PF_LEN 4
-/* Number of interrupt vectors to allocate per VF. */
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_VF_OFST 8
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_VF_LEN 4
-
-
-/***********************************/
-/* MC_CMD_SET_VECTOR_CFG
- * Set Interrupt Vector config for this PF.
- */
-#define MC_CMD_SET_VECTOR_CFG 0xc0
-#undef MC_CMD_0xc0_PRIVILEGE_CTG
-
-#define MC_CMD_0xc0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_SET_VECTOR_CFG_IN msgrequest */
-#define    MC_CMD_SET_VECTOR_CFG_IN_LEN 12
-/* Base absolute interrupt vector number, or MC_CMD_RESOURCE_INSTANCE_ANY to
- * let the system find a suitable base.
- */
-#define       MC_CMD_SET_VECTOR_CFG_IN_VEC_BASE_OFST 0
-#define       MC_CMD_SET_VECTOR_CFG_IN_VEC_BASE_LEN 4
-/* Number of interrupt vectors allocate to this PF. */
-#define       MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_PF_OFST 4
-#define       MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_PF_LEN 4
-/* Number of interrupt vectors to allocate per VF. */
-#define       MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_VF_OFST 8
-#define       MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_VF_LEN 4
-
-/* MC_CMD_SET_VECTOR_CFG_OUT msgresponse */
-#define    MC_CMD_SET_VECTOR_CFG_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_VPORT_ADD_MAC_ADDRESS
  * Add a MAC address to a v-port
  */
@@ -19810,124 +20304,6 @@
 
 
 /***********************************/
-/* MC_CMD_EVB_PORT_QUERY
- * read some config of v-port.
- */
-#define MC_CMD_EVB_PORT_QUERY 0x62
-#undef MC_CMD_0x62_PRIVILEGE_CTG
-
-#define MC_CMD_0x62_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_EVB_PORT_QUERY_IN msgrequest */
-#define    MC_CMD_EVB_PORT_QUERY_IN_LEN 4
-/* The handle of the v-port */
-#define       MC_CMD_EVB_PORT_QUERY_IN_PORT_ID_OFST 0
-#define       MC_CMD_EVB_PORT_QUERY_IN_PORT_ID_LEN 4
-
-/* MC_CMD_EVB_PORT_QUERY_OUT msgresponse */
-#define    MC_CMD_EVB_PORT_QUERY_OUT_LEN 8
-/* The EVB port flags as defined at MC_CMD_VPORT_ALLOC. */
-#define       MC_CMD_EVB_PORT_QUERY_OUT_PORT_FLAGS_OFST 0
-#define       MC_CMD_EVB_PORT_QUERY_OUT_PORT_FLAGS_LEN 4
-/* The number of VLAN tags that may be used on a v-adaptor connected to this
- * EVB port.
- */
-#define       MC_CMD_EVB_PORT_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS_OFST 4
-#define       MC_CMD_EVB_PORT_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DUMP_BUFTBL_ENTRIES
- * Dump buffer table entries, mainly for command client debug use. Dumps
- * absolute entries, and does not use chunk handles. All entries must be in
- * range, and used for q page mapping, Although the latter restriction may be
- * lifted in future.
- */
-#define MC_CMD_DUMP_BUFTBL_ENTRIES 0xab
-#undef MC_CMD_0xab_PRIVILEGE_CTG
-
-#define MC_CMD_0xab_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_DUMP_BUFTBL_ENTRIES_IN msgrequest */
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_IN_LEN 8
-/* Index of the first buffer table entry. */
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_IN_FIRSTID_OFST 0
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_IN_FIRSTID_LEN 4
-/* Number of buffer table entries to dump. */
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_IN_NUMENTRIES_OFST 4
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_IN_NUMENTRIES_LEN 4
-
-/* MC_CMD_DUMP_BUFTBL_ENTRIES_OUT msgresponse */
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMIN 12
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMAX 252
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LEN(num) (0+12*(num))
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_NUM(len) (((len)-0)/12)
-/* Raw buffer table entries, layed out as BUFTBL_ENTRY. */
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_OFST 0
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_LEN 12
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MINNUM 1
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MAXNUM 21
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MAXNUM_MCDI2 85
-
-
-/***********************************/
-/* MC_CMD_SET_RXDP_CONFIG
- * Set global RXDP configuration settings
- */
-#define MC_CMD_SET_RXDP_CONFIG 0xc1
-#undef MC_CMD_0xc1_PRIVILEGE_CTG
-
-#define MC_CMD_0xc1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_RXDP_CONFIG_IN msgrequest */
-#define    MC_CMD_SET_RXDP_CONFIG_IN_LEN 4
-#define       MC_CMD_SET_RXDP_CONFIG_IN_DATA_OFST 0
-#define       MC_CMD_SET_RXDP_CONFIG_IN_DATA_LEN 4
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_OFST 0
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_LBN 0
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_WIDTH 1
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_OFST 0
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_LBN 1
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_WIDTH 2
-/* enum: pad to 64 bytes */
-#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_64 0x0
-/* enum: pad to 128 bytes (Medford only) */
-#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_128 0x1
-/* enum: pad to 256 bytes (Medford only) */
-#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_256 0x2
-
-/* MC_CMD_SET_RXDP_CONFIG_OUT msgresponse */
-#define    MC_CMD_SET_RXDP_CONFIG_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_RXDP_CONFIG
- * Get global RXDP configuration settings
- */
-#define MC_CMD_GET_RXDP_CONFIG 0xc2
-#undef MC_CMD_0xc2_PRIVILEGE_CTG
-
-#define MC_CMD_0xc2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_RXDP_CONFIG_IN msgrequest */
-#define    MC_CMD_GET_RXDP_CONFIG_IN_LEN 0
-
-/* MC_CMD_GET_RXDP_CONFIG_OUT msgresponse */
-#define    MC_CMD_GET_RXDP_CONFIG_OUT_LEN 4
-#define       MC_CMD_GET_RXDP_CONFIG_OUT_DATA_OFST 0
-#define       MC_CMD_GET_RXDP_CONFIG_OUT_DATA_LEN 4
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_OFST 0
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_LBN 0
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_WIDTH 1
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_OFST 0
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_LBN 1
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_WIDTH 2
-/*             Enum values, see field(s): */
-/*                MC_CMD_SET_RXDP_CONFIG/MC_CMD_SET_RXDP_CONFIG_IN/PAD_HOST_LEN */
-
-
-/***********************************/
 /* MC_CMD_GET_CLOCK
  * Return the system and PDCPU clock frequencies.
  */
@@ -19950,210 +20326,6 @@
 
 
 /***********************************/
-/* MC_CMD_SET_CLOCK
- * Control the system and DPCPU clock frequencies. Changes are lost reboot.
- */
-#define MC_CMD_SET_CLOCK 0xad
-#undef MC_CMD_0xad_PRIVILEGE_CTG
-
-#define MC_CMD_0xad_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SET_CLOCK_IN msgrequest */
-#define    MC_CMD_SET_CLOCK_IN_LEN 28
-/* Requested frequency in MHz for system clock domain */
-#define       MC_CMD_SET_CLOCK_IN_SYS_FREQ_OFST 0
-#define       MC_CMD_SET_CLOCK_IN_SYS_FREQ_LEN 4
-/* enum: Leave the system clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_SYS_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for inter-core clock domain */
-#define       MC_CMD_SET_CLOCK_IN_ICORE_FREQ_OFST 4
-#define       MC_CMD_SET_CLOCK_IN_ICORE_FREQ_LEN 4
-/* enum: Leave the inter-core clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_ICORE_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for DPCPU clock domain */
-#define       MC_CMD_SET_CLOCK_IN_DPCPU_FREQ_OFST 8
-#define       MC_CMD_SET_CLOCK_IN_DPCPU_FREQ_LEN 4
-/* enum: Leave the DPCPU clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_DPCPU_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for PCS clock domain */
-#define       MC_CMD_SET_CLOCK_IN_PCS_FREQ_OFST 12
-#define       MC_CMD_SET_CLOCK_IN_PCS_FREQ_LEN 4
-/* enum: Leave the PCS clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_PCS_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for MC clock domain */
-#define       MC_CMD_SET_CLOCK_IN_MC_FREQ_OFST 16
-#define       MC_CMD_SET_CLOCK_IN_MC_FREQ_LEN 4
-/* enum: Leave the MC clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_MC_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for rmon clock domain */
-#define       MC_CMD_SET_CLOCK_IN_RMON_FREQ_OFST 20
-#define       MC_CMD_SET_CLOCK_IN_RMON_FREQ_LEN 4
-/* enum: Leave the rmon clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_RMON_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for vswitch clock domain */
-#define       MC_CMD_SET_CLOCK_IN_VSWITCH_FREQ_OFST 24
-#define       MC_CMD_SET_CLOCK_IN_VSWITCH_FREQ_LEN 4
-/* enum: Leave the vswitch clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_VSWITCH_DOMAIN_DONT_CHANGE 0x0
-
-/* MC_CMD_SET_CLOCK_OUT msgresponse */
-#define    MC_CMD_SET_CLOCK_OUT_LEN 28
-/* Resulting system frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_SYS_FREQ_OFST 0
-#define       MC_CMD_SET_CLOCK_OUT_SYS_FREQ_LEN 4
-/* enum: The system clock domain doesn't exist */
-#define          MC_CMD_SET_CLOCK_OUT_SYS_DOMAIN_UNSUPPORTED 0x0
-/* Resulting inter-core frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_ICORE_FREQ_OFST 4
-#define       MC_CMD_SET_CLOCK_OUT_ICORE_FREQ_LEN 4
-/* enum: The inter-core clock domain doesn't exist / isn't used */
-#define          MC_CMD_SET_CLOCK_OUT_ICORE_DOMAIN_UNSUPPORTED 0x0
-/* Resulting DPCPU frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_DPCPU_FREQ_OFST 8
-#define       MC_CMD_SET_CLOCK_OUT_DPCPU_FREQ_LEN 4
-/* enum: The dpcpu clock domain doesn't exist */
-#define          MC_CMD_SET_CLOCK_OUT_DPCPU_DOMAIN_UNSUPPORTED 0x0
-/* Resulting PCS frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_PCS_FREQ_OFST 12
-#define       MC_CMD_SET_CLOCK_OUT_PCS_FREQ_LEN 4
-/* enum: The PCS clock domain doesn't exist / isn't controlled */
-#define          MC_CMD_SET_CLOCK_OUT_PCS_DOMAIN_UNSUPPORTED 0x0
-/* Resulting MC frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_MC_FREQ_OFST 16
-#define       MC_CMD_SET_CLOCK_OUT_MC_FREQ_LEN 4
-/* enum: The MC clock domain doesn't exist / isn't controlled */
-#define          MC_CMD_SET_CLOCK_OUT_MC_DOMAIN_UNSUPPORTED 0x0
-/* Resulting rmon frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_RMON_FREQ_OFST 20
-#define       MC_CMD_SET_CLOCK_OUT_RMON_FREQ_LEN 4
-/* enum: The rmon clock domain doesn't exist / isn't controlled */
-#define          MC_CMD_SET_CLOCK_OUT_RMON_DOMAIN_UNSUPPORTED 0x0
-/* Resulting vswitch frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_VSWITCH_FREQ_OFST 24
-#define       MC_CMD_SET_CLOCK_OUT_VSWITCH_FREQ_LEN 4
-/* enum: The vswitch clock domain doesn't exist / isn't controlled */
-#define          MC_CMD_SET_CLOCK_OUT_VSWITCH_DOMAIN_UNSUPPORTED 0x0
-
-
-/***********************************/
-/* MC_CMD_DPCPU_RPC
- * Send an arbitrary DPCPU message.
- */
-#define MC_CMD_DPCPU_RPC 0xae
-#undef MC_CMD_0xae_PRIVILEGE_CTG
-
-#define MC_CMD_0xae_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_DPCPU_RPC_IN msgrequest */
-#define    MC_CMD_DPCPU_RPC_IN_LEN 36
-#define       MC_CMD_DPCPU_RPC_IN_CPU_OFST 0
-#define       MC_CMD_DPCPU_RPC_IN_CPU_LEN 4
-/* enum: RxDPCPU0 */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_RX0 0x0
-/* enum: TxDPCPU0 */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_TX0 0x1
-/* enum: TxDPCPU1 */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_TX1 0x2
-/* enum: RxDPCPU1 (Medford only) */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_RX1 0x3
-/* enum: RxDPCPU (will be for the calling function; for now, just an alias of
- * DPCPU_RX0)
- */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_RX 0x80
-/* enum: TxDPCPU (will be for the calling function; for now, just an alias of
- * DPCPU_TX0)
- */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_TX 0x81
-/* First 8 bits [39:32] of DATA are consumed by MC-DPCPU protocol and must be
- * initialised to zero
- */
-#define       MC_CMD_DPCPU_RPC_IN_DATA_OFST 4
-#define       MC_CMD_DPCPU_RPC_IN_DATA_LEN 32
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_CMDNUM_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_CMDNUM_LBN 8
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_CMDNUM_WIDTH 8
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_READ 0x6 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_WRITE 0x7 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_SELF_TEST 0xc /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_CSR_ACCESS 0xe /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_READ 0x46 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_WRITE 0x47 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_SELF_TEST 0x4a /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_CSR_ACCESS 0x4c /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_SET_MC_REPLAY_CNTXT 0x4d /* enum */
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_OBJID_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_OBJID_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_OBJID_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_ADDR_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_ADDR_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_ADDR_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_COUNT_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_COUNT_LBN 48
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_COUNT_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_INFO_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_INFO_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_INFO_WIDTH 240
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_WIDTH 16
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_STOP_RETURN_RESULT 0x0 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_READ 0x1 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_WRITE 0x2 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_WRITE_READ 0x3 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_PIPELINED_READ 0x4 /* enum */
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_START_DELAY_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_START_DELAY_LBN 48
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_START_DELAY_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_RPT_COUNT_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_RPT_COUNT_LBN 64
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_RPT_COUNT_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_GAP_DELAY_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_GAP_DELAY_LBN 80
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_GAP_DELAY_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_WIDTH 16
-#define          MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_CUT_THROUGH 0x1 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_STORE_FORWARD 0x2 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_STORE_FORWARD_FIRST 0x3 /* enum */
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_CNTXT_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_CNTXT_LBN 64
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_CNTXT_WIDTH 16
-#define       MC_CMD_DPCPU_RPC_IN_WDATA_OFST 12
-#define       MC_CMD_DPCPU_RPC_IN_WDATA_LEN 24
-/* Register data to write. Only valid in write/write-read. */
-#define       MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_DATA_OFST 16
-#define       MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_DATA_LEN 4
-/* Register address. */
-#define       MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_ADDRESS_OFST 20
-#define       MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_ADDRESS_LEN 4
-
-/* MC_CMD_DPCPU_RPC_OUT msgresponse */
-#define    MC_CMD_DPCPU_RPC_OUT_LEN 36
-#define       MC_CMD_DPCPU_RPC_OUT_RC_OFST 0
-#define       MC_CMD_DPCPU_RPC_OUT_RC_LEN 4
-/* DATA */
-#define       MC_CMD_DPCPU_RPC_OUT_DATA_OFST 4
-#define       MC_CMD_DPCPU_RPC_OUT_DATA_LEN 32
-#define        MC_CMD_DPCPU_RPC_OUT_HDR_CMD_RESP_ERRCODE_OFST 4
-#define        MC_CMD_DPCPU_RPC_OUT_HDR_CMD_RESP_ERRCODE_LBN 32
-#define        MC_CMD_DPCPU_RPC_OUT_HDR_CMD_RESP_ERRCODE_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_COUNT_OFST 4
-#define        MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_COUNT_LBN 48
-#define        MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_COUNT_WIDTH 16
-#define       MC_CMD_DPCPU_RPC_OUT_RDATA_OFST 12
-#define       MC_CMD_DPCPU_RPC_OUT_RDATA_LEN 24
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_1_OFST 12
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_1_LEN 4
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_2_OFST 16
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_2_LEN 4
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_3_OFST 20
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_3_LEN 4
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_4_OFST 24
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_4_LEN 4
-
-
-/***********************************/
 /* MC_CMD_TRIGGER_INTERRUPT
  * Trigger an interrupt by prodding the BIU.
  */
@@ -20173,66 +20345,6 @@
 
 
 /***********************************/
-/* MC_CMD_SHMBOOT_OP
- * Special operations to support (for now) shmboot.
- */
-#define MC_CMD_SHMBOOT_OP 0xe6
-#undef MC_CMD_0xe6_PRIVILEGE_CTG
-
-#define MC_CMD_0xe6_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SHMBOOT_OP_IN msgrequest */
-#define    MC_CMD_SHMBOOT_OP_IN_LEN 4
-/* Identifies the operation to perform */
-#define       MC_CMD_SHMBOOT_OP_IN_SHMBOOT_OP_OFST 0
-#define       MC_CMD_SHMBOOT_OP_IN_SHMBOOT_OP_LEN 4
-/* enum: Copy slave_data section to the slave core. (Greenport only) */
-#define          MC_CMD_SHMBOOT_OP_IN_PUSH_SLAVE_DATA 0x0
-
-/* MC_CMD_SHMBOOT_OP_OUT msgresponse */
-#define    MC_CMD_SHMBOOT_OP_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_CAP_BLK_READ
- * Read multiple 64bit words from capture block memory
- */
-#define MC_CMD_CAP_BLK_READ 0xe7
-#undef MC_CMD_0xe7_PRIVILEGE_CTG
-
-#define MC_CMD_0xe7_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_CAP_BLK_READ_IN msgrequest */
-#define    MC_CMD_CAP_BLK_READ_IN_LEN 12
-#define       MC_CMD_CAP_BLK_READ_IN_CAP_REG_OFST 0
-#define       MC_CMD_CAP_BLK_READ_IN_CAP_REG_LEN 4
-#define       MC_CMD_CAP_BLK_READ_IN_ADDR_OFST 4
-#define       MC_CMD_CAP_BLK_READ_IN_ADDR_LEN 4
-#define       MC_CMD_CAP_BLK_READ_IN_COUNT_OFST 8
-#define       MC_CMD_CAP_BLK_READ_IN_COUNT_LEN 4
-
-/* MC_CMD_CAP_BLK_READ_OUT msgresponse */
-#define    MC_CMD_CAP_BLK_READ_OUT_LENMIN 8
-#define    MC_CMD_CAP_BLK_READ_OUT_LENMAX 248
-#define    MC_CMD_CAP_BLK_READ_OUT_LENMAX_MCDI2 1016
-#define    MC_CMD_CAP_BLK_READ_OUT_LEN(num) (0+8*(num))
-#define    MC_CMD_CAP_BLK_READ_OUT_BUFFER_NUM(len) (((len)-0)/8)
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_OFST 0
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LEN 8
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_OFST 0
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_LEN 4
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_LBN 0
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_WIDTH 32
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_OFST 4
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_LEN 4
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_LBN 32
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_WIDTH 32
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_MINNUM 1
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_MAXNUM 31
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_MAXNUM_MCDI2 127
-
-
-/***********************************/
 /* MC_CMD_DUMP_DO
  * Take a dump of the DUT state
  */
@@ -20380,34 +20492,6 @@
 
 
 /***********************************/
-/* MC_CMD_SET_PSU
- * Adjusts power supply parameters. This is a warranty-voiding operation.
- * Returns: ENOENT if the parameter or rail specified does not exist, EINVAL if
- * the parameter is out of range.
- */
-#define MC_CMD_SET_PSU 0xea
-#undef MC_CMD_0xea_PRIVILEGE_CTG
-
-#define MC_CMD_0xea_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SET_PSU_IN msgrequest */
-#define    MC_CMD_SET_PSU_IN_LEN 12
-#define       MC_CMD_SET_PSU_IN_PARAM_OFST 0
-#define       MC_CMD_SET_PSU_IN_PARAM_LEN 4
-#define          MC_CMD_SET_PSU_IN_PARAM_SUPPLY_VOLTAGE 0x0 /* enum */
-#define       MC_CMD_SET_PSU_IN_RAIL_OFST 4
-#define       MC_CMD_SET_PSU_IN_RAIL_LEN 4
-#define          MC_CMD_SET_PSU_IN_RAIL_0V9 0x0 /* enum */
-#define          MC_CMD_SET_PSU_IN_RAIL_1V2 0x1 /* enum */
-/* desired value, eg voltage in mV */
-#define       MC_CMD_SET_PSU_IN_VALUE_OFST 8
-#define       MC_CMD_SET_PSU_IN_VALUE_LEN 4
-
-/* MC_CMD_SET_PSU_OUT msgresponse */
-#define    MC_CMD_SET_PSU_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_GET_FUNCTION_INFO
  * Get function information. PF and VF number.
  */
@@ -20448,7 +20532,7 @@
 #define MC_CMD_ENABLE_OFFLINE_BIST 0xed
 #undef MC_CMD_0xed_PRIVILEGE_CTG
 
-#define MC_CMD_0xed_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0xed_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_ENABLE_OFFLINE_BIST_IN msgrequest */
 #define    MC_CMD_ENABLE_OFFLINE_BIST_IN_LEN 0
@@ -20458,137 +20542,13 @@
 
 
 /***********************************/
-/* MC_CMD_UART_SEND_DATA
- * Send checksummed[sic] block of data over the uart. Response is a placeholder
- * should we wish to make this reliable; currently requests are fire-and-
- * forget.
- */
-#define MC_CMD_UART_SEND_DATA 0xee
-#undef MC_CMD_0xee_PRIVILEGE_CTG
-
-#define MC_CMD_0xee_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_UART_SEND_DATA_OUT msgrequest */
-#define    MC_CMD_UART_SEND_DATA_OUT_LENMIN 16
-#define    MC_CMD_UART_SEND_DATA_OUT_LENMAX 252
-#define    MC_CMD_UART_SEND_DATA_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_UART_SEND_DATA_OUT_LEN(num) (16+1*(num))
-#define    MC_CMD_UART_SEND_DATA_OUT_DATA_NUM(len) (((len)-16)/1)
-/* CRC32 over OFFSET, LENGTH, RESERVED, DATA */
-#define       MC_CMD_UART_SEND_DATA_OUT_CHECKSUM_OFST 0
-#define       MC_CMD_UART_SEND_DATA_OUT_CHECKSUM_LEN 4
-/* Offset at which to write the data */
-#define       MC_CMD_UART_SEND_DATA_OUT_OFFSET_OFST 4
-#define       MC_CMD_UART_SEND_DATA_OUT_OFFSET_LEN 4
-/* Length of data */
-#define       MC_CMD_UART_SEND_DATA_OUT_LENGTH_OFST 8
-#define       MC_CMD_UART_SEND_DATA_OUT_LENGTH_LEN 4
-/* Reserved for future use */
-#define       MC_CMD_UART_SEND_DATA_OUT_RESERVED_OFST 12
-#define       MC_CMD_UART_SEND_DATA_OUT_RESERVED_LEN 4
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_OFST 16
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_LEN 1
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_MINNUM 0
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_MAXNUM 236
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_MAXNUM_MCDI2 1004
-
-/* MC_CMD_UART_SEND_DATA_IN msgresponse */
-#define    MC_CMD_UART_SEND_DATA_IN_LEN 0
-
-
-/***********************************/
-/* MC_CMD_UART_RECV_DATA
- * Request checksummed[sic] block of data over the uart. Only a placeholder,
- * subject to change and not currently implemented.
- */
-#define MC_CMD_UART_RECV_DATA 0xef
-#undef MC_CMD_0xef_PRIVILEGE_CTG
-
-#define MC_CMD_0xef_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_UART_RECV_DATA_OUT msgrequest */
-#define    MC_CMD_UART_RECV_DATA_OUT_LEN 16
-/* CRC32 over OFFSET, LENGTH, RESERVED */
-#define       MC_CMD_UART_RECV_DATA_OUT_CHECKSUM_OFST 0
-#define       MC_CMD_UART_RECV_DATA_OUT_CHECKSUM_LEN 4
-/* Offset from which to read the data */
-#define       MC_CMD_UART_RECV_DATA_OUT_OFFSET_OFST 4
-#define       MC_CMD_UART_RECV_DATA_OUT_OFFSET_LEN 4
-/* Length of data */
-#define       MC_CMD_UART_RECV_DATA_OUT_LENGTH_OFST 8
-#define       MC_CMD_UART_RECV_DATA_OUT_LENGTH_LEN 4
-/* Reserved for future use */
-#define       MC_CMD_UART_RECV_DATA_OUT_RESERVED_OFST 12
-#define       MC_CMD_UART_RECV_DATA_OUT_RESERVED_LEN 4
-
-/* MC_CMD_UART_RECV_DATA_IN msgresponse */
-#define    MC_CMD_UART_RECV_DATA_IN_LENMIN 16
-#define    MC_CMD_UART_RECV_DATA_IN_LENMAX 252
-#define    MC_CMD_UART_RECV_DATA_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_UART_RECV_DATA_IN_LEN(num) (16+1*(num))
-#define    MC_CMD_UART_RECV_DATA_IN_DATA_NUM(len) (((len)-16)/1)
-/* CRC32 over RESERVED1, RESERVED2, RESERVED3, DATA */
-#define       MC_CMD_UART_RECV_DATA_IN_CHECKSUM_OFST 0
-#define       MC_CMD_UART_RECV_DATA_IN_CHECKSUM_LEN 4
-/* Offset at which to write the data */
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED1_OFST 4
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED1_LEN 4
-/* Length of data */
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED2_OFST 8
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED2_LEN 4
-/* Reserved for future use */
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED3_OFST 12
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED3_LEN 4
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_OFST 16
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_LEN 1
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_MINNUM 0
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_MAXNUM 236
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_MAXNUM_MCDI2 1004
-
-
-/***********************************/
-/* MC_CMD_READ_FUSES
- * Read data programmed into the device One-Time-Programmable (OTP) Fuses
- */
-#define MC_CMD_READ_FUSES 0xf0
-#undef MC_CMD_0xf0_PRIVILEGE_CTG
-
-#define MC_CMD_0xf0_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_READ_FUSES_IN msgrequest */
-#define    MC_CMD_READ_FUSES_IN_LEN 8
-/* Offset in OTP to read */
-#define       MC_CMD_READ_FUSES_IN_OFFSET_OFST 0
-#define       MC_CMD_READ_FUSES_IN_OFFSET_LEN 4
-/* Length of data to read in bytes */
-#define       MC_CMD_READ_FUSES_IN_LENGTH_OFST 4
-#define       MC_CMD_READ_FUSES_IN_LENGTH_LEN 4
-
-/* MC_CMD_READ_FUSES_OUT msgresponse */
-#define    MC_CMD_READ_FUSES_OUT_LENMIN 4
-#define    MC_CMD_READ_FUSES_OUT_LENMAX 252
-#define    MC_CMD_READ_FUSES_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_READ_FUSES_OUT_LEN(num) (4+1*(num))
-#define    MC_CMD_READ_FUSES_OUT_DATA_NUM(len) (((len)-4)/1)
-/* Length of returned OTP data in bytes */
-#define       MC_CMD_READ_FUSES_OUT_LENGTH_OFST 0
-#define       MC_CMD_READ_FUSES_OUT_LENGTH_LEN 4
-/* Returned data */
-#define       MC_CMD_READ_FUSES_OUT_DATA_OFST 4
-#define       MC_CMD_READ_FUSES_OUT_DATA_LEN 1
-#define       MC_CMD_READ_FUSES_OUT_DATA_MINNUM 0
-#define       MC_CMD_READ_FUSES_OUT_DATA_MAXNUM 248
-#define       MC_CMD_READ_FUSES_OUT_DATA_MAXNUM_MCDI2 1016
-
-
-/***********************************/
 /* MC_CMD_KR_TUNE
  * Get or set KR Serdes RXEQ and TX Driver settings
  */
 #define MC_CMD_KR_TUNE 0xf1
 #undef MC_CMD_0xf1_PRIVILEGE_CTG
 
-#define MC_CMD_0xf1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0xf1_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_KR_TUNE_IN msgrequest */
 #define    MC_CMD_KR_TUNE_IN_LENMIN 4
@@ -21138,262 +21098,6 @@
 
 
 /***********************************/
-/* MC_CMD_PCIE_TUNE
- * Get or set PCIE Serdes RXEQ and TX Driver settings
- */
-#define MC_CMD_PCIE_TUNE 0xf2
-#undef MC_CMD_0xf2_PRIVILEGE_CTG
-
-#define MC_CMD_0xf2_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PCIE_TUNE_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_IN_LENMIN 4
-#define    MC_CMD_PCIE_TUNE_IN_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_IN_LEN(num) (4+4*(num))
-#define    MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_NUM(len) (((len)-4)/4)
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_OP_LEN 1
-/* enum: Get current RXEQ settings */
-#define          MC_CMD_PCIE_TUNE_IN_RXEQ_GET 0x0
-/* enum: Override RXEQ settings */
-#define          MC_CMD_PCIE_TUNE_IN_RXEQ_SET 0x1
-/* enum: Get current TX Driver settings */
-#define          MC_CMD_PCIE_TUNE_IN_TXEQ_GET 0x2
-/* enum: Override TX Driver settings */
-#define          MC_CMD_PCIE_TUNE_IN_TXEQ_SET 0x3
-/* enum: Start PCIe Serdes Eye diagram plot on a given lane. */
-#define          MC_CMD_PCIE_TUNE_IN_START_EYE_PLOT 0x5
-/* enum: Poll PCIe Serdes Eye diagram plot. Returns one row of BER data. The
- * caller should call this command repeatedly after starting eye plot, until no
- * more data is returned.
- */
-#define          MC_CMD_PCIE_TUNE_IN_POLL_EYE_PLOT 0x6
-/* enum: Enable the SERDES BIST and set it to generate a 200MHz square wave */
-#define          MC_CMD_PCIE_TUNE_IN_BIST_SQUARE_WAVE 0x7
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_LEN 3
-/* Arguments specific to the operation */
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_OFST 4
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_LEN 4
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_MINNUM 0
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_MAXNUM 62
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_MAXNUM_MCDI2 254
-
-/* MC_CMD_PCIE_TUNE_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_OUT_LEN 0
-
-/* MC_CMD_PCIE_TUNE_RXEQ_GET_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_IN_LEN 4
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_RSVD_LEN 3
-
-/* MC_CMD_PCIE_TUNE_RXEQ_GET_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LENMIN 4
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_NUM(len) (((len)-0)/4)
-/* RXEQ Parameter */
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_OFST 0
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LEN 4
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_MINNUM 1
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM 63
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM_MCDI2 255
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_ID_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_ID_LBN 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_ID_WIDTH 8
-/* enum: Attenuation (0-15) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_ATT 0x0
-/* enum: CTLE Boost (0-15) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_BOOST 0x1
-/* enum: DFE Tap1 (0 - max negative, 64 - zero, 127 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP1 0x2
-/* enum: DFE Tap2 (0 - max negative, 32 - zero, 63 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP2 0x3
-/* enum: DFE Tap3 (0 - max negative, 32 - zero, 63 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP3 0x4
-/* enum: DFE Tap4 (0 - max negative, 32 - zero, 63 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP4 0x5
-/* enum: DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP5 0x6
-/* enum: DFE DLev */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_DLEV 0x7
-/* enum: Figure of Merit */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_FOM 0x8
-/* enum: CTLE EQ Capacitor (HF Gain) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_CTLE_EQC 0x9
-/* enum: CTLE EQ Resistor (DC Gain) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_CTLE_EQRES 0xa
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 5
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_0 0x0 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_1 0x1 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_2 0x2 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_3 0x3 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_4 0x4 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_5 0x5 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_6 0x6 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_7 0x7 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_8 0x8 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_9 0x9 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_10 0xa /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_11 0xb /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_12 0xc /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_13 0xd /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_14 0xe /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_15 0xf /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_ALL 0x10 /* enum */
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_LBN 13
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_WIDTH 1
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_LBN 14
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_WIDTH 10
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_LBN 24
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
-
-/* MC_CMD_PCIE_TUNE_RXEQ_SET_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMIN 8
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LEN(num) (4+4*(num))
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_NUM(len) (((len)-4)/4)
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_RSVD_LEN 3
-/* RXEQ Parameter */
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_OFST 4
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LEN 4
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MINNUM 1
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MAXNUM 62
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MAXNUM_MCDI2 254
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_LBN 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_WIDTH 8
-/*             Enum values, see field(s): */
-/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_ID */
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_LBN 8
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_WIDTH 5
-/*             Enum values, see field(s): */
-/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_LANE */
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_LBN 13
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_WIDTH 1
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_LBN 14
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_WIDTH 2
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_LBN 16
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_WIDTH 8
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_LBN 24
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_WIDTH 8
-
-/* MC_CMD_PCIE_TUNE_RXEQ_SET_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_OUT_LEN 0
-
-/* MC_CMD_PCIE_TUNE_TXEQ_GET_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_IN_LEN 4
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_RSVD_LEN 3
-
-/* MC_CMD_PCIE_TUNE_TXEQ_GET_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LENMIN 4
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_NUM(len) (((len)-0)/4)
-/* RXEQ Parameter */
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_OFST 0
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LEN 4
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_MINNUM 1
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM 63
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM_MCDI2 255
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_ID_OFST 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_ID_LBN 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_ID_WIDTH 8
-/* enum: TxMargin (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_TXMARGIN 0x0
-/* enum: TxSwing (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_TXSWING 0x1
-/* enum: De-emphasis coefficient C(-1) (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_CM1 0x2
-/* enum: De-emphasis coefficient C(0) (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_C0 0x3
-/* enum: De-emphasis coefficient C(+1) (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_CP1 0x4
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LANE_OFST 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LANE_LBN 8
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LANE_WIDTH 4
-/*             Enum values, see field(s): */
-/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_LANE */
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_RESERVED_OFST 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_RESERVED_LBN 12
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_RESERVED_WIDTH 12
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_OFST 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_LBN 24
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
-
-/* MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LEN 8
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_RSVD_LEN 3
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LANE_OFST 4
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LANE_LEN 4
-
-/* MC_CMD_PCIE_TUNE_START_EYE_PLOT_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_START_EYE_PLOT_OUT_LEN 0
-
-/* MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_LEN 4
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_RSVD_LEN 3
-
-/* MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMIN 0
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LEN(num) (0+2*(num))
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_NUM(len) (((len)-0)/2)
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_OFST 0
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_LEN 2
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MINNUM 0
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM 126
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM_MCDI2 510
-
-/* MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_IN_LEN 0
-
-/* MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_OUT msgrequest */
-#define    MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_LICENSING
  * Operations on the NVRAM_PARTITION_TYPE_LICENSE application license partition
  * - not used for V3 licensing
@@ -21532,56 +21236,6 @@
 
 
 /***********************************/
-/* MC_CMD_LICENSING_GET_ID_V3
- * Get ID and type from the NVRAM_PARTITION_TYPE_LICENSE application license
- * partition - V3 licensing (Medford)
- */
-#define MC_CMD_LICENSING_GET_ID_V3 0xd1
-#undef MC_CMD_0xd1_PRIVILEGE_CTG
-
-#define MC_CMD_0xd1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_LICENSING_GET_ID_V3_IN msgrequest */
-#define    MC_CMD_LICENSING_GET_ID_V3_IN_LEN 0
-
-/* MC_CMD_LICENSING_GET_ID_V3_OUT msgresponse */
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMIN 8
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMAX 252
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LEN(num) (8+1*(num))
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_NUM(len) (((len)-8)/1)
-/* type of license (eg 3) */
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_TYPE_OFST 0
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_TYPE_LEN 4
-/* length of the license ID (in bytes) */
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LENGTH_OFST 4
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LENGTH_LEN 4
-/* the unique license ID of the adapter */
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_OFST 8
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LEN 1
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MINNUM 0
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MAXNUM 244
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MAXNUM_MCDI2 1012
-
-
-/***********************************/
-/* MC_CMD_MC2MC_PROXY
- * Execute an arbitrary MCDI command on the slave MC of a dual-core device.
- * This will fail on a single-core system.
- */
-#define MC_CMD_MC2MC_PROXY 0xf4
-#undef MC_CMD_0xf4_PRIVILEGE_CTG
-
-#define MC_CMD_0xf4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_MC2MC_PROXY_IN msgrequest */
-#define    MC_CMD_MC2MC_PROXY_IN_LEN 0
-
-/* MC_CMD_MC2MC_PROXY_OUT msgresponse */
-#define    MC_CMD_MC2MC_PROXY_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_GET_LICENSED_APP_STATE
  * Query the state of an individual licensed application. (Note that the actual
  * state may be invalidated by the MC_CMD_LICENSING OP_UPDATE_LICENSE operation
@@ -21610,424 +21264,6 @@
 
 
 /***********************************/
-/* MC_CMD_GET_LICENSED_V3_APP_STATE
- * Query the state of an individual licensed application. (Note that the actual
- * state may be invalidated by the MC_CMD_LICENSING_V3 OP_UPDATE_LICENSE
- * operation or a reboot of the MC.) Used for V3 licensing (Medford)
- */
-#define MC_CMD_GET_LICENSED_V3_APP_STATE 0xd2
-#undef MC_CMD_0xd2_PRIVILEGE_CTG
-
-#define MC_CMD_0xd2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_LICENSED_V3_APP_STATE_IN msgrequest */
-#define    MC_CMD_GET_LICENSED_V3_APP_STATE_IN_LEN 8
-/* application ID to query (LICENSED_V3_APPS_xxx) expressed as a single bit
- * mask
- */
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LEN 8
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_LBN 0
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_WIDTH 32
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_OFST 4
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_LBN 32
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_WIDTH 32
-
-/* MC_CMD_GET_LICENSED_V3_APP_STATE_OUT msgresponse */
-#define    MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_LEN 4
-/* state of this application */
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_STATE_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_STATE_LEN 4
-/* enum: no (or invalid) license is present for the application */
-#define          MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_NOT_LICENSED 0x0
-/* enum: a valid license is present for the application */
-#define          MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_LICENSED 0x1
-
-
-/***********************************/
-/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES
- * Query the state of an one or more licensed features. (Note that the actual
- * state may be invalidated by the MC_CMD_LICENSING_V3 OP_UPDATE_LICENSE
- * operation or a reboot of the MC.) Used for V3 licensing (Medford)
- */
-#define MC_CMD_GET_LICENSED_V3_FEATURE_STATES 0xd3
-#undef MC_CMD_0xd3_PRIVILEGE_CTG
-
-#define MC_CMD_0xd3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN msgrequest */
-#define    MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_LEN 8
-/* features to query (LICENSED_V3_FEATURES_xxx) expressed as a mask with one or
- * more bits set
- */
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LEN 8
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_LBN 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_WIDTH 32
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_OFST 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_LBN 32
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_WIDTH 32
-
-/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT msgresponse */
-#define    MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_LEN 8
-/* states of these features - bit set for licensed, clear for not licensed */
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LEN 8
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_LBN 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_WIDTH 32
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_OFST 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_LBN 32
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_LICENSED_APP_OP
- * Perform an action for an individual licensed application - not used for V3
- * licensing.
- */
-#define MC_CMD_LICENSED_APP_OP 0xf6
-#undef MC_CMD_0xf6_PRIVILEGE_CTG
-
-#define MC_CMD_0xf6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_LICENSED_APP_OP_IN msgrequest */
-#define    MC_CMD_LICENSED_APP_OP_IN_LENMIN 8
-#define    MC_CMD_LICENSED_APP_OP_IN_LENMAX 252
-#define    MC_CMD_LICENSED_APP_OP_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_LICENSED_APP_OP_IN_LEN(num) (8+4*(num))
-#define    MC_CMD_LICENSED_APP_OP_IN_ARGS_NUM(len) (((len)-8)/4)
-/* application ID */
-#define       MC_CMD_LICENSED_APP_OP_IN_APP_ID_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_IN_APP_ID_LEN 4
-/* the type of operation requested */
-#define       MC_CMD_LICENSED_APP_OP_IN_OP_OFST 4
-#define       MC_CMD_LICENSED_APP_OP_IN_OP_LEN 4
-/* enum: validate application */
-#define          MC_CMD_LICENSED_APP_OP_IN_OP_VALIDATE 0x0
-/* enum: mask application */
-#define          MC_CMD_LICENSED_APP_OP_IN_OP_MASK 0x1
-/* arguments specific to this particular operation */
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_OFST 8
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_LEN 4
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_MINNUM 0
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_MAXNUM 61
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_MAXNUM_MCDI2 253
-
-/* MC_CMD_LICENSED_APP_OP_OUT msgresponse */
-#define    MC_CMD_LICENSED_APP_OP_OUT_LENMIN 0
-#define    MC_CMD_LICENSED_APP_OP_OUT_LENMAX 252
-#define    MC_CMD_LICENSED_APP_OP_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_LICENSED_APP_OP_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_LICENSED_APP_OP_OUT_RESULT_NUM(len) (((len)-0)/4)
-/* result specific to this particular operation */
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_LEN 4
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_MINNUM 0
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_MAXNUM 63
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_MAXNUM_MCDI2 255
-
-/* MC_CMD_LICENSED_APP_OP_VALIDATE_IN msgrequest */
-#define    MC_CMD_LICENSED_APP_OP_VALIDATE_IN_LEN 72
-/* application ID */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_APP_ID_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_APP_ID_LEN 4
-/* the type of operation requested */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_OP_OFST 4
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_OP_LEN 4
-/* validation challenge */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_CHALLENGE_OFST 8
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_CHALLENGE_LEN 64
-
-/* MC_CMD_LICENSED_APP_OP_VALIDATE_OUT msgresponse */
-#define    MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_LEN 68
-/* feature expiry (time_t) */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_EXPIRY_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_EXPIRY_LEN 4
-/* validation response */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_OFST 4
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_LEN 64
-
-/* MC_CMD_LICENSED_APP_OP_MASK_IN msgrequest */
-#define    MC_CMD_LICENSED_APP_OP_MASK_IN_LEN 12
-/* application ID */
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_APP_ID_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_APP_ID_LEN 4
-/* the type of operation requested */
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_OP_OFST 4
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_OP_LEN 4
-/* flag */
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_FLAG_OFST 8
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_FLAG_LEN 4
-
-/* MC_CMD_LICENSED_APP_OP_MASK_OUT msgresponse */
-#define    MC_CMD_LICENSED_APP_OP_MASK_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_LICENSED_V3_VALIDATE_APP
- * Perform validation for an individual licensed application - V3 licensing
- * (Medford)
- */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP 0xd4
-#undef MC_CMD_0xd4_PRIVILEGE_CTG
-
-#define MC_CMD_0xd4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_LICENSED_V3_VALIDATE_APP_IN msgrequest */
-#define    MC_CMD_LICENSED_V3_VALIDATE_APP_IN_LEN 56
-/* challenge for validation (384 bits) */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_OFST 0
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_LEN 48
-/* application ID expressed as a single bit mask */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_OFST 48
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LEN 8
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_OFST 48
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_LEN 4
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_LBN 384
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_WIDTH 32
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_OFST 52
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_LEN 4
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_LBN 416
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_WIDTH 32
-
-/* MC_CMD_LICENSED_V3_VALIDATE_APP_OUT msgresponse */
-#define    MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_LEN 116
-/* validation response to challenge in the form of ECDSA signature consisting
- * of two 384-bit integers, r and s, in big-endian order. The signature signs a
- * SHA-384 digest of a message constructed from the concatenation of the input
- * message and the remaining fields of this output message, e.g. challenge[48
- * bytes] ... expiry_time[4 bytes] ...
- */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_OFST 0
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_LEN 96
-/* application expiry time */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_TIME_OFST 96
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_TIME_LEN 4
-/* application expiry units */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNITS_OFST 100
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNITS_LEN 4
-/* enum: expiry units are accounting units */
-#define          MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_ACC 0x0
-/* enum: expiry units are calendar days */
-#define          MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_DAYS 0x1
-/* base MAC address of the NIC stored in NVRAM (note that this is a constant
- * value for a given NIC regardless which function is calling, effectively this
- * is PF0 base MAC address)
- */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_BASE_MACADDR_OFST 104
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_BASE_MACADDR_LEN 6
-/* MAC address of v-adaptor associated with the client. If no such v-adapator
- * exists, then the field is filled with 0xFF.
- */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_VADAPTOR_MACADDR_OFST 110
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_VADAPTOR_MACADDR_LEN 6
-
-
-/***********************************/
-/* MC_CMD_LICENSED_V3_MASK_FEATURES
- * Mask features - V3 licensing (Medford)
- */
-#define MC_CMD_LICENSED_V3_MASK_FEATURES 0xd5
-#undef MC_CMD_0xd5_PRIVILEGE_CTG
-
-#define MC_CMD_0xd5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_LICENSED_V3_MASK_FEATURES_IN msgrequest */
-#define    MC_CMD_LICENSED_V3_MASK_FEATURES_IN_LEN 12
-/* mask to be applied to features to be changed */
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_OFST 0
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LEN 8
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_OFST 0
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_LEN 4
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_LBN 0
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_WIDTH 32
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_OFST 4
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_LEN 4
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_LBN 32
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_WIDTH 32
-/* whether to turn on or turn off the masked features */
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_FLAG_OFST 8
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_FLAG_LEN 4
-/* enum: turn the features off */
-#define          MC_CMD_LICENSED_V3_MASK_FEATURES_IN_OFF 0x0
-/* enum: turn the features back on */
-#define          MC_CMD_LICENSED_V3_MASK_FEATURES_IN_ON 0x1
-
-/* MC_CMD_LICENSED_V3_MASK_FEATURES_OUT msgresponse */
-#define    MC_CMD_LICENSED_V3_MASK_FEATURES_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_LICENSING_V3_TEMPORARY
- * Perform operations to support installation of a single temporary license in
- * the adapter, in addition to those found in the licensing partition. See
- * SF-116124-SW for an overview of how this could be used. The license is
- * stored in MC persistent data and so will survive a MC reboot, but will be
- * erased when the adapter is power cycled
- */
-#define MC_CMD_LICENSING_V3_TEMPORARY 0xd6
-#undef MC_CMD_0xd6_PRIVILEGE_CTG
-
-#define MC_CMD_0xd6_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_IN msgrequest */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_IN_LEN 4
-/* operation code */
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_OP_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_OP_LEN 4
-/* enum: install a new license, overwriting any existing temporary license.
- * This is an asynchronous operation owing to the time taken to validate an
- * ECDSA license
- */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_SET 0x0
-/* enum: clear the license immediately rather than waiting for the next power
- * cycle
- */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_CLEAR 0x1
-/* enum: get the status of the asynchronous MC_CMD_LICENSING_V3_TEMPORARY_SET
- * operation
- */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_STATUS 0x2
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_IN_SET msgrequest */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LEN 164
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_OP_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_OP_LEN 4
-/* ECDSA license and signature */
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LICENSE_OFST 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LICENSE_LEN 160
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR msgrequest */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR_LEN 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR_OP_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR_OP_LEN 4
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS msgrequest */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS_LEN 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS_OP_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS_OP_LEN 4
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS msgresponse */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LEN 12
-/* status code */
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_STATUS_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_STATUS_LEN 4
-/* enum: finished validating and installing license */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_STATUS_OK 0x0
-/* enum: license validation and installation in progress */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_STATUS_IN_PROGRESS 0x1
-/* enum: licensing error. More specific error messages are not provided to
- * avoid exposing details of the licensing system to the client
- */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_STATUS_ERROR 0x2
-/* bitmask of licensed features */
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_OFST 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LEN 8
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_OFST 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_LEN 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_LBN 32
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_WIDTH 32
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_OFST 8
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_LEN 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_LBN 64
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_SET_PORT_SNIFF_CONFIG
- * Configure RX port sniffing for the physical port associated with the calling
- * function. Only a privileged function may change the port sniffing
- * configuration. A copy of all traffic delivered to the host (non-promiscuous
- * mode) or all traffic arriving at the port (promiscuous mode) may be
- * delivered to a specific queue, or a set of queues with RSS.
- */
-#define MC_CMD_SET_PORT_SNIFF_CONFIG 0xf7
-#undef MC_CMD_0xf7_PRIVILEGE_CTG
-
-#define MC_CMD_0xf7_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_PORT_SNIFF_CONFIG_IN msgrequest */
-#define    MC_CMD_SET_PORT_SNIFF_CONFIG_IN_LEN 16
-/* configuration flags */
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_FLAGS_OFST 0
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_FLAGS_LEN 4
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_OFST 0
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_LBN 0
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_WIDTH 1
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_OFST 0
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_LBN 1
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_WIDTH 1
-/* receive queue handle (for RSS mode, this is the base queue) */
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_QUEUE_OFST 4
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_QUEUE_LEN 4
-/* receive mode */
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_OFST 8
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_LEN 4
-/* enum: receive to just the specified queue */
-#define          MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_SIMPLE 0x0
-/* enum: receive to multiple queues using RSS context */
-#define          MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_RSS 0x1
-/* RSS context (for RX_MODE_RSS) as returned by MC_CMD_RSS_CONTEXT_ALLOC. Note
- * that these handles should be considered opaque to the host, although a value
- * of 0xFFFFFFFF is guaranteed never to be a valid handle.
- */
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_OFST 12
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_LEN 4
-
-/* MC_CMD_SET_PORT_SNIFF_CONFIG_OUT msgresponse */
-#define    MC_CMD_SET_PORT_SNIFF_CONFIG_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_PORT_SNIFF_CONFIG
- * Obtain the current RX port sniffing configuration for the physical port
- * associated with the calling function. Only a privileged function may read
- * the configuration.
- */
-#define MC_CMD_GET_PORT_SNIFF_CONFIG 0xf8
-#undef MC_CMD_0xf8_PRIVILEGE_CTG
-
-#define MC_CMD_0xf8_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PORT_SNIFF_CONFIG_IN msgrequest */
-#define    MC_CMD_GET_PORT_SNIFF_CONFIG_IN_LEN 0
-
-/* MC_CMD_GET_PORT_SNIFF_CONFIG_OUT msgresponse */
-#define    MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_LEN 16
-/* configuration flags */
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_FLAGS_OFST 0
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_OFST 0
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_LBN 0
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_WIDTH 1
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_OFST 0
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_LBN 1
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_WIDTH 1
-/* receiving queue handle (for RSS mode, this is the base queue) */
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_OFST 4
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_LEN 4
-/* receive mode */
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_OFST 8
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_LEN 4
-/* enum: receiving to just the specified queue */
-#define          MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_SIMPLE 0x0
-/* enum: receiving to multiple queues using RSS context */
-#define          MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_RSS 0x1
-/* RSS context (for RX_MODE_RSS) */
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_OFST 12
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_LEN 4
-
-
-/***********************************/
 /* MC_CMD_SET_PARSER_DISP_CONFIG
  * Change configuration related to the parser-dispatcher subsystem.
  */
@@ -22073,305 +21309,6 @@
 
 
 /***********************************/
-/* MC_CMD_GET_PARSER_DISP_CONFIG
- * Read configuration related to the parser-dispatcher subsystem.
- */
-#define MC_CMD_GET_PARSER_DISP_CONFIG 0xfa
-#undef MC_CMD_0xfa_PRIVILEGE_CTG
-
-#define MC_CMD_0xfa_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PARSER_DISP_CONFIG_IN msgrequest */
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_IN_LEN 8
-/* the type of configuration setting to read */
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_IN_TYPE_OFST 0
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_IN_TYPE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_SET_PARSER_DISP_CONFIG/MC_CMD_SET_PARSER_DISP_CONFIG_IN/TYPE */
-/* handle for the entity to query: queue handle, EVB port ID, etc. depending on
- * the type of configuration setting being read
- */
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_IN_ENTITY_OFST 4
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_IN_ENTITY_LEN 4
-
-/* MC_CMD_GET_PARSER_DISP_CONFIG_OUT msgresponse */
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LENMIN 4
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LENMAX 252
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_NUM(len) (((len)-0)/4)
-/* current value: the details depend on the type of configuration setting being
- * read
- */
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_OFST 0
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_LEN 4
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_MINNUM 1
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_MAXNUM 63
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_MAXNUM_MCDI2 255
-
-
-/***********************************/
-/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG
- * Configure TX port sniffing for the physical port associated with the calling
- * function. Only a privileged function may change the port sniffing
- * configuration. A copy of all traffic transmitted through the port may be
- * delivered to a specific queue, or a set of queues with RSS. Note that these
- * packets are delivered with transmit timestamps in the packet prefix, not
- * receive timestamps, so it is likely that the queue(s) will need to be
- * dedicated as TX sniff receivers.
- */
-#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG 0xfb
-#undef MC_CMD_0xfb_PRIVILEGE_CTG
-
-#define MC_CMD_0xfb_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN msgrequest */
-#define    MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_LEN 16
-/* configuration flags */
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_FLAGS_OFST 0
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_FLAGS_LEN 4
-#define        MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_ENABLE_OFST 0
-#define        MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_ENABLE_LBN 0
-#define        MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_ENABLE_WIDTH 1
-/* receive queue handle (for RSS mode, this is the base queue) */
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_QUEUE_OFST 4
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_QUEUE_LEN 4
-/* receive mode */
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_OFST 8
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_LEN 4
-/* enum: receive to just the specified queue */
-#define          MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_SIMPLE 0x0
-/* enum: receive to multiple queues using RSS context */
-#define          MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_RSS 0x1
-/* RSS context (for RX_MODE_RSS) as returned by MC_CMD_RSS_CONTEXT_ALLOC. Note
- * that these handles should be considered opaque to the host, although a value
- * of 0xFFFFFFFF is guaranteed never to be a valid handle.
- */
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_OFST 12
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_LEN 4
-
-/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG_OUT msgresponse */
-#define    MC_CMD_SET_TX_PORT_SNIFF_CONFIG_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG
- * Obtain the current TX port sniffing configuration for the physical port
- * associated with the calling function. Only a privileged function may read
- * the configuration.
- */
-#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG 0xfc
-#undef MC_CMD_0xfc_PRIVILEGE_CTG
-
-#define MC_CMD_0xfc_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG_IN msgrequest */
-#define    MC_CMD_GET_TX_PORT_SNIFF_CONFIG_IN_LEN 0
-
-/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT msgresponse */
-#define    MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_LEN 16
-/* configuration flags */
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_FLAGS_OFST 0
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_ENABLE_OFST 0
-#define        MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_ENABLE_LBN 0
-#define        MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_ENABLE_WIDTH 1
-/* receiving queue handle (for RSS mode, this is the base queue) */
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_OFST 4
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_LEN 4
-/* receive mode */
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_OFST 8
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_LEN 4
-/* enum: receiving to just the specified queue */
-#define          MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_SIMPLE 0x0
-/* enum: receiving to multiple queues using RSS context */
-#define          MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_RSS 0x1
-/* RSS context (for RX_MODE_RSS) */
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_OFST 12
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_LEN 4
-
-
-/***********************************/
-/* MC_CMD_RMON_STATS_RX_ERRORS
- * Per queue rx error stats.
- */
-#define MC_CMD_RMON_STATS_RX_ERRORS 0xfe
-#undef MC_CMD_0xfe_PRIVILEGE_CTG
-
-#define MC_CMD_0xfe_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_RMON_STATS_RX_ERRORS_IN msgrequest */
-#define    MC_CMD_RMON_STATS_RX_ERRORS_IN_LEN 8
-/* The rx queue to get stats for. */
-#define       MC_CMD_RMON_STATS_RX_ERRORS_IN_RX_QUEUE_OFST 0
-#define       MC_CMD_RMON_STATS_RX_ERRORS_IN_RX_QUEUE_LEN 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_IN_FLAGS_OFST 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_IN_FLAGS_LEN 4
-#define        MC_CMD_RMON_STATS_RX_ERRORS_IN_RST_OFST 4
-#define        MC_CMD_RMON_STATS_RX_ERRORS_IN_RST_LBN 0
-#define        MC_CMD_RMON_STATS_RX_ERRORS_IN_RST_WIDTH 1
-
-/* MC_CMD_RMON_STATS_RX_ERRORS_OUT msgresponse */
-#define    MC_CMD_RMON_STATS_RX_ERRORS_OUT_LEN 16
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_CRC_ERRORS_OFST 0
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_CRC_ERRORS_LEN 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_TRUNC_ERRORS_OFST 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_TRUNC_ERRORS_LEN 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_NO_DESC_DROPS_OFST 8
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_NO_DESC_DROPS_LEN 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_ABORT_OFST 12
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_ABORT_LEN 4
-
-
-/***********************************/
-/* MC_CMD_GET_PCIE_RESOURCE_INFO
- * Find out about available PCIE resources
- */
-#define MC_CMD_GET_PCIE_RESOURCE_INFO 0xfd
-#undef MC_CMD_0xfd_PRIVILEGE_CTG
-
-#define MC_CMD_0xfd_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PCIE_RESOURCE_INFO_IN msgrequest */
-#define    MC_CMD_GET_PCIE_RESOURCE_INFO_IN_LEN 0
-
-/* MC_CMD_GET_PCIE_RESOURCE_INFO_OUT msgresponse */
-#define    MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_LEN 28
-/* The maximum number of PFs the device can expose */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PFS_OFST 0
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PFS_LEN 4
-/* The maximum number of VFs the device can expose in total */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VFS_OFST 4
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VFS_LEN 4
-/* The maximum number of MSI-X vectors the device can provide in total */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VECTORS_OFST 8
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VECTORS_LEN 4
-/* the number of MSI-X vectors the device will allocate by default to each PF
- */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_PF_VECTORS_OFST 12
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_PF_VECTORS_LEN 4
-/* the number of MSI-X vectors the device will allocate by default to each VF
- */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_VF_VECTORS_OFST 16
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_VF_VECTORS_LEN 4
-/* the maximum number of MSI-X vectors the device can allocate to any one PF */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PF_VECTORS_OFST 20
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PF_VECTORS_LEN 4
-/* the maximum number of MSI-X vectors the device can allocate to any one VF */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VF_VECTORS_OFST 24
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VF_VECTORS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_GET_PORT_MODES
- * Find out about available port modes
- */
-#define MC_CMD_GET_PORT_MODES 0xff
-#undef MC_CMD_0xff_PRIVILEGE_CTG
-
-#define MC_CMD_0xff_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PORT_MODES_IN msgrequest */
-#define    MC_CMD_GET_PORT_MODES_IN_LEN 0
-
-/* MC_CMD_GET_PORT_MODES_OUT msgresponse */
-#define    MC_CMD_GET_PORT_MODES_OUT_LEN 12
-/* Bitmask of port modes available on the board (indexed by TLV_PORT_MODE_*)
- * that are supported for customer use in production firmware.
- */
-#define       MC_CMD_GET_PORT_MODES_OUT_MODES_OFST 0
-#define       MC_CMD_GET_PORT_MODES_OUT_MODES_LEN 4
-/* Default (canonical) board mode */
-#define       MC_CMD_GET_PORT_MODES_OUT_DEFAULT_MODE_OFST 4
-#define       MC_CMD_GET_PORT_MODES_OUT_DEFAULT_MODE_LEN 4
-/* Current board mode */
-#define       MC_CMD_GET_PORT_MODES_OUT_CURRENT_MODE_OFST 8
-#define       MC_CMD_GET_PORT_MODES_OUT_CURRENT_MODE_LEN 4
-
-/* MC_CMD_GET_PORT_MODES_OUT_V2 msgresponse */
-#define    MC_CMD_GET_PORT_MODES_OUT_V2_LEN 16
-/* Bitmask of port modes available on the board (indexed by TLV_PORT_MODE_*)
- * that are supported for customer use in production firmware.
- */
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_MODES_OFST 0
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_MODES_LEN 4
-/* Default (canonical) board mode */
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_DEFAULT_MODE_OFST 4
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_DEFAULT_MODE_LEN 4
-/* Current board mode */
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_CURRENT_MODE_OFST 8
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_CURRENT_MODE_LEN 4
-/* Bitmask of engineering port modes available on the board (indexed by
- * TLV_PORT_MODE_*). A superset of MC_CMD_GET_PORT_MODES_OUT/MODES that
- * contains all modes implemented in firmware for a particular board. Modes
- * listed in MODES are considered production modes and should be exposed in
- * userland tools. Modes listed in ENGINEERING_MODES, but not in MODES
- * should be considered hidden (not to be exposed in userland tools) and for
- * engineering use only. There are no other semantic differences and any mode
- * listed in either MODES or ENGINEERING_MODES can be set on the board.
- */
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_ENGINEERING_MODES_OFST 12
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_ENGINEERING_MODES_LEN 4
-
-
-/***********************************/
-/* MC_CMD_OVERRIDE_PORT_MODE
- * Override flash config port mode for subsequent MC reboot(s). Override data
- * is stored in the presistent data section of DMEM and activated on next MC
- * warm reboot. A cold reboot resets the override. It is assumed that a
- * sufficient number of PFs are available and that port mapping is valid for
- * the new port mode, as the override does not affect PF configuration.
- */
-#define MC_CMD_OVERRIDE_PORT_MODE 0x137
-#undef MC_CMD_0x137_PRIVILEGE_CTG
-
-#define MC_CMD_0x137_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_OVERRIDE_PORT_MODE_IN msgrequest */
-#define    MC_CMD_OVERRIDE_PORT_MODE_IN_LEN 8
-#define       MC_CMD_OVERRIDE_PORT_MODE_IN_FLAGS_OFST 0
-#define       MC_CMD_OVERRIDE_PORT_MODE_IN_FLAGS_LEN 4
-#define        MC_CMD_OVERRIDE_PORT_MODE_IN_ENABLE_OFST 0
-#define        MC_CMD_OVERRIDE_PORT_MODE_IN_ENABLE_LBN 0
-#define        MC_CMD_OVERRIDE_PORT_MODE_IN_ENABLE_WIDTH 1
-/* New mode (TLV_PORT_MODE_*) to set, if override enabled */
-#define       MC_CMD_OVERRIDE_PORT_MODE_IN_MODE_OFST 4
-#define       MC_CMD_OVERRIDE_PORT_MODE_IN_MODE_LEN 4
-
-/* MC_CMD_OVERRIDE_PORT_MODE_OUT msgresponse */
-#define    MC_CMD_OVERRIDE_PORT_MODE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_READ_ATB
- * Sample voltages on the ATB
- */
-#define MC_CMD_READ_ATB 0x100
-#undef MC_CMD_0x100_PRIVILEGE_CTG
-
-#define MC_CMD_0x100_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_READ_ATB_IN msgrequest */
-#define    MC_CMD_READ_ATB_IN_LEN 16
-#define       MC_CMD_READ_ATB_IN_SIGNAL_BUS_OFST 0
-#define       MC_CMD_READ_ATB_IN_SIGNAL_BUS_LEN 4
-#define          MC_CMD_READ_ATB_IN_BUS_CCOM 0x0 /* enum */
-#define          MC_CMD_READ_ATB_IN_BUS_CKR 0x1 /* enum */
-#define          MC_CMD_READ_ATB_IN_BUS_CPCIE 0x8 /* enum */
-#define       MC_CMD_READ_ATB_IN_SIGNAL_EN_BITNO_OFST 4
-#define       MC_CMD_READ_ATB_IN_SIGNAL_EN_BITNO_LEN 4
-#define       MC_CMD_READ_ATB_IN_SIGNAL_SEL_OFST 8
-#define       MC_CMD_READ_ATB_IN_SIGNAL_SEL_LEN 4
-#define       MC_CMD_READ_ATB_IN_SETTLING_TIME_US_OFST 12
-#define       MC_CMD_READ_ATB_IN_SETTLING_TIME_US_LEN 4
-
-/* MC_CMD_READ_ATB_OUT msgresponse */
-#define    MC_CMD_READ_ATB_OUT_LEN 4
-#define       MC_CMD_READ_ATB_OUT_SAMPLE_MV_OFST 0
-#define       MC_CMD_READ_ATB_OUT_SAMPLE_MV_LEN 4
-
-
-/***********************************/
 /* MC_CMD_GET_WORKAROUNDS
  * Read the list of all implemented and all currently enabled workarounds. The
  * enums here must correspond with those in MC_CMD_WORKAROUND.
@@ -22538,447 +21475,6 @@
 #define       MC_CMD_LINK_STATE_MODE_OUT_OLD_MODE_OFST 0
 #define       MC_CMD_LINK_STATE_MODE_OUT_OLD_MODE_LEN 4
 
-
-/***********************************/
-/* MC_CMD_GET_SNAPSHOT_LENGTH
- * Obtain the current range of allowable values for the SNAPSHOT_LENGTH
- * parameter to MC_CMD_INIT_RXQ.
- */
-#define MC_CMD_GET_SNAPSHOT_LENGTH 0x101
-#undef MC_CMD_0x101_PRIVILEGE_CTG
-
-#define MC_CMD_0x101_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_SNAPSHOT_LENGTH_IN msgrequest */
-#define    MC_CMD_GET_SNAPSHOT_LENGTH_IN_LEN 0
-
-/* MC_CMD_GET_SNAPSHOT_LENGTH_OUT msgresponse */
-#define    MC_CMD_GET_SNAPSHOT_LENGTH_OUT_LEN 8
-/* Minimum acceptable snapshot length. */
-#define       MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MIN_OFST 0
-#define       MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MIN_LEN 4
-/* Maximum acceptable snapshot length. */
-#define       MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MAX_OFST 4
-#define       MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MAX_LEN 4
-
-
-/***********************************/
-/* MC_CMD_FUSE_DIAGS
- * Additional fuse diagnostics
- */
-#define MC_CMD_FUSE_DIAGS 0x102
-#undef MC_CMD_0x102_PRIVILEGE_CTG
-
-#define MC_CMD_0x102_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_FUSE_DIAGS_IN msgrequest */
-#define    MC_CMD_FUSE_DIAGS_IN_LEN 0
-
-/* MC_CMD_FUSE_DIAGS_OUT msgresponse */
-#define    MC_CMD_FUSE_DIAGS_OUT_LEN 48
-/* Total number of mismatched bits between pairs in area 0 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_MISMATCH_BITS_OFST 0
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_MISMATCH_BITS_LEN 4
-/* Total number of unexpectedly clear (set in B but not A) bits in area 0 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_A_BAD_BITS_OFST 4
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_A_BAD_BITS_LEN 4
-/* Total number of unexpectedly clear (set in A but not B) bits in area 0 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_B_BAD_BITS_OFST 8
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_B_BAD_BITS_LEN 4
-/* Checksum of data after logical OR of pairs in area 0 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_CHECKSUM_OFST 12
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_CHECKSUM_LEN 4
-/* Total number of mismatched bits between pairs in area 1 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_MISMATCH_BITS_OFST 16
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_MISMATCH_BITS_LEN 4
-/* Total number of unexpectedly clear (set in B but not A) bits in area 1 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_A_BAD_BITS_OFST 20
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_A_BAD_BITS_LEN 4
-/* Total number of unexpectedly clear (set in A but not B) bits in area 1 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_B_BAD_BITS_OFST 24
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_B_BAD_BITS_LEN 4
-/* Checksum of data after logical OR of pairs in area 1 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_CHECKSUM_OFST 28
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_CHECKSUM_LEN 4
-/* Total number of mismatched bits between pairs in area 2 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_MISMATCH_BITS_OFST 32
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_MISMATCH_BITS_LEN 4
-/* Total number of unexpectedly clear (set in B but not A) bits in area 2 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_A_BAD_BITS_OFST 36
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_A_BAD_BITS_LEN 4
-/* Total number of unexpectedly clear (set in A but not B) bits in area 2 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_B_BAD_BITS_OFST 40
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_B_BAD_BITS_LEN 4
-/* Checksum of data after logical OR of pairs in area 2 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_CHECKSUM_OFST 44
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_CHECKSUM_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PRIVILEGE_MODIFY
- * Modify the privileges of a set of PCIe functions. Note that this operation
- * only effects non-admin functions unless the admin privilege itself is
- * included in one of the masks provided.
- */
-#define MC_CMD_PRIVILEGE_MODIFY 0x60
-#undef MC_CMD_0x60_PRIVILEGE_CTG
-
-#define MC_CMD_0x60_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PRIVILEGE_MODIFY_IN msgrequest */
-#define    MC_CMD_PRIVILEGE_MODIFY_IN_LEN 16
-/* The groups of functions to have their privilege masks modified. */
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_FN_GROUP_OFST 0
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_FN_GROUP_LEN 4
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_NONE 0x0 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_ALL 0x1 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_PFS_ONLY 0x2 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_VFS_ONLY 0x3 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_VFS_OF_PF 0x4 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_ONE 0x5 /* enum */
-/* For VFS_OF_PF specify the PF, for ONE specify the target function */
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_OFST 4
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_LEN 4
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_PF_OFST 4
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_PF_LBN 0
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_PF_WIDTH 16
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_VF_OFST 4
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_VF_LBN 16
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_VF_WIDTH 16
-/* Privileges to be added to the target functions. For privilege definitions
- * refer to the command MC_CMD_PRIVILEGE_MASK
- */
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_ADD_MASK_OFST 8
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_ADD_MASK_LEN 4
-/* Privileges to be removed from the target functions. For privilege
- * definitions refer to the command MC_CMD_PRIVILEGE_MASK
- */
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_REMOVE_MASK_OFST 12
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_REMOVE_MASK_LEN 4
-
-/* MC_CMD_PRIVILEGE_MODIFY_OUT msgresponse */
-#define    MC_CMD_PRIVILEGE_MODIFY_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_READ_BYTES
- * Read XPM memory
- */
-#define MC_CMD_XPM_READ_BYTES 0x103
-#undef MC_CMD_0x103_PRIVILEGE_CTG
-
-#define MC_CMD_0x103_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_XPM_READ_BYTES_IN msgrequest */
-#define    MC_CMD_XPM_READ_BYTES_IN_LEN 8
-/* Start address (byte) */
-#define       MC_CMD_XPM_READ_BYTES_IN_ADDR_OFST 0
-#define       MC_CMD_XPM_READ_BYTES_IN_ADDR_LEN 4
-/* Count (bytes) */
-#define       MC_CMD_XPM_READ_BYTES_IN_COUNT_OFST 4
-#define       MC_CMD_XPM_READ_BYTES_IN_COUNT_LEN 4
-
-/* MC_CMD_XPM_READ_BYTES_OUT msgresponse */
-#define    MC_CMD_XPM_READ_BYTES_OUT_LENMIN 0
-#define    MC_CMD_XPM_READ_BYTES_OUT_LENMAX 252
-#define    MC_CMD_XPM_READ_BYTES_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_XPM_READ_BYTES_OUT_LEN(num) (0+1*(num))
-#define    MC_CMD_XPM_READ_BYTES_OUT_DATA_NUM(len) (((len)-0)/1)
-/* Data */
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_OFST 0
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_LEN 1
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_MINNUM 0
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_MAXNUM 252
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_MAXNUM_MCDI2 1020
-
-
-/***********************************/
-/* MC_CMD_XPM_WRITE_BYTES
- * Write XPM memory
- */
-#define MC_CMD_XPM_WRITE_BYTES 0x104
-#undef MC_CMD_0x104_PRIVILEGE_CTG
-
-#define MC_CMD_0x104_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_WRITE_BYTES_IN msgrequest */
-#define    MC_CMD_XPM_WRITE_BYTES_IN_LENMIN 8
-#define    MC_CMD_XPM_WRITE_BYTES_IN_LENMAX 252
-#define    MC_CMD_XPM_WRITE_BYTES_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_XPM_WRITE_BYTES_IN_LEN(num) (8+1*(num))
-#define    MC_CMD_XPM_WRITE_BYTES_IN_DATA_NUM(len) (((len)-8)/1)
-/* Start address (byte) */
-#define       MC_CMD_XPM_WRITE_BYTES_IN_ADDR_OFST 0
-#define       MC_CMD_XPM_WRITE_BYTES_IN_ADDR_LEN 4
-/* Count (bytes) */
-#define       MC_CMD_XPM_WRITE_BYTES_IN_COUNT_OFST 4
-#define       MC_CMD_XPM_WRITE_BYTES_IN_COUNT_LEN 4
-/* Data */
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_OFST 8
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_LEN 1
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_MINNUM 0
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_MAXNUM 244
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_MAXNUM_MCDI2 1012
-
-/* MC_CMD_XPM_WRITE_BYTES_OUT msgresponse */
-#define    MC_CMD_XPM_WRITE_BYTES_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_READ_SECTOR
- * Read XPM sector
- */
-#define MC_CMD_XPM_READ_SECTOR 0x105
-#undef MC_CMD_0x105_PRIVILEGE_CTG
-
-#define MC_CMD_0x105_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_READ_SECTOR_IN msgrequest */
-#define    MC_CMD_XPM_READ_SECTOR_IN_LEN 8
-/* Sector index */
-#define       MC_CMD_XPM_READ_SECTOR_IN_INDEX_OFST 0
-#define       MC_CMD_XPM_READ_SECTOR_IN_INDEX_LEN 4
-/* Sector size */
-#define       MC_CMD_XPM_READ_SECTOR_IN_SIZE_OFST 4
-#define       MC_CMD_XPM_READ_SECTOR_IN_SIZE_LEN 4
-
-/* MC_CMD_XPM_READ_SECTOR_OUT msgresponse */
-#define    MC_CMD_XPM_READ_SECTOR_OUT_LENMIN 4
-#define    MC_CMD_XPM_READ_SECTOR_OUT_LENMAX 36
-#define    MC_CMD_XPM_READ_SECTOR_OUT_LENMAX_MCDI2 36
-#define    MC_CMD_XPM_READ_SECTOR_OUT_LEN(num) (4+1*(num))
-#define    MC_CMD_XPM_READ_SECTOR_OUT_DATA_NUM(len) (((len)-4)/1)
-/* Sector type */
-#define       MC_CMD_XPM_READ_SECTOR_OUT_TYPE_OFST 0
-#define       MC_CMD_XPM_READ_SECTOR_OUT_TYPE_LEN 4
-#define          MC_CMD_XPM_READ_SECTOR_OUT_BLANK 0x0 /* enum */
-#define          MC_CMD_XPM_READ_SECTOR_OUT_CRYPTO_KEY_128 0x1 /* enum */
-#define          MC_CMD_XPM_READ_SECTOR_OUT_CRYPTO_KEY_256 0x2 /* enum */
-#define          MC_CMD_XPM_READ_SECTOR_OUT_CRYPTO_DATA 0x3 /* enum */
-#define          MC_CMD_XPM_READ_SECTOR_OUT_INVALID 0xff /* enum */
-/* Sector data */
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_OFST 4
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_LEN 1
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_MINNUM 0
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_MAXNUM 32
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_MAXNUM_MCDI2 32
-
-
-/***********************************/
-/* MC_CMD_XPM_WRITE_SECTOR
- * Write XPM sector
- */
-#define MC_CMD_XPM_WRITE_SECTOR 0x106
-#undef MC_CMD_0x106_PRIVILEGE_CTG
-
-#define MC_CMD_0x106_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_WRITE_SECTOR_IN msgrequest */
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_LENMIN 12
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_LENMAX 44
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_LENMAX_MCDI2 44
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_LEN(num) (12+1*(num))
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_DATA_NUM(len) (((len)-12)/1)
-/* If writing fails due to an uncorrectable error, try up to RETRIES following
- * sectors (or until no more space available). If 0, only one write attempt is
- * made. Note that uncorrectable errors are unlikely, thanks to XPM self-repair
- * mechanism.
- */
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_RETRIES_OFST 0
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_RETRIES_LEN 1
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_RESERVED_OFST 1
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_RESERVED_LEN 3
-/* Sector type */
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_TYPE_OFST 4
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_TYPE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_XPM_READ_SECTOR/MC_CMD_XPM_READ_SECTOR_OUT/TYPE */
-/* Sector size */
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_SIZE_OFST 8
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_SIZE_LEN 4
-/* Sector data */
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_OFST 12
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_LEN 1
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_MINNUM 0
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_MAXNUM 32
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_MAXNUM_MCDI2 32
-
-/* MC_CMD_XPM_WRITE_SECTOR_OUT msgresponse */
-#define    MC_CMD_XPM_WRITE_SECTOR_OUT_LEN 4
-/* New sector index */
-#define       MC_CMD_XPM_WRITE_SECTOR_OUT_INDEX_OFST 0
-#define       MC_CMD_XPM_WRITE_SECTOR_OUT_INDEX_LEN 4
-
-
-/***********************************/
-/* MC_CMD_XPM_INVALIDATE_SECTOR
- * Invalidate XPM sector
- */
-#define MC_CMD_XPM_INVALIDATE_SECTOR 0x107
-#undef MC_CMD_0x107_PRIVILEGE_CTG
-
-#define MC_CMD_0x107_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_INVALIDATE_SECTOR_IN msgrequest */
-#define    MC_CMD_XPM_INVALIDATE_SECTOR_IN_LEN 4
-/* Sector index */
-#define       MC_CMD_XPM_INVALIDATE_SECTOR_IN_INDEX_OFST 0
-#define       MC_CMD_XPM_INVALIDATE_SECTOR_IN_INDEX_LEN 4
-
-/* MC_CMD_XPM_INVALIDATE_SECTOR_OUT msgresponse */
-#define    MC_CMD_XPM_INVALIDATE_SECTOR_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_BLANK_CHECK
- * Blank-check XPM memory and report bad locations
- */
-#define MC_CMD_XPM_BLANK_CHECK 0x108
-#undef MC_CMD_0x108_PRIVILEGE_CTG
-
-#define MC_CMD_0x108_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_BLANK_CHECK_IN msgrequest */
-#define    MC_CMD_XPM_BLANK_CHECK_IN_LEN 8
-/* Start address (byte) */
-#define       MC_CMD_XPM_BLANK_CHECK_IN_ADDR_OFST 0
-#define       MC_CMD_XPM_BLANK_CHECK_IN_ADDR_LEN 4
-/* Count (bytes) */
-#define       MC_CMD_XPM_BLANK_CHECK_IN_COUNT_OFST 4
-#define       MC_CMD_XPM_BLANK_CHECK_IN_COUNT_LEN 4
-
-/* MC_CMD_XPM_BLANK_CHECK_OUT msgresponse */
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_LENMIN 4
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_LENMAX 252
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_LEN(num) (4+2*(num))
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_NUM(len) (((len)-4)/2)
-/* Total number of bad (non-blank) locations */
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_COUNT_OFST 0
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_COUNT_LEN 4
-/* Addresses of bad locations (may be less than BAD_COUNT, if all cannot fit
- * into MCDI response)
- */
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_OFST 4
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_LEN 2
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_MINNUM 0
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_MAXNUM 124
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_MAXNUM_MCDI2 508
-
-
-/***********************************/
-/* MC_CMD_XPM_REPAIR
- * Blank-check and repair XPM memory
- */
-#define MC_CMD_XPM_REPAIR 0x109
-#undef MC_CMD_0x109_PRIVILEGE_CTG
-
-#define MC_CMD_0x109_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_REPAIR_IN msgrequest */
-#define    MC_CMD_XPM_REPAIR_IN_LEN 8
-/* Start address (byte) */
-#define       MC_CMD_XPM_REPAIR_IN_ADDR_OFST 0
-#define       MC_CMD_XPM_REPAIR_IN_ADDR_LEN 4
-/* Count (bytes) */
-#define       MC_CMD_XPM_REPAIR_IN_COUNT_OFST 4
-#define       MC_CMD_XPM_REPAIR_IN_COUNT_LEN 4
-
-/* MC_CMD_XPM_REPAIR_OUT msgresponse */
-#define    MC_CMD_XPM_REPAIR_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_DECODER_TEST
- * Test XPM memory address decoders for gross manufacturing defects. Can only
- * be performed on an unprogrammed part.
- */
-#define MC_CMD_XPM_DECODER_TEST 0x10a
-#undef MC_CMD_0x10a_PRIVILEGE_CTG
-
-#define MC_CMD_0x10a_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_DECODER_TEST_IN msgrequest */
-#define    MC_CMD_XPM_DECODER_TEST_IN_LEN 0
-
-/* MC_CMD_XPM_DECODER_TEST_OUT msgresponse */
-#define    MC_CMD_XPM_DECODER_TEST_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_WRITE_TEST
- * XPM memory write test. Test XPM write logic for gross manufacturing defects
- * by writing to a dedicated test row. There are 16 locations in the test row
- * and the test can only be performed on locations that have not been
- * previously used (i.e. can be run at most 16 times). The test will pick the
- * first available location to use, or fail with ENOSPC if none left.
- */
-#define MC_CMD_XPM_WRITE_TEST 0x10b
-#undef MC_CMD_0x10b_PRIVILEGE_CTG
-
-#define MC_CMD_0x10b_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_WRITE_TEST_IN msgrequest */
-#define    MC_CMD_XPM_WRITE_TEST_IN_LEN 0
-
-/* MC_CMD_XPM_WRITE_TEST_OUT msgresponse */
-#define    MC_CMD_XPM_WRITE_TEST_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_EXEC_SIGNED
- * Check the CMAC of the contents of IMEM and DMEM against the value supplied
- * and if correct begin execution from the start of IMEM. The caller supplies a
- * key ID, the length of IMEM and DMEM to validate and the expected CMAC. CMAC
- * computation runs from the start of IMEM, and from the start of DMEM + 16k,
- * to match flash booting. The command will respond with EINVAL if the CMAC
- * does match, otherwise it will respond with success before it jumps to IMEM.
- */
-#define MC_CMD_EXEC_SIGNED 0x10c
-#undef MC_CMD_0x10c_PRIVILEGE_CTG
-
-#define MC_CMD_0x10c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_EXEC_SIGNED_IN msgrequest */
-#define    MC_CMD_EXEC_SIGNED_IN_LEN 28
-/* the length of code to include in the CMAC */
-#define       MC_CMD_EXEC_SIGNED_IN_CODELEN_OFST 0
-#define       MC_CMD_EXEC_SIGNED_IN_CODELEN_LEN 4
-/* the length of date to include in the CMAC */
-#define       MC_CMD_EXEC_SIGNED_IN_DATALEN_OFST 4
-#define       MC_CMD_EXEC_SIGNED_IN_DATALEN_LEN 4
-/* the XPM sector containing the key to use */
-#define       MC_CMD_EXEC_SIGNED_IN_KEYSECTOR_OFST 8
-#define       MC_CMD_EXEC_SIGNED_IN_KEYSECTOR_LEN 4
-/* the expected CMAC value */
-#define       MC_CMD_EXEC_SIGNED_IN_CMAC_OFST 12
-#define       MC_CMD_EXEC_SIGNED_IN_CMAC_LEN 16
-
-/* MC_CMD_EXEC_SIGNED_OUT msgresponse */
-#define    MC_CMD_EXEC_SIGNED_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_PREPARE_SIGNED
- * Prepare to upload a signed image. This will scrub the specified length of
- * the data region, which must be at least as large as the DATALEN supplied to
- * MC_CMD_EXEC_SIGNED.
- */
-#define MC_CMD_PREPARE_SIGNED 0x10d
-#undef MC_CMD_0x10d_PRIVILEGE_CTG
-
-#define MC_CMD_0x10d_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PREPARE_SIGNED_IN msgrequest */
-#define    MC_CMD_PREPARE_SIGNED_IN_LEN 4
-/* the length of data area to clear */
-#define       MC_CMD_PREPARE_SIGNED_IN_DATALEN_OFST 0
-#define       MC_CMD_PREPARE_SIGNED_IN_DATALEN_LEN 4
-
-/* MC_CMD_PREPARE_SIGNED_OUT msgresponse */
-#define    MC_CMD_PREPARE_SIGNED_OUT_LEN 0
-
-
 /* TUNNEL_ENCAP_UDP_PORT_ENTRY structuredef */
 #define    TUNNEL_ENCAP_UDP_PORT_ENTRY_LEN 4
 /* UDP port (the standard ports are named below but any port may be used) */
@@ -23049,110 +21545,6 @@
 
 
 /***********************************/
-/* MC_CMD_RX_BALANCING
- * Configure a port upconverter to distribute the packets on both RX engines.
- * Packets are distributed based on a table with the destination vFIFO. The
- * index of the table is a hash of source and destination of IPV4 and VLAN
- * priority.
- */
-#define MC_CMD_RX_BALANCING 0x118
-#undef MC_CMD_0x118_PRIVILEGE_CTG
-
-#define MC_CMD_0x118_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_RX_BALANCING_IN msgrequest */
-#define    MC_CMD_RX_BALANCING_IN_LEN 16
-/* The RX port whose upconverter table will be modified */
-#define       MC_CMD_RX_BALANCING_IN_PORT_OFST 0
-#define       MC_CMD_RX_BALANCING_IN_PORT_LEN 4
-/* The VLAN priority associated to the table index and vFIFO */
-#define       MC_CMD_RX_BALANCING_IN_PRIORITY_OFST 4
-#define       MC_CMD_RX_BALANCING_IN_PRIORITY_LEN 4
-/* The resulting bit of SRC^DST for indexing the table */
-#define       MC_CMD_RX_BALANCING_IN_SRC_DST_OFST 8
-#define       MC_CMD_RX_BALANCING_IN_SRC_DST_LEN 4
-/* The RX engine to which the vFIFO in the table entry will point to */
-#define       MC_CMD_RX_BALANCING_IN_ENG_OFST 12
-#define       MC_CMD_RX_BALANCING_IN_ENG_LEN 4
-
-/* MC_CMD_RX_BALANCING_OUT msgresponse */
-#define    MC_CMD_RX_BALANCING_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_NVRAM_PRIVATE_APPEND
- * Append a single TLV to the MC_USAGE_TLV partition. Returns MC_CMD_ERR_EEXIST
- * if the tag is already present.
- */
-#define MC_CMD_NVRAM_PRIVATE_APPEND 0x11c
-#undef MC_CMD_0x11c_PRIVILEGE_CTG
-
-#define MC_CMD_0x11c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_NVRAM_PRIVATE_APPEND_IN msgrequest */
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENMIN 9
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENMAX 252
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_LEN(num) (8+1*(num))
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_NUM(len) (((len)-8)/1)
-/* The tag to be appended */
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_TAG_OFST 0
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_TAG_LEN 4
-/* The length of the data */
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENGTH_OFST 4
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENGTH_LEN 4
-/* The data to be contained in the TLV structure */
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_OFST 8
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_LEN 1
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_MINNUM 1
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_MAXNUM 244
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_MAXNUM_MCDI2 1012
-
-/* MC_CMD_NVRAM_PRIVATE_APPEND_OUT msgresponse */
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_VERIFY_CONTENTS
- * Verify that the contents of the XPM memory is correct (Medford only). This
- * is used during manufacture to check that the XPM memory has been programmed
- * correctly at ATE.
- */
-#define MC_CMD_XPM_VERIFY_CONTENTS 0x11b
-#undef MC_CMD_0x11b_PRIVILEGE_CTG
-
-#define MC_CMD_0x11b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_XPM_VERIFY_CONTENTS_IN msgrequest */
-#define    MC_CMD_XPM_VERIFY_CONTENTS_IN_LEN 4
-/* Data type to be checked */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_IN_DATA_TYPE_OFST 0
-#define       MC_CMD_XPM_VERIFY_CONTENTS_IN_DATA_TYPE_LEN 4
-
-/* MC_CMD_XPM_VERIFY_CONTENTS_OUT msgresponse */
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_LENMIN 12
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_LENMAX 252
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_LEN(num) (12+1*(num))
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_NUM(len) (((len)-12)/1)
-/* Number of sectors found (test builds only) */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_SECTORS_OFST 0
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_SECTORS_LEN 4
-/* Number of bytes found (test builds only) */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_BYTES_OFST 4
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_BYTES_LEN 4
-/* Length of signature */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIG_LENGTH_OFST 8
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIG_LENGTH_LEN 4
-/* Signature */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_OFST 12
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_LEN 1
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_MINNUM 0
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_MAXNUM 240
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_MAXNUM_MCDI2 1008
-
-
-/***********************************/
 /* MC_CMD_SET_EVQ_TMR
  * Update the timer load, timer reload and timer mode values for a given EVQ.
  * The requested timer values (in TMR_LOAD_REQ_NS and TMR_RELOAD_REQ_NS) will
@@ -23262,576 +21654,6 @@
 #define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_STEP_OFST 32
 #define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_STEP_LEN 4
 
-
-/***********************************/
-/* MC_CMD_ALLOCATE_TX_VFIFO_CP
- * When we use the TX_vFIFO_ULL mode, we can allocate common pools using the
- * non used switch buffers.
- */
-#define MC_CMD_ALLOCATE_TX_VFIFO_CP 0x11d
-#undef MC_CMD_0x11d_PRIVILEGE_CTG
-
-#define MC_CMD_0x11d_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_ALLOCATE_TX_VFIFO_CP_IN msgrequest */
-#define    MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_LEN 20
-/* Desired instance. Must be set to a specific instance, which is a function
- * local queue index. The calling client must be the currently-assigned user of
- * this VI (see MC_CMD_SET_VI_USER).
- */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INSTANCE_OFST 0
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INSTANCE_LEN 4
-/* Will the common pool be used as TX_vFIFO_ULL (1) */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_MODE_OFST 4
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_MODE_LEN 4
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_ENABLED 0x1 /* enum */
-/* enum: Using this interface without TX_vFIFO_ULL is not supported for now */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_DISABLED 0x0
-/* Number of buffers to reserve for the common pool */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_SIZE_OFST 8
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_SIZE_LEN 4
-/* TX datapath to which the Common Pool is connected to. */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INGRESS_OFST 12
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INGRESS_LEN 4
-/* enum: Extracts information from function */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_USE_FUNCTION_VALUE -0x1
-/* Network port or RX Engine to which the common pool connects. */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_EGRESS_OFST 16
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_EGRESS_LEN 4
-/* enum: Extracts information from function */
-/*               MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_USE_FUNCTION_VALUE -0x1 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT0 0x0 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT1 0x1 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT2 0x2 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT3 0x3 /* enum */
-/* enum: To enable Switch loopback with Rx engine 0 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_RX_ENGINE0 0x4
-/* enum: To enable Switch loopback with Rx engine 1 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_RX_ENGINE1 0x5
-
-/* MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT msgresponse */
-#define    MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT_LEN 4
-/* ID of the common pool allocated */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT_CP_ID_OFST 0
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT_CP_ID_LEN 4
-
-
-/***********************************/
-/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO
- * When we use the TX_vFIFO_ULL mode, we can allocate vFIFOs using the
- * previously allocated common pools.
- */
-#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO 0x11e
-#undef MC_CMD_0x11e_PRIVILEGE_CTG
-
-#define MC_CMD_0x11e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN msgrequest */
-#define    MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_LEN 20
-/* Common pool previously allocated to which the new vFIFO will be associated
- */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_CP_OFST 0
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_CP_LEN 4
-/* Port or RX engine to associate the vFIFO egress */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_EGRESS_OFST 4
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_EGRESS_LEN 4
-/* enum: Extracts information from common pool */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_USE_CP_VALUE -0x1
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT0 0x0 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT1 0x1 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT2 0x2 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT3 0x3 /* enum */
-/* enum: To enable Switch loopback with Rx engine 0 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_RX_ENGINE0 0x4
-/* enum: To enable Switch loopback with Rx engine 1 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_RX_ENGINE1 0x5
-/* Minimum number of buffers that the pool must have */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_SIZE_OFST 8
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_SIZE_LEN 4
-/* enum: Do not check the space available */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_NO_MINIMUM 0x0
-/* Will the vFIFO be used as TX_vFIFO_ULL */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_MODE_OFST 12
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_MODE_LEN 4
-/* Network priority of the vFIFO,if applicable */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PRIORITY_OFST 16
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PRIORITY_LEN 4
-/* enum: Search for the lowest unused priority */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_LOWEST_AVAILABLE -0x1
-
-/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT msgresponse */
-#define    MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_LEN 8
-/* Short vFIFO ID */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_VID_OFST 0
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_VID_LEN 4
-/* Network priority of the vFIFO */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_PRIORITY_OFST 4
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_PRIORITY_LEN 4
-
-
-/***********************************/
-/* MC_CMD_TEARDOWN_TX_VFIFO_VF
- * This interface clears the configuration of the given vFIFO and leaves it
- * ready to be re-used.
- */
-#define MC_CMD_TEARDOWN_TX_VFIFO_VF 0x11f
-#undef MC_CMD_0x11f_PRIVILEGE_CTG
-
-#define MC_CMD_0x11f_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TEARDOWN_TX_VFIFO_VF_IN msgrequest */
-#define    MC_CMD_TEARDOWN_TX_VFIFO_VF_IN_LEN 4
-/* Short vFIFO ID */
-#define       MC_CMD_TEARDOWN_TX_VFIFO_VF_IN_VFIFO_OFST 0
-#define       MC_CMD_TEARDOWN_TX_VFIFO_VF_IN_VFIFO_LEN 4
-
-/* MC_CMD_TEARDOWN_TX_VFIFO_VF_OUT msgresponse */
-#define    MC_CMD_TEARDOWN_TX_VFIFO_VF_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DEALLOCATE_TX_VFIFO_CP
- * This interface clears the configuration of the given common pool and leaves
- * it ready to be re-used.
- */
-#define MC_CMD_DEALLOCATE_TX_VFIFO_CP 0x121
-#undef MC_CMD_0x121_PRIVILEGE_CTG
-
-#define MC_CMD_0x121_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN msgrequest */
-#define    MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN_LEN 4
-/* Common pool ID given when pool allocated */
-#define       MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN_POOL_ID_OFST 0
-#define       MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN_POOL_ID_LEN 4
-
-/* MC_CMD_DEALLOCATE_TX_VFIFO_CP_OUT msgresponse */
-#define    MC_CMD_DEALLOCATE_TX_VFIFO_CP_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS
- * This interface allows the host to find out how many common pool buffers are
- * not yet assigned.
- */
-#define MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS 0x124
-#undef MC_CMD_0x124_PRIVILEGE_CTG
-
-#define MC_CMD_0x124_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_IN msgrequest */
-#define    MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_IN_LEN 0
-
-/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT msgresponse */
-#define    MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_LEN 8
-/* Available buffers for the ENG to NET vFIFOs. */
-#define       MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_NET_OFST 0
-#define       MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_NET_LEN 4
-/* Available buffers for the ENG to ENG and NET to ENG vFIFOs. */
-#define       MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_ENG_OFST 4
-#define       MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_ENG_LEN 4
-
-
-/***********************************/
-/* MC_CMD_SUC_VERSION
- * Get the version of the SUC
- */
-#define MC_CMD_SUC_VERSION 0x134
-#undef MC_CMD_0x134_PRIVILEGE_CTG
-
-#define MC_CMD_0x134_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_SUC_VERSION_IN msgrequest */
-#define    MC_CMD_SUC_VERSION_IN_LEN 0
-
-/* MC_CMD_SUC_VERSION_OUT msgresponse */
-#define    MC_CMD_SUC_VERSION_OUT_LEN 24
-/* The SUC firmware version as four numbers - a.b.c.d */
-#define       MC_CMD_SUC_VERSION_OUT_VERSION_OFST 0
-#define       MC_CMD_SUC_VERSION_OUT_VERSION_LEN 4
-#define       MC_CMD_SUC_VERSION_OUT_VERSION_NUM 4
-/* The date, in seconds since the Unix epoch, when the firmware image was
- * built.
- */
-#define       MC_CMD_SUC_VERSION_OUT_BUILD_DATE_OFST 16
-#define       MC_CMD_SUC_VERSION_OUT_BUILD_DATE_LEN 4
-/* The ID of the SUC chip. This is specific to the platform but typically
- * indicates family, memory sizes etc. See SF-116728-SW for further details.
- */
-#define       MC_CMD_SUC_VERSION_OUT_CHIP_ID_OFST 20
-#define       MC_CMD_SUC_VERSION_OUT_CHIP_ID_LEN 4
-
-/* MC_CMD_SUC_BOOT_VERSION_IN msgrequest: Get the version of the SUC boot
- * loader.
- */
-#define    MC_CMD_SUC_BOOT_VERSION_IN_LEN 4
-#define       MC_CMD_SUC_BOOT_VERSION_IN_MAGIC_OFST 0
-#define       MC_CMD_SUC_BOOT_VERSION_IN_MAGIC_LEN 4
-/* enum: Requests the SUC boot version. */
-#define          MC_CMD_SUC_VERSION_GET_BOOT_VERSION 0xb007700b
-
-/* MC_CMD_SUC_BOOT_VERSION_OUT msgresponse */
-#define    MC_CMD_SUC_BOOT_VERSION_OUT_LEN 4
-/* The SUC boot version */
-#define       MC_CMD_SUC_BOOT_VERSION_OUT_VERSION_OFST 0
-#define       MC_CMD_SUC_BOOT_VERSION_OUT_VERSION_LEN 4
-
-
-/***********************************/
-/* MC_CMD_GET_RX_PREFIX_ID
- * This command is part of the mechanism for configuring the format of the RX
- * packet prefix. It takes as input a bitmask of the fields the host would like
- * to be in the prefix. If the hardware supports RX prefixes with that
- * combination of fields, then this command returns a list of prefix-ids,
- * opaque identifiers suitable for use in the RX_PREFIX_ID field of a
- * MC_CMD_INIT_RXQ_V5_IN message. If the combination of fields is not
- * supported, returns ENOTSUP. If the firmware can't create any new prefix-ids
- * due to resource constraints, returns ENOSPC.
- */
-#define MC_CMD_GET_RX_PREFIX_ID 0x13b
-#undef MC_CMD_0x13b_PRIVILEGE_CTG
-
-#define MC_CMD_0x13b_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_RX_PREFIX_ID_IN msgrequest */
-#define    MC_CMD_GET_RX_PREFIX_ID_IN_LEN 8
-/* Field bitmask. */
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_OFST 0
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LEN 8
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LO_OFST 0
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LO_LEN 4
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LO_LBN 0
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LO_WIDTH 32
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_HI_OFST 4
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_HI_LEN 4
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_HI_LBN 32
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_HI_WIDTH 32
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_LENGTH_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_LENGTH_LBN 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_LENGTH_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_VALID_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_VALID_LBN 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_VALID_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_FLAG_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_FLAG_LBN 2
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_FLAG_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CLASS_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CLASS_LBN 3
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CLASS_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_PARTIAL_TSTAMP_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_PARTIAL_TSTAMP_LBN 4
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_PARTIAL_TSTAMP_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_LBN 5
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_MARK_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_MARK_LBN 6
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_MARK_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_MPORT_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_MPORT_LBN 7
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_MPORT_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_VPORT_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_VPORT_LBN 7
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_VPORT_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CSUM_FRAME_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CSUM_FRAME_LBN 8
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CSUM_FRAME_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIP_TCI_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIP_TCI_LBN 9
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIP_TCI_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIPPED_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIPPED_LBN 10
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIPPED_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VSWITCH_STATUS_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VSWITCH_STATUS_LBN 11
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VSWITCH_STATUS_WIDTH 1
-
-/* MC_CMD_GET_RX_PREFIX_ID_OUT msgresponse */
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_LENMIN 8
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_LENMAX 252
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_LEN(num) (4+4*(num))
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_NUM(len) (((len)-4)/4)
-/* Number of prefix-ids returned */
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_NUM_RX_PREFIX_IDS_OFST 0
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_NUM_RX_PREFIX_IDS_LEN 4
-/* Opaque prefix identifiers which can be passed into MC_CMD_INIT_RXQ_V5 or
- * MC_CMD_QUERY_PREFIX_ID
- */
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_OFST 4
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_LEN 4
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_MINNUM 1
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_MAXNUM 62
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_MAXNUM_MCDI2 254
-
-/* RX_PREFIX_FIELD_INFO structuredef: Information about a single RX prefix
- * field
- */
-#define    RX_PREFIX_FIELD_INFO_LEN 4
-/* The offset of the field from the start of the prefix, in bits */
-#define       RX_PREFIX_FIELD_INFO_OFFSET_BITS_OFST 0
-#define       RX_PREFIX_FIELD_INFO_OFFSET_BITS_LEN 2
-#define       RX_PREFIX_FIELD_INFO_OFFSET_BITS_LBN 0
-#define       RX_PREFIX_FIELD_INFO_OFFSET_BITS_WIDTH 16
-/* The width of the field, in bits */
-#define       RX_PREFIX_FIELD_INFO_WIDTH_BITS_OFST 2
-#define       RX_PREFIX_FIELD_INFO_WIDTH_BITS_LEN 1
-#define       RX_PREFIX_FIELD_INFO_WIDTH_BITS_LBN 16
-#define       RX_PREFIX_FIELD_INFO_WIDTH_BITS_WIDTH 8
-/* The type of the field. These enum values are in the same order as the fields
- * in the MC_CMD_GET_RX_PREFIX_ID_IN bitmask
- */
-#define       RX_PREFIX_FIELD_INFO_TYPE_OFST 3
-#define       RX_PREFIX_FIELD_INFO_TYPE_LEN 1
-#define          RX_PREFIX_FIELD_INFO_LENGTH 0x0 /* enum */
-#define          RX_PREFIX_FIELD_INFO_RSS_HASH_VALID 0x1 /* enum */
-#define          RX_PREFIX_FIELD_INFO_USER_FLAG 0x2 /* enum */
-#define          RX_PREFIX_FIELD_INFO_CLASS 0x3 /* enum */
-#define          RX_PREFIX_FIELD_INFO_PARTIAL_TSTAMP 0x4 /* enum */
-#define          RX_PREFIX_FIELD_INFO_RSS_HASH 0x5 /* enum */
-#define          RX_PREFIX_FIELD_INFO_USER_MARK 0x6 /* enum */
-#define          RX_PREFIX_FIELD_INFO_INGRESS_MPORT 0x7 /* enum */
-#define          RX_PREFIX_FIELD_INFO_INGRESS_VPORT 0x7 /* enum */
-#define          RX_PREFIX_FIELD_INFO_CSUM_FRAME 0x8 /* enum */
-#define          RX_PREFIX_FIELD_INFO_VLAN_STRIP_TCI 0x9 /* enum */
-#define          RX_PREFIX_FIELD_INFO_VLAN_STRIPPED 0xa /* enum */
-#define          RX_PREFIX_FIELD_INFO_VSWITCH_STATUS 0xb /* enum */
-#define       RX_PREFIX_FIELD_INFO_TYPE_LBN 24
-#define       RX_PREFIX_FIELD_INFO_TYPE_WIDTH 8
-
-/* RX_PREFIX_FIXED_RESPONSE structuredef: Information about an RX prefix in
- * which every field has a fixed offset and width
- */
-#define    RX_PREFIX_FIXED_RESPONSE_LENMIN 4
-#define    RX_PREFIX_FIXED_RESPONSE_LENMAX 252
-#define    RX_PREFIX_FIXED_RESPONSE_LENMAX_MCDI2 1020
-#define    RX_PREFIX_FIXED_RESPONSE_LEN(num) (4+4*(num))
-#define    RX_PREFIX_FIXED_RESPONSE_FIELDS_NUM(len) (((len)-4)/4)
-/* Length of the RX prefix in bytes */
-#define       RX_PREFIX_FIXED_RESPONSE_PREFIX_LENGTH_BYTES_OFST 0
-#define       RX_PREFIX_FIXED_RESPONSE_PREFIX_LENGTH_BYTES_LEN 1
-#define       RX_PREFIX_FIXED_RESPONSE_PREFIX_LENGTH_BYTES_LBN 0
-#define       RX_PREFIX_FIXED_RESPONSE_PREFIX_LENGTH_BYTES_WIDTH 8
-/* Number of fields present in the prefix */
-#define       RX_PREFIX_FIXED_RESPONSE_FIELD_COUNT_OFST 1
-#define       RX_PREFIX_FIXED_RESPONSE_FIELD_COUNT_LEN 1
-#define       RX_PREFIX_FIXED_RESPONSE_FIELD_COUNT_LBN 8
-#define       RX_PREFIX_FIXED_RESPONSE_FIELD_COUNT_WIDTH 8
-#define       RX_PREFIX_FIXED_RESPONSE_RESERVED_OFST 2
-#define       RX_PREFIX_FIXED_RESPONSE_RESERVED_LEN 2
-#define       RX_PREFIX_FIXED_RESPONSE_RESERVED_LBN 16
-#define       RX_PREFIX_FIXED_RESPONSE_RESERVED_WIDTH 16
-/* Array of RX_PREFIX_FIELD_INFO structures, of length FIELD_COUNT */
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_OFST 4
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_LEN 4
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_MINNUM 0
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_MAXNUM 62
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_MAXNUM_MCDI2 254
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_LBN 32
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_QUERY_RX_PREFIX_ID
- * This command takes an RX prefix id (obtained from MC_CMD_GET_RX_PREFIX_ID)
- * and returns a description of the RX prefix of packets delievered to an RXQ
- * created with that prefix id
- */
-#define MC_CMD_QUERY_RX_PREFIX_ID 0x13c
-#undef MC_CMD_0x13c_PRIVILEGE_CTG
-
-#define MC_CMD_0x13c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_QUERY_RX_PREFIX_ID_IN msgrequest */
-#define    MC_CMD_QUERY_RX_PREFIX_ID_IN_LEN 4
-/* Prefix id to query */
-#define       MC_CMD_QUERY_RX_PREFIX_ID_IN_RX_PREFIX_ID_OFST 0
-#define       MC_CMD_QUERY_RX_PREFIX_ID_IN_RX_PREFIX_ID_LEN 4
-
-/* MC_CMD_QUERY_RX_PREFIX_ID_OUT msgresponse */
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_LENMIN 4
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_LENMAX 252
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_LEN(num) (4+1*(num))
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_NUM(len) (((len)-4)/1)
-/* An enum describing the structure of this response. */
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_TYPE_OFST 0
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_TYPE_LEN 1
-/* enum: The response is of format RX_PREFIX_FIXED_RESPONSE */
-#define          MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_TYPE_FIXED 0x0
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESERVED_OFST 1
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESERVED_LEN 3
-/* The response. Its format is as defined by the RESPONSE_TYPE value */
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_OFST 4
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_LEN 1
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_MINNUM 0
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_MAXNUM 248
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_MAXNUM_MCDI2 1016
-
-
-/***********************************/
-/* MC_CMD_BUNDLE
- * A command to perform various bundle-related operations on insecure cards.
- */
-#define MC_CMD_BUNDLE 0x13d
-#undef MC_CMD_0x13d_PRIVILEGE_CTG
-
-#define MC_CMD_0x13d_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_BUNDLE_IN msgrequest */
-#define    MC_CMD_BUNDLE_IN_LEN 4
-/* Sub-command code */
-#define       MC_CMD_BUNDLE_IN_OP_OFST 0
-#define       MC_CMD_BUNDLE_IN_OP_LEN 4
-/* enum: Get the current host access mode set on component partitions. */
-#define          MC_CMD_BUNDLE_IN_OP_COMPONENT_ACCESS_GET 0x0
-/* enum: Set the host access mode set on component partitions. */
-#define          MC_CMD_BUNDLE_IN_OP_COMPONENT_ACCESS_SET 0x1
-
-/* MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_IN msgrequest: Retrieve the current
- * access mode on component partitions such as MC_FIRMWARE, SUC_FIRMWARE and
- * EXPANSION_UEFI. This command only works on engineering (insecure) cards. On
- * secure adapters, this command returns MC_CMD_ERR_EPERM.
- */
-#define    MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_IN_LEN 4
-/* Sub-command code. Must be OP_COMPONENT_ACCESS_GET. */
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_IN_OP_OFST 0
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_IN_OP_LEN 4
-
-/* MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT msgresponse: Returns the access
- * control mode.
- */
-#define    MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT_LEN 4
-/* Access mode of component partitions. */
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT_ACCESS_MODE_OFST 0
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT_ACCESS_MODE_LEN 4
-/* enum: Component partitions are read-only from the host. */
-#define          MC_CMD_BUNDLE_COMPONENTS_READ_ONLY 0x0
-/* enum: Component partitions can read read-from written-to by the host. */
-#define          MC_CMD_BUNDLE_COMPONENTS_READ_WRITE 0x1
-
-/* MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN msgrequest: The component
- * partitions such as MC_FIRMWARE, SUC_FIRMWARE, EXPANSION_UEFI are set as
- * read-only on firmware built with bundle support. This command marks these
- * partitions as read/writeable. The access status set by this command does not
- * persist across MC reboots. This command only works on engineering (insecure)
- * cards. On secure adapters, this command returns MC_CMD_ERR_EPERM.
- */
-#define    MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_LEN 8
-/* Sub-command code. Must be OP_COMPONENT_ACCESS_SET. */
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_OP_OFST 0
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_OP_LEN 4
-/* Access mode of component partitions. */
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_ACCESS_MODE_OFST 4
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_ACCESS_MODE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT/ACCESS_MODE */
-
-/* MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_OUT msgresponse */
-#define    MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_VPD
- * Read all VPD starting from a given address
- */
-#define MC_CMD_GET_VPD 0x165
-#undef MC_CMD_0x165_PRIVILEGE_CTG
-
-#define MC_CMD_0x165_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_VPD_IN msgresponse */
-#define    MC_CMD_GET_VPD_IN_LEN 4
-/* VPD address to start from. In case VPD is longer than MCDI buffer
- * (unlikely), user can make multiple calls with different starting addresses.
- */
-#define       MC_CMD_GET_VPD_IN_ADDR_OFST 0
-#define       MC_CMD_GET_VPD_IN_ADDR_LEN 4
-
-/* MC_CMD_GET_VPD_OUT msgresponse */
-#define    MC_CMD_GET_VPD_OUT_LENMIN 0
-#define    MC_CMD_GET_VPD_OUT_LENMAX 252
-#define    MC_CMD_GET_VPD_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_GET_VPD_OUT_LEN(num) (0+1*(num))
-#define    MC_CMD_GET_VPD_OUT_DATA_NUM(len) (((len)-0)/1)
-/* VPD data returned. */
-#define       MC_CMD_GET_VPD_OUT_DATA_OFST 0
-#define       MC_CMD_GET_VPD_OUT_DATA_LEN 1
-#define       MC_CMD_GET_VPD_OUT_DATA_MINNUM 0
-#define       MC_CMD_GET_VPD_OUT_DATA_MAXNUM 252
-#define       MC_CMD_GET_VPD_OUT_DATA_MAXNUM_MCDI2 1020
-
-
-/***********************************/
-/* MC_CMD_GET_NCSI_INFO
- * Provide information about the NC-SI stack
- */
-#define MC_CMD_GET_NCSI_INFO 0x167
-#undef MC_CMD_0x167_PRIVILEGE_CTG
-
-#define MC_CMD_0x167_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_NCSI_INFO_IN msgrequest */
-#define    MC_CMD_GET_NCSI_INFO_IN_LEN 8
-/* Operation to be performed */
-#define       MC_CMD_GET_NCSI_INFO_IN_OP_OFST 0
-#define       MC_CMD_GET_NCSI_INFO_IN_OP_LEN 4
-/* enum: Information on the link settings. */
-#define          MC_CMD_GET_NCSI_INFO_IN_OP_LINK 0x0
-/* enum: Statistics associated with the channel */
-#define          MC_CMD_GET_NCSI_INFO_IN_OP_STATISTICS 0x1
-/* The NC-SI channel on which the operation is to be performed */
-#define       MC_CMD_GET_NCSI_INFO_IN_CHANNEL_OFST 4
-#define       MC_CMD_GET_NCSI_INFO_IN_CHANNEL_LEN 4
-
-/* MC_CMD_GET_NCSI_INFO_LINK_OUT msgresponse */
-#define    MC_CMD_GET_NCSI_INFO_LINK_OUT_LEN 12
-/* Settings as received from BMC. */
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_SETTINGS_OFST 0
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_SETTINGS_LEN 4
-/* Advertised capabilities applied to channel. */
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_ADV_CAP_OFST 4
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_ADV_CAP_LEN 4
-/* General status */
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_STATUS_OFST 8
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_STATUS_LEN 4
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_STATE_OFST 8
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_STATE_LBN 0
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_STATE_WIDTH 2
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ENABLE_OFST 8
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ENABLE_LBN 2
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ENABLE_WIDTH 1
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_NETWORK_TX_OFST 8
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_NETWORK_TX_LBN 3
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_NETWORK_TX_WIDTH 1
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ATTACHED_OFST 8
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ATTACHED_LBN 4
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ATTACHED_WIDTH 1
-
-/* MC_CMD_GET_NCSI_INFO_STATISTICS_OUT msgresponse */
-#define    MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_LEN 28
-/* The number of NC-SI commands received. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMDS_RX_OFST 0
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMDS_RX_LEN 4
-/* The number of NC-SI commands dropped. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_PKTS_DROPPED_OFST 4
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_PKTS_DROPPED_LEN 4
-/* The number of invalid NC-SI commands received. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMD_TYPE_ERRS_OFST 8
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMD_TYPE_ERRS_LEN 4
-/* The number of checksum errors seen. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMD_CSUM_ERRS_OFST 12
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMD_CSUM_ERRS_LEN 4
-/* The number of NC-SI requests received. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_RX_PKTS_OFST 16
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_RX_PKTS_LEN 4
-/* The number of NC-SI responses sent (includes AENs) */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_TX_PKTS_OFST 20
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_TX_PKTS_LEN 4
-/* The number of NC-SI AENs sent */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_AENS_SENT_OFST 24
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_AENS_SENT_LEN 4
-
 /* CLIENT_HANDLE structuredef: A client is an abstract entity that can make
  * requests of the device and that can own resources managed by the device.
  * Examples of clients include PCIe functions and dynamic clients. A client
@@ -23848,59 +21670,10 @@
 #define       CLIENT_HANDLE_OPAQUE_LBN 0
 #define       CLIENT_HANDLE_OPAQUE_WIDTH 32
 
-/* CLOCK_INFO structuredef: Information about a single hardware clock */
-#define    CLOCK_INFO_LEN 28
-/* Enumeration that uniquely identifies the clock */
-#define       CLOCK_INFO_CLOCK_ID_OFST 0
-#define       CLOCK_INFO_CLOCK_ID_LEN 2
-/* enum: The Riverhead CMC (card MC) */
-#define          CLOCK_INFO_CLOCK_CMC 0x0
-/* enum: The Riverhead NMC (network MC) */
-#define          CLOCK_INFO_CLOCK_NMC 0x1
-/* enum: The Riverhead SDNET slice main logic */
-#define          CLOCK_INFO_CLOCK_SDNET 0x2
-/* enum: The Riverhead SDNET LUT */
-#define          CLOCK_INFO_CLOCK_SDNET_LUT 0x3
-/* enum: The Riverhead SDNET control logic */
-#define          CLOCK_INFO_CLOCK_SDNET_CTRL 0x4
-/* enum: The Riverhead Streaming SubSystem */
-#define          CLOCK_INFO_CLOCK_SSS 0x5
-/* enum: The Riverhead network MAC and associated CSR registers */
-#define          CLOCK_INFO_CLOCK_MAC 0x6
-#define       CLOCK_INFO_CLOCK_ID_LBN 0
-#define       CLOCK_INFO_CLOCK_ID_WIDTH 16
-/* Assorted flags */
-#define       CLOCK_INFO_FLAGS_OFST 2
-#define       CLOCK_INFO_FLAGS_LEN 2
-#define        CLOCK_INFO_SETTABLE_OFST 2
-#define        CLOCK_INFO_SETTABLE_LBN 0
-#define        CLOCK_INFO_SETTABLE_WIDTH 1
-#define       CLOCK_INFO_FLAGS_LBN 16
-#define       CLOCK_INFO_FLAGS_WIDTH 16
-/* The frequency in HZ */
-#define       CLOCK_INFO_FREQUENCY_OFST 4
-#define       CLOCK_INFO_FREQUENCY_LEN 8
-#define       CLOCK_INFO_FREQUENCY_LO_OFST 4
-#define       CLOCK_INFO_FREQUENCY_LO_LEN 4
-#define       CLOCK_INFO_FREQUENCY_LO_LBN 32
-#define       CLOCK_INFO_FREQUENCY_LO_WIDTH 32
-#define       CLOCK_INFO_FREQUENCY_HI_OFST 8
-#define       CLOCK_INFO_FREQUENCY_HI_LEN 4
-#define       CLOCK_INFO_FREQUENCY_HI_LBN 64
-#define       CLOCK_INFO_FREQUENCY_HI_WIDTH 32
-#define       CLOCK_INFO_FREQUENCY_LBN 32
-#define       CLOCK_INFO_FREQUENCY_WIDTH 64
-/* Human-readable ASCII name for clock, with NUL termination */
-#define       CLOCK_INFO_NAME_OFST 12
-#define       CLOCK_INFO_NAME_LEN 1
-#define       CLOCK_INFO_NAME_NUM 16
-#define       CLOCK_INFO_NAME_LBN 96
-#define       CLOCK_INFO_NAME_WIDTH 8
-
 /* SCHED_CREDIT_CHECK_RESULT structuredef */
 #define    SCHED_CREDIT_CHECK_RESULT_LEN 16
-/* The instance of the scheduler. Refer to XN-200389-AW for the location of
- * these schedulers in the hardware.
+/* The instance of the scheduler. Refer to XN-200389-AW (snic/hnic) and
+ * XN-200425-TC (cdx) for the location of these schedulers in the hardware.
  */
 #define       SCHED_CREDIT_CHECK_RESULT_SCHED_INSTANCE_OFST 0
 #define       SCHED_CREDIT_CHECK_RESULT_SCHED_INSTANCE_LEN 1
@@ -23914,6 +21687,16 @@
 #define          SCHED_CREDIT_CHECK_RESULT_DMAC_H2C 0x7 /* enum */
 #define          SCHED_CREDIT_CHECK_RESULT_HUB_NET_B 0x8 /* enum */
 #define          SCHED_CREDIT_CHECK_RESULT_HUB_NET_REPLAY 0x9 /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_ADAPTER_C2H_C 0xa /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_A2_H2C_C 0xb /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_A3_SOFT_ADAPTOR_C 0xc /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_A4_DPU_WRITE_C 0xd /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_JRC_RRU 0xe /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_CDM_SINK 0xf /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_PCIE_SINK 0x10 /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_UPORT_SINK 0x11 /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_PSX_SINK 0x12 /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_A5_DPU_READ_C 0x13 /* enum */
 #define       SCHED_CREDIT_CHECK_RESULT_SCHED_INSTANCE_LBN 0
 #define       SCHED_CREDIT_CHECK_RESULT_SCHED_INSTANCE_WIDTH 8
 /* The type of node that this result refers to. */
@@ -23923,6 +21706,10 @@
 #define          SCHED_CREDIT_CHECK_RESULT_DEST 0x0
 /* enum: Source node */
 #define          SCHED_CREDIT_CHECK_RESULT_SOURCE 0x1
+/* enum: Destination node credit type 1 (new to the Keystone schedulers, see
+ * SF-120268-TC)
+ */
+#define          SCHED_CREDIT_CHECK_RESULT_DEST_CREDIT1 0x2
 #define       SCHED_CREDIT_CHECK_RESULT_NODE_TYPE_LBN 8
 #define       SCHED_CREDIT_CHECK_RESULT_NODE_TYPE_WIDTH 8
 /* Level of node in scheduler hierarchy (level 0 is the bottom of the
@@ -23950,592 +21737,6 @@
 
 
 /***********************************/
-/* MC_CMD_GET_CLOCKS_INFO
- * Get information about the device clocks
- */
-#define MC_CMD_GET_CLOCKS_INFO 0x166
-#undef MC_CMD_0x166_PRIVILEGE_CTG
-
-#define MC_CMD_0x166_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_CLOCKS_INFO_IN msgrequest */
-#define    MC_CMD_GET_CLOCKS_INFO_IN_LEN 0
-
-/* MC_CMD_GET_CLOCKS_INFO_OUT msgresponse */
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_LENMIN 0
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_LENMAX 252
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_LENMAX_MCDI2 1008
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_LEN(num) (0+28*(num))
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_NUM(len) (((len)-0)/28)
-/* An array of CLOCK_INFO structures. */
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_OFST 0
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_LEN 28
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_MINNUM 0
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_MAXNUM 9
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_MAXNUM_MCDI2 36
-
-
-/***********************************/
-/* MC_CMD_VNIC_ENCAP_RULE_ADD
- * Add a rule for detecting encapsulations in the VNIC stage. Currently this
- * only affects checksum validation in VNIC RX - on TX the send descriptor
- * explicitly specifies encapsulation. These rules are per-VNIC, i.e. only
- * apply to the current driver. If a rule matches, then the packet is
- * considered to have the corresponding encapsulation type, and the inner
- * packet is parsed. It is up to the driver to ensure that overlapping rules
- * are not inserted. (If a packet would match multiple rules, a random one of
- * them will be used.) A rule with the exact same match criteria may not be
- * inserted twice (EALREADY). Only a limited number MATCH_FLAGS values are
- * supported, use MC_CMD_GET_PARSER_DISP_INFO with OP
- * OP_GET_SUPPORTED_VNIC_ENCAP_RULE_MATCHES to get a list of supported
- * combinations. Each driver may only have a limited set of active rules -
- * returns ENOSPC if the caller's table is full.
- */
-#define MC_CMD_VNIC_ENCAP_RULE_ADD 0x16d
-#undef MC_CMD_0x16d_PRIVILEGE_CTG
-
-#define MC_CMD_0x16d_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VNIC_ENCAP_RULE_ADD_IN msgrequest */
-#define    MC_CMD_VNIC_ENCAP_RULE_ADD_IN_LEN 36
-/* Set to MAE_MPORT_SELECTOR_ASSIGNED. In the future this may be relaxed. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MPORT_SELECTOR_OFST 0
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MPORT_SELECTOR_LEN 4
-/* Any non-zero bits other than the ones named below or an unsupported
- * combination will cause the NIC to return EOPNOTSUPP. In the future more
- * flags may be added.
- */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_FLAGS_OFST 4
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_FLAGS_LEN 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_ETHER_TYPE_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_ETHER_TYPE_LBN 0
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_ETHER_TYPE_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_OUTER_VLAN_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_OUTER_VLAN_LBN 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_OUTER_VLAN_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_IP_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_IP_LBN 2
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_IP_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_IP_PROTO_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_IP_PROTO_LBN 3
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_IP_PROTO_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_PORT_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_PORT_LBN 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_PORT_WIDTH 1
-/* Only if MATCH_ETHER_TYPE is set. Ethertype value as bytes in network order.
- * Currently only IPv4 (0x0800) and IPv6 (0x86DD) ethertypes may be used.
- */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ETHER_TYPE_OFST 8
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ETHER_TYPE_LEN 2
-/* Only if MATCH_OUTER_VLAN is set. VID value as bytes in network order.
- * (Deprecated)
- */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_LBN 80
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_WIDTH 12
-/* Only if MATCH_OUTER_VLAN is set. Aligned wrapper for OUTER_VLAN_VID. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_WORD_OFST 10
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_WORD_LEN 2
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_VID_OFST 10
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_VID_LBN 0
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_VID_WIDTH 12
-/* Only if MATCH_DST_IP is set. IP address as bytes in network order. In the
- * case of IPv4, the IP should be in the first 4 bytes and all other bytes
- * should be zero.
- */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_DST_IP_OFST 12
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_DST_IP_LEN 16
-/* Only if MATCH_IP_PROTO is set. Currently only UDP proto (17) may be used. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_IP_PROTO_OFST 28
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_IP_PROTO_LEN 1
-/* Actions that should be applied to packets match the rule. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ACTION_FLAGS_OFST 29
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ACTION_FLAGS_LEN 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STRIP_OUTER_VLAN_OFST 29
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STRIP_OUTER_VLAN_LBN 0
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STRIP_OUTER_VLAN_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_RSS_ON_OUTER_OFST 29
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_RSS_ON_OUTER_LBN 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_RSS_ON_OUTER_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STEER_ON_OUTER_OFST 29
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STEER_ON_OUTER_LBN 2
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STEER_ON_OUTER_WIDTH 1
-/* Only if MATCH_DST_PORT is set. Port number as bytes in network order. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_DST_PORT_OFST 30
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_DST_PORT_LEN 2
-/* Resulting encapsulation type, as per MAE_MCDI_ENCAP_TYPE enumeration. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ENCAP_TYPE_OFST 32
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ENCAP_TYPE_LEN 4
-
-/* MC_CMD_VNIC_ENCAP_RULE_ADD_OUT msgresponse */
-#define    MC_CMD_VNIC_ENCAP_RULE_ADD_OUT_LEN 4
-/* Handle to inserted rule. Used for removing the rule. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_OUT_HANDLE_OFST 0
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_OUT_HANDLE_LEN 4
-
-
-/***********************************/
-/* MC_CMD_VNIC_ENCAP_RULE_REMOVE
- * Remove a VNIC encapsulation rule. Packets which would have previously
- * matched the rule will then be considered as unencapsulated. Returns EALREADY
- * if the input HANDLE doesn't correspond to an existing rule.
- */
-#define MC_CMD_VNIC_ENCAP_RULE_REMOVE 0x16e
-#undef MC_CMD_0x16e_PRIVILEGE_CTG
-
-#define MC_CMD_0x16e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VNIC_ENCAP_RULE_REMOVE_IN msgrequest */
-#define    MC_CMD_VNIC_ENCAP_RULE_REMOVE_IN_LEN 4
-/* Handle which was returned by MC_CMD_VNIC_ENCAP_RULE_ADD. */
-#define       MC_CMD_VNIC_ENCAP_RULE_REMOVE_IN_HANDLE_OFST 0
-#define       MC_CMD_VNIC_ENCAP_RULE_REMOVE_IN_HANDLE_LEN 4
-
-/* MC_CMD_VNIC_ENCAP_RULE_REMOVE_OUT msgresponse */
-#define    MC_CMD_VNIC_ENCAP_RULE_REMOVE_OUT_LEN 0
-
-/* UUID structuredef: An RFC4122 standard UUID. The values here are stored in
- * the endianness specified by the RFC; users should ignore the broken-out
- * fields and instead do straight memory copies to ensure correct ordering.
- */
-#define    UUID_LEN 16
-#define       UUID_TIME_LOW_OFST 0
-#define       UUID_TIME_LOW_LEN 4
-#define       UUID_TIME_LOW_LBN 0
-#define       UUID_TIME_LOW_WIDTH 32
-#define       UUID_TIME_MID_OFST 4
-#define       UUID_TIME_MID_LEN 2
-#define       UUID_TIME_MID_LBN 32
-#define       UUID_TIME_MID_WIDTH 16
-#define       UUID_TIME_HI_LBN 52
-#define       UUID_TIME_HI_WIDTH 12
-#define       UUID_VERSION_LBN 48
-#define       UUID_VERSION_WIDTH 4
-#define       UUID_RESERVED_LBN 64
-#define       UUID_RESERVED_WIDTH 2
-#define       UUID_CLK_SEQ_LBN 66
-#define       UUID_CLK_SEQ_WIDTH 14
-#define       UUID_NODE_OFST 10
-#define       UUID_NODE_LEN 6
-#define       UUID_NODE_LBN 80
-#define       UUID_NODE_WIDTH 48
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_ALLOC
- * Create a handle to a datapath plugin's extension. This involves finding a
- * currently-loaded plugin offering the given functionality (as identified by
- * the UUID) and allocating a handle to track the usage of it. Plugin
- * functionality is identified by 'extension' rather than any other identifier
- * so that a single plugin bitfile may offer more than one piece of independent
- * functionality. If two bitfiles are loaded which both offer the same
- * extension, then the metadata is interrogated further to determine which is
- * the newest and that is the one opened. See SF-123625-SW for architectural
- * detail on datapath plugins.
- */
-#define MC_CMD_PLUGIN_ALLOC 0x1ad
-#undef MC_CMD_0x1ad_PRIVILEGE_CTG
-
-#define MC_CMD_0x1ad_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_ALLOC_IN msgrequest */
-#define    MC_CMD_PLUGIN_ALLOC_IN_LEN 24
-/* The functionality requested of the plugin, as a UUID structure */
-#define       MC_CMD_PLUGIN_ALLOC_IN_UUID_OFST 0
-#define       MC_CMD_PLUGIN_ALLOC_IN_UUID_LEN 16
-/* Additional options for opening the handle */
-#define       MC_CMD_PLUGIN_ALLOC_IN_FLAGS_OFST 16
-#define       MC_CMD_PLUGIN_ALLOC_IN_FLAGS_LEN 4
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_INFO_ONLY_OFST 16
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_INFO_ONLY_LBN 0
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_INFO_ONLY_WIDTH 1
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_ALLOW_DISABLED_OFST 16
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_ALLOW_DISABLED_LBN 1
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_ALLOW_DISABLED_WIDTH 1
-/* Load the extension only if it is in the specified administrative group.
- * Specify ANY to load the extension wherever it is found (if there are
- * multiple choices then the extension with the highest MINOR_VER/PATCH_VER
- * will be loaded). See MC_CMD_PLUGIN_GET_META_GLOBAL for a description of
- * administrative groups.
- */
-#define       MC_CMD_PLUGIN_ALLOC_IN_ADMIN_GROUP_OFST 20
-#define       MC_CMD_PLUGIN_ALLOC_IN_ADMIN_GROUP_LEN 2
-/* enum: Load the extension from any ADMIN_GROUP. */
-#define          MC_CMD_PLUGIN_ALLOC_IN_ANY 0xffff
-/* Reserved */
-#define       MC_CMD_PLUGIN_ALLOC_IN_RESERVED_OFST 22
-#define       MC_CMD_PLUGIN_ALLOC_IN_RESERVED_LEN 2
-
-/* MC_CMD_PLUGIN_ALLOC_OUT msgresponse */
-#define    MC_CMD_PLUGIN_ALLOC_OUT_LEN 4
-/* Unique identifier of this usage */
-#define       MC_CMD_PLUGIN_ALLOC_OUT_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_ALLOC_OUT_HANDLE_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_FREE
- * Delete a handle to a plugin's extension.
- */
-#define MC_CMD_PLUGIN_FREE 0x1ae
-#undef MC_CMD_0x1ae_PRIVILEGE_CTG
-
-#define MC_CMD_0x1ae_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_FREE_IN msgrequest */
-#define    MC_CMD_PLUGIN_FREE_IN_LEN 4
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_FREE_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_FREE_IN_HANDLE_LEN 4
-
-/* MC_CMD_PLUGIN_FREE_OUT msgresponse */
-#define    MC_CMD_PLUGIN_FREE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_GET_META_GLOBAL
- * Returns the global metadata applying to the whole plugin extension. See the
- * other metadata calls for subtypes of data.
- */
-#define MC_CMD_PLUGIN_GET_META_GLOBAL 0x1af
-#undef MC_CMD_0x1af_PRIVILEGE_CTG
-
-#define MC_CMD_0x1af_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_GET_META_GLOBAL_IN msgrequest */
-#define    MC_CMD_PLUGIN_GET_META_GLOBAL_IN_LEN 4
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_IN_HANDLE_LEN 4
-
-/* MC_CMD_PLUGIN_GET_META_GLOBAL_OUT msgresponse */
-#define    MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_LEN 36
-/* Unique identifier of this plugin extension. This is identical to the value
- * which was requested when the handle was allocated.
- */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_UUID_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_UUID_LEN 16
-/* semver sub-version of this plugin extension */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MINOR_VER_OFST 16
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MINOR_VER_LEN 2
-/* semver micro-version of this plugin extension */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_PATCH_VER_OFST 18
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_PATCH_VER_LEN 2
-/* Number of different messages which can be sent to this extension */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_NUM_MSGS_OFST 20
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_NUM_MSGS_LEN 4
-/* Byte offset within the VI window of the plugin's mapped CSR window. */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_OFFSET_OFST 24
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_OFFSET_LEN 2
-/* Number of bytes mapped through to the plugin's CSRs. 0 if that feature was
- * not requested by the plugin (in which case MAPPED_CSR_OFFSET and
- * MAPPED_CSR_FLAGS are ignored).
- */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_SIZE_OFST 26
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_SIZE_LEN 2
-/* Flags indicating how to perform the CSR window mapping. */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAGS_OFST 28
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAGS_LEN 4
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_READ_OFST 28
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_READ_LBN 0
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_READ_WIDTH 1
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_WRITE_OFST 28
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_WRITE_LBN 1
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_WRITE_WIDTH 1
-/* Identifier of the set of extensions which all change state together.
- * Extensions having the same ADMIN_GROUP will always load and unload at the
- * same time. ADMIN_GROUP values themselves are arbitrary (but they contain a
- * generation number as an implementation detail to ensure that they're not
- * reused rapidly).
- */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_ADMIN_GROUP_OFST 32
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_ADMIN_GROUP_LEN 1
-/* Bitshift in MC_CMD_DEVEL_CLIENT_PRIVILEGE_MODIFY's MASK parameters
- * corresponding to this extension, i.e. set the bit 1<<PRIVILEGE_BIT to permit
- * access to this extension.
- */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_PRIVILEGE_BIT_OFST 33
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_PRIVILEGE_BIT_LEN 1
-/* Reserved */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_RESERVED_OFST 34
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_RESERVED_LEN 2
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_GET_META_PUBLISHER
- * Returns metadata supplied by the plugin author which describes this
- * extension in a human-readable way. Contrast with
- * MC_CMD_PLUGIN_GET_META_GLOBAL, which returns information needed for software
- * to operate.
- */
-#define MC_CMD_PLUGIN_GET_META_PUBLISHER 0x1b0
-#undef MC_CMD_0x1b0_PRIVILEGE_CTG
-
-#define MC_CMD_0x1b0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_GET_META_PUBLISHER_IN msgrequest */
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_LEN 12
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_HANDLE_LEN 4
-/* Category of data to return */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_SUBTYPE_OFST 4
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_SUBTYPE_LEN 4
-/* enum: Top-level information about the extension. The returned data is an
- * array of key/value pairs using the keys in RFC5013 (Dublin Core) to describe
- * the extension. The data is a back-to-back list of zero-terminated strings;
- * the even-numbered fields (0,2,4,...) are keys and their following odd-
- * numbered fields are the corresponding values. Both keys and values are
- * nominally UTF-8. Per RFC5013, the same key may be repeated any number of
- * times. Note that all information (including the key/value structure itself
- * and the UTF-8 encoding) may have been provided by the plugin author, so
- * callers must be cautious about parsing it. Callers should parse only the
- * top-level structure to separate out the keys and values; the contents of the
- * values is not expected to be machine-readable.
- */
-#define          MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_EXTENSION_KVS 0x0
-/* Byte position of the data to be returned within the full data block of the
- * given SUBTYPE.
- */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_OFFSET_OFST 8
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_OFFSET_LEN 4
-
-/* MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT msgresponse */
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_LENMIN 4
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_LENMAX 252
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_LEN(num) (4+1*(num))
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_NUM(len) (((len)-4)/1)
-/* Full length of the data block of the requested SUBTYPE, in bytes. */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_TOTAL_SIZE_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_TOTAL_SIZE_LEN 4
-/* The information requested by SUBTYPE. */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_OFST 4
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_LEN 1
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_MINNUM 0
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_MAXNUM 248
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_MAXNUM_MCDI2 1016
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_GET_META_MSG
- * Returns the simple metadata for a specific plugin request message. This
- * supplies information necessary for the host to know how to build an
- * MC_CMD_PLUGIN_REQ request.
- */
-#define MC_CMD_PLUGIN_GET_META_MSG 0x1b1
-#undef MC_CMD_0x1b1_PRIVILEGE_CTG
-
-#define MC_CMD_0x1b1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_GET_META_MSG_IN msgrequest */
-#define    MC_CMD_PLUGIN_GET_META_MSG_IN_LEN 8
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_GET_META_MSG_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_MSG_IN_HANDLE_LEN 4
-/* Unique message ID to obtain */
-#define       MC_CMD_PLUGIN_GET_META_MSG_IN_ID_OFST 4
-#define       MC_CMD_PLUGIN_GET_META_MSG_IN_ID_LEN 4
-
-/* MC_CMD_PLUGIN_GET_META_MSG_OUT msgresponse */
-#define    MC_CMD_PLUGIN_GET_META_MSG_OUT_LEN 44
-/* Unique message ID. This is the same value as the input parameter; it exists
- * to allow future MCDI extensions which enumerate all messages.
- */
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_ID_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_ID_LEN 4
-/* Packed index number of this message, assigned by the MC to give each message
- * a unique ID in an array to allow for more efficient storage/management.
- */
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_INDEX_OFST 4
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_INDEX_LEN 4
-/* Short human-readable codename for this message. This is conventionally
- * formatted as a C identifier in the basic ASCII character set with any spare
- * bytes at the end set to 0, however this convention is not enforced by the MC
- * so consumers must check for all potential malformations before using it for
- * a trusted purpose.
- */
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_NAME_OFST 8
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_NAME_LEN 32
-/* Number of bytes of data which must be passed from the host kernel to the MC
- * for this message's payload, and which are passed back again in the response.
- * The MC's plugin metadata loader will have validated that the number of bytes
- * specified here will fit in to MC_CMD_PLUGIN_REQ_IN_DATA in a single MCDI
- * message.
- */
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_DATA_SIZE_OFST 40
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_DATA_SIZE_LEN 4
-
-/* PLUGIN_EXTENSION structuredef: Used within MC_CMD_PLUGIN_GET_ALL to describe
- * an individual extension.
- */
-#define    PLUGIN_EXTENSION_LEN 20
-#define       PLUGIN_EXTENSION_UUID_OFST 0
-#define       PLUGIN_EXTENSION_UUID_LEN 16
-#define       PLUGIN_EXTENSION_UUID_LBN 0
-#define       PLUGIN_EXTENSION_UUID_WIDTH 128
-#define       PLUGIN_EXTENSION_ADMIN_GROUP_OFST 16
-#define       PLUGIN_EXTENSION_ADMIN_GROUP_LEN 1
-#define       PLUGIN_EXTENSION_ADMIN_GROUP_LBN 128
-#define       PLUGIN_EXTENSION_ADMIN_GROUP_WIDTH 8
-#define       PLUGIN_EXTENSION_FLAG_ENABLED_LBN 136
-#define       PLUGIN_EXTENSION_FLAG_ENABLED_WIDTH 1
-#define       PLUGIN_EXTENSION_RESERVED_LBN 137
-#define       PLUGIN_EXTENSION_RESERVED_WIDTH 23
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_GET_ALL
- * Returns a list of all plugin extensions currently loaded and available. The
- * UUIDs returned can be passed to MC_CMD_PLUGIN_ALLOC in order to obtain more
- * detailed metadata via the MC_CMD_PLUGIN_GET_META_* family of requests. The
- * ADMIN_GROUP field collects how extensions are grouped in to units which are
- * loaded/unloaded together; extensions with the same value are in the same
- * group.
- */
-#define MC_CMD_PLUGIN_GET_ALL 0x1b2
-#undef MC_CMD_0x1b2_PRIVILEGE_CTG
-
-#define MC_CMD_0x1b2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_GET_ALL_IN msgrequest */
-#define    MC_CMD_PLUGIN_GET_ALL_IN_LEN 4
-/* Additional options for querying. Note that if neither FLAG_INCLUDE_ENABLED
- * nor FLAG_INCLUDE_DISABLED are specified then the result set will be empty.
- */
-#define       MC_CMD_PLUGIN_GET_ALL_IN_FLAGS_OFST 0
-#define       MC_CMD_PLUGIN_GET_ALL_IN_FLAGS_LEN 4
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_ENABLED_OFST 0
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_ENABLED_LBN 0
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_ENABLED_WIDTH 1
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_DISABLED_OFST 0
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_DISABLED_LBN 1
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_DISABLED_WIDTH 1
-
-/* MC_CMD_PLUGIN_GET_ALL_OUT msgresponse */
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_LENMIN 0
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_LENMAX 240
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_LEN(num) (0+20*(num))
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_NUM(len) (((len)-0)/20)
-/* The list of available plugin extensions, as an array of PLUGIN_EXTENSION
- * structs.
- */
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_OFST 0
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_LEN 20
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_MINNUM 0
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_MAXNUM 12
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_MAXNUM_MCDI2 51
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_REQ
- * Send a command to a plugin. A plugin may define an arbitrary number of
- * 'messages' which it allows applications on the host system to send, each
- * identified by a 32-bit ID.
- */
-#define MC_CMD_PLUGIN_REQ 0x1b3
-#undef MC_CMD_0x1b3_PRIVILEGE_CTG
-
-#define MC_CMD_0x1b3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_REQ_IN msgrequest */
-#define    MC_CMD_PLUGIN_REQ_IN_LENMIN 8
-#define    MC_CMD_PLUGIN_REQ_IN_LENMAX 252
-#define    MC_CMD_PLUGIN_REQ_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_PLUGIN_REQ_IN_LEN(num) (8+1*(num))
-#define    MC_CMD_PLUGIN_REQ_IN_DATA_NUM(len) (((len)-8)/1)
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_REQ_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_REQ_IN_HANDLE_LEN 4
-/* Message ID defined by the plugin author */
-#define       MC_CMD_PLUGIN_REQ_IN_ID_OFST 4
-#define       MC_CMD_PLUGIN_REQ_IN_ID_LEN 4
-/* Data blob being the parameter to the message. This must be of the length
- * specified by MC_CMD_PLUGIN_GET_META_MSG_IN_MCDI_PARAM_SIZE.
- */
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_OFST 8
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_LEN 1
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_MINNUM 0
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_MAXNUM 244
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_MAXNUM_MCDI2 1012
-
-/* MC_CMD_PLUGIN_REQ_OUT msgresponse */
-#define    MC_CMD_PLUGIN_REQ_OUT_LENMIN 0
-#define    MC_CMD_PLUGIN_REQ_OUT_LENMAX 252
-#define    MC_CMD_PLUGIN_REQ_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PLUGIN_REQ_OUT_LEN(num) (0+1*(num))
-#define    MC_CMD_PLUGIN_REQ_OUT_DATA_NUM(len) (((len)-0)/1)
-/* The input data, as transformed and/or updated by the plugin's eBPF. Will be
- * the same size as the input DATA parameter.
- */
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_OFST 0
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_LEN 1
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_MINNUM 0
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_MAXNUM 252
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_MAXNUM_MCDI2 1020
-
-/* DESC_ADDR_REGION structuredef: Describes a contiguous region of DESC_ADDR
- * space that maps to a contiguous region of TRGT_ADDR space. Addresses
- * DESC_ADDR in the range [DESC_ADDR_BASE:DESC_ADDR_BASE + 1 <<
- * WINDOW_SIZE_LOG2) map to TRGT_ADDR = DESC_ADDR - DESC_ADDR_BASE +
- * TRGT_ADDR_BASE.
- */
-#define    DESC_ADDR_REGION_LEN 32
-/* The start of the region in DESC_ADDR space. */
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_OFST 0
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LEN 8
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LO_OFST 0
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LO_LEN 4
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LO_LBN 0
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LO_WIDTH 32
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_HI_OFST 4
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_HI_LEN 4
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_HI_LBN 32
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_HI_WIDTH 32
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LBN 0
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_WIDTH 64
-/* The start of the region in TRGT_ADDR space. Drivers can set this via
- * MC_CMD_SET_DESC_ADDR_REGIONS.
- */
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_OFST 8
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LEN 8
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LO_OFST 8
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LO_LEN 4
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LO_LBN 64
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LO_WIDTH 32
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_HI_OFST 12
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_HI_LEN 4
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_HI_LBN 96
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_HI_WIDTH 32
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LBN 64
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_WIDTH 64
-/* The size of the region. */
-#define       DESC_ADDR_REGION_WINDOW_SIZE_LOG2_OFST 16
-#define       DESC_ADDR_REGION_WINDOW_SIZE_LOG2_LEN 4
-#define       DESC_ADDR_REGION_WINDOW_SIZE_LOG2_LBN 128
-#define       DESC_ADDR_REGION_WINDOW_SIZE_LOG2_WIDTH 32
-/* The alignment restriction on TRGT_ADDR. TRGT_ADDR values set by the driver
- * must be a multiple of 1 << TRGT_ADDR_ALIGN_LOG2.
- */
-#define       DESC_ADDR_REGION_TRGT_ADDR_ALIGN_LOG2_OFST 20
-#define       DESC_ADDR_REGION_TRGT_ADDR_ALIGN_LOG2_LEN 4
-#define       DESC_ADDR_REGION_TRGT_ADDR_ALIGN_LOG2_LBN 160
-#define       DESC_ADDR_REGION_TRGT_ADDR_ALIGN_LOG2_WIDTH 32
-#define       DESC_ADDR_REGION_RSVD_OFST 24
-#define       DESC_ADDR_REGION_RSVD_LEN 8
-#define       DESC_ADDR_REGION_RSVD_LO_OFST 24
-#define       DESC_ADDR_REGION_RSVD_LO_LEN 4
-#define       DESC_ADDR_REGION_RSVD_LO_LBN 192
-#define       DESC_ADDR_REGION_RSVD_LO_WIDTH 32
-#define       DESC_ADDR_REGION_RSVD_HI_OFST 28
-#define       DESC_ADDR_REGION_RSVD_HI_LEN 4
-#define       DESC_ADDR_REGION_RSVD_HI_LBN 224
-#define       DESC_ADDR_REGION_RSVD_HI_WIDTH 32
-#define       DESC_ADDR_REGION_RSVD_LBN 192
-#define       DESC_ADDR_REGION_RSVD_WIDTH 64
-
-
-/***********************************/
 /* MC_CMD_GET_DESC_ADDR_INFO
  * Returns a description of the mapping from DESC_ADDR to TRGT_ADDR for the calling function's address space.
  */
@@ -24836,122 +22037,6 @@
 
 
 /***********************************/
-/* MC_CMD_GET_BOARD_ATTR
- * Retrieve physical build-level board attributes as configured at
- * manufacturing stage. Fields originate from EEPROM and per-platform constants
- * in firmware. Fields are used in development to identify/ differentiate
- * boards based on build levels/parameters, and also in manufacturing to cross
- * check "what was programmed in manufacturing" is same as "what firmware
- * thinks has been programmed" as there are two layers to translation within
- * firmware before the attributes reach this MCDI handler. Some parameters are
- * retrieved as part of other commands and therefore not replicated here. See
- * GET_VERSION_OUT.
- */
-#define MC_CMD_GET_BOARD_ATTR 0x1c6
-#undef MC_CMD_0x1c6_PRIVILEGE_CTG
-
-#define MC_CMD_0x1c6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_BOARD_ATTR_IN msgrequest */
-#define    MC_CMD_GET_BOARD_ATTR_IN_LEN 0
-
-/* MC_CMD_GET_BOARD_ATTR_OUT msgresponse */
-#define    MC_CMD_GET_BOARD_ATTR_OUT_LEN 16
-/* Defines board capabilities and validity of attributes returned in this
- * response-message.
- */
-#define       MC_CMD_GET_BOARD_ATTR_OUT_FLAGS_OFST 0
-#define       MC_CMD_GET_BOARD_ATTR_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_FAN_OFST 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_FAN_LBN 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_FAN_WIDTH 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_SOC_OFST 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_SOC_LBN 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_SOC_WIDTH 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_AUX_POWER_OFST 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_AUX_POWER_LBN 2
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_AUX_POWER_WIDTH 1
-#define       MC_CMD_GET_BOARD_ATTR_OUT_ATTRIBUTES_OFST 4
-#define       MC_CMD_GET_BOARD_ATTR_OUT_ATTRIBUTES_LEN 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SOC_EE_OFST 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SOC_EE_LBN 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SOC_EE_WIDTH 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SUC_EE_OFST 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SUC_EE_LBN 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SUC_EE_WIDTH 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_FPGA_VOLTAGES_SUPPORTED_OFST 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_FPGA_VOLTAGES_SUPPORTED_LBN 16
-#define        MC_CMD_GET_BOARD_ATTR_OUT_FPGA_VOLTAGES_SUPPORTED_WIDTH 8
-/* enum: The FPGA voltage on the adapter can be set to low */
-#define          MC_CMD_FPGA_VOLTAGE_LOW 0x0
-/* enum: The FPGA voltage on the adapter can be set to regular */
-#define          MC_CMD_FPGA_VOLTAGE_REG 0x1
-/* enum: The FPGA voltage on the adapter can be set to high */
-#define          MC_CMD_FPGA_VOLTAGE_HIGH 0x2
-#define        MC_CMD_GET_BOARD_ATTR_OUT_CAGE_COUNT_OFST 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_CAGE_COUNT_LBN 24
-#define        MC_CMD_GET_BOARD_ATTR_OUT_CAGE_COUNT_WIDTH 8
-/* An array of cage types on the board */
-#define       MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_OFST 8
-#define       MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_LEN 1
-#define       MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_NUM 8
-/* enum: The cages are not known */
-#define          MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_UNKNOWN 0x0
-/* enum: The cages are SFP/SFP+ */
-#define          MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_SFP 0x1
-/* enum: The cages are QSFP/QSFP+ */
-#define          MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_QSFP 0x2
-
-
-/***********************************/
-/* MC_CMD_GET_SOC_STATE
- * Retrieve current state of the System-on-Chip. This command is valid when
- * MC_CMD_GET_BOARD_ATTR:HAS_SOC is set.
- */
-#define MC_CMD_GET_SOC_STATE 0x1c7
-#undef MC_CMD_0x1c7_PRIVILEGE_CTG
-
-#define MC_CMD_0x1c7_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_SOC_STATE_IN msgrequest */
-#define    MC_CMD_GET_SOC_STATE_IN_LEN 0
-
-/* MC_CMD_GET_SOC_STATE_OUT msgresponse */
-#define    MC_CMD_GET_SOC_STATE_OUT_LEN 12
-/* Status flags for the SoC */
-#define       MC_CMD_GET_SOC_STATE_OUT_FLAGS_OFST 0
-#define       MC_CMD_GET_SOC_STATE_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_SOC_STATE_OUT_SHOULD_THROTTLE_OFST 0
-#define        MC_CMD_GET_SOC_STATE_OUT_SHOULD_THROTTLE_LBN 0
-#define        MC_CMD_GET_SOC_STATE_OUT_SHOULD_THROTTLE_WIDTH 1
-#define        MC_CMD_GET_SOC_STATE_OUT_OS_RECOVERY_REQUIRED_OFST 0
-#define        MC_CMD_GET_SOC_STATE_OUT_OS_RECOVERY_REQUIRED_LBN 1
-#define        MC_CMD_GET_SOC_STATE_OUT_OS_RECOVERY_REQUIRED_WIDTH 1
-#define        MC_CMD_GET_SOC_STATE_OUT_WDT_FIRED_OFST 0
-#define        MC_CMD_GET_SOC_STATE_OUT_WDT_FIRED_LBN 2
-#define        MC_CMD_GET_SOC_STATE_OUT_WDT_FIRED_WIDTH 1
-/* Status fields for the SoC */
-#define       MC_CMD_GET_SOC_STATE_OUT_ATTRIBUTES_OFST 4
-#define       MC_CMD_GET_SOC_STATE_OUT_ATTRIBUTES_LEN 4
-#define        MC_CMD_GET_SOC_STATE_OUT_RUN_STATE_OFST 4
-#define        MC_CMD_GET_SOC_STATE_OUT_RUN_STATE_LBN 0
-#define        MC_CMD_GET_SOC_STATE_OUT_RUN_STATE_WIDTH 8
-/* enum: Power on (set by SUC on power up) */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_BOOT 0x0
-/* enum: Running bootloader */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_BOOTLOADER 0x1
-/* enum: Bootloader has started OS. OS is booting */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_OS_START 0x2
-/* enum: OS is running */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_OS_RUNNING 0x3
-/* enum: Maintenance OS is running */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_OS_MAINTENANCE 0x4
-/* Number of SoC resets since power on */
-#define       MC_CMD_GET_SOC_STATE_OUT_RESET_COUNT_OFST 8
-#define       MC_CMD_GET_SOC_STATE_OUT_RESET_COUNT_LEN 4
-
-
-/***********************************/
 /* MC_CMD_CHECK_SCHEDULER_CREDITS
  * For debugging purposes. For each source and destination node in the hardware
  * schedulers, check whether the number of credits is as it should be. This
@@ -25010,76 +22095,6 @@
 
 
 /***********************************/
-/* MC_CMD_TXQ_STATS
- * Query per-TXQ statistics.
- */
-#define MC_CMD_TXQ_STATS 0x1d5
-#undef MC_CMD_0x1d5_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d5_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TXQ_STATS_IN msgrequest */
-#define    MC_CMD_TXQ_STATS_IN_LEN 8
-/* Instance of TXQ to retrieve statistics for */
-#define       MC_CMD_TXQ_STATS_IN_INSTANCE_OFST 0
-#define       MC_CMD_TXQ_STATS_IN_INSTANCE_LEN 4
-/* Flags for the request */
-#define       MC_CMD_TXQ_STATS_IN_FLAGS_OFST 4
-#define       MC_CMD_TXQ_STATS_IN_FLAGS_LEN 4
-#define        MC_CMD_TXQ_STATS_IN_CLEAR_OFST 4
-#define        MC_CMD_TXQ_STATS_IN_CLEAR_LBN 0
-#define        MC_CMD_TXQ_STATS_IN_CLEAR_WIDTH 1
-
-/* MC_CMD_TXQ_STATS_OUT msgresponse */
-#define    MC_CMD_TXQ_STATS_OUT_LENMIN 0
-#define    MC_CMD_TXQ_STATS_OUT_LENMAX 248
-#define    MC_CMD_TXQ_STATS_OUT_LENMAX_MCDI2 1016
-#define    MC_CMD_TXQ_STATS_OUT_LEN(num) (0+8*(num))
-#define    MC_CMD_TXQ_STATS_OUT_STATISTICS_NUM(len) (((len)-0)/8)
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_OFST 0
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LEN 8
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LO_OFST 0
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LO_LEN 4
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LO_LBN 0
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LO_WIDTH 32
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_HI_OFST 4
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_HI_LEN 4
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_HI_LBN 32
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_HI_WIDTH 32
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_MINNUM 0
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_MAXNUM 31
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_MAXNUM_MCDI2 127
-#define          MC_CMD_TXQ_STATS_CTPIO_MAX_FILL 0x0 /* enum */
-
-/* FUNCTION_PERSONALITY structuredef: The meanings of the personalities are
- * defined in SF-120734-TC with more information in SF-122717-TC.
- */
-#define    FUNCTION_PERSONALITY_LEN 4
-#define       FUNCTION_PERSONALITY_ID_OFST 0
-#define       FUNCTION_PERSONALITY_ID_LEN 4
-/* enum: Function has no assigned personality */
-#define          FUNCTION_PERSONALITY_NULL 0x0
-/* enum: Function has an EF100-style function control window and VI windows
- * with both EF100 and vDPA doorbells.
- */
-#define          FUNCTION_PERSONALITY_EF100 0x1
-/* enum: Function has virtio net device configuration registers and doorbells
- * for virtio queue pairs.
- */
-#define          FUNCTION_PERSONALITY_VIRTIO_NET 0x2
-/* enum: Function has virtio block device configuration registers and a
- * doorbell for a single virtqueue.
- */
-#define          FUNCTION_PERSONALITY_VIRTIO_BLK 0x3
-/* enum: Function is a Xilinx acceleration device - management function */
-#define          FUNCTION_PERSONALITY_ACCEL_MGMT 0x4
-/* enum: Function is a Xilinx acceleration device - user function */
-#define          FUNCTION_PERSONALITY_ACCEL_USR 0x5
-#define       FUNCTION_PERSONALITY_ID_LBN 0
-#define       FUNCTION_PERSONALITY_ID_WIDTH 32
-
-
-/***********************************/
 /* MC_CMD_VIRTIO_GET_FEATURES
  * Get a list of the virtio features supported by the device.
  */
@@ -25162,37 +22177,6 @@
 
 
 /***********************************/
-/* MC_CMD_VIRTIO_GET_CAPABILITIES
- * Get virtio capabilities supported by the device. Returns general virtio
- * capabilities and limitations of the hardware / firmware implementation
- * (hardware device as a whole), rather than that of individual configured
- * virtio devices. At present, only the absolute maximum number of queues
- * allowed on multi-queue devices is returned. Response is expected to be
- * extended as necessary in the future.
- */
-#define MC_CMD_VIRTIO_GET_CAPABILITIES 0x1d3
-#undef MC_CMD_0x1d3_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VIRTIO_GET_CAPABILITIES_IN msgrequest */
-#define    MC_CMD_VIRTIO_GET_CAPABILITIES_IN_LEN 4
-/* Type of device to get capabilities for. Matches the device id as defined by
- * the virtio spec.
- */
-#define       MC_CMD_VIRTIO_GET_CAPABILITIES_IN_DEVICE_ID_OFST 0
-#define       MC_CMD_VIRTIO_GET_CAPABILITIES_IN_DEVICE_ID_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_VIRTIO_GET_FEATURES/MC_CMD_VIRTIO_GET_FEATURES_IN/DEVICE_ID */
-
-/* MC_CMD_VIRTIO_GET_CAPABILITIES_OUT msgresponse */
-#define    MC_CMD_VIRTIO_GET_CAPABILITIES_OUT_LEN 4
-/* Maximum number of queues supported for a single device instance */
-#define       MC_CMD_VIRTIO_GET_CAPABILITIES_OUT_MAX_QUEUES_OFST 0
-#define       MC_CMD_VIRTIO_GET_CAPABILITIES_OUT_MAX_QUEUES_LEN 4
-
-
-/***********************************/
 /* MC_CMD_VIRTIO_INIT_QUEUE
  * Create a virtio virtqueue. Fails with EALREADY if the queue already exists.
  * Fails with ENOSUP if a feature is requested that isn't supported. Fails with
@@ -25474,866 +22458,6 @@
 #define       PCIE_FUNCTION_INTF_LBN 32
 #define       PCIE_FUNCTION_INTF_WIDTH 32
 
-/* QUEUE_ID structuredef: Structure representing an absolute queue identifier
- * (absolute VI number + VI relative queue number). On Keystone, a VI can
- * contain multiple queues (at present, up to 2), each with separate controls
- * for direction. This structure is required to uniquely identify the absolute
- * source queue for descriptor proxy functions.
- */
-#define    QUEUE_ID_LEN 4
-/* Absolute VI number */
-#define       QUEUE_ID_ABS_VI_OFST 0
-#define       QUEUE_ID_ABS_VI_LEN 2
-#define       QUEUE_ID_ABS_VI_LBN 0
-#define       QUEUE_ID_ABS_VI_WIDTH 16
-/* Relative queue number within the VI */
-#define       QUEUE_ID_REL_QUEUE_LBN 16
-#define       QUEUE_ID_REL_QUEUE_WIDTH 1
-#define       QUEUE_ID_RESERVED_LBN 17
-#define       QUEUE_ID_RESERVED_WIDTH 15
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_CREATE
- * Descriptor proxy functions are abstract devices that forward all request
- * submitted to the host PCIe function (descriptors submitted to Virtio or
- * EF100 queues) to be handled on another function (most commonly on the
- * embedded Application Processor), via EF100 descriptor proxy, memory-to-
- * memory and descriptor-to-completion mechanisms. Primary user is Virtio-blk
- * subsystem, see SF-122927-TC. This function allocates a new descriptor proxy
- * function on the host and assigns a user-defined label. The actual function
- * configuration is not persisted until the caller configures it with
- * MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN and commits with
- * MC_CMD_DESC_PROXY_FUNC_COMMIT_IN.
- */
-#define MC_CMD_DESC_PROXY_FUNC_CREATE 0x172
-#undef MC_CMD_0x172_PRIVILEGE_CTG
-
-#define MC_CMD_0x172_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_CREATE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_CREATE_IN_LEN 52
-/* PCIe Function ID to allocate (as struct PCIE_FUNCTION). Set to
- * {PF_ANY,VF_ANY,interface} for "any available function" Set to
- * {PF_ANY,VF_NULL,interface} for "any available PF"
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LEN 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LO_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LO_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LO_LBN 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LO_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_HI_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_HI_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_HI_LBN 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_HI_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_PF_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_PF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_VF_OFST 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_VF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_INTF_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_INTF_LEN 4
-/* The personality to set. The meanings of the personalities are defined in
- * SF-120734-TC with more information in SF-122717-TC. At present, we only
- * support proxying for VIRTIO_BLK
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_PERSONALITY_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_PERSONALITY_LEN 4
-/*            Enum values, see field(s): */
-/*               FUNCTION_PERSONALITY/ID */
-/* User-defined label (zero-terminated ASCII string) to uniquely identify the
- * function
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_LABEL_OFST 12
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_LABEL_LEN 40
-
-/* MC_CMD_DESC_PROXY_FUNC_CREATE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_LEN 12
-/* Handle to the descriptor proxy function */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_HANDLE_LEN 4
-/* Allocated function ID (as struct PCIE_FUNCTION) */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LEN 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LO_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LO_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LO_LBN 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LO_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_HI_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_HI_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_HI_LBN 64
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_HI_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_PF_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_PF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_VF_OFST 6
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_VF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_INTF_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_INTF_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_DESTROY
- * Remove an existing descriptor proxy function. Underlying function
- * personality and configuration reverts back to factory default. Function
- * configuration is committed immediately to specified store and any function
- * ownership is released.
- */
-#define MC_CMD_DESC_PROXY_FUNC_DESTROY 0x173
-#undef MC_CMD_0x173_PRIVILEGE_CTG
-
-#define MC_CMD_0x173_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_DESTROY_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_LEN 44
-/* User-defined label (zero-terminated ASCII string) to uniquely identify the
- * function
- */
-#define       MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_LABEL_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_LABEL_LEN 40
-/* Store from which to remove function configuration */
-#define       MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_STORE_OFST 40
-#define       MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_STORE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_DESC_PROXY_FUNC_COMMIT/MC_CMD_DESC_PROXY_FUNC_COMMIT_IN/STORE */
-
-/* MC_CMD_DESC_PROXY_FUNC_DESTROY_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_DESTROY_OUT_LEN 0
-
-/* VIRTIO_BLK_CONFIG structuredef: Virtio block device configuration. See
- * Virtio specification v1.1, Sections 5.2.3 and 6 for definition of feature
- * bits. See Virtio specification v1.1, Section 5.2.4 (struct
- * virtio_blk_config) for definition of remaining configuration fields
- */
-#define    VIRTIO_BLK_CONFIG_LEN 68
-/* Virtio block device features to advertise, per Virtio 1.1, 5.2.3 and 6 */
-#define       VIRTIO_BLK_CONFIG_FEATURES_OFST 0
-#define       VIRTIO_BLK_CONFIG_FEATURES_LEN 8
-#define       VIRTIO_BLK_CONFIG_FEATURES_LO_OFST 0
-#define       VIRTIO_BLK_CONFIG_FEATURES_LO_LEN 4
-#define       VIRTIO_BLK_CONFIG_FEATURES_LO_LBN 0
-#define       VIRTIO_BLK_CONFIG_FEATURES_LO_WIDTH 32
-#define       VIRTIO_BLK_CONFIG_FEATURES_HI_OFST 4
-#define       VIRTIO_BLK_CONFIG_FEATURES_HI_LEN 4
-#define       VIRTIO_BLK_CONFIG_FEATURES_HI_LBN 32
-#define       VIRTIO_BLK_CONFIG_FEATURES_HI_WIDTH 32
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BARRIER_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BARRIER_LBN 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BARRIER_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SIZE_MAX_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SIZE_MAX_LBN 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SIZE_MAX_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SEG_MAX_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SEG_MAX_LBN 2
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SEG_MAX_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_GEOMETRY_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_GEOMETRY_LBN 4
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_GEOMETRY_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_RO_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_RO_LBN 5
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_RO_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BLK_SIZE_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BLK_SIZE_LBN 6
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BLK_SIZE_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SCSI_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SCSI_LBN 7
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SCSI_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_FLUSH_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_FLUSH_LBN 9
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_FLUSH_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_TOPOLOGY_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_TOPOLOGY_LBN 10
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_TOPOLOGY_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_CONFIG_WCE_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_CONFIG_WCE_LBN 11
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_CONFIG_WCE_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_MQ_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_MQ_LBN 12
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_MQ_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_DISCARD_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_DISCARD_LBN 13
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_DISCARD_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_WRITE_ZEROES_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_WRITE_ZEROES_LBN 14
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_WRITE_ZEROES_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_INDIRECT_DESC_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_INDIRECT_DESC_LBN 28
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_INDIRECT_DESC_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_EVENT_IDX_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_EVENT_IDX_LBN 29
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_EVENT_IDX_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_VERSION_1_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_VERSION_1_LBN 32
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_VERSION_1_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ACCESS_PLATFORM_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ACCESS_PLATFORM_LBN 33
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ACCESS_PLATFORM_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_PACKED_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_PACKED_LBN 34
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_PACKED_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_IN_ORDER_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_IN_ORDER_LBN 35
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_IN_ORDER_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ORDER_PLATFORM_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ORDER_PLATFORM_LBN 36
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ORDER_PLATFORM_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_SR_IOV_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_SR_IOV_LBN 37
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_SR_IOV_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_NOTIFICATION_DATA_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_NOTIFICATION_DATA_LBN 38
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_NOTIFICATION_DATA_WIDTH 1
-#define       VIRTIO_BLK_CONFIG_FEATURES_LBN 0
-#define       VIRTIO_BLK_CONFIG_FEATURES_WIDTH 64
-/* The capacity of the device (expressed in 512-byte sectors) */
-#define       VIRTIO_BLK_CONFIG_CAPACITY_OFST 8
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LEN 8
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LO_OFST 8
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LO_LEN 4
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LO_LBN 64
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LO_WIDTH 32
-#define       VIRTIO_BLK_CONFIG_CAPACITY_HI_OFST 12
-#define       VIRTIO_BLK_CONFIG_CAPACITY_HI_LEN 4
-#define       VIRTIO_BLK_CONFIG_CAPACITY_HI_LBN 96
-#define       VIRTIO_BLK_CONFIG_CAPACITY_HI_WIDTH 32
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LBN 64
-#define       VIRTIO_BLK_CONFIG_CAPACITY_WIDTH 64
-/* Maximum size of any single segment. Only valid when VIRTIO_BLK_F_SIZE_MAX is
- * set.
- */
-#define       VIRTIO_BLK_CONFIG_SIZE_MAX_OFST 16
-#define       VIRTIO_BLK_CONFIG_SIZE_MAX_LEN 4
-#define       VIRTIO_BLK_CONFIG_SIZE_MAX_LBN 128
-#define       VIRTIO_BLK_CONFIG_SIZE_MAX_WIDTH 32
-/* Maximum number of segments in a request. Only valid when
- * VIRTIO_BLK_F_SEG_MAX is set.
- */
-#define       VIRTIO_BLK_CONFIG_SEG_MAX_OFST 20
-#define       VIRTIO_BLK_CONFIG_SEG_MAX_LEN 4
-#define       VIRTIO_BLK_CONFIG_SEG_MAX_LBN 160
-#define       VIRTIO_BLK_CONFIG_SEG_MAX_WIDTH 32
-/* Disk-style geometry - cylinders. Only valid when VIRTIO_BLK_F_GEOMETRY is
- * set.
- */
-#define       VIRTIO_BLK_CONFIG_CYLINDERS_OFST 24
-#define       VIRTIO_BLK_CONFIG_CYLINDERS_LEN 2
-#define       VIRTIO_BLK_CONFIG_CYLINDERS_LBN 192
-#define       VIRTIO_BLK_CONFIG_CYLINDERS_WIDTH 16
-/* Disk-style geometry - heads. Only valid when VIRTIO_BLK_F_GEOMETRY is set.
- */
-#define       VIRTIO_BLK_CONFIG_HEADS_OFST 26
-#define       VIRTIO_BLK_CONFIG_HEADS_LEN 1
-#define       VIRTIO_BLK_CONFIG_HEADS_LBN 208
-#define       VIRTIO_BLK_CONFIG_HEADS_WIDTH 8
-/* Disk-style geometry - sectors. Only valid when VIRTIO_BLK_F_GEOMETRY is set.
- */
-#define       VIRTIO_BLK_CONFIG_SECTORS_OFST 27
-#define       VIRTIO_BLK_CONFIG_SECTORS_LEN 1
-#define       VIRTIO_BLK_CONFIG_SECTORS_LBN 216
-#define       VIRTIO_BLK_CONFIG_SECTORS_WIDTH 8
-/* Block size of disk. Only valid when VIRTIO_BLK_F_BLK_SIZE is set. */
-#define       VIRTIO_BLK_CONFIG_BLK_SIZE_OFST 28
-#define       VIRTIO_BLK_CONFIG_BLK_SIZE_LEN 4
-#define       VIRTIO_BLK_CONFIG_BLK_SIZE_LBN 224
-#define       VIRTIO_BLK_CONFIG_BLK_SIZE_WIDTH 32
-/* Block topology - number of logical blocks per physical block (log2). Only
- * valid when VIRTIO_BLK_F_TOPOLOGY is set.
- */
-#define       VIRTIO_BLK_CONFIG_PHYSICAL_BLOCK_EXP_OFST 32
-#define       VIRTIO_BLK_CONFIG_PHYSICAL_BLOCK_EXP_LEN 1
-#define       VIRTIO_BLK_CONFIG_PHYSICAL_BLOCK_EXP_LBN 256
-#define       VIRTIO_BLK_CONFIG_PHYSICAL_BLOCK_EXP_WIDTH 8
-/* Block topology - offset of first aligned logical block. Only valid when
- * VIRTIO_BLK_F_TOPOLOGY is set.
- */
-#define       VIRTIO_BLK_CONFIG_ALIGNMENT_OFFSET_OFST 33
-#define       VIRTIO_BLK_CONFIG_ALIGNMENT_OFFSET_LEN 1
-#define       VIRTIO_BLK_CONFIG_ALIGNMENT_OFFSET_LBN 264
-#define       VIRTIO_BLK_CONFIG_ALIGNMENT_OFFSET_WIDTH 8
-/* Block topology - suggested minimum I/O size in blocks. Only valid when
- * VIRTIO_BLK_F_TOPOLOGY is set.
- */
-#define       VIRTIO_BLK_CONFIG_MIN_IO_SIZE_OFST 34
-#define       VIRTIO_BLK_CONFIG_MIN_IO_SIZE_LEN 2
-#define       VIRTIO_BLK_CONFIG_MIN_IO_SIZE_LBN 272
-#define       VIRTIO_BLK_CONFIG_MIN_IO_SIZE_WIDTH 16
-/* Block topology - optimal (suggested maximum) I/O size in blocks. Only valid
- * when VIRTIO_BLK_F_TOPOLOGY is set.
- */
-#define       VIRTIO_BLK_CONFIG_OPT_IO_SIZE_OFST 36
-#define       VIRTIO_BLK_CONFIG_OPT_IO_SIZE_LEN 4
-#define       VIRTIO_BLK_CONFIG_OPT_IO_SIZE_LBN 288
-#define       VIRTIO_BLK_CONFIG_OPT_IO_SIZE_WIDTH 32
-/* Unused, set to zero. Note that virtio_blk_config.writeback is volatile and
- * not carried in config data.
- */
-#define       VIRTIO_BLK_CONFIG_UNUSED0_OFST 40
-#define       VIRTIO_BLK_CONFIG_UNUSED0_LEN 2
-#define       VIRTIO_BLK_CONFIG_UNUSED0_LBN 320
-#define       VIRTIO_BLK_CONFIG_UNUSED0_WIDTH 16
-/* Number of queues. Only valid if the VIRTIO_BLK_F_MQ feature is negotiated.
- */
-#define       VIRTIO_BLK_CONFIG_NUM_QUEUES_OFST 42
-#define       VIRTIO_BLK_CONFIG_NUM_QUEUES_LEN 2
-#define       VIRTIO_BLK_CONFIG_NUM_QUEUES_LBN 336
-#define       VIRTIO_BLK_CONFIG_NUM_QUEUES_WIDTH 16
-/* Maximum discard sectors size, in 512-byte units. Only valid if
- * VIRTIO_BLK_F_DISCARD is set.
- */
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SECTORS_OFST 44
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SECTORS_LEN 4
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SECTORS_LBN 352
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SECTORS_WIDTH 32
-/* Maximum discard segment number. Only valid if VIRTIO_BLK_F_DISCARD is set.
- */
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SEG_OFST 48
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SEG_LEN 4
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SEG_LBN 384
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SEG_WIDTH 32
-/* Discard sector alignment, in 512-byte units. Only valid if
- * VIRTIO_BLK_F_DISCARD is set.
- */
-#define       VIRTIO_BLK_CONFIG_DISCARD_SECTOR_ALIGNMENT_OFST 52
-#define       VIRTIO_BLK_CONFIG_DISCARD_SECTOR_ALIGNMENT_LEN 4
-#define       VIRTIO_BLK_CONFIG_DISCARD_SECTOR_ALIGNMENT_LBN 416
-#define       VIRTIO_BLK_CONFIG_DISCARD_SECTOR_ALIGNMENT_WIDTH 32
-/* Maximum write zeroes sectors size, in 512-byte units. Only valid if
- * VIRTIO_BLK_F_WRITE_ZEROES is set.
- */
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SECTORS_OFST 56
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SECTORS_LEN 4
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SECTORS_LBN 448
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SECTORS_WIDTH 32
-/* Maximum write zeroes segment number. Only valid if VIRTIO_BLK_F_WRITE_ZEROES
- * is set.
- */
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SEG_OFST 60
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SEG_LEN 4
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SEG_LBN 480
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SEG_WIDTH 32
-/* Write zeroes request can result in deallocating one or more sectors. Only
- * valid if VIRTIO_BLK_F_WRITE_ZEROES is set.
- */
-#define       VIRTIO_BLK_CONFIG_WRITE_ZEROES_MAY_UNMAP_OFST 64
-#define       VIRTIO_BLK_CONFIG_WRITE_ZEROES_MAY_UNMAP_LEN 1
-#define       VIRTIO_BLK_CONFIG_WRITE_ZEROES_MAY_UNMAP_LBN 512
-#define       VIRTIO_BLK_CONFIG_WRITE_ZEROES_MAY_UNMAP_WIDTH 8
-/* Unused, set to zero. */
-#define       VIRTIO_BLK_CONFIG_UNUSED1_OFST 65
-#define       VIRTIO_BLK_CONFIG_UNUSED1_LEN 3
-#define       VIRTIO_BLK_CONFIG_UNUSED1_LBN 520
-#define       VIRTIO_BLK_CONFIG_UNUSED1_WIDTH 24
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_CONFIG_SET
- * Set configuration for an existing descriptor proxy function. Configuration
- * data must match function personality. The actual function configuration is
- * not persisted until the caller commits with MC_CMD_DESC_PROXY_FUNC_COMMIT_IN
- */
-#define MC_CMD_DESC_PROXY_FUNC_CONFIG_SET 0x174
-#undef MC_CMD_0x174_PRIVILEGE_CTG
-
-#define MC_CMD_0x174_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_LENMIN 20
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_LENMAX 252
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_LEN(num) (20+1*(num))
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_NUM(len) (((len)-20)/1)
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_HANDLE_LEN 4
-/* Reserved for future extension, set to zero. */
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_RESERVED_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_RESERVED_LEN 16
-/* Configuration data. Format of configuration data is determined implicitly
- * from function personality referred to by HANDLE. Currently, only supported
- * format is VIRTIO_BLK_CONFIG.
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_OFST 20
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_LEN 1
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_MINNUM 0
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_MAXNUM 232
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_MAXNUM_MCDI2 1000
-
-/* MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_COMMIT
- * Commit function configuration to non-volatile or volatile store. Once
- * configuration is applied to hardware (which may happen immediately or on
- * next function/device reset) a DESC_PROXY_FUNC_CONFIG_SET MCDI event will be
- * delivered to callers MCDI event queue.
- */
-#define MC_CMD_DESC_PROXY_FUNC_COMMIT 0x175
-#undef MC_CMD_0x175_PRIVILEGE_CTG
-
-#define MC_CMD_0x175_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_COMMIT_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_LEN 8
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_HANDLE_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_STORE_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_STORE_LEN 4
-/* enum: Store into non-volatile (dynamic) config */
-#define          MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_NON_VOLATILE 0x0
-/* enum: Store into volatile (ephemeral) config */
-#define          MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_VOLATILE 0x1
-
-/* MC_CMD_DESC_PROXY_FUNC_COMMIT_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_COMMIT_OUT_LEN 4
-/* Generation count to be delivered in an event once configuration becomes live
- */
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_OUT_CONFIG_GENERATION_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_OUT_CONFIG_GENERATION_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_OPEN
- * Retrieve a handle for an existing descriptor proxy function. Returns an
- * integer handle, valid until function is deallocated, MC rebooted or power-
- * cycle. Returns ENODEV if no function with given label exists.
- */
-#define MC_CMD_DESC_PROXY_FUNC_OPEN 0x176
-#undef MC_CMD_0x176_PRIVILEGE_CTG
-
-#define MC_CMD_0x176_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_OPEN_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_IN_LEN 40
-/* User-defined label (zero-terminated ASCII string) to uniquely identify the
- * function
- */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_IN_LABEL_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_IN_LABEL_LEN 40
-
-/* MC_CMD_DESC_PROXY_FUNC_OPEN_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LENMIN 40
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LENMAX 252
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LEN(num) (40+1*(num))
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_NUM(len) (((len)-40)/1)
-/* Handle to the descriptor proxy function */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_HANDLE_LEN 4
-/* PCIe Function ID (as struct PCIE_FUNCTION) */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LEN 8
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LO_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LO_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LO_LBN 32
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LO_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_HI_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_HI_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_HI_LBN 64
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_HI_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_PF_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_PF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_VF_OFST 6
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_VF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_INTF_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_INTF_LEN 4
-/* Function personality */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_PERSONALITY_OFST 12
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_PERSONALITY_LEN 4
-/*            Enum values, see field(s): */
-/*               FUNCTION_PERSONALITY/ID */
-/* Function configuration state */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_STATUS_OFST 16
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_STATUS_LEN 4
-/* enum: Function configuration is visible to the host (live) */
-#define          MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LIVE 0x0
-/* enum: Function configuration is pending reset */
-#define          MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_PENDING 0x1
-/* enum: Function configuration is missing (created, but no configuration
- * committed)
- */
-#define          MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_UNCONFIGURED 0x2
-/* Generation count to be delivered in an event once the configuration becomes
- * live (if status is "pending")
- */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_GENERATION_OFST 20
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_GENERATION_LEN 4
-/* Reserved for future extension, set to zero. */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_RESERVED_OFST 24
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_RESERVED_LEN 16
-/* Configuration data corresponding to function personality. Currently, only
- * supported format is VIRTIO_BLK_CONFIG. Not valid if status is UNCONFIGURED.
- */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_OFST 40
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_LEN 1
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_MINNUM 0
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_MAXNUM 212
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_MAXNUM_MCDI2 980
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_CLOSE
- * Releases a handle for an open descriptor proxy function. If proxying was
- * enabled on the device, the caller is expected to gracefully stop it using
- * MC_CMD_DESC_PROXY_FUNC_DISABLE prior to calling this function. Closing an
- * active device without disabling proxying will result in forced close, which
- * will put the device into a failed state and signal the host driver of the
- * error (for virtio, DEVICE_NEEDS_RESET flag would be set on the host side)
- */
-#define MC_CMD_DESC_PROXY_FUNC_CLOSE 0x1a1
-#undef MC_CMD_0x1a1_PRIVILEGE_CTG
-
-#define MC_CMD_0x1a1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_CLOSE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_CLOSE_IN_LEN 4
-/* Handle to the descriptor proxy function */
-#define       MC_CMD_DESC_PROXY_FUNC_CLOSE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CLOSE_IN_HANDLE_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_CLOSE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_CLOSE_OUT_LEN 0
-
-/* DESC_PROXY_FUNC_MAP structuredef */
-#define    DESC_PROXY_FUNC_MAP_LEN 52
-/* PCIe function ID (as struct PCIE_FUNCTION) */
-#define       DESC_PROXY_FUNC_MAP_FUNC_OFST 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_LEN 8
-#define       DESC_PROXY_FUNC_MAP_FUNC_LO_OFST 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_LO_LEN 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_LO_LBN 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_LO_WIDTH 32
-#define       DESC_PROXY_FUNC_MAP_FUNC_HI_OFST 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_HI_LEN 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_HI_LBN 32
-#define       DESC_PROXY_FUNC_MAP_FUNC_HI_WIDTH 32
-#define       DESC_PROXY_FUNC_MAP_FUNC_LBN 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_WIDTH 64
-#define       DESC_PROXY_FUNC_MAP_FUNC_PF_OFST 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_PF_LEN 2
-#define       DESC_PROXY_FUNC_MAP_FUNC_PF_LBN 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_PF_WIDTH 16
-#define       DESC_PROXY_FUNC_MAP_FUNC_VF_OFST 2
-#define       DESC_PROXY_FUNC_MAP_FUNC_VF_LEN 2
-#define       DESC_PROXY_FUNC_MAP_FUNC_VF_LBN 16
-#define       DESC_PROXY_FUNC_MAP_FUNC_VF_WIDTH 16
-#define       DESC_PROXY_FUNC_MAP_FUNC_INTF_OFST 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_INTF_LEN 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_INTF_LBN 32
-#define       DESC_PROXY_FUNC_MAP_FUNC_INTF_WIDTH 32
-/* Function personality */
-#define       DESC_PROXY_FUNC_MAP_PERSONALITY_OFST 8
-#define       DESC_PROXY_FUNC_MAP_PERSONALITY_LEN 4
-/*            Enum values, see field(s): */
-/*               FUNCTION_PERSONALITY/ID */
-#define       DESC_PROXY_FUNC_MAP_PERSONALITY_LBN 64
-#define       DESC_PROXY_FUNC_MAP_PERSONALITY_WIDTH 32
-/* User-defined label (zero-terminated ASCII string) to uniquely identify the
- * function
- */
-#define       DESC_PROXY_FUNC_MAP_LABEL_OFST 12
-#define       DESC_PROXY_FUNC_MAP_LABEL_LEN 40
-#define       DESC_PROXY_FUNC_MAP_LABEL_LBN 96
-#define       DESC_PROXY_FUNC_MAP_LABEL_WIDTH 320
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_ENUM
- * Enumerate existing descriptor proxy functions
- */
-#define MC_CMD_DESC_PROXY_FUNC_ENUM 0x177
-#undef MC_CMD_0x177_PRIVILEGE_CTG
-
-#define MC_CMD_0x177_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_ENUM_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_IN_LEN 4
-/* Starting index, set to 0 on first request. See
- * MC_CMD_DESC_PROXY_FUNC_ENUM_OUT/FLAGS.
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_IN_START_IDX_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_IN_START_IDX_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_ENUM_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_LENMIN 4
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_LENMAX 212
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_LENMAX_MCDI2 992
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_LEN(num) (4+52*(num))
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_NUM(len) (((len)-4)/52)
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FLAGS_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FLAGS_LEN 4
-#define        MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_MORE_DATA_OFST 0
-#define        MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_MORE_DATA_LBN 0
-#define        MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_MORE_DATA_WIDTH 1
-/* Function map, as array of DESC_PROXY_FUNC_MAP */
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_LEN 52
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_MINNUM 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_MAXNUM 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_MAXNUM_MCDI2 19
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE
- * Enable descriptor proxying for function into target event queue. Returns VI
- * allocation info for the proxy source function, so that the caller can map
- * absolute VI IDs from descriptor proxy events back to the originating
- * function. This is a legacy function that only supports single queue proxy
- * devices. It is also limited in that it can only be called after host driver
- * attach (once VI allocation is known) and will return MC_CMD_ERR_ENOTCONN
- * otherwise. For new code, see MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE which
- * supports multi-queue devices and has no dependency on host driver attach.
- */
-#define MC_CMD_DESC_PROXY_FUNC_ENABLE 0x178
-#undef MC_CMD_0x178_PRIVILEGE_CTG
-
-#define MC_CMD_0x178_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_LEN 8
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_HANDLE_LEN 4
-/* Descriptor proxy sink queue (caller function relative). Must be extended
- * width event queue
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_TARGET_EVQ_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_TARGET_EVQ_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_LEN 8
-/* The number of VIs allocated on the function */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_VI_COUNT_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_VI_COUNT_LEN 4
-/* The base absolute VI number allocated to the function. */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_VI_BASE_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_VI_BASE_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE
- * Enable descriptor proxying for a source queue on a host function into target
- * event queue. Source queue number is a relative virtqueue number on the
- * source function (0 to max_virtqueues-1). For a multi-queue device, the
- * caller must enable all source queues individually. To retrieve absolute VI
- * information for the source function (so that VI IDs from descriptor proxy
- * events can be mapped back to source function / queue) see
- * MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO
- */
-#define MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE 0x1d0
-#undef MC_CMD_0x1d0_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d0_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_LEN 12
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_HANDLE_LEN 4
-/* Source relative queue number to enable proxying on */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_SOURCE_QUEUE_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_SOURCE_QUEUE_LEN 4
-/* Descriptor proxy sink queue (caller function relative). Must be extended
- * width event queue
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_TARGET_EVQ_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_TARGET_EVQ_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE
- * Disable descriptor proxying for function. For multi-queue functions,
- * disables all queues.
- */
-#define MC_CMD_DESC_PROXY_FUNC_DISABLE 0x179
-#undef MC_CMD_0x179_PRIVILEGE_CTG
-
-#define MC_CMD_0x179_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_DISABLE_IN_LEN 4
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_IN_HANDLE_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_DISABLE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE
- * Disable descriptor proxying for a specific source queue on a function.
- */
-#define MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE 0x1d1
-#undef MC_CMD_0x1d1_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_LEN 8
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_HANDLE_LEN 4
-/* Source relative queue number to disable proxying on */
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_SOURCE_QUEUE_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_SOURCE_QUEUE_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_GET_VI_INFO
- * Returns absolute VI allocation information for the descriptor proxy source
- * function referenced by HANDLE, so that the caller can map absolute VI IDs
- * from descriptor proxy events back to the originating function and queue. The
- * call is only valid after the host driver for the source function has
- * attached (after receiving a driver attach event for the descriptor proxy
- * function) and will fail with ENOTCONN otherwise.
- */
-#define MC_CMD_DESC_PROXY_GET_VI_INFO 0x1d2
-#undef MC_CMD_0x1d2_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d2_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_GET_VI_INFO_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_GET_VI_INFO_IN_LEN 4
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_GET_VI_INFO_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_GET_VI_INFO_IN_HANDLE_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_LENMIN 0
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_LENMAX 252
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_NUM(len) (((len)-0)/4)
-/* VI information (VI ID + VI relative queue number) for each of the source
- * queues (in order from 0 to max_virtqueues-1), as array of QUEUE_ID
- * structures.
- */
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_MINNUM 0
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_MAXNUM 63
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_MAXNUM_MCDI2 255
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_ABS_VI_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_ABS_VI_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_REL_QUEUE_LBN 16
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_REL_QUEUE_WIDTH 1
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_RESERVED_LBN 17
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_RESERVED_WIDTH 15
-
-
-/***********************************/
-/* MC_CMD_GET_ADDR_SPC_ID
- * Get Address space identifier for use in mem2mem descriptors for a given
- * target. See SF-120734-TC for details on ADDR_SPC_IDs and mem2mem
- * descriptors.
- */
-#define MC_CMD_GET_ADDR_SPC_ID 0x1a0
-#undef MC_CMD_0x1a0_PRIVILEGE_CTG
-
-#define MC_CMD_0x1a0_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_GET_ADDR_SPC_ID_IN msgrequest */
-#define    MC_CMD_GET_ADDR_SPC_ID_IN_LEN 16
-/* Resource type to get ADDR_SPC_ID for */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_TYPE_OFST 0
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_TYPE_LEN 4
-/* enum: Address space ID for host/AP memory DMA over the same interface this
- * MCDI was called on
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_SELF 0x0
-/* enum: Address space ID for host/AP memory DMA via PCI interface and function
- * specified by FUNC
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_PCI_FUNC 0x1
-/* enum: Address space ID for host/AP memory DMA via PCI interface and function
- * specified by FUNC with PASID value specified by PASID
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_PCI_FUNC_PASID 0x2
-/* enum: Address space ID for host/AP memory DMA via PCI interface and function
- * specified by FUNC with PASID value of relative VI specified by VI
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_REL_VI 0x3
-/* enum: Address space ID for host/AP memory DMA via PCI interface, function
- * and PASID value of absolute VI specified by VI
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_ABS_VI 0x4
-/* enum: Address space ID for host memory DMA via PCI interface and function of
- * descriptor proxy function specified by HANDLE
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_DESC_PROXY_HANDLE 0x5
-/* enum: Address space ID for DMA to/from MC memory */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_MC_MEM 0x6
-/* enum: Address space ID for DMA to/from other SmartNIC memory (on-chip, DDR)
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_NIC_MEM 0x7
-/* PCIe Function ID (as struct PCIE_FUNCTION). Only valid if TYPE is PCI_FUNC,
- * PCI_FUNC_PASID or REL_VI.
- */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LEN 8
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LO_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LO_LEN 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LO_LBN 32
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LO_WIDTH 32
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_HI_OFST 8
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_HI_LEN 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_HI_LBN 64
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_HI_WIDTH 32
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_PF_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_PF_LEN 2
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_VF_OFST 6
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_VF_LEN 2
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_INTF_OFST 8
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_INTF_LEN 4
-/* PASID value. Only valid if TYPE is PCI_FUNC_PASID. */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_PASID_OFST 12
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_PASID_LEN 4
-/* Relative or absolute VI number. Only valid if TYPE is REL_VI or ABS_VI */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_VI_OFST 12
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_VI_LEN 4
-/* Descriptor proxy function handle. Only valid if TYPE is DESC_PROXY_HANDLE.
- */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_HANDLE_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_HANDLE_LEN 4
-
-/* MC_CMD_GET_ADDR_SPC_ID_OUT msgresponse */
-#define    MC_CMD_GET_ADDR_SPC_ID_OUT_LEN 8
-/* Address Space ID for the requested target. Only the lower 36 bits are valid
- * in the current SmartNIC implementation.
- */
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_OFST 0
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LEN 8
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LO_OFST 0
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LO_LEN 4
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LO_LBN 0
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LO_WIDTH 32
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_HI_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_HI_LEN 4
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_HI_LBN 32
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_HI_WIDTH 32
-
 
 /***********************************/
 /* MC_CMD_GET_CLIENT_HANDLE
@@ -26359,7 +22483,8 @@
  * INTF=CALLER, PF=PF_NULL, VF=... to refer to a VF child of the calling PF or
  * a sibling VF of the calling VF. - INTF=CALLER, PF=..., VF=VF_NULL to refer
  * to a PF on the calling interface - INTF=CALLER, PF=..., VF=... to refer to a
- * VF on the calling interface - INTF=..., PF=..., VF=VF_NULL to refer to a PF
+ * VF on the calling interface - INTF=..., PF=PF_NULL, VF=VF_NULL to refer to
+ * the named interface itself - INTF=..., PF=..., VF=VF_NULL to refer to a PF
  * on a named interface - INTF=..., PF=..., VF=... to refer to a VF on a named
  * interface where ... refers to a small integer for the VF/PF fields, and to
  * values from the PCIE_INTERFACE enum for for the INTF field. It's only
@@ -26380,6 +22505,7 @@
  * backwards compatibility only, callers should use PCIE_INTERFACE_CALLER.
  */
 #define          MC_CMD_GET_CLIENT_HANDLE_IN_PCIE_FUNCTION_INTF_NULL 0xffffffff
+/* See structuredef: PCIE_FUNCTION */
 #define       MC_CMD_GET_CLIENT_HANDLE_IN_FUNC_PF_OFST 4
 #define       MC_CMD_GET_CLIENT_HANDLE_IN_FUNC_PF_LEN 2
 #define       MC_CMD_GET_CLIENT_HANDLE_IN_FUNC_VF_OFST 6
@@ -27350,7 +23476,7 @@
 /* MAE_MPORT_SELECTOR structuredef: MPORTS are identified by an opaque unsigned
  * integer value (mport_id) that is guaranteed to be representable within
  * 32-bits or within any NIC interface field that needs store the value
- * (whichever is narrowers). This selector structure provides a stable way to
+ * (whichever is narrower). This selector structure provides a stable way to
  * refer to m-ports.
  */
 #define    MAE_MPORT_SELECTOR_LEN 4
@@ -27425,10 +23551,22 @@
 #define       MAE_MPORT_SELECTOR_FLAT_WIDTH 32
 
 /* MAE_LINK_ENDPOINT_SELECTOR structuredef: Structure that identifies a real or
- * virtual network port by MAE port and link end
+ * virtual network port by MAE port and link end. Intended to be used by
+ * network port MCDI commands. Setting FLAT to MAE_LINK_ENDPOINT_COMPAT is
+ * equivalent to using the previous version of the command. Not all possible
+ * combinations of MPORT_END and MPORT_SELECTOR in MAE_LINK_ENDPOINT_SELECTOR
+ * will work in all circumstances. 1. Some will always work (e.g. a VF can
+ * always address its logical MAC using MPORT_SELECTOR=ASSIGNED,LINK_END=VNIC),
+ * 2. Some are not meaningful and will always fail with EINVAL (e.g. attempting
+ * to address the VNIC end of a link to a physical port), 3. Some are
+ * meaningful but require the MCDI client to have the required permission and
+ * fail with EPERM otherwise (e.g. trying to set the MAC on a VF the caller
+ * cannot administer), and 4. Some could be implementation-specific and fail
+ * with ENOTSUP if not available (no examples exist right now). See
+ * SF-123581-TC section 4.3 for more details.
  */
 #define    MAE_LINK_ENDPOINT_SELECTOR_LEN 8
-/* The MAE MPORT of interest */
+/* Identifier for the MAE MPORT of interest */
 #define       MAE_LINK_ENDPOINT_SELECTOR_MPORT_SELECTOR_OFST 0
 #define       MAE_LINK_ENDPOINT_SELECTOR_MPORT_SELECTOR_LEN 4
 #define       MAE_LINK_ENDPOINT_SELECTOR_MPORT_SELECTOR_LBN 0
@@ -27829,6 +23967,8 @@
 #define       MC_CMD_MAE_COUNTER_ALLOC_OUT_COUNTER_ID_MAXNUM_MCDI2 253
 /* enum: A counter ID that is guaranteed never to represent a real counter */
 #define          MC_CMD_MAE_COUNTER_ALLOC_OUT_COUNTER_ID_NULL 0xffffffff
+/*            Other enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 
 
 /***********************************/
@@ -28266,6 +24406,24 @@
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_SUPPRESS_SELF_DELIVERY_OFST 0
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_SUPPRESS_SELF_DELIVERY_LBN 14
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_SUPPRESS_SELF_DELIVERY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_C_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_C_PL_LBN 15
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_C_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_D_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_D_PL_LBN 16
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_D_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_LBN 17
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_SET_NET_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_SET_NET_CHAN_LBN 18
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_SET_NET_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_PLUGIN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_PLUGIN_LBN 19
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_PLUGIN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_INC_L4_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_INC_L4_LBN 20
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_INC_L4_WIDTH 1
 /* If VLAN_PUSH >= 1, TCI value to be inserted as outermost VLAN. */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_VLAN0_TCI_BE_OFST 4
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_VLAN0_TCI_BE_LEN 2
@@ -28291,19 +24449,23 @@
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_DELIVER_OFST 20
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_DELIVER_LEN 4
 /* Allows an action set to trigger several counter updates. Set to
- * COUNTER_LIST_ID_NULL to request no counter action.
+ * MAE_COUNTER_ID_NULL to request no counter action.
  */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_COUNTER_LIST_ID_OFST 24
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_COUNTER_LIST_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 /* If a driver only wished to update one counter within this action set, then
  * it can supply a COUNTER_ID instead of allocating a single-element counter
  * list. The ID must have been allocated with COUNTER_TYPE=AR. This field
- * should be set to COUNTER_ID_NULL if this behaviour is not required. It is
- * not valid to supply a non-NULL value for both COUNTER_LIST_ID and
+ * should be set to MAE_COUNTER_ID_NULL if this behaviour is not required. It
+ * is not valid to supply a non-NULL value for both COUNTER_LIST_ID and
  * COUNTER_ID.
  */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_COUNTER_ID_OFST 28
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_COUNTER_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_MARK_VALUE_OFST 32
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_MARK_VALUE_LEN 4
 /* Set to MAC_ID_NULL to request no source MAC replacement. */
@@ -28347,6 +24509,24 @@
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_SUPPRESS_SELF_DELIVERY_OFST 0
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_SUPPRESS_SELF_DELIVERY_LBN 14
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_SUPPRESS_SELF_DELIVERY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_C_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_C_PL_LBN 15
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_C_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_D_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_D_PL_LBN 16
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_D_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_LBN 17
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_SET_NET_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_SET_NET_CHAN_LBN 18
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_SET_NET_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_PLUGIN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_PLUGIN_LBN 19
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_PLUGIN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_INC_L4_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_INC_L4_LBN 20
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_INC_L4_WIDTH 1
 /* If VLAN_PUSH >= 1, TCI value to be inserted as outermost VLAN. */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_VLAN0_TCI_BE_OFST 4
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_VLAN0_TCI_BE_LEN 2
@@ -28372,19 +24552,23 @@
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DELIVER_OFST 20
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DELIVER_LEN 4
 /* Allows an action set to trigger several counter updates. Set to
- * COUNTER_LIST_ID_NULL to request no counter action.
+ * MAE_COUNTER_ID_NULL to request no counter action.
  */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_COUNTER_LIST_ID_OFST 24
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_COUNTER_LIST_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 /* If a driver only wished to update one counter within this action set, then
  * it can supply a COUNTER_ID instead of allocating a single-element counter
  * list. The ID must have been allocated with COUNTER_TYPE=AR. This field
- * should be set to COUNTER_ID_NULL if this behaviour is not required. It is
- * not valid to supply a non-NULL value for both COUNTER_LIST_ID and
+ * should be set to MAE_COUNTER_ID_NULL if this behaviour is not required. It
+ * is not valid to supply a non-NULL value for both COUNTER_LIST_ID and
  * COUNTER_ID.
  */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_COUNTER_ID_OFST 28
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_COUNTER_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_MARK_VALUE_OFST 32
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_MARK_VALUE_LEN 4
 /* Set to MAC_ID_NULL to request no source MAC replacement. */
@@ -28437,6 +24621,172 @@
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_ECN_ECT_1_TO_CE_LBN 6
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_ECN_ECT_1_TO_CE_WIDTH 1
 
+/* MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN msgrequest: Only supported if
+ * MAE_ACTION_SET_ALLOC_V3_SUPPORTED is advertised in
+ * MC_CMD_GET_CAPABILITIES_V10_OUT.
+ */
+#define    MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LEN 53
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAGS_OFST 0
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAGS_LEN 4
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_PUSH_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_PUSH_LBN 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_PUSH_WIDTH 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_POP_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_POP_LBN 4
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_POP_WIDTH 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DECAP_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DECAP_LBN 8
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DECAP_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_LBN 9
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAG_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAG_LBN 10
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAG_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_NAT_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_NAT_LBN 11
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_NAT_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DECR_IP_TTL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DECR_IP_TTL_LBN 12
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DECR_IP_TTL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_SRC_MPORT_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_SRC_MPORT_LBN 13
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_SRC_MPORT_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SUPPRESS_SELF_DELIVERY_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SUPPRESS_SELF_DELIVERY_LBN 14
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SUPPRESS_SELF_DELIVERY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_C_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_C_PL_LBN 15
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_C_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_D_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_D_PL_LBN 16
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_D_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_LBN 17
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_NET_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_NET_CHAN_LBN 18
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_NET_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_PLUGIN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_PLUGIN_LBN 19
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_PLUGIN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_INC_L4_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_INC_L4_LBN 20
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_INC_L4_WIDTH 1
+/* If VLAN_PUSH >= 1, TCI value to be inserted as outermost VLAN. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN0_TCI_BE_OFST 4
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN0_TCI_BE_LEN 2
+/* If VLAN_PUSH >= 1, TPID value to be inserted as outermost VLAN. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN0_PROTO_BE_OFST 6
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN0_PROTO_BE_LEN 2
+/* If VLAN_PUSH == 2, inner TCI value to be inserted. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN1_TCI_BE_OFST 8
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN1_TCI_BE_LEN 2
+/* If VLAN_PUSH == 2, inner TPID value to be inserted. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN1_PROTO_BE_OFST 10
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN1_PROTO_BE_LEN 2
+/* Reserved. Ignored by firmware. Should be set to zero or 0xffffffff. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RSVD_OFST 12
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RSVD_LEN 4
+/* Set to ENCAP_HEADER_ID_NULL to request no encap action */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ENCAP_HEADER_ID_OFST 16
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ENCAP_HEADER_ID_LEN 4
+/* An m-port selector identifying the m-port that the modified packet should be
+ * delivered to. Set to MPORT_SELECTOR_NULL to request no delivery of the
+ * packet.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DELIVER_OFST 20
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DELIVER_LEN 4
+/* Allows an action set to trigger several counter updates. Set to
+ * MAE_COUNTER_ID_NULL to request no counter action.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_COUNTER_LIST_ID_OFST 24
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_COUNTER_LIST_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
+/* If a driver only wished to update one counter within this action set, then
+ * it can supply a COUNTER_ID instead of allocating a single-element counter
+ * list. The ID must have been allocated with COUNTER_TYPE=AR. This field
+ * should be set to MAE_COUNTER_ID_NULL if this behaviour is not required. It
+ * is not valid to supply a non-NULL value for both COUNTER_LIST_ID and
+ * COUNTER_ID.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_COUNTER_ID_OFST 28
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_COUNTER_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_VALUE_OFST 32
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_VALUE_LEN 4
+/* Set to MAC_ID_NULL to request no source MAC replacement. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SRC_MAC_ID_OFST 36
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SRC_MAC_ID_LEN 4
+/* Set to MAC_ID_NULL to request no destination MAC replacement. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DST_MAC_ID_OFST 40
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DST_MAC_ID_LEN 4
+/* Source m-port ID to be reported for DO_SET_SRC_MPORT action. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_REPORTED_SRC_MPORT_OFST 44
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_REPORTED_SRC_MPORT_LEN 4
+/* Actions for modifying the Differentiated Services Code-Point (DSCP) bits
+ * within IPv4 and IPv6 headers.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_CONTROL_OFST 48
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_CONTROL_LEN 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_ENCAP_COPY_OFST 48
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_ENCAP_COPY_LBN 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_ENCAP_COPY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_DECAP_COPY_OFST 48
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_DECAP_COPY_LBN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_DECAP_COPY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_DSCP_OFST 48
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_DSCP_LBN 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_DSCP_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_VALUE_OFST 48
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_VALUE_LBN 3
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_VALUE_WIDTH 6
+/* Actions for modifying the Explicit Congestion Notification (ECN) bits within
+ * IPv4 and IPv6 headers.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_CONTROL_OFST 50
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_CONTROL_LEN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_ENCAP_COPY_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_ENCAP_COPY_LBN 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_ENCAP_COPY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_DECAP_COPY_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_DECAP_COPY_LBN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_DECAP_COPY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_ECN_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_ECN_LBN 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_ECN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_VALUE_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_VALUE_LBN 3
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_VALUE_WIDTH 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_0_TO_CE_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_0_TO_CE_LBN 5
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_0_TO_CE_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_1_TO_CE_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_1_TO_CE_LBN 6
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_1_TO_CE_WIDTH 1
+/* Actions for overwriting CH_ROUTE subfields. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OVERWRITE_OFST 51
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OVERWRITE_LEN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_C_PL_OFST 51
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_C_PL_LBN 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_C_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_D_PL_OFST 51
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_D_PL_LBN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_D_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_PL_CHAN_OFST 51
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_PL_CHAN_LBN 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_PL_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OUT_HOST_CHAN_OFST 51
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OUT_HOST_CHAN_LBN 3
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OUT_HOST_CHAN_WIDTH 1
+/* Override outgoing CH_VC to network port for DO_SET_NET_CHAN action. Cannot
+ * be used in conjunction with DO_SET_SRC_MPORT action.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_NET_CHAN_OFST 52
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_NET_CHAN_LEN 1
+
 /* MC_CMD_MAE_ACTION_SET_ALLOC_OUT msgresponse */
 #define    MC_CMD_MAE_ACTION_SET_ALLOC_OUT_LEN 4
 /* The MSB of the AS_ID is guaranteed to be clear if the ID is not
@@ -28680,58 +25030,6 @@
 #define       MC_CMD_MAE_OUTER_RULE_REMOVE_OUT_REMOVED_OR_ID_MAXNUM 32
 #define       MC_CMD_MAE_OUTER_RULE_REMOVE_OUT_REMOVED_OR_ID_MAXNUM_MCDI2 32
 
-
-/***********************************/
-/* MC_CMD_MAE_OUTER_RULE_UPDATE
- * Atomically change the response of an Outer Rule.
- */
-#define MC_CMD_MAE_OUTER_RULE_UPDATE 0x17d
-#undef MC_CMD_0x17d_PRIVILEGE_CTG
-
-#define MC_CMD_0x17d_PRIVILEGE_CTG SRIOV_CTG_MAE
-
-/* MC_CMD_MAE_OUTER_RULE_UPDATE_IN msgrequest */
-#define    MC_CMD_MAE_OUTER_RULE_UPDATE_IN_LEN 16
-/* ID of outer rule to update */
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_OR_ID_OFST 0
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_OR_ID_LEN 4
-/* Packets matching the rule will be parsed with this encapsulation. */
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_ENCAP_TYPE_OFST 4
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_ENCAP_TYPE_LEN 4
-/*            Enum values, see field(s): */
-/*               MAE_MCDI_ENCAP_TYPE */
-/* This field controls the actions that are performed when a rule is hit. */
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_ACTION_CONTROL_OFST 8
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_ACTION_CONTROL_LEN 4
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_CT_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_CT_LBN 0
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_CT_WIDTH 1
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_VNI_MODE_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_VNI_MODE_LBN 1
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_VNI_MODE_WIDTH 2
-/*             Enum values, see field(s): */
-/*                MAE_CT_VNI_MODE */
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_COUNT_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_COUNT_LBN 3
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_COUNT_WIDTH 1
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_TCP_FLAGS_INHIBIT_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_TCP_FLAGS_INHIBIT_LBN 4
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_TCP_FLAGS_INHIBIT_WIDTH 1
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_RECIRC_ID_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_RECIRC_ID_LBN 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_RECIRC_ID_WIDTH 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_DOMAIN_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_DOMAIN_LBN 16
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_DOMAIN_WIDTH 16
-/* ID of counter to increment when the rule is hit. Only used if the DO_COUNT
- * flag is set. The ID must have been allocated with COUNTER_TYPE=OR.
- */
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_COUNTER_ID_OFST 12
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_COUNTER_ID_LEN 4
-
-/* MC_CMD_MAE_OUTER_RULE_UPDATE_OUT msgresponse */
-#define    MC_CMD_MAE_OUTER_RULE_UPDATE_OUT_LEN 0
-
 /* MAE_ACTION_RULE_RESPONSE structuredef */
 #define    MAE_ACTION_RULE_RESPONSE_LEN 16
 #define       MAE_ACTION_RULE_RESPONSE_ASL_ID_OFST 0
@@ -29122,142 +25420,6 @@
 #define       MAE_MPORT_DESC_VNIC_PLUGIN_TBD_LBN 352
 #define       MAE_MPORT_DESC_VNIC_PLUGIN_TBD_WIDTH 32
 
-/* MAE_MPORT_DESC_V2 structuredef */
-#define    MAE_MPORT_DESC_V2_LEN 56
-#define       MAE_MPORT_DESC_V2_MPORT_ID_OFST 0
-#define       MAE_MPORT_DESC_V2_MPORT_ID_LEN 4
-#define       MAE_MPORT_DESC_V2_MPORT_ID_LBN 0
-#define       MAE_MPORT_DESC_V2_MPORT_ID_WIDTH 32
-/* Reserved for future purposes, contains information independent of caller */
-#define       MAE_MPORT_DESC_V2_FLAGS_OFST 4
-#define       MAE_MPORT_DESC_V2_FLAGS_LEN 4
-#define       MAE_MPORT_DESC_V2_FLAGS_LBN 32
-#define       MAE_MPORT_DESC_V2_FLAGS_WIDTH 32
-#define       MAE_MPORT_DESC_V2_CALLER_FLAGS_OFST 8
-#define       MAE_MPORT_DESC_V2_CALLER_FLAGS_LEN 4
-#define        MAE_MPORT_DESC_V2_CAN_RECEIVE_ON_OFST 8
-#define        MAE_MPORT_DESC_V2_CAN_RECEIVE_ON_LBN 0
-#define        MAE_MPORT_DESC_V2_CAN_RECEIVE_ON_WIDTH 1
-#define        MAE_MPORT_DESC_V2_CAN_DELIVER_TO_OFST 8
-#define        MAE_MPORT_DESC_V2_CAN_DELIVER_TO_LBN 1
-#define        MAE_MPORT_DESC_V2_CAN_DELIVER_TO_WIDTH 1
-#define        MAE_MPORT_DESC_V2_CAN_DELETE_OFST 8
-#define        MAE_MPORT_DESC_V2_CAN_DELETE_LBN 2
-#define        MAE_MPORT_DESC_V2_CAN_DELETE_WIDTH 1
-#define        MAE_MPORT_DESC_V2_IS_ZOMBIE_OFST 8
-#define        MAE_MPORT_DESC_V2_IS_ZOMBIE_LBN 3
-#define        MAE_MPORT_DESC_V2_IS_ZOMBIE_WIDTH 1
-#define       MAE_MPORT_DESC_V2_CALLER_FLAGS_LBN 64
-#define       MAE_MPORT_DESC_V2_CALLER_FLAGS_WIDTH 32
-/* Not the ideal name; it's really the type of thing connected to the m-port */
-#define       MAE_MPORT_DESC_V2_MPORT_TYPE_OFST 12
-#define       MAE_MPORT_DESC_V2_MPORT_TYPE_LEN 4
-/* enum: Connected to a MAC... */
-#define          MAE_MPORT_DESC_V2_MPORT_TYPE_NET_PORT 0x0
-/* enum: Adds metadata and delivers to another m-port */
-#define          MAE_MPORT_DESC_V2_MPORT_TYPE_ALIAS 0x1
-/* enum: Connected to a VNIC. */
-#define          MAE_MPORT_DESC_V2_MPORT_TYPE_VNIC 0x2
-#define       MAE_MPORT_DESC_V2_MPORT_TYPE_LBN 96
-#define       MAE_MPORT_DESC_V2_MPORT_TYPE_WIDTH 32
-/* 128-bit value available to drivers for m-port identification. */
-#define       MAE_MPORT_DESC_V2_UUID_OFST 16
-#define       MAE_MPORT_DESC_V2_UUID_LEN 16
-#define       MAE_MPORT_DESC_V2_UUID_LBN 128
-#define       MAE_MPORT_DESC_V2_UUID_WIDTH 128
-/* Big wadge of space reserved for other common properties */
-#define       MAE_MPORT_DESC_V2_RESERVED_OFST 32
-#define       MAE_MPORT_DESC_V2_RESERVED_LEN 8
-#define       MAE_MPORT_DESC_V2_RESERVED_LO_OFST 32
-#define       MAE_MPORT_DESC_V2_RESERVED_LO_LEN 4
-#define       MAE_MPORT_DESC_V2_RESERVED_LO_LBN 256
-#define       MAE_MPORT_DESC_V2_RESERVED_LO_WIDTH 32
-#define       MAE_MPORT_DESC_V2_RESERVED_HI_OFST 36
-#define       MAE_MPORT_DESC_V2_RESERVED_HI_LEN 4
-#define       MAE_MPORT_DESC_V2_RESERVED_HI_LBN 288
-#define       MAE_MPORT_DESC_V2_RESERVED_HI_WIDTH 32
-#define       MAE_MPORT_DESC_V2_RESERVED_LBN 256
-#define       MAE_MPORT_DESC_V2_RESERVED_WIDTH 64
-/* Logical port index. Only valid when type NET Port. */
-#define       MAE_MPORT_DESC_V2_NET_PORT_IDX_OFST 40
-#define       MAE_MPORT_DESC_V2_NET_PORT_IDX_LEN 4
-#define       MAE_MPORT_DESC_V2_NET_PORT_IDX_LBN 320
-#define       MAE_MPORT_DESC_V2_NET_PORT_IDX_WIDTH 32
-/* The m-port delivered to */
-#define       MAE_MPORT_DESC_V2_ALIAS_DELIVER_MPORT_ID_OFST 40
-#define       MAE_MPORT_DESC_V2_ALIAS_DELIVER_MPORT_ID_LEN 4
-#define       MAE_MPORT_DESC_V2_ALIAS_DELIVER_MPORT_ID_LBN 320
-#define       MAE_MPORT_DESC_V2_ALIAS_DELIVER_MPORT_ID_WIDTH 32
-/* The type of thing that owns the VNIC */
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_OFST 40
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_LEN 4
-#define          MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_FUNCTION 0x1 /* enum */
-#define          MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_PLUGIN 0x2 /* enum */
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_LBN 320
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_WIDTH 32
-/* The PCIe interface on which the function lives. CJK: We need an enumeration
- * of interfaces that we extend as new interface (types) appear. This belongs
- * elsewhere and should be referenced from here
- */
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_INTERFACE_OFST 44
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_INTERFACE_LEN 4
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_INTERFACE_LBN 352
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_INTERFACE_WIDTH 32
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_PF_IDX_OFST 48
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_PF_IDX_LEN 2
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_PF_IDX_LBN 384
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_PF_IDX_WIDTH 16
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_VF_IDX_OFST 50
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_VF_IDX_LEN 2
-/* enum: Indicates that the function is a PF */
-#define          MAE_MPORT_DESC_V2_VF_IDX_NULL 0xffff
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_VF_IDX_LBN 400
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_VF_IDX_WIDTH 16
-/* Reserved. Should be ignored for now. */
-#define       MAE_MPORT_DESC_V2_VNIC_PLUGIN_TBD_OFST 44
-#define       MAE_MPORT_DESC_V2_VNIC_PLUGIN_TBD_LEN 4
-#define       MAE_MPORT_DESC_V2_VNIC_PLUGIN_TBD_LBN 352
-#define       MAE_MPORT_DESC_V2_VNIC_PLUGIN_TBD_WIDTH 32
-/* A client handle for the VNIC's owner. Only valid for type VNIC. */
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_HANDLE_OFST 52
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_HANDLE_LEN 4
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_HANDLE_LBN 416
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_HANDLE_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_MAE_MPORT_ENUMERATE
- * Deprecated in favour of MAE_MPORT_READ_JOURNAL. Support for this command
- * will be removed at some future point.
- */
-#define MC_CMD_MAE_MPORT_ENUMERATE 0x17c
-#undef MC_CMD_0x17c_PRIVILEGE_CTG
-
-#define MC_CMD_0x17c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_MAE_MPORT_ENUMERATE_IN msgrequest */
-#define    MC_CMD_MAE_MPORT_ENUMERATE_IN_LEN 0
-
-/* MC_CMD_MAE_MPORT_ENUMERATE_OUT msgresponse */
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_LENMIN 8
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_LENMAX 252
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_LEN(num) (8+1*(num))
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_NUM(len) (((len)-8)/1)
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_COUNT_OFST 0
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_COUNT_LEN 4
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_SIZEOF_MPORT_DESC_OFST 4
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_SIZEOF_MPORT_DESC_LEN 4
-/* Any array of MAE_MPORT_DESC structures. The MAE_MPORT_DESC structure may
- * grow in future version of this command. Drivers should use a stride of
- * SIZEOF_MPORT_DESC. Fields beyond SIZEOF_MPORT_DESC are not present.
- */
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_OFST 8
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_LEN 1
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_MINNUM 0
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_MAXNUM 244
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_MAXNUM_MCDI2 1012
-
 
 /***********************************/
 /* MC_CMD_MAE_MPORT_READ_JOURNAL
@@ -29570,73 +25732,6 @@
 
 
 /***********************************/
-/* MC_CMD_TABLE_UPDATE
- * Update an existing entry in a table with a new response value. May return
- * EINVAL for unknown table ID or other bad request parameters, ENOENT if the
- * entry does not already exist, or EPERM if the operation is not permitted. In
- * case of an error, the additional MCDI error argument field returns the raw
- * error code from the underlying CAM driver.
- */
-#define MC_CMD_TABLE_UPDATE 0x1ce
-#undef MC_CMD_0x1ce_PRIVILEGE_CTG
-
-#define MC_CMD_0x1ce_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TABLE_UPDATE_IN msgrequest */
-#define    MC_CMD_TABLE_UPDATE_IN_LENMIN 16
-#define    MC_CMD_TABLE_UPDATE_IN_LENMAX 252
-#define    MC_CMD_TABLE_UPDATE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_TABLE_UPDATE_IN_LEN(num) (12+4*(num))
-#define    MC_CMD_TABLE_UPDATE_IN_DATA_NUM(len) (((len)-12)/4)
-/* Table identifier. */
-#define       MC_CMD_TABLE_UPDATE_IN_TABLE_ID_OFST 0
-#define       MC_CMD_TABLE_UPDATE_IN_TABLE_ID_LEN 4
-/*            Enum values, see field(s): */
-/*               TABLE_ID */
-/* Width in bits of supplied key data (must match table properties). */
-#define       MC_CMD_TABLE_UPDATE_IN_KEY_WIDTH_OFST 4
-#define       MC_CMD_TABLE_UPDATE_IN_KEY_WIDTH_LEN 2
-/* Width in bits of supplied mask data (0 for direct/BCAM tables, or for STCAM
- * when allocated MASK_ID is used instead).
- */
-#define       MC_CMD_TABLE_UPDATE_IN_MASK_WIDTH_OFST 6
-#define       MC_CMD_TABLE_UPDATE_IN_MASK_WIDTH_LEN 2
-/* Width in bits of supplied response data (for INSERT and UPDATE operations
- * this must match the table properties; for DELETE operations, no response
- * data is required and this must be 0).
- */
-#define       MC_CMD_TABLE_UPDATE_IN_RESP_WIDTH_OFST 8
-#define       MC_CMD_TABLE_UPDATE_IN_RESP_WIDTH_LEN 2
-/* Mask ID for STCAM table - used instead of mask data if the table descriptor
- * reports ALLOC_MASKS==1. Otherwise set to 0.
- */
-#define       MC_CMD_TABLE_UPDATE_IN_MASK_ID_OFST 6
-#define       MC_CMD_TABLE_UPDATE_IN_MASK_ID_LEN 2
-/* Priority for TCAM or STCAM, in range 0..N_PRIORITIES-1, otherwise 0. */
-#define       MC_CMD_TABLE_UPDATE_IN_PRIORITY_OFST 8
-#define       MC_CMD_TABLE_UPDATE_IN_PRIORITY_LEN 2
-/* (32-bit alignment padding - set to 0) */
-#define       MC_CMD_TABLE_UPDATE_IN_RESERVED_OFST 10
-#define       MC_CMD_TABLE_UPDATE_IN_RESERVED_LEN 2
-/* Sequence of key, mask (if MASK_WIDTH > 0), and response (if RESP_WIDTH > 0)
- * data values. Each of these items is logically treated as a single wide N-bit
- * value, in which the individual fields have been placed within that value per
- * the LBN and WIDTH information from the table field descriptors. The wide
- * N-bit value is padded with 0 bits at the MSB end if necessary to make a
- * multiple of 32 bits. The value is then packed into this command as a
- * sequence of 32-bit words, bits [31:0] first, then bits [63:32], etc.
- */
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_OFST 12
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_LEN 4
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_MINNUM 1
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_MAXNUM 60
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_MAXNUM_MCDI2 252
-
-/* MC_CMD_TABLE_UPDATE_OUT msgresponse */
-#define    MC_CMD_TABLE_UPDATE_OUT_LEN 0
-
-
-/***********************************/
 /* MC_CMD_TABLE_DELETE
  * Delete an existing entry in a table. May return EINVAL for unknown table ID
  * or other bad request parameters, ENOENT if the entry does not exist, or
@@ -29702,5 +25797,124 @@
 /* MC_CMD_TABLE_DELETE_OUT msgresponse */
 #define    MC_CMD_TABLE_DELETE_OUT_LEN 0
 
+/* MC_CMD_QUEUE_HANDLE structuredef: On X4, to distinguish between full-
+ * featured (X2-style) VIs and low-latency (X3-style) queues, we use the top
+ * bits of the queue handle to specify the queue type in all MCDI calls which
+ * refer to VIs/queues. These bits should be masked off when indexing into a
+ * queue in the BAR.
+ */
+#define    MC_CMD_QUEUE_HANDLE_LEN 4
+/* Combined queue number and type. This is the ID returned by and passed into
+ * MCDI calls that use queues.
+ */
+#define       MC_CMD_QUEUE_HANDLE_QUEUE_HANDLE_OFST 0
+#define       MC_CMD_QUEUE_HANDLE_QUEUE_HANDLE_LEN 4
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_NUM_OFST 0
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_NUM_LBN 0
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_NUM_WIDTH 24
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_OFST 0
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_LBN 24
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_WIDTH 8
+/* enum: Indicates that the queue instance is a full-featured VI */
+#define          MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_FF_VI 0x0
+/* enum: Indicates that the queue instance is a LL TXQ */
+#define          MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_LL_TXQ 0x1
+/* enum: Indicates that the queue instance is a LL RXQ */
+#define          MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_LL_RXQ 0x2
+/* enum: Indicates that the queue instance is a LL EVQ */
+#define          MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_LL_EVQ 0x3
+#define       MC_CMD_QUEUE_HANDLE_QUEUE_HANDLE_LBN 0
+#define       MC_CMD_QUEUE_HANDLE_QUEUE_HANDLE_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_ALLOC_LL_QUEUES
+ * Allocate low latency (X3-style) queues for current PCI function. Can be
+ * called more than once if desired to allocate more queues.
+ */
+#define MC_CMD_ALLOC_LL_QUEUES 0x1dd
+#undef MC_CMD_0x1dd_PRIVILEGE_CTG
+
+#define MC_CMD_0x1dd_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_ALLOC_LL_QUEUES_IN msgrequest */
+#define    MC_CMD_ALLOC_LL_QUEUES_IN_LEN 24
+/* The minimum number of TXQs that is acceptable */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_TXQ_COUNT_OFST 0
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_TXQ_COUNT_LEN 4
+/* The maximum number of TXQs that would be useful */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_TXQ_COUNT_OFST 4
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_TXQ_COUNT_LEN 4
+/* The minimum number of RXQs that is acceptable */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_RXQ_COUNT_OFST 8
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_RXQ_COUNT_LEN 4
+/* The maximum number of RXQs that would be useful */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_RXQ_COUNT_OFST 12
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_RXQ_COUNT_LEN 4
+/* The minimum number of EVQs that is acceptable */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_EVQ_COUNT_OFST 16
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_EVQ_COUNT_LEN 4
+/* The maximum number of EVQs that would be useful */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_EVQ_COUNT_OFST 20
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_EVQ_COUNT_LEN 4
+
+/* MC_CMD_ALLOC_LL_QUEUES_OUT msgresponse */
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_LENMIN 16
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_LENMAX 252
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_LEN(num) (12+4*(num))
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_NUM(len) (((len)-12)/4)
+/* The number of TXQs allocated in this request */
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_TXQ_COUNT_OFST 0
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_TXQ_COUNT_LEN 4
+/* The number of RXQs allocated in this request */
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_RXQ_COUNT_OFST 4
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_RXQ_COUNT_LEN 4
+/* The number of EVQs allocated in this request */
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_EVQ_COUNT_OFST 8
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_EVQ_COUNT_LEN 4
+/* A list of allocated queues, returned as MC_CMD_QUEUE_HANDLEs, not
+ * necessarily contiguous. TXQs are first in the list, followed by RXQs then
+ * EVQs. The type of each queue is indicated by the top bits (see the
+ * QUEUE_TYPE enum)
+ */
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_OFST 12
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_LEN 4
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_MINNUM 1
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_MAXNUM 60
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_MAXNUM_MCDI2 252
+
+
+/***********************************/
+/* MC_CMD_FREE_LL_QUEUES
+ * Free low latency (X3-style) queues for current PCI function.
+ */
+#define MC_CMD_FREE_LL_QUEUES 0x1de
+#undef MC_CMD_0x1de_PRIVILEGE_CTG
+
+#define MC_CMD_0x1de_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_FREE_LL_QUEUES_IN msgrequest */
+#define    MC_CMD_FREE_LL_QUEUES_IN_LENMIN 8
+#define    MC_CMD_FREE_LL_QUEUES_IN_LENMAX 252
+#define    MC_CMD_FREE_LL_QUEUES_IN_LENMAX_MCDI2 1020
+#define    MC_CMD_FREE_LL_QUEUES_IN_LEN(num) (4+4*(num))
+#define    MC_CMD_FREE_LL_QUEUES_IN_QUEUES_NUM(len) (((len)-4)/4)
+/* The number of queues to free. */
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUE_COUNT_OFST 0
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUE_COUNT_LEN 4
+/* A list of queues to free, as a list of MC_CMD_QUEUE_HANDLEs. They must have
+ * all been previously allocated by MC_CMD_ALLOC_LL_QUEUES. The type of each
+ * queue should be indicated by the top bits.
+ */
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_OFST 4
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_LEN 4
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_MINNUM 1
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_MAXNUM 62
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_MAXNUM_MCDI2 254
+
+/* MC_CMD_FREE_LL_QUEUES_OUT msgresponse */
+#define    MC_CMD_FREE_LL_QUEUES_OUT_LEN 0
+
 
 #endif /* MCDI_PCOL_H */
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index ad4694fa3dda..7b236d291d8c 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -17,58 +17,6 @@
 #include "selftest.h"
 #include "mcdi_port_common.h"
 
-static int efx_mcdi_mdio_read(struct net_device *net_dev,
-			      int prtad, int devad, u16 addr)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_MDIO_READ_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_MDIO_READ_OUT_LEN);
-	size_t outlen;
-	int rc;
-
-	MCDI_SET_DWORD(inbuf, MDIO_READ_IN_BUS, efx->mdio_bus);
-	MCDI_SET_DWORD(inbuf, MDIO_READ_IN_PRTAD, prtad);
-	MCDI_SET_DWORD(inbuf, MDIO_READ_IN_DEVAD, devad);
-	MCDI_SET_DWORD(inbuf, MDIO_READ_IN_ADDR, addr);
-
-	rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_READ, inbuf, sizeof(inbuf),
-			  outbuf, sizeof(outbuf), &outlen);
-	if (rc)
-		return rc;
-
-	if (MCDI_DWORD(outbuf, MDIO_READ_OUT_STATUS) !=
-	    MC_CMD_MDIO_STATUS_GOOD)
-		return -EIO;
-
-	return (u16)MCDI_DWORD(outbuf, MDIO_READ_OUT_VALUE);
-}
-
-static int efx_mcdi_mdio_write(struct net_device *net_dev,
-			       int prtad, int devad, u16 addr, u16 value)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_MDIO_WRITE_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_MDIO_WRITE_OUT_LEN);
-	size_t outlen;
-	int rc;
-
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_BUS, efx->mdio_bus);
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_PRTAD, prtad);
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_DEVAD, devad);
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_ADDR, addr);
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_VALUE, value);
-
-	rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_WRITE, inbuf, sizeof(inbuf),
-			  outbuf, sizeof(outbuf), &outlen);
-	if (rc)
-		return rc;
-
-	if (MCDI_DWORD(outbuf, MDIO_WRITE_OUT_STATUS) !=
-	    MC_CMD_MDIO_STATUS_GOOD)
-		return -EIO;
-
-	return 0;
-}
 
 u32 efx_mcdi_phy_get_caps(struct efx_nic *efx)
 {
@@ -97,12 +45,7 @@ int efx_mcdi_port_probe(struct efx_nic *efx)
 {
 	int rc;
 
-	/* Set up MDIO structure for PHY */
-	efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22;
-	efx->mdio.mdio_read = efx_mcdi_mdio_read;
-	efx->mdio.mdio_write = efx_mcdi_mdio_write;
-
-	/* Fill out MDIO structure, loopback modes, and initial link state */
+	/* Fill out loopback modes and initial link state */
 	rc = efx_mcdi_phy_probe(efx);
 	if (rc != 0)
 		return rc;
diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c
index 76ea26722ca4..dae684194ac8 100644
--- a/drivers/net/ethernet/sfc/mcdi_port_common.c
+++ b/drivers/net/ethernet/sfc/mcdi_port_common.c
@@ -448,15 +448,6 @@ int efx_mcdi_phy_probe(struct efx_nic *efx)
 	efx->phy_data = phy_data;
 	efx->phy_type = phy_data->type;
 
-	efx->mdio_bus = phy_data->channel;
-	efx->mdio.prtad = phy_data->port;
-	efx->mdio.mmds = phy_data->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22);
-	efx->mdio.mode_support = 0;
-	if (phy_data->mmd_mask & (1 << MC_CMD_MMD_CLAUSE22))
-		efx->mdio.mode_support |= MDIO_SUPPORTS_C22;
-	if (phy_data->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22))
-		efx->mdio.mode_support |= MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22;
-
 	caps = MCDI_DWORD(outbuf, GET_LINK_OUT_CAP);
 	if (caps & (1 << MC_CMD_PHY_CAP_AN_LBN))
 		mcdi_to_ethtool_linkset(phy_data->media, caps,
@@ -546,8 +537,6 @@ void efx_mcdi_phy_get_link_ksettings(struct efx_nic *efx, struct ethtool_link_ks
 	cmd->base.port = mcdi_to_ethtool_media(phy_cfg->media);
 	cmd->base.phy_address = phy_cfg->port;
 	cmd->base.autoneg = !!(efx->link_advertising[0] & ADVERTISED_Autoneg);
-	cmd->base.mdio_support = (efx->mdio.mode_support &
-			      (MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22));
 
 	mcdi_to_ethtool_linkset(phy_cfg->media, phy_cfg->supported_cap,
 				cmd->link_modes.supported);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 620ba6ef3514..5c0f306fb019 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -15,7 +15,7 @@
 #include <linux/ethtool.h>
 #include <linux/if_vlan.h>
 #include <linux/timer.h>
-#include <linux/mdio.h>
+#include <linux/mii.h>
 #include <linux/list.h>
 #include <linux/pci.h>
 #include <linux/device.h>
@@ -831,6 +831,7 @@ struct efx_arfs_rule {
 /**
  * struct efx_async_filter_insertion - Request to asynchronously insert a filter
  * @net_dev: Reference to the netdevice
+ * @net_dev_tracker: reference tracker entry for @net_dev
  * @spec: The filter to insert
  * @work: Workitem for this request
  * @rxq_index: Identifies the channel for which this request was made
@@ -838,6 +839,7 @@ struct efx_arfs_rule {
  */
 struct efx_async_filter_insertion {
 	struct net_device *net_dev;
+	netdevice_tracker net_dev_tracker;
 	struct efx_filter_spec spec;
 	struct work_struct work;
 	u16 rxq_index;
@@ -954,8 +956,6 @@ struct efx_mae;
  * @stats_buffer: DMA buffer for statistics
  * @phy_type: PHY type
  * @phy_data: PHY private data (including PHY-specific stats)
- * @mdio: PHY MDIO interface
- * @mdio_bus: PHY MDIO bus ID (only used by Siena)
  * @phy_mode: PHY operating mode. Serialised by @mac_lock.
  * @link_advertising: Autonegotiation advertising flags
  * @fec_config: Forward Error Correction configuration flags.  For bit positions
@@ -1004,6 +1004,7 @@ struct efx_mae;
  * @dl_port: devlink port associated with the PF
  * @mem_bar: The BAR that is mapped into membase.
  * @reg_base: Offset from the start of the bar to the function control window.
+ * @reflash_mutex: Mutex for serialising firmware reflash operations.
  * @monitor_work: Hardware monitor workitem
  * @biu_lock: BIU (bus interface unit) lock
  * @last_irq_cpu: Last CPU to handle a possible test interrupt.  This
@@ -1129,8 +1130,6 @@ struct efx_nic {
 
 	unsigned int phy_type;
 	void *phy_data;
-	struct mdio_if_info mdio;
-	unsigned int mdio_bus;
 	enum efx_phy_mode phy_mode;
 
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(link_advertising);
@@ -1189,6 +1188,7 @@ struct efx_nic {
 	struct devlink_port *dl_port;
 	unsigned int mem_bar;
 	u32 reg_base;
+	struct mutex reflash_mutex;
 
 	/* The following fields may be written more often */
 
@@ -1381,6 +1381,8 @@ struct efx_udp_tunnel {
  * @can_rx_scatter: NIC is able to scatter packets to multiple buffers
  * @always_rx_scatter: NIC will always scatter packets to multiple buffers
  * @option_descriptors: NIC supports TX option descriptors
+ * @flash_auto_partition: firmware flash uses AUTO partition, driver does
+ *	not need to perform image parsing
  * @min_interrupt_mode: Lowest capability interrupt mode supported
  *	from &enum efx_int_mode.
  * @timer_period_max: Maximum period of interrupt timer (in ticks)
@@ -1557,6 +1559,7 @@ struct efx_nic_type {
 	bool can_rx_scatter;
 	bool always_rx_scatter;
 	bool option_descriptors;
+	bool flash_auto_partition;
 	unsigned int min_interrupt_mode;
 	unsigned int timer_period_max;
 	netdev_features_t offload_features;
diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
index ab358fe13e1d..f4f75299dfa9 100644
--- a/drivers/net/ethernet/sfc/rx_common.c
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -285,7 +285,7 @@ void efx_fini_rx_queue(struct efx_rx_queue *rx_queue)
 	netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
 		  "shutting down RX queue %d\n", efx_rx_queue_index(rx_queue));
 
-	del_timer_sync(&rx_queue->slow_fill);
+	timer_delete_sync(&rx_queue->slow_fill);
 	if (rx_queue->grant_credits)
 		flush_work(&rx_queue->grant_work);
 
@@ -352,7 +352,8 @@ void efx_free_rx_buffers(struct efx_rx_queue *rx_queue,
 
 void efx_rx_slow_fill(struct timer_list *t)
 {
-	struct efx_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
+	struct efx_rx_queue *rx_queue = timer_container_of(rx_queue, t,
+							   slow_fill);
 
 	/* Post an event to cause NAPI to run and refill the queue */
 	efx_nic_generate_fill_event(rx_queue);
@@ -897,7 +898,7 @@ static void efx_filter_rfs_work(struct work_struct *data)
 
 	/* Release references */
 	clear_bit(slot_idx, &efx->rps_slot_map);
-	dev_put(req->net_dev);
+	netdev_put(req->net_dev, &req->net_dev_tracker);
 }
 
 int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
@@ -989,7 +990,8 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 	}
 
 	/* Queue the request */
-	dev_hold(req->net_dev = net_dev);
+	req->net_dev = net_dev;
+	netdev_hold(req->net_dev, &req->net_dev_tracker, GFP_ATOMIC);
 	INIT_WORK(&req->work, efx_filter_rfs_work);
 	req->rxq_index = rxq_index;
 	req->flow_id = flow_id;
diff --git a/drivers/net/ethernet/sfc/siena/mcdi.c b/drivers/net/ethernet/sfc/siena/mcdi.c
index 3f7899daa86a..c8f0fb43e285 100644
--- a/drivers/net/ethernet/sfc/siena/mcdi.c
+++ b/drivers/net/ethernet/sfc/siena/mcdi.c
@@ -534,7 +534,7 @@ static bool efx_mcdi_complete_async(struct efx_mcdi_iface *mcdi, bool timeout)
 	 * of it aborting the next request.
 	 */
 	if (!timeout)
-		del_timer_sync(&mcdi->async_timer);
+		timer_delete_sync(&mcdi->async_timer);
 
 	spin_lock(&mcdi->async_lock);
 	async = list_first_entry(&mcdi->async_list,
@@ -609,7 +609,7 @@ static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno,
 
 static void efx_mcdi_timeout_async(struct timer_list *t)
 {
-	struct efx_mcdi_iface *mcdi = from_timer(mcdi, t, async_timer);
+	struct efx_mcdi_iface *mcdi = timer_container_of(mcdi, t, async_timer);
 
 	efx_mcdi_complete_async(mcdi, true);
 }
@@ -1145,7 +1145,7 @@ void efx_siena_mcdi_flush_async(struct efx_nic *efx)
 	/* We must be in poll or fail mode so no more requests can be queued */
 	BUG_ON(mcdi->mode == MCDI_MODE_EVENTS);
 
-	del_timer_sync(&mcdi->async_timer);
+	timer_delete_sync(&mcdi->async_timer);
 
 	/* If a request is still running, make sure we give the MC
 	 * time to complete it so that the response won't overwrite our
diff --git a/drivers/net/ethernet/sfc/siena/net_driver.h b/drivers/net/ethernet/sfc/siena/net_driver.h
index 9785eff10607..2be3bad3c993 100644
--- a/drivers/net/ethernet/sfc/siena/net_driver.h
+++ b/drivers/net/ethernet/sfc/siena/net_driver.h
@@ -753,6 +753,7 @@ struct efx_arfs_rule {
 /**
  * struct efx_async_filter_insertion - Request to asynchronously insert a filter
  * @net_dev: Reference to the netdevice
+ * @net_dev_tracker: reference tracker entry for @net_dev
  * @spec: The filter to insert
  * @work: Workitem for this request
  * @rxq_index: Identifies the channel for which this request was made
@@ -760,6 +761,7 @@ struct efx_arfs_rule {
  */
 struct efx_async_filter_insertion {
 	struct net_device *net_dev;
+	netdevice_tracker net_dev_tracker;
 	struct efx_filter_spec spec;
 	struct work_struct work;
 	u16 rxq_index;
diff --git a/drivers/net/ethernet/sfc/siena/rx_common.c b/drivers/net/ethernet/sfc/siena/rx_common.c
index 082e35c6caaa..98d27174015d 100644
--- a/drivers/net/ethernet/sfc/siena/rx_common.c
+++ b/drivers/net/ethernet/sfc/siena/rx_common.c
@@ -284,7 +284,7 @@ void efx_siena_fini_rx_queue(struct efx_rx_queue *rx_queue)
 	netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
 		  "shutting down RX queue %d\n", efx_rx_queue_index(rx_queue));
 
-	del_timer_sync(&rx_queue->slow_fill);
+	timer_delete_sync(&rx_queue->slow_fill);
 
 	/* Release RX buffers from the current read ptr to the write ptr */
 	if (rx_queue->buffer) {
@@ -349,7 +349,8 @@ void efx_siena_free_rx_buffers(struct efx_rx_queue *rx_queue,
 
 void efx_siena_rx_slow_fill(struct timer_list *t)
 {
-	struct efx_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
+	struct efx_rx_queue *rx_queue = timer_container_of(rx_queue, t,
+							   slow_fill);
 
 	/* Post an event to cause NAPI to run and refill the queue */
 	efx_nic_generate_fill_event(rx_queue);
@@ -888,7 +889,7 @@ static void efx_filter_rfs_work(struct work_struct *data)
 
 	/* Release references */
 	clear_bit(slot_idx, &efx->rps_slot_map);
-	dev_put(req->net_dev);
+	netdev_put(req->net_dev, &req->net_dev_tracker);
 }
 
 int efx_siena_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
@@ -980,7 +981,8 @@ int efx_siena_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 	}
 
 	/* Queue the request */
-	dev_hold(req->net_dev = net_dev);
+	req->net_dev = net_dev;
+	netdev_hold(req->net_dev, &req->net_dev_tracker, GFP_ATOMIC);
 	INIT_WORK(&req->work, efx_filter_rfs_work);
 	req->rxq_index = rxq_index;
 	req->flow_id = flow_id;
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 0d93164988fc..fa94aa3cd5fe 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -1043,7 +1043,7 @@ static int efx_tc_flower_handle_lhs_actions(struct efx_nic *efx,
 				return -EOPNOTSUPP;
 			}
 			if (fa->ct.action) {
-				NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled ct.action %u for LHS rule\n",
+				NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled ct.action %u for LHS rule",
 						       fa->ct.action);
 				return -EOPNOTSUPP;
 			}
@@ -1056,7 +1056,7 @@ static int efx_tc_flower_handle_lhs_actions(struct efx_nic *efx,
 			act->zone = ct_zone;
 			break;
 		default:
-			NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled action %u for LHS rule\n",
+			NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled action %u for LHS rule",
 					       fa->id);
 			return -EOPNOTSUPP;
 		}
@@ -1581,7 +1581,7 @@ static int efx_tc_flower_replace_foreign_lhs(struct efx_nic *efx,
 
 	type = efx_tc_indr_netdev_type(net_dev);
 	if (type == EFX_ENCAP_TYPE_NONE) {
-		NL_SET_ERR_MSG_MOD(extack, "Egress encap match on unsupported tunnel device\n");
+		NL_SET_ERR_MSG_MOD(extack, "Egress encap match on unsupported tunnel device");
 		return -EOPNOTSUPP;
 	}
 
diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c
index d90206f27161..c0603f54cec3 100644
--- a/drivers/net/ethernet/sfc/tc_conntrack.c
+++ b/drivers/net/ethernet/sfc/tc_conntrack.c
@@ -16,7 +16,7 @@ static int efx_tc_flow_block(enum tc_setup_type type, void *type_data,
 			     void *cb_priv);
 
 static const struct rhashtable_params efx_tc_ct_zone_ht_params = {
-	.key_len	= offsetof(struct efx_tc_ct_zone, linkage),
+	.key_len	= sizeof_field(struct efx_tc_ct_zone, zone),
 	.key_offset	= 0,
 	.head_offset	= offsetof(struct efx_tc_ct_zone, linkage),
 };
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 4535579018c9..39731069d99e 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -570,7 +570,7 @@ static inline void ioc3_setup_duplex(struct ioc3_private *ip)
 
 static void ioc3_timer(struct timer_list *t)
 {
-	struct ioc3_private *ip = from_timer(ip, t, ioc3_timer);
+	struct ioc3_private *ip = timer_container_of(ip, t, ioc3_timer);
 
 	/* Print the link status if it has changed */
 	mii_check_media(&ip->mii, 1, 0);
@@ -718,7 +718,7 @@ static void ioc3_init(struct net_device *dev)
 	struct ioc3_private *ip = netdev_priv(dev);
 	struct ioc3_ethregs *regs = ip->regs;
 
-	del_timer_sync(&ip->ioc3_timer);	/* Kill if running	*/
+	timer_delete_sync(&ip->ioc3_timer);	/* Kill if running	*/
 
 	writel(EMCR_RST, &regs->emcr);		/* Reset		*/
 	readl(&regs->emcr);			/* Flush WB		*/
@@ -801,7 +801,7 @@ static int ioc3_close(struct net_device *dev)
 {
 	struct ioc3_private *ip = netdev_priv(dev);
 
-	del_timer_sync(&ip->ioc3_timer);
+	timer_delete_sync(&ip->ioc3_timer);
 
 	netif_stop_queue(dev);
 
@@ -950,7 +950,7 @@ static int ioc3eth_probe(struct platform_device *pdev)
 	return 0;
 
 out_stop:
-	del_timer_sync(&ip->ioc3_timer);
+	timer_delete_sync(&ip->ioc3_timer);
 	if (ip->rxr)
 		dma_free_coherent(ip->dma_dev, RX_RING_SIZE, ip->rxr,
 				  ip->rxr_dma);
@@ -971,7 +971,7 @@ static void ioc3eth_remove(struct platform_device *pdev)
 	dma_free_coherent(ip->dma_dev, TX_RING_SIZE + SZ_16K - 1, ip->tx_ring, ip->txr_dma);
 
 	unregister_netdev(dev);
-	del_timer_sync(&ip->ioc3_timer);
+	timer_delete_sync(&ip->ioc3_timer);
 	free_netdev(dev);
 }
 
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index dda4e488c77a..15e46e6ac262 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -758,7 +758,7 @@ static irqreturn_t sis190_irq(int irq, void *__dev)
 
 	if (status & LinkChange) {
 		netif_info(tp, intr, dev, "link change\n");
-		del_timer(&tp->timer);
+		timer_delete(&tp->timer);
 		schedule_work(&tp->phy_task);
 	}
 
@@ -1023,7 +1023,7 @@ out_unlock:
 
 static void sis190_phy_timer(struct timer_list *t)
 {
-	struct sis190_private *tp = from_timer(tp, t, timer);
+	struct sis190_private *tp = timer_container_of(tp, t, timer);
 	struct net_device *dev = tp->dev;
 
 	if (likely(netif_running(dev)))
@@ -1034,7 +1034,7 @@ static inline void sis190_delete_timer(struct net_device *dev)
 {
 	struct sis190_private *tp = netdev_priv(dev);
 
-	del_timer_sync(&tp->timer);
+	timer_delete_sync(&tp->timer);
 }
 
 static inline void sis190_request_timer(struct net_device *dev)
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 85b850372efe..b461918dc5f4 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -468,7 +468,7 @@ static int sis900_probe(struct pci_dev *pci_dev,
 	SET_NETDEV_DEV(net_dev, &pci_dev->dev);
 
 	/* We do a request_region() to register /proc/ioports info. */
-	ret = pci_request_regions(pci_dev, "sis900");
+	ret = pcim_request_all_regions(pci_dev, "sis900");
 	if (ret)
 		goto err_out;
 
@@ -1314,7 +1314,8 @@ static void sis630_set_eq(struct net_device *net_dev, u8 revision)
 
 static void sis900_timer(struct timer_list *t)
 {
-	struct sis900_private *sis_priv = from_timer(sis_priv, t, timer);
+	struct sis900_private *sis_priv = timer_container_of(sis_priv, t,
+							     timer);
 	struct net_device *net_dev = sis_priv->mii_info.dev;
 	struct mii_phy *mii_phy = sis_priv->mii;
 	static const int next_tick = 5*HZ;
@@ -1983,7 +1984,7 @@ static int sis900_close(struct net_device *net_dev)
 	/* Stop the chip's Tx and Rx Status Machine */
 	sw32(cr, RxDIS | TxDIS | sr32(cr));
 
-	del_timer(&sis_priv->timer);
+	timer_delete(&sis_priv->timer);
 
 	free_irq(pdev->irq, net_dev);
 
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 013e90d69182..45f703fe0e5a 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -850,7 +850,7 @@ static void check_media(struct net_device *dev)
 
 static void epic_timer(struct timer_list *t)
 {
-	struct epic_private *ep = from_timer(ep, t, timer);
+	struct epic_private *ep = timer_container_of(ep, t, timer);
 	struct net_device *dev = ep->mii.dev;
 	void __iomem *ioaddr = ep->ioaddr;
 	int next_tick = 5*HZ;
@@ -1292,7 +1292,7 @@ static int epic_close(struct net_device *dev)
 		netdev_dbg(dev, "Shutting down ethercard, status was %2.2x.\n",
 			   er32(INTSTAT));
 
-	del_timer_sync(&ep->timer);
+	timer_delete_sync(&ep->timer);
 
 	epic_disable_int(dev, ep);
 
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index 86e3ec25df07..cc0c75694351 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -1105,7 +1105,7 @@ static int smc_close(struct net_device *dev)
     outw(CTL_POWERDOWN, ioaddr + CONTROL );
 
     link->open--;
-    del_timer_sync(&smc->media);
+    timer_delete_sync(&smc->media);
 
     return 0;
 } /* smc_close */
@@ -1713,7 +1713,7 @@ static void smc_reset(struct net_device *dev)
 
 static void media_check(struct timer_list *t)
 {
-    struct smc_private *smc = from_timer(smc, t, media);
+    struct smc_private *smc = timer_container_of(smc, t, media);
     struct net_device *dev = smc->mii_if.dev;
     unsigned int ioaddr = dev->base_addr;
     u_short i, media, saved_bank;
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index f539813878f5..2e1106097965 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -43,7 +43,6 @@
 #include <linux/smsc911x.h>
 #include <linux/device.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_net.h>
 #include <linux/acpi.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index dc99821c6226..ee890de69ffe 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -970,7 +970,7 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 		struct netsec_desc *desc = &dring->desc[idx];
 		struct page *page = virt_to_page(desc->addr);
-		u32 xdp_result = NETSEC_XDP_PASS;
+		u32 metasize, xdp_result = NETSEC_XDP_PASS;
 		struct sk_buff *skb = NULL;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
@@ -1019,7 +1019,7 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		prefetch(desc->addr);
 
 		xdp_prepare_buff(&xdp, desc->addr, NETSEC_RXBUF_HEADROOM,
-				 pkt_len, false);
+				 pkt_len, true);
 
 		if (xdp_prog) {
 			xdp_result = netsec_run_xdp(priv, xdp_prog, &xdp);
@@ -1048,6 +1048,9 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 
 		skb_reserve(skb, xdp.data - xdp.data_hard_start);
 		skb_put(skb, xdp.data_end - xdp.data);
+		metasize = xdp.data - xdp.data_meta;
+		if (metasize)
+			skb_metadata_set(skb, metasize);
 		skb->protocol = eth_type_trans(skb, priv->ndev);
 
 		if (priv->rx_cksum_offload_flag &&
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 6658536a4e17..67fa879b1e52 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -3,6 +3,7 @@ config STMMAC_ETH
 	tristate "STMicroelectronics Multi-Gigabit Ethernet driver"
 	depends on HAS_IOMEM && HAS_DMA
 	depends on PTP_1588_CLOCK_OPTIONAL
+	depends on ETHTOOL_NETLINK
 	select MII
 	select PCS_XPCS
 	select PAGE_POOL
@@ -131,6 +132,17 @@ config DWMAC_QCOM_ETHQOS
 	  This selects the Qualcomm ETHQOS glue layer support for the
 	  stmmac device driver.
 
+config DWMAC_RENESAS_GBETH
+	tristate "Renesas RZ/V2H(P) GBETH support"
+	default ARCH_RENESAS
+	depends on OF && (ARCH_RENESAS || COMPILE_TEST)
+	help
+	  Support for Gigabit Ethernet Interface (GBETH) on Renesas
+	  RZ/V2H(P) SoCs.
+
+	  This selects the Renesas RZ/V2H(P) Soc specific glue layer support
+	  for the stmmac device driver.
+
 config DWMAC_ROCKCHIP
 	tristate "Rockchip dwmac support"
 	default ARCH_ROCKCHIP
@@ -154,6 +166,18 @@ config DWMAC_RZN1
 	  the stmmac device driver. This support can make use of a custom MII
 	  converter PCS device.
 
+config DWMAC_S32
+	tristate "NXP S32G/S32R GMAC support"
+	default ARCH_S32
+	depends on OF && (ARCH_S32 || COMPILE_TEST)
+	help
+	  Support for ethernet controller on NXP S32CC SOCs.
+
+	  This selects NXP SoC glue layer support for the stmmac
+	  device driver. This driver is used for the S32CC series
+	  SOCs GMAC ethernet controller, ie. S32G2xx, S32G3xx and
+	  S32R45.
+
 config DWMAC_SOCFPGA
 	tristate "SOCFPGA dwmac support"
 	default ARCH_INTEL_SOCFPGA
@@ -169,6 +193,17 @@ config DWMAC_SOCFPGA
 	  for the stmmac device driver. This driver is used for
 	  arria5 and cyclone5 FPGA SoCs.
 
+config DWMAC_SOPHGO
+	tristate "Sophgo dwmac support"
+	depends on OF && (ARCH_SOPHGO || COMPILE_TEST)
+	default m if ARCH_SOPHGO
+	help
+	  Support for ethernet controllers on Sophgo RISC-V SoCs
+
+	  This selects the Sophgo SoC specific glue layer support
+	  for the stmmac device driver. This driver is used for the
+	  ethernet controllers on various Sophgo SoCs.
+
 config DWMAC_STARFIVE
 	tristate "StarFive dwmac support"
 	depends on OF && (ARCH_STARFIVE || COMPILE_TEST)
@@ -295,6 +330,7 @@ config DWMAC_INTEL
 	default X86
 	depends on X86 && STMMAC_ETH && PCI
 	depends on COMMON_CLK
+	depends on ACPI
 	help
 	  This selects the Intel platform specific bus support for the
 	  stmmac driver. This driver is used for Intel Quark/EHL/TGL.
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 2389fd261344..b591d93f8503 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -6,7 +6,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o	\
 	      dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \
 	      stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o dwxgmac2_descs.o \
-	      stmmac_xdp.o stmmac_est.o stmmac_fpe.o \
+	      stmmac_xdp.o stmmac_est.o stmmac_fpe.o stmmac_vlan.o \
 	      $(stmmac-y)
 
 stmmac-$(CONFIG_STMMAC_SELFTESTS) += stmmac_selftests.o
@@ -20,9 +20,12 @@ obj-$(CONFIG_DWMAC_LPC18XX)	+= dwmac-lpc18xx.o
 obj-$(CONFIG_DWMAC_MEDIATEK)	+= dwmac-mediatek.o
 obj-$(CONFIG_DWMAC_MESON)	+= dwmac-meson.o dwmac-meson8b.o
 obj-$(CONFIG_DWMAC_QCOM_ETHQOS)	+= dwmac-qcom-ethqos.o
+obj-$(CONFIG_DWMAC_RENESAS_GBETH) += dwmac-renesas-gbeth.o
 obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
 obj-$(CONFIG_DWMAC_RZN1)	+= dwmac-rzn1.o
+obj-$(CONFIG_DWMAC_S32)		+= dwmac-s32.o
 obj-$(CONFIG_DWMAC_SOCFPGA)	+= dwmac-altr-socfpga.o
+obj-$(CONFIG_DWMAC_SOPHGO)	+= dwmac-sophgo.o
 obj-$(CONFIG_DWMAC_STARFIVE)	+= dwmac-starfive.o
 obj-$(CONFIG_DWMAC_STI)		+= dwmac-sti.o
 obj-$(CONFIG_DWMAC_STM32)	+= dwmac-stm32.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 1367fa5c9b8e..ea5da5793362 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -101,8 +101,8 @@ struct stmmac_rxq_stats {
 /* Updates on each CPU protected by not allowing nested irqs. */
 struct stmmac_pcpu_stats {
 	struct u64_stats_sync syncp;
-	u64_stats_t rx_normal_irq_n[MTL_MAX_TX_QUEUES];
-	u64_stats_t tx_normal_irq_n[MTL_MAX_RX_QUEUES];
+	u64_stats_t rx_normal_irq_n[MTL_MAX_RX_QUEUES];
+	u64_stats_t tx_normal_irq_n[MTL_MAX_TX_QUEUES];
 };
 
 /* Extra statistic and debug information exposed by ethtool */
@@ -257,6 +257,8 @@ struct stmmac_safety_stats {
 #define CSR_F_150M	150000000
 #define CSR_F_250M	250000000
 #define CSR_F_300M	300000000
+#define CSR_F_500M	500000000
+#define CSR_F_800M	800000000
 
 #define	MAC_CSR_H_FRQ_MASK	0x20
 
@@ -528,6 +530,20 @@ struct dma_features {
 #define STMMAC_DEFAULT_TWT_LS	0x1E
 #define STMMAC_ET_MAX		0xFFFFF
 
+/* Common LPI register bits */
+#define LPI_CTRL_STATUS_LPITCSE	BIT(21)	/* LPI Tx Clock Stop Enable, gmac4, xgmac2 only */
+#define LPI_CTRL_STATUS_LPIATE	BIT(20)	/* LPI Timer Enable, gmac4 only */
+#define LPI_CTRL_STATUS_LPITXA	BIT(19)	/* Enable LPI TX Automate */
+#define LPI_CTRL_STATUS_PLSEN	BIT(18)	/* Enable PHY Link Status */
+#define LPI_CTRL_STATUS_PLS	BIT(17)	/* PHY Link Status */
+#define LPI_CTRL_STATUS_LPIEN	BIT(16)	/* LPI Enable */
+#define LPI_CTRL_STATUS_RLPIST	BIT(9)	/* Receive LPI state, gmac1000 only? */
+#define LPI_CTRL_STATUS_TLPIST	BIT(8)	/* Transmit LPI state, gmac1000 only? */
+#define LPI_CTRL_STATUS_RLPIEX	BIT(3)	/* Receive LPI Exit */
+#define LPI_CTRL_STATUS_RLPIEN	BIT(2)	/* Receive LPI Entry */
+#define LPI_CTRL_STATUS_TLPIEX	BIT(1)	/* Transmit LPI Exit */
+#define LPI_CTRL_STATUS_TLPIEN	BIT(0)	/* Transmit LPI Entry */
+
 #define STMMAC_CHAIN_MODE	0x1
 #define STMMAC_RING_MODE	0x2
 
@@ -543,18 +559,8 @@ struct dma_features {
 #define STMMAC_VLAN_INSERT	0x2
 #define STMMAC_VLAN_REPLACE	0x3
 
-extern const struct stmmac_desc_ops enh_desc_ops;
-extern const struct stmmac_desc_ops ndesc_ops;
-
 struct mac_device_info;
 
-extern const struct stmmac_hwtimestamp stmmac_ptp;
-extern const struct stmmac_hwtimestamp dwmac1000_ptp;
-extern const struct stmmac_mode_ops dwmac4_ring_mode_ops;
-
-extern const struct ptp_clock_info stmmac_ptp_clock_ops;
-extern const struct ptp_clock_info dwmac1000_ptp_clock_ops;
-
 struct mac_link {
 	u32 caps;
 	u32 speed_mask;
@@ -596,6 +602,7 @@ struct mac_device_info {
 	const struct stmmac_tc_ops *tc;
 	const struct stmmac_mmc_ops *mmc;
 	const struct stmmac_est_ops *est;
+	const struct stmmac_vlan_ops *vlan;
 	struct dw_xpcs *xpcs;
 	struct phylink_pcs *phylink_pcs;
 	struct mii_regs mii;	/* MII register Addresses */
@@ -641,8 +648,4 @@ void stmmac_dwmac4_set_mac(void __iomem *ioaddr, bool enable);
 
 void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr);
 
-extern const struct stmmac_mode_ops ring_mode_ops;
-extern const struct stmmac_mode_ops chain_mode_ops;
-extern const struct stmmac_desc_ops dwmac4_desc_ops;
-
 #endif /* __COMMON_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
index ef99ef3f1ab4..84072c8ed741 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
@@ -59,18 +59,18 @@ static void anarion_gmac_exit(struct platform_device *pdev, void *priv)
 	gmac_write_reg(gmac, GMAC_RESET_CONTROL_REG, 1);
 }
 
-static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev)
+static struct anarion_gmac *
+anarion_config_dt(struct platform_device *pdev,
+		  struct plat_stmmacenet_data *plat_dat)
 {
 	struct anarion_gmac *gmac;
-	phy_interface_t phy_mode;
 	void __iomem *ctl_block;
-	int err;
 
 	ctl_block = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(ctl_block)) {
-		err = PTR_ERR(ctl_block);
-		dev_err(&pdev->dev, "Cannot get reset region (%d)!\n", err);
-		return ERR_PTR(err);
+		dev_err(&pdev->dev, "Cannot get reset region (%pe)!\n",
+			ctl_block);
+		return ERR_CAST(ctl_block);
 	}
 
 	gmac = devm_kzalloc(&pdev->dev, sizeof(*gmac), GFP_KERNEL);
@@ -79,21 +79,11 @@ static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev)
 
 	gmac->ctl_block = ctl_block;
 
-	err = of_get_phy_mode(pdev->dev.of_node, &phy_mode);
-	if (err)
-		return ERR_PTR(err);
-
-	switch (phy_mode) {
-	case PHY_INTERFACE_MODE_RGMII:
-		fallthrough;
-	case PHY_INTERFACE_MODE_RGMII_ID:
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-	case PHY_INTERFACE_MODE_RGMII_TXID:
+	if (phy_interface_mode_is_rgmii(plat_dat->phy_interface)) {
 		gmac->phy_intf_sel = GMAC_CONFIG_INTF_RGMII;
-		break;
-	default:
-		dev_err(&pdev->dev, "Unsupported phy-mode (%d)\n",
-			phy_mode);
+	} else {
+		dev_err(&pdev->dev, "Unsupported phy-mode (%s)\n",
+			phy_modes(plat_dat->phy_interface));
 		return ERR_PTR(-ENOTSUPP);
 	}
 
@@ -111,20 +101,19 @@ static int anarion_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	gmac = anarion_config_dt(pdev);
-	if (IS_ERR(gmac))
-		return PTR_ERR(gmac);
-
 	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
 
+	gmac = anarion_config_dt(pdev, plat_dat);
+	if (IS_ERR(gmac))
+		return PTR_ERR(gmac);
+
 	plat_dat->init = anarion_gmac_init;
 	plat_dat->exit = anarion_gmac_exit;
-	anarion_gmac_init(pdev, gmac);
 	plat_dat->bsp_priv = gmac;
 
-	return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
 static const struct of_device_id anarion_dwmac_match[] = {
@@ -135,7 +124,6 @@ MODULE_DEVICE_TABLE(of, anarion_dwmac_match);
 
 static struct platform_driver anarion_dwmac_driver = {
 	.probe  = anarion_dwmac_probe,
-	.remove = stmmac_pltfr_remove,
 	.driver = {
 		.name           = "anarion-dwmac",
 		.pm		= &stmmac_pltfr_pm_ops,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 83290e707df5..09ae16e026eb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -29,10 +29,6 @@ struct tegra_eqos {
 	void __iomem *regs;
 
 	struct reset_control *rst;
-	struct clk *clk_master;
-	struct clk *clk_slave;
-	struct clk *clk_tx;
-	struct clk *clk_rx;
 
 	struct gpio_desc *reset;
 };
@@ -46,7 +42,9 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 	u32 a_index = 0;
 
 	if (!plat_dat->axi) {
-		plat_dat->axi = kzalloc(sizeof(struct stmmac_axi), GFP_KERNEL);
+		plat_dat->axi = devm_kzalloc(&pdev->dev,
+					     sizeof(struct stmmac_axi),
+					     GFP_KERNEL);
 
 		if (!plat_dat->axi)
 			return -ENOMEM;
@@ -123,49 +121,9 @@ static int dwc_qos_probe(struct platform_device *pdev,
 			 struct plat_stmmacenet_data *plat_dat,
 			 struct stmmac_resources *stmmac_res)
 {
-	int err;
-
-	plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
-	if (IS_ERR(plat_dat->stmmac_clk)) {
-		dev_err(&pdev->dev, "apb_pclk clock not found.\n");
-		return PTR_ERR(plat_dat->stmmac_clk);
-	}
-
-	err = clk_prepare_enable(plat_dat->stmmac_clk);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n",
-			err);
-		return err;
-	}
-
-	plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
-	if (IS_ERR(plat_dat->pclk)) {
-		dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
-		err = PTR_ERR(plat_dat->pclk);
-		goto disable;
-	}
-
-	err = clk_prepare_enable(plat_dat->pclk);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n",
-			err);
-		goto disable;
-	}
+	plat_dat->pclk = stmmac_pltfr_find_clk(plat_dat, "phy_ref_clk");
 
 	return 0;
-
-disable:
-	clk_disable_unprepare(plat_dat->stmmac_clk);
-	return err;
-}
-
-static void dwc_qos_remove(struct platform_device *pdev)
-{
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	clk_disable_unprepare(priv->plat->pclk);
-	clk_disable_unprepare(priv->plat->stmmac_clk);
 }
 
 #define SDMEMCOMPPADCTRL 0x8800
@@ -178,35 +136,34 @@ static void dwc_qos_remove(struct platform_device *pdev)
 #define AUTO_CAL_STATUS 0x880c
 #define  AUTO_CAL_STATUS_ACTIVE BIT(31)
 
-static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static void tegra_eqos_fix_speed(void *bsp_priv, int speed, unsigned int mode)
 {
-	struct tegra_eqos *eqos = priv;
-	unsigned long rate = 125000000;
+	struct tegra_eqos *eqos = bsp_priv;
 	bool needs_calibration = false;
+	struct stmmac_priv *priv;
 	u32 value;
 	int err;
 
 	switch (speed) {
 	case SPEED_1000:
-		needs_calibration = true;
-		rate = 125000000;
-		break;
-
 	case SPEED_100:
 		needs_calibration = true;
-		rate = 25000000;
-		break;
+		fallthrough;
 
 	case SPEED_10:
-		rate = 2500000;
 		break;
 
 	default:
-		dev_err(eqos->dev, "invalid speed %u\n", speed);
+		dev_err(eqos->dev, "invalid speed %d\n", speed);
 		break;
 	}
 
 	if (needs_calibration) {
+		priv = netdev_priv(dev_get_drvdata(eqos->dev));
+
+		/* Calibration should be done with the MDIO bus idle */
+		mutex_lock(&priv->mii->mdio_lock);
+
 		/* calibrate */
 		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
 		value |= SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
@@ -240,33 +197,17 @@ static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mo
 		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
 		value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
 		writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+
+		mutex_unlock(&priv->mii->mdio_lock);
 	} else {
 		value = readl(eqos->regs + AUTO_CAL_CONFIG);
 		value &= ~AUTO_CAL_CONFIG_ENABLE;
 		writel(value, eqos->regs + AUTO_CAL_CONFIG);
 	}
-
-	err = clk_set_rate(eqos->clk_tx, rate);
-	if (err < 0)
-		dev_err(eqos->dev, "failed to set TX rate: %d\n", err);
-}
-
-static int tegra_eqos_init(struct platform_device *pdev, void *priv)
-{
-	struct tegra_eqos *eqos = priv;
-	unsigned long rate;
-	u32 value;
-
-	rate = clk_get_rate(eqos->clk_slave);
-
-	value = (rate / 1000000) - 1;
-	writel(value, eqos->regs + GMAC_1US_TIC_COUNTER);
-
-	return 0;
 }
 
 static int tegra_eqos_probe(struct platform_device *pdev,
-			    struct plat_stmmacenet_data *data,
+			    struct plat_stmmacenet_data *plat_dat,
 			    struct stmmac_resources *res)
 {
 	struct device *dev = &pdev->dev;
@@ -283,59 +224,19 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 	if (!is_of_node(dev->fwnode))
 		goto bypass_clk_reset_gpio;
 
-	eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus");
-	if (IS_ERR(eqos->clk_master)) {
-		err = PTR_ERR(eqos->clk_master);
-		goto error;
-	}
-
-	err = clk_prepare_enable(eqos->clk_master);
-	if (err < 0)
-		goto error;
-
-	eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus");
-	if (IS_ERR(eqos->clk_slave)) {
-		err = PTR_ERR(eqos->clk_slave);
-		goto disable_master;
-	}
-
-	data->stmmac_clk = eqos->clk_slave;
-
-	err = clk_prepare_enable(eqos->clk_slave);
-	if (err < 0)
-		goto disable_master;
-
-	eqos->clk_rx = devm_clk_get(&pdev->dev, "rx");
-	if (IS_ERR(eqos->clk_rx)) {
-		err = PTR_ERR(eqos->clk_rx);
-		goto disable_slave;
-	}
-
-	err = clk_prepare_enable(eqos->clk_rx);
-	if (err < 0)
-		goto disable_slave;
-
-	eqos->clk_tx = devm_clk_get(&pdev->dev, "tx");
-	if (IS_ERR(eqos->clk_tx)) {
-		err = PTR_ERR(eqos->clk_tx);
-		goto disable_rx;
-	}
-
-	err = clk_prepare_enable(eqos->clk_tx);
-	if (err < 0)
-		goto disable_rx;
+	plat_dat->clk_tx_i = stmmac_pltfr_find_clk(plat_dat, "tx");
 
 	eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(eqos->reset)) {
 		err = PTR_ERR(eqos->reset);
-		goto disable_tx;
+		return err;
 	}
 
 	usleep_range(2000, 4000);
 	gpiod_set_value(eqos->reset, 0);
 
 	/* MDIO bus was already reset just above */
-	data->mdio_bus_data->needs_reset = false;
+	plat_dat->mdio_bus_data->needs_reset = false;
 
 	eqos->rst = devm_reset_control_get(&pdev->dev, "eqos");
 	if (IS_ERR(eqos->rst)) {
@@ -356,29 +257,17 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 	usleep_range(2000, 4000);
 
 bypass_clk_reset_gpio:
-	data->fix_mac_speed = tegra_eqos_fix_speed;
-	data->init = tegra_eqos_init;
-	data->bsp_priv = eqos;
-	data->flags |= STMMAC_FLAG_SPH_DISABLE;
-
-	err = tegra_eqos_init(pdev, eqos);
-	if (err < 0)
-		goto reset;
+	plat_dat->fix_mac_speed = tegra_eqos_fix_speed;
+	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
+	plat_dat->bsp_priv = eqos;
+	plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE |
+			   STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP;
 
 	return 0;
-reset:
-	reset_control_assert(eqos->rst);
+
 reset_phy:
 	gpiod_set_value(eqos->reset, 1);
-disable_tx:
-	clk_disable_unprepare(eqos->clk_tx);
-disable_rx:
-	clk_disable_unprepare(eqos->clk_rx);
-disable_slave:
-	clk_disable_unprepare(eqos->clk_slave);
-disable_master:
-	clk_disable_unprepare(eqos->clk_master);
-error:
+
 	return err;
 }
 
@@ -388,27 +277,29 @@ static void tegra_eqos_remove(struct platform_device *pdev)
 
 	reset_control_assert(eqos->rst);
 	gpiod_set_value(eqos->reset, 1);
-	clk_disable_unprepare(eqos->clk_tx);
-	clk_disable_unprepare(eqos->clk_rx);
-	clk_disable_unprepare(eqos->clk_slave);
-	clk_disable_unprepare(eqos->clk_master);
 }
 
 struct dwc_eth_dwmac_data {
 	int (*probe)(struct platform_device *pdev,
-		     struct plat_stmmacenet_data *data,
+		     struct plat_stmmacenet_data *plat_dat,
 		     struct stmmac_resources *res);
 	void (*remove)(struct platform_device *pdev);
+	const char *stmmac_clk_name;
 };
 
 static const struct dwc_eth_dwmac_data dwc_qos_data = {
 	.probe = dwc_qos_probe,
-	.remove = dwc_qos_remove,
+	.stmmac_clk_name = "apb_pclk",
 };
 
 static const struct dwc_eth_dwmac_data tegra_eqos_data = {
 	.probe = tegra_eqos_probe,
 	.remove = tegra_eqos_remove,
+	.stmmac_clk_name = "slave_bus",
+};
+
+static const struct dwc_eth_dwmac_data fsd_eqos_data = {
+	.stmmac_clk_name = "slave_bus",
 };
 
 static int dwc_eth_dwmac_probe(struct platform_device *pdev)
@@ -439,9 +330,23 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
 
-	ret = data->probe(pdev, plat_dat, &stmmac_res);
+	ret = devm_clk_bulk_get_all(&pdev->dev, &plat_dat->clks);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret, "Failed to retrieve all required clocks\n");
+	plat_dat->num_clks = ret;
+
+	ret = clk_bulk_prepare_enable(plat_dat->num_clks, plat_dat->clks);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to enable clocks\n");
+
+	plat_dat->stmmac_clk = stmmac_pltfr_find_clk(plat_dat,
+						     data->stmmac_clk_name);
+
+	if (data->probe)
+		ret = data->probe(pdev, plat_dat, &stmmac_res);
 	if (ret < 0) {
 		dev_err_probe(&pdev->dev, ret, "failed to probe subdriver\n");
+		clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks);
 		return ret;
 	}
 
@@ -456,7 +361,8 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	return ret;
 
 remove:
-	data->remove(pdev);
+	if (data->remove)
+		data->remove(pdev);
 
 	return ret;
 }
@@ -464,15 +370,21 @@ remove:
 static void dwc_eth_dwmac_remove(struct platform_device *pdev)
 {
 	const struct dwc_eth_dwmac_data *data = device_get_match_data(&pdev->dev);
+	struct plat_stmmacenet_data *plat_dat = dev_get_platdata(&pdev->dev);
 
 	stmmac_dvr_remove(&pdev->dev);
 
-	data->remove(pdev);
+	if (data->remove)
+		data->remove(pdev);
+
+	if (plat_dat)
+		clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks);
 }
 
 static const struct of_device_id dwc_eth_dwmac_match[] = {
 	{ .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data },
 	{ .compatible = "nvidia,tegra186-eqos", .data = &tegra_eqos_data },
+	{ .compatible = "tesla,fsd-ethqos", .data = &fsd_eqos_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 641f3cd019a3..889e2bb6f7f5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -36,6 +36,8 @@
 #define MX93_GPR_ENET_QOS_INTF_SEL_RMII		(0x4 << 1)
 #define MX93_GPR_ENET_QOS_INTF_SEL_RGMII	(0x1 << 1)
 #define MX93_GPR_ENET_QOS_CLK_GEN_EN		(0x1 << 0)
+#define MX93_GPR_ENET_QOS_CLK_SEL_MASK		BIT_MASK(0)
+#define MX93_GPR_CLK_SEL_OFFSET			(4)
 
 #define DMA_BUS_MODE			0x00001000
 #define DMA_BUS_MODE_SFT_RESET		(0x1 << 0)
@@ -49,7 +51,7 @@ struct imx_dwmac_ops {
 
 	int (*fix_soc_reset)(void *priv, void __iomem *ioaddr);
 	int (*set_intf_mode)(struct plat_stmmacenet_data *plat_dat);
-	void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode);
+	void (*fix_mac_speed)(void *priv, int speed, unsigned int mode);
 };
 
 struct imx_priv_data {
@@ -108,13 +110,21 @@ imx8dxl_set_intf_mode(struct plat_stmmacenet_data *plat_dat)
 static int imx93_set_intf_mode(struct plat_stmmacenet_data *plat_dat)
 {
 	struct imx_priv_data *dwmac = plat_dat->bsp_priv;
-	int val;
+	int val, ret;
 
 	switch (plat_dat->mac_interface) {
 	case PHY_INTERFACE_MODE_MII:
 		val = MX93_GPR_ENET_QOS_INTF_SEL_MII;
 		break;
 	case PHY_INTERFACE_MODE_RMII:
+		if (dwmac->rmii_refclk_ext) {
+			ret = regmap_clear_bits(dwmac->intf_regmap,
+						dwmac->intf_reg_off +
+						MX93_GPR_CLK_SEL_OFFSET,
+						MX93_GPR_ENET_QOS_CLK_SEL_MASK);
+			if (ret)
+				return ret;
+		}
 		val = MX93_GPR_ENET_QOS_INTF_SEL_RMII;
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
@@ -182,11 +192,24 @@ static void imx_dwmac_exit(struct platform_device *pdev, void *priv)
 	/* nothing to do now */
 }
 
-static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static int imx_dwmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+				     phy_interface_t interface, int speed)
+{
+	struct imx_priv_data *dwmac = bsp_priv;
+
+	interface = dwmac->plat_dat->mac_interface;
+	if (interface == PHY_INTERFACE_MODE_RMII ||
+	    interface == PHY_INTERFACE_MODE_MII)
+		return 0;
+
+	return stmmac_set_clk_tx_rate(bsp_priv, clk_tx_i, interface, speed);
+}
+
+static void imx_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct plat_stmmacenet_data *plat_dat;
 	struct imx_priv_data *dwmac = priv;
-	unsigned long rate;
+	long rate;
 	int err;
 
 	plat_dat = dwmac->plat_dat;
@@ -196,18 +219,9 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod
 	    (plat_dat->mac_interface == PHY_INTERFACE_MODE_MII))
 		return;
 
-	switch (speed) {
-	case SPEED_1000:
-		rate = 125000000;
-		break;
-	case SPEED_100:
-		rate = 25000000;
-		break;
-	case SPEED_10:
-		rate = 2500000;
-		break;
-	default:
-		dev_err(dwmac->dev, "invalid speed %u\n", speed);
+	rate = rgmii_clock(speed);
+	if (rate < 0) {
+		dev_err(dwmac->dev, "invalid speed %d\n", speed);
 		return;
 	}
 
@@ -216,7 +230,7 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod
 		dev_err(dwmac->dev, "failed to set tx rate %lu\n", rate);
 }
 
-static void imx93_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static void imx93_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct imx_priv_data *dwmac = priv;
 	unsigned int iface;
@@ -301,15 +315,11 @@ imx_dwmac_parse_dt(struct imx_priv_data *dwmac, struct device *dev)
 		 * is required by i.MX8MP, i.MX93.
 		 * is optinoal for i.MX8DXL.
 		 */
-		dwmac->intf_regmap = syscon_regmap_lookup_by_phandle(np, "intf_mode");
+		dwmac->intf_regmap =
+			syscon_regmap_lookup_by_phandle_args(np, "intf_mode", 1,
+							     &dwmac->intf_reg_off);
 		if (IS_ERR(dwmac->intf_regmap))
 			return PTR_ERR(dwmac->intf_regmap);
-
-		err = of_property_read_u32_index(np, "intf_mode", 1, &dwmac->intf_reg_off);
-		if (err) {
-			dev_err(dev, "Can't get intf mode reg offset (%d)\n", err);
-			return err;
-		}
 	}
 
 	return err;
@@ -361,7 +371,6 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	plat_dat->init = imx_dwmac_init;
 	plat_dat->exit = imx_dwmac_exit;
 	plat_dat->clks_config = imx_dwmac_clks_config;
-	plat_dat->fix_mac_speed = imx_dwmac_fix_speed;
 	plat_dat->bsp_priv = dwmac;
 	dwmac->plat_dat = plat_dat;
 	dwmac->base_addr = stmmac_res.addr;
@@ -370,24 +379,19 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = imx_dwmac_init(pdev, dwmac);
-	if (ret)
-		goto err_dwmac_init;
-
-	if (dwmac->ops->fix_mac_speed)
+	if (dwmac->ops->fix_mac_speed) {
 		plat_dat->fix_mac_speed = dwmac->ops->fix_mac_speed;
+	} else if (!dwmac->ops->mac_rgmii_txclk_auto_adj) {
+		plat_dat->clk_tx_i = dwmac->clk_tx;
+		plat_dat->set_clk_tx_rate = imx_dwmac_set_clk_tx_rate;
+	}
+
 	dwmac->plat_dat->fix_soc_reset = dwmac->ops->fix_soc_reset;
 
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	ret = stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 	if (ret)
-		goto err_drv_probe;
-
-	return 0;
+		imx_dwmac_clks_config(dwmac, false);
 
-err_drv_probe:
-	imx_dwmac_exit(pdev, plat_dat->bsp_priv);
-err_dwmac_init:
-	imx_dwmac_clks_config(dwmac, false);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
index 066783d66422..15abe214131f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
@@ -56,6 +56,7 @@ enum ingenic_mac_version {
 
 struct ingenic_mac {
 	const struct ingenic_soc_info *soc_info;
+	struct plat_stmmacenet_data *plat_dat;
 	struct device *dev;
 	struct regmap *regmap;
 
@@ -70,13 +71,13 @@ struct ingenic_soc_info {
 	int (*set_mode)(struct plat_stmmacenet_data *plat_dat);
 };
 
-static int ingenic_mac_init(struct plat_stmmacenet_data *plat_dat)
+static int ingenic_mac_init(struct platform_device *pdev, void *bsp_priv)
 {
-	struct ingenic_mac *mac = plat_dat->bsp_priv;
+	struct ingenic_mac *mac = bsp_priv;
 	int ret;
 
 	if (mac->soc_info->set_mode) {
-		ret = mac->soc_info->set_mode(plat_dat);
+		ret = mac->soc_info->set_mode(mac->plat_dat);
 		if (ret)
 			return ret;
 	}
@@ -284,44 +285,14 @@ static int ingenic_mac_probe(struct platform_device *pdev)
 
 	mac->soc_info = data;
 	mac->dev = &pdev->dev;
+	mac->plat_dat = plat_dat;
 
 	plat_dat->bsp_priv = mac;
+	plat_dat->init = ingenic_mac_init;
 
-	ret = ingenic_mac_init(plat_dat);
-	if (ret)
-		return ret;
-
-	return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int ingenic_mac_suspend(struct device *dev)
-{
-	int ret;
-
-	ret = stmmac_suspend(dev);
-
-	return ret;
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
-static int ingenic_mac_resume(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-	int ret;
-
-	ret = ingenic_mac_init(priv->plat);
-	if (ret)
-		return ret;
-
-	ret = stmmac_resume(dev);
-
-	return ret;
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static SIMPLE_DEV_PM_OPS(ingenic_mac_pm_ops, ingenic_mac_suspend, ingenic_mac_resume);
-
 static struct ingenic_soc_info jz4775_soc_info = {
 	.version = ID_JZ4775,
 	.mask = MACPHYC_TXCLK_SEL_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK,
@@ -370,10 +341,9 @@ MODULE_DEVICE_TABLE(of, ingenic_mac_of_matches);
 
 static struct platform_driver ingenic_mac_driver = {
 	.probe		= ingenic_mac_probe,
-	.remove		= stmmac_pltfr_remove,
 	.driver		= {
 		.name	= "ingenic-mac",
-		.pm		= pm_ptr(&ingenic_mac_pm_ops),
+		.pm		= &stmmac_pltfr_pm_ops,
 		.of_match_table = ingenic_mac_of_matches,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index d94f0a150e93..4ea7b0a803d7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -22,45 +22,12 @@ struct intel_dwmac {
 };
 
 struct intel_dwmac_data {
-	void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode);
 	unsigned long ptp_ref_clk_rate;
 	unsigned long tx_clk_rate;
 	bool tx_clk_en;
 };
 
-static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
-{
-	struct intel_dwmac *dwmac = priv;
-	unsigned long rate;
-	int ret;
-
-	rate = clk_get_rate(dwmac->tx_clk);
-
-	switch (speed) {
-	case SPEED_1000:
-		rate = 125000000;
-		break;
-
-	case SPEED_100:
-		rate = 25000000;
-		break;
-
-	case SPEED_10:
-		rate = 2500000;
-		break;
-
-	default:
-		dev_err(dwmac->dev, "Invalid speed\n");
-		break;
-	}
-
-	ret = clk_set_rate(dwmac->tx_clk, rate);
-	if (ret)
-		dev_err(dwmac->dev, "Failed to configure tx clock rate\n");
-}
-
 static const struct intel_dwmac_data kmb_data = {
-	.fix_mac_speed = kmb_eth_fix_mac_speed,
 	.ptp_ref_clk_rate = 200000000,
 	.tx_clk_rate = 125000000,
 	.tx_clk_en = true,
@@ -103,8 +70,6 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 	 * platform_match().
 	 */
 	dwmac->data = device_get_match_data(&pdev->dev);
-	if (dwmac->data->fix_mac_speed)
-		plat_dat->fix_mac_speed = dwmac->data->fix_mac_speed;
 
 	/* Enable TX clock */
 	if (dwmac->data->tx_clk_en) {
@@ -146,15 +111,9 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 		}
 	}
 
+	plat_dat->clk_tx_i = dwmac->tx_clk;
+	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
 	plat_dat->bsp_priv = dwmac;
-	plat_dat->eee_usecs_rate = plat_dat->clk_ptp_rate;
-
-	if (plat_dat->eee_usecs_rate > 0) {
-		u32 tx_lpi_usec;
-
-		tx_lpi_usec = (plat_dat->eee_usecs_rate / 1000000) - 1;
-		writel(tx_lpi_usec, stmmac_res.addr + GMAC_1US_TIC_COUNTER);
-	}
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 48acba5eb178..9a47015254bb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -5,15 +5,30 @@
 #include <linux/clk-provider.h>
 #include <linux/pci.h>
 #include <linux/dmi.h>
+#include <linux/platform_data/x86/intel_pmc_ipc.h>
 #include "dwmac-intel.h"
 #include "dwmac4.h"
 #include "stmmac.h"
 #include "stmmac_ptp.h"
 
+struct pmc_serdes_regs {
+	u8 index;
+	u32 val;
+};
+
+struct pmc_serdes_reg_info {
+	const struct pmc_serdes_regs *regs;
+	u8 num_regs;
+};
+
 struct intel_priv_data {
 	int mdio_adhoc_addr;	/* mdio address for serdes & etc */
 	unsigned long crossts_adj;
 	bool is_pse;
+	const int *tsn_lane_regs;
+	int max_tsn_lane_regs;
+	struct pmc_serdes_reg_info pid_1g;
+	struct pmc_serdes_reg_info pid_2p5g;
 };
 
 /* This struct is used to associate PCI Function of MAC controller on a board,
@@ -35,6 +50,45 @@ struct stmmac_pci_info {
 	int (*setup)(struct pci_dev *pdev, struct plat_stmmacenet_data *plat);
 };
 
+static const struct pmc_serdes_regs pid_modphy3_1g_regs[] = {
+	{ PID_MODPHY3_B_MODPHY_PCR_LCPLL_DWORD0,	B_MODPHY_PCR_LCPLL_DWORD0_1G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD2,	N_MODPHY_PCR_LCPLL_DWORD2_1G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD7,	N_MODPHY_PCR_LCPLL_DWORD7_1G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LPPLL_DWORD10,	N_MODPHY_PCR_LPPLL_DWORD10_1G },
+	{ PID_MODPHY3_N_MODPHY_PCR_CMN_ANA_DWORD30,	N_MODPHY_PCR_CMN_ANA_DWORD30_1G },
+	{}
+};
+
+static const struct pmc_serdes_regs pid_modphy3_2p5g_regs[] = {
+	{ PID_MODPHY3_B_MODPHY_PCR_LCPLL_DWORD0,	B_MODPHY_PCR_LCPLL_DWORD0_2P5G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD2,	N_MODPHY_PCR_LCPLL_DWORD2_2P5G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD7,	N_MODPHY_PCR_LCPLL_DWORD7_2P5G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LPPLL_DWORD10,	N_MODPHY_PCR_LPPLL_DWORD10_2P5G },
+	{ PID_MODPHY3_N_MODPHY_PCR_CMN_ANA_DWORD30,	N_MODPHY_PCR_CMN_ANA_DWORD30_2P5G },
+	{}
+};
+
+static const struct pmc_serdes_regs pid_modphy1_1g_regs[] = {
+	{ PID_MODPHY1_B_MODPHY_PCR_LCPLL_DWORD0,	B_MODPHY_PCR_LCPLL_DWORD0_1G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD2,	N_MODPHY_PCR_LCPLL_DWORD2_1G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD7,	N_MODPHY_PCR_LCPLL_DWORD7_1G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LPPLL_DWORD10,	N_MODPHY_PCR_LPPLL_DWORD10_1G },
+	{ PID_MODPHY1_N_MODPHY_PCR_CMN_ANA_DWORD30,	N_MODPHY_PCR_CMN_ANA_DWORD30_1G },
+	{}
+};
+
+static const struct pmc_serdes_regs pid_modphy1_2p5g_regs[] = {
+	{ PID_MODPHY1_B_MODPHY_PCR_LCPLL_DWORD0,	B_MODPHY_PCR_LCPLL_DWORD0_2P5G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD2,	N_MODPHY_PCR_LCPLL_DWORD2_2P5G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD7,	N_MODPHY_PCR_LCPLL_DWORD7_2P5G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LPPLL_DWORD10,	N_MODPHY_PCR_LPPLL_DWORD10_2P5G },
+	{ PID_MODPHY1_N_MODPHY_PCR_CMN_ANA_DWORD30,	N_MODPHY_PCR_CMN_ANA_DWORD30_2P5G },
+	{}
+};
+
+static const int ehl_tsn_lane_regs[] = {7, 8, 9, 10, 11};
+static const int adln_tsn_lane_regs[] = {6};
+
 static int stmmac_pci_find_phy_addr(struct pci_dev *pdev,
 				    const struct dmi_system_id *dmi_list)
 {
@@ -93,7 +147,7 @@ static int intel_serdes_powerup(struct net_device *ndev, void *priv_data)
 	data &= ~SERDES_RATE_MASK;
 	data &= ~SERDES_PCLK_MASK;
 
-	if (priv->plat->max_speed == 2500)
+	if (priv->plat->phy_interface == PHY_INTERFACE_MODE_2500BASEX)
 		data |= SERDES_RATE_PCIE_GEN2 << SERDES_RATE_PCIE_SHIFT |
 			SERDES_PCLK_37p5MHZ << SERDES_PCLK_SHIFT;
 	else
@@ -230,28 +284,28 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data)
 	}
 }
 
-static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data)
+static void tgl_get_interfaces(struct stmmac_priv *priv, void *bsp_priv,
+			       unsigned long *interfaces)
 {
-	struct intel_priv_data *intel_priv = intel_data;
-	struct stmmac_priv *priv = netdev_priv(ndev);
-	int serdes_phy_addr = 0;
-	u32 data = 0;
-
-	serdes_phy_addr = intel_priv->mdio_adhoc_addr;
+	struct intel_priv_data *intel_priv = bsp_priv;
+	phy_interface_t interface;
+	int data;
 
 	/* Determine the link speed mode: 2.5Gbps/1Gbps */
-	data = mdiobus_read(priv->mii, serdes_phy_addr,
-			    SERDES_GCR);
+	data = mdiobus_read(priv->mii, intel_priv->mdio_adhoc_addr, SERDES_GCR);
+	if (data < 0)
+		return;
 
-	if (((data & SERDES_LINK_MODE_MASK) >> SERDES_LINK_MODE_SHIFT) ==
-	    SERDES_LINK_MODE_2G5) {
+	if (FIELD_GET(SERDES_LINK_MODE_MASK, data) == SERDES_LINK_MODE_2G5) {
 		dev_info(priv->device, "Link Speed Mode: 2.5Gbps\n");
-		priv->plat->max_speed = 2500;
-		priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX;
 		priv->plat->mdio_bus_data->default_an_inband = false;
+		interface = PHY_INTERFACE_MODE_2500BASEX;
 	} else {
-		priv->plat->max_speed = 1000;
+		interface = PHY_INTERFACE_MODE_SGMII;
 	}
+
+	__set_bit(interface, interfaces);
+	priv->plat->phy_interface = interface;
 }
 
 /* Program PTP Clock Frequency for different variant of
@@ -415,6 +469,95 @@ static void intel_mgbe_pse_crossts_adj(struct intel_priv_data *intel_priv,
 	}
 }
 
+static int intel_tsn_lane_is_available(struct net_device *ndev,
+				       struct intel_priv_data *intel_priv)
+{
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct pmc_ipc_cmd tmp = {};
+	struct pmc_ipc_rbuf rbuf = {};
+	int ret = 0, i, j;
+	const int max_fia_regs = 5;
+
+	tmp.cmd = IPC_SOC_REGISTER_ACCESS;
+	tmp.sub_cmd = IPC_SOC_SUB_CMD_READ;
+
+	for (i = 0; i < max_fia_regs; i++) {
+		tmp.wbuf[0] = R_PCH_FIA_15_PCR_LOS1_REG_BASE + i;
+
+		ret = intel_pmc_ipc(&tmp, &rbuf);
+		if (ret < 0) {
+			netdev_info(priv->dev, "Failed to read from PMC.\n");
+			return ret;
+		}
+
+		for (j = 0; j <= intel_priv->max_tsn_lane_regs; j++)
+			if ((rbuf.buf[0] >>
+				(4 * (intel_priv->tsn_lane_regs[j] % 8)) &
+					B_PCH_FIA_PCR_L0O) == 0xB)
+				return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int intel_set_reg_access(const struct pmc_serdes_regs *regs, int max_regs)
+{
+	int ret = 0, i;
+
+	for (i = 0; i < max_regs; i++) {
+		struct pmc_ipc_cmd tmp = {};
+		struct pmc_ipc_rbuf rbuf = {};
+
+		tmp.cmd = IPC_SOC_REGISTER_ACCESS;
+		tmp.sub_cmd = IPC_SOC_SUB_CMD_WRITE;
+		tmp.wbuf[0] = (u32)regs[i].index;
+		tmp.wbuf[1] = regs[i].val;
+
+		ret = intel_pmc_ipc(&tmp, &rbuf);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int intel_mac_finish(struct net_device *ndev,
+			    void *intel_data,
+			    unsigned int mode,
+			    phy_interface_t interface)
+{
+	struct intel_priv_data *intel_priv = intel_data;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	const struct pmc_serdes_regs *regs;
+	int max_regs = 0;
+	int ret = 0;
+
+	ret = intel_tsn_lane_is_available(ndev, intel_priv);
+	if (ret < 0) {
+		netdev_info(priv->dev, "No TSN lane available to set the registers.\n");
+		return ret;
+	}
+
+	if (interface == PHY_INTERFACE_MODE_2500BASEX) {
+		regs = intel_priv->pid_2p5g.regs;
+		max_regs = intel_priv->pid_2p5g.num_regs;
+	} else {
+		regs = intel_priv->pid_1g.regs;
+		max_regs = intel_priv->pid_1g.num_regs;
+	}
+
+	ret = intel_set_reg_access(regs, max_regs);
+	if (ret < 0)
+		return ret;
+
+	priv->plat->phy_interface = interface;
+
+	intel_serdes_powerdown(ndev, intel_priv);
+	intel_serdes_powerup(ndev, intel_priv);
+
+	return ret;
+}
+
 static void common_default_data(struct plat_stmmacenet_data *plat)
 {
 	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
@@ -539,7 +682,6 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->axi->axi_blen[2] = 16;
 
 	plat->ptp_max_adj = plat->clk_ptp_rate;
-	plat->eee_usecs_rate = plat->clk_ptp_rate;
 
 	/* Set system clock */
 	sprintf(clk_name, "%s-%s", "stmmac", pci_name(pdev));
@@ -624,6 +766,8 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 static int ehl_common_data(struct pci_dev *pdev,
 			   struct plat_stmmacenet_data *plat)
 {
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
 	plat->rx_queues_to_use = 8;
 	plat->tx_queues_to_use = 8;
 	plat->flags |= STMMAC_FLAG_USE_PHY_WOL;
@@ -639,20 +783,29 @@ static int ehl_common_data(struct pci_dev *pdev,
 	plat->safety_feat_cfg->prtyen = 0;
 	plat->safety_feat_cfg->tmouten = 0;
 
+	intel_priv->tsn_lane_regs = ehl_tsn_lane_regs;
+	intel_priv->max_tsn_lane_regs = ARRAY_SIZE(ehl_tsn_lane_regs);
+
 	return intel_mgbe_common_data(pdev, plat);
 }
 
 static int ehl_sgmii_data(struct pci_dev *pdev,
 			  struct plat_stmmacenet_data *plat)
 {
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
 	plat->bus_id = 1;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
-	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
-
+	plat->mac_finish = intel_mac_finish;
 	plat->clk_ptp_rate = 204800000;
 
+	intel_priv->pid_1g.regs = pid_modphy3_1g_regs;
+	intel_priv->pid_1g.num_regs = ARRAY_SIZE(pid_modphy3_1g_regs);
+	intel_priv->pid_2p5g.regs = pid_modphy3_2p5g_regs;
+	intel_priv->pid_2p5g.num_regs = ARRAY_SIZE(pid_modphy3_2p5g_regs);
+
 	return ehl_common_data(pdev, plat);
 }
 
@@ -705,10 +858,18 @@ static struct stmmac_pci_info ehl_pse0_rgmii1g_info = {
 static int ehl_pse0_sgmii1g_data(struct pci_dev *pdev,
 				 struct plat_stmmacenet_data *plat)
 {
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
-	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
+	plat->mac_finish = intel_mac_finish;
+
+	intel_priv->pid_1g.regs = pid_modphy1_1g_regs;
+	intel_priv->pid_1g.num_regs = ARRAY_SIZE(pid_modphy1_1g_regs);
+	intel_priv->pid_2p5g.regs = pid_modphy1_2p5g_regs;
+	intel_priv->pid_2p5g.num_regs = ARRAY_SIZE(pid_modphy1_2p5g_regs);
+
 	return ehl_pse0_common_data(pdev, plat);
 }
 
@@ -746,10 +907,18 @@ static struct stmmac_pci_info ehl_pse1_rgmii1g_info = {
 static int ehl_pse1_sgmii1g_data(struct pci_dev *pdev,
 				 struct plat_stmmacenet_data *plat)
 {
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
-	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
+	plat->mac_finish = intel_mac_finish;
+
+	intel_priv->pid_1g.regs = pid_modphy1_1g_regs;
+	intel_priv->pid_1g.num_regs = ARRAY_SIZE(pid_modphy1_1g_regs);
+	intel_priv->pid_2p5g.regs = pid_modphy1_2p5g_regs;
+	intel_priv->pid_2p5g.num_regs = ARRAY_SIZE(pid_modphy1_2p5g_regs);
+
 	return ehl_pse1_common_data(pdev, plat);
 }
 
@@ -763,7 +932,7 @@ static int tgl_common_data(struct pci_dev *pdev,
 	plat->rx_queues_to_use = 6;
 	plat->tx_queues_to_use = 4;
 	plat->clk_ptp_rate = 204800000;
-	plat->speed_mode_2500 = intel_speed_mode_2500;
+	plat->get_interfaces = tgl_get_interfaces;
 
 	plat->safety_feat_cfg->tsoee = 1;
 	plat->safety_feat_cfg->mrxpee = 0;
@@ -782,7 +951,6 @@ static int tgl_sgmii_phy0_data(struct pci_dev *pdev,
 			       struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 1;
-	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 	return tgl_common_data(pdev, plat);
@@ -796,7 +964,6 @@ static int tgl_sgmii_phy1_data(struct pci_dev *pdev,
 			       struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 2;
-	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 	return tgl_common_data(pdev, plat);
@@ -810,7 +977,6 @@ static int adls_sgmii_phy0_data(struct pci_dev *pdev,
 				struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 1;
-	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 
 	/* SerDes power up and power down are done in BIOS for ADL */
 
@@ -825,7 +991,6 @@ static int adls_sgmii_phy1_data(struct pci_dev *pdev,
 				struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 2;
-	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 
 	/* SerDes power up and power down are done in BIOS for ADL */
 
@@ -835,6 +1000,55 @@ static int adls_sgmii_phy1_data(struct pci_dev *pdev,
 static struct stmmac_pci_info adls_sgmii1g_phy1_info = {
 	.setup = adls_sgmii_phy1_data,
 };
+
+static int adln_common_data(struct pci_dev *pdev,
+			    struct plat_stmmacenet_data *plat)
+{
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
+	plat->rx_queues_to_use = 6;
+	plat->tx_queues_to_use = 4;
+	plat->clk_ptp_rate = 204800000;
+
+	plat->safety_feat_cfg->tsoee = 1;
+	plat->safety_feat_cfg->mrxpee = 0;
+	plat->safety_feat_cfg->mestee = 1;
+	plat->safety_feat_cfg->mrxee = 1;
+	plat->safety_feat_cfg->mtxee = 1;
+	plat->safety_feat_cfg->epsi = 0;
+	plat->safety_feat_cfg->edpp = 0;
+	plat->safety_feat_cfg->prtyen = 0;
+	plat->safety_feat_cfg->tmouten = 0;
+
+	intel_priv->tsn_lane_regs = adln_tsn_lane_regs;
+	intel_priv->max_tsn_lane_regs = ARRAY_SIZE(adln_tsn_lane_regs);
+
+	return intel_mgbe_common_data(pdev, plat);
+}
+
+static int adln_sgmii_phy0_data(struct pci_dev *pdev,
+				struct plat_stmmacenet_data *plat)
+{
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
+	plat->bus_id = 1;
+	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->serdes_powerup = intel_serdes_powerup;
+	plat->serdes_powerdown = intel_serdes_powerdown;
+	plat->mac_finish = intel_mac_finish;
+
+	intel_priv->pid_1g.regs = pid_modphy1_1g_regs;
+	intel_priv->pid_1g.num_regs = ARRAY_SIZE(pid_modphy1_1g_regs);
+	intel_priv->pid_2p5g.regs = pid_modphy1_2p5g_regs;
+	intel_priv->pid_2p5g.num_regs = ARRAY_SIZE(pid_modphy1_2p5g_regs);
+
+	return adln_common_data(pdev, plat);
+}
+
+static struct stmmac_pci_info adln_sgmii1g_phy0_info = {
+	.setup = adln_sgmii_phy0_data,
+};
+
 static const struct stmmac_pci_func_data galileo_stmmac_func_data[] = {
 	{
 		.func = 6,
@@ -1094,13 +1308,6 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	memset(&res, 0, sizeof(res));
 	res.addr = pcim_iomap_table(pdev)[0];
 
-	if (plat->eee_usecs_rate > 0) {
-		u32 tx_lpi_usec;
-
-		tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
-		writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
-	}
-
 	ret = stmmac_config_multi_msi(pdev, plat, &res);
 	if (ret) {
 		ret = stmmac_config_single_msi(pdev, plat, &res);
@@ -1217,8 +1424,8 @@ static const struct pci_device_id intel_eth_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1, &tgl_sgmii1g_phy1_info) },
 	{ PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_0, &adls_sgmii1g_phy0_info) },
 	{ PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_1, &adls_sgmii1g_phy1_info) },
-	{ PCI_DEVICE_DATA(INTEL, ADLN_SGMII1G, &tgl_sgmii1g_phy0_info) },
-	{ PCI_DEVICE_DATA(INTEL, RPLP_SGMII1G, &tgl_sgmii1g_phy0_info) },
+	{ PCI_DEVICE_DATA(INTEL, ADLN_SGMII1G, &adln_sgmii1g_phy0_info) },
+	{ PCI_DEVICE_DATA(INTEL, RPLP_SGMII1G, &adln_sgmii1g_phy0_info) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, intel_eth_pci_id_table);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
index 0a37987478c1..7511c224b312 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
@@ -21,7 +21,6 @@
 #define SERDES_RATE_MASK	GENMASK(9, 8)
 #define SERDES_PCLK_MASK	GENMASK(14, 12)	/* PCLK rate to PHY */
 #define SERDES_LINK_MODE_MASK	GENMASK(2, 1)
-#define SERDES_LINK_MODE_SHIFT	1
 #define SERDES_PWR_ST_SHIFT	4
 #define SERDES_PWR_ST_P0	0x0
 #define SERDES_PWR_ST_P3	0x3
@@ -50,4 +49,33 @@
 #define PCH_PTP_CLK_FREQ_19_2MHZ	(GMAC_GPO0)
 #define PCH_PTP_CLK_FREQ_200MHZ		(0)
 
+/* Modphy Register index */
+#define R_PCH_FIA_15_PCR_LOS1_REG_BASE			8
+#define R_PCH_FIA_15_PCR_LOS2_REG_BASE			9
+#define R_PCH_FIA_15_PCR_LOS3_REG_BASE			10
+#define R_PCH_FIA_15_PCR_LOS4_REG_BASE			11
+#define R_PCH_FIA_15_PCR_LOS5_REG_BASE			12
+#define B_PCH_FIA_PCR_L0O				GENMASK(3, 0)
+#define PID_MODPHY1_B_MODPHY_PCR_LCPLL_DWORD0		13
+#define PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD2		14
+#define PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD7		15
+#define PID_MODPHY1_N_MODPHY_PCR_LPPLL_DWORD10		16
+#define PID_MODPHY1_N_MODPHY_PCR_CMN_ANA_DWORD30	17
+#define PID_MODPHY3_B_MODPHY_PCR_LCPLL_DWORD0		18
+#define PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD2		19
+#define PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD7		20
+#define PID_MODPHY3_N_MODPHY_PCR_LPPLL_DWORD10		21
+#define PID_MODPHY3_N_MODPHY_PCR_CMN_ANA_DWORD30	22
+
+#define B_MODPHY_PCR_LCPLL_DWORD0_1G		0x46AAAA41
+#define N_MODPHY_PCR_LCPLL_DWORD2_1G		0x00000139
+#define N_MODPHY_PCR_LCPLL_DWORD7_1G		0x002A0003
+#define N_MODPHY_PCR_LPPLL_DWORD10_1G		0x00170008
+#define N_MODPHY_PCR_CMN_ANA_DWORD30_1G		0x0000D4AC
+#define B_MODPHY_PCR_LCPLL_DWORD0_2P5G		0x58555551
+#define N_MODPHY_PCR_LCPLL_DWORD2_2P5G		0x0000012D
+#define N_MODPHY_PCR_LCPLL_DWORD7_2P5G		0x001F0003
+#define N_MODPHY_PCR_LPPLL_DWORD10_2P5G		0x00170008
+#define N_MODPHY_PCR_CMN_ANA_DWORD30_2P5G	0x8200ACAC
+
 #endif /* __DWMAC_INTEL_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 61227dcf56dc..ca4035cbb55b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -112,7 +112,7 @@ struct ipq806x_gmac {
 	phy_interface_t phy_mode;
 };
 
-static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, unsigned int speed)
+static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, int speed)
 {
 	struct device *dev = &gmac->pdev->dev;
 	int div;
@@ -138,7 +138,7 @@ static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, unsigned int speed)
 	return div;
 }
 
-static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, unsigned int speed)
+static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, int speed)
 {
 	struct device *dev = &gmac->pdev->dev;
 	int div;
@@ -164,7 +164,7 @@ static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, unsigned int speed)
 	return div;
 }
 
-static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, unsigned int speed)
+static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, int speed)
 {
 	uint32_t clk_bits, val;
 	int div;
@@ -211,16 +211,12 @@ static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, unsigned int speed)
 	return 0;
 }
 
-static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac)
+static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac,
+				 struct plat_stmmacenet_data *plat_dat)
 {
 	struct device *dev = &gmac->pdev->dev;
-	int ret;
 
-	ret = of_get_phy_mode(dev->of_node, &gmac->phy_mode);
-	if (ret) {
-		dev_err(dev, "missing phy mode property\n");
-		return -EINVAL;
-	}
+	gmac->phy_mode = plat_dat->phy_interface;
 
 	if (of_property_read_u32(dev->of_node, "qcom,id", &gmac->id) < 0) {
 		dev_err(dev, "missing qcom id property\n");
@@ -260,11 +256,12 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac)
 	return PTR_ERR_OR_ZERO(gmac->qsgmii_csr);
 }
 
-static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static int ipq806x_gmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+					phy_interface_t interface, int speed)
 {
-	struct ipq806x_gmac *gmac = priv;
+	struct ipq806x_gmac *gmac = bsp_priv;
 
-	ipq806x_gmac_set_speed(gmac, speed);
+	return ipq806x_gmac_set_speed(gmac, speed);
 }
 
 static int
@@ -397,7 +394,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 
 	gmac->pdev = pdev;
 
-	err = ipq806x_gmac_of_parse(gmac);
+	err = ipq806x_gmac_of_parse(gmac, plat_dat);
 	if (err) {
 		dev_err(dev, "device tree parsing error\n");
 		return err;
@@ -478,7 +475,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 
 	plat_dat->has_gmac = true;
 	plat_dat->bsp_priv = gmac;
-	plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed;
+	plat_dat->set_clk_tx_rate = ipq806x_gmac_set_clk_tx_rate;
 	plat_dat->multicast_filter_bins = 0;
 	plat_dat->tx_fifo_size = 8192;
 	plat_dat->rx_fifo_size = 8192;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index bfe6e2d631bd..e1591e6217d4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -11,6 +11,8 @@
 #include "dwmac_dma.h"
 #include "dwmac1000.h"
 
+#define DRIVER_NAME "dwmac-loongson-pci"
+
 /* Normal Loongson Tx Summary */
 #define DMA_INTR_ENA_NIE_TX_LOONGSON	0x00040000
 /* Normal Loongson Rx Summary */
@@ -64,12 +66,14 @@
 					 DMA_STATUS_TPS | DMA_STATUS_TI  | \
 					 DMA_STATUS_MSK_COMMON_LOONGSON)
 
-#define PCI_DEVICE_ID_LOONGSON_GMAC	0x7a03
+#define PCI_DEVICE_ID_LOONGSON_GMAC1	0x7a03
+#define PCI_DEVICE_ID_LOONGSON_GMAC2	0x7a23
 #define PCI_DEVICE_ID_LOONGSON_GNET	0x7a13
-#define DWMAC_CORE_LS_MULTICHAN	0x10	/* Loongson custom ID */
-#define CHANNEL_NUM			8
+#define DWMAC_CORE_MULTICHAN_V1	0x10	/* Loongson custom ID 0x10 */
+#define DWMAC_CORE_MULTICHAN_V2	0x12	/* Loongson custom ID 0x12 */
 
 struct loongson_data {
+	u32 multichan;
 	u32 loongson_id;
 	struct device *dev;
 };
@@ -81,6 +85,8 @@ struct stmmac_pci_info {
 static void loongson_default_data(struct pci_dev *pdev,
 				  struct plat_stmmacenet_data *plat)
 {
+	struct loongson_data *ld = plat->bsp_priv;
+
 	/* Get bus_id, this can be overwritten later */
 	plat->bus_id = pci_dev_id(pdev);
 
@@ -114,31 +120,37 @@ static void loongson_default_data(struct pci_dev *pdev,
 
 	plat->dma_cfg->pbl = 32;
 	plat->dma_cfg->pblx8 = true;
-}
 
-static int loongson_gmac_data(struct pci_dev *pdev,
-			      struct plat_stmmacenet_data *plat)
-{
-	struct loongson_data *ld;
-	int i;
-
-	ld = plat->bsp_priv;
-
-	loongson_default_data(pdev, plat);
-
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
-		plat->rx_queues_to_use = CHANNEL_NUM;
-		plat->tx_queues_to_use = CHANNEL_NUM;
+	switch (ld->loongson_id) {
+	case DWMAC_CORE_MULTICHAN_V1:
+		ld->multichan = 1;
+		plat->rx_queues_to_use = 8;
+		plat->tx_queues_to_use = 8;
 
 		/* Only channel 0 supports checksum,
 		 * so turn off checksum to enable multiple channels.
 		 */
-		for (i = 1; i < CHANNEL_NUM; i++)
+		for (int i = 1; i < 8; i++)
 			plat->tx_queues_cfg[i].coe_unsupported = 1;
-	} else {
+
+		break;
+	case DWMAC_CORE_MULTICHAN_V2:
+		ld->multichan = 1;
+		plat->rx_queues_to_use = 4;
+		plat->tx_queues_to_use = 4;
+		break;
+	default:
+		ld->multichan = 0;
 		plat->tx_queues_to_use = 1;
 		plat->rx_queues_to_use = 1;
+		break;
 	}
+}
+
+static int loongson_gmac_data(struct pci_dev *pdev,
+			      struct plat_stmmacenet_data *plat)
+{
+	loongson_default_data(pdev, plat);
 
 	plat->phy_interface = PHY_INTERFACE_MODE_RGMII_ID;
 
@@ -149,8 +161,7 @@ static struct stmmac_pci_info loongson_gmac_pci_info = {
 	.setup = loongson_gmac_data,
 };
 
-static void loongson_gnet_fix_speed(void *priv, unsigned int speed,
-				    unsigned int mode)
+static void loongson_gnet_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct loongson_data *ld = (struct loongson_data *)priv;
 	struct net_device *ndev = dev_get_drvdata(ld->dev);
@@ -171,27 +182,8 @@ static void loongson_gnet_fix_speed(void *priv, unsigned int speed,
 static int loongson_gnet_data(struct pci_dev *pdev,
 			      struct plat_stmmacenet_data *plat)
 {
-	struct loongson_data *ld;
-	int i;
-
-	ld = plat->bsp_priv;
-
 	loongson_default_data(pdev, plat);
 
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
-		plat->rx_queues_to_use = CHANNEL_NUM;
-		plat->tx_queues_to_use = CHANNEL_NUM;
-
-		/* Only channel 0 supports checksum,
-		 * so turn off checksum to enable multiple channels.
-		 */
-		for (i = 1; i < CHANNEL_NUM; i++)
-			plat->tx_queues_cfg[i].coe_unsupported = 1;
-	} else {
-		plat->tx_queues_to_use = 1;
-		plat->rx_queues_to_use = 1;
-	}
-
 	plat->phy_interface = PHY_INTERFACE_MODE_GMII;
 	plat->mdio_bus_data->phy_mask = ~(u32)BIT(2);
 	plat->fix_mac_speed = loongson_gnet_fix_speed;
@@ -349,14 +341,14 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv)
 		return NULL;
 
 	/* The Loongson GMAC and GNET devices are based on the DW GMAC
-	 * v3.50a and v3.73a IP-cores. But the HW designers have changed the
-	 * GMAC_VERSION.SNPSVER field to the custom 0x10 value on the
-	 * network controllers with the multi-channels feature
+	 * v3.50a and v3.73a IP-cores. But the HW designers have changed
+	 * the GMAC_VERSION.SNPSVER field to the custom 0x10/0x12 value
+	 * on the network controllers with the multi-channels feature
 	 * available to emphasize the differences: multiple DMA-channels,
 	 * AV feature and GMAC_INT_STATUS CSR flags layout. Get back the
 	 * original value so the correct HW-interface would be selected.
 	 */
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
+	if (ld->multichan) {
 		priv->synopsys_id = DWMAC_CORE_3_70;
 		*dma = dwmac1000_dma_ops;
 		dma->init_chan = loongson_dwmac_dma_init_channel;
@@ -377,13 +369,13 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv)
 	if (mac->multicast_filter_bins)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
-	/* Loongson GMAC doesn't support the flow control. LS2K2000
-	 * GNET doesn't support the half-duplex link mode.
+	/* Loongson GMAC doesn't support the flow control. Loongson GNET
+	 * without multi-channel doesn't support the half-duplex link mode.
 	 */
-	if (pdev->device == PCI_DEVICE_ID_LOONGSON_GMAC) {
+	if (pdev->device != PCI_DEVICE_ID_LOONGSON_GNET) {
 		mac->link.caps = MAC_10 | MAC_100 | MAC_1000;
 	} else {
-		if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+		if (ld->multichan)
 			mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 					 MAC_10 | MAC_100 | MAC_1000;
 		else
@@ -412,9 +404,11 @@ static int loongson_dwmac_msi_config(struct pci_dev *pdev,
 				     struct plat_stmmacenet_data *plat,
 				     struct stmmac_resources *res)
 {
-	int i, ret, vecs;
+	int i, ch_num, ret, vecs;
+
+	ch_num = min(plat->tx_queues_to_use, plat->rx_queues_to_use);
 
-	vecs = roundup_pow_of_two(CHANNEL_NUM * 2 + 1);
+	vecs = roundup_pow_of_two(ch_num * 2 + 1);
 	ret = pci_alloc_irq_vectors(pdev, vecs, vecs, PCI_IRQ_MSI);
 	if (ret < 0) {
 		dev_warn(&pdev->dev, "Failed to allocate MSI IRQs\n");
@@ -423,14 +417,12 @@ static int loongson_dwmac_msi_config(struct pci_dev *pdev,
 
 	res->irq = pci_irq_vector(pdev, 0);
 
-	for (i = 0; i < plat->rx_queues_to_use; i++) {
-		res->rx_irq[CHANNEL_NUM - 1 - i] =
-			pci_irq_vector(pdev, 1 + i * 2);
+	for (i = 0; i < ch_num; i++) {
+		res->rx_irq[ch_num - 1 - i] = pci_irq_vector(pdev, 1 + i * 2);
 	}
 
-	for (i = 0; i < plat->tx_queues_to_use; i++) {
-		res->tx_irq[CHANNEL_NUM - 1 - i] =
-			pci_irq_vector(pdev, 2 + i * 2);
+	for (i = 0; i < ch_num; i++) {
+		res->tx_irq[ch_num - 1 - i] = pci_irq_vector(pdev, 2 + i * 2);
 	}
 
 	plat->flags |= STMMAC_FLAG_MULTI_MSI_EN;
@@ -516,13 +508,26 @@ static int loongson_dwmac_acpi_config(struct pci_dev *pdev,
 	return 0;
 }
 
+/* Loongson's DWMAC device may take nearly two seconds to complete DMA reset */
+static int loongson_dwmac_fix_reset(void *priv, void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + DMA_BUS_MODE);
+
+	value |= DMA_BUS_MODE_SFT_RESET;
+	writel(value, ioaddr + DMA_BUS_MODE);
+
+	return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value,
+				  !(value & DMA_BUS_MODE_SFT_RESET),
+				  10000, 2000000);
+}
+
 static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct plat_stmmacenet_data *plat;
+	struct stmmac_resources res = {};
 	struct stmmac_pci_info *info;
-	struct stmmac_resources res;
 	struct loongson_data *ld;
-	int ret, i;
+	int ret;
 
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
@@ -552,20 +557,14 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	pci_set_master(pdev);
 
 	/* Get the base address of device */
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (pci_resource_len(pdev, i) == 0)
-			continue;
-		ret = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
-		if (ret)
-			goto err_disable_device;
-		break;
-	}
-
-	memset(&res, 0, sizeof(res));
-	res.addr = pcim_iomap_table(pdev)[0];
+	res.addr = pcim_iomap_region(pdev, 0, DRIVER_NAME);
+	ret = PTR_ERR_OR_ZERO(res.addr);
+	if (ret)
+		goto err_disable_device;
 
 	plat->bsp_priv = ld;
 	plat->setup = loongson_dwmac_setup;
+	plat->fix_soc_reset = loongson_dwmac_fix_reset;
 	ld->dev = &pdev->dev;
 	ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff;
 
@@ -574,6 +573,9 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (ret)
 		goto err_disable_device;
 
+	plat->tx_fifo_size = SZ_16K * plat->tx_queues_to_use;
+	plat->rx_fifo_size = SZ_16K * plat->rx_queues_to_use;
+
 	if (dev_of_node(&pdev->dev))
 		ret = loongson_dwmac_dt_config(pdev, plat, &res);
 	else
@@ -582,7 +584,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 		goto err_disable_device;
 
 	/* Use the common MAC IRQ if per-channel MSIs allocation failed */
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+	if (ld->multichan)
 		loongson_dwmac_msi_config(pdev, plat, &res);
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
@@ -594,7 +596,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 err_plat_clear:
 	if (dev_of_node(&pdev->dev))
 		loongson_dwmac_dt_clear(pdev, plat);
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+	if (ld->multichan)
 		loongson_dwmac_msi_clear(pdev);
 err_disable_device:
 	pci_disable_device(pdev);
@@ -606,7 +608,6 @@ static void loongson_dwmac_remove(struct pci_dev *pdev)
 	struct net_device *ndev = dev_get_drvdata(&pdev->dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	struct loongson_data *ld;
-	int i;
 
 	ld = priv->plat->bsp_priv;
 	stmmac_dvr_remove(&pdev->dev);
@@ -614,16 +615,9 @@ static void loongson_dwmac_remove(struct pci_dev *pdev)
 	if (dev_of_node(&pdev->dev))
 		loongson_dwmac_dt_clear(pdev, priv->plat);
 
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+	if (ld->multichan)
 		loongson_dwmac_msi_clear(pdev);
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (pci_resource_len(pdev, i) == 0)
-			continue;
-		pcim_iounmap_regions(pdev, BIT(i));
-		break;
-	}
-
 	pci_disable_device(pdev);
 }
 
@@ -666,14 +660,15 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend,
 			 loongson_dwmac_resume);
 
 static const struct pci_device_id loongson_dwmac_id_table[] = {
-	{ PCI_DEVICE_DATA(LOONGSON, GMAC, &loongson_gmac_pci_info) },
+	{ PCI_DEVICE_DATA(LOONGSON, GMAC1, &loongson_gmac_pci_info) },
+	{ PCI_DEVICE_DATA(LOONGSON, GMAC2, &loongson_gmac_pci_info) },
 	{ PCI_DEVICE_DATA(LOONGSON, GNET, &loongson_gnet_pci_info) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
 
 static struct pci_driver loongson_dwmac_driver = {
-	.name = "dwmac-loongson-pci",
+	.name = DRIVER_NAME,
 	.id_table = loongson_dwmac_id_table,
 	.probe = loongson_dwmac_probe,
 	.remove = loongson_dwmac_remove,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index c9636832a570..39421d6a34e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -456,7 +456,6 @@ static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat)
 {
 	struct mac_delay_struct *mac_delay = &plat->mac_delay;
 	u32 tx_delay_ps, rx_delay_ps;
-	int err;
 
 	plat->peri_regmap = syscon_regmap_lookup_by_phandle(plat->np, "mediatek,pericfg");
 	if (IS_ERR(plat->peri_regmap)) {
@@ -464,12 +463,6 @@ static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat)
 		return PTR_ERR(plat->peri_regmap);
 	}
 
-	err = of_get_phy_mode(plat->np, &plat->phy_mode);
-	if (err) {
-		dev_err(plat->dev, "not find phy-mode\n");
-		return err;
-	}
-
 	if (!of_property_read_u32(plat->np, "mediatek,tx-delay-ps", &tx_delay_ps)) {
 		if (tx_delay_ps < plat->variant->tx_delay_max) {
 			mac_delay->tx_delay = tx_delay_ps;
@@ -587,7 +580,7 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev,
 {
 	int i;
 
-	plat->mac_interface = priv_plat->phy_mode;
+	priv_plat->phy_mode = plat->phy_interface;
 	if (priv_plat->mac_wol)
 		plat->flags &= ~STMMAC_FLAG_USE_PHY_WOL;
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
index 5469fa1b429e..07c504d07604 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
@@ -22,9 +22,10 @@ struct meson_dwmac {
 	void __iomem	*reg;
 };
 
-static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static int meson6_dwmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+					phy_interface_t interface, int speed)
 {
-	struct meson_dwmac *dwmac = priv;
+	struct meson_dwmac *dwmac = bsp_priv;
 	unsigned int val;
 
 	val = readl(dwmac->reg);
@@ -39,6 +40,8 @@ static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned
 	}
 
 	writel(val, dwmac->reg);
+
+	return 0;
 }
 
 static int meson6_dwmac_probe(struct platform_device *pdev)
@@ -65,7 +68,7 @@ static int meson6_dwmac_probe(struct platform_device *pdev)
 		return PTR_ERR(dwmac->reg);
 
 	plat_dat->bsp_priv = dwmac;
-	plat_dat->fix_mac_speed = meson6_dwmac_fix_mac_speed;
+	plat_dat->set_clk_tx_rate = meson6_dwmac_set_clk_tx_rate;
 
 	return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 9c2d62d133ad..a50782994b97 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -417,11 +417,7 @@ static int meson8b_dwmac_probe(struct platform_device *pdev)
 		return PTR_ERR(dwmac->regs);
 
 	dwmac->dev = &pdev->dev;
-	ret = of_get_phy_mode(pdev->dev.of_node, &dwmac->phy_mode);
-	if (ret) {
-		dev_err(&pdev->dev, "missing phy-mode property\n");
-		return ret;
-	}
+	dwmac->phy_mode = plat_dat->phy_interface;
 
 	/* use 2ns as fallback since this value was previously hardcoded */
 	if (of_property_read_u32(pdev->dev.of_node, "amlogic,tx-delay-ns",
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 901a3c1959fa..e30bdf72331a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -106,12 +106,11 @@ struct qcom_ethqos {
 	struct platform_device *pdev;
 	void __iomem *rgmii_base;
 	void __iomem *mac_base;
-	int (*configure_func)(struct qcom_ethqos *ethqos);
+	int (*configure_func)(struct qcom_ethqos *ethqos, int speed);
 
 	unsigned int link_clk_rate;
 	struct clk *link_clk;
 	struct phy *serdes_phy;
-	unsigned int speed;
 	int serdes_speed;
 	phy_interface_t phy_mode;
 
@@ -169,30 +168,17 @@ static void rgmii_dump(void *priv)
 		rgmii_readl(ethqos, EMAC_SYSTEM_LOW_POWER_DEBUG));
 }
 
-/* Clock rates */
-#define RGMII_1000_NOM_CLK_FREQ			(250 * 1000 * 1000UL)
-#define RGMII_ID_MODE_100_LOW_SVS_CLK_FREQ	 (50 * 1000 * 1000UL)
-#define RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ	  (5 * 1000 * 1000UL)
-
 static void
-ethqos_update_link_clk(struct qcom_ethqos *ethqos, unsigned int speed)
+ethqos_update_link_clk(struct qcom_ethqos *ethqos, int speed)
 {
+	long rate;
+
 	if (!phy_interface_mode_is_rgmii(ethqos->phy_mode))
 		return;
 
-	switch (speed) {
-	case SPEED_1000:
-		ethqos->link_clk_rate =  RGMII_1000_NOM_CLK_FREQ;
-		break;
-
-	case SPEED_100:
-		ethqos->link_clk_rate =  RGMII_ID_MODE_100_LOW_SVS_CLK_FREQ;
-		break;
-
-	case SPEED_10:
-		ethqos->link_clk_rate =  RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ;
-		break;
-	}
+	rate = rgmii_clock(speed);
+	if (rate > 0)
+		ethqos->link_clk_rate = rate * 2;
 
 	clk_set_rate(ethqos->link_clk, ethqos->link_clk_rate);
 }
@@ -398,7 +384,7 @@ static int ethqos_dll_configure(struct qcom_ethqos *ethqos)
 	return 0;
 }
 
-static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos)
+static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos, int speed)
 {
 	struct device *dev = &ethqos->pdev->dev;
 	int phase_shift;
@@ -425,7 +411,7 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos)
 	rgmii_updatel(ethqos, RGMII_CONFIG_INTF_SEL,
 		      0, RGMII_IO_MACRO_CONFIG);
 
-	switch (ethqos->speed) {
+	switch (speed) {
 	case SPEED_1000:
 		rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE,
 			      RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG);
@@ -545,14 +531,14 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos)
 			      loopback, RGMII_IO_MACRO_CONFIG);
 		break;
 	default:
-		dev_err(dev, "Invalid speed %d\n", ethqos->speed);
+		dev_err(dev, "Invalid speed %d\n", speed);
 		return -EINVAL;
 	}
 
 	return 0;
 }
 
-static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
+static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos, int speed)
 {
 	struct device *dev = &ethqos->pdev->dev;
 	volatile unsigned int dll_lock;
@@ -575,7 +561,7 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 		      SDCC_DLL_CONFIG_PDN, SDCC_HC_REG_DLL_CONFIG);
 
 	if (ethqos->has_emac_ge_3) {
-		if (ethqos->speed == SPEED_1000) {
+		if (speed == SPEED_1000) {
 			rgmii_writel(ethqos, 0x1800000, SDCC_TEST_CTL);
 			rgmii_writel(ethqos, 0x2C010800, SDCC_USR_CTL);
 			rgmii_writel(ethqos, 0xA001, SDCC_HC_REG_DLL_CONFIG2);
@@ -593,7 +579,7 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_PDN, 0,
 		      SDCC_HC_REG_DLL_CONFIG);
 
-	if (ethqos->speed != SPEED_100 && ethqos->speed != SPEED_10) {
+	if (speed != SPEED_100 && speed != SPEED_10) {
 		/* Set DLL_EN */
 		rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_EN,
 			      SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG);
@@ -620,10 +606,10 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 			dev_err(dev, "Timeout while waiting for DLL lock\n");
 	}
 
-	if (ethqos->speed == SPEED_1000)
+	if (speed == SPEED_1000)
 		ethqos_dll_configure(ethqos);
 
-	ethqos_rgmii_macro_init(ethqos);
+	ethqos_rgmii_macro_init(ethqos, speed);
 
 	return 0;
 }
@@ -639,7 +625,7 @@ static void ethqos_set_serdes_speed(struct qcom_ethqos *ethqos, int speed)
 /* On interface toggle MAC registers gets reset.
  * Configure MAC block for SGMII on ethernet phy link up
  */
-static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
+static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed)
 {
 	struct net_device *dev = platform_get_drvdata(ethqos->pdev);
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -647,7 +633,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 
 	val = readl(ethqos->mac_base + MAC_CTRL_REG);
 
-	switch (ethqos->speed) {
+	switch (speed) {
 	case SPEED_2500:
 		val &= ~ETHQOS_MAC_CTRL_PORT_SEL;
 		rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG,
@@ -686,27 +672,18 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 	return val;
 }
 
-static void qcom_ethqos_speed_mode_2500(struct net_device *ndev, void *data)
+static int ethqos_configure(struct qcom_ethqos *ethqos, int speed)
 {
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	priv->plat->max_speed = 2500;
-	priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX;
+	return ethqos->configure_func(ethqos, speed);
 }
 
-static int ethqos_configure(struct qcom_ethqos *ethqos)
-{
-	return ethqos->configure_func(ethqos);
-}
-
-static void ethqos_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void ethqos_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct qcom_ethqos *ethqos = priv;
 
 	qcom_ethqos_set_sgmii_loopback(ethqos, false);
-	ethqos->speed = speed;
 	ethqos_update_link_clk(ethqos, speed);
-	ethqos_configure(ethqos);
+	ethqos_configure(ethqos, speed);
 }
 
 static int qcom_ethqos_serdes_powerup(struct net_device *ndev, void *priv)
@@ -722,7 +699,7 @@ static int qcom_ethqos_serdes_powerup(struct net_device *ndev, void *priv)
 	if (ret)
 		return ret;
 
-	return phy_set_speed(ethqos->serdes_phy, ethqos->speed);
+	return phy_set_speed(ethqos->serdes_phy, ethqos->serdes_speed);
 }
 
 static void qcom_ethqos_serdes_powerdown(struct net_device *ndev, void *priv)
@@ -777,7 +754,7 @@ static void ethqos_ptp_clk_freq_config(struct stmmac_priv *priv)
 		netdev_err(priv->dev, "Failed to max out clk_ptp_ref: %d\n", err);
 	plat_dat->clk_ptp_rate = clk_get_rate(plat_dat->clk_ptp_ref);
 
-	netdev_dbg(priv->dev, "PTP rate %d\n", plat_dat->clk_ptp_rate);
+	netdev_dbg(priv->dev, "PTP rate %lu\n", plat_dat->clk_ptp_rate);
 }
 
 static int qcom_ethqos_probe(struct platform_device *pdev)
@@ -807,9 +784,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	if (!ethqos)
 		return -ENOMEM;
 
-	ret = of_get_phy_mode(np, &ethqos->phy_mode);
-	if (ret)
-		return dev_err_probe(dev, ret, "Failed to get phy mode\n");
+	ethqos->phy_mode = plat_dat->phy_interface;
 	switch (ethqos->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
@@ -818,8 +793,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		ethqos->configure_func = ethqos_configure_rgmii;
 		break;
 	case PHY_INTERFACE_MODE_2500BASEX:
-		plat_dat->speed_mode_2500 = qcom_ethqos_speed_mode_2500;
-		fallthrough;
 	case PHY_INTERFACE_MODE_SGMII:
 		ethqos->configure_func = ethqos_configure_sgmii;
 		break;
@@ -862,7 +835,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(ethqos->serdes_phy),
 				     "Failed to get serdes phy\n");
 
-	ethqos->speed = SPEED_1000;
 	ethqos->serdes_speed = SPEED_1000;
 	ethqos_update_link_clk(ethqos, SPEED_1000);
 	ethqos_set_func_clk_en(ethqos);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c
new file mode 100644
index 000000000000..9a774046455b
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * dwmac-renesas-gbeth.c - DWMAC Specific Glue layer for Renesas GBETH
+ *
+ * The Rx and Tx clocks are supplied as follows for the GBETH IP.
+ *
+ *                         Rx / Tx
+ *   -------+------------- on / off -------
+ *          |
+ *          |            Rx-180 / Tx-180
+ *          +---- not ---- on / off -------
+ *
+ * Copyright (C) 2025 Renesas Electronics Corporation
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include "stmmac_platform.h"
+
+struct renesas_gbeth {
+	struct plat_stmmacenet_data *plat_dat;
+	struct reset_control *rstc;
+	struct device *dev;
+};
+
+static const char *const renesas_gbeth_clks[] = {
+	"tx", "tx-180", "rx", "rx-180",
+};
+
+static int renesas_gbeth_init(struct platform_device *pdev, void *priv)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct renesas_gbeth *gbeth = priv;
+	int ret;
+
+	plat_dat = gbeth->plat_dat;
+
+	ret = reset_control_deassert(gbeth->rstc);
+	if (ret) {
+		dev_err(gbeth->dev, "Reset deassert failed\n");
+		return ret;
+	}
+
+	ret = clk_bulk_prepare_enable(plat_dat->num_clks,
+				      plat_dat->clks);
+	if (ret)
+		reset_control_assert(gbeth->rstc);
+
+	return ret;
+}
+
+static void renesas_gbeth_exit(struct platform_device *pdev, void *priv)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct renesas_gbeth *gbeth = priv;
+	int ret;
+
+	plat_dat = gbeth->plat_dat;
+
+	clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks);
+
+	ret = reset_control_assert(gbeth->rstc);
+	if (ret)
+		dev_err(gbeth->dev, "Reset assert failed\n");
+}
+
+static int renesas_gbeth_probe(struct platform_device *pdev)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct device *dev = &pdev->dev;
+	struct renesas_gbeth *gbeth;
+	unsigned int i;
+	int err;
+
+	err = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (err)
+		return dev_err_probe(dev, err,
+				     "failed to get resources\n");
+
+	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return dev_err_probe(dev, PTR_ERR(plat_dat),
+				     "dt configuration failed\n");
+
+	gbeth = devm_kzalloc(dev, sizeof(*gbeth), GFP_KERNEL);
+	if (!gbeth)
+		return -ENOMEM;
+
+	plat_dat->num_clks = ARRAY_SIZE(renesas_gbeth_clks);
+	plat_dat->clks = devm_kcalloc(dev, plat_dat->num_clks,
+				      sizeof(*plat_dat->clks), GFP_KERNEL);
+	if (!plat_dat->clks)
+		return -ENOMEM;
+
+	for (i = 0; i < plat_dat->num_clks; i++)
+		plat_dat->clks[i].id = renesas_gbeth_clks[i];
+
+	err = devm_clk_bulk_get(dev, plat_dat->num_clks, plat_dat->clks);
+	if (err < 0)
+		return err;
+
+	plat_dat->clk_tx_i = stmmac_pltfr_find_clk(plat_dat, "tx");
+	if (!plat_dat->clk_tx_i)
+		return dev_err_probe(dev, -EINVAL,
+				     "error finding tx clock\n");
+
+	gbeth->rstc = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(gbeth->rstc))
+		return PTR_ERR(gbeth->rstc);
+
+	gbeth->dev = dev;
+	gbeth->plat_dat = plat_dat;
+	plat_dat->bsp_priv = gbeth;
+	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
+	plat_dat->init = renesas_gbeth_init;
+	plat_dat->exit = renesas_gbeth_exit;
+	plat_dat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY |
+			   STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP |
+			   STMMAC_FLAG_SPH_DISABLE;
+
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
+}
+
+static const struct of_device_id renesas_gbeth_match[] = {
+	{ .compatible = "renesas,rzv2h-gbeth", },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, renesas_gbeth_match);
+
+static struct platform_driver renesas_gbeth_driver = {
+	.probe  = renesas_gbeth_probe,
+	.driver = {
+		.name		= "renesas-gbeth",
+		.of_match_table	= renesas_gbeth_match,
+	},
+};
+module_platform_driver(renesas_gbeth_driver);
+
+MODULE_AUTHOR("Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>");
+MODULE_DESCRIPTION("Renesas GBETH DWMAC Specific Glue layer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 8cb374668b74..700858ff6f7c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -33,6 +33,8 @@ struct rk_gmac_ops {
 	void (*set_clock_selection)(struct rk_priv_data *bsp_priv, bool input,
 				    bool enable);
 	void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv);
+	void (*integrated_phy_powerdown)(struct rk_priv_data *bsp_priv);
+	bool php_grf_required;
 	bool regs_valid;
 	u32 regs[];
 };
@@ -91,6 +93,76 @@ struct rk_priv_data {
 	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
 	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
 
+#define RK_GRF_MACPHY_CON0		0xb00
+#define RK_GRF_MACPHY_CON1		0xb04
+#define RK_GRF_MACPHY_CON2		0xb08
+#define RK_GRF_MACPHY_CON3		0xb0c
+
+#define RK_MACPHY_ENABLE		GRF_BIT(0)
+#define RK_MACPHY_DISABLE		GRF_CLR_BIT(0)
+#define RK_MACPHY_CFG_CLK_50M		GRF_BIT(14)
+#define RK_GMAC2PHY_RMII_MODE		(GRF_BIT(6) | GRF_CLR_BIT(7))
+#define RK_GRF_CON2_MACPHY_ID		HIWORD_UPDATE(0x1234, 0xffff, 0)
+#define RK_GRF_CON3_MACPHY_ID		HIWORD_UPDATE(0x35, 0x3f, 0)
+
+static void rk_gmac_integrated_ephy_powerup(struct rk_priv_data *priv)
+{
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_CFG_CLK_50M);
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_GMAC2PHY_RMII_MODE);
+
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON2, RK_GRF_CON2_MACPHY_ID);
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON3, RK_GRF_CON3_MACPHY_ID);
+
+	if (priv->phy_reset) {
+		/* PHY needs to be disabled before trying to reset it */
+		regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
+		if (priv->phy_reset)
+			reset_control_assert(priv->phy_reset);
+		usleep_range(10, 20);
+		if (priv->phy_reset)
+			reset_control_deassert(priv->phy_reset);
+		usleep_range(10, 20);
+		regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_ENABLE);
+		msleep(30);
+	}
+}
+
+static void rk_gmac_integrated_ephy_powerdown(struct rk_priv_data *priv)
+{
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
+	if (priv->phy_reset)
+		reset_control_assert(priv->phy_reset);
+}
+
+#define RK_FEPHY_SHUTDOWN		GRF_BIT(1)
+#define RK_FEPHY_POWERUP		GRF_CLR_BIT(1)
+#define RK_FEPHY_INTERNAL_RMII_SEL	GRF_BIT(6)
+#define RK_FEPHY_24M_CLK_SEL		(GRF_BIT(8) | GRF_BIT(9))
+#define RK_FEPHY_PHY_ID			GRF_BIT(11)
+
+static void rk_gmac_integrated_fephy_powerup(struct rk_priv_data *priv,
+					     unsigned int reg)
+{
+	reset_control_assert(priv->phy_reset);
+	usleep_range(20, 30);
+
+	regmap_write(priv->grf, reg,
+		     RK_FEPHY_POWERUP |
+		     RK_FEPHY_INTERNAL_RMII_SEL |
+		     RK_FEPHY_24M_CLK_SEL |
+		     RK_FEPHY_PHY_ID);
+	usleep_range(10000, 12000);
+
+	reset_control_deassert(priv->phy_reset);
+	usleep_range(50000, 60000);
+}
+
+static void rk_gmac_integrated_fephy_powerdown(struct rk_priv_data *priv,
+					       unsigned int reg)
+{
+	regmap_write(priv->grf, reg, RK_FEPHY_SHUTDOWN);
+}
+
 #define PX30_GRF_GMAC_CON1		0x0904
 
 /* PX30_GRF_GMAC_CON1 */
@@ -101,13 +173,6 @@ struct rk_priv_data {
 
 static void px30_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
 		     PX30_GMAC_PHY_INTF_SEL_RMII);
 }
@@ -181,13 +246,6 @@ static const struct rk_gmac_ops px30_ops = {
 static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
 		     RK3128_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3128_GMAC_RMII_MODE_CLR);
@@ -199,13 +257,6 @@ static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
 		     RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE);
 }
@@ -214,11 +265,6 @@ static void rk3128_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
 			     RK3128_GMAC_CLK_2_5M);
@@ -236,11 +282,6 @@ static void rk3128_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
 			     RK3128_GMAC_RMII_CLK_2_5M |
@@ -297,13 +338,6 @@ static const struct rk_gmac_ops rk3128_ops = {
 static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 		     RK3228_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3228_GMAC_RMII_MODE_CLR |
@@ -316,13 +350,6 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3228_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 		     RK3228_GMAC_PHY_INTF_SEL_RMII |
 		     RK3228_GMAC_RMII_MODE);
@@ -335,11 +362,6 @@ static void rk3228_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 			     RK3228_GMAC_CLK_2_5M);
@@ -357,11 +379,6 @@ static void rk3228_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 			     RK3228_GMAC_RMII_CLK_2_5M |
@@ -378,6 +395,8 @@ static void rk3228_integrated_phy_powerup(struct rk_priv_data *priv)
 {
 	regmap_write(priv->grf, RK3228_GRF_CON_MUX,
 		     RK3228_GRF_CON_MUX_GMAC_INTEGRATED_PHY);
+
+	rk_gmac_integrated_ephy_powerup(priv);
 }
 
 static const struct rk_gmac_ops rk3228_ops = {
@@ -385,7 +404,8 @@ static const struct rk_gmac_ops rk3228_ops = {
 	.set_to_rmii = rk3228_set_to_rmii,
 	.set_rgmii_speed = rk3228_set_rgmii_speed,
 	.set_rmii_speed = rk3228_set_rmii_speed,
-	.integrated_phy_powerup =  rk3228_integrated_phy_powerup,
+	.integrated_phy_powerup = rk3228_integrated_phy_powerup,
+	.integrated_phy_powerdown = rk_gmac_integrated_ephy_powerdown,
 };
 
 #define RK3288_GRF_SOC_CON1	0x0248
@@ -419,13 +439,6 @@ static const struct rk_gmac_ops rk3228_ops = {
 static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
 		     RK3288_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3288_GMAC_RMII_MODE_CLR);
@@ -437,13 +450,6 @@ static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3288_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
 		     RK3288_GMAC_PHY_INTF_SEL_RMII | RK3288_GMAC_RMII_MODE);
 }
@@ -452,11 +458,6 @@ static void rk3288_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
 			     RK3288_GMAC_CLK_2_5M);
@@ -474,11 +475,6 @@ static void rk3288_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
 			     RK3288_GMAC_RMII_CLK_2_5M |
@@ -511,13 +507,6 @@ static const struct rk_gmac_ops rk3288_ops = {
 
 static void rk3308_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0,
 		     RK3308_GMAC_PHY_INTF_SEL_RMII);
 }
@@ -526,11 +515,6 @@ static void rk3308_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0,
 			     RK3308_GMAC_SPEED_10M);
@@ -583,13 +567,6 @@ static const struct rk_gmac_ops rk3308_ops = {
 static void rk3328_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1,
 		     RK3328_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3328_GMAC_RMII_MODE_CLR |
@@ -603,14 +580,8 @@ static void rk3328_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3328_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	unsigned int reg;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	reg = bsp_priv->integrated_phy ? RK3328_GRF_MAC_CON2 :
 		  RK3328_GRF_MAC_CON1;
 
@@ -623,11 +594,6 @@ static void rk3328_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1,
 			     RK3328_GMAC_CLK_2_5M);
@@ -646,11 +612,6 @@ static void rk3328_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 	struct device *dev = &bsp_priv->pdev->dev;
 	unsigned int reg;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	reg = bsp_priv->integrated_phy ? RK3328_GRF_MAC_CON2 :
 		  RK3328_GRF_MAC_CON1;
 
@@ -670,6 +631,8 @@ static void rk3328_integrated_phy_powerup(struct rk_priv_data *priv)
 {
 	regmap_write(priv->grf, RK3328_GRF_MACPHY_CON1,
 		     RK3328_MACPHY_RMII_MODE);
+
+	rk_gmac_integrated_ephy_powerup(priv);
 }
 
 static const struct rk_gmac_ops rk3328_ops = {
@@ -677,7 +640,8 @@ static const struct rk_gmac_ops rk3328_ops = {
 	.set_to_rmii = rk3328_set_to_rmii,
 	.set_rgmii_speed = rk3328_set_rgmii_speed,
 	.set_rmii_speed = rk3328_set_rmii_speed,
-	.integrated_phy_powerup =  rk3328_integrated_phy_powerup,
+	.integrated_phy_powerup = rk3328_integrated_phy_powerup,
+	.integrated_phy_powerdown = rk_gmac_integrated_ephy_powerdown,
 };
 
 #define RK3366_GRF_SOC_CON6	0x0418
@@ -711,13 +675,6 @@ static const struct rk_gmac_ops rk3328_ops = {
 static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6,
 		     RK3366_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3366_GMAC_RMII_MODE_CLR);
@@ -729,13 +686,6 @@ static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3366_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6,
 		     RK3366_GMAC_PHY_INTF_SEL_RMII | RK3366_GMAC_RMII_MODE);
 }
@@ -744,11 +694,6 @@ static void rk3366_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6,
 			     RK3366_GMAC_CLK_2_5M);
@@ -766,11 +711,6 @@ static void rk3366_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6,
 			     RK3366_GMAC_RMII_CLK_2_5M |
@@ -822,13 +762,6 @@ static const struct rk_gmac_ops rk3366_ops = {
 static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
 		     RK3368_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3368_GMAC_RMII_MODE_CLR);
@@ -840,13 +773,6 @@ static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3368_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
 		     RK3368_GMAC_PHY_INTF_SEL_RMII | RK3368_GMAC_RMII_MODE);
 }
@@ -855,11 +781,6 @@ static void rk3368_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
 			     RK3368_GMAC_CLK_2_5M);
@@ -877,11 +798,6 @@ static void rk3368_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
 			     RK3368_GMAC_RMII_CLK_2_5M |
@@ -933,13 +849,6 @@ static const struct rk_gmac_ops rk3368_ops = {
 static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5,
 		     RK3399_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3399_GMAC_RMII_MODE_CLR);
@@ -951,13 +860,6 @@ static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3399_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5,
 		     RK3399_GMAC_PHY_INTF_SEL_RMII | RK3399_GMAC_RMII_MODE);
 }
@@ -966,11 +868,6 @@ static void rk3399_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5,
 			     RK3399_GMAC_CLK_2_5M);
@@ -988,11 +885,6 @@ static void rk3399_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5,
 			     RK3399_GMAC_RMII_CLK_2_5M |
@@ -1013,6 +905,149 @@ static const struct rk_gmac_ops rk3399_ops = {
 	.set_rmii_speed = rk3399_set_rmii_speed,
 };
 
+#define RK3528_VO_GRF_GMAC_CON		0x0018
+#define RK3528_VO_GRF_MACPHY_CON0	0x001c
+#define RK3528_VO_GRF_MACPHY_CON1	0x0020
+#define RK3528_VPU_GRF_GMAC_CON5	0x0018
+#define RK3528_VPU_GRF_GMAC_CON6	0x001c
+
+#define RK3528_GMAC_RXCLK_DLY_ENABLE	GRF_BIT(15)
+#define RK3528_GMAC_RXCLK_DLY_DISABLE	GRF_CLR_BIT(15)
+#define RK3528_GMAC_TXCLK_DLY_ENABLE	GRF_BIT(14)
+#define RK3528_GMAC_TXCLK_DLY_DISABLE	GRF_CLR_BIT(14)
+
+#define RK3528_GMAC_CLK_RX_DL_CFG(val)	HIWORD_UPDATE(val, 0xFF, 8)
+#define RK3528_GMAC_CLK_TX_DL_CFG(val)	HIWORD_UPDATE(val, 0xFF, 0)
+
+#define RK3528_GMAC0_PHY_INTF_SEL_RMII	GRF_BIT(1)
+#define RK3528_GMAC1_PHY_INTF_SEL_RGMII	GRF_CLR_BIT(8)
+#define RK3528_GMAC1_PHY_INTF_SEL_RMII	GRF_BIT(8)
+
+#define RK3528_GMAC1_CLK_SELECT_CRU	GRF_CLR_BIT(12)
+#define RK3528_GMAC1_CLK_SELECT_IO	GRF_BIT(12)
+
+#define RK3528_GMAC0_CLK_RMII_DIV2	GRF_BIT(3)
+#define RK3528_GMAC0_CLK_RMII_DIV20	GRF_CLR_BIT(3)
+#define RK3528_GMAC1_CLK_RMII_DIV2	GRF_BIT(10)
+#define RK3528_GMAC1_CLK_RMII_DIV20	GRF_CLR_BIT(10)
+
+#define RK3528_GMAC1_CLK_RGMII_DIV1	(GRF_CLR_BIT(11) | GRF_CLR_BIT(10))
+#define RK3528_GMAC1_CLK_RGMII_DIV5	(GRF_BIT(11) | GRF_BIT(10))
+#define RK3528_GMAC1_CLK_RGMII_DIV50	(GRF_BIT(11) | GRF_CLR_BIT(10))
+
+#define RK3528_GMAC0_CLK_RMII_GATE	GRF_BIT(2)
+#define RK3528_GMAC0_CLK_RMII_NOGATE	GRF_CLR_BIT(2)
+#define RK3528_GMAC1_CLK_RMII_GATE	GRF_BIT(9)
+#define RK3528_GMAC1_CLK_RMII_NOGATE	GRF_CLR_BIT(9)
+
+static void rk3528_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
+{
+	regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+		     RK3528_GMAC1_PHY_INTF_SEL_RGMII);
+
+	regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+		     DELAY_ENABLE(RK3528, tx_delay, rx_delay));
+
+	regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON6,
+		     RK3528_GMAC_CLK_RX_DL_CFG(rx_delay) |
+		     RK3528_GMAC_CLK_TX_DL_CFG(tx_delay));
+}
+
+static void rk3528_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	if (bsp_priv->id == 1)
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+			     RK3528_GMAC1_PHY_INTF_SEL_RMII);
+	else
+		regmap_write(bsp_priv->grf, RK3528_VO_GRF_GMAC_CON,
+			     RK3528_GMAC0_PHY_INTF_SEL_RMII |
+			     RK3528_GMAC0_CLK_RMII_DIV2);
+}
+
+static void rk3528_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (speed == 10)
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+			     RK3528_GMAC1_CLK_RGMII_DIV50);
+	else if (speed == 100)
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+			     RK3528_GMAC1_CLK_RGMII_DIV5);
+	else if (speed == 1000)
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+			     RK3528_GMAC1_CLK_RGMII_DIV1);
+	else
+		dev_err(dev, "unknown speed value for RGMII! speed=%d", speed);
+}
+
+static void rk3528_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	unsigned int reg, val;
+
+	if (speed == 10)
+		val = bsp_priv->id == 1 ? RK3528_GMAC1_CLK_RMII_DIV20 :
+					  RK3528_GMAC0_CLK_RMII_DIV20;
+	else if (speed == 100)
+		val = bsp_priv->id == 1 ? RK3528_GMAC1_CLK_RMII_DIV2 :
+					  RK3528_GMAC0_CLK_RMII_DIV2;
+	else {
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+		return;
+	}
+
+	reg = bsp_priv->id == 1 ? RK3528_VPU_GRF_GMAC_CON5 :
+				  RK3528_VO_GRF_GMAC_CON;
+
+	regmap_write(bsp_priv->grf, reg, val);
+}
+
+static void rk3528_set_clock_selection(struct rk_priv_data *bsp_priv,
+				       bool input, bool enable)
+{
+	unsigned int val;
+
+	if (bsp_priv->id == 1) {
+		val = input ? RK3528_GMAC1_CLK_SELECT_IO :
+			      RK3528_GMAC1_CLK_SELECT_CRU;
+		val |= enable ? RK3528_GMAC1_CLK_RMII_NOGATE :
+				RK3528_GMAC1_CLK_RMII_GATE;
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5, val);
+	} else {
+		val = enable ? RK3528_GMAC0_CLK_RMII_NOGATE :
+			       RK3528_GMAC0_CLK_RMII_GATE;
+		regmap_write(bsp_priv->grf, RK3528_VO_GRF_GMAC_CON, val);
+	}
+}
+
+static void rk3528_integrated_phy_powerup(struct rk_priv_data *bsp_priv)
+{
+	rk_gmac_integrated_fephy_powerup(bsp_priv, RK3528_VO_GRF_MACPHY_CON0);
+}
+
+static void rk3528_integrated_phy_powerdown(struct rk_priv_data *bsp_priv)
+{
+	rk_gmac_integrated_fephy_powerdown(bsp_priv, RK3528_VO_GRF_MACPHY_CON0);
+}
+
+static const struct rk_gmac_ops rk3528_ops = {
+	.set_to_rgmii = rk3528_set_to_rgmii,
+	.set_to_rmii = rk3528_set_to_rmii,
+	.set_rgmii_speed = rk3528_set_rgmii_speed,
+	.set_rmii_speed = rk3528_set_rmii_speed,
+	.set_clock_selection = rk3528_set_clock_selection,
+	.integrated_phy_powerup = rk3528_integrated_phy_powerup,
+	.integrated_phy_powerdown = rk3528_integrated_phy_powerdown,
+	.regs_valid = true,
+	.regs = {
+		0xffbd0000, /* gmac0 */
+		0xffbe0000, /* gmac1 */
+		0x0, /* sentinel */
+	},
+};
+
 #define RK3568_GRF_GMAC0_CON0		0x0380
 #define RK3568_GRF_GMAC0_CON1		0x0384
 #define RK3568_GRF_GMAC1_CON0		0x0388
@@ -1037,14 +1072,8 @@ static const struct rk_gmac_ops rk3399_ops = {
 static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	u32 con0, con1;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	con0 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON0 :
 				     RK3568_GRF_GMAC0_CON0;
 	con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 :
@@ -1062,14 +1091,8 @@ static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3568_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	u32 con1;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 :
 				     RK3568_GRF_GMAC0_CON1;
 	regmap_write(bsp_priv->grf, con1, RK3568_GMAC_PHY_INTF_SEL_RMII);
@@ -1079,20 +1102,11 @@ static void rk3568_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk;
 	struct device *dev = &bsp_priv->pdev->dev;
-	unsigned long rate;
+	long rate;
 	int ret;
 
-	switch (speed) {
-	case 10:
-		rate = 2500000;
-		break;
-	case 100:
-		rate = 25000000;
-		break;
-	case 1000:
-		rate = 125000000;
-		break;
-	default:
+	rate = rgmii_clock(speed);
+	if (rate < 0) {
 		dev_err(dev, "unknown speed value for GMAC speed=%d", speed);
 		return;
 	}
@@ -1156,14 +1170,8 @@ static const struct rk_gmac_ops rk3568_ops = {
 static void rk3576_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	unsigned int offset_con;
 
-	if (IS_ERR(bsp_priv->grf) || IS_ERR(bsp_priv->php_grf)) {
-		dev_err(dev, "Missing rockchip,grf or rockchip,php-grf property\n");
-		return;
-	}
-
 	offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 :
 					 RK3576_GRF_GMAC_CON0;
 
@@ -1189,14 +1197,8 @@ static void rk3576_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3576_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	unsigned int offset_con;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 :
 					 RK3576_GRF_GMAC_CON0;
 
@@ -1263,6 +1265,7 @@ static const struct rk_gmac_ops rk3576_ops = {
 	.set_rgmii_speed = rk3576_set_gmac_speed,
 	.set_rmii_speed = rk3576_set_gmac_speed,
 	.set_clock_selection = rk3576_set_clock_selection,
+	.php_grf_required = true,
 	.regs_valid = true,
 	.regs = {
 		0x2a220000, /* gmac0 */
@@ -1315,14 +1318,8 @@ static const struct rk_gmac_ops rk3576_ops = {
 static void rk3588_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	u32 offset_con, id = bsp_priv->id;
 
-	if (IS_ERR(bsp_priv->grf) || IS_ERR(bsp_priv->php_grf)) {
-		dev_err(dev, "Missing rockchip,grf or rockchip,php_grf property\n");
-		return;
-	}
-
 	offset_con = bsp_priv->id == 1 ? RK3588_GRF_GMAC_CON9 :
 					 RK3588_GRF_GMAC_CON8;
 
@@ -1343,13 +1340,6 @@ static void rk3588_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3588_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->php_grf)) {
-		dev_err(dev, "%s: Missing rockchip,php_grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->php_grf, RK3588_GRF_GMAC_CON0,
 		     RK3588_GMAC_PHY_INTF_SEL_RMII(bsp_priv->id));
 
@@ -1410,6 +1400,7 @@ static const struct rk_gmac_ops rk3588_ops = {
 	.set_rgmii_speed = rk3588_set_gmac_speed,
 	.set_rmii_speed = rk3588_set_gmac_speed,
 	.set_clock_selection = rk3588_set_clock_selection,
+	.php_grf_required = true,
 	.regs_valid = true,
 	.regs = {
 		0xfe1b0000, /* gmac0 */
@@ -1432,13 +1423,6 @@ static const struct rk_gmac_ops rk3588_ops = {
 
 static void rv1108_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0,
 		     RV1108_GMAC_PHY_INTF_SEL_RMII);
 }
@@ -1447,11 +1431,6 @@ static void rv1108_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0,
 			     RV1108_GMAC_RMII_CLK_2_5M |
@@ -1500,13 +1479,6 @@ static const struct rk_gmac_ops rv1108_ops = {
 static void rv1126_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RV1126_GRF_GMAC_CON0,
 		     RV1126_GMAC_PHY_INTF_SEL_RGMII |
 		     RV1126_GMAC_M0_RXCLK_DLY_ENABLE |
@@ -1525,13 +1497,6 @@ static void rv1126_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rv1126_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RV1126_GRF_GMAC_CON0,
 		     RV1126_GMAC_PHY_INTF_SEL_RMII);
 }
@@ -1540,20 +1505,11 @@ static void rv1126_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk;
 	struct device *dev = &bsp_priv->pdev->dev;
-	unsigned long rate;
+	long rate;
 	int ret;
 
-	switch (speed) {
-	case 10:
-		rate = 2500000;
-		break;
-	case 100:
-		rate = 25000000;
-		break;
-	case 1000:
-		rate = 125000000;
-		break;
-	default:
+	rate = rgmii_clock(speed);
+	if (rate < 0) {
 		dev_err(dev, "unknown speed value for RGMII speed=%d", speed);
 		return;
 	}
@@ -1596,50 +1552,6 @@ static const struct rk_gmac_ops rv1126_ops = {
 	.set_rmii_speed = rv1126_set_rmii_speed,
 };
 
-#define RK_GRF_MACPHY_CON0		0xb00
-#define RK_GRF_MACPHY_CON1		0xb04
-#define RK_GRF_MACPHY_CON2		0xb08
-#define RK_GRF_MACPHY_CON3		0xb0c
-
-#define RK_MACPHY_ENABLE		GRF_BIT(0)
-#define RK_MACPHY_DISABLE		GRF_CLR_BIT(0)
-#define RK_MACPHY_CFG_CLK_50M		GRF_BIT(14)
-#define RK_GMAC2PHY_RMII_MODE		(GRF_BIT(6) | GRF_CLR_BIT(7))
-#define RK_GRF_CON2_MACPHY_ID		HIWORD_UPDATE(0x1234, 0xffff, 0)
-#define RK_GRF_CON3_MACPHY_ID		HIWORD_UPDATE(0x35, 0x3f, 0)
-
-static void rk_gmac_integrated_phy_powerup(struct rk_priv_data *priv)
-{
-	if (priv->ops->integrated_phy_powerup)
-		priv->ops->integrated_phy_powerup(priv);
-
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_CFG_CLK_50M);
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_GMAC2PHY_RMII_MODE);
-
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON2, RK_GRF_CON2_MACPHY_ID);
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON3, RK_GRF_CON3_MACPHY_ID);
-
-	if (priv->phy_reset) {
-		/* PHY needs to be disabled before trying to reset it */
-		regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
-		if (priv->phy_reset)
-			reset_control_assert(priv->phy_reset);
-		usleep_range(10, 20);
-		if (priv->phy_reset)
-			reset_control_deassert(priv->phy_reset);
-		usleep_range(10, 20);
-		regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_ENABLE);
-		msleep(30);
-	}
-}
-
-static void rk_gmac_integrated_phy_powerdown(struct rk_priv_data *priv)
-{
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
-	if (priv->phy_reset)
-		reset_control_assert(priv->phy_reset);
-}
-
 static int rk_gmac_clk_init(struct plat_stmmacenet_data *plat)
 {
 	struct rk_priv_data *bsp_priv = plat->bsp_priv;
@@ -1767,7 +1679,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 	if (!bsp_priv)
 		return ERR_PTR(-ENOMEM);
 
-	of_get_phy_mode(dev->of_node, &bsp_priv->phy_iface);
+	bsp_priv->phy_iface = plat->phy_interface;
 	bsp_priv->ops = ops;
 
 	/* Some SoCs have multiple MAC controllers, which need
@@ -1830,8 +1742,22 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 
 	bsp_priv->grf = syscon_regmap_lookup_by_phandle(dev->of_node,
 							"rockchip,grf");
-	bsp_priv->php_grf = syscon_regmap_lookup_by_phandle(dev->of_node,
-							    "rockchip,php-grf");
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err_probe(dev, PTR_ERR(bsp_priv->grf),
+			      "failed to lookup rockchip,grf\n");
+		return ERR_CAST(bsp_priv->grf);
+	}
+
+	if (ops->php_grf_required) {
+		bsp_priv->php_grf =
+			syscon_regmap_lookup_by_phandle(dev->of_node,
+							"rockchip,php-grf");
+		if (IS_ERR(bsp_priv->php_grf)) {
+			dev_err_probe(dev, PTR_ERR(bsp_priv->php_grf),
+				      "failed to lookup rockchip,php-grf\n");
+			return ERR_CAST(bsp_priv->php_grf);
+		}
+	}
 
 	if (plat->phy_node) {
 		bsp_priv->integrated_phy = of_property_read_bool(plat->phy_node,
@@ -1921,16 +1847,16 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 
 	pm_runtime_get_sync(dev);
 
-	if (bsp_priv->integrated_phy)
-		rk_gmac_integrated_phy_powerup(bsp_priv);
+	if (bsp_priv->integrated_phy && bsp_priv->ops->integrated_phy_powerup)
+		bsp_priv->ops->integrated_phy_powerup(bsp_priv);
 
 	return 0;
 }
 
 static void rk_gmac_powerdown(struct rk_priv_data *gmac)
 {
-	if (gmac->integrated_phy)
-		rk_gmac_integrated_phy_powerdown(gmac);
+	if (gmac->integrated_phy && gmac->ops->integrated_phy_powerdown)
+		gmac->ops->integrated_phy_powerdown(gmac);
 
 	pm_runtime_put_sync(&gmac->pdev->dev);
 
@@ -1938,9 +1864,10 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac)
 	gmac_clk_enable(gmac, false);
 }
 
-static void rk_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static int rk_set_clk_tx_rate(void *bsp_priv_, struct clk *clk_tx_i,
+			      phy_interface_t interface, int speed)
 {
-	struct rk_priv_data *bsp_priv = priv;
+	struct rk_priv_data *bsp_priv = bsp_priv_;
 	struct device *dev = &bsp_priv->pdev->dev;
 
 	switch (bsp_priv->phy_iface) {
@@ -1958,6 +1885,8 @@ static void rk_fix_speed(void *priv, unsigned int speed, unsigned int mode)
 	default:
 		dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface);
 	}
+
+	return 0;
 }
 
 static int rk_gmac_probe(struct platform_device *pdev)
@@ -1984,9 +1913,13 @@ static int rk_gmac_probe(struct platform_device *pdev)
 	/* If the stmmac is not already selected as gmac4,
 	 * then make sure we fallback to gmac.
 	 */
-	if (!plat_dat->has_gmac4)
+	if (!plat_dat->has_gmac4) {
 		plat_dat->has_gmac = true;
-	plat_dat->fix_mac_speed = rk_fix_speed;
+		plat_dat->rx_fifo_size = 4096;
+		plat_dat->tx_fifo_size = 2048;
+	}
+
+	plat_dat->set_clk_tx_rate = rk_set_clk_tx_rate;
 
 	plat_dat->bsp_priv = rk_gmac_setup(pdev, plat_dat, data);
 	if (IS_ERR(plat_dat->bsp_priv))
@@ -2062,6 +1995,7 @@ static const struct of_device_id rk_gmac_dwmac_match[] = {
 	{ .compatible = "rockchip,rk3366-gmac", .data = &rk3366_ops },
 	{ .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops },
 	{ .compatible = "rockchip,rk3399-gmac", .data = &rk3399_ops },
+	{ .compatible = "rockchip,rk3528-gmac", .data = &rk3528_ops },
 	{ .compatible = "rockchip,rk3568-gmac", .data = &rk3568_ops },
 	{ .compatible = "rockchip,rk3576-gmac", .data = &rk3576_ops },
 	{ .compatible = "rockchip,rk3588-gmac", .data = &rk3588_ops },
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c
new file mode 100644
index 000000000000..221539d760bc
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NXP S32G/R GMAC glue layer
+ *
+ * Copyright 2019-2024 NXP
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/ethtool.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_mdio.h>
+#include <linux/of_address.h>
+#include <linux/phy.h>
+#include <linux/phylink.h>
+#include <linux/platform_device.h>
+#include <linux/stmmac.h>
+
+#include "stmmac_platform.h"
+
+#define GMAC_INTF_RATE_125M	125000000	/* 125MHz */
+
+/* SoC PHY interface control register */
+#define PHY_INTF_SEL_MII	0x00
+#define PHY_INTF_SEL_SGMII	0x01
+#define PHY_INTF_SEL_RGMII	0x02
+#define PHY_INTF_SEL_RMII	0x08
+
+struct s32_priv_data {
+	void __iomem *ioaddr;
+	void __iomem *ctrl_sts;
+	struct device *dev;
+	phy_interface_t *intf_mode;
+	struct clk *tx_clk;
+	struct clk *rx_clk;
+};
+
+static int s32_gmac_write_phy_intf_select(struct s32_priv_data *gmac)
+{
+	writel(PHY_INTF_SEL_RGMII, gmac->ctrl_sts);
+
+	dev_dbg(gmac->dev, "PHY mode set to %s\n", phy_modes(*gmac->intf_mode));
+
+	return 0;
+}
+
+static int s32_gmac_init(struct platform_device *pdev, void *priv)
+{
+	struct s32_priv_data *gmac = priv;
+	int ret;
+
+	/* Set initial TX interface clock */
+	ret = clk_prepare_enable(gmac->tx_clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't enable tx clock\n");
+		return ret;
+	}
+	ret = clk_set_rate(gmac->tx_clk, GMAC_INTF_RATE_125M);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't set tx clock\n");
+		goto err_tx_disable;
+	}
+
+	/* Set initial RX interface clock */
+	ret = clk_prepare_enable(gmac->rx_clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't enable rx clock\n");
+		goto err_tx_disable;
+	}
+	ret = clk_set_rate(gmac->rx_clk, GMAC_INTF_RATE_125M);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't set rx clock\n");
+		goto err_txrx_disable;
+	}
+
+	/* Set interface mode */
+	ret = s32_gmac_write_phy_intf_select(gmac);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't set PHY interface mode\n");
+		goto err_txrx_disable;
+	}
+
+	return 0;
+
+err_txrx_disable:
+	clk_disable_unprepare(gmac->rx_clk);
+err_tx_disable:
+	clk_disable_unprepare(gmac->tx_clk);
+	return ret;
+}
+
+static void s32_gmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct s32_priv_data *gmac = priv;
+
+	clk_disable_unprepare(gmac->tx_clk);
+	clk_disable_unprepare(gmac->rx_clk);
+}
+
+static int s32_dwmac_probe(struct platform_device *pdev)
+{
+	struct plat_stmmacenet_data *plat;
+	struct device *dev = &pdev->dev;
+	struct stmmac_resources res;
+	struct s32_priv_data *gmac;
+	int ret;
+
+	gmac = devm_kzalloc(&pdev->dev, sizeof(*gmac), GFP_KERNEL);
+	if (!gmac)
+		return -ENOMEM;
+
+	gmac->dev = &pdev->dev;
+
+	ret = stmmac_get_platform_resources(pdev, &res);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "Failed to get platform resources\n");
+
+	plat = devm_stmmac_probe_config_dt(pdev, res.mac);
+	if (IS_ERR(plat))
+		return dev_err_probe(dev, PTR_ERR(plat),
+				     "dt configuration failed\n");
+
+	/* PHY interface mode control reg */
+	gmac->ctrl_sts = devm_platform_get_and_ioremap_resource(pdev, 1, NULL);
+	if (IS_ERR(gmac->ctrl_sts))
+		return dev_err_probe(dev, PTR_ERR(gmac->ctrl_sts),
+				     "S32CC config region is missing\n");
+
+	/* tx clock */
+	gmac->tx_clk = devm_clk_get(&pdev->dev, "tx");
+	if (IS_ERR(gmac->tx_clk))
+		return dev_err_probe(dev, PTR_ERR(gmac->tx_clk),
+				     "tx clock not found\n");
+
+	/* rx clock */
+	gmac->rx_clk = devm_clk_get(&pdev->dev, "rx");
+	if (IS_ERR(gmac->rx_clk))
+		return dev_err_probe(dev, PTR_ERR(gmac->rx_clk),
+				     "rx clock not found\n");
+
+	gmac->intf_mode = &plat->phy_interface;
+	gmac->ioaddr = res.addr;
+
+	/* S32CC core feature set */
+	plat->has_gmac4 = true;
+	plat->pmt = 1;
+	plat->flags |= STMMAC_FLAG_SPH_DISABLE;
+	plat->rx_fifo_size = 20480;
+	plat->tx_fifo_size = 20480;
+
+	plat->init = s32_gmac_init;
+	plat->exit = s32_gmac_exit;
+
+	plat->clk_tx_i = gmac->tx_clk;
+	plat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
+
+	plat->bsp_priv = gmac;
+
+	return stmmac_pltfr_probe(pdev, plat, &res);
+}
+
+static const struct of_device_id s32_dwmac_match[] = {
+	{ .compatible = "nxp,s32g2-dwmac" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, s32_dwmac_match);
+
+static struct platform_driver s32_dwmac_driver = {
+	.probe = s32_dwmac_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name = "s32-dwmac",
+		.pm = &stmmac_pltfr_pm_ops,
+		.of_match_table = s32_dwmac_match,
+	},
+};
+module_platform_driver(s32_dwmac_driver);
+
+MODULE_AUTHOR("Jan Petrous (OSS) <jan.petrous@oss.nxp.com>");
+MODULE_DESCRIPTION("NXP S32G/R common chassis GMAC driver");
+MODULE_LICENSE("GPL");
+
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 16020b72dec8..72b50f6d72f4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -50,6 +50,7 @@ struct socfpga_dwmac {
 	u32	reg_offset;
 	u32	reg_shift;
 	struct	device *dev;
+	struct plat_stmmacenet_data *plat_dat;
 	struct regmap *sys_mgr_base_addr;
 	struct reset_control *stmmac_rst;
 	struct reset_control *stmmac_ocp_rst;
@@ -58,17 +59,15 @@ struct socfpga_dwmac {
 	void __iomem *sgmii_adapter_base;
 	bool f2h_ptp_ref_clk;
 	const struct socfpga_dwmac_ops *ops;
-	struct mdio_device *pcs_mdiodev;
 };
 
-static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void socfpga_dwmac_fix_mac_speed(void *bsp_priv, int speed,
+					unsigned int mode)
 {
-	struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv;
+	struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)bsp_priv;
+	struct stmmac_priv *priv = netdev_priv(dev_get_drvdata(dwmac->dev));
 	void __iomem *splitter_base = dwmac->splitter_base;
 	void __iomem *sgmii_adapter_base = dwmac->sgmii_adapter_base;
-	struct device *dev = dwmac->dev;
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct phy_device *phy_dev = ndev->phydev;
 	u32 val;
 
 	if (sgmii_adapter_base)
@@ -95,7 +94,9 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned
 		writel(val, splitter_base + EMAC_SPLITTER_CTRL_REG);
 	}
 
-	if (phy_dev && sgmii_adapter_base)
+	if ((priv->plat->phy_interface == PHY_INTERFACE_MODE_SGMII ||
+	     priv->plat->phy_interface == PHY_INTERFACE_MODE_1000BASEX) &&
+	     sgmii_adapter_base)
 		writew(SGMII_ADAPTER_ENABLE,
 		       sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG);
 }
@@ -233,10 +234,7 @@ err_node_put:
 
 static int socfpga_get_plat_phymode(struct socfpga_dwmac *dwmac)
 {
-	struct net_device *ndev = dev_get_drvdata(dwmac->dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	return priv->plat->mac_interface;
+	return dwmac->plat_dat->mac_interface;
 }
 
 static void socfpga_sgmii_config(struct socfpga_dwmac *dwmac, bool enable)
@@ -258,6 +256,7 @@ static int socfpga_set_phy_mode_common(int phymode, u32 *val)
 	case PHY_INTERFACE_MODE_MII:
 	case PHY_INTERFACE_MODE_GMII:
 	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_1000BASEX:
 		*val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
 		break;
 	case PHY_INTERFACE_MODE_RMII:
@@ -435,6 +434,13 @@ static struct phylink_pcs *socfpga_dwmac_select_pcs(struct stmmac_priv *priv,
 	return priv->hw->phylink_pcs;
 }
 
+static int socfpga_dwmac_init(struct platform_device *pdev, void *bsp_priv)
+{
+	struct socfpga_dwmac *dwmac = bsp_priv;
+
+	return dwmac->ops->set_phy_mode(dwmac);
+}
+
 static int socfpga_dwmac_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat_dat;
@@ -442,8 +448,6 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	struct device		*dev = &pdev->dev;
 	int			ret;
 	struct socfpga_dwmac	*dwmac;
-	struct net_device	*ndev;
-	struct stmmac_priv	*stpriv;
 	const struct socfpga_dwmac_ops *ops;
 
 	ops = device_get_match_data(&pdev->dev);
@@ -479,9 +483,17 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* The socfpga driver needs to control the stmmac reset to set the phy
+	 * mode. Create a copy of the core reset handle so it can be used by
+	 * the driver later.
+	 */
+	dwmac->stmmac_rst = plat_dat->stmmac_rst;
 	dwmac->ops = ops;
+	dwmac->plat_dat = plat_dat;
+
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed;
+	plat_dat->init = socfpga_dwmac_init;
 	plat_dat->pcs_init = socfpga_dwmac_pcs_init;
 	plat_dat->pcs_exit = socfpga_dwmac_pcs_exit;
 	plat_dat->select_pcs = socfpga_dwmac_select_pcs;
@@ -489,85 +501,9 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 
 	plat_dat->riwt_off = 1;
 
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		return ret;
-
-	ndev = platform_get_drvdata(pdev);
-	stpriv = netdev_priv(ndev);
-
-	/* The socfpga driver needs to control the stmmac reset to set the phy
-	 * mode. Create a copy of the core reset handle so it can be used by
-	 * the driver later.
-	 */
-	dwmac->stmmac_rst = stpriv->plat->stmmac_rst;
-
-	ret = ops->set_phy_mode(dwmac);
-	if (ret)
-		goto err_dvr_remove;
-
-	return 0;
-
-err_dvr_remove:
-	stmmac_dvr_remove(&pdev->dev);
-
-	return ret;
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int socfpga_dwmac_resume(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-	struct socfpga_dwmac *dwmac_priv = get_stmmac_bsp_priv(dev);
-
-	dwmac_priv->ops->set_phy_mode(priv->plat->bsp_priv);
-
-	/* Before the enet controller is suspended, the phy is suspended.
-	 * This causes the phy clock to be gated. The enet controller is
-	 * resumed before the phy, so the clock is still gated "off" when
-	 * the enet controller is resumed. This code makes sure the phy
-	 * is "resumed" before reinitializing the enet controller since
-	 * the enet controller depends on an active phy clock to complete
-	 * a DMA reset. A DMA reset will "time out" if executed
-	 * with no phy clock input on the Synopsys enet controller.
-	 * Verified through Synopsys Case #8000711656.
-	 *
-	 * Note that the phy clock is also gated when the phy is isolated.
-	 * Phy "suspend" and "isolate" controls are located in phy basic
-	 * control register 0, and can be modified by the phy driver
-	 * framework.
-	 */
-	if (ndev->phydev)
-		phy_resume(ndev->phydev);
-
-	return stmmac_resume(dev);
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static int __maybe_unused socfpga_dwmac_runtime_suspend(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	stmmac_bus_clks_config(priv, false);
-
-	return 0;
-}
-
-static int __maybe_unused socfpga_dwmac_runtime_resume(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	return stmmac_bus_clks_config(priv, true);
-}
-
-static const struct dev_pm_ops socfpga_dwmac_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(stmmac_suspend, socfpga_dwmac_resume)
-	SET_RUNTIME_PM_OPS(socfpga_dwmac_runtime_suspend, socfpga_dwmac_runtime_resume, NULL)
-};
-
 static const struct socfpga_dwmac_ops socfpga_gen5_ops = {
 	.set_phy_mode = socfpga_gen5_set_phy_mode,
 };
@@ -585,10 +521,9 @@ MODULE_DEVICE_TABLE(of, socfpga_dwmac_match);
 
 static struct platform_driver socfpga_dwmac_driver = {
 	.probe  = socfpga_dwmac_probe,
-	.remove = stmmac_pltfr_remove,
 	.driver = {
 		.name           = "socfpga-dwmac",
-		.pm		= &socfpga_dwmac_pm_ops,
+		.pm		= &stmmac_pltfr_pm_ops,
 		.of_match_table = socfpga_dwmac_match,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c
new file mode 100644
index 000000000000..3303784cbbf8
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Sophgo DWMAC platform driver
+ *
+ * Copyright (C) 2024 Inochi Amaoto <inochiama@gmail.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
+
+#include "stmmac_platform.h"
+
+static int sophgo_sg2044_dwmac_init(struct platform_device *pdev,
+				    struct plat_stmmacenet_data *plat_dat,
+				    struct stmmac_resources *stmmac_res)
+{
+	plat_dat->clk_tx_i = devm_clk_get_enabled(&pdev->dev, "tx");
+	if (IS_ERR(plat_dat->clk_tx_i))
+		return dev_err_probe(&pdev->dev, PTR_ERR(plat_dat->clk_tx_i),
+				     "failed to get tx clock\n");
+
+	plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE;
+	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
+	plat_dat->multicast_filter_bins = 0;
+	plat_dat->unicast_filter_entries = 1;
+
+	return 0;
+}
+
+static int sophgo_dwmac_probe(struct platform_device *pdev)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to get platform resources\n");
+
+	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return dev_err_probe(dev, PTR_ERR(plat_dat),
+				     "failed to parse DT parameters\n");
+
+	ret = sophgo_sg2044_dwmac_init(pdev, plat_dat, &stmmac_res);
+	if (ret)
+		return ret;
+
+	return stmmac_dvr_probe(dev, plat_dat, &stmmac_res);
+}
+
+static const struct of_device_id sophgo_dwmac_match[] = {
+	{ .compatible = "sophgo,sg2044-dwmac" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sophgo_dwmac_match);
+
+static struct platform_driver sophgo_dwmac_driver = {
+	.probe  = sophgo_dwmac_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name = "sophgo-dwmac",
+		.pm = &stmmac_pltfr_pm_ops,
+		.of_match_table = sophgo_dwmac_match,
+	},
+};
+module_platform_driver(sophgo_dwmac_driver);
+
+MODULE_AUTHOR("Inochi Amaoto <inochiama@gmail.com>");
+MODULE_DESCRIPTION("Sophgo DWMAC platform driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
index 421666279dd3..2013d7477eb7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
@@ -27,38 +27,9 @@ struct starfive_dwmac_data {
 
 struct starfive_dwmac {
 	struct device *dev;
-	struct clk *clk_tx;
 	const struct starfive_dwmac_data *data;
 };
 
-static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
-{
-	struct starfive_dwmac *dwmac = priv;
-	unsigned long rate;
-	int err;
-
-	rate = clk_get_rate(dwmac->clk_tx);
-
-	switch (speed) {
-	case SPEED_1000:
-		rate = 125000000;
-		break;
-	case SPEED_100:
-		rate = 25000000;
-		break;
-	case SPEED_10:
-		rate = 2500000;
-		break;
-	default:
-		dev_err(dwmac->dev, "invalid speed %u\n", speed);
-		break;
-	}
-
-	err = clk_set_rate(dwmac->clk_tx, rate);
-	if (err)
-		dev_err(dwmac->dev, "failed to set tx rate %lu\n", rate);
-}
-
 static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat)
 {
 	struct starfive_dwmac *dwmac = plat_dat->bsp_priv;
@@ -133,9 +104,9 @@ static int starfive_dwmac_probe(struct platform_device *pdev)
 
 	dwmac->data = device_get_match_data(&pdev->dev);
 
-	dwmac->clk_tx = devm_clk_get_enabled(&pdev->dev, "tx");
-	if (IS_ERR(dwmac->clk_tx))
-		return dev_err_probe(&pdev->dev, PTR_ERR(dwmac->clk_tx),
+	plat_dat->clk_tx_i = devm_clk_get_enabled(&pdev->dev, "tx");
+	if (IS_ERR(plat_dat->clk_tx_i))
+		return dev_err_probe(&pdev->dev, PTR_ERR(plat_dat->clk_tx_i),
 				     "error getting tx clock\n");
 
 	clk_gtx = devm_clk_get_enabled(&pdev->dev, "gtx");
@@ -150,9 +121,10 @@ static int starfive_dwmac_probe(struct platform_device *pdev)
 	 * internally, because rgmii_rxin will be adaptively adjusted.
 	 */
 	if (!device_property_read_bool(&pdev->dev, "starfive,tx-use-rgmii-clk"))
-		plat_dat->fix_mac_speed = starfive_dwmac_fix_mac_speed;
+		plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
 
 	dwmac->dev = &pdev->dev;
+	plat_dat->flags |= STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP;
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->dma_cfg->dche = true;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index a6ff02d905a9..53d5ce1f6dc6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -21,17 +21,9 @@
 
 #include "stmmac_platform.h"
 
-#define DWMAC_125MHZ	125000000
 #define DWMAC_50MHZ	50000000
-#define DWMAC_25MHZ	25000000
-#define DWMAC_2_5MHZ	2500000
 
-#define IS_PHY_IF_MODE_RGMII(iface)	(iface == PHY_INTERFACE_MODE_RGMII || \
-			iface == PHY_INTERFACE_MODE_RGMII_ID || \
-			iface == PHY_INTERFACE_MODE_RGMII_RXID || \
-			iface == PHY_INTERFACE_MODE_RGMII_TXID)
-
-#define IS_PHY_IF_MODE_GBIT(iface)	(IS_PHY_IF_MODE_RGMII(iface) || \
+#define IS_PHY_IF_MODE_GBIT(iface)	(phy_interface_mode_is_rgmii(iface) || \
 					 iface == PHY_INTERFACE_MODE_GMII)
 
 /* STiH4xx register definitions (STiH407/STiH410 families)
@@ -102,12 +94,12 @@ struct sti_dwmac {
 	int clk_sel_reg;	/* GMAC ext clk selection register */
 	struct regmap *regmap;
 	bool gmac_en;
-	u32 speed;
-	void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode);
+	int speed;
+	void (*fix_retime_src)(void *priv, int speed, unsigned int mode);
 };
 
 struct sti_dwmac_of_data {
-	void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode);
+	void (*fix_retime_src)(void *priv, int speed, unsigned int mode);
 };
 
 static u32 phy_intf_sels[] = {
@@ -135,12 +127,12 @@ static u32 stih4xx_tx_retime_val[] = {
 				 | STIH4XX_ETH_SEL_INTERNAL_NOTEXT_PHYCLK,
 };
 
-static void stih4xx_fix_retime_src(void *priv, u32 spd, unsigned int mode)
+static void stih4xx_fix_retime_src(void *priv, int spd, unsigned int mode)
 {
 	struct sti_dwmac *dwmac = priv;
 	u32 src = dwmac->tx_retime_src;
 	u32 reg = dwmac->ctrl_reg;
-	u32 freq = 0;
+	long freq = 0;
 
 	if (dwmac->interface == PHY_INTERFACE_MODE_MII) {
 		src = TX_RETIME_SRC_TXCLK;
@@ -151,21 +143,16 @@ static void stih4xx_fix_retime_src(void *priv, u32 spd, unsigned int mode)
 			src = TX_RETIME_SRC_CLKGEN;
 			freq = DWMAC_50MHZ;
 		}
-	} else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) {
+	} else if (phy_interface_mode_is_rgmii(dwmac->interface)) {
 		/* On GiGa clk source can be either ext or from clkgen */
-		if (spd == SPEED_1000) {
-			freq = DWMAC_125MHZ;
-		} else {
+		freq = rgmii_clock(spd);
+
+		if (spd != SPEED_1000 && freq > 0)
 			/* Switch to clkgen for these speeds */
 			src = TX_RETIME_SRC_CLKGEN;
-			if (spd == SPEED_100)
-				freq = DWMAC_25MHZ;
-			else if (spd == SPEED_10)
-				freq = DWMAC_2_5MHZ;
-		}
 	}
 
-	if (src == TX_RETIME_SRC_CLKGEN && freq)
+	if (src == TX_RETIME_SRC_CLKGEN && freq > 0)
 		clk_set_rate(dwmac->clk, freq);
 
 	regmap_update_bits(dwmac->regmap, reg, STIH4XX_RETIME_SRC_MASK,
@@ -193,7 +180,8 @@ static int sti_dwmac_set_mode(struct sti_dwmac *dwmac)
 }
 
 static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
-				struct platform_device *pdev)
+				struct platform_device *pdev,
+				struct plat_stmmacenet_data *plat_dat)
 {
 	struct resource *res;
 	struct device *dev = &pdev->dev;
@@ -207,22 +195,12 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
 	if (res)
 		dwmac->clk_sel_reg = res->start;
 
-	regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon");
+	regmap = syscon_regmap_lookup_by_phandle_args(np, "st,syscon",
+						      1, &dwmac->ctrl_reg);
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
 
-	err = of_property_read_u32_index(np, "st,syscon", 1, &dwmac->ctrl_reg);
-	if (err) {
-		dev_err(dev, "Can't get sysconfig ctrl offset (%d)\n", err);
-		return err;
-	}
-
-	err = of_get_phy_mode(np, &dwmac->interface);
-	if (err && err != -ENODEV) {
-		dev_err(dev, "Can't get phy-mode\n");
-		return err;
-	}
-
+	dwmac->interface = plat_dat->phy_interface;
 	dwmac->regmap = regmap;
 	dwmac->gmac_en = of_property_read_bool(np, "st,gmac_en");
 	dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk");
@@ -255,6 +233,29 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
 	return 0;
 }
 
+static int sti_dwmac_init(struct platform_device *pdev, void *bsp_priv)
+{
+	struct sti_dwmac *dwmac = bsp_priv;
+	int ret;
+
+	ret = clk_prepare_enable(dwmac->clk);
+	if (ret)
+		return ret;
+
+	ret = sti_dwmac_set_mode(dwmac);
+	if (ret)
+		clk_disable_unprepare(dwmac->clk);
+
+	return ret;
+}
+
+static void sti_dwmac_exit(struct platform_device *pdev, void *bsp_priv)
+{
+	struct sti_dwmac *dwmac = bsp_priv;
+
+	clk_disable_unprepare(dwmac->clk);
+}
+
 static int sti_dwmac_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat_dat;
@@ -281,7 +282,7 @@ static int sti_dwmac_probe(struct platform_device *pdev)
 	if (!dwmac)
 		return -ENOMEM;
 
-	ret = sti_dwmac_parse_data(dwmac, pdev);
+	ret = sti_dwmac_parse_data(dwmac, pdev, plat_dat);
 	if (ret) {
 		dev_err(&pdev->dev, "Unable to parse OF data\n");
 		return ret;
@@ -291,61 +292,12 @@ static int sti_dwmac_probe(struct platform_device *pdev)
 
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->fix_mac_speed = data->fix_retime_src;
+	plat_dat->init = sti_dwmac_init;
+	plat_dat->exit = sti_dwmac_exit;
 
-	ret = clk_prepare_enable(dwmac->clk);
-	if (ret)
-		return ret;
-
-	ret = sti_dwmac_set_mode(dwmac);
-	if (ret)
-		goto disable_clk;
-
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		goto disable_clk;
-
-	return 0;
-
-disable_clk:
-	clk_disable_unprepare(dwmac->clk);
-
-	return ret;
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
-static void sti_dwmac_remove(struct platform_device *pdev)
-{
-	struct sti_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev);
-
-	stmmac_dvr_remove(&pdev->dev);
-
-	clk_disable_unprepare(dwmac->clk);
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int sti_dwmac_suspend(struct device *dev)
-{
-	struct sti_dwmac *dwmac = get_stmmac_bsp_priv(dev);
-	int ret = stmmac_suspend(dev);
-
-	clk_disable_unprepare(dwmac->clk);
-
-	return ret;
-}
-
-static int sti_dwmac_resume(struct device *dev)
-{
-	struct sti_dwmac *dwmac = get_stmmac_bsp_priv(dev);
-
-	clk_prepare_enable(dwmac->clk);
-	sti_dwmac_set_mode(dwmac);
-
-	return stmmac_resume(dev);
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static SIMPLE_DEV_PM_OPS(sti_dwmac_pm_ops, sti_dwmac_suspend,
-					   sti_dwmac_resume);
-
 static const struct sti_dwmac_of_data stih4xx_dwmac_data = {
 	.fix_retime_src = stih4xx_fix_retime_src,
 };
@@ -358,10 +310,9 @@ MODULE_DEVICE_TABLE(of, sti_dwmac_match);
 
 static struct platform_driver sti_dwmac_driver = {
 	.probe  = sti_dwmac_probe,
-	.remove = sti_dwmac_remove,
 	.driver = {
 		.name           = "sti-dwmac",
-		.pm		= &sti_dwmac_pm_ops,
+		.pm		= &stmmac_pltfr_pm_ops,
 		.of_match_table = sti_dwmac_match,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index 1e8bac665cc9..1eb16eec9c0d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -119,7 +119,7 @@ struct stm32_ops {
 	u32 syscfg_clr_off;
 };
 
-static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac, bool resume)
+static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac)
 {
 	int ret;
 
@@ -127,11 +127,9 @@ static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac, bool resume)
 	if (ret)
 		goto err_clk_tx;
 
-	if (!dwmac->ops->clk_rx_enable_in_suspend || !resume) {
-		ret = clk_prepare_enable(dwmac->clk_rx);
-		if (ret)
-			goto err_clk_rx;
-	}
+	ret = clk_prepare_enable(dwmac->clk_rx);
+	if (ret)
+		goto err_clk_rx;
 
 	ret = clk_prepare_enable(dwmac->syscfg_clk);
 	if (ret)
@@ -148,15 +146,14 @@ static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac, bool resume)
 err_clk_eth_ck:
 	clk_disable_unprepare(dwmac->syscfg_clk);
 err_syscfg_clk:
-	if (!dwmac->ops->clk_rx_enable_in_suspend || !resume)
-		clk_disable_unprepare(dwmac->clk_rx);
+	clk_disable_unprepare(dwmac->clk_rx);
 err_clk_rx:
 	clk_disable_unprepare(dwmac->clk_tx);
 err_clk_tx:
 	return ret;
 }
 
-static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat, bool resume)
+static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat)
 {
 	struct stm32_dwmac *dwmac = plat_dat->bsp_priv;
 	int ret;
@@ -167,7 +164,7 @@ static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat, bool resume)
 			return ret;
 	}
 
-	return stm32_dwmac_clk_enable(dwmac, resume);
+	return stm32_dwmac_clk_enable(dwmac);
 }
 
 static int stm32mp1_select_ethck_external(struct plat_stmmacenet_data *plat_dat)
@@ -382,12 +379,10 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat)
 				 SYSCFG_MCU_ETH_MASK, val << 23);
 }
 
-static void stm32_dwmac_clk_disable(struct stm32_dwmac *dwmac, bool suspend)
+static void stm32_dwmac_clk_disable(struct stm32_dwmac *dwmac)
 {
 	clk_disable_unprepare(dwmac->clk_tx);
-	if (!dwmac->ops->clk_rx_enable_in_suspend || !suspend)
-		clk_disable_unprepare(dwmac->clk_rx);
-
+	clk_disable_unprepare(dwmac->clk_rx);
 	clk_disable_unprepare(dwmac->syscfg_clk);
 	if (dwmac->enable_eth_ck)
 		clk_disable_unprepare(dwmac->clk_eth_ck);
@@ -419,16 +414,11 @@ static int stm32_dwmac_parse_data(struct stm32_dwmac *dwmac,
 	}
 
 	/* Get mode register */
-	dwmac->regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon");
+	dwmac->regmap = syscon_regmap_lookup_by_phandle_args(np, "st,syscon",
+							     1, &dwmac->mode_reg);
 	if (IS_ERR(dwmac->regmap))
 		return PTR_ERR(dwmac->regmap);
 
-	err = of_property_read_u32_index(np, "st,syscon", 1, &dwmac->mode_reg);
-	if (err) {
-		dev_err(dev, "Can't get sysconfig mode offset (%d)\n", err);
-		return err;
-	}
-
 	if (dwmac->ops->is_mp2)
 		return 0;
 
@@ -543,20 +533,35 @@ static int stm32_dwmac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	plat_dat->flags |= STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP;
 	plat_dat->bsp_priv = dwmac;
 
-	ret = stm32_dwmac_init(plat_dat, false);
+	ret = stm32_dwmac_init(plat_dat);
 	if (ret)
 		return ret;
 
+	/* If this platform requires the clock to be running in suspend,
+	 * prepare and enable the receive clock an additional time to keep
+	 * it running.
+	 */
+	if (dwmac->ops->clk_rx_enable_in_suspend) {
+		ret = clk_prepare_enable(dwmac->clk_rx);
+		if (ret)
+			goto err_clk_disable;
+	}
+
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
-		goto err_clk_disable;
+		goto err_clk_disable_suspend;
 
 	return 0;
 
+err_clk_disable_suspend:
+	if (dwmac->ops->clk_rx_enable_in_suspend)
+		clk_disable_unprepare(dwmac->clk_rx);
+
 err_clk_disable:
-	stm32_dwmac_clk_disable(dwmac, false);
+	stm32_dwmac_clk_disable(dwmac);
 
 	return ret;
 }
@@ -569,7 +574,15 @@ static void stm32_dwmac_remove(struct platform_device *pdev)
 
 	stmmac_dvr_remove(&pdev->dev);
 
-	stm32_dwmac_clk_disable(dwmac, false);
+	/* If this platform requires the clock to be running in suspend,
+	 * we need to disable and unprepare the receive clock an additional
+	 * time to balance the extra clk_prepare_enable() in the probe
+	 * function.
+	 */
+	if (dwmac->ops->clk_rx_enable_in_suspend)
+		clk_disable_unprepare(dwmac->clk_rx);
+
+	stm32_dwmac_clk_disable(dwmac);
 
 	if (dwmac->irq_pwr_wakeup >= 0) {
 		dev_pm_clear_wake_irq(&pdev->dev);
@@ -600,7 +613,7 @@ static int stm32_dwmac_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
-	stm32_dwmac_clk_disable(dwmac, true);
+	stm32_dwmac_clk_disable(dwmac);
 
 	if (dwmac->ops->suspend)
 		ret = dwmac->ops->suspend(dwmac);
@@ -618,7 +631,7 @@ static int stm32_dwmac_resume(struct device *dev)
 	if (dwmac->ops->resume)
 		dwmac->ops->resume(dwmac);
 
-	ret = stm32_dwmac_init(priv->plat, true);
+	ret = stm32_dwmac_init(priv->plat);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 4b7b2582a120..2796dc426943 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -964,7 +964,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev,
 		/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
 		 * address. No need to mask it again.
 		 */
-		reg |= 1 << H3_EPHY_ADDR_SHIFT;
+		reg |= ret << H3_EPHY_ADDR_SHIFT;
 	} else {
 		/* For SoCs without internal PHY the PHY selection bit should be
 		 * set to 0 (external PHY).
@@ -1155,11 +1155,10 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	struct stmmac_resources stmmac_res;
 	struct sunxi_priv_data *gmac;
 	struct device *dev = &pdev->dev;
-	phy_interface_t interface;
-	int ret;
 	struct stmmac_priv *priv;
 	struct net_device *ndev;
 	struct regmap *regmap;
+	int ret;
 
 	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
 	if (ret)
@@ -1219,10 +1218,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = of_get_phy_mode(dev->of_node, &interface);
-	if (ret)
-		return -EINVAL;
-
 	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
@@ -1230,7 +1225,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	/* platform data specifying hardware features and callbacks.
 	 * hardware features were copied from Allwinner drivers.
 	 */
-	plat_dat->mac_interface = interface;
 	plat_dat->rx_coe = STMMAC_RX_COE_TYPE2;
 	plat_dat->tx_coe = 1;
 	plat_dat->flags |= STMMAC_FLAG_HAS_SUN8I;
@@ -1245,14 +1239,10 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = sun8i_dwmac_init(pdev, plat_dat->bsp_priv);
+	ret = stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 	if (ret)
 		goto dwmac_syscon;
 
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		goto dwmac_exit;
-
 	ndev = dev_get_drvdata(&pdev->dev);
 	priv = netdev_priv(ndev);
 
@@ -1289,9 +1279,7 @@ dwmac_mux:
 	clk_put(gmac->ephy_clk);
 dwmac_remove:
 	pm_runtime_put_noidle(&pdev->dev);
-	stmmac_dvr_remove(&pdev->dev);
-dwmac_exit:
-	sun8i_dwmac_exit(pdev, gmac);
+	stmmac_pltfr_remove(pdev);
 dwmac_syscon:
 	sun8i_dwmac_unset_syscon(gmac);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 9ae318436c4a..1eadcf5d1ad6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -72,28 +72,28 @@ static void sun7i_gmac_exit(struct platform_device *pdev, void *priv)
 		regulator_disable(gmac->regulator);
 }
 
-static void sun7i_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static int sun7i_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+				 phy_interface_t interface, int speed)
 {
-	struct sunxi_priv_data *gmac = priv;
-
-	/* only GMII mode requires us to reconfigure the clock lines */
-	if (gmac->interface != PHY_INTERFACE_MODE_GMII)
-		return;
-
-	if (gmac->clk_enabled) {
-		clk_disable(gmac->tx_clk);
-		gmac->clk_enabled = 0;
-	}
-	clk_unprepare(gmac->tx_clk);
-
-	if (speed == 1000) {
-		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE);
-		clk_prepare_enable(gmac->tx_clk);
-		gmac->clk_enabled = 1;
-	} else {
-		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_MII_RATE);
-		clk_prepare(gmac->tx_clk);
+	struct sunxi_priv_data *gmac = bsp_priv;
+
+	if (interface == PHY_INTERFACE_MODE_GMII) {
+		if (gmac->clk_enabled) {
+			clk_disable(gmac->tx_clk);
+			gmac->clk_enabled = 0;
+		}
+		clk_unprepare(gmac->tx_clk);
+
+		if (speed == 1000) {
+			clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE);
+			clk_prepare_enable(gmac->tx_clk);
+			gmac->clk_enabled = 1;
+		} else {
+			clk_set_rate(gmac->tx_clk, SUN7I_GMAC_MII_RATE);
+			clk_prepare(gmac->tx_clk);
+		}
 	}
+	return 0;
 }
 
 static int sun7i_gmac_probe(struct platform_device *pdev)
@@ -116,11 +116,7 @@ static int sun7i_gmac_probe(struct platform_device *pdev)
 	if (!gmac)
 		return -ENOMEM;
 
-	ret = of_get_phy_mode(dev->of_node, &gmac->interface);
-	if (ret && ret != -ENODEV) {
-		dev_err(dev, "Can't get phy-mode\n");
-		return ret;
-	}
+	gmac->interface = plat_dat->phy_interface;
 
 	gmac->tx_clk = devm_clk_get(dev, "allwinner_gmac_tx");
 	if (IS_ERR(gmac->tx_clk)) {
@@ -144,24 +140,11 @@ static int sun7i_gmac_probe(struct platform_device *pdev)
 	plat_dat->bsp_priv = gmac;
 	plat_dat->init = sun7i_gmac_init;
 	plat_dat->exit = sun7i_gmac_exit;
-	plat_dat->fix_mac_speed = sun7i_fix_speed;
+	plat_dat->set_clk_tx_rate = sun7i_set_clk_tx_rate;
 	plat_dat->tx_fifo_size = 4096;
 	plat_dat->rx_fifo_size = 16384;
 
-	ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv);
-	if (ret)
-		return ret;
-
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		goto err_gmac_exit;
-
-	return 0;
-
-err_gmac_exit:
-	sun7i_gmac_exit(pdev, plat_dat->bsp_priv);
-
-	return ret;
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
 static const struct of_device_id sun7i_dwmac_match[] = {
@@ -172,7 +155,6 @@ MODULE_DEVICE_TABLE(of, sun7i_dwmac_match);
 
 static struct platform_driver sun7i_dwmac_driver = {
 	.probe  = sun7i_gmac_probe,
-	.remove = stmmac_pltfr_remove,
 	.driver = {
 		.name           = "sun7i-dwmac",
 		.pm		= &stmmac_pltfr_pm_ops,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
index 3827997d2132..dc903b846b1b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/iommu.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/module.h>
@@ -19,6 +20,8 @@ struct tegra_mgbe {
 	struct reset_control *rst_mac;
 	struct reset_control *rst_pcs;
 
+	u32 iommu_sid;
+
 	void __iomem *hv;
 	void __iomem *regs;
 	void __iomem *xpcs;
@@ -50,7 +53,6 @@ struct tegra_mgbe {
 #define MGBE_WRAP_COMMON_INTR_ENABLE	0x8704
 #define MAC_SBD_INTR			BIT(2)
 #define MGBE_WRAP_AXI_ASID0_CTRL	0x8400
-#define MGBE_SID			0x6
 
 static int __maybe_unused tegra_mgbe_suspend(struct device *dev)
 {
@@ -84,7 +86,7 @@ static int __maybe_unused tegra_mgbe_resume(struct device *dev)
 	writel(MAC_SBD_INTR, mgbe->regs + MGBE_WRAP_COMMON_INTR_ENABLE);
 
 	/* Program SID */
-	writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL);
+	writel(mgbe->iommu_sid, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL);
 
 	value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_STATUS);
 	if ((value & XPCS_WRAP_UPHY_STATUS_TX_P_UP) == 0) {
@@ -241,6 +243,12 @@ static int tegra_mgbe_probe(struct platform_device *pdev)
 	if (IS_ERR(mgbe->xpcs))
 		return PTR_ERR(mgbe->xpcs);
 
+	/* get controller's stream id from iommu property in device tree */
+	if (!tegra_dev_iommu_get_stream_id(mgbe->dev, &mgbe->iommu_sid)) {
+		dev_err(mgbe->dev, "failed to get iommu stream id\n");
+		return -EINVAL;
+	}
+
 	res.addr = mgbe->regs;
 	res.irq = irq;
 
@@ -346,7 +354,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev)
 	writel(MAC_SBD_INTR, mgbe->regs + MGBE_WRAP_COMMON_INTR_ENABLE);
 
 	/* Program SID */
-	writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL);
+	writel(mgbe->iommu_sid, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL);
 
 	plat->flags |= STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
index dce84ed184e9..c72ee759aae5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
@@ -45,9 +45,6 @@
 #define  TXCLK_DIR_OUTPUT		FIELD_PREP(TXCLK_DIR_MASK, 0)
 #define  TXCLK_DIR_INPUT		FIELD_PREP(TXCLK_DIR_MASK, 1)
 
-#define GMAC_GMII_RGMII_RATE	125000000
-#define GMAC_MII_RATE		25000000
-
 struct thead_dwmac {
 	struct plat_stmmacenet_data *plat;
 	void __iomem *apb_base;
@@ -104,11 +101,13 @@ static int thead_dwmac_set_txclk_dir(struct plat_stmmacenet_data *plat)
 	return 0;
 }
 
-static void thead_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static int thead_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+				 phy_interface_t interface, int speed)
 {
+	struct thead_dwmac *dwmac = bsp_priv;
 	struct plat_stmmacenet_data *plat;
-	struct thead_dwmac *dwmac = priv;
 	unsigned long rate;
+	long tx_rate;
 	u32 div, reg;
 
 	plat = dwmac->plat;
@@ -116,44 +115,37 @@ static void thead_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int m
 	switch (plat->mac_interface) {
 	/* For MII, rxc/txc is provided by phy */
 	case PHY_INTERFACE_MODE_MII:
-		return;
+		return 0;
 
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		rate = clk_get_rate(plat->stmmac_clk);
-		if (!rate || rate % GMAC_GMII_RGMII_RATE != 0 ||
-		    rate % GMAC_MII_RATE != 0) {
-			dev_err(dwmac->dev, "invalid gmac rate %ld\n", rate);
-			return;
-		}
 
 		writel(0, dwmac->apb_base + GMAC_PLLCLK_DIV);
 
-		switch (speed) {
-		case SPEED_1000:
-			div = rate / GMAC_GMII_RGMII_RATE;
-			break;
-		case SPEED_100:
-			div = rate / GMAC_MII_RATE;
-			break;
-		case SPEED_10:
-			div = rate * 10 / GMAC_MII_RATE;
-			break;
-		default:
-			dev_err(dwmac->dev, "invalid speed %u\n", speed);
-			return;
+		tx_rate = rgmii_clock(speed);
+		if (tx_rate < 0) {
+			dev_err(dwmac->dev, "invalid speed %d\n", speed);
+			return tx_rate;
+		}
+
+		div = rate / tx_rate;
+		if (rate != tx_rate * div) {
+			dev_err(dwmac->dev, "invalid gmac rate %lu\n", rate);
+			return -EINVAL;
 		}
 
 		reg = FIELD_PREP(GMAC_PLLCLK_DIV_EN, 1) |
 		      FIELD_PREP(GMAC_PLLCLK_DIV_NUM, div);
 		writel(reg, dwmac->apb_base + GMAC_PLLCLK_DIV);
-		break;
+		return 0;
+
 	default:
 		dev_err(dwmac->dev, "unsupported phy interface %d\n",
 			plat->mac_interface);
-		return;
+		return -EINVAL;
 	}
 }
 
@@ -245,7 +237,7 @@ static int thead_dwmac_probe(struct platform_device *pdev)
 	dwmac->plat = plat;
 	dwmac->apb_base = apb;
 	plat->bsp_priv = dwmac;
-	plat->fix_mac_speed = thead_dwmac_fix_speed;
+	plat->set_clk_tx_rate = thead_set_clk_tx_rate;
 	plat->init = thead_dwmac_init;
 
 	return devm_stmmac_pltfr_probe(pdev, plat, &stmmac_res);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
index eccf7f537467..5e6ac82a89b9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -51,21 +51,14 @@ struct visconti_eth {
 	u32 phy_intf_sel;
 	struct clk *phy_ref_clk;
 	struct device *dev;
-	spinlock_t lock; /* lock to protect register update */
 };
 
-static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static int visconti_eth_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+					phy_interface_t interface, int speed)
 {
-	struct visconti_eth *dwmac = priv;
+	struct visconti_eth *dwmac = bsp_priv;
 	struct net_device *netdev = dev_get_drvdata(dwmac->dev);
 	unsigned int val, clk_sel_val = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dwmac->lock, flags);
-
-	/* adjust link */
-	val = readl(dwmac->reg + MAC_CTRL_REG);
-	val &= ~(GMAC_CONFIG_PS | GMAC_CONFIG_FES);
 
 	switch (speed) {
 	case SPEED_1000:
@@ -77,24 +70,19 @@ static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned
 			clk_sel_val = ETHER_CLK_SEL_FREQ_SEL_25M;
 		if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RMII)
 			clk_sel_val = ETHER_CLK_SEL_DIV_SEL_2;
-		val |= GMAC_CONFIG_PS | GMAC_CONFIG_FES;
 		break;
 	case SPEED_10:
 		if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RGMII)
 			clk_sel_val = ETHER_CLK_SEL_FREQ_SEL_2P5M;
 		if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RMII)
 			clk_sel_val = ETHER_CLK_SEL_DIV_SEL_20;
-		val |= GMAC_CONFIG_PS;
 		break;
 	default:
 		/* No bit control */
 		netdev_err(netdev, "Unsupported speed request (%d)", speed);
-		spin_unlock_irqrestore(&dwmac->lock, flags);
-		return;
+		return -EINVAL;
 	}
 
-	writel(val, dwmac->reg + MAC_CTRL_REG);
-
 	/* Stop internal clock */
 	val = readl(dwmac->reg + REG_ETHER_CLOCK_SEL);
 	val &= ~(ETHER_CLK_SEL_RMII_CLK_EN | ETHER_CLK_SEL_RX_TX_CLK_EN);
@@ -136,7 +124,7 @@ static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned
 		break;
 	}
 
-	spin_unlock_irqrestore(&dwmac->lock, flags);
+	return 0;
 }
 
 static int visconti_eth_init_hw(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat)
@@ -228,11 +216,10 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev)
 	if (!dwmac)
 		return -ENOMEM;
 
-	spin_lock_init(&dwmac->lock);
 	dwmac->reg = stmmac_res.addr;
 	dwmac->dev = &pdev->dev;
 	plat_dat->bsp_priv = dwmac;
-	plat_dat->fix_mac_speed = visconti_eth_fix_mac_speed;
+	plat_dat->set_clk_tx_rate = visconti_eth_set_clk_tx_rate;
 
 	ret = visconti_eth_clock_probe(pdev, plat_dat);
 	if (ret)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 600fea8f712f..0c011a47d5a3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -59,22 +59,11 @@ enum power_event {
 /* Energy Efficient Ethernet (EEE)
  *
  * LPI status, timer and control register offset
+ * For LPI control and status bit definitions, see common.h.
  */
 #define LPI_CTRL_STATUS	0x0030
 #define LPI_TIMER_CTRL	0x0034
 
-/* LPI control and status defines */
-#define LPI_CTRL_STATUS_LPITXA	0x00080000	/* Enable LPI TX Automate */
-#define LPI_CTRL_STATUS_PLSEN	0x00040000	/* Enable PHY Link Status */
-#define LPI_CTRL_STATUS_PLS	0x00020000	/* PHY Link Status */
-#define LPI_CTRL_STATUS_LPIEN	0x00010000	/* LPI Enable */
-#define LPI_CTRL_STATUS_RLPIST	0x00000200	/* Receive LPI state */
-#define LPI_CTRL_STATUS_TLPIST	0x00000100	/* Transmit LPI state */
-#define LPI_CTRL_STATUS_RLPIEX	0x00000008	/* Receive LPI Exit */
-#define LPI_CTRL_STATUS_RLPIEN	0x00000004	/* Receive LPI Entry */
-#define LPI_CTRL_STATUS_TLPIEX	0x00000002	/* Transmit LPI Exit */
-#define LPI_CTRL_STATUS_TLPIEN	0x00000001	/* Transmit LPI Entry */
-
 /* GMAC HW ADDR regs */
 #define GMAC_ADDR_HIGH(reg)	((reg > 15) ? 0x00000800 + (reg - 16) * 8 : \
 				 0x00000040 + (reg * 8))
@@ -331,8 +320,8 @@ enum rtc_control {
 
 /* PTP and timestamping registers */
 
-#define GMAC3_X_ATSNS       GENMASK(19, 16)
-#define GMAC3_X_ATSNS_SHIFT 16
+#define GMAC3_X_ATSNS       GENMASK(29, 25)
+#define GMAC3_X_ATSNS_SHIFT 25
 
 #define GMAC_PTP_TCR_ATSFC	BIT(24)
 #define GMAC_PTP_TCR_ATSEN0	BIT(25)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 96bcda0856ec..56b76aaa58f0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/ethtool.h>
 #include <linux/io.h>
+#include <linux/string_choices.h>
 #include "stmmac.h"
 #include "stmmac_pcs.h"
 #include "stmmac_ptp.h"
@@ -342,31 +343,24 @@ static int dwmac1000_irq_status(struct mac_device_info *hw,
 	return ret;
 }
 
-static void dwmac1000_set_eee_mode(struct mac_device_info *hw,
-				   bool en_tx_lpi_clockgating)
+static int dwmac1000_set_lpi_mode(struct mac_device_info *hw,
+				  enum stmmac_lpi_mode mode,
+				  bool en_tx_lpi_clockgating, u32 et)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value;
 
-	/*TODO - en_tx_lpi_clockgating treatment */
+	if (mode == STMMAC_LPI_TIMER)
+		return -EOPNOTSUPP;
 
-	/* Enable the link status receive on RGMII, SGMII ore SMII
-	 * receive path and instruct the transmit to enter in LPI
-	 * state.
-	 */
 	value = readl(ioaddr + LPI_CTRL_STATUS);
-	value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+	if (mode == STMMAC_LPI_FORCED)
+		value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+	else
+		value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA);
 	writel(value, ioaddr + LPI_CTRL_STATUS);
-}
-
-static void dwmac1000_reset_eee_mode(struct mac_device_info *hw)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
 
-	value = readl(ioaddr + LPI_CTRL_STATUS);
-	value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA);
-	writel(value, ioaddr + LPI_CTRL_STATUS);
+	return 0;
 }
 
 static void dwmac1000_set_eee_pls(struct mac_device_info *hw, int link)
@@ -509,8 +503,7 @@ const struct stmmac_ops dwmac1000_ops = {
 	.pmt = dwmac1000_pmt,
 	.set_umac_addr = dwmac1000_set_umac_addr,
 	.get_umac_addr = dwmac1000_get_umac_addr,
-	.set_eee_mode = dwmac1000_set_eee_mode,
-	.reset_eee_mode = dwmac1000_reset_eee_mode,
+	.set_lpi_mode = dwmac1000_set_lpi_mode,
 	.set_eee_timer = dwmac1000_set_eee_timer,
 	.set_eee_pls = dwmac1000_set_eee_pls,
 	.debug = dwmac1000_debug,
@@ -560,7 +553,7 @@ void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
 	u64 ns;
 
 	ns = readl(ptpaddr + GMAC_PTP_ATNR);
-	ns += readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
+	ns += (u64)readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
 
 	*ptp_time = ns;
 }
@@ -633,7 +626,7 @@ int dwmac1000_ptp_enable(struct ptp_clock_info *ptp,
 		}
 
 		netdev_dbg(priv->dev, "Auxiliary Snapshot %s.\n",
-			   on ? "enabled" : "disabled");
+			   str_enabled_disabled(on));
 		writel(tcr_val, ptpaddr + PTP_TCR);
 
 		/* wait for auxts fifo clear to finish */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 184d41a306af..f4694fd576f5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -17,11 +17,7 @@
 #define GMAC_EXT_CONFIG			0x00000004
 #define GMAC_PACKET_FILTER		0x00000008
 #define GMAC_HASH_TAB(x)		(0x10 + (x) * 4)
-#define GMAC_VLAN_TAG			0x00000050
-#define GMAC_VLAN_TAG_DATA		0x00000054
-#define GMAC_VLAN_HASH_TABLE		0x00000058
 #define GMAC_RX_FLOW_CTRL		0x00000090
-#define GMAC_VLAN_INCL			0x00000060
 #define GMAC_QX_TX_FLOW_CTRL(x)		(0x70 + x * 4)
 #define GMAC_TXQ_PRTY_MAP0		0x98
 #define GMAC_TXQ_PRTY_MAP1		0x9C
@@ -31,7 +27,6 @@
 #define GMAC_RXQ_CTRL3			0x000000ac
 #define GMAC_INT_STATUS			0x000000b0
 #define GMAC_INT_EN			0x000000b4
-#define GMAC_1US_TIC_COUNTER		0x000000dc
 #define GMAC_PCS_BASE			0x000000e0
 #define GMAC_PHYIF_CONTROL_STATUS	0x000000f8
 #define GMAC_PMT			0x000000c0
@@ -82,42 +77,6 @@
 
 #define GMAC_MAX_PERFECT_ADDRESSES	128
 
-/* MAC VLAN */
-#define GMAC_VLAN_EDVLP			BIT(26)
-#define GMAC_VLAN_VTHM			BIT(25)
-#define GMAC_VLAN_DOVLTC		BIT(20)
-#define GMAC_VLAN_ESVL			BIT(18)
-#define GMAC_VLAN_ETV			BIT(16)
-#define GMAC_VLAN_VID			GENMASK(15, 0)
-#define GMAC_VLAN_VLTI			BIT(20)
-#define GMAC_VLAN_CSVL			BIT(19)
-#define GMAC_VLAN_VLC			GENMASK(17, 16)
-#define GMAC_VLAN_VLC_SHIFT		16
-#define GMAC_VLAN_VLHT			GENMASK(15, 0)
-
-/* MAC VLAN Tag */
-#define GMAC_VLAN_TAG_VID		GENMASK(15, 0)
-#define GMAC_VLAN_TAG_ETV		BIT(16)
-
-/* MAC VLAN Tag Control */
-#define GMAC_VLAN_TAG_CTRL_OB		BIT(0)
-#define GMAC_VLAN_TAG_CTRL_CT		BIT(1)
-#define GMAC_VLAN_TAG_CTRL_OFS_MASK	GENMASK(6, 2)
-#define GMAC_VLAN_TAG_CTRL_OFS_SHIFT	2
-#define GMAC_VLAN_TAG_CTRL_EVLS_MASK	GENMASK(22, 21)
-#define GMAC_VLAN_TAG_CTRL_EVLS_SHIFT	21
-#define GMAC_VLAN_TAG_CTRL_EVLRXS	BIT(24)
-
-#define GMAC_VLAN_TAG_STRIP_NONE	(0x0 << GMAC_VLAN_TAG_CTRL_EVLS_SHIFT)
-#define GMAC_VLAN_TAG_STRIP_PASS	(0x1 << GMAC_VLAN_TAG_CTRL_EVLS_SHIFT)
-#define GMAC_VLAN_TAG_STRIP_FAIL	(0x2 << GMAC_VLAN_TAG_CTRL_EVLS_SHIFT)
-#define GMAC_VLAN_TAG_STRIP_ALL		(0x3 << GMAC_VLAN_TAG_CTRL_EVLS_SHIFT)
-
-/* MAC VLAN Tag Data/Filter */
-#define GMAC_VLAN_TAG_DATA_VID		GENMASK(15, 0)
-#define GMAC_VLAN_TAG_DATA_VEN		BIT(16)
-#define GMAC_VLAN_TAG_DATA_ETV		BIT(17)
-
 /* MAC RX Queue Enable */
 #define GMAC_RX_QUEUE_CLEAR(queue)	~(GENMASK(1, 0) << ((queue) * 2))
 #define GMAC_RX_AV_QUEUE_ENABLE(queue)	BIT((queue) * 2)
@@ -177,23 +136,13 @@ enum power_event {
 /* Energy Efficient Ethernet (EEE) for GMAC4
  *
  * LPI status, timer and control register offset
+ * For LPI control and status bit definitions, see common.h.
  */
 #define GMAC4_LPI_CTRL_STATUS	0xd0
 #define GMAC4_LPI_TIMER_CTRL	0xd4
 #define GMAC4_LPI_ENTRY_TIMER	0xd8
 #define GMAC4_MAC_ONEUS_TIC_COUNTER	0xdc
 
-/* LPI control and status defines */
-#define GMAC4_LPI_CTRL_STATUS_LPITCSE	BIT(21)	/* LPI Tx Clock Stop Enable */
-#define GMAC4_LPI_CTRL_STATUS_LPIATE	BIT(20) /* LPI Timer Enable */
-#define GMAC4_LPI_CTRL_STATUS_LPITXA	BIT(19)	/* Enable LPI TX Automate */
-#define GMAC4_LPI_CTRL_STATUS_PLS	BIT(17) /* PHY Link Status */
-#define GMAC4_LPI_CTRL_STATUS_LPIEN	BIT(16)	/* LPI Enable */
-#define GMAC4_LPI_CTRL_STATUS_RLPIEX	BIT(3) /* Receive LPI Exit */
-#define GMAC4_LPI_CTRL_STATUS_RLPIEN	BIT(2) /* Receive LPI Entry */
-#define GMAC4_LPI_CTRL_STATUS_TLPIEX	BIT(1) /* Transmit LPI Exit */
-#define GMAC4_LPI_CTRL_STATUS_TLPIEN	BIT(0) /* Transmit LPI Entry */
-
 /* MAC Debug bitmap */
 #define GMAC_DEBUG_TFCSTS_MASK		GENMASK(18, 17)
 #define GMAC_DEBUG_TFCSTS_SHIFT		17
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index c25781874aa7..9c2549d4100f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -18,6 +18,7 @@
 #include "stmmac.h"
 #include "stmmac_fpe.h"
 #include "stmmac_pcs.h"
+#include "stmmac_vlan.h"
 #include "dwmac4.h"
 #include "dwmac5.h"
 
@@ -27,7 +28,7 @@ static void dwmac4_core_init(struct mac_device_info *hw,
 	struct stmmac_priv *priv = netdev_priv(dev);
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONFIG);
-	u32 clk_rate;
+	unsigned long clk_rate;
 
 	value |= GMAC_CORE_INIT;
 
@@ -376,33 +377,46 @@ static void dwmac4_get_umac_addr(struct mac_device_info *hw,
 				   GMAC_ADDR_LOW(reg_n));
 }
 
-static void dwmac4_set_eee_mode(struct mac_device_info *hw,
-				bool en_tx_lpi_clockgating)
+static int dwmac4_set_lpi_mode(struct mac_device_info *hw,
+			       enum stmmac_lpi_mode mode,
+			       bool en_tx_lpi_clockgating, u32 et)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
+	u32 value, mask;
 
-	/* Enable the link status receive on RGMII, SGMII ore SMII
-	 * receive path and instruct the transmit to enter in LPI
-	 * state.
-	 */
-	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	value |= GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA;
+	if (mode == STMMAC_LPI_DISABLE) {
+		value = 0;
+	} else {
+		value = LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
 
-	if (en_tx_lpi_clockgating)
-		value |= GMAC4_LPI_CTRL_STATUS_LPITCSE;
+		if (mode == STMMAC_LPI_TIMER) {
+			/* Return ERANGE if the timer is larger than the
+			 * register field.
+			 */
+			if (et > STMMAC_ET_MAX)
+				return -ERANGE;
 
-	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
-}
+			/* Set the hardware LPI entry timer */
+			writel(et, ioaddr + GMAC4_LPI_ENTRY_TIMER);
 
-static void dwmac4_reset_eee_mode(struct mac_device_info *hw)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
+			/* Interpret a zero LPI entry timer to mean
+			 * immediate entry into LPI mode.
+			 */
+			if (et)
+				value |= LPI_CTRL_STATUS_LPIATE;
+		}
 
-	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	value &= ~(GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA);
+		if (en_tx_lpi_clockgating)
+			value |= LPI_CTRL_STATUS_LPITCSE;
+	}
+
+	mask = LPI_CTRL_STATUS_LPIATE | LPI_CTRL_STATUS_LPIEN |
+	       LPI_CTRL_STATUS_LPITXA | LPI_CTRL_STATUS_LPITCSE;
+
+	value |= readl(ioaddr + GMAC4_LPI_CTRL_STATUS) & ~mask;
 	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
+
+	return 0;
 }
 
 static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link)
@@ -413,34 +427,13 @@ static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link)
 	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
 
 	if (link)
-		value |= GMAC4_LPI_CTRL_STATUS_PLS;
+		value |= LPI_CTRL_STATUS_PLS;
 	else
-		value &= ~GMAC4_LPI_CTRL_STATUS_PLS;
+		value &= ~LPI_CTRL_STATUS_PLS;
 
 	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
 }
 
-static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, int et)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	int value = et & STMMAC_ET_MAX;
-	int regval;
-
-	/* Program LPI entry timer value into register */
-	writel(value, ioaddr + GMAC4_LPI_ENTRY_TIMER);
-
-	/* Enable/disable LPI entry timer */
-	regval = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	regval |= GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA;
-
-	if (et)
-		regval |= GMAC4_LPI_CTRL_STATUS_LPIATE;
-	else
-		regval &= ~GMAC4_LPI_CTRL_STATUS_LPIATE;
-
-	writel(regval, ioaddr + GMAC4_LPI_CTRL_STATUS);
-}
-
 static void dwmac4_set_eee_timer(struct mac_device_info *hw, int ls, int tw)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -456,165 +449,6 @@ static void dwmac4_set_eee_timer(struct mac_device_info *hw, int ls, int tw)
 	writel(value, ioaddr + GMAC4_LPI_TIMER_CTRL);
 }
 
-static void dwmac4_write_single_vlan(struct net_device *dev, u16 vid)
-{
-	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
-	u32 val;
-
-	val = readl(ioaddr + GMAC_VLAN_TAG);
-	val &= ~GMAC_VLAN_TAG_VID;
-	val |= GMAC_VLAN_TAG_ETV | vid;
-
-	writel(val, ioaddr + GMAC_VLAN_TAG);
-}
-
-static int dwmac4_write_vlan_filter(struct net_device *dev,
-				    struct mac_device_info *hw,
-				    u8 index, u32 data)
-{
-	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
-	int ret;
-	u32 val;
-
-	if (index >= hw->num_vlan)
-		return -EINVAL;
-
-	writel(data, ioaddr + GMAC_VLAN_TAG_DATA);
-
-	val = readl(ioaddr + GMAC_VLAN_TAG);
-	val &= ~(GMAC_VLAN_TAG_CTRL_OFS_MASK |
-		GMAC_VLAN_TAG_CTRL_CT |
-		GMAC_VLAN_TAG_CTRL_OB);
-	val |= (index << GMAC_VLAN_TAG_CTRL_OFS_SHIFT) | GMAC_VLAN_TAG_CTRL_OB;
-
-	writel(val, ioaddr + GMAC_VLAN_TAG);
-
-	ret = readl_poll_timeout(ioaddr + GMAC_VLAN_TAG, val,
-				 !(val & GMAC_VLAN_TAG_CTRL_OB),
-				 1000, 500000);
-	if (ret) {
-		netdev_err(dev, "Timeout accessing MAC_VLAN_Tag_Filter\n");
-		return -EBUSY;
-	}
-
-	return 0;
-}
-
-static int dwmac4_add_hw_vlan_rx_fltr(struct net_device *dev,
-				      struct mac_device_info *hw,
-				      __be16 proto, u16 vid)
-{
-	int index = -1;
-	u32 val = 0;
-	int i, ret;
-
-	if (vid > 4095)
-		return -EINVAL;
-
-	/* Single Rx VLAN Filter */
-	if (hw->num_vlan == 1) {
-		/* For single VLAN filter, VID 0 means VLAN promiscuous */
-		if (vid == 0) {
-			netdev_warn(dev, "Adding VLAN ID 0 is not supported\n");
-			return -EPERM;
-		}
-
-		if (hw->vlan_filter[0] & GMAC_VLAN_TAG_VID) {
-			netdev_err(dev, "Only single VLAN ID supported\n");
-			return -EPERM;
-		}
-
-		hw->vlan_filter[0] = vid;
-		dwmac4_write_single_vlan(dev, vid);
-
-		return 0;
-	}
-
-	/* Extended Rx VLAN Filter Enable */
-	val |= GMAC_VLAN_TAG_DATA_ETV | GMAC_VLAN_TAG_DATA_VEN | vid;
-
-	for (i = 0; i < hw->num_vlan; i++) {
-		if (hw->vlan_filter[i] == val)
-			return 0;
-		else if (!(hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VEN))
-			index = i;
-	}
-
-	if (index == -1) {
-		netdev_err(dev, "MAC_VLAN_Tag_Filter full (size: %0u)\n",
-			   hw->num_vlan);
-		return -EPERM;
-	}
-
-	ret = dwmac4_write_vlan_filter(dev, hw, index, val);
-
-	if (!ret)
-		hw->vlan_filter[index] = val;
-
-	return ret;
-}
-
-static int dwmac4_del_hw_vlan_rx_fltr(struct net_device *dev,
-				      struct mac_device_info *hw,
-				      __be16 proto, u16 vid)
-{
-	int i, ret = 0;
-
-	/* Single Rx VLAN Filter */
-	if (hw->num_vlan == 1) {
-		if ((hw->vlan_filter[0] & GMAC_VLAN_TAG_VID) == vid) {
-			hw->vlan_filter[0] = 0;
-			dwmac4_write_single_vlan(dev, 0);
-		}
-		return 0;
-	}
-
-	/* Extended Rx VLAN Filter Enable */
-	for (i = 0; i < hw->num_vlan; i++) {
-		if ((hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VID) == vid) {
-			ret = dwmac4_write_vlan_filter(dev, hw, i, 0);
-
-			if (!ret)
-				hw->vlan_filter[i] = 0;
-			else
-				return ret;
-		}
-	}
-
-	return ret;
-}
-
-static void dwmac4_restore_hw_vlan_rx_fltr(struct net_device *dev,
-					   struct mac_device_info *hw)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-	u32 hash;
-	u32 val;
-	int i;
-
-	/* Single Rx VLAN Filter */
-	if (hw->num_vlan == 1) {
-		dwmac4_write_single_vlan(dev, hw->vlan_filter[0]);
-		return;
-	}
-
-	/* Extended Rx VLAN Filter Enable */
-	for (i = 0; i < hw->num_vlan; i++) {
-		if (hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VEN) {
-			val = hw->vlan_filter[i];
-			dwmac4_write_vlan_filter(dev, hw, i, val);
-		}
-	}
-
-	hash = readl(ioaddr + GMAC_VLAN_HASH_TABLE);
-	if (hash & GMAC_VLAN_VLHT) {
-		value = readl(ioaddr + GMAC_VLAN_TAG);
-		value |= GMAC_VLAN_VTHM;
-		writel(value, ioaddr + GMAC_VLAN_TAG);
-	}
-}
-
 static void dwmac4_set_filter(struct mac_device_info *hw,
 			      struct net_device *dev)
 {
@@ -849,17 +683,17 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 		/* Clear LPI interrupt by reading MAC_LPI_Control_Status */
 		u32 status = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
 
-		if (status & GMAC4_LPI_CTRL_STATUS_TLPIEN) {
+		if (status & LPI_CTRL_STATUS_TLPIEN) {
 			ret |= CORE_IRQ_TX_PATH_IN_LPI_MODE;
 			x->irq_tx_path_in_lpi_mode_n++;
 		}
-		if (status & GMAC4_LPI_CTRL_STATUS_TLPIEX) {
+		if (status & LPI_CTRL_STATUS_TLPIEX) {
 			ret |= CORE_IRQ_TX_PATH_EXIT_LPI_MODE;
 			x->irq_tx_path_exit_lpi_mode_n++;
 		}
-		if (status & GMAC4_LPI_CTRL_STATUS_RLPIEN)
+		if (status & LPI_CTRL_STATUS_RLPIEN)
 			x->irq_rx_path_in_lpi_mode_n++;
-		if (status & GMAC4_LPI_CTRL_STATUS_RLPIEX)
+		if (status & LPI_CTRL_STATUS_RLPIEX)
 			x->irq_rx_path_exit_lpi_mode_n++;
 	}
 
@@ -973,45 +807,6 @@ static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable)
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				    u16 perfect_match, bool is_double)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-
-	writel(hash, ioaddr + GMAC_VLAN_HASH_TABLE);
-
-	value = readl(ioaddr + GMAC_VLAN_TAG);
-
-	if (hash) {
-		value |= GMAC_VLAN_VTHM | GMAC_VLAN_ETV;
-		if (is_double) {
-			value |= GMAC_VLAN_EDVLP;
-			value |= GMAC_VLAN_ESVL;
-			value |= GMAC_VLAN_DOVLTC;
-		}
-
-		writel(value, ioaddr + GMAC_VLAN_TAG);
-	} else if (perfect_match) {
-		u32 value = GMAC_VLAN_ETV;
-
-		if (is_double) {
-			value |= GMAC_VLAN_EDVLP;
-			value |= GMAC_VLAN_ESVL;
-			value |= GMAC_VLAN_DOVLTC;
-		}
-
-		writel(value | perfect_match, ioaddr + GMAC_VLAN_TAG);
-	} else {
-		value &= ~(GMAC_VLAN_VTHM | GMAC_VLAN_ETV);
-		value &= ~(GMAC_VLAN_EDVLP | GMAC_VLAN_ESVL);
-		value &= ~GMAC_VLAN_DOVLTC;
-		value &= ~GMAC_VLAN_VID;
-
-		writel(value, ioaddr + GMAC_VLAN_TAG);
-	}
-}
-
 static void dwmac4_sarc_configure(void __iomem *ioaddr, int val)
 {
 	u32 value = readl(ioaddr + GMAC_CONFIG);
@@ -1022,19 +817,6 @@ static void dwmac4_sarc_configure(void __iomem *ioaddr, int val)
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-static void dwmac4_enable_vlan(struct mac_device_info *hw, u32 type)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-
-	value = readl(ioaddr + GMAC_VLAN_INCL);
-	value |= GMAC_VLAN_VLTI;
-	value |= GMAC_VLAN_CSVL; /* Only use SVLAN */
-	value &= ~GMAC_VLAN_VLC;
-	value |= (type << GMAC_VLAN_VLC_SHIFT) & GMAC_VLAN_VLC;
-	writel(value, ioaddr + GMAC_VLAN_INCL);
-}
-
 static void dwmac4_set_arp_offload(struct mac_device_info *hw, bool en,
 				   u32 addr)
 {
@@ -1151,35 +933,6 @@ static int dwmac4_config_l4_filter(struct mac_device_info *hw, u32 filter_no,
 	return 0;
 }
 
-static void dwmac4_rx_hw_vlan(struct mac_device_info *hw,
-			      struct dma_desc *rx_desc, struct sk_buff *skb)
-{
-	if (hw->desc->get_rx_vlan_valid(rx_desc)) {
-		u16 vid = hw->desc->get_rx_vlan_tci(rx_desc);
-
-		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
-	}
-}
-
-static void dwmac4_set_hw_vlan_mode(struct mac_device_info *hw)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value = readl(ioaddr + GMAC_VLAN_TAG);
-
-	value &= ~GMAC_VLAN_TAG_CTRL_EVLS_MASK;
-
-	if (hw->hw_vlan_en)
-		/* Always strip VLAN on Receive */
-		value |= GMAC_VLAN_TAG_STRIP_ALL;
-	else
-		/* Do not strip VLAN on Receive */
-		value |= GMAC_VLAN_TAG_STRIP_NONE;
-
-	/* Enable outer VLAN Tag in Rx DMA descriptor */
-	value |= GMAC_VLAN_TAG_CTRL_EVLRXS;
-	writel(value, ioaddr + GMAC_VLAN_TAG);
-}
-
 const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
 	.update_caps = dwmac4_update_caps,
@@ -1201,9 +954,7 @@ const struct stmmac_ops dwmac4_ops = {
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
-	.set_eee_mode = dwmac4_set_eee_mode,
-	.reset_eee_mode = dwmac4_reset_eee_mode,
-	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
+	.set_lpi_mode = dwmac4_set_lpi_mode,
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
@@ -1211,17 +962,10 @@ const struct stmmac_ops dwmac4_ops = {
 	.debug = dwmac4_debug,
 	.set_filter = dwmac4_set_filter,
 	.set_mac_loopback = dwmac4_set_mac_loopback,
-	.update_vlan_hash = dwmac4_update_vlan_hash,
 	.sarc_configure = dwmac4_sarc_configure,
-	.enable_vlan = dwmac4_enable_vlan,
 	.set_arp_offload = dwmac4_set_arp_offload,
 	.config_l3_filter = dwmac4_config_l3_filter,
 	.config_l4_filter = dwmac4_config_l4_filter,
-	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
-	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
-	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
-	.rx_hw_vlan = dwmac4_rx_hw_vlan,
-	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
 const struct stmmac_ops dwmac410_ops = {
@@ -1245,9 +989,7 @@ const struct stmmac_ops dwmac410_ops = {
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
-	.set_eee_mode = dwmac4_set_eee_mode,
-	.reset_eee_mode = dwmac4_reset_eee_mode,
-	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
+	.set_lpi_mode = dwmac4_set_lpi_mode,
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
@@ -1256,18 +998,11 @@ const struct stmmac_ops dwmac410_ops = {
 	.set_filter = dwmac4_set_filter,
 	.flex_pps_config = dwmac5_flex_pps_config,
 	.set_mac_loopback = dwmac4_set_mac_loopback,
-	.update_vlan_hash = dwmac4_update_vlan_hash,
 	.sarc_configure = dwmac4_sarc_configure,
-	.enable_vlan = dwmac4_enable_vlan,
 	.set_arp_offload = dwmac4_set_arp_offload,
 	.config_l3_filter = dwmac4_config_l3_filter,
 	.config_l4_filter = dwmac4_config_l4_filter,
 	.fpe_map_preemption_class = dwmac5_fpe_map_preemption_class,
-	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
-	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
-	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
-	.rx_hw_vlan = dwmac4_rx_hw_vlan,
-	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
 const struct stmmac_ops dwmac510_ops = {
@@ -1291,9 +1026,7 @@ const struct stmmac_ops dwmac510_ops = {
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
-	.set_eee_mode = dwmac4_set_eee_mode,
-	.reset_eee_mode = dwmac4_reset_eee_mode,
-	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
+	.set_lpi_mode = dwmac4_set_lpi_mode,
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
@@ -1306,51 +1039,13 @@ const struct stmmac_ops dwmac510_ops = {
 	.rxp_config = dwmac5_rxp_config,
 	.flex_pps_config = dwmac5_flex_pps_config,
 	.set_mac_loopback = dwmac4_set_mac_loopback,
-	.update_vlan_hash = dwmac4_update_vlan_hash,
 	.sarc_configure = dwmac4_sarc_configure,
-	.enable_vlan = dwmac4_enable_vlan,
 	.set_arp_offload = dwmac4_set_arp_offload,
 	.config_l3_filter = dwmac4_config_l3_filter,
 	.config_l4_filter = dwmac4_config_l4_filter,
 	.fpe_map_preemption_class = dwmac5_fpe_map_preemption_class,
-	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
-	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
-	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
-	.rx_hw_vlan = dwmac4_rx_hw_vlan,
-	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
-static u32 dwmac4_get_num_vlan(void __iomem *ioaddr)
-{
-	u32 val, num_vlan;
-
-	val = readl(ioaddr + GMAC_HW_FEATURE3);
-	switch (val & GMAC_HW_FEAT_NRVF) {
-	case 0:
-		num_vlan = 1;
-		break;
-	case 1:
-		num_vlan = 4;
-		break;
-	case 2:
-		num_vlan = 8;
-		break;
-	case 3:
-		num_vlan = 16;
-		break;
-	case 4:
-		num_vlan = 24;
-		break;
-	case 5:
-		num_vlan = 32;
-		break;
-	default:
-		num_vlan = 1;
-	}
-
-	return num_vlan;
-}
-
 int dwmac4_setup(struct stmmac_priv *priv)
 {
 	struct mac_device_info *mac = priv->hw;
@@ -1382,7 +1077,7 @@ int dwmac4_setup(struct stmmac_priv *priv)
 	mac->mii.reg_mask = GENMASK(20, 16);
 	mac->mii.clk_csr_shift = 8;
 	mac->mii.clk_csr_mask = GENMASK(11, 8);
-	mac->num_vlan = dwmac4_get_num_vlan(priv->ioaddr);
+	mac->num_vlan = stmmac_get_num_vlan(priv->ioaddr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
index 1ce6f43d545a..806555976496 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
@@ -144,4 +144,7 @@
 /* TDS3 use for both format (read and write back) */
 #define RDES3_OWN			BIT(31)
 
+extern const struct stmmac_mode_ops dwmac4_ring_mode_ops;
+extern const struct stmmac_desc_ops dwmac4_desc_ops;
+
 #endif /* __DWMAC4_DESCS_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index a04a79003692..0d408ee17f33 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -57,19 +57,6 @@
 #define XGMAC_FILTER_PR			BIT(0)
 #define XGMAC_HASH_TABLE(x)		(0x00000010 + (x) * 4)
 #define XGMAC_MAX_HASH_TABLE		8
-#define XGMAC_VLAN_TAG			0x00000050
-#define XGMAC_VLAN_EDVLP		BIT(26)
-#define XGMAC_VLAN_VTHM			BIT(25)
-#define XGMAC_VLAN_DOVLTC		BIT(20)
-#define XGMAC_VLAN_ESVL			BIT(18)
-#define XGMAC_VLAN_ETV			BIT(16)
-#define XGMAC_VLAN_VID			GENMASK(15, 0)
-#define XGMAC_VLAN_HASH_TABLE		0x00000058
-#define XGMAC_VLAN_INCL			0x00000060
-#define XGMAC_VLAN_VLTI			BIT(20)
-#define XGMAC_VLAN_CSVL			BIT(19)
-#define XGMAC_VLAN_VLC			GENMASK(17, 16)
-#define XGMAC_VLAN_VLC_SHIFT		16
 #define XGMAC_RXQ_CTRL0			0x000000a0
 #define XGMAC_RXQEN(x)			GENMASK((x) * 2 + 1, (x) * 2)
 #define XGMAC_RXQEN_SHIFT(x)		((x) * 2)
@@ -112,14 +99,7 @@
 #define XGMAC_MGKPKTEN			BIT(1)
 #define XGMAC_PWRDWN			BIT(0)
 #define XGMAC_LPI_CTRL			0x000000d0
-#define XGMAC_TXCGE			BIT(21)
-#define XGMAC_LPITXA			BIT(19)
-#define XGMAC_PLS			BIT(17)
-#define XGMAC_LPITXEN			BIT(16)
-#define XGMAC_RLPIEX			BIT(3)
-#define XGMAC_RLPIEN			BIT(2)
-#define XGMAC_TLPIEX			BIT(1)
-#define XGMAC_TLPIEN			BIT(0)
+/* For definitions, see LPI_CTRL_STATUS_xxx in common.h */
 #define XGMAC_LPI_TIMER_CTRL		0x000000d4
 #define XGMAC_HW_FEATURE0		0x0000011c
 #define XGMAC_HWFEAT_EDMA		BIT(31)
@@ -484,6 +464,7 @@
 #define XGMAC_RDES3_RSV			BIT(26)
 #define XGMAC_RDES3_L34T		GENMASK(23, 20)
 #define XGMAC_RDES3_L34T_SHIFT		20
+#define XGMAC_RDES3_ET_LT		GENMASK(19, 16)
 #define XGMAC_L34T_IP4TCP		0x1
 #define XGMAC_L34T_IP4UDP		0x2
 #define XGMAC_L34T_IP6TCP		0x9
@@ -493,4 +474,20 @@
 #define XGMAC_RDES3_TSD			BIT(6)
 #define XGMAC_RDES3_TSA			BIT(4)
 
+/* RDES0 (write back format) */
+#define XGMAC_RDES0_VLAN_TAG_MASK	GENMASK(15, 0)
+
+/* Error Type or L2 Type(ET/LT) Field Number */
+#define XGMAC_ET_LT_VLAN_STAG		8
+#define XGMAC_ET_LT_VLAN_CTAG		9
+#define XGMAC_ET_LT_DVLAN_CTAG_CTAG	10
+#define XGMAC_ET_LT_DVLAN_STAG_STAG	11
+#define XGMAC_ET_LT_DVLAN_CTAG_STAG	12
+#define XGMAC_ET_LT_DVLAN_STAG_CTAG	13
+
+extern const struct stmmac_ops dwxgmac210_ops;
+extern const struct stmmac_ops dwxlgmac2_ops;
+extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
+extern const struct stmmac_desc_ops dwxgmac210_desc_ops;
+
 #endif /* __STMMAC_DWXGMAC2_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 9a60a6e8f633..6cadf8de4fdf 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -10,6 +10,7 @@
 #include "stmmac.h"
 #include "stmmac_fpe.h"
 #include "stmmac_ptp.h"
+#include "stmmac_vlan.h"
 #include "dwxlgmac2.h"
 #include "dwxgmac2.h"
 
@@ -316,17 +317,17 @@ static int dwxgmac2_host_irq_status(struct mac_device_info *hw,
 	if (stat & XGMAC_LPIIS) {
 		u32 lpi = readl(ioaddr + XGMAC_LPI_CTRL);
 
-		if (lpi & XGMAC_TLPIEN) {
+		if (lpi & LPI_CTRL_STATUS_TLPIEN) {
 			ret |= CORE_IRQ_TX_PATH_IN_LPI_MODE;
 			x->irq_tx_path_in_lpi_mode_n++;
 		}
-		if (lpi & XGMAC_TLPIEX) {
+		if (lpi & LPI_CTRL_STATUS_TLPIEX) {
 			ret |= CORE_IRQ_TX_PATH_EXIT_LPI_MODE;
 			x->irq_tx_path_exit_lpi_mode_n++;
 		}
-		if (lpi & XGMAC_RLPIEN)
+		if (lpi & LPI_CTRL_STATUS_RLPIEN)
 			x->irq_rx_path_in_lpi_mode_n++;
-		if (lpi & XGMAC_RLPIEX)
+		if (lpi & LPI_CTRL_STATUS_RLPIEX)
 			x->irq_rx_path_exit_lpi_mode_n++;
 	}
 
@@ -425,29 +426,28 @@ static void dwxgmac2_get_umac_addr(struct mac_device_info *hw,
 	addr[5] = (hi_addr >> 8) & 0xff;
 }
 
-static void dwxgmac2_set_eee_mode(struct mac_device_info *hw,
-				  bool en_tx_lpi_clockgating)
+static int dwxgmac2_set_lpi_mode(struct mac_device_info *hw,
+				 enum stmmac_lpi_mode mode,
+				 bool en_tx_lpi_clockgating, u32 et)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value;
 
-	value = readl(ioaddr + XGMAC_LPI_CTRL);
-
-	value |= XGMAC_LPITXEN | XGMAC_LPITXA;
-	if (en_tx_lpi_clockgating)
-		value |= XGMAC_TXCGE;
-
-	writel(value, ioaddr + XGMAC_LPI_CTRL);
-}
-
-static void dwxgmac2_reset_eee_mode(struct mac_device_info *hw)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
+	if (mode == STMMAC_LPI_TIMER)
+		return -EOPNOTSUPP;
 
 	value = readl(ioaddr + XGMAC_LPI_CTRL);
-	value &= ~(XGMAC_LPITXEN | XGMAC_LPITXA | XGMAC_TXCGE);
+	if (mode == STMMAC_LPI_FORCED) {
+		value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+		if (en_tx_lpi_clockgating)
+			value |= LPI_CTRL_STATUS_LPITCSE;
+	} else {
+		value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA |
+			   LPI_CTRL_STATUS_LPITCSE);
+	}
 	writel(value, ioaddr + XGMAC_LPI_CTRL);
+
+	return 0;
 }
 
 static void dwxgmac2_set_eee_pls(struct mac_device_info *hw, int link)
@@ -457,9 +457,9 @@ static void dwxgmac2_set_eee_pls(struct mac_device_info *hw, int link)
 
 	value = readl(ioaddr + XGMAC_LPI_CTRL);
 	if (link)
-		value |= XGMAC_PLS;
+		value |= LPI_CTRL_STATUS_PLS;
 	else
-		value &= ~XGMAC_PLS;
+		value &= ~LPI_CTRL_STATUS_PLS;
 	writel(value, ioaddr + XGMAC_LPI_CTRL);
 }
 
@@ -615,76 +615,6 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
 	return 0;
 }
 
-static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				      u16 perfect_match, bool is_double)
-{
-	void __iomem *ioaddr = hw->pcsr;
-
-	writel(hash, ioaddr + XGMAC_VLAN_HASH_TABLE);
-
-	if (hash) {
-		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
-
-		value |= XGMAC_FILTER_VTFE;
-
-		writel(value, ioaddr + XGMAC_PACKET_FILTER);
-
-		value = readl(ioaddr + XGMAC_VLAN_TAG);
-
-		value |= XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV;
-		if (is_double) {
-			value |= XGMAC_VLAN_EDVLP;
-			value |= XGMAC_VLAN_ESVL;
-			value |= XGMAC_VLAN_DOVLTC;
-		} else {
-			value &= ~XGMAC_VLAN_EDVLP;
-			value &= ~XGMAC_VLAN_ESVL;
-			value &= ~XGMAC_VLAN_DOVLTC;
-		}
-
-		value &= ~XGMAC_VLAN_VID;
-		writel(value, ioaddr + XGMAC_VLAN_TAG);
-	} else if (perfect_match) {
-		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
-
-		value |= XGMAC_FILTER_VTFE;
-
-		writel(value, ioaddr + XGMAC_PACKET_FILTER);
-
-		value = readl(ioaddr + XGMAC_VLAN_TAG);
-
-		value &= ~XGMAC_VLAN_VTHM;
-		value |= XGMAC_VLAN_ETV;
-		if (is_double) {
-			value |= XGMAC_VLAN_EDVLP;
-			value |= XGMAC_VLAN_ESVL;
-			value |= XGMAC_VLAN_DOVLTC;
-		} else {
-			value &= ~XGMAC_VLAN_EDVLP;
-			value &= ~XGMAC_VLAN_ESVL;
-			value &= ~XGMAC_VLAN_DOVLTC;
-		}
-
-		value &= ~XGMAC_VLAN_VID;
-		writel(value | perfect_match, ioaddr + XGMAC_VLAN_TAG);
-	} else {
-		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
-
-		value &= ~XGMAC_FILTER_VTFE;
-
-		writel(value, ioaddr + XGMAC_PACKET_FILTER);
-
-		value = readl(ioaddr + XGMAC_VLAN_TAG);
-
-		value &= ~(XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV);
-		value &= ~(XGMAC_VLAN_EDVLP | XGMAC_VLAN_ESVL);
-		value &= ~XGMAC_VLAN_DOVLTC;
-		value &= ~XGMAC_VLAN_VID;
-
-		writel(value, ioaddr + XGMAC_VLAN_TAG);
-	}
-}
-
 struct dwxgmac3_error_desc {
 	bool valid;
 	const char *desc;
@@ -1301,19 +1231,6 @@ static void dwxgmac2_sarc_configure(void __iomem *ioaddr, int val)
 	writel(value, ioaddr + XGMAC_TX_CONFIG);
 }
 
-static void dwxgmac2_enable_vlan(struct mac_device_info *hw, u32 type)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-
-	value = readl(ioaddr + XGMAC_VLAN_INCL);
-	value |= XGMAC_VLAN_VLTI;
-	value |= XGMAC_VLAN_CSVL; /* Only use SVLAN */
-	value &= ~XGMAC_VLAN_VLC;
-	value |= (type << XGMAC_VLAN_VLC_SHIFT) & XGMAC_VLAN_VLC;
-	writel(value, ioaddr + XGMAC_VLAN_INCL);
-}
-
 static int dwxgmac2_filter_wait(struct mac_device_info *hw)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -1525,8 +1442,7 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.pmt = dwxgmac2_pmt,
 	.set_umac_addr = dwxgmac2_set_umac_addr,
 	.get_umac_addr = dwxgmac2_get_umac_addr,
-	.set_eee_mode = dwxgmac2_set_eee_mode,
-	.reset_eee_mode = dwxgmac2_reset_eee_mode,
+	.set_lpi_mode = dwxgmac2_set_lpi_mode,
 	.set_eee_timer = dwxgmac2_set_eee_timer,
 	.set_eee_pls = dwxgmac2_set_eee_pls,
 	.debug = NULL,
@@ -1536,12 +1452,10 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.safety_feat_dump = dwxgmac3_safety_feat_dump,
 	.set_mac_loopback = dwxgmac2_set_mac_loopback,
 	.rss_configure = dwxgmac2_rss_configure,
-	.update_vlan_hash = dwxgmac2_update_vlan_hash,
 	.rxp_config = dwxgmac3_rxp_config,
 	.get_mac_tx_timestamp = dwxgmac2_get_mac_tx_timestamp,
 	.flex_pps_config = dwxgmac2_flex_pps_config,
 	.sarc_configure = dwxgmac2_sarc_configure,
-	.enable_vlan = dwxgmac2_enable_vlan,
 	.config_l3_filter = dwxgmac2_config_l3_filter,
 	.config_l4_filter = dwxgmac2_config_l4_filter,
 	.set_arp_offload = dwxgmac2_set_arp_offload,
@@ -1582,8 +1496,7 @@ const struct stmmac_ops dwxlgmac2_ops = {
 	.pmt = dwxgmac2_pmt,
 	.set_umac_addr = dwxgmac2_set_umac_addr,
 	.get_umac_addr = dwxgmac2_get_umac_addr,
-	.set_eee_mode = dwxgmac2_set_eee_mode,
-	.reset_eee_mode = dwxgmac2_reset_eee_mode,
+	.set_lpi_mode = dwxgmac2_set_lpi_mode,
 	.set_eee_timer = dwxgmac2_set_eee_timer,
 	.set_eee_pls = dwxgmac2_set_eee_pls,
 	.debug = NULL,
@@ -1593,12 +1506,10 @@ const struct stmmac_ops dwxlgmac2_ops = {
 	.safety_feat_dump = dwxgmac3_safety_feat_dump,
 	.set_mac_loopback = dwxgmac2_set_mac_loopback,
 	.rss_configure = dwxgmac2_rss_configure,
-	.update_vlan_hash = dwxgmac2_update_vlan_hash,
 	.rxp_config = dwxgmac3_rxp_config,
 	.get_mac_tx_timestamp = dwxgmac2_get_mac_tx_timestamp,
 	.flex_pps_config = dwxgmac2_flex_pps_config,
 	.sarc_configure = dwxgmac2_sarc_configure,
-	.enable_vlan = dwxgmac2_enable_vlan,
 	.config_l3_filter = dwxgmac2_config_l3_filter,
 	.config_l4_filter = dwxgmac2_config_l4_filter,
 	.set_arp_offload = dwxgmac2_set_arp_offload,
@@ -1641,6 +1552,7 @@ int dwxgmac2_setup(struct stmmac_priv *priv)
 	mac->mii.reg_mask = GENMASK(15, 0);
 	mac->mii.clk_csr_shift = 19;
 	mac->mii.clk_csr_mask = GENMASK(21, 19);
+	mac->num_vlan = stmmac_get_num_vlan(priv->ioaddr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index 389aad7b5c1e..a2980482fcce 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -4,6 +4,7 @@
  * stmmac XGMAC support.
  */
 
+#include <linux/bitfield.h>
 #include <linux/stmmac.h>
 #include "common.h"
 #include "dwxgmac2.h"
@@ -69,6 +70,21 @@ static int dwxgmac2_get_tx_ls(struct dma_desc *p)
 	return (le32_to_cpu(p->des3) & XGMAC_RDES3_LD) > 0;
 }
 
+static u16 dwxgmac2_wrback_get_rx_vlan_tci(struct dma_desc *p)
+{
+	return le32_to_cpu(p->des0) & XGMAC_RDES0_VLAN_TAG_MASK;
+}
+
+static bool dwxgmac2_wrback_get_rx_vlan_valid(struct dma_desc *p)
+{
+	u32 et_lt;
+
+	et_lt = FIELD_GET(XGMAC_RDES3_ET_LT, le32_to_cpu(p->des3));
+
+	return et_lt >= XGMAC_ET_LT_VLAN_STAG &&
+	       et_lt <= XGMAC_ET_LT_DVLAN_STAG_CTAG;
+}
+
 static int dwxgmac2_get_rx_frame_len(struct dma_desc *p, int rx_coe)
 {
 	return (le32_to_cpu(p->des3) & XGMAC_RDES3_PL);
@@ -351,6 +367,8 @@ const struct stmmac_desc_ops dwxgmac210_desc_ops = {
 	.set_tx_owner = dwxgmac2_set_tx_owner,
 	.set_rx_owner = dwxgmac2_set_rx_owner,
 	.get_tx_ls = dwxgmac2_get_tx_ls,
+	.get_rx_vlan_tci = dwxgmac2_wrback_get_rx_vlan_tci,
+	.get_rx_vlan_valid = dwxgmac2_wrback_get_rx_vlan_valid,
 	.get_rx_frame_len = dwxgmac2_get_rx_frame_len,
 	.enable_tx_timestamp = dwxgmac2_enable_tx_timestamp,
 	.get_tx_timestamp_status = dwxgmac2_get_tx_timestamp_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index a72d336a8350..99635b37044a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -9,6 +9,9 @@
 #include "stmmac_fpe.h"
 #include "stmmac_ptp.h"
 #include "stmmac_est.h"
+#include "stmmac_vlan.h"
+#include "dwmac4_descs.h"
+#include "dwxgmac2.h"
 
 static u32 stmmac_get_id(struct stmmac_priv *priv, u32 id_reg)
 {
@@ -118,6 +121,7 @@ static const struct stmmac_hwif_entry {
 	const void *tc;
 	const void *mmc;
 	const void *est;
+	const void *vlan;
 	int (*setup)(struct stmmac_priv *priv);
 	int (*quirks)(struct stmmac_priv *priv);
 } stmmac_hw[] = {
@@ -173,6 +177,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac4_dma_ops,
 		.mac = &dwmac4_ops,
+		.vlan = &dwmac_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = NULL,
@@ -195,6 +200,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac4_dma_ops,
 		.mac = &dwmac410_ops,
+		.vlan = &dwmac_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = &dwmac4_ring_mode_ops,
@@ -217,6 +223,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
 		.mac = &dwmac410_ops,
+		.vlan = &dwmac_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = &dwmac4_ring_mode_ops,
@@ -239,6 +246,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
 		.mac = &dwmac510_ops,
+		.vlan = &dwmac_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = &dwmac4_ring_mode_ops,
@@ -262,10 +270,11 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwxgmac210_desc_ops,
 		.dma = &dwxgmac210_dma_ops,
 		.mac = &dwxgmac210_ops,
+		.vlan = &dwxgmac210_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = NULL,
-		.tc = &dwxgmac_tc_ops,
+		.tc = &dwmac510_tc_ops,
 		.mmc = &dwxgmac_mmc_ops,
 		.est = &dwmac510_est_ops,
 		.setup = dwxgmac2_setup,
@@ -285,10 +294,11 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwxgmac210_desc_ops,
 		.dma = &dwxgmac210_dma_ops,
 		.mac = &dwxlgmac2_ops,
+		.vlan = &dwxlgmac2_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = NULL,
-		.tc = &dwxgmac_tc_ops,
+		.tc = &dwmac510_tc_ops,
 		.mmc = &dwxgmac_mmc_ops,
 		.est = &dwmac510_est_ops,
 		.setup = dwxlgmac2_setup,
@@ -366,6 +376,7 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 		mac->tc = mac->tc ? : entry->tc;
 		mac->mmc = mac->mmc ? : entry->mmc;
 		mac->est = mac->est ? : entry->est;
+		mac->vlan = mac->vlan ? : entry->vlan;
 
 		priv->hw = mac;
 		priv->fpe_cfg.reg = entry->regs.fpe_reg;
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 64f8ed67dcc4..ae4efffb785f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -306,6 +306,12 @@ struct stmmac_pps_cfg;
 struct stmmac_rss;
 struct stmmac_est;
 
+enum stmmac_lpi_mode {
+	STMMAC_LPI_DISABLE,
+	STMMAC_LPI_FORCED,
+	STMMAC_LPI_TIMER,
+};
+
 /* Helpers to program the MAC core */
 struct stmmac_ops {
 	/* MAC core initialization */
@@ -360,10 +366,9 @@ struct stmmac_ops {
 			      unsigned int reg_n);
 	void (*get_umac_addr)(struct mac_device_info *hw, unsigned char *addr,
 			      unsigned int reg_n);
-	void (*set_eee_mode)(struct mac_device_info *hw,
-			     bool en_tx_lpi_clockgating);
-	void (*reset_eee_mode)(struct mac_device_info *hw);
-	void (*set_eee_lpi_entry_timer)(struct mac_device_info *hw, int et);
+	int (*set_lpi_mode)(struct mac_device_info *hw,
+			    enum stmmac_lpi_mode mode,
+			    bool en_tx_lpi_clockgating, u32 et);
 	void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw);
 	void (*set_eee_pls)(struct mac_device_info *hw, int link);
 	void (*debug)(struct stmmac_priv *priv, void __iomem *ioaddr,
@@ -393,21 +398,6 @@ struct stmmac_ops {
 	/* RSS */
 	int (*rss_configure)(struct mac_device_info *hw,
 			     struct stmmac_rss *cfg, u32 num_rxq);
-	/* VLAN */
-	void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
-				 u16 perfect_match, bool is_double);
-	void (*enable_vlan)(struct mac_device_info *hw, u32 type);
-	void (*rx_hw_vlan)(struct mac_device_info *hw, struct dma_desc *rx_desc,
-			   struct sk_buff *skb);
-	void (*set_hw_vlan_mode)(struct mac_device_info *hw);
-	int (*add_hw_vlan_rx_fltr)(struct net_device *dev,
-				   struct mac_device_info *hw,
-				   __be16 proto, u16 vid);
-	int (*del_hw_vlan_rx_fltr)(struct net_device *dev,
-				   struct mac_device_info *hw,
-				   __be16 proto, u16 vid);
-	void (*restore_hw_vlan_rx_fltr)(struct net_device *dev,
-					struct mac_device_info *hw);
 	/* TX Timestamp */
 	int (*get_mac_tx_timestamp)(struct mac_device_info *hw, u64 *ts);
 	/* Source Address Insertion / Replacement */
@@ -467,12 +457,8 @@ struct stmmac_ops {
 	stmmac_do_void_callback(__priv, mac, set_umac_addr, __args)
 #define stmmac_get_umac_addr(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, get_umac_addr, __args)
-#define stmmac_set_eee_mode(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, set_eee_mode, __args)
-#define stmmac_reset_eee_mode(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, reset_eee_mode, __args)
-#define stmmac_set_eee_lpi_timer(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, set_eee_lpi_entry_timer, __args)
+#define stmmac_set_lpi_mode(__priv, __args...) \
+	stmmac_do_callback(__priv, mac, set_lpi_mode, __args)
 #define stmmac_set_eee_timer(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, set_eee_timer, __args)
 #define stmmac_set_eee_pls(__priv, __args...) \
@@ -497,20 +483,6 @@ struct stmmac_ops {
 	stmmac_do_void_callback(__priv, mac, set_mac_loopback, __args)
 #define stmmac_rss_configure(__priv, __args...) \
 	stmmac_do_callback(__priv, mac, rss_configure, __args)
-#define stmmac_update_vlan_hash(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, update_vlan_hash, __args)
-#define stmmac_enable_vlan(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, enable_vlan, __args)
-#define stmmac_rx_hw_vlan(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, rx_hw_vlan, __args)
-#define stmmac_set_hw_vlan_mode(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, set_hw_vlan_mode, __args)
-#define stmmac_add_hw_vlan_rx_fltr(__priv, __args...) \
-	stmmac_do_callback(__priv, mac, add_hw_vlan_rx_fltr, __args)
-#define stmmac_del_hw_vlan_rx_fltr(__priv, __args...) \
-	stmmac_do_callback(__priv, mac, del_hw_vlan_rx_fltr, __args)
-#define stmmac_restore_hw_vlan_rx_fltr(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, restore_hw_vlan_rx_fltr, __args)
 #define stmmac_get_mac_tx_timestamp(__priv, __args...) \
 	stmmac_do_callback(__priv, mac, get_mac_tx_timestamp, __args)
 #define stmmac_sarc_configure(__priv, __args...) \
@@ -658,6 +630,39 @@ struct stmmac_est_ops {
 #define stmmac_est_irq_status(__priv, __args...) \
 	stmmac_do_void_callback(__priv, est, irq_status, __args)
 
+struct stmmac_vlan_ops {
+	/* VLAN */
+	void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
+				 u16 perfect_match, bool is_double);
+	void (*enable_vlan)(struct mac_device_info *hw, u32 type);
+	void (*rx_hw_vlan)(struct mac_device_info *hw, struct dma_desc *rx_desc,
+			   struct sk_buff *skb);
+	void (*set_hw_vlan_mode)(struct mac_device_info *hw);
+	int (*add_hw_vlan_rx_fltr)(struct net_device *dev,
+				   struct mac_device_info *hw,
+				   __be16 proto, u16 vid);
+	int (*del_hw_vlan_rx_fltr)(struct net_device *dev,
+				   struct mac_device_info *hw,
+				   __be16 proto, u16 vid);
+	void (*restore_hw_vlan_rx_fltr)(struct net_device *dev,
+					struct mac_device_info *hw);
+};
+
+#define stmmac_update_vlan_hash(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, update_vlan_hash, __args)
+#define stmmac_enable_vlan(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, enable_vlan, __args)
+#define stmmac_rx_hw_vlan(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, rx_hw_vlan, __args)
+#define stmmac_set_hw_vlan_mode(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, set_hw_vlan_mode, __args)
+#define stmmac_add_hw_vlan_rx_fltr(__priv, __args...) \
+	stmmac_do_callback(__priv, vlan, add_hw_vlan_rx_fltr, __args)
+#define stmmac_del_hw_vlan_rx_fltr(__priv, __args...) \
+	stmmac_do_callback(__priv, vlan, del_hw_vlan_rx_fltr, __args)
+#define stmmac_restore_hw_vlan_rx_fltr(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, restore_hw_vlan_rx_fltr, __args)
+
 struct stmmac_regs_off {
 	const struct stmmac_fpe_reg *fpe_reg;
 	u32 ptp_off;
@@ -665,6 +670,15 @@ struct stmmac_regs_off {
 	u32 est_off;
 };
 
+extern const struct stmmac_desc_ops enh_desc_ops;
+extern const struct stmmac_desc_ops ndesc_ops;
+
+extern const struct stmmac_hwtimestamp stmmac_ptp;
+extern const struct stmmac_hwtimestamp dwmac1000_ptp;
+
+extern const struct stmmac_mode_ops ring_mode_ops;
+extern const struct stmmac_mode_ops chain_mode_ops;
+
 extern const struct stmmac_ops dwmac100_ops;
 extern const struct stmmac_dma_ops dwmac100_dma_ops;
 extern const struct stmmac_ops dwmac1000_ops;
@@ -676,14 +690,6 @@ extern const struct stmmac_dma_ops dwmac410_dma_ops;
 extern const struct stmmac_ops dwmac510_ops;
 extern const struct stmmac_tc_ops dwmac4_tc_ops;
 extern const struct stmmac_tc_ops dwmac510_tc_ops;
-extern const struct stmmac_tc_ops dwxgmac_tc_ops;
-extern const struct stmmac_ops dwxgmac210_ops;
-extern const struct stmmac_ops dwxlgmac2_ops;
-extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
-extern const struct stmmac_desc_ops dwxgmac210_desc_ops;
-extern const struct stmmac_mmc_ops dwmac_mmc_ops;
-extern const struct stmmac_mmc_ops dwxgmac_mmc_ops;
-extern const struct stmmac_est_ops dwmac510_est_ops;
 
 #define GMAC_VERSION		0x00000020	/* GMAC CORE Version */
 #define GMAC4_VERSION		0x00000110	/* GMAC4+ CORE Version */
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h
index 5d1ea3e07459..1cba39fb2c44 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc.h
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h
@@ -139,4 +139,7 @@ struct stmmac_counters {
 	unsigned int mmc_rx_fpe_fragment_cntr;
 };
 
+extern const struct stmmac_mmc_ops dwmac_mmc_ops;
+extern const struct stmmac_mmc_ops dwxgmac_mmc_ops;
+
 #endif /* __MMC_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 1d86439b8a14..cda09cf5dcca 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -106,6 +106,8 @@ struct stmmac_metadata_request {
 	struct stmmac_priv *priv;
 	struct dma_desc *tx_desc;
 	bool *set_ic;
+	struct dma_edesc *edesc;
+	int tbs;
 };
 
 struct stmmac_xsk_tx_complete {
@@ -126,7 +128,7 @@ struct stmmac_rx_queue {
 	unsigned int cur_rx;
 	unsigned int dirty_rx;
 	unsigned int buf_alloc_num;
-	u32 rx_zeroc_thresh;
+	unsigned int napi_skb_frag_size;
 	dma_addr_t dma_rx_phy;
 	u32 rx_tail_addr;
 	unsigned int state_saved;
@@ -147,21 +149,9 @@ struct stmmac_channel {
 };
 
 struct stmmac_fpe_cfg {
-	/* Serialize access to MAC Merge state between ethtool requests
-	 * and link state updates.
-	 */
-	spinlock_t lock;
-
+	struct ethtool_mmsv mmsv;
 	const struct stmmac_fpe_reg *reg;
-	u32 fpe_csr;				/* MAC_FPE_CTRL_STS reg cache */
-
-	enum ethtool_mm_verify_status status;
-	struct timer_list verify_timer;
-	bool verify_enabled;
-	int verify_retries;
-	bool pmac_enabled;
-	u32 verify_time;
-	bool tx_enabled;
+	u32 fpe_csr;	/* MAC_FPE_CTRL_STS reg cache */
 };
 
 struct stmmac_tc_entry {
@@ -257,7 +247,7 @@ struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_coal_frames[MTL_MAX_TX_QUEUES];
 	u32 tx_coal_timer[MTL_MAX_TX_QUEUES];
-	u32 rx_coal_frames[MTL_MAX_TX_QUEUES];
+	u32 rx_coal_frames[MTL_MAX_RX_QUEUES];
 
 	int hwts_tx_en;
 	bool tx_path_in_lpi_mode;
@@ -265,9 +255,7 @@ struct stmmac_priv {
 	int sph;
 	int sph_cap;
 	u32 sarc_type;
-
-	unsigned int rx_copybreak;
-	u32 rx_riwt[MTL_MAX_TX_QUEUES];
+	u32 rx_riwt[MTL_MAX_RX_QUEUES];
 	int hwts_rx_en;
 
 	void __iomem *ioaddr;
@@ -282,9 +270,7 @@ struct stmmac_priv {
 	/* Generic channel for NAPI */
 	struct stmmac_channel channel[STMMAC_CH_MAX];
 
-	int speed;
-	unsigned int flow_ctrl;
-	unsigned int pause;
+	unsigned int pause_time;
 	struct mii_bus *mii;
 
 	struct phylink_config phylink_config;
@@ -307,16 +293,15 @@ struct stmmac_priv {
 	int clk_csr;
 	struct timer_list eee_ctrl_timer;
 	int lpi_irq;
-	int eee_enabled;
-	int eee_active;
-	int tx_lpi_timer;
-	int tx_lpi_enabled;
-	int eee_tw_timer;
+	u32 tx_lpi_timer;
+	bool tx_lpi_clk_stop;
+	bool eee_enabled;
+	bool eee_active;
 	bool eee_sw_timer_en;
 	unsigned int mode;
 	unsigned int chain_mode;
 	int extend_desc;
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_clock_ops;
 	unsigned int default_addend;
@@ -346,7 +331,7 @@ struct stmmac_priv {
 	char int_name_sfty[IFNAMSIZ + 10];
 	char int_name_sfty_ce[IFNAMSIZ + 10];
 	char int_name_sfty_ue[IFNAMSIZ + 10];
-	char int_name_rx_irq[MTL_MAX_TX_QUEUES][IFNAMSIZ + 14];
+	char int_name_rx_irq[MTL_MAX_RX_QUEUES][IFNAMSIZ + 14];
 	char int_name_tx_irq[MTL_MAX_TX_QUEUES][IFNAMSIZ + 18];
 
 #ifdef CONFIG_DEBUG_FS
@@ -407,25 +392,17 @@ void stmmac_dvr_remove(struct device *dev);
 int stmmac_dvr_probe(struct device *device,
 		     struct plat_stmmacenet_data *plat_dat,
 		     struct stmmac_resources *res);
-void stmmac_disable_eee_mode(struct stmmac_priv *priv);
-bool stmmac_eee_init(struct stmmac_priv *priv);
 int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt);
 int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size);
 int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled);
+int stmmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+			   phy_interface_t interface, int speed);
 
 static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv)
 {
 	return !!priv->xdp_prog;
 }
 
-static inline unsigned int stmmac_rx_offset(struct stmmac_priv *priv)
-{
-	if (stmmac_xdp_is_enabled(priv))
-		return XDP_PACKET_HEADROOM;
-
-	return 0;
-}
-
 void stmmac_disable_rx_queue(struct stmmac_priv *priv, u32 queue);
 void stmmac_enable_rx_queue(struct stmmac_priv *priv, u32 queue);
 void stmmac_disable_tx_queue(struct stmmac_priv *priv, u32 queue);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
index c9693f77e1f6..ac6f2e3a3fcd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
@@ -32,6 +32,11 @@ static int est_configure(struct stmmac_priv *priv, struct stmmac_est *cfg,
 	int i, ret = 0;
 	u32 ctrl;
 
+	if (!ptp_rate) {
+		netdev_warn(priv->dev, "Invalid PTP rate");
+		return -EINVAL;
+	}
+
 	ret |= est_write(est_addr, EST_BTR_LOW, cfg->btr[0], false);
 	ret |= est_write(est_addr, EST_BTR_HIGH, cfg->btr[1], false);
 	ret |= est_write(est_addr, EST_TER, cfg->ter, false);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h
index 7a858c566e7e..d247fa383a6e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.h
@@ -62,3 +62,5 @@
 #define EST_SRWO			BIT(0)
 
 #define EST_GCL_DATA			0x00000034
+
+extern const struct stmmac_est_ops dwmac510_est_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 1d77389ce953..f702f7b7bf9f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -37,7 +37,7 @@
 #define ETHTOOL_DMA_OFFSET	55
 
 struct stmmac_stats {
-	char stat_string[ETH_GSTRING_LEN];
+	char stat_string[ETH_GSTRING_LEN] __nonstring;
 	int sizeof_stat;
 	int stat_offset;
 };
@@ -654,7 +654,7 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 					     (*(u32 *)p);
 			}
 		}
-		if (priv->eee_enabled) {
+		if (priv->dma_cap.eee) {
 			int val = phylink_get_eee_err(priv->phylink);
 			if (val)
 				priv->xstats.phy_eee_wakeup_error_n = val;
@@ -898,9 +898,6 @@ static int stmmac_ethtool_op_get_eee(struct net_device *dev,
 	if (!priv->dma_cap.eee)
 		return -EOPNOTSUPP;
 
-	edata->tx_lpi_timer = priv->tx_lpi_timer;
-	edata->tx_lpi_enabled = priv->tx_lpi_enabled;
-
 	return phylink_ethtool_get_eee(priv->phylink, edata);
 }
 
@@ -908,29 +905,11 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev,
 				     struct ethtool_keee *edata)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	int ret;
 
 	if (!priv->dma_cap.eee)
 		return -EOPNOTSUPP;
 
-	if (priv->tx_lpi_enabled != edata->tx_lpi_enabled)
-		netdev_warn(priv->dev,
-			    "Setting EEE tx-lpi is not supported\n");
-
-	if (!edata->eee_enabled)
-		stmmac_disable_eee_mode(priv);
-
-	ret = phylink_ethtool_set_eee(priv->phylink, edata);
-	if (ret)
-		return ret;
-
-	if (edata->eee_enabled &&
-	    priv->tx_lpi_timer != edata->tx_lpi_timer) {
-		priv->tx_lpi_timer = edata->tx_lpi_timer;
-		stmmac_eee_init(priv);
-	}
-
-	return 0;
+	return phylink_ethtool_set_eee(priv->phylink, edata);
 }
 
 static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv)
@@ -1227,77 +1206,20 @@ static int stmmac_get_ts_info(struct net_device *dev,
 		return ethtool_op_get_ts_info(dev, info);
 }
 
-static int stmmac_get_tunable(struct net_device *dev,
-			      const struct ethtool_tunable *tuna, void *data)
-{
-	struct stmmac_priv *priv = netdev_priv(dev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		*(u32 *)data = priv->rx_copybreak;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
-static int stmmac_set_tunable(struct net_device *dev,
-			      const struct ethtool_tunable *tuna,
-			      const void *data)
-{
-	struct stmmac_priv *priv = netdev_priv(dev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		priv->rx_copybreak = *(u32 *)data;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
 static int stmmac_get_mm(struct net_device *ndev,
 			 struct ethtool_mm_state *state)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
-	unsigned long flags;
 	u32 frag_size;
 
 	if (!stmmac_fpe_supported(priv))
 		return -EOPNOTSUPP;
 
-	spin_lock_irqsave(&priv->fpe_cfg.lock, flags);
-
-	state->max_verify_time = STMMAC_FPE_MM_MAX_VERIFY_TIME_MS;
-	state->verify_enabled = priv->fpe_cfg.verify_enabled;
-	state->pmac_enabled = priv->fpe_cfg.pmac_enabled;
-	state->verify_time = priv->fpe_cfg.verify_time;
-	state->tx_enabled = priv->fpe_cfg.tx_enabled;
-	state->verify_status = priv->fpe_cfg.status;
 	state->rx_min_frag_size = ETH_ZLEN;
-
-	/* FPE active if common tx_enabled and
-	 * (verification success or disabled(forced))
-	 */
-	if (state->tx_enabled &&
-	    (state->verify_status == ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED ||
-	     state->verify_status == ETHTOOL_MM_VERIFY_STATUS_DISABLED))
-		state->tx_active = true;
-	else
-		state->tx_active = false;
-
 	frag_size = stmmac_fpe_get_add_frag_size(priv);
 	state->tx_min_frag_size = ethtool_mm_frag_size_add_to_min(frag_size);
 
-	spin_unlock_irqrestore(&priv->fpe_cfg.lock, flags);
+	ethtool_mmsv_get_mm(&priv->fpe_cfg.mmsv, state);
 
 	return 0;
 }
@@ -1306,8 +1228,6 @@ static int stmmac_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg,
 			 struct netlink_ext_ack *extack)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
-	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-	unsigned long flags;
 	u32 frag_size;
 	int err;
 
@@ -1316,23 +1236,8 @@ static int stmmac_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg,
 	if (err)
 		return err;
 
-	/* Wait for the verification that's currently in progress to finish */
-	timer_shutdown_sync(&fpe_cfg->verify_timer);
-
-	spin_lock_irqsave(&fpe_cfg->lock, flags);
-
-	fpe_cfg->verify_enabled = cfg->verify_enabled;
-	fpe_cfg->pmac_enabled = cfg->pmac_enabled;
-	fpe_cfg->verify_time = cfg->verify_time;
-	fpe_cfg->tx_enabled = cfg->tx_enabled;
-
-	if (!cfg->verify_enabled)
-		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
-
 	stmmac_fpe_set_add_frag_size(priv, frag_size);
-	stmmac_fpe_apply(priv);
-
-	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
+	ethtool_mmsv_set_mm(&priv->fpe_cfg.mmsv, cfg);
 
 	return 0;
 }
@@ -1390,8 +1295,6 @@ static const struct ethtool_ops stmmac_ethtool_ops = {
 	.set_per_queue_coalesce = stmmac_set_per_queue_coalesce,
 	.get_channels = stmmac_get_channels,
 	.set_channels = stmmac_set_channels,
-	.get_tunable = stmmac_get_tunable,
-	.set_tunable = stmmac_set_tunable,
 	.get_link_ksettings = stmmac_ethtool_get_link_ksettings,
 	.set_link_ksettings = stmmac_ethtool_set_link_ksettings,
 	.get_mm = stmmac_get_mm,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c
index 3a4bee029c7f..75b470ee621a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c
@@ -27,12 +27,6 @@
 #define STMMAC_MAC_FPE_CTRL_STS_SVER	BIT(1)
 #define STMMAC_MAC_FPE_CTRL_STS_EFPE	BIT(0)
 
-/* FPE link-partner hand-shaking mPacket type */
-enum stmmac_mpacket_type {
-	MPACKET_VERIFY = 0,
-	MPACKET_RESPONSE = 1,
-};
-
 struct stmmac_fpe_reg {
 	const u32 mac_fpe_reg;		/* offset of MAC_FPE_CTRL_STS */
 	const u32 mtl_fpe_reg;		/* offset of MTL_FPE_CTRL_STS */
@@ -48,10 +42,10 @@ bool stmmac_fpe_supported(struct stmmac_priv *priv)
 		priv->hw->mac->fpe_map_preemption_class;
 }
 
-static void stmmac_fpe_configure(struct stmmac_priv *priv, bool tx_enable,
-				 bool pmac_enable)
+static void stmmac_fpe_configure_tx(struct ethtool_mmsv *mmsv, bool tx_enable)
 {
-	struct stmmac_fpe_cfg *cfg = &priv->fpe_cfg;
+	struct stmmac_fpe_cfg *cfg = container_of(mmsv, struct stmmac_fpe_cfg, mmsv);
+	struct stmmac_priv *priv = container_of(cfg, struct stmmac_priv, fpe_cfg);
 	const struct stmmac_fpe_reg *reg = cfg->reg;
 	u32 num_rxq = priv->plat->rx_queues_to_use;
 	void __iomem *ioaddr = priv->ioaddr;
@@ -68,6 +62,15 @@ static void stmmac_fpe_configure(struct stmmac_priv *priv, bool tx_enable,
 		cfg->fpe_csr = 0;
 	}
 	writel(cfg->fpe_csr, ioaddr + reg->mac_fpe_reg);
+}
+
+static void stmmac_fpe_configure_pmac(struct ethtool_mmsv *mmsv, bool pmac_enable)
+{
+	struct stmmac_fpe_cfg *cfg = container_of(mmsv, struct stmmac_fpe_cfg, mmsv);
+	struct stmmac_priv *priv = container_of(cfg, struct stmmac_priv, fpe_cfg);
+	const struct stmmac_fpe_reg *reg = cfg->reg;
+	void __iomem *ioaddr = priv->ioaddr;
+	u32 value;
 
 	value = readl(ioaddr + reg->int_en_reg);
 
@@ -85,47 +88,45 @@ static void stmmac_fpe_configure(struct stmmac_priv *priv, bool tx_enable,
 	writel(value, ioaddr + reg->int_en_reg);
 }
 
-static void stmmac_fpe_send_mpacket(struct stmmac_priv *priv,
-				    enum stmmac_mpacket_type type)
+static void stmmac_fpe_send_mpacket(struct ethtool_mmsv *mmsv,
+				    enum ethtool_mpacket type)
 {
-	const struct stmmac_fpe_reg *reg = priv->fpe_cfg.reg;
+	struct stmmac_fpe_cfg *cfg = container_of(mmsv, struct stmmac_fpe_cfg, mmsv);
+	struct stmmac_priv *priv = container_of(cfg, struct stmmac_priv, fpe_cfg);
+	const struct stmmac_fpe_reg *reg = cfg->reg;
 	void __iomem *ioaddr = priv->ioaddr;
-	u32 value = priv->fpe_cfg.fpe_csr;
+	u32 value = cfg->fpe_csr;
 
-	if (type == MPACKET_VERIFY)
+	if (type == ETHTOOL_MPACKET_VERIFY)
 		value |= STMMAC_MAC_FPE_CTRL_STS_SVER;
-	else if (type == MPACKET_RESPONSE)
+	else if (type == ETHTOOL_MPACKET_RESPONSE)
 		value |= STMMAC_MAC_FPE_CTRL_STS_SRSP;
 
 	writel(value, ioaddr + reg->mac_fpe_reg);
 }
 
+static const struct ethtool_mmsv_ops stmmac_mmsv_ops = {
+	.configure_tx = stmmac_fpe_configure_tx,
+	.configure_pmac = stmmac_fpe_configure_pmac,
+	.send_mpacket = stmmac_fpe_send_mpacket,
+};
+
 static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status)
 {
 	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
+	struct ethtool_mmsv *mmsv = &fpe_cfg->mmsv;
 
-	/* This is interrupt context, just spin_lock() */
-	spin_lock(&fpe_cfg->lock);
-
-	if (!fpe_cfg->pmac_enabled || status == FPE_EVENT_UNKNOWN)
-		goto unlock_out;
+	if (status == FPE_EVENT_UNKNOWN)
+		return;
 
-	/* LP has sent verify mPacket */
 	if ((status & FPE_EVENT_RVER) == FPE_EVENT_RVER)
-		stmmac_fpe_send_mpacket(priv, MPACKET_RESPONSE);
+		ethtool_mmsv_event_handle(mmsv, ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET);
 
-	/* Local has sent verify mPacket */
-	if ((status & FPE_EVENT_TVER) == FPE_EVENT_TVER &&
-	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED)
-		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_VERIFYING;
+	if ((status & FPE_EVENT_TVER) == FPE_EVENT_TVER)
+		ethtool_mmsv_event_handle(mmsv, ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET);
 
-	/* LP has sent response mPacket */
-	if ((status & FPE_EVENT_RRSP) == FPE_EVENT_RRSP &&
-	    fpe_cfg->status == ETHTOOL_MM_VERIFY_STATUS_VERIFYING)
-		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED;
-
-unlock_out:
-	spin_unlock(&fpe_cfg->lock);
+	if ((status & FPE_EVENT_RRSP) == FPE_EVENT_RRSP)
+		ethtool_mmsv_event_handle(mmsv, ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET);
 }
 
 void stmmac_fpe_irq_status(struct stmmac_priv *priv)
@@ -164,119 +165,16 @@ void stmmac_fpe_irq_status(struct stmmac_priv *priv)
 	stmmac_fpe_event_status(priv, status);
 }
 
-/**
- * stmmac_fpe_verify_timer - Timer for MAC Merge verification
- * @t:  timer_list struct containing private info
- *
- * Verify the MAC Merge capability in the local TX direction, by
- * transmitting Verify mPackets up to 3 times. Wait until link
- * partner responds with a Response mPacket, otherwise fail.
- */
-static void stmmac_fpe_verify_timer(struct timer_list *t)
-{
-	struct stmmac_fpe_cfg *fpe_cfg = from_timer(fpe_cfg, t, verify_timer);
-	struct stmmac_priv *priv = container_of(fpe_cfg, struct stmmac_priv,
-						fpe_cfg);
-	unsigned long flags;
-	bool rearm = false;
-
-	spin_lock_irqsave(&fpe_cfg->lock, flags);
-
-	switch (fpe_cfg->status) {
-	case ETHTOOL_MM_VERIFY_STATUS_INITIAL:
-	case ETHTOOL_MM_VERIFY_STATUS_VERIFYING:
-		if (fpe_cfg->verify_retries != 0) {
-			stmmac_fpe_send_mpacket(priv, MPACKET_VERIFY);
-			rearm = true;
-		} else {
-			fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_FAILED;
-		}
-
-		fpe_cfg->verify_retries--;
-		break;
-
-	case ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED:
-		stmmac_fpe_configure(priv, true, true);
-		break;
-
-	default:
-		break;
-	}
-
-	if (rearm) {
-		mod_timer(&fpe_cfg->verify_timer,
-			  jiffies + msecs_to_jiffies(fpe_cfg->verify_time));
-	}
-
-	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
-}
-
-static void stmmac_fpe_verify_timer_arm(struct stmmac_fpe_cfg *fpe_cfg)
-{
-	if (fpe_cfg->pmac_enabled && fpe_cfg->tx_enabled &&
-	    fpe_cfg->verify_enabled &&
-	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_FAILED &&
-	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED) {
-		timer_setup(&fpe_cfg->verify_timer, stmmac_fpe_verify_timer, 0);
-		mod_timer(&fpe_cfg->verify_timer, jiffies);
-	}
-}
-
 void stmmac_fpe_init(struct stmmac_priv *priv)
 {
-	priv->fpe_cfg.verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES;
-	priv->fpe_cfg.verify_time = STMMAC_FPE_MM_MAX_VERIFY_TIME_MS;
-	priv->fpe_cfg.status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
-	timer_setup(&priv->fpe_cfg.verify_timer, stmmac_fpe_verify_timer, 0);
-	spin_lock_init(&priv->fpe_cfg.lock);
+	ethtool_mmsv_init(&priv->fpe_cfg.mmsv, priv->dev,
+			  &stmmac_mmsv_ops);
 
 	if ((!priv->fpe_cfg.reg || !priv->hw->mac->fpe_map_preemption_class) &&
 	    priv->dma_cap.fpesel)
 		dev_info(priv->device, "FPE is not supported by driver.\n");
 }
 
-void stmmac_fpe_apply(struct stmmac_priv *priv)
-{
-	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-
-	/* If verification is disabled, configure FPE right away.
-	 * Otherwise let the timer code do it.
-	 */
-	if (!fpe_cfg->verify_enabled) {
-		stmmac_fpe_configure(priv, fpe_cfg->tx_enabled,
-				     fpe_cfg->pmac_enabled);
-	} else {
-		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_INITIAL;
-		fpe_cfg->verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES;
-
-		if (netif_running(priv->dev))
-			stmmac_fpe_verify_timer_arm(fpe_cfg);
-	}
-}
-
-void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
-{
-	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-	unsigned long flags;
-
-	timer_shutdown_sync(&fpe_cfg->verify_timer);
-
-	spin_lock_irqsave(&fpe_cfg->lock, flags);
-
-	if (is_up && fpe_cfg->pmac_enabled) {
-		/* VERIFY process requires pmac enabled when NIC comes up */
-		stmmac_fpe_configure(priv, false, true);
-
-		/* New link => maybe new partner => new verification process */
-		stmmac_fpe_apply(priv);
-	} else {
-		/* No link => turn off EFPE */
-		stmmac_fpe_configure(priv, false, false);
-	}
-
-	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
-}
-
 int stmmac_fpe_get_add_frag_size(struct stmmac_priv *priv)
 {
 	const struct stmmac_fpe_reg *reg = priv->fpe_cfg.reg;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h
index b884eac7142d..3fc46acf7001 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h
@@ -9,15 +9,10 @@
 #include <linux/types.h>
 #include <linux/netdevice.h>
 
-#define STMMAC_FPE_MM_MAX_VERIFY_RETRIES	3
-#define STMMAC_FPE_MM_MAX_VERIFY_TIME_MS	128
-
 struct stmmac_priv;
 
-void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up);
 bool stmmac_fpe_supported(struct stmmac_priv *priv);
 void stmmac_fpe_init(struct stmmac_priv *priv);
-void stmmac_fpe_apply(struct stmmac_priv *priv);
 void stmmac_fpe_irq_status(struct stmmac_priv *priv);
 int stmmac_fpe_get_add_frag_size(struct stmmac_priv *priv);
 void stmmac_fpe_set_add_frag_size(struct stmmac_priv *priv, u32 add_frag_size);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 0f59aa982604..e2840fa241f2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -222,7 +222,7 @@ static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
 	u64 ns;
 
 	ns = readl(ptpaddr + PTP_ATNR);
-	ns += readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
+	ns += (u64)readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
 
 	*ptp_time = ns;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9b262cdad60b..b948df1bff9a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -77,7 +77,6 @@ module_param(phyaddr, int, 0444);
 MODULE_PARM_DESC(phyaddr, "Physical device address");
 
 #define STMMAC_TX_THRESH(x)	((x)->dma_conf.dma_tx_size / 4)
-#define STMMAC_RX_THRESH(x)	((x)->dma_conf.dma_rx_size / 4)
 
 /* Limit to make sure XDP TX and slow path can coexist */
 #define STMMAC_XSK_TX_BUDGET_MAX	256
@@ -89,33 +88,32 @@ MODULE_PARM_DESC(phyaddr, "Physical device address");
 #define STMMAC_XDP_TX		BIT(1)
 #define STMMAC_XDP_REDIRECT	BIT(2)
 
-static int flow_ctrl = FLOW_AUTO;
+static int flow_ctrl = 0xdead;
 module_param(flow_ctrl, int, 0644);
-MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off]");
+MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off] (obsolete)");
 
 static int pause = PAUSE_TIME;
 module_param(pause, int, 0644);
-MODULE_PARM_DESC(pause, "Flow Control Pause Time");
+MODULE_PARM_DESC(pause, "Flow Control Pause Time (units of 512 bit times)");
 
 #define TC_DEFAULT 64
 static int tc = TC_DEFAULT;
 module_param(tc, int, 0644);
 MODULE_PARM_DESC(tc, "DMA threshold control value");
 
+/* This is unused */
 #define	DEFAULT_BUFSIZE	1536
 static int buf_sz = DEFAULT_BUFSIZE;
 module_param(buf_sz, int, 0644);
 MODULE_PARM_DESC(buf_sz, "DMA buffer size");
 
-#define	STMMAC_RX_COPYBREAK	256
-
 static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
 				      NETIF_MSG_LINK | NETIF_MSG_IFUP |
 				      NETIF_MSG_IFDOWN | NETIF_MSG_TIMER);
 
 #define STMMAC_DEFAULT_LPI_TIMER	1000
-static int eee_timer = STMMAC_DEFAULT_LPI_TIMER;
-module_param(eee_timer, int, 0644);
+static unsigned int eee_timer = STMMAC_DEFAULT_LPI_TIMER;
+module_param(eee_timer, uint, 0644);
 MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec");
 #define STMMAC_LPI_T(x) (jiffies + usecs_to_jiffies(x))
 
@@ -181,6 +179,38 @@ int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled)
 EXPORT_SYMBOL_GPL(stmmac_bus_clks_config);
 
 /**
+ * stmmac_set_clk_tx_rate() - set the clock rate for the MAC transmit clock
+ * @bsp_priv: BSP private data structure (unused)
+ * @clk_tx_i: the transmit clock
+ * @interface: the selected interface mode
+ * @speed: the speed that the MAC will be operating at
+ *
+ * Set the transmit clock rate for the MAC, normally 2.5MHz for 10Mbps,
+ * 25MHz for 100Mbps and 125MHz for 1Gbps. This is suitable for at least
+ * MII, GMII, RGMII and RMII interface modes. Platforms can hook this into
+ * the plat_data->set_clk_tx_rate method directly, call it via their own
+ * implementation, or implement their own method should they have more
+ * complex requirements. It is intended to only be used in this method.
+ *
+ * plat_data->clk_tx_i must be filled in.
+ */
+int stmmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+			   phy_interface_t interface, int speed)
+{
+	long rate = rgmii_clock(speed);
+
+	/* Silently ignore unsupported speeds as rgmii_clock() only
+	 * supports 10, 100 and 1000Mbps. We do not want to spit
+	 * errors for 2500 and higher speeds here.
+	 */
+	if (rate < 0)
+		return 0;
+
+	return clk_set_rate(clk_tx_i, rate);
+}
+EXPORT_SYMBOL_GPL(stmmac_set_clk_tx_rate);
+
+/**
  * stmmac_verify_args - verify the driver parameters.
  * Description: it checks the driver parameters and set a default in case of
  * errors.
@@ -189,16 +219,11 @@ static void stmmac_verify_args(void)
 {
 	if (unlikely(watchdog < 0))
 		watchdog = TX_TIMEO;
-	if (unlikely((buf_sz < DEFAULT_BUFSIZE) || (buf_sz > BUF_SIZE_16KiB)))
-		buf_sz = DEFAULT_BUFSIZE;
-	if (unlikely(flow_ctrl > 1))
-		flow_ctrl = FLOW_AUTO;
-	else if (likely(flow_ctrl < 0))
-		flow_ctrl = FLOW_OFF;
 	if (unlikely((pause < 0) || (pause > 0xffff)))
 		pause = PAUSE_TIME;
-	if (eee_timer < 0)
-		eee_timer = STMMAC_DEFAULT_LPI_TIMER;
+
+	if (flow_ctrl != 0xdead)
+		pr_warn("stmmac: module parameter 'flow_ctrl' is obsolete - please remove from your module configuration\n");
 }
 
 static void __stmmac_disable_all_queues(struct stmmac_priv *priv)
@@ -301,7 +326,7 @@ static void stmmac_global_err(struct stmmac_priv *priv)
  */
 static void stmmac_clk_csr_set(struct stmmac_priv *priv)
 {
-	u32 clk_rate;
+	unsigned long clk_rate;
 
 	clk_rate = clk_get_rate(priv->plat->stmmac_clk);
 
@@ -325,6 +350,10 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv)
 			priv->clk_csr = STMMAC_CSR_150_250M;
 		else if ((clk_rate >= CSR_F_250M) && (clk_rate <= CSR_F_300M))
 			priv->clk_csr = STMMAC_CSR_250_300M;
+		else if ((clk_rate >= CSR_F_300M) && (clk_rate < CSR_F_500M))
+			priv->clk_csr = STMMAC_CSR_300_500M;
+		else if ((clk_rate >= CSR_F_500M) && (clk_rate < CSR_F_800M))
+			priv->clk_csr = STMMAC_CSR_500_800M;
 	}
 
 	if (priv->plat->flags & STMMAC_FLAG_HAS_SUN8I) {
@@ -391,23 +420,7 @@ static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue)
 	return dirty;
 }
 
-static void stmmac_lpi_entry_timer_config(struct stmmac_priv *priv, bool en)
-{
-	int tx_lpi_timer;
-
-	/* Clear/set the SW EEE timer flag based on LPI ET enablement */
-	priv->eee_sw_timer_en = en ? 0 : 1;
-	tx_lpi_timer  = en ? priv->tx_lpi_timer : 0;
-	stmmac_set_eee_lpi_timer(priv, priv->hw, tx_lpi_timer);
-}
-
-/**
- * stmmac_enable_eee_mode - check and enter in LPI mode
- * @priv: driver private structure
- * Description: this function is to verify and enter in LPI mode in case of
- * EEE.
- */
-static int stmmac_enable_eee_mode(struct stmmac_priv *priv)
+static bool stmmac_eee_tx_busy(struct stmmac_priv *priv)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	u32 queue;
@@ -417,31 +430,45 @@ static int stmmac_enable_eee_mode(struct stmmac_priv *priv)
 		struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
 
 		if (tx_q->dirty_tx != tx_q->cur_tx)
-			return -EBUSY; /* still unfinished work */
+			return true; /* still unfinished work */
 	}
 
-	/* Check and enter in LPI mode */
-	if (!priv->tx_path_in_lpi_mode)
-		stmmac_set_eee_mode(priv, priv->hw,
-			priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING);
-	return 0;
+	return false;
+}
+
+static void stmmac_restart_sw_lpi_timer(struct stmmac_priv *priv)
+{
+	mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
 }
 
 /**
- * stmmac_disable_eee_mode - disable and exit from LPI mode
+ * stmmac_try_to_start_sw_lpi - check and enter in LPI mode
  * @priv: driver private structure
- * Description: this function is to exit and disable EEE in case of
- * LPI state is true. This is called by the xmit.
+ * Description: this function is to verify and enter in LPI mode in case of
+ * EEE.
  */
-void stmmac_disable_eee_mode(struct stmmac_priv *priv)
+static void stmmac_try_to_start_sw_lpi(struct stmmac_priv *priv)
 {
-	if (!priv->eee_sw_timer_en) {
-		stmmac_lpi_entry_timer_config(priv, 0);
+	if (stmmac_eee_tx_busy(priv)) {
+		stmmac_restart_sw_lpi_timer(priv);
 		return;
 	}
 
-	stmmac_reset_eee_mode(priv, priv->hw);
-	del_timer_sync(&priv->eee_ctrl_timer);
+	/* Check and enter in LPI mode */
+	if (!priv->tx_path_in_lpi_mode)
+		stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_FORCED,
+				    priv->tx_lpi_clk_stop, 0);
+}
+
+/**
+ * stmmac_stop_sw_lpi - stop transmitting LPI
+ * @priv: driver private structure
+ * Description: When using software-controlled LPI, stop transmitting LPI state.
+ */
+static void stmmac_stop_sw_lpi(struct stmmac_priv *priv)
+{
+	timer_delete_sync(&priv->eee_ctrl_timer);
+	stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_DISABLE, false, 0);
 	priv->tx_path_in_lpi_mode = false;
 }
 
@@ -454,69 +481,9 @@ void stmmac_disable_eee_mode(struct stmmac_priv *priv)
  */
 static void stmmac_eee_ctrl_timer(struct timer_list *t)
 {
-	struct stmmac_priv *priv = from_timer(priv, t, eee_ctrl_timer);
-
-	if (stmmac_enable_eee_mode(priv))
-		mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
-}
-
-/**
- * stmmac_eee_init - init EEE
- * @priv: driver private structure
- * Description:
- *  if the GMAC supports the EEE (from the HW cap reg) and the phy device
- *  can also manage EEE, this function enable the LPI state and start related
- *  timer.
- */
-bool stmmac_eee_init(struct stmmac_priv *priv)
-{
-	int eee_tw_timer = priv->eee_tw_timer;
-
-	/* Check if MAC core supports the EEE feature. */
-	if (!priv->dma_cap.eee)
-		return false;
-
-	mutex_lock(&priv->lock);
-
-	/* Check if it needs to be deactivated */
-	if (!priv->eee_active) {
-		if (priv->eee_enabled) {
-			netdev_dbg(priv->dev, "disable EEE\n");
-			stmmac_lpi_entry_timer_config(priv, 0);
-			del_timer_sync(&priv->eee_ctrl_timer);
-			stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer);
-			if (priv->hw->xpcs)
-				xpcs_config_eee(priv->hw->xpcs,
-						priv->plat->mult_fact_100ns,
-						false);
-		}
-		mutex_unlock(&priv->lock);
-		return false;
-	}
-
-	if (priv->eee_active && !priv->eee_enabled) {
-		timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0);
-		stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
-				     eee_tw_timer);
-		if (priv->hw->xpcs)
-			xpcs_config_eee(priv->hw->xpcs,
-					priv->plat->mult_fact_100ns,
-					true);
-	}
+	struct stmmac_priv *priv = timer_container_of(priv, t, eee_ctrl_timer);
 
-	if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {
-		del_timer_sync(&priv->eee_ctrl_timer);
-		priv->tx_path_in_lpi_mode = false;
-		stmmac_lpi_entry_timer_config(priv, 1);
-	} else {
-		stmmac_lpi_entry_timer_config(priv, 0);
-		mod_timer(&priv->eee_ctrl_timer,
-			  STMMAC_LPI_T(priv->tx_lpi_timer));
-	}
-
-	mutex_unlock(&priv->lock);
-	netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
-	return true;
+	stmmac_try_to_start_sw_lpi(priv);
 }
 
 /* stmmac_get_tx_hwtstamp - get HW TX timestamps
@@ -601,18 +568,19 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 /**
  *  stmmac_hwtstamp_set - control hardware timestamping.
  *  @dev: device pointer.
- *  @ifr: An IOCTL specific structure, that can contain a pointer to
- *  a proprietary structure used to pass information to the driver.
+ *  @config: the timestamping configuration.
+ *  @extack: netlink extended ack structure for error reporting.
  *  Description:
  *  This function configures the MAC to enable/disable both outgoing(TX)
  *  and incoming(RX) packets time stamping based on user input.
  *  Return Value:
  *  0 on success and an appropriate -ve integer on failure.
  */
-static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+static int stmmac_hwtstamp_set(struct net_device *dev,
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config config;
 	u32 ptp_v2 = 0;
 	u32 tstamp_all = 0;
 	u32 ptp_over_ipv4_udp = 0;
@@ -623,34 +591,36 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	u32 ts_event_en = 0;
 
 	if (!(priv->dma_cap.time_stamp || priv->adv_ts)) {
-		netdev_alert(priv->dev, "No support for HW time stamping\n");
+		NL_SET_ERR_MSG_MOD(extack, "No support for HW time stamping");
 		priv->hwts_tx_en = 0;
 		priv->hwts_rx_en = 0;
 
 		return -EOPNOTSUPP;
 	}
 
-	if (copy_from_user(&config, ifr->ifr_data,
-			   sizeof(config)))
-		return -EFAULT;
+	if (!netif_running(dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot change timestamping configuration while down");
+		return -ENODEV;
+	}
 
 	netdev_dbg(priv->dev, "%s config flags:0x%x, tx_type:0x%x, rx_filter:0x%x\n",
-		   __func__, config.flags, config.tx_type, config.rx_filter);
+		   __func__, config->flags, config->tx_type, config->rx_filter);
 
-	if (config.tx_type != HWTSTAMP_TX_OFF &&
-	    config.tx_type != HWTSTAMP_TX_ON)
+	if (config->tx_type != HWTSTAMP_TX_OFF &&
+	    config->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
 	if (priv->adv_ts) {
-		switch (config.rx_filter) {
+		switch (config->rx_filter) {
 		case HWTSTAMP_FILTER_NONE:
 			/* time stamp no incoming packet at all */
-			config.rx_filter = HWTSTAMP_FILTER_NONE;
+			config->rx_filter = HWTSTAMP_FILTER_NONE;
 			break;
 
 		case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 			/* PTP v1, UDP, any kind of event packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 			/* 'xmac' hardware can support Sync, Pdelay_Req and
 			 * Pdelay_resp by setting bit14 and bits17/16 to 01
 			 * This leaves Delay_Req timestamps out.
@@ -664,7 +634,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 			/* PTP v1, UDP, Sync packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
 			/* take time stamp for SYNC messages only */
 			ts_event_en = PTP_TCR_TSEVNTENA;
 
@@ -674,7 +644,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 			/* PTP v1, UDP, Delay_req packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
 			/* take time stamp for Delay_Req messages only */
 			ts_master_en = PTP_TCR_TSMSTRENA;
 			ts_event_en = PTP_TCR_TSEVNTENA;
@@ -685,7 +655,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 			/* PTP v2, UDP, any kind of event packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for all event messages */
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
@@ -696,7 +666,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 			/* PTP v2, UDP, Sync packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_SYNC;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_SYNC;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for SYNC messages only */
 			ts_event_en = PTP_TCR_TSEVNTENA;
@@ -707,7 +677,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 			/* PTP v2, UDP, Delay_req packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for Delay_Req messages only */
 			ts_master_en = PTP_TCR_TSMSTRENA;
@@ -719,7 +689,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_EVENT:
 			/* PTP v2/802.AS1 any layer, any kind of event packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
 			if (priv->synopsys_id < DWMAC_CORE_4_10)
@@ -731,7 +701,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_SYNC:
 			/* PTP v2/802.AS1, any layer, Sync packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_SYNC;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_SYNC;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for SYNC messages only */
 			ts_event_en = PTP_TCR_TSEVNTENA;
@@ -743,7 +713,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 			/* PTP v2/802.AS1, any layer, Delay_req packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_DELAY_REQ;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_DELAY_REQ;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for Delay_Req messages only */
 			ts_master_en = PTP_TCR_TSMSTRENA;
@@ -757,7 +727,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 		case HWTSTAMP_FILTER_NTP_ALL:
 		case HWTSTAMP_FILTER_ALL:
 			/* time stamp any incoming packet */
-			config.rx_filter = HWTSTAMP_FILTER_ALL;
+			config->rx_filter = HWTSTAMP_FILTER_ALL;
 			tstamp_all = PTP_TCR_TSENALL;
 			break;
 
@@ -765,18 +735,18 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 			return -ERANGE;
 		}
 	} else {
-		switch (config.rx_filter) {
+		switch (config->rx_filter) {
 		case HWTSTAMP_FILTER_NONE:
-			config.rx_filter = HWTSTAMP_FILTER_NONE;
+			config->rx_filter = HWTSTAMP_FILTER_NONE;
 			break;
 		default:
 			/* PTP v1, UDP, any kind of event packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 			break;
 		}
 	}
-	priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1);
-	priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON;
+	priv->hwts_rx_en = config->rx_filter != HWTSTAMP_FILTER_NONE;
+	priv->hwts_tx_en = config->tx_type == HWTSTAMP_TX_ON;
 
 	priv->systime_flags = STMMAC_HWTS_ACTIVE;
 
@@ -789,31 +759,30 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 	stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags);
 
-	memcpy(&priv->tstamp_config, &config, sizeof(config));
+	priv->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
 /**
  *  stmmac_hwtstamp_get - read hardware timestamping.
  *  @dev: device pointer.
- *  @ifr: An IOCTL specific structure, that can contain a pointer to
- *  a proprietary structure used to pass information to the driver.
+ *  @config: the timestamping configuration.
  *  Description:
  *  This function obtain the current hardware timestamping settings
  *  as requested.
  */
-static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+static int stmmac_hwtstamp_get(struct net_device *dev,
+			       struct kernel_hwtstamp_config *config)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config *config = &priv->tstamp_config;
 
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
-	return copy_to_user(ifr->ifr_data, config,
-			    sizeof(*config)) ? -EFAULT : 0;
+	*config = priv->tstamp_config;
+
+	return 0;
 }
 
 /**
@@ -836,6 +805,11 @@ int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags)
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
+	if (!priv->plat->clk_ptp_rate) {
+		netdev_err(priv->dev, "Invalid PTP clock rate");
+		return -EINVAL;
+	}
+
 	stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags);
 	priv->systime_flags = systime_flags;
 
@@ -920,14 +894,16 @@ static void stmmac_release_ptp(struct stmmac_priv *priv)
  *  stmmac_mac_flow_ctrl - Configure flow control in all queues
  *  @priv: driver private structure
  *  @duplex: duplex passed to the next function
+ *  @flow_ctrl: desired flow control modes
  *  Description: It is used for configuring the flow control in all queues
  */
-static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
+static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex,
+				 unsigned int flow_ctrl)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 
-	stmmac_flow_ctrl(priv, priv->hw, duplex, priv->flow_ctrl,
-			priv->pause, tx_cnt);
+	stmmac_flow_ctrl(priv, priv->hw, duplex, flow_ctrl, priv->pause_time,
+			 tx_cnt);
 }
 
 static unsigned long stmmac_mac_get_caps(struct phylink_config *config,
@@ -973,13 +949,11 @@ static void stmmac_mac_link_down(struct phylink_config *config,
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
 
 	stmmac_mac_set(priv, priv->ioaddr, false);
-	priv->eee_active = false;
-	priv->tx_lpi_enabled = false;
-	priv->eee_enabled = stmmac_eee_init(priv);
-	stmmac_set_eee_pls(priv, priv->hw, false);
+	if (priv->dma_cap.eee)
+		stmmac_set_eee_pls(priv, priv->hw, false);
 
 	if (stmmac_fpe_supported(priv))
-		stmmac_fpe_link_state_handle(priv, false);
+		ethtool_mmsv_link_state_handle(&priv->fpe_cfg.mmsv, false);
 }
 
 static void stmmac_mac_link_up(struct phylink_config *config,
@@ -989,7 +963,9 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 			       bool tx_pause, bool rx_pause)
 {
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+	unsigned int flow_ctrl;
 	u32 old_ctrl, ctrl;
+	int ret;
 
 	if ((priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) &&
 	    priv->plat->serdes_powerup)
@@ -1057,8 +1033,6 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 		}
 	}
 
-	priv->speed = speed;
-
 	if (priv->plat->fix_mac_speed)
 		priv->plat->fix_mac_speed(priv->plat->bsp_priv, speed, mode);
 
@@ -1069,42 +1043,121 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 
 	/* Flow Control operation */
 	if (rx_pause && tx_pause)
-		priv->flow_ctrl = FLOW_AUTO;
+		flow_ctrl = FLOW_AUTO;
 	else if (rx_pause && !tx_pause)
-		priv->flow_ctrl = FLOW_RX;
+		flow_ctrl = FLOW_RX;
 	else if (!rx_pause && tx_pause)
-		priv->flow_ctrl = FLOW_TX;
+		flow_ctrl = FLOW_TX;
 	else
-		priv->flow_ctrl = FLOW_OFF;
+		flow_ctrl = FLOW_OFF;
 
-	stmmac_mac_flow_ctrl(priv, duplex);
+	stmmac_mac_flow_ctrl(priv, duplex, flow_ctrl);
 
 	if (ctrl != old_ctrl)
 		writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
 
+	if (priv->plat->set_clk_tx_rate) {
+		ret = priv->plat->set_clk_tx_rate(priv->plat->bsp_priv,
+						priv->plat->clk_tx_i,
+						interface, speed);
+		if (ret < 0)
+			netdev_err(priv->dev,
+				   "failed to configure transmit clock for %dMbps: %pe\n",
+				   speed, ERR_PTR(ret));
+	}
+
 	stmmac_mac_set(priv, priv->ioaddr, true);
-	if (phy && priv->dma_cap.eee) {
-		priv->eee_active =
-			phy_init_eee(phy, !(priv->plat->flags &
-				STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) >= 0;
-		priv->eee_enabled = stmmac_eee_init(priv);
-		priv->tx_lpi_enabled = priv->eee_enabled;
+	if (priv->dma_cap.eee)
 		stmmac_set_eee_pls(priv, priv->hw, true);
-	}
 
 	if (stmmac_fpe_supported(priv))
-		stmmac_fpe_link_state_handle(priv, true);
+		ethtool_mmsv_link_state_handle(&priv->fpe_cfg.mmsv, true);
 
 	if (priv->plat->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
 		stmmac_hwtstamp_correct_latency(priv, priv);
 }
 
+static void stmmac_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+
+	priv->eee_active = false;
+
+	mutex_lock(&priv->lock);
+
+	priv->eee_enabled = false;
+
+	netdev_dbg(priv->dev, "disable EEE\n");
+	priv->eee_sw_timer_en = false;
+	timer_delete_sync(&priv->eee_ctrl_timer);
+	stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_DISABLE, false, 0);
+	priv->tx_path_in_lpi_mode = false;
+
+	stmmac_set_eee_timer(priv, priv->hw, 0, STMMAC_DEFAULT_TWT_LS);
+	mutex_unlock(&priv->lock);
+}
+
+static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				    bool tx_clk_stop)
+{
+	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+	int ret;
+
+	priv->tx_lpi_timer = timer;
+	priv->eee_active = true;
+
+	mutex_lock(&priv->lock);
+
+	priv->eee_enabled = true;
+
+	/* Update the transmit clock stop according to PHY capability if
+	 * the platform allows
+	 */
+	if (priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP)
+		priv->tx_lpi_clk_stop = tx_clk_stop;
+
+	stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
+			     STMMAC_DEFAULT_TWT_LS);
+
+	/* Try to cnfigure the hardware timer. */
+	ret = stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_TIMER,
+				  priv->tx_lpi_clk_stop, priv->tx_lpi_timer);
+
+	if (ret) {
+		/* Hardware timer mode not supported, or value out of range.
+		 * Fall back to using software LPI mode
+		 */
+		priv->eee_sw_timer_en = true;
+		stmmac_restart_sw_lpi_timer(priv);
+	}
+
+	mutex_unlock(&priv->lock);
+	netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
+
+	return 0;
+}
+
+static int stmmac_mac_finish(struct phylink_config *config, unsigned int mode,
+			     phy_interface_t interface)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	if (priv->plat->mac_finish)
+		priv->plat->mac_finish(ndev, priv->plat->bsp_priv, mode, interface);
+
+	return 0;
+}
+
 static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
 	.mac_get_caps = stmmac_mac_get_caps,
 	.mac_select_pcs = stmmac_mac_select_pcs,
 	.mac_config = stmmac_mac_config,
 	.mac_link_down = stmmac_mac_link_down,
 	.mac_link_up = stmmac_mac_link_up,
+	.mac_disable_tx_lpi = stmmac_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = stmmac_mac_enable_tx_lpi,
+	.mac_finish = stmmac_mac_finish,
 };
 
 /**
@@ -1177,15 +1230,27 @@ static int stmmac_init_phy(struct net_device *dev)
 			return -ENODEV;
 		}
 
-		if (priv->dma_cap.eee)
-			phy_support_eee(phydev);
-
 		ret = phylink_connect_phy(priv->phylink, phydev);
 	} else {
 		fwnode_handle_put(phy_fwnode);
 		ret = phylink_fwnode_phy_connect(priv->phylink, fwnode, 0);
 	}
 
+	if (ret == 0) {
+		struct ethtool_keee eee;
+
+		/* Configure phylib's copy of the LPI timer. Normally,
+		 * phylink_config.lpi_timer_default would do this, but there is
+		 * a chance that userspace could change the eee_timer setting
+		 * via sysfs before the first open. Thus, preserve existing
+		 * behaviour.
+		 */
+		if (!phylink_ethtool_get_eee(priv->phylink, &eee)) {
+			eee.tx_lpi_timer = priv->tx_lpi_timer;
+			phylink_ethtool_set_eee(priv->phylink, &eee);
+		}
+	}
+
 	if (!priv->plat->pmt) {
 		struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
 
@@ -1200,38 +1265,74 @@ static int stmmac_init_phy(struct net_device *dev)
 static int stmmac_phy_setup(struct stmmac_priv *priv)
 {
 	struct stmmac_mdio_bus_data *mdio_bus_data;
-	int mode = priv->plat->phy_interface;
+	struct phylink_config *config;
 	struct fwnode_handle *fwnode;
+	struct phylink_pcs *pcs;
 	struct phylink *phylink;
 
-	priv->phylink_config.dev = &priv->dev->dev;
-	priv->phylink_config.type = PHYLINK_NETDEV;
-	priv->phylink_config.mac_managed_pm = true;
+	config = &priv->phylink_config;
+
+	config->dev = &priv->dev->dev;
+	config->type = PHYLINK_NETDEV;
+	config->mac_managed_pm = true;
 
 	/* Stmmac always requires an RX clock for hardware initialization */
-	priv->phylink_config.mac_requires_rxc = true;
+	config->mac_requires_rxc = true;
+
+	if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI))
+		config->eee_rx_clk_stop_enable = true;
+
+	/* Set the default transmit clock stop bit based on the platform glue */
+	priv->tx_lpi_clk_stop = priv->plat->flags &
+				STMMAC_FLAG_EN_TX_LPI_CLOCKGATING;
 
 	mdio_bus_data = priv->plat->mdio_bus_data;
 	if (mdio_bus_data)
-		priv->phylink_config.default_an_inband =
-			mdio_bus_data->default_an_inband;
+		config->default_an_inband = mdio_bus_data->default_an_inband;
 
-	/* Set the platform/firmware specified interface mode. Note, phylink
-	 * deals with the PHY interface mode, not the MAC interface mode.
+	/* Get the PHY interface modes (at the PHY end of the link) that
+	 * are supported by the platform.
 	 */
-	__set_bit(mode, priv->phylink_config.supported_interfaces);
+	if (priv->plat->get_interfaces)
+		priv->plat->get_interfaces(priv, priv->plat->bsp_priv,
+					   config->supported_interfaces);
+
+	/* Set the platform/firmware specified interface mode if the
+	 * supported interfaces have not already been provided using
+	 * phy_interface as a last resort.
+	 */
+	if (phy_interface_empty(config->supported_interfaces))
+		__set_bit(priv->plat->phy_interface,
+			  config->supported_interfaces);
 
 	/* If we have an xpcs, it defines which PHY interfaces are supported. */
 	if (priv->hw->xpcs)
-		xpcs_get_interfaces(priv->hw->xpcs,
-				    priv->phylink_config.supported_interfaces);
+		pcs = xpcs_to_phylink_pcs(priv->hw->xpcs);
+	else
+		pcs = priv->hw->phylink_pcs;
+
+	if (pcs)
+		phy_interface_or(config->supported_interfaces,
+				 config->supported_interfaces,
+				 pcs->supported_interfaces);
+
+	if (priv->dma_cap.eee) {
+		/* Assume all supported interfaces also support LPI */
+		memcpy(config->lpi_interfaces, config->supported_interfaces,
+		       sizeof(config->lpi_interfaces));
+
+		/* All full duplex speeds above 100Mbps are supported */
+		config->lpi_capabilities = ~(MAC_1000FD - 1) | MAC_100FD;
+		config->lpi_timer_default = eee_timer * 1000;
+		config->eee_enabled_default = true;
+	}
 
 	fwnode = priv->plat->port_node;
 	if (!fwnode)
 		fwnode = dev_fwnode(priv->device);
 
-	phylink = phylink_create(&priv->phylink_config, fwnode,
-				 mode, &stmmac_phylink_mac_ops);
+	phylink = phylink_create(config, fwnode, priv->plat->phy_interface,
+				 &stmmac_phylink_mac_ops);
 	if (IS_ERR(phylink))
 		return PTR_ERR(phylink);
 
@@ -1307,6 +1408,14 @@ static void stmmac_display_rings(struct stmmac_priv *priv,
 	stmmac_display_tx_rings(priv, dma_conf);
 }
 
+static unsigned int stmmac_rx_offset(struct stmmac_priv *priv)
+{
+	if (stmmac_xdp_is_enabled(priv))
+		return XDP_PACKET_HEADROOM;
+
+	return NET_SKB_PAD;
+}
+
 static int stmmac_set_bfsize(int mtu, int bufsize)
 {
 	int ret = bufsize;
@@ -2003,22 +2112,31 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv,
 	struct stmmac_channel *ch = &priv->channel[queue];
 	bool xdp_prog = stmmac_xdp_is_enabled(priv);
 	struct page_pool_params pp_params = { 0 };
-	unsigned int num_pages;
+	unsigned int dma_buf_sz_pad, num_pages;
 	unsigned int napi_id;
 	int ret;
 
+	dma_buf_sz_pad = stmmac_rx_offset(priv) + dma_conf->dma_buf_sz +
+			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	num_pages = DIV_ROUND_UP(dma_buf_sz_pad, PAGE_SIZE);
+
 	rx_q->queue_index = queue;
 	rx_q->priv_data = priv;
+	rx_q->napi_skb_frag_size = num_pages * PAGE_SIZE;
 
 	pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
 	pp_params.pool_size = dma_conf->dma_rx_size;
-	num_pages = DIV_ROUND_UP(dma_conf->dma_buf_sz, PAGE_SIZE);
-	pp_params.order = ilog2(num_pages);
+	pp_params.order = order_base_2(num_pages);
 	pp_params.nid = dev_to_node(priv->device);
 	pp_params.dev = priv->device;
 	pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	pp_params.offset = stmmac_rx_offset(priv);
-	pp_params.max_len = STMMAC_MAX_RX_BUF_SIZE(num_pages);
+	pp_params.max_len = dma_conf->dma_buf_sz;
+
+	if (priv->sph) {
+		pp_params.offset = 0;
+		pp_params.max_len += stmmac_rx_offset(priv);
+	}
 
 	rx_q->page_pool = page_pool_create(&pp_params);
 	if (IS_ERR(rx_q->page_pool)) {
@@ -2445,9 +2563,20 @@ static u64 stmmac_xsk_fill_timestamp(void *_priv)
 	return 0;
 }
 
+static void stmmac_xsk_request_launch_time(u64 launch_time, void *_priv)
+{
+	struct timespec64 ts = ns_to_timespec64(launch_time);
+	struct stmmac_metadata_request *meta_req = _priv;
+
+	if (meta_req->tbs & STMMAC_TBS_EN)
+		stmmac_set_desc_tbs(meta_req->priv, meta_req->edesc, ts.tv_sec,
+				    ts.tv_nsec);
+}
+
 static const struct xsk_tx_metadata_ops stmmac_xsk_tx_metadata_ops = {
 	.tmo_request_timestamp		= stmmac_xsk_request_timestamp,
 	.tmo_fill_timestamp		= stmmac_xsk_fill_timestamp,
+	.tmo_request_launch_time	= stmmac_xsk_request_launch_time,
 };
 
 static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -2531,6 +2660,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		meta_req.priv = priv;
 		meta_req.tx_desc = tx_desc;
 		meta_req.set_ic = &set_ic;
+		meta_req.tbs = tx_q->tbs;
+		meta_req.edesc = &tx_q->dma_entx[entry];
 		xsk_tx_metadata_request(meta, &stmmac_xsk_tx_metadata_ops,
 					&meta_req);
 		if (set_ic) {
@@ -2757,11 +2888,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 			xmits = budget;
 	}
 
-	if (priv->eee_enabled && !priv->tx_path_in_lpi_mode &&
-	    priv->eee_sw_timer_en) {
-		if (stmmac_enable_eee_mode(priv))
-			mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
-	}
+	if (priv->eee_sw_timer_en && !priv->tx_path_in_lpi_mode)
+		stmmac_restart_sw_lpi_timer(priv);
 
 	/* We still have pending packets, let's call for a new scheduling */
 	if (tx_q->dirty_tx != tx_q->cur_tx)
@@ -2996,7 +3124,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	int ret = 0;
 
 	if (!priv->plat->dma_cfg || !priv->plat->dma_cfg->pbl) {
-		dev_err(priv->device, "Invalid DMA configuration\n");
+		netdev_err(priv->dev, "Invalid DMA configuration\n");
 		return -EINVAL;
 	}
 
@@ -3005,7 +3133,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 
 	ret = stmmac_reset(priv, priv->ioaddr);
 	if (ret) {
-		dev_err(priv->device, "Failed to reset the dma\n");
+		netdev_err(priv->dev, "Failed to reset the dma\n");
 		return ret;
 	}
 
@@ -3123,8 +3251,7 @@ static void stmmac_init_coalesce(struct stmmac_priv *priv)
 		priv->tx_coal_frames[chan] = STMMAC_TX_FRAMES;
 		priv->tx_coal_timer[chan] = STMMAC_COAL_TX_TIMER;
 
-		hrtimer_init(&tx_q->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		tx_q->txtimer.function = stmmac_tx_timer;
+		hrtimer_setup(&tx_q->txtimer, stmmac_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	}
 
 	for (chan = 0; chan < rx_channel_count; chan++)
@@ -3372,9 +3499,18 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 	if (priv->hw->phylink_pcs)
 		phylink_pcs_pre_init(priv->phylink, priv->hw->phylink_pcs);
 
+	/* Note that clk_rx_i must be running for reset to complete. This
+	 * clock may also be required when setting the MAC address.
+	 *
+	 * Block the receive clock stop for LPI mode at the PHY in case
+	 * the link is established with EEE mode active.
+	 */
+	phylink_rx_clk_stop_block(priv->phylink);
+
 	/* DMA initialization and SW reset */
 	ret = stmmac_init_dma_engine(priv);
 	if (ret < 0) {
+		phylink_rx_clk_stop_unblock(priv->phylink);
 		netdev_err(priv->dev, "%s: DMA engine initialization failed\n",
 			   __func__);
 		return ret;
@@ -3382,6 +3518,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 
 	/* Copy the MAC addr into the HW  */
 	stmmac_set_umac_addr(priv, priv->hw, dev->dev_addr, 0);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 	/* PS and related bits will be programmed according to the speed */
 	if (priv->hw->pcs) {
@@ -3436,12 +3573,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 	else if (ptp_register)
 		stmmac_ptp_register(priv);
 
-	priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS;
-
-	/* Convert the timer from msec to usec */
-	if (!priv->tx_lpi_timer)
-		priv->tx_lpi_timer = eee_timer * 1000;
-
 	if (priv->use_riwt) {
 		u32 queue;
 
@@ -3498,7 +3629,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 	/* Start the ball rolling... */
 	stmmac_start_all_dma(priv);
 
+	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_hw_vlan_mode(priv, priv->hw);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 	return 0;
 }
@@ -3570,7 +3703,6 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	enum request_irq_err irq_err;
-	cpumask_t cpu_mask;
 	int irq_idx = 0;
 	char *int_name;
 	int ret;
@@ -3699,9 +3831,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 			irq_idx = i;
 			goto irq_error;
 		}
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
-		irq_set_affinity_hint(priv->rx_irq[i], &cpu_mask);
+		irq_set_affinity_hint(priv->rx_irq[i],
+				      cpumask_of(i % num_online_cpus()));
 	}
 
 	/* Request Tx MSI irq */
@@ -3724,9 +3855,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 			irq_idx = i;
 			goto irq_error;
 		}
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
-		irq_set_affinity_hint(priv->tx_irq[i], &cpu_mask);
+		irq_set_affinity_hint(priv->tx_irq[i],
+				      cpumask_of(i % num_online_cpus()));
 	}
 
 	return 0;
@@ -3908,6 +4038,10 @@ static int __stmmac_open(struct net_device *dev,
 	u32 chan;
 	int ret;
 
+	/* Initialise the tx lpi timer, converting from msec to usec */
+	if (!priv->tx_lpi_timer)
+		priv->tx_lpi_timer = eee_timer * 1000;
+
 	ret = pm_runtime_resume_and_get(priv->device);
 	if (ret < 0)
 		return ret;
@@ -3923,9 +4057,6 @@ static int __stmmac_open(struct net_device *dev,
 		}
 	}
 
-	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
-
-	buf_sz = dma_conf->dma_buf_sz;
 	for (int i = 0; i < MTL_MAX_TX_QUEUES; i++)
 		if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN)
 			dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs;
@@ -4024,20 +4155,12 @@ static int stmmac_release(struct net_device *dev)
 	/* Free the IRQ lines */
 	stmmac_free_irq(dev, REQ_IRQ_ERR_ALL, 0);
 
-	if (priv->eee_enabled) {
-		priv->tx_path_in_lpi_mode = false;
-		del_timer_sync(&priv->eee_ctrl_timer);
-	}
-
 	/* Stop TX/RX DMA and clear the descriptors */
 	stmmac_stop_all_dma(priv);
 
 	/* Release and free the Rx/Tx resources */
 	free_dma_desc_resources(priv, &priv->dma_conf);
 
-	/* Disable the MAC Rx/Tx */
-	stmmac_mac_set(priv, priv->ioaddr, false);
-
 	/* Powerdown Serdes if there is */
 	if (priv->plat->serdes_powerdown)
 		priv->plat->serdes_powerdown(dev, priv->plat->bsp_priv);
@@ -4045,7 +4168,7 @@ static int stmmac_release(struct net_device *dev)
 	stmmac_release_ptp(priv);
 
 	if (stmmac_fpe_supported(priv))
-		timer_shutdown_sync(&priv->fpe_cfg.verify_timer);
+		ethtool_mmsv_stop(&priv->fpe_cfg.mmsv);
 
 	pm_runtime_put(priv->device);
 
@@ -4117,11 +4240,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des,
 			desc = &tx_q->dma_tx[tx_q->cur_tx];
 
 		curr_addr = des + (total_len - tmp_len);
-		if (priv->dma_cap.addr64 <= 32)
-			desc->des0 = cpu_to_le32(curr_addr);
-		else
-			stmmac_set_desc_addr(priv, desc, curr_addr);
-
+		stmmac_set_desc_addr(priv, desc, curr_addr);
 		buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ?
 			    TSO_MAX_BUFF_SIZE : tmp_len;
 
@@ -4167,17 +4286,27 @@ static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue)
  *  First Descriptor
  *   --------
  *   | DES0 |---> buffer1 = L2/L3/L4 header
- *   | DES1 |---> TCP Payload (can continue on next descr...)
- *   | DES2 |---> buffer 1 and 2 len
+ *   | DES1 |---> can be used as buffer2 for TCP Payload if the DMA AXI address
+ *   |      |     width is 32-bit, but we never use it.
+ *   |      |     Also can be used as the most-significant 8-bits or 16-bits of
+ *   |      |     buffer1 address pointer if the DMA AXI address width is 40-bit
+ *   |      |     or 48-bit, and we always use it.
+ *   | DES2 |---> buffer1 len
  *   | DES3 |---> must set TSE, TCP hdr len-> [22:19]. TCP payload len [17:0]
  *   --------
+ *   --------
+ *   | DES0 |---> buffer1 = TCP Payload (can continue on next descr...)
+ *   | DES1 |---> same as the First Descriptor
+ *   | DES2 |---> buffer1 len
+ *   | DES3 |
+ *   --------
  *	|
  *     ...
  *	|
  *   --------
- *   | DES0 | --| Split TCP Payload on Buffers 1 and 2
- *   | DES1 | --|
- *   | DES2 | --> buffer 1 and 2 len
+ *   | DES0 |---> buffer1 = Split TCP Payload
+ *   | DES1 |---> same as the First Descriptor
+ *   | DES2 |---> buffer1 len
  *   | DES3 |
  *   --------
  *
@@ -4187,15 +4316,14 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dma_desc *desc, *first, *mss_desc = NULL;
 	struct stmmac_priv *priv = netdev_priv(dev);
-	int tmp_pay_len = 0, first_tx, nfrags;
 	unsigned int first_entry, tx_packets;
 	struct stmmac_txq_stats *txq_stats;
 	struct stmmac_tx_queue *tx_q;
 	u32 pay_len, mss, queue;
+	int i, first_tx, nfrags;
 	u8 proto_hdr_len, hdr;
 	dma_addr_t des;
 	bool set_ic;
-	int i;
 
 	/* Always insert VLAN tag to SKB payload for TSO frames.
 	 *
@@ -4280,23 +4408,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (dma_mapping_error(priv->device, des))
 		goto dma_map_err;
 
-	if (priv->dma_cap.addr64 <= 32) {
-		first->des0 = cpu_to_le32(des);
-
-		/* Fill start of payload in buff2 of first descriptor */
-		if (pay_len)
-			first->des1 = cpu_to_le32(des + proto_hdr_len);
-
-		/* If needed take extra descriptors to fill the remaining payload */
-		tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
-	} else {
-		stmmac_set_desc_addr(priv, first, des);
-		tmp_pay_len = pay_len;
-		des += proto_hdr_len;
-		pay_len = 0;
-	}
-
-	stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue);
+	stmmac_set_desc_addr(priv, first, des);
+	stmmac_tso_allocator(priv, des + proto_hdr_len, pay_len,
+			     (nfrags == 0), queue);
 
 	/* In case two or more DMA transmit descriptors are allocated for this
 	 * non-paged SKB data, the DMA buffer address should be saved to
@@ -4390,8 +4504,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
 
-	skb_tx_timestamp(skb);
-
 	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 		     priv->hwts_tx_en)) {
 		/* declare that device is doing timestamping */
@@ -4400,11 +4512,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	/* Complete the first descriptor before granting the DMA */
-	stmmac_prepare_tso_tx_desc(priv, first, 1,
-			proto_hdr_len,
-			pay_len,
-			1, tx_q->tx_skbuff_dma[first_entry].last_segment,
-			hdr / 4, (skb->len - proto_hdr_len));
+	stmmac_prepare_tso_tx_desc(priv, first, 1, proto_hdr_len, 0, 1,
+				   tx_q->tx_skbuff_dma[first_entry].last_segment,
+				   hdr / 4, (skb->len - proto_hdr_len));
 
 	/* If context desc is used to change MSS */
 	if (mss_desc) {
@@ -4426,6 +4536,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
+	skb_tx_timestamp(skb);
 
 	stmmac_flush_tx_descriptors(priv, queue);
 	stmmac_tx_timer_arm(priv, queue);
@@ -4491,7 +4602,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	first_tx = tx_q->cur_tx;
 
 	if (priv->tx_path_in_lpi_mode && priv->eee_sw_timer_en)
-		stmmac_disable_eee_mode(priv);
+		stmmac_stop_sw_lpi(priv);
 
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
@@ -4669,8 +4780,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
 
-	skb_tx_timestamp(skb);
-
 	/* Ready to fill the first descriptor and set the OWN bit w/o any
 	 * problems because all the descriptors are actually ready to be
 	 * passed to the DMA engine.
@@ -4717,7 +4826,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr, queue);
-
+	skb_tx_timestamp(skb);
 	stmmac_flush_tx_descriptors(priv, queue);
 	stmmac_tx_timer_arm(priv, queue);
 
@@ -5398,10 +5507,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	struct sk_buff *skb = NULL;
 	struct stmmac_xdp_buff ctx;
 	int xdp_status = 0;
-	int buf_sz;
+	int bufsz;
 
 	dma_dir = page_pool_get_dma_dir(rx_q->page_pool);
-	buf_sz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE;
+	bufsz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE;
 	limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit);
 
 	if (netif_msg_rx_status(priv)) {
@@ -5472,7 +5581,7 @@ read_again:
 		if (priv->extend_desc)
 			stmmac_rx_extended_status(priv, &priv->xstats, rx_q->dma_erx + entry);
 		if (unlikely(status == discard_frame)) {
-			page_pool_recycle_direct(rx_q->page_pool, buf->page);
+			page_pool_put_page(rx_q->page_pool, buf->page, 0, true);
 			buf->page = NULL;
 			error = 1;
 			if (!priv->hwts_rx_en)
@@ -5490,10 +5599,6 @@ read_again:
 
 		/* Buffer is good. Go on. */
 
-		prefetch(page_address(buf->page) + buf->page_offset);
-		if (buf->sec_page)
-			prefetch(page_address(buf->sec_page));
-
 		buf1_len = stmmac_rx_buf1_len(priv, p, status, len);
 		len += buf1_len;
 		buf2_len = stmmac_rx_buf2_len(priv, p, status, len);
@@ -5515,8 +5620,10 @@ read_again:
 
 			dma_sync_single_for_cpu(priv->device, buf->addr,
 						buf1_len, dma_dir);
+			net_prefetch(page_address(buf->page) +
+				     buf->page_offset);
 
-			xdp_init_buff(&ctx.xdp, buf_sz, &rx_q->xdp_rxq);
+			xdp_init_buff(&ctx.xdp, bufsz, &rx_q->xdp_rxq);
 			xdp_prepare_buff(&ctx.xdp, page_address(buf->page),
 					 buf->page_offset, buf1_len, true);
 
@@ -5568,22 +5675,26 @@ read_again:
 		}
 
 		if (!skb) {
+			unsigned int head_pad_len;
+
 			/* XDP program may expand or reduce tail */
 			buf1_len = ctx.xdp.data_end - ctx.xdp.data;
 
-			skb = napi_alloc_skb(&ch->rx_napi, buf1_len);
+			skb = napi_build_skb(page_address(buf->page),
+					     rx_q->napi_skb_frag_size);
 			if (!skb) {
+				page_pool_recycle_direct(rx_q->page_pool,
+							 buf->page);
 				rx_dropped++;
 				count++;
 				goto drain_data;
 			}
 
 			/* XDP program may adjust header */
-			skb_copy_to_linear_data(skb, ctx.xdp.data, buf1_len);
+			head_pad_len = ctx.xdp.data - ctx.xdp.data_hard_start;
+			skb_reserve(skb, head_pad_len);
 			skb_put(skb, buf1_len);
-
-			/* Data payload copied into SKB, page ready for recycle */
-			page_pool_recycle_direct(rx_q->page_pool, buf->page);
+			skb_mark_for_recycle(skb);
 			buf->page = NULL;
 		} else if (buf1_len) {
 			dma_sync_single_for_cpu(priv->device, buf->addr,
@@ -5591,9 +5702,6 @@ read_again:
 			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 					buf->page, buf->page_offset, buf1_len,
 					priv->dma_conf.dma_buf_sz);
-
-			/* Data payload appended into SKB */
-			skb_mark_for_recycle(skb);
 			buf->page = NULL;
 		}
 
@@ -5603,9 +5711,6 @@ read_again:
 			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 					buf->sec_page, 0, buf2_len,
 					priv->dma_conf.dma_buf_sz);
-
-			/* Data payload appended into SKB */
-			skb_mark_for_recycle(skb);
 			buf->sec_page = NULL;
 		}
 
@@ -5804,6 +5909,9 @@ static void stmmac_tx_timeout(struct net_device *dev, unsigned int txqueue)
  *  whenever multicast addresses must be enabled/disabled.
  *  Return value:
  *  void.
+ *
+ *  FIXME: This may need RXC to be running, but it may be called with BH
+ *  disabled, which means we can't call phylink_rx_clk_stop*().
  */
 static void stmmac_set_rx_mode(struct net_device *dev)
 {
@@ -5936,7 +6044,9 @@ static int stmmac_set_features(struct net_device *netdev,
 	else
 		priv->hw->hw_vlan_en = false;
 
+	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_hw_vlan_mode(priv, priv->hw);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 	return 0;
 }
@@ -6122,12 +6232,6 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	case SIOCSMIIREG:
 		ret = phylink_mii_ioctl(priv->phylink, rq, cmd);
 		break;
-	case SIOCSHWTSTAMP:
-		ret = stmmac_hwtstamp_set(dev, rq);
-		break;
-	case SIOCGHWTSTAMP:
-		ret = stmmac_hwtstamp_get(dev, rq);
-		break;
 	default:
 		break;
 	}
@@ -6220,7 +6324,9 @@ static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
 	if (ret)
 		goto set_mac_error;
 
+	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_umac_addr(priv, priv->hw, ndev->dev_addr, 0);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 set_mac_error:
 	pm_runtime_put(priv->device);
@@ -6488,11 +6594,7 @@ static int stmmac_device_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_CHANGENAME:
-		if (priv->dbgfs_dir)
-			priv->dbgfs_dir = debugfs_rename(stmmac_fs_dir,
-							 priv->dbgfs_dir,
-							 stmmac_fs_dir,
-							 dev->name);
+		debugfs_change_name(priv->dbgfs_dir, "%s", dev->name);
 		break;
 	}
 done:
@@ -6580,6 +6682,9 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 	return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double);
 }
 
+/* FIXME: This may need RXC to be running, but it may be called with BH
+ * disabled, which means we can't call phylink_rx_clk_stop*().
+ */
 static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -6611,6 +6716,9 @@ err_pm_put:
 	return ret;
 }
 
+/* FIXME: This may need RXC to be running, but it may be called with BH
+ * disabled, which means we can't call phylink_rx_clk_stop*().
+ */
 static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -6922,8 +7030,7 @@ int stmmac_xdp_open(struct net_device *dev)
 		stmmac_set_tx_tail_ptr(priv, priv->ioaddr,
 				       tx_q->tx_tail_addr, chan);
 
-		hrtimer_init(&tx_q->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		tx_q->txtimer.function = stmmac_tx_timer;
+		hrtimer_setup(&tx_q->txtimer, stmmac_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	}
 
 	/* Enable the MAC Rx/Tx */
@@ -7063,6 +7170,8 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_bpf = stmmac_bpf,
 	.ndo_xdp_xmit = stmmac_xdp_xmit,
 	.ndo_xsk_wakeup = stmmac_xsk_wakeup,
+	.ndo_hwtstamp_get = stmmac_hwtstamp_get,
+	.ndo_hwtstamp_set = stmmac_hwtstamp_set,
 };
 
 static void stmmac_reset_subtask(struct stmmac_priv *priv)
@@ -7174,6 +7283,36 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	if (priv->dma_cap.tsoen)
 		dev_info(priv->device, "TSO supported\n");
 
+	if (priv->dma_cap.number_rx_queues &&
+	    priv->plat->rx_queues_to_use > priv->dma_cap.number_rx_queues) {
+		dev_warn(priv->device,
+			 "Number of Rx queues (%u) exceeds dma capability\n",
+			 priv->plat->rx_queues_to_use);
+		priv->plat->rx_queues_to_use = priv->dma_cap.number_rx_queues;
+	}
+	if (priv->dma_cap.number_tx_queues &&
+	    priv->plat->tx_queues_to_use > priv->dma_cap.number_tx_queues) {
+		dev_warn(priv->device,
+			 "Number of Tx queues (%u) exceeds dma capability\n",
+			 priv->plat->tx_queues_to_use);
+		priv->plat->tx_queues_to_use = priv->dma_cap.number_tx_queues;
+	}
+
+	if (priv->dma_cap.rx_fifo_size &&
+	    priv->plat->rx_fifo_size > priv->dma_cap.rx_fifo_size) {
+		dev_warn(priv->device,
+			 "Rx FIFO size (%u) exceeds dma capability\n",
+			 priv->plat->rx_fifo_size);
+		priv->plat->rx_fifo_size = priv->dma_cap.rx_fifo_size;
+	}
+	if (priv->dma_cap.tx_fifo_size &&
+	    priv->plat->tx_fifo_size > priv->dma_cap.tx_fifo_size) {
+		dev_warn(priv->device,
+			 "Tx FIFO size (%u) exceeds dma capability\n",
+			 priv->plat->tx_fifo_size);
+		priv->plat->tx_fifo_size = priv->dma_cap.tx_fifo_size;
+	}
+
 	priv->hw->vlan_fail_q_en =
 		(priv->plat->flags & STMMAC_FLAG_VLAN_FAIL_Q_EN);
 	priv->hw->vlan_fail_q = priv->plat->vlan_fail_q;
@@ -7366,7 +7505,7 @@ int stmmac_dvr_probe(struct device *device,
 		return -ENOMEM;
 
 	stmmac_set_ethtool_ops(ndev);
-	priv->pause = pause;
+	priv->pause_time = pause;
 	priv->plat = plat_dat;
 	priv->ioaddr = res->addr;
 	priv->dev->base_addr = (unsigned long)res->addr;
@@ -7406,6 +7545,8 @@ int stmmac_dvr_probe(struct device *device,
 
 	INIT_WORK(&priv->service_task, stmmac_service_task);
 
+	timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0);
+
 	/* Override with kernel parameters if supplied XXX CRS XXX
 	 * this needs to have multiple instances
 	 */
@@ -7512,7 +7653,7 @@ int stmmac_dvr_probe(struct device *device,
 #ifdef STMMAC_VLAN_TAG_USED
 	/* Both mac100 and gmac support receive VLAN tag detection */
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX;
-	if (priv->plat->has_gmac4) {
+	if (priv->plat->has_gmac4 || priv->plat->has_xgmac) {
 		ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
 		priv->hw->hw_vlan_en = true;
 	}
@@ -7560,9 +7701,6 @@ int stmmac_dvr_probe(struct device *device,
 			 "%s: warning: maxmtu having invalid value (%d)\n",
 			 __func__, priv->plat->maxmtu);
 
-	if (flow_ctrl)
-		priv->flow_ctrl = FLOW_AUTO;	/* RX/TX pause on */
-
 	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	/* Setup channels NAPI */
@@ -7598,9 +7736,6 @@ int stmmac_dvr_probe(struct device *device,
 		goto error_mdio_register;
 	}
 
-	if (priv->plat->speed_mode_2500)
-		priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv);
-
 	ret = stmmac_pcs_setup(ndev);
 	if (ret)
 		goto error_pcs_setup;
@@ -7664,8 +7799,6 @@ void stmmac_dvr_remove(struct device *dev)
 
 	pm_runtime_get_sync(dev);
 
-	stmmac_stop_all_dma(priv);
-	stmmac_mac_set(priv, priv->ioaddr, false);
 	unregister_netdev(ndev);
 
 #ifdef CONFIG_DEBUG_FS
@@ -7713,9 +7846,9 @@ int stmmac_suspend(struct device *dev)
 	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
 		hrtimer_cancel(&priv->dma_conf.tx_queue[chan].txtimer);
 
-	if (priv->eee_enabled) {
+	if (priv->eee_sw_timer_en) {
 		priv->tx_path_in_lpi_mode = false;
-		del_timer_sync(&priv->eee_ctrl_timer);
+		timer_delete_sync(&priv->eee_ctrl_timer);
 	}
 
 	/* Stop TX/RX DMA */
@@ -7736,19 +7869,16 @@ int stmmac_suspend(struct device *dev)
 	mutex_unlock(&priv->lock);
 
 	rtnl_lock();
-	if (device_may_wakeup(priv->device) && priv->plat->pmt) {
-		phylink_suspend(priv->phylink, true);
-	} else {
-		if (device_may_wakeup(priv->device))
-			phylink_speed_down(priv->phylink, false);
-		phylink_suspend(priv->phylink, false);
-	}
+	if (device_may_wakeup(priv->device) && !priv->plat->pmt)
+		phylink_speed_down(priv->phylink, false);
+
+	phylink_suspend(priv->phylink,
+			device_may_wakeup(priv->device) && priv->plat->pmt);
 	rtnl_unlock();
 
 	if (stmmac_fpe_supported(priv))
-		timer_shutdown_sync(&priv->fpe_cfg.verify_timer);
+		ethtool_mmsv_stop(&priv->fpe_cfg.mmsv);
 
-	priv->speed = SPEED_UNKNOWN;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(stmmac_suspend);
@@ -7832,16 +7962,12 @@ int stmmac_resume(struct device *dev)
 	}
 
 	rtnl_lock();
-	if (device_may_wakeup(priv->device) && priv->plat->pmt) {
-		phylink_resume(priv->phylink);
-	} else {
-		phylink_resume(priv->phylink);
-		if (device_may_wakeup(priv->device))
-			phylink_speed_up(priv->phylink);
-	}
-	rtnl_unlock();
 
-	rtnl_lock();
+	/* Prepare the PHY to resume, ensuring that its clocks which are
+	 * necessary for the MAC DMA reset to complete are running
+	 */
+	phylink_prepare_resume(priv->phylink);
+
 	mutex_lock(&priv->lock);
 
 	stmmac_reset_queues_param(priv);
@@ -7851,14 +7977,25 @@ int stmmac_resume(struct device *dev)
 
 	stmmac_hw_setup(ndev, false);
 	stmmac_init_coalesce(priv);
+	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_rx_mode(ndev);
 
 	stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 	stmmac_enable_all_queues(priv);
 	stmmac_enable_all_dma_irq(priv);
 
 	mutex_unlock(&priv->lock);
+
+	/* phylink_resume() must be called after the hardware has been
+	 * initialised because it may bring the link up immediately in a
+	 * workqueue thread, which will race with initialisation.
+	 */
+	phylink_resume(priv->phylink);
+	if (device_may_wakeup(priv->device) && !priv->plat->pmt)
+		phylink_speed_up(priv->phylink);
+
 	rtnl_unlock();
 
 	netif_device_attach(ndev);
@@ -7881,9 +8018,6 @@ static int __init stmmac_cmdline_opt(char *str)
 		} else if (!strncmp(opt, "phyaddr:", 8)) {
 			if (kstrtoint(opt + 8, 0, &phyaddr))
 				goto err;
-		} else if (!strncmp(opt, "buf_sz:", 7)) {
-			if (kstrtoint(opt + 7, 0, &buf_sz))
-				goto err;
 		} else if (!strncmp(opt, "tc:", 3)) {
 			if (kstrtoint(opt + 3, 0, &tc))
 				goto err;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 0c7d81ddd440..836f2848dfeb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -524,6 +524,9 @@ int stmmac_pcs_setup(struct net_device *ndev)
 	if (ret)
 		return dev_err_probe(priv->device, ret, "No xPCS found\n");
 
+	if (xpcs)
+		xpcs_config_eee_mult_fact(xpcs, priv->plat->mult_fact_100ns);
+
 	priv->hw->xpcs = xpcs;
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 352b01678c22..9c1b54b701f7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -155,9 +155,9 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 {
 	struct stmmac_pci_info *info = (struct stmmac_pci_info *)id->driver_data;
 	struct plat_stmmacenet_data *plat;
-	struct stmmac_resources res;
-	int i;
+	struct stmmac_resources res = {};
 	int ret;
+	int i;
 
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
@@ -192,9 +192,9 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
 			continue;
-		ret = pcim_iomap_regions(pdev, BIT(i), pci_name(pdev));
-		if (ret)
-			return ret;
+		res.addr = pcim_iomap_region(pdev, i, STMMAC_RESOURCE_NAME);
+		if (IS_ERR(res.addr))
+			return PTR_ERR(res.addr);
 		break;
 	}
 
@@ -204,8 +204,6 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
-	memset(&res, 0, sizeof(res));
-	res.addr = pcim_iomap_table(pdev)[i];
 	res.wol_irq = pdev->irq;
 	res.irq = pdev->irq;
 
@@ -226,21 +224,11 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
  * stmmac_pci_remove
  *
  * @pdev: platform device pointer
- * Description: this function calls the main to free the net resources
- * and releases the PCI resources.
+ * Description: this function calls the main to free the net resources.
  */
 static void stmmac_pci_remove(struct pci_dev *pdev)
 {
-	int i;
-
 	stmmac_dvr_remove(&pdev->dev);
-
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (pci_resource_len(pdev, i) == 0)
-			continue;
-		pcim_iounmap_regions(pdev, BIT(i));
-		break;
-	}
 }
 
 static int __maybe_unused stmmac_pci_suspend(struct device *dev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 3ac32444e492..b80c1efdb323 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -405,21 +405,16 @@ static int stmmac_of_get_mac_mode(struct device_node *np)
 	return -ENODEV;
 }
 
-/**
- * stmmac_remove_config_dt - undo the effects of stmmac_probe_config_dt()
- * @pdev: platform_device structure
- * @plat: driver data platform structure
- *
- * Release resources claimed by stmmac_probe_config_dt().
- */
-static void stmmac_remove_config_dt(struct platform_device *pdev,
-				    struct plat_stmmacenet_data *plat)
-{
-	clk_disable_unprepare(plat->stmmac_clk);
-	clk_disable_unprepare(plat->pclk);
-	of_node_put(plat->phy_node);
-	of_node_put(plat->mdio_node);
-}
+/* Compatible string array for all gmac4 devices */
+static const char * const stmmac_gmac4_compats[] = {
+	"snps,dwmac-4.00",
+	"snps,dwmac-4.10a",
+	"snps,dwmac-4.20a",
+	"snps,dwmac-5.10a",
+	"snps,dwmac-5.20",
+	"snps,dwmac-5.30a",
+	NULL
+};
 
 /**
  * stmmac_probe_config_dt - parse device-tree driver parameters
@@ -435,6 +430,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_dma_cfg *dma_cfg;
+	static int bus_id = -ENODEV;
 	int phy_mode;
 	void *ret;
 	int rc;
@@ -470,8 +466,14 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	of_property_read_u32(np, "max-speed", &plat->max_speed);
 
 	plat->bus_id = of_alias_get_id(np, "ethernet");
-	if (plat->bus_id < 0)
-		plat->bus_id = 0;
+	if (plat->bus_id < 0) {
+		if (bus_id < 0)
+			bus_id = of_alias_get_highest_id("ethernet");
+		/* No ethernet alias found, init at -1 so first bus_id is 0 */
+		if (bus_id < 0)
+			bus_id = -1;
+		plat->bus_id = ++bus_id;
+	}
 
 	/* Default to phy auto-detection */
 	plat->phy_addr = -1;
@@ -490,8 +492,10 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
 	rc = stmmac_mdio_setup(plat, np, &pdev->dev);
-	if (rc)
-		return ERR_PTR(rc);
+	if (rc) {
+		ret = ERR_PTR(rc);
+		goto error_put_phy;
+	}
 
 	of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size);
 
@@ -500,8 +504,11 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	plat->force_sf_dma_mode =
 		of_property_read_bool(np, "snps,force_sf_dma_mode");
 
-	if (of_property_read_bool(np, "snps,en-tx-lpi-clockgating"))
+	if (of_property_read_bool(np, "snps,en-tx-lpi-clockgating")) {
+		dev_warn(&pdev->dev,
+			 "OF property snps,en-tx-lpi-clockgating is deprecated, please convert driver to use STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP\n");
 		plat->flags |= STMMAC_FLAG_EN_TX_LPI_CLOCKGATING;
+	}
 
 	/* Set the maxmtu to a default of JUMBO_LEN in case the
 	 * parameter is not present in the device tree.
@@ -552,11 +559,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		plat->pmt = 1;
 	}
 
-	if (of_device_is_compatible(np, "snps,dwmac-4.00") ||
-	    of_device_is_compatible(np, "snps,dwmac-4.10a") ||
-	    of_device_is_compatible(np, "snps,dwmac-4.20a") ||
-	    of_device_is_compatible(np, "snps,dwmac-5.10a") ||
-	    of_device_is_compatible(np, "snps,dwmac-5.20")) {
+	if (of_device_compatible_match(np, stmmac_gmac4_compats)) {
 		plat->has_gmac4 = 1;
 		plat->has_gmac = 0;
 		plat->pmt = 1;
@@ -581,8 +584,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg),
 			       GFP_KERNEL);
 	if (!dma_cfg) {
-		stmmac_remove_config_dt(pdev, plat);
-		return ERR_PTR(-ENOMEM);
+		ret = ERR_PTR(-ENOMEM);
+		goto error_put_mdio;
 	}
 	plat->dma_cfg = dma_cfg;
 
@@ -610,8 +613,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 
 	rc = stmmac_mtl_setup(pdev, plat);
 	if (rc) {
-		stmmac_remove_config_dt(pdev, plat);
-		return ERR_PTR(rc);
+		ret = ERR_PTR(rc);
+		goto error_put_mdio;
 	}
 
 	/* clock setup */
@@ -640,7 +643,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		dev_info(&pdev->dev, "PTP uses main clock\n");
 	} else {
 		plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref);
-		dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate);
+		dev_dbg(&pdev->dev, "PTP rate %lu\n", plat->clk_ptp_rate);
 	}
 
 	plat->stmmac_rst = devm_reset_control_get_optional(&pdev->dev,
@@ -663,6 +666,10 @@ error_hw_init:
 	clk_disable_unprepare(plat->pclk);
 error_pclk_get:
 	clk_disable_unprepare(plat->stmmac_clk);
+error_put_mdio:
+	of_node_put(plat->mdio_node);
+error_put_phy:
+	of_node_put(plat->phy_node);
 
 	return ret;
 }
@@ -671,16 +678,17 @@ static void devm_stmmac_remove_config_dt(void *data)
 {
 	struct plat_stmmacenet_data *plat = data;
 
-	/* Platform data argument is unused */
-	stmmac_remove_config_dt(NULL, plat);
+	clk_disable_unprepare(plat->stmmac_clk);
+	clk_disable_unprepare(plat->pclk);
+	of_node_put(plat->mdio_node);
+	of_node_put(plat->phy_node);
 }
 
 /**
  * devm_stmmac_probe_config_dt
  * @pdev: platform_device structure
  * @mac: MAC address to use
- * Description: Devres variant of stmmac_probe_config_dt(). Does not require
- * the user to call stmmac_remove_config_dt() at driver detach.
+ * Description: Devres variant of stmmac_probe_config_dt().
  */
 struct plat_stmmacenet_data *
 devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
@@ -708,6 +716,17 @@ devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 #endif /* CONFIG_OF */
 EXPORT_SYMBOL_GPL(devm_stmmac_probe_config_dt);
 
+struct clk *stmmac_pltfr_find_clk(struct plat_stmmacenet_data *plat_dat,
+				  const char *name)
+{
+	for (int i = 0; i < plat_dat->num_clks; i++)
+		if (strcmp(plat_dat->clks[i].id, name) == 0)
+			return plat_dat->clks[i].clk;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(stmmac_pltfr_find_clk);
+
 int stmmac_get_platform_resources(struct platform_device *pdev,
 				  struct stmmac_resources *stmmac_res)
 {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
index 72dc1a32e46d..6e6561e29d6e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
@@ -14,6 +14,9 @@
 struct plat_stmmacenet_data *
 devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac);
 
+struct clk *stmmac_pltfr_find_clk(struct plat_stmmacenet_data *plat_dat,
+				  const char *name);
+
 int stmmac_get_platform_resources(struct platform_device *pdev,
 				  struct stmmac_resources *stmmac_res);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 429b2d357813..3767ba495e78 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -317,7 +317,7 @@ void stmmac_ptp_register(struct stmmac_priv *priv)
 
 	/* Calculate the clock domain crossing (CDC) error if necessary */
 	priv->plat->cdc_error_adj = 0;
-	if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate)
+	if (priv->plat->has_gmac4)
 		priv->plat->cdc_error_adj = (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate;
 
 	/* Update the ptp clock parameters based on feature discovery, when
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index 4cc70480ce0f..3fe0e3a80e80 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -104,4 +104,7 @@ int dwmac1000_ptp_enable(struct ptp_clock_info *ptp,
 void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time);
 void dwmac1000_timestamp_interrupt(struct stmmac_priv *priv);
 
+extern const struct ptp_clock_info stmmac_ptp_clock_ops;
+extern const struct ptp_clock_info dwmac1000_ptp_clock_ops;
+
 #endif	/* __STMMAC_PTP_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index 3ca1c2a816ff..a01bc394d1ac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -382,14 +382,14 @@ static int stmmac_test_phy_loopback(struct stmmac_priv *priv)
 	if (!priv->dev->phydev)
 		return -EOPNOTSUPP;
 
-	ret = phy_loopback(priv->dev->phydev, true);
+	ret = phy_loopback(priv->dev->phydev, true, 0);
 	if (ret)
 		return ret;
 
 	attr.dst = priv->dev->dev_addr;
 	ret = __stmmac_test_loopback(priv, &attr);
 
-	phy_loopback(priv->dev->phydev, false);
+	phy_loopback(priv->dev->phydev, false, 0);
 	return ret;
 }
 
@@ -1985,7 +1985,7 @@ void stmmac_selftest_run(struct net_device *dev,
 		case STMMAC_LOOPBACK_PHY:
 			ret = -EOPNOTSUPP;
 			if (dev->phydev)
-				ret = phy_loopback(dev->phydev, true);
+				ret = phy_loopback(dev->phydev, true, 0);
 			if (!ret)
 				break;
 			fallthrough;
@@ -2018,7 +2018,7 @@ void stmmac_selftest_run(struct net_device *dev,
 		case STMMAC_LOOPBACK_PHY:
 			ret = -EOPNOTSUPP;
 			if (dev->phydev)
-				ret = phy_loopback(dev->phydev, false);
+				ret = phy_loopback(dev->phydev, false, 0);
 			if (!ret)
 				break;
 			fallthrough;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 6a79e6a111ed..694d6ee14381 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -1284,14 +1284,3 @@ const struct stmmac_tc_ops dwmac510_tc_ops = {
 	.query_caps = tc_query_caps,
 	.setup_mqprio = tc_setup_dwmac510_mqprio,
 };
-
-const struct stmmac_tc_ops dwxgmac_tc_ops = {
-	.init = tc_init,
-	.setup_cls_u32 = tc_setup_cls_u32,
-	.setup_cbs = tc_setup_cbs,
-	.setup_cls = tc_setup_cls,
-	.setup_taprio = tc_setup_taprio,
-	.setup_etf = tc_setup_etf,
-	.query_caps = tc_query_caps,
-	.setup_mqprio = tc_setup_dwmac510_mqprio,
-};
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
new file mode 100644
index 000000000000..0b6f6228ae35
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
@@ -0,0 +1,374 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025, Altera Corporation
+ * stmmac VLAN (802.1Q) handling
+ */
+
+#include "stmmac.h"
+#include "stmmac_vlan.h"
+
+static void vlan_write_single(struct net_device *dev, u16 vid)
+{
+	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
+	u32 val;
+
+	val = readl(ioaddr + VLAN_TAG);
+	val &= ~VLAN_TAG_VID;
+	val |= VLAN_TAG_ETV | vid;
+
+	writel(val, ioaddr + VLAN_TAG);
+}
+
+static int vlan_write_filter(struct net_device *dev,
+			     struct mac_device_info *hw,
+			     u8 index, u32 data)
+{
+	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
+	int ret;
+	u32 val;
+
+	if (index >= hw->num_vlan)
+		return -EINVAL;
+
+	writel(data, ioaddr + VLAN_TAG_DATA);
+
+	val = readl(ioaddr + VLAN_TAG);
+	val &= ~(VLAN_TAG_CTRL_OFS_MASK |
+		VLAN_TAG_CTRL_CT |
+		VLAN_TAG_CTRL_OB);
+	val |= (index << VLAN_TAG_CTRL_OFS_SHIFT) | VLAN_TAG_CTRL_OB;
+
+	writel(val, ioaddr + VLAN_TAG);
+
+	ret = readl_poll_timeout(ioaddr + VLAN_TAG, val,
+				 !(val & VLAN_TAG_CTRL_OB),
+				 1000, 500000);
+	if (ret) {
+		netdev_err(dev, "Timeout accessing MAC_VLAN_Tag_Filter\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int vlan_add_hw_rx_fltr(struct net_device *dev,
+			       struct mac_device_info *hw,
+			       __be16 proto, u16 vid)
+{
+	int index = -1;
+	u32 val = 0;
+	int i, ret;
+
+	if (vid > 4095)
+		return -EINVAL;
+
+	/* Single Rx VLAN Filter */
+	if (hw->num_vlan == 1) {
+		/* For single VLAN filter, VID 0 means VLAN promiscuous */
+		if (vid == 0) {
+			netdev_warn(dev, "Adding VLAN ID 0 is not supported\n");
+			return -EPERM;
+		}
+
+		if (hw->vlan_filter[0] & VLAN_TAG_VID) {
+			netdev_err(dev, "Only single VLAN ID supported\n");
+			return -EPERM;
+		}
+
+		hw->vlan_filter[0] = vid;
+		vlan_write_single(dev, vid);
+
+		return 0;
+	}
+
+	/* Extended Rx VLAN Filter Enable */
+	val |= VLAN_TAG_DATA_ETV | VLAN_TAG_DATA_VEN | vid;
+
+	for (i = 0; i < hw->num_vlan; i++) {
+		if (hw->vlan_filter[i] == val)
+			return 0;
+		else if (!(hw->vlan_filter[i] & VLAN_TAG_DATA_VEN))
+			index = i;
+	}
+
+	if (index == -1) {
+		netdev_err(dev, "MAC_VLAN_Tag_Filter full (size: %0u)\n",
+			   hw->num_vlan);
+		return -EPERM;
+	}
+
+	ret = vlan_write_filter(dev, hw, index, val);
+
+	if (!ret)
+		hw->vlan_filter[index] = val;
+
+	return ret;
+}
+
+static int vlan_del_hw_rx_fltr(struct net_device *dev,
+			       struct mac_device_info *hw,
+			       __be16 proto, u16 vid)
+{
+	int i, ret = 0;
+
+	/* Single Rx VLAN Filter */
+	if (hw->num_vlan == 1) {
+		if ((hw->vlan_filter[0] & VLAN_TAG_VID) == vid) {
+			hw->vlan_filter[0] = 0;
+			vlan_write_single(dev, 0);
+		}
+		return 0;
+	}
+
+	/* Extended Rx VLAN Filter Enable */
+	for (i = 0; i < hw->num_vlan; i++) {
+		if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid) {
+			ret = vlan_write_filter(dev, hw, i, 0);
+
+			if (!ret)
+				hw->vlan_filter[i] = 0;
+			else
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+static void vlan_restore_hw_rx_fltr(struct net_device *dev,
+				    struct mac_device_info *hw)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+	u32 hash;
+	u32 val;
+	int i;
+
+	/* Single Rx VLAN Filter */
+	if (hw->num_vlan == 1) {
+		vlan_write_single(dev, hw->vlan_filter[0]);
+		return;
+	}
+
+	/* Extended Rx VLAN Filter Enable */
+	for (i = 0; i < hw->num_vlan; i++) {
+		if (hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) {
+			val = hw->vlan_filter[i];
+			vlan_write_filter(dev, hw, i, val);
+		}
+	}
+
+	hash = readl(ioaddr + VLAN_HASH_TABLE);
+	if (hash & VLAN_VLHT) {
+		value = readl(ioaddr + VLAN_TAG);
+		value |= VLAN_VTHM;
+		writel(value, ioaddr + VLAN_TAG);
+	}
+}
+
+static void vlan_update_hash(struct mac_device_info *hw, u32 hash,
+			     u16 perfect_match, bool is_double)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	writel(hash, ioaddr + VLAN_HASH_TABLE);
+
+	value = readl(ioaddr + VLAN_TAG);
+
+	if (hash) {
+		value |= VLAN_VTHM | VLAN_ETV;
+		if (is_double) {
+			value |= VLAN_EDVLP;
+			value |= VLAN_ESVL;
+			value |= VLAN_DOVLTC;
+		}
+
+		writel(value, ioaddr + VLAN_TAG);
+	} else if (perfect_match) {
+		u32 value = VLAN_ETV;
+
+		if (is_double) {
+			value |= VLAN_EDVLP;
+			value |= VLAN_ESVL;
+			value |= VLAN_DOVLTC;
+		}
+
+		writel(value | perfect_match, ioaddr + VLAN_TAG);
+	} else {
+		value &= ~(VLAN_VTHM | VLAN_ETV);
+		value &= ~(VLAN_EDVLP | VLAN_ESVL);
+		value &= ~VLAN_DOVLTC;
+		value &= ~VLAN_VID;
+
+		writel(value, ioaddr + VLAN_TAG);
+	}
+}
+
+static void vlan_enable(struct mac_device_info *hw, u32 type)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + VLAN_INCL);
+	value |= VLAN_VLTI;
+	value |= VLAN_CSVL; /* Only use SVLAN */
+	value &= ~VLAN_VLC;
+	value |= (type << VLAN_VLC_SHIFT) & VLAN_VLC;
+	writel(value, ioaddr + VLAN_INCL);
+}
+
+static void vlan_rx_hw(struct mac_device_info *hw,
+		       struct dma_desc *rx_desc, struct sk_buff *skb)
+{
+	if (hw->desc->get_rx_vlan_valid(rx_desc)) {
+		u16 vid = hw->desc->get_rx_vlan_tci(rx_desc);
+
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
+	}
+}
+
+static void vlan_set_hw_mode(struct mac_device_info *hw)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + VLAN_TAG);
+
+	value &= ~VLAN_TAG_CTRL_EVLS_MASK;
+
+	if (hw->hw_vlan_en)
+		/* Always strip VLAN on Receive */
+		value |= VLAN_TAG_STRIP_ALL;
+	else
+		/* Do not strip VLAN on Receive */
+		value |= VLAN_TAG_STRIP_NONE;
+
+	/* Enable outer VLAN Tag in Rx DMA descriptor */
+	value |= VLAN_TAG_CTRL_EVLRXS;
+	writel(value, ioaddr + VLAN_TAG);
+}
+
+static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
+				      u16 perfect_match, bool is_double)
+{
+	void __iomem *ioaddr = hw->pcsr;
+
+	writel(hash, ioaddr + VLAN_HASH_TABLE);
+
+	if (hash) {
+		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
+
+		value |= XGMAC_FILTER_VTFE;
+
+		writel(value, ioaddr + XGMAC_PACKET_FILTER);
+
+		value = readl(ioaddr + VLAN_TAG);
+
+		value |= VLAN_VTHM | VLAN_ETV;
+		if (is_double) {
+			value |= VLAN_EDVLP;
+			value |= VLAN_ESVL;
+			value |= VLAN_DOVLTC;
+		} else {
+			value &= ~VLAN_EDVLP;
+			value &= ~VLAN_ESVL;
+			value &= ~VLAN_DOVLTC;
+		}
+
+		value &= ~VLAN_VID;
+		writel(value, ioaddr + VLAN_TAG);
+	} else if (perfect_match) {
+		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
+
+		value |= XGMAC_FILTER_VTFE;
+
+		writel(value, ioaddr + XGMAC_PACKET_FILTER);
+
+		value = readl(ioaddr + VLAN_TAG);
+
+		value &= ~VLAN_VTHM;
+		value |= VLAN_ETV;
+		if (is_double) {
+			value |= VLAN_EDVLP;
+			value |= VLAN_ESVL;
+			value |= VLAN_DOVLTC;
+		} else {
+			value &= ~VLAN_EDVLP;
+			value &= ~VLAN_ESVL;
+			value &= ~VLAN_DOVLTC;
+		}
+
+		value &= ~VLAN_VID;
+		writel(value | perfect_match, ioaddr + VLAN_TAG);
+	} else {
+		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
+
+		value &= ~XGMAC_FILTER_VTFE;
+
+		writel(value, ioaddr + XGMAC_PACKET_FILTER);
+
+		value = readl(ioaddr + VLAN_TAG);
+
+		value &= ~(VLAN_VTHM | VLAN_ETV);
+		value &= ~(VLAN_EDVLP | VLAN_ESVL);
+		value &= ~VLAN_DOVLTC;
+		value &= ~VLAN_VID;
+
+		writel(value, ioaddr + VLAN_TAG);
+	}
+}
+
+const struct stmmac_vlan_ops dwmac_vlan_ops = {
+	.update_vlan_hash = vlan_update_hash,
+	.enable_vlan = vlan_enable,
+	.add_hw_vlan_rx_fltr = vlan_add_hw_rx_fltr,
+	.del_hw_vlan_rx_fltr = vlan_del_hw_rx_fltr,
+	.restore_hw_vlan_rx_fltr = vlan_restore_hw_rx_fltr,
+	.rx_hw_vlan = vlan_rx_hw,
+	.set_hw_vlan_mode = vlan_set_hw_mode,
+};
+
+const struct stmmac_vlan_ops dwxlgmac2_vlan_ops = {
+	.update_vlan_hash = dwxgmac2_update_vlan_hash,
+	.enable_vlan = vlan_enable,
+};
+
+const struct stmmac_vlan_ops dwxgmac210_vlan_ops = {
+	.update_vlan_hash = dwxgmac2_update_vlan_hash,
+	.enable_vlan = vlan_enable,
+	.add_hw_vlan_rx_fltr = vlan_add_hw_rx_fltr,
+	.del_hw_vlan_rx_fltr = vlan_del_hw_rx_fltr,
+	.restore_hw_vlan_rx_fltr = vlan_restore_hw_rx_fltr,
+	.rx_hw_vlan = vlan_rx_hw,
+	.set_hw_vlan_mode = vlan_set_hw_mode,
+};
+
+u32 stmmac_get_num_vlan(void __iomem *ioaddr)
+{
+	u32 val, num_vlan;
+
+	val = readl(ioaddr + HW_FEATURE3);
+	switch (val & VLAN_HW_FEAT_NRVF) {
+	case 0:
+		num_vlan = 1;
+		break;
+	case 1:
+		num_vlan = 4;
+		break;
+	case 2:
+		num_vlan = 8;
+		break;
+	case 3:
+		num_vlan = 16;
+		break;
+	case 4:
+		num_vlan = 24;
+		break;
+	case 5:
+		num_vlan = 32;
+		break;
+	default:
+		num_vlan = 1;
+	}
+
+	return num_vlan;
+}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.h
new file mode 100644
index 000000000000..c24f89a9049b
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2025, Altera Corporation
+ * stmmac VLAN(802.1Q) handling
+ */
+
+#ifndef __STMMAC_VLAN_H__
+#define __STMMAC_VLAN_H__
+
+#include <linux/bitfield.h>
+#include "dwxgmac2.h"
+
+#define VLAN_TAG			0x00000050
+#define VLAN_TAG_DATA			0x00000054
+#define VLAN_HASH_TABLE			0x00000058
+#define VLAN_INCL			0x00000060
+
+/* MAC VLAN */
+#define VLAN_EDVLP			BIT(26)
+#define VLAN_VTHM			BIT(25)
+#define VLAN_DOVLTC			BIT(20)
+#define VLAN_ESVL			BIT(18)
+#define VLAN_ETV			BIT(16)
+#define VLAN_VID			GENMASK(15, 0)
+#define VLAN_VLTI			BIT(20)
+#define VLAN_CSVL			BIT(19)
+#define VLAN_VLC			GENMASK(17, 16)
+#define VLAN_VLC_SHIFT			16
+#define VLAN_VLHT			GENMASK(15, 0)
+
+/* MAC VLAN Tag */
+#define VLAN_TAG_VID			GENMASK(15, 0)
+#define VLAN_TAG_ETV			BIT(16)
+
+/* MAC VLAN Tag Control */
+#define VLAN_TAG_CTRL_OB		BIT(0)
+#define VLAN_TAG_CTRL_CT		BIT(1)
+#define VLAN_TAG_CTRL_OFS_MASK		GENMASK(6, 2)
+#define VLAN_TAG_CTRL_OFS_SHIFT		2
+#define VLAN_TAG_CTRL_EVLS_MASK		GENMASK(22, 21)
+#define VLAN_TAG_CTRL_EVLS_SHIFT	21
+#define VLAN_TAG_CTRL_EVLRXS		BIT(24)
+
+#define VLAN_TAG_STRIP_NONE		FIELD_PREP(VLAN_TAG_CTRL_EVLS_MASK, 0x0)
+#define VLAN_TAG_STRIP_PASS		FIELD_PREP(VLAN_TAG_CTRL_EVLS_MASK, 0x1)
+#define VLAN_TAG_STRIP_FAIL		FIELD_PREP(VLAN_TAG_CTRL_EVLS_MASK, 0x2)
+#define VLAN_TAG_STRIP_ALL		FIELD_PREP(VLAN_TAG_CTRL_EVLS_MASK, 0x3)
+
+/* MAC VLAN Tag Data/Filter */
+#define VLAN_TAG_DATA_VID		GENMASK(15, 0)
+#define VLAN_TAG_DATA_VEN		BIT(16)
+#define VLAN_TAG_DATA_ETV		BIT(17)
+
+/* MAC VLAN HW FEAT */
+#define HW_FEATURE3			0x00000128
+#define VLAN_HW_FEAT_NRVF		GENMASK(2, 0)
+
+extern const struct stmmac_vlan_ops dwmac_vlan_ops;
+extern const struct stmmac_vlan_ops dwxgmac210_vlan_ops;
+extern const struct stmmac_vlan_ops dwxlgmac2_vlan_ops;
+
+u32 stmmac_get_num_vlan(void __iomem *ioaddr);
+
+#endif /* __STMMAC_VLAN_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h
index 896dc987d4ef..77ce8cfbe976 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h
@@ -4,7 +4,6 @@
 #ifndef _STMMAC_XDP_H_
 #define _STMMAC_XDP_H_
 
-#define STMMAC_MAX_RX_BUF_SIZE(num)	(((num) * PAGE_SIZE) - XDP_PACKET_HEADROOM)
 #define STMMAC_RX_DMA_ATTR	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
 
 int stmmac_xdp_setup_pool(struct stmmac_priv *priv, struct xsk_buff_pool *pool,
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index b8948d5b779a..acfb523214b9 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -3779,7 +3779,7 @@ static void cas_shutdown(struct cas *cp)
 	/* Make us not-running to avoid timers respawning */
 	cp->hw_running = 0;
 
-	del_timer_sync(&cp->link_timer);
+	timer_delete_sync(&cp->link_timer);
 
 	/* Stop the reset task */
 #if 0
@@ -4021,7 +4021,7 @@ done:
 
 static void cas_link_timer(struct timer_list *t)
 {
-	struct cas *cp = from_timer(cp, t, link_timer);
+	struct cas *cp = timer_container_of(cp, t, link_timer);
 	int mask, pending = 0, reset = 0;
 	unsigned long flags;
 
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index a9a6670b5ff1..6fc37ab27f7b 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -390,7 +390,7 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	return 0;
 
 err_out_del_timer:
-	del_timer_sync(&port->clean_timer);
+	timer_delete_sync(&port->clean_timer);
 	list_del_rcu(&port->list);
 	synchronize_rcu();
 	netif_napi_del(&port->napi);
@@ -408,8 +408,8 @@ static void vsw_port_remove(struct vio_dev *vdev)
 	unsigned long flags;
 
 	if (port) {
-		del_timer_sync(&port->vio.timer);
-		del_timer_sync(&port->clean_timer);
+		timer_delete_sync(&port->vio.timer);
+		timer_delete_sync(&port->clean_timer);
 
 		napi_disable(&port->napi);
 		unregister_netdev(port->dev);
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index df6d35d41b97..26119d02a94d 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -2225,7 +2225,7 @@ static int niu_link_status(struct niu *np, int *link_up_p)
 
 static void niu_timer(struct timer_list *t)
 {
-	struct niu *np = from_timer(np, t, timer);
+	struct niu *np = timer_container_of(np, t, timer);
 	unsigned long off;
 	int err, link_up;
 
@@ -3303,7 +3303,7 @@ static struct page *niu_find_rxpage(struct rx_ring_info *rp, u64 addr,
 	addr &= PAGE_MASK;
 	pp = &rp->rxhash[h];
 	for (; (p = *pp) != NULL; pp = &niu_next_page(p)) {
-		if (p->index == addr) {
+		if (p->private == addr) {
 			*link = pp;
 			goto found;
 		}
@@ -3318,7 +3318,7 @@ static void niu_hash_page(struct rx_ring_info *rp, struct page *page, u64 base)
 {
 	unsigned int h = niu_hash_rxaddr(rp, base);
 
-	page->index = base;
+	page->private = base;
 	niu_next_page(page) = rp->rxhash[h];
 	rp->rxhash[h] = page;
 }
@@ -3336,7 +3336,7 @@ static int niu_rbr_add_page(struct niu *np, struct rx_ring_info *rp,
 
 	addr = np->ops->map_page(np->device, page, 0,
 				 PAGE_SIZE, DMA_FROM_DEVICE);
-	if (!addr) {
+	if (np->ops->mapping_error(np->device, addr)) {
 		__free_page(page);
 		return -ENOMEM;
 	}
@@ -3400,11 +3400,11 @@ static int niu_rx_pkt_ignore(struct niu *np, struct rx_ring_info *rp)
 
 		rcr_size = rp->rbr_sizes[(val & RCR_ENTRY_PKTBUFSZ) >>
 					 RCR_ENTRY_PKTBUFSZ_SHIFT];
-		if ((page->index + PAGE_SIZE) - rcr_size == addr) {
+		if ((page->private + PAGE_SIZE) - rcr_size == addr) {
 			*link = niu_next_page(page);
-			np->ops->unmap_page(np->device, page->index,
+			np->ops->unmap_page(np->device, page->private,
 					    PAGE_SIZE, DMA_FROM_DEVICE);
-			page->index = 0;
+			page->private = 0;
 			niu_next_page(page) = NULL;
 			__free_page(page);
 			rp->rbr_refill_pending++;
@@ -3469,11 +3469,11 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 			append_size = append_size - skb->len;
 
 		niu_rx_skb_append(skb, page, off, append_size, rcr_size);
-		if ((page->index + rp->rbr_block_size) - rcr_size == addr) {
+		if ((page->private + rp->rbr_block_size) - rcr_size == addr) {
 			*link = niu_next_page(page);
-			np->ops->unmap_page(np->device, page->index,
+			np->ops->unmap_page(np->device, page->private,
 					    PAGE_SIZE, DMA_FROM_DEVICE);
-			page->index = 0;
+			page->private = 0;
 			niu_next_page(page) = NULL;
 			rp->rbr_refill_pending++;
 		} else
@@ -3538,11 +3538,11 @@ static void niu_rbr_free(struct niu *np, struct rx_ring_info *rp)
 		page = rp->rxhash[i];
 		while (page) {
 			struct page *next = niu_next_page(page);
-			u64 base = page->index;
+			u64 base = page->private;
 
 			np->ops->unmap_page(np->device, base, PAGE_SIZE,
 					    DMA_FROM_DEVICE);
-			page->index = 0;
+			page->private = 0;
 			niu_next_page(page) = NULL;
 
 			__free_page(page);
@@ -6086,7 +6086,7 @@ static void niu_enable_napi(struct niu *np)
 	int i;
 
 	for (i = 0; i < np->num_ldg; i++)
-		napi_enable(&np->ldg[i].napi);
+		napi_enable_locked(&np->ldg[i].napi);
 }
 
 static void niu_disable_napi(struct niu *np)
@@ -6116,7 +6116,9 @@ static int niu_open(struct net_device *dev)
 	if (err)
 		goto out_free_channels;
 
+	netdev_lock(dev);
 	niu_enable_napi(np);
+	netdev_unlock(dev);
 
 	spin_lock_irq(&np->lock);
 
@@ -6163,7 +6165,7 @@ static void niu_full_shutdown(struct niu *np, struct net_device *dev)
 	niu_disable_napi(np);
 	netif_tx_stop_all_queues(dev);
 
-	del_timer_sync(&np->timer);
+	timer_delete_sync(&np->timer);
 
 	spin_lock_irq(&np->lock);
 
@@ -6460,7 +6462,7 @@ static void niu_reset_buffers(struct niu *np)
 				page = rp->rxhash[j];
 				while (page) {
 					struct page *next = niu_next_page(page);
-					u64 base = page->index;
+					u64 base = page->private;
 					base = base >> RBR_DESCR_ADDR_SHIFT;
 					rp->rbr[k++] = cpu_to_le32(base);
 					page = next;
@@ -6509,7 +6511,7 @@ static void niu_reset_task(struct work_struct *work)
 
 	spin_unlock_irqrestore(&np->lock, flags);
 
-	del_timer_sync(&np->timer);
+	timer_delete_sync(&np->timer);
 
 	niu_netif_stop(np);
 
@@ -6521,6 +6523,7 @@ static void niu_reset_task(struct work_struct *work)
 
 	niu_reset_buffers(np);
 
+	netdev_lock(np->dev);
 	spin_lock_irqsave(&np->lock, flags);
 
 	err = niu_init_hw(np);
@@ -6531,6 +6534,7 @@ static void niu_reset_task(struct work_struct *work)
 	}
 
 	spin_unlock_irqrestore(&np->lock, flags);
+	netdev_unlock(np->dev);
 }
 
 static void niu_tx_timeout(struct net_device *dev, unsigned int txqueue)
@@ -6672,6 +6676,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 	len = skb_headlen(skb);
 	mapping = np->ops->map_single(np->device, skb->data,
 				      len, DMA_TO_DEVICE);
+	if (np->ops->mapping_error(np->device, mapping))
+		goto out_drop;
 
 	prod = rp->prod;
 
@@ -6713,6 +6719,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 		mapping = np->ops->map_page(np->device, skb_frag_page(frag),
 					    skb_frag_off(frag), len,
 					    DMA_TO_DEVICE);
+		if (np->ops->mapping_error(np->device, mapping))
+			goto out_unmap;
 
 		rp->tx_buffs[prod].skb = NULL;
 		rp->tx_buffs[prod].mapping = mapping;
@@ -6737,6 +6745,19 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 out:
 	return NETDEV_TX_OK;
 
+out_unmap:
+	while (i--) {
+		const skb_frag_t *frag;
+
+		prod = PREVIOUS_TX(rp, prod);
+		frag = &skb_shinfo(skb)->frags[i];
+		np->ops->unmap_page(np->device, rp->tx_buffs[prod].mapping,
+				    skb_frag_size(frag), DMA_TO_DEVICE);
+	}
+
+	np->ops->unmap_single(np->device, rp->tx_buffs[rp->prod].mapping,
+			      skb_headlen(skb), DMA_TO_DEVICE);
+
 out_drop:
 	rp->tx_errors++;
 	kfree_skb(skb);
@@ -6761,7 +6782,9 @@ static int niu_change_mtu(struct net_device *dev, int new_mtu)
 
 	niu_free_channels(np);
 
+	netdev_lock(dev);
 	niu_enable_napi(np);
+	netdev_unlock(dev);
 
 	err = niu_alloc_channels(np);
 	if (err)
@@ -9058,6 +9081,8 @@ static void niu_try_msix(struct niu *np, u8 *ldg_num_map)
 		msi_vec[i].entry = i;
 	}
 
+	pdev->dev_flags |= PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST;
+
 	num_irqs = pci_enable_msix_range(pdev, msi_vec, 1, num_irqs);
 	if (num_irqs < 0) {
 		np->flags &= ~NIU_FLAGS_MSIX;
@@ -9636,6 +9661,11 @@ static void niu_pci_unmap_single(struct device *dev, u64 dma_address,
 	dma_unmap_single(dev, dma_address, size, direction);
 }
 
+static int niu_pci_mapping_error(struct device *dev, u64 addr)
+{
+	return dma_mapping_error(dev, addr);
+}
+
 static const struct niu_ops niu_pci_ops = {
 	.alloc_coherent	= niu_pci_alloc_coherent,
 	.free_coherent	= niu_pci_free_coherent,
@@ -9643,6 +9673,7 @@ static const struct niu_ops niu_pci_ops = {
 	.unmap_page	= niu_pci_unmap_page,
 	.map_single	= niu_pci_map_single,
 	.unmap_single	= niu_pci_unmap_single,
+	.mapping_error	= niu_pci_mapping_error,
 };
 
 static void niu_driver_version(void)
@@ -9908,7 +9939,7 @@ static int __maybe_unused niu_suspend(struct device *dev_d)
 	flush_work(&np->reset_task);
 	niu_netif_stop(np);
 
-	del_timer_sync(&np->timer);
+	timer_delete_sync(&np->timer);
 
 	spin_lock_irqsave(&np->lock, flags);
 	niu_enable_interrupts(np, 0);
@@ -9937,6 +9968,7 @@ static int __maybe_unused niu_resume(struct device *dev_d)
 
 	spin_lock_irqsave(&np->lock, flags);
 
+	netdev_lock(dev);
 	err = niu_init_hw(np);
 	if (!err) {
 		np->timer.expires = jiffies + HZ;
@@ -9945,6 +9977,7 @@ static int __maybe_unused niu_resume(struct device *dev_d)
 	}
 
 	spin_unlock_irqrestore(&np->lock, flags);
+	netdev_unlock(dev);
 
 	return err;
 }
@@ -10009,6 +10042,11 @@ static void niu_phys_unmap_single(struct device *dev, u64 dma_address,
 	/* Nothing to do.  */
 }
 
+static int niu_phys_mapping_error(struct device *dev, u64 dma_address)
+{
+	return false;
+}
+
 static const struct niu_ops niu_phys_ops = {
 	.alloc_coherent	= niu_phys_alloc_coherent,
 	.free_coherent	= niu_phys_free_coherent,
@@ -10016,6 +10054,7 @@ static const struct niu_ops niu_phys_ops = {
 	.unmap_page	= niu_phys_unmap_page,
 	.map_single	= niu_phys_map_single,
 	.unmap_single	= niu_phys_unmap_single,
+	.mapping_error	= niu_phys_mapping_error,
 };
 
 static int niu_of_probe(struct platform_device *op)
diff --git a/drivers/net/ethernet/sun/niu.h b/drivers/net/ethernet/sun/niu.h
index 04c215f91fc0..0b169c08b0f2 100644
--- a/drivers/net/ethernet/sun/niu.h
+++ b/drivers/net/ethernet/sun/niu.h
@@ -2879,6 +2879,9 @@ struct tx_ring_info {
 #define NEXT_TX(tp, index) \
 	(((index) + 1) < (tp)->pending ? ((index) + 1) : 0)
 
+#define PREVIOUS_TX(tp, index) \
+	(((index) - 1) >= 0 ? ((index) - 1) : (((tp)->pending) - 1))
+
 static inline u32 niu_tx_avail(struct tx_ring_info *tp)
 {
 	return (tp->pending -
@@ -3140,6 +3143,7 @@ struct niu_ops {
 			  enum dma_data_direction direction);
 	void (*unmap_single)(struct device *dev, u64 dma_address,
 			     size_t size, enum dma_data_direction direction);
+	int (*mapping_error)(struct device *dev, u64 dma_address);
 };
 
 struct niu_link_config {
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index bbb3a6ca19ed..edb2fd3a6551 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -526,7 +526,7 @@ static int try_next_permutation(struct bigmac *bp, void __iomem *tregs)
 
 static void bigmac_timer(struct timer_list *t)
 {
-	struct bigmac *bp = from_timer(bp, t, bigmac_timer);
+	struct bigmac *bp = timer_container_of(bp, t, bigmac_timer);
 	void __iomem *tregs = bp->tregs;
 	int restart_timer = 0;
 
@@ -931,7 +931,7 @@ static int bigmac_close(struct net_device *dev)
 {
 	struct bigmac *bp = netdev_priv(dev);
 
-	del_timer(&bp->bigmac_timer);
+	timer_delete(&bp->bigmac_timer);
 	bp->timer_state = asleep;
 	bp->timer_ticks = 0;
 
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 3e5f9b17c777..8e69d917d827 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -1481,7 +1481,7 @@ static int gem_mdio_link_not_up(struct gem *gp)
 
 static void gem_link_timer(struct timer_list *t)
 {
-	struct gem *gp = from_timer(gp, t, link_timer);
+	struct gem *gp = timer_container_of(gp, t, link_timer);
 	struct net_device *dev = gp->dev;
 	int restart_aneg = 0;
 
@@ -2180,7 +2180,7 @@ static void gem_do_stop(struct net_device *dev, int wol)
 	gem_disable_ints(gp);
 
 	/* Stop the link timer */
-	del_timer_sync(&gp->link_timer);
+	timer_delete_sync(&gp->link_timer);
 
 	/* We cannot cancel the reset task while holding the
 	 * rtnl lock, we'd get an A->B / B->A deadlock stituation
@@ -2230,7 +2230,7 @@ static void gem_reset_task(struct work_struct *work)
 	}
 
 	/* Stop the link timer */
-	del_timer_sync(&gp->link_timer);
+	timer_delete_sync(&gp->link_timer);
 
 	/* Stop NAPI and tx */
 	gem_netif_stop(gp);
@@ -2610,7 +2610,7 @@ static int gem_set_link_ksettings(struct net_device *dev,
 
 	/* Apply settings and restart link process. */
 	if (netif_device_present(gp->dev)) {
-		del_timer_sync(&gp->link_timer);
+		timer_delete_sync(&gp->link_timer);
 		gem_begin_auto_negotiation(gp, cmd);
 	}
 
@@ -2626,7 +2626,7 @@ static int gem_nway_reset(struct net_device *dev)
 
 	/* Restart link process  */
 	if (netif_device_present(gp->dev)) {
-		del_timer_sync(&gp->link_timer);
+		timer_delete_sync(&gp->link_timer);
 		gem_begin_auto_negotiation(gp, NULL);
 	}
 
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 50ace461a1af..4bc0e114d5ee 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -721,7 +721,7 @@ force_link:
 
 static void happy_meal_timer(struct timer_list *t)
 {
-	struct happy_meal *hp = from_timer(hp, t, happy_timer);
+	struct happy_meal *hp = timer_container_of(hp, t, happy_timer);
 	void __iomem *tregs = hp->tcvregs;
 	int restart_timer = 0;
 
@@ -1265,7 +1265,7 @@ static int happy_meal_init(struct happy_meal *hp)
 	u32 regtmp, rxcfg;
 
 	/* If auto-negotiation timer is running, kill it. */
-	del_timer(&hp->happy_timer);
+	timer_delete(&hp->happy_timer);
 
 	HMD("happy_flags[%08x]\n", hp->happy_flags);
 	if (!(hp->happy_flags & HFLAG_INIT)) {
@@ -1922,7 +1922,7 @@ static int happy_meal_close(struct net_device *dev)
 	happy_meal_clean_rings(hp);
 
 	/* If auto-negotiation timer is running, kill it. */
-	del_timer(&hp->happy_timer);
+	timer_delete(&hp->happy_timer);
 
 	spin_unlock_irq(&hp->happy_lock);
 
@@ -2184,7 +2184,7 @@ static int hme_set_link_ksettings(struct net_device *dev,
 
 	/* Ok, do it to it. */
 	spin_lock_irq(&hp->happy_lock);
-	del_timer(&hp->happy_timer);
+	timer_delete(&hp->happy_timer);
 	happy_meal_begin_auto_negotiation(hp, hp->tcvregs, cmd);
 	spin_unlock_irq(&hp->happy_lock);
 
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 1e887d951a04..a2a3e94da4b8 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -505,7 +505,7 @@ static void vnet_port_remove(struct vio_dev *vdev)
 	struct vnet_port *port = dev_get_drvdata(&vdev->dev);
 
 	if (port) {
-		del_timer_sync(&port->vio.timer);
+		timer_delete_sync(&port->vio.timer);
 
 		napi_disable(&port->napi);
 
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index 1cacb2a0ee03..0212853c9430 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1044,7 +1044,7 @@ static inline void vnet_free_skbs(struct sk_buff *skb)
 
 void sunvnet_clean_timer_expire_common(struct timer_list *t)
 {
-	struct vnet_port *port = from_timer(port, t, clean_timer);
+	struct vnet_port *port = timer_container_of(port, t, clean_timer);
 	struct sk_buff *freeskbs;
 	unsigned pending;
 
@@ -1058,7 +1058,7 @@ void sunvnet_clean_timer_expire_common(struct timer_list *t)
 		(void)mod_timer(&port->clean_timer,
 				jiffies + VNET_CLEAN_TIMEOUT);
 	 else
-		del_timer(&port->clean_timer);
+		timer_delete(&port->clean_timer);
 }
 EXPORT_SYMBOL_GPL(sunvnet_clean_timer_expire_common);
 
@@ -1513,7 +1513,7 @@ out_dropped:
 		(void)mod_timer(&port->clean_timer,
 				jiffies + VNET_CLEAN_TIMEOUT);
 	else if (port)
-		del_timer(&port->clean_timer);
+		timer_delete(&port->clean_timer);
 	rcu_read_unlock();
 	dev_kfree_skb(skb);
 	vnet_free_skbs(freeskbs);
@@ -1707,7 +1707,7 @@ EXPORT_SYMBOL_GPL(sunvnet_port_free_tx_bufs_common);
 
 void vnet_port_reset(struct vnet_port *port)
 {
-	del_timer(&port->clean_timer);
+	timer_delete(&port->clean_timer);
 	sunvnet_port_free_tx_bufs_common(port);
 	port->rmtu = 0;
 	port->tso = (port->vsw == 0);  /* no tso in vsw, misbehaves in bridge */
diff --git a/drivers/net/ethernet/sunplus/spl2sw_driver.c b/drivers/net/ethernet/sunplus/spl2sw_driver.c
index 721d8ed3f302..5e0e4c9ecbb0 100644
--- a/drivers/net/ethernet/sunplus/spl2sw_driver.c
+++ b/drivers/net/ethernet/sunplus/spl2sw_driver.c
@@ -199,7 +199,7 @@ static const struct net_device_ops netdev_ops = {
 	.ndo_start_xmit = spl2sw_ethernet_start_xmit,
 	.ndo_set_rx_mode = spl2sw_ethernet_set_rx_mode,
 	.ndo_set_mac_address = spl2sw_ethernet_set_mac_address,
-	.ndo_do_ioctl = phy_do_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl,
 	.ndo_tx_timeout = spl2sw_ethernet_tx_timeout,
 };
 
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
index d1793b6154c7..37101dc50d04 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
@@ -360,7 +360,8 @@ static irqreturn_t xlgmac_dma_isr(int irq, void *data)
 
 static void xlgmac_tx_timer(struct timer_list *t)
 {
-	struct xlgmac_channel *channel = from_timer(channel, t, tx_timer);
+	struct xlgmac_channel *channel = timer_container_of(channel, t,
+							    tx_timer);
 	struct xlgmac_pdata *pdata = channel->pdata;
 	struct napi_struct *napi;
 
@@ -405,7 +406,7 @@ static void xlgmac_stop_timers(struct xlgmac_pdata *pdata)
 		if (!channel->tx_ring)
 			break;
 
-		del_timer_sync(&channel->tx_timer);
+		timer_delete_sync(&channel->tx_timer);
 	}
 }
 
diff --git a/drivers/net/ethernet/tehuti/tn40.c b/drivers/net/ethernet/tehuti/tn40.c
index 259bdac24cf2..558b791a97ed 100644
--- a/drivers/net/ethernet/tehuti/tn40.c
+++ b/drivers/net/ethernet/tehuti/tn40.c
@@ -1778,7 +1778,7 @@ static int tn40_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ret = tn40_phy_register(priv);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to set up PHY.\n");
-		goto err_free_irq;
+		goto err_cleanup_swnodes;
 	}
 
 	ret = tn40_priv_init(priv);
@@ -1795,6 +1795,8 @@ static int tn40_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 err_unregister_phydev:
 	tn40_phy_unregister(priv);
+err_cleanup_swnodes:
+	tn40_swnodes_cleanup(priv);
 err_free_irq:
 	pci_free_irq_vectors(pdev);
 err_unset_drvdata:
@@ -1816,6 +1818,7 @@ static void tn40_remove(struct pci_dev *pdev)
 	unregister_netdev(ndev);
 
 	tn40_phy_unregister(priv);
+	tn40_swnodes_cleanup(priv);
 	pci_free_irq_vectors(priv->pdev);
 	pci_set_drvdata(pdev, NULL);
 	iounmap(priv->regs);
@@ -1832,6 +1835,10 @@ static const struct pci_device_id tn40_id_table[] = {
 			 PCI_VENDOR_ID_ASUSTEK, 0x8709) },
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, 0x4022,
 			 PCI_VENDOR_ID_EDIMAX, 0x8103) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, PCI_DEVICE_ID_TEHUTI_TN9510,
+			 PCI_VENDOR_ID_TEHUTI, 0x3015) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, PCI_DEVICE_ID_TEHUTI_TN9510,
+			 PCI_VENDOR_ID_EDIMAX, 0x8102) },
 	{ }
 };
 
diff --git a/drivers/net/ethernet/tehuti/tn40.h b/drivers/net/ethernet/tehuti/tn40.h
index 490781fe5120..25da8686d469 100644
--- a/drivers/net/ethernet/tehuti/tn40.h
+++ b/drivers/net/ethernet/tehuti/tn40.h
@@ -4,10 +4,13 @@
 #ifndef _TN40_H_
 #define _TN40_H_
 
+#include <linux/property.h>
 #include "tn40_regs.h"
 
 #define TN40_DRV_NAME "tn40xx"
 
+#define PCI_DEVICE_ID_TEHUTI_TN9510	0x4025
+
 #define TN40_MDIO_SPEED_1MHZ (1)
 #define TN40_MDIO_SPEED_6MHZ (6)
 
@@ -102,10 +105,39 @@ struct tn40_txdb {
 	int size; /* Number of elements in the db */
 };
 
+#define NODE_PROP(_NAME, _PROP)	(		\
+	(const struct software_node) {		\
+		.name = _NAME,			\
+		.properties = _PROP,		\
+	})
+
+#define NODE_PAR_PROP(_NAME, _PAR, _PROP)	(	\
+	(const struct software_node) {		\
+		.name = _NAME,			\
+		.parent = _PAR,			\
+		.properties = _PROP,		\
+	})
+
+enum tn40_swnodes {
+	SWNODE_MDIO,
+	SWNODE_PHY,
+	SWNODE_MAX
+};
+
+struct tn40_nodes {
+	char phy_name[32];
+	char mdio_name[32];
+	struct property_entry phy_props[3];
+	struct software_node swnodes[SWNODE_MAX];
+	const struct software_node *group[SWNODE_MAX + 1];
+};
+
 struct tn40_priv {
 	struct net_device *ndev;
 	struct pci_dev *pdev;
 
+	struct tn40_nodes nodes;
+
 	struct napi_struct napi;
 	/* RX FIFOs: 1 for data (full) descs, and 2 for free descs */
 	struct tn40_rxd_fifo rxd_fifo0;
@@ -225,6 +257,7 @@ static inline void tn40_write_reg(struct tn40_priv *priv, u32 reg, u32 val)
 
 int tn40_set_link_speed(struct tn40_priv *priv, u32 speed);
 
+void tn40_swnodes_cleanup(struct tn40_priv *priv);
 int tn40_mdiobus_init(struct tn40_priv *priv);
 
 int tn40_phy_register(struct tn40_priv *priv);
diff --git a/drivers/net/ethernet/tehuti/tn40_mdio.c b/drivers/net/ethernet/tehuti/tn40_mdio.c
index af18615d64a8..fb1a4a2e4dbc 100644
--- a/drivers/net/ethernet/tehuti/tn40_mdio.c
+++ b/drivers/net/ethernet/tehuti/tn40_mdio.c
@@ -14,6 +14,8 @@
 	 (FIELD_PREP(TN40_MDIO_PRTAD_MASK, (port))))
 #define TN40_MDIO_CMD_READ BIT(15)
 
+#define AQR105_FIRMWARE "tehuti/aqr105-tn40xx.cld"
+
 static void tn40_mdio_set_speed(struct tn40_priv *priv, u32 speed)
 {
 	void __iomem *regs = priv->regs;
@@ -111,6 +113,56 @@ static int tn40_mdio_write_c45(struct mii_bus *mii_bus, int addr, int devnum,
 	return  tn40_mdio_write(mii_bus->priv, addr, devnum, regnum, val);
 }
 
+/* registers an mdio node and an aqr105 PHY at address 1
+ * tn40_mdio-%id {
+ *	ethernet-phy@1 {
+ *		compatible = "ethernet-phy-id03a1.b4a3";
+ *		reg = <1>;
+ *		firmware-name = AQR105_FIRMWARE;
+ *	};
+ * };
+ */
+static int tn40_swnodes_register(struct tn40_priv *priv)
+{
+	struct tn40_nodes *nodes = &priv->nodes;
+	struct pci_dev *pdev = priv->pdev;
+	struct software_node *swnodes;
+	u32 id;
+
+	id = pci_dev_id(pdev);
+
+	snprintf(nodes->phy_name, sizeof(nodes->phy_name), "ethernet-phy@1");
+	snprintf(nodes->mdio_name, sizeof(nodes->mdio_name), "tn40_mdio-%x",
+		 id);
+
+	swnodes = nodes->swnodes;
+
+	swnodes[SWNODE_MDIO] = NODE_PROP(nodes->mdio_name, NULL);
+
+	nodes->phy_props[0] = PROPERTY_ENTRY_STRING("compatible",
+						    "ethernet-phy-id03a1.b4a3");
+	nodes->phy_props[1] = PROPERTY_ENTRY_U32("reg", 1);
+	nodes->phy_props[2] = PROPERTY_ENTRY_STRING("firmware-name",
+						    AQR105_FIRMWARE);
+	swnodes[SWNODE_PHY] = NODE_PAR_PROP(nodes->phy_name,
+					    &swnodes[SWNODE_MDIO],
+					    nodes->phy_props);
+
+	nodes->group[SWNODE_PHY] = &swnodes[SWNODE_PHY];
+	nodes->group[SWNODE_MDIO] = &swnodes[SWNODE_MDIO];
+	return software_node_register_node_group(nodes->group);
+}
+
+void tn40_swnodes_cleanup(struct tn40_priv *priv)
+{
+	/* cleanup of swnodes is only needed for AQR105-based cards */
+	if (priv->pdev->device == PCI_DEVICE_ID_TEHUTI_TN9510) {
+		fwnode_handle_put(dev_fwnode(&priv->mdio->dev));
+		device_remove_software_node(&priv->mdio->dev);
+		software_node_unregister_node_group(priv->nodes.group);
+	}
+}
+
 int tn40_mdiobus_init(struct tn40_priv *priv)
 {
 	struct pci_dev *pdev = priv->pdev;
@@ -129,14 +181,40 @@ int tn40_mdiobus_init(struct tn40_priv *priv)
 
 	bus->read_c45 = tn40_mdio_read_c45;
 	bus->write_c45 = tn40_mdio_write_c45;
+	priv->mdio = bus;
 
+	/* provide swnodes for AQR105-based cards only */
+	if (pdev->device == PCI_DEVICE_ID_TEHUTI_TN9510) {
+		ret = tn40_swnodes_register(priv);
+		if (ret) {
+			pr_err("swnodes failed\n");
+			return ret;
+		}
+
+		ret = device_add_software_node(&bus->dev,
+					       priv->nodes.group[SWNODE_MDIO]);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"device_add_software_node failed: %d\n", ret);
+			goto err_swnodes_unregister;
+		}
+	}
+
+	tn40_mdio_set_speed(priv, TN40_MDIO_SPEED_6MHZ);
 	ret = devm_mdiobus_register(&pdev->dev, bus);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register mdiobus %d %u %u\n",
 			ret, bus->state, MDIOBUS_UNREGISTERED);
-		return ret;
+		goto err_swnodes_cleanup;
 	}
-	tn40_mdio_set_speed(priv, TN40_MDIO_SPEED_6MHZ);
-	priv->mdio = bus;
 	return 0;
+
+err_swnodes_unregister:
+	software_node_unregister_node_group(priv->nodes.group);
+	return ret;
+err_swnodes_cleanup:
+	tn40_swnodes_cleanup(priv);
+	return ret;
 }
+
+MODULE_FIRMWARE(AQR105_FIRMWARE);
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 0d5a862cd78a..a07c910c497a 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -99,6 +99,7 @@ config TI_K3_AM65_CPSW_NUSS
 	select NET_DEVLINK
 	select TI_DAVINCI_MDIO
 	select PHYLINK
+	select PAGE_POOL
 	select TI_K3_CPPI_DESC_POOL
 	imply PHY_TI_GMII_SEL
 	depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS
@@ -204,6 +205,7 @@ config TI_ICSSG_PRUETH_SR1
 	select PHYLIB
 	select TI_ICSS_IEP
 	select TI_K3_CPPI_DESC_POOL
+	select PAGE_POOL
 	depends on PRU_REMOTEPROC
 	depends on NET_SWITCHDEV
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 14e1df721f2e..f20d1ff192ef 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -32,6 +32,7 @@
 #include <linux/dma/ti-cppi5.h>
 #include <linux/dma/k3-udma-glue.h>
 #include <net/page_pool/helpers.h>
+#include <net/dsa.h>
 #include <net/switchdev.h>
 
 #include "cpsw_ale.h"
@@ -163,6 +164,7 @@
 #define AM65_CPSW_CPPI_TX_PKT_TYPE 0x7
 
 /* XDP */
+#define AM65_CPSW_XDP_TX       BIT(2)
 #define AM65_CPSW_XDP_CONSUMED BIT(1)
 #define AM65_CPSW_XDP_REDIRECT BIT(0)
 #define AM65_CPSW_XDP_PASS     0
@@ -425,7 +427,7 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev,
 
 	if (netif_tx_queue_stopped(netif_txq)) {
 		/* try recover if stopped by us */
-		txq_trans_update(netif_txq);
+		txq_trans_update(ndev, netif_txq);
 		netif_tx_wake_queue(netif_txq);
 	}
 }
@@ -497,35 +499,62 @@ static void am65_cpsw_init_host_port_switch(struct am65_cpsw_common *common);
 static void am65_cpsw_init_host_port_emac(struct am65_cpsw_common *common);
 static void am65_cpsw_init_port_switch_ale(struct am65_cpsw_port *port);
 static void am65_cpsw_init_port_emac_ale(struct am65_cpsw_port *port);
+static inline void am65_cpsw_put_page(struct am65_cpsw_rx_flow *flow,
+				      struct page *page,
+				      bool allow_direct);
+static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma);
+static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma);
 
-static void am65_cpsw_destroy_xdp_rxqs(struct am65_cpsw_common *common)
+static void am65_cpsw_destroy_rxq(struct am65_cpsw_common *common, int id)
 {
 	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
 	struct am65_cpsw_rx_flow *flow;
 	struct xdp_rxq_info *rxq;
-	int id, port;
+	int port;
 
-	for (id = 0; id < common->rx_ch_num_flows; id++) {
-		flow = &rx_chn->flows[id];
+	flow = &rx_chn->flows[id];
+	napi_disable(&flow->napi_rx);
+	hrtimer_cancel(&flow->rx_hrtimer);
+	k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, id, rx_chn,
+				  am65_cpsw_nuss_rx_cleanup);
 
-		for (port = 0; port < common->port_num; port++) {
-			if (!common->ports[port].ndev)
-				continue;
+	for (port = 0; port < common->port_num; port++) {
+		if (!common->ports[port].ndev)
+			continue;
 
-			rxq = &common->ports[port].xdp_rxq[id];
+		rxq = &common->ports[port].xdp_rxq[id];
 
-			if (xdp_rxq_info_is_reg(rxq))
-				xdp_rxq_info_unreg(rxq);
-		}
+		if (xdp_rxq_info_is_reg(rxq))
+			xdp_rxq_info_unreg(rxq);
+	}
 
-		if (flow->page_pool) {
-			page_pool_destroy(flow->page_pool);
-			flow->page_pool = NULL;
-		}
+	if (flow->page_pool) {
+		page_pool_destroy(flow->page_pool);
+		flow->page_pool = NULL;
+	}
+}
+
+static void am65_cpsw_destroy_rxqs(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	int id;
+
+	reinit_completion(&common->tdown_complete);
+	k3_udma_glue_tdown_rx_chn(rx_chn->rx_chn, true);
+
+	if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) {
+		id = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000));
+		if (!id)
+			dev_err(common->dev, "rx teardown timeout\n");
 	}
+
+	for (id = common->rx_ch_num_flows - 1; id >= 0; id--)
+		am65_cpsw_destroy_rxq(common, id);
+
+	k3_udma_glue_disable_rx_chn(common->rx_chns.rx_chn);
 }
 
-static int am65_cpsw_create_xdp_rxqs(struct am65_cpsw_common *common)
+static int am65_cpsw_create_rxq(struct am65_cpsw_common *common, int id)
 {
 	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
 	struct page_pool_params pp_params = {
@@ -540,45 +569,162 @@ static int am65_cpsw_create_xdp_rxqs(struct am65_cpsw_common *common)
 	struct am65_cpsw_rx_flow *flow;
 	struct xdp_rxq_info *rxq;
 	struct page_pool *pool;
-	int id, port, ret;
+	struct page *page;
+	int port, ret, i;
+
+	flow = &rx_chn->flows[id];
+	pp_params.napi = &flow->napi_rx;
+	pool = page_pool_create(&pp_params);
+	if (IS_ERR(pool)) {
+		ret = PTR_ERR(pool);
+		return ret;
+	}
+
+	flow->page_pool = pool;
+
+	/* using same page pool is allowed as no running rx handlers
+	 * simultaneously for both ndevs
+	 */
+	for (port = 0; port < common->port_num; port++) {
+		if (!common->ports[port].ndev)
+		/* FIXME should we BUG here? */
+			continue;
+
+		rxq = &common->ports[port].xdp_rxq[id];
+		ret = xdp_rxq_info_reg(rxq, common->ports[port].ndev,
+				       id, flow->napi_rx.napi_id);
+		if (ret)
+			goto err;
+
+		ret = xdp_rxq_info_reg_mem_model(rxq,
+						 MEM_TYPE_PAGE_POOL,
+						 pool);
+		if (ret)
+			goto err;
+	}
+
+	for (i = 0; i < AM65_CPSW_MAX_RX_DESC; i++) {
+		page = page_pool_dev_alloc_pages(flow->page_pool);
+		if (!page) {
+			dev_err(common->dev, "cannot allocate page in flow %d\n",
+				id);
+			ret = -ENOMEM;
+			goto err;
+		}
+
+		ret = am65_cpsw_nuss_rx_push(common, page, id);
+		if (ret < 0) {
+			dev_err(common->dev,
+				"cannot submit page to rx channel flow %d, error %d\n",
+				id, ret);
+			am65_cpsw_put_page(flow, page, false);
+			goto err;
+		}
+	}
+
+	napi_enable(&flow->napi_rx);
+	return 0;
+
+err:
+	am65_cpsw_destroy_rxq(common, id);
+	return ret;
+}
+
+static int am65_cpsw_create_rxqs(struct am65_cpsw_common *common)
+{
+	int id, ret;
 
 	for (id = 0; id < common->rx_ch_num_flows; id++) {
-		flow = &rx_chn->flows[id];
-		pp_params.napi = &flow->napi_rx;
-		pool = page_pool_create(&pp_params);
-		if (IS_ERR(pool)) {
-			ret = PTR_ERR(pool);
+		ret = am65_cpsw_create_rxq(common, id);
+		if (ret) {
+			dev_err(common->dev, "couldn't create rxq %d: %d\n",
+				id, ret);
 			goto err;
 		}
+	}
 
-		flow->page_pool = pool;
+	ret = k3_udma_glue_enable_rx_chn(common->rx_chns.rx_chn);
+	if (ret) {
+		dev_err(common->dev, "couldn't enable rx chn: %d\n", ret);
+		goto err;
+	}
 
-		/* using same page pool is allowed as no running rx handlers
-		 * simultaneously for both ndevs
-		 */
-		for (port = 0; port < common->port_num; port++) {
-			if (!common->ports[port].ndev)
-				continue;
+	return 0;
+
+err:
+	for (--id; id >= 0; id--)
+		am65_cpsw_destroy_rxq(common, id);
+
+	return ret;
+}
+
+static void am65_cpsw_destroy_txq(struct am65_cpsw_common *common, int id)
+{
+	struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[id];
+
+	napi_disable(&tx_chn->napi_tx);
+	hrtimer_cancel(&tx_chn->tx_hrtimer);
+	k3_udma_glue_reset_tx_chn(tx_chn->tx_chn, tx_chn,
+				  am65_cpsw_nuss_tx_cleanup);
+	k3_udma_glue_disable_tx_chn(tx_chn->tx_chn);
+}
+
+static void am65_cpsw_destroy_txqs(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_tx_chn *tx_chn = common->tx_chns;
+	int id;
+
+	/* shutdown tx channels */
+	atomic_set(&common->tdown_cnt, common->tx_ch_num);
+	/* ensure new tdown_cnt value is visible */
+	smp_mb__after_atomic();
+	reinit_completion(&common->tdown_complete);
+
+	for (id = 0; id < common->tx_ch_num; id++)
+		k3_udma_glue_tdown_tx_chn(tx_chn[id].tx_chn, false);
+
+	id = wait_for_completion_timeout(&common->tdown_complete,
+					 msecs_to_jiffies(1000));
+	if (!id)
+		dev_err(common->dev, "tx teardown timeout\n");
+
+	for (id = common->tx_ch_num - 1; id >= 0; id--)
+		am65_cpsw_destroy_txq(common, id);
+}
+
+static int am65_cpsw_create_txq(struct am65_cpsw_common *common, int id)
+{
+	struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[id];
+	int ret;
+
+	ret = k3_udma_glue_enable_tx_chn(tx_chn->tx_chn);
+	if (ret)
+		return ret;
 
-			rxq = &common->ports[port].xdp_rxq[id];
+	napi_enable(&tx_chn->napi_tx);
 
-			ret = xdp_rxq_info_reg(rxq, common->ports[port].ndev,
-					       id, flow->napi_rx.napi_id);
-			if (ret)
-				goto err;
+	return 0;
+}
 
-			ret = xdp_rxq_info_reg_mem_model(rxq,
-							 MEM_TYPE_PAGE_POOL,
-							 pool);
-			if (ret)
-				goto err;
+static int am65_cpsw_create_txqs(struct am65_cpsw_common *common)
+{
+	int id, ret;
+
+	for (id = 0; id < common->tx_ch_num; id++) {
+		ret = am65_cpsw_create_txq(common, id);
+		if (ret) {
+			dev_err(common->dev, "couldn't create txq %d: %d\n",
+				id, ret);
+			goto err;
 		}
 	}
 
 	return 0;
 
 err:
-	am65_cpsw_destroy_xdp_rxqs(common);
+	for (--id; id >= 0; id--)
+		am65_cpsw_destroy_txq(common, id);
+
 	return ret;
 }
 
@@ -642,7 +788,6 @@ static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma)
 	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-
 	am65_cpsw_put_page(&rx_chn->flows[flow_id], page, false);
 }
 
@@ -684,21 +829,30 @@ static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn,
 static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct am65_cpsw_tx_chn *tx_chn = data;
+	enum am65_cpsw_tx_buf_type buf_type;
+	struct am65_cpsw_tx_swdata *swdata;
 	struct cppi5_host_desc_t *desc_tx;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
-	void **swdata;
 
 	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
+	buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
+	if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
+		skb = swdata->skb;
+		dev_kfree_skb_any(skb);
+	} else {
+		xdpf = swdata->xdpf;
+		xdp_return_frame(xdpf);
+	}
 
-	dev_kfree_skb_any(skb);
+	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
 }
 
 static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
 					   struct net_device *ndev,
-					   unsigned int len)
+					   unsigned int len,
+					   unsigned int headroom)
 {
 	struct sk_buff *skb;
 
@@ -708,7 +862,7 @@ static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, AM65_CPSW_HEADROOM);
+	skb_reserve(skb, headroom);
 	skb->dev = ndev;
 
 	return skb;
@@ -717,12 +871,8 @@ static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
 static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 {
 	struct am65_cpsw_host *host_p = am65_common_get_host(common);
-	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
-	struct am65_cpsw_tx_chn *tx_chn = common->tx_chns;
-	int port_idx, i, ret, tx, flow_idx;
-	struct am65_cpsw_rx_flow *flow;
 	u32 val, port_mask;
-	struct page *page;
+	int port_idx, ret;
 
 	if (common->usage_count)
 		return 0;
@@ -762,7 +912,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 			     ALE_DEFAULT_THREAD_ID, 0);
 	cpsw_ale_control_set(common->ale, HOST_PORT_NUM,
 			     ALE_DEFAULT_THREAD_ENABLE, 1);
-	/* switch to vlan unaware mode */
+	/* switch to vlan aware mode */
 	cpsw_ale_control_set(common->ale, HOST_PORT_NUM, ALE_VLAN_AWARE, 1);
 	cpsw_ale_control_set(common->ale, HOST_PORT_NUM,
 			     ALE_PORT_STATE, ALE_PORT_STATE_FORWARD);
@@ -782,151 +932,38 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 
 	am65_cpsw_qos_tx_p0_rate_init(common);
 
-	ret = am65_cpsw_create_xdp_rxqs(common);
-	if (ret) {
-		dev_err(common->dev, "Failed to create XDP rx queues\n");
+	ret = am65_cpsw_create_rxqs(common);
+	if (ret)
 		return ret;
-	}
-
-	for (flow_idx = 0; flow_idx < common->rx_ch_num_flows; flow_idx++) {
-		flow = &rx_chn->flows[flow_idx];
-		for (i = 0; i < AM65_CPSW_MAX_RX_DESC; i++) {
-			page = page_pool_dev_alloc_pages(flow->page_pool);
-			if (!page) {
-				dev_err(common->dev, "cannot allocate page in flow %d\n",
-					flow_idx);
-				ret = -ENOMEM;
-				goto fail_rx;
-			}
-
-			ret = am65_cpsw_nuss_rx_push(common, page, flow_idx);
-			if (ret < 0) {
-				dev_err(common->dev,
-					"cannot submit page to rx channel flow %d, error %d\n",
-					flow_idx, ret);
-				am65_cpsw_put_page(flow, page, false);
-				goto fail_rx;
-			}
-		}
-	}
 
-	ret = k3_udma_glue_enable_rx_chn(rx_chn->rx_chn);
-	if (ret) {
-		dev_err(common->dev, "couldn't enable rx chn: %d\n", ret);
-		goto fail_rx;
-	}
-
-	for (i = 0; i < common->rx_ch_num_flows ; i++) {
-		napi_enable(&rx_chn->flows[i].napi_rx);
-		if (rx_chn->flows[i].irq_disabled) {
-			rx_chn->flows[i].irq_disabled = false;
-			enable_irq(rx_chn->flows[i].irq);
-		}
-	}
-
-	for (tx = 0; tx < common->tx_ch_num; tx++) {
-		ret = k3_udma_glue_enable_tx_chn(tx_chn[tx].tx_chn);
-		if (ret) {
-			dev_err(common->dev, "couldn't enable tx chn %d: %d\n",
-				tx, ret);
-			tx--;
-			goto fail_tx;
-		}
-		napi_enable(&tx_chn[tx].napi_tx);
-	}
+	ret = am65_cpsw_create_txqs(common);
+	if (ret)
+		goto cleanup_rx;
 
 	dev_dbg(common->dev, "cpsw_nuss started\n");
 	return 0;
 
-fail_tx:
-	while (tx >= 0) {
-		napi_disable(&tx_chn[tx].napi_tx);
-		k3_udma_glue_disable_tx_chn(tx_chn[tx].tx_chn);
-		tx--;
-	}
-
-	for (flow_idx = 0; i < common->rx_ch_num_flows; flow_idx++) {
-		flow = &rx_chn->flows[flow_idx];
-		if (!flow->irq_disabled) {
-			disable_irq(flow->irq);
-			flow->irq_disabled = true;
-		}
-		napi_disable(&flow->napi_rx);
-	}
-
-	k3_udma_glue_disable_rx_chn(rx_chn->rx_chn);
-
-fail_rx:
-	for (i = 0; i < common->rx_ch_num_flows; i++)
-		k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn,
-					  am65_cpsw_nuss_rx_cleanup, !!i);
-
-	am65_cpsw_destroy_xdp_rxqs(common);
+cleanup_rx:
+	am65_cpsw_destroy_rxqs(common);
 
 	return ret;
 }
 
 static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 {
-	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
-	struct am65_cpsw_tx_chn *tx_chn = common->tx_chns;
-	int i;
-
 	if (common->usage_count != 1)
 		return 0;
 
 	cpsw_ale_control_set(common->ale, HOST_PORT_NUM,
 			     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
 
-	/* shutdown tx channels */
-	atomic_set(&common->tdown_cnt, common->tx_ch_num);
-	/* ensure new tdown_cnt value is visible */
-	smp_mb__after_atomic();
-	reinit_completion(&common->tdown_complete);
-
-	for (i = 0; i < common->tx_ch_num; i++)
-		k3_udma_glue_tdown_tx_chn(tx_chn[i].tx_chn, false);
-
-	i = wait_for_completion_timeout(&common->tdown_complete,
-					msecs_to_jiffies(1000));
-	if (!i)
-		dev_err(common->dev, "tx timeout\n");
-	for (i = 0; i < common->tx_ch_num; i++) {
-		napi_disable(&tx_chn[i].napi_tx);
-		hrtimer_cancel(&tx_chn[i].tx_hrtimer);
-	}
-
-	for (i = 0; i < common->tx_ch_num; i++) {
-		k3_udma_glue_reset_tx_chn(tx_chn[i].tx_chn, &tx_chn[i],
-					  am65_cpsw_nuss_tx_cleanup);
-		k3_udma_glue_disable_tx_chn(tx_chn[i].tx_chn);
-	}
-
-	reinit_completion(&common->tdown_complete);
-	k3_udma_glue_tdown_rx_chn(rx_chn->rx_chn, true);
-
-	if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) {
-		i = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000));
-		if (!i)
-			dev_err(common->dev, "rx teardown timeout\n");
-	}
-
-	for (i = common->rx_ch_num_flows - 1; i >= 0; i--) {
-		napi_disable(&rx_chn->flows[i].napi_rx);
-		hrtimer_cancel(&rx_chn->flows[i].rx_hrtimer);
-		k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn,
-					  am65_cpsw_nuss_rx_cleanup, !!i);
-	}
-
-	k3_udma_glue_disable_rx_chn(rx_chn->rx_chn);
-
+	am65_cpsw_destroy_txqs(common);
+	am65_cpsw_destroy_rxqs(common);
 	cpsw_ale_stop(common->ale);
 
 	writel(0, common->cpsw_base + AM65_CPSW_REG_CTL);
 	writel(0, common->cpsw_base + AM65_CPSW_REG_STAT_PORT_EN);
 
-	am65_cpsw_destroy_xdp_rxqs(common);
-
 	dev_dbg(common->dev, "cpsw_nuss stopped\n");
 	return 0;
 }
@@ -1014,6 +1051,15 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev)
 
 	common->usage_count++;
 
+	/* VLAN aware CPSW mode is incompatible with some DSA tagging schemes.
+	 * Therefore disable VLAN_AWARE mode if any of the ports is a DSA Port.
+	 */
+	if (netdev_uses_dsa(ndev)) {
+		reg = readl(common->cpsw_base + AM65_CPSW_REG_CTL);
+		reg &= ~AM65_CPSW_CTL_VLAN_AWARE;
+		writel(reg, common->cpsw_base + AM65_CPSW_REG_CTL);
+	}
+
 	am65_cpsw_port_set_sl_mac(port, ndev->dev_addr);
 	am65_cpsw_port_enable_dscp_map(port);
 
@@ -1053,10 +1099,10 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 	struct cppi5_host_desc_t *host_desc;
+	struct am65_cpsw_tx_swdata *swdata;
 	struct netdev_queue *netif_txq;
 	dma_addr_t dma_desc, dma_buf;
 	u32 pkt_len = xdpf->len;
-	void **swdata;
 	int ret;
 
 	host_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
@@ -1086,7 +1132,8 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
 	cppi5_hdesc_attach_buf(host_desc, dma_buf, pkt_len, dma_buf, pkt_len);
 
 	swdata = cppi5_hdesc_get_swdata(host_desc);
-	*(swdata) = xdpf;
+	swdata->ndev = ndev;
+	swdata->xdpf = xdpf;
 
 	/* Report BQL before sending the packet */
 	netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
@@ -1122,20 +1169,21 @@ pool_free:
 
 static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 			     struct am65_cpsw_port *port,
-			     struct xdp_buff *xdp,
-			     int cpu, int *len)
+			     struct xdp_buff *xdp, int *len)
 {
 	struct am65_cpsw_common *common = flow->common;
 	struct net_device *ndev = port->ndev;
 	int ret = AM65_CPSW_XDP_CONSUMED;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
+	int cpu = smp_processor_id();
 	struct xdp_frame *xdpf;
 	struct bpf_prog *prog;
-	struct page *page;
+	int pkt_len;
 	u32 act;
 	int err;
 
+	pkt_len = *len;
 	prog = READ_ONCE(port->xdp_prog);
 	if (!prog)
 		return AM65_CPSW_XDP_PASS;
@@ -1146,15 +1194,16 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 
 	switch (act) {
 	case XDP_PASS:
-		ret = AM65_CPSW_XDP_PASS;
-		goto out;
+		return AM65_CPSW_XDP_PASS;
 	case XDP_TX:
 		tx_chn = &common->tx_chns[cpu % AM65_CPSW_MAX_QUEUES];
 		netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
 
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		if (unlikely(!xdpf))
+		if (unlikely(!xdpf)) {
+			ndev->stats.tx_dropped++;
 			goto drop;
+		}
 
 		__netif_tx_lock(netif_txq, cpu);
 		err = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf,
@@ -1163,16 +1212,14 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 		if (err)
 			goto drop;
 
-		dev_sw_netstats_tx_add(ndev, 1, *len);
-		ret = AM65_CPSW_XDP_CONSUMED;
-		goto out;
+		dev_sw_netstats_rx_add(ndev, pkt_len);
+		return AM65_CPSW_XDP_TX;
 	case XDP_REDIRECT:
 		if (unlikely(xdp_do_redirect(ndev, xdp, prog)))
 			goto drop;
 
-		dev_sw_netstats_rx_add(ndev, *len);
-		ret = AM65_CPSW_XDP_REDIRECT;
-		goto out;
+		dev_sw_netstats_rx_add(ndev, pkt_len);
+		return AM65_CPSW_XDP_REDIRECT;
 	default:
 		bpf_warn_invalid_xdp_action(ndev, prog, act);
 		fallthrough;
@@ -1184,10 +1231,6 @@ drop:
 		ndev->stats.rx_dropped++;
 	}
 
-	page = virt_to_head_page(xdp->data);
-	am65_cpsw_put_page(flow, page, true);
-
-out:
 	return ret;
 }
 
@@ -1225,7 +1268,7 @@ static void am65_cpsw_nuss_rx_csum(struct sk_buff *skb, u32 csum_info)
 }
 
 static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
-				     int cpu, int *xdp_state)
+				     int *xdp_state)
 {
 	struct am65_cpsw_rx_chn *rx_chn = &flow->common->rx_chns;
 	u32 buf_dma_len, pkt_len, port_id = 0, csum_info;
@@ -1279,28 +1322,32 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 	dev_dbg(dev, "%s rx csum_info:%#x\n", __func__, csum_info);
 
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
-
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	skb = am65_cpsw_build_skb(page_addr, ndev,
-				  AM65_CPSW_MAX_PACKET_SIZE);
-	if (unlikely(!skb)) {
-		new_page = page;
-		goto requeue;
-	}
-
 	if (port->xdp_prog) {
 		xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq[flow->id]);
 		xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM,
 				 pkt_len, false);
-		*xdp_state = am65_cpsw_run_xdp(flow, port, &xdp,
-					       cpu, &pkt_len);
+		*xdp_state = am65_cpsw_run_xdp(flow, port, &xdp, &pkt_len);
+		if (*xdp_state == AM65_CPSW_XDP_CONSUMED) {
+			page = virt_to_head_page(xdp.data);
+			am65_cpsw_put_page(flow, page, true);
+			goto allocate;
+		}
+
 		if (*xdp_state != AM65_CPSW_XDP_PASS)
 			goto allocate;
 
-		/* Compute additional headroom to be reserved */
-		headroom = (xdp.data - xdp.data_hard_start) - skb_headroom(skb);
-		skb_reserve(skb, headroom);
+		headroom = xdp.data - xdp.data_hard_start;
+	} else {
+		headroom = AM65_CPSW_HEADROOM;
+	}
+
+	skb = am65_cpsw_build_skb(page_addr, ndev,
+				  AM65_CPSW_MAX_PACKET_SIZE, headroom);
+	if (unlikely(!skb)) {
+		new_page = page;
+		goto requeue;
 	}
 
 	ndev_priv = netdev_priv(ndev);
@@ -1353,7 +1400,6 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 {
 	struct am65_cpsw_rx_flow *flow = am65_cpsw_napi_to_rx_flow(napi_rx);
 	struct am65_cpsw_common *common = flow->common;
-	int cpu = smp_processor_id();
 	int xdp_state_or = 0;
 	int cur_budget, ret;
 	int xdp_state;
@@ -1362,7 +1408,7 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 	/* process only this flow */
 	cur_budget = budget;
 	while (cur_budget--) {
-		ret = am65_cpsw_nuss_rx_packets(flow, cpu, &xdp_state);
+		ret = am65_cpsw_nuss_rx_packets(flow, &xdp_state);
 		xdp_state_or |= xdp_state;
 		if (ret)
 			break;
@@ -1390,52 +1436,6 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 	return num_rx;
 }
 
-static struct sk_buff *
-am65_cpsw_nuss_tx_compl_packet_skb(struct am65_cpsw_tx_chn *tx_chn,
-				   dma_addr_t desc_dma)
-{
-	struct cppi5_host_desc_t *desc_tx;
-	struct sk_buff *skb;
-	void **swdata;
-
-	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
-					     desc_dma);
-	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
-
-	am65_cpts_tx_timestamp(tx_chn->common->cpts, skb);
-
-	dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
-
-	return skb;
-}
-
-static struct xdp_frame *
-am65_cpsw_nuss_tx_compl_packet_xdp(struct am65_cpsw_common *common,
-				   struct am65_cpsw_tx_chn *tx_chn,
-				   dma_addr_t desc_dma,
-				   struct net_device **ndev)
-{
-	struct cppi5_host_desc_t *desc_tx;
-	struct am65_cpsw_port *port;
-	struct xdp_frame *xdpf;
-	u32 port_id = 0;
-	void **swdata;
-
-	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
-	cppi5_desc_get_tags_ids(&desc_tx->hdr, NULL, &port_id);
-	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	xdpf = *(swdata);
-	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
-
-	port = am65_common_get_port(common, port_id);
-	dev_sw_netstats_tx_add(port->ndev, 1, xdpf->len);
-	*ndev = port->ndev;
-
-	return xdpf;
-}
-
 static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_device *ndev,
 				   struct netdev_queue *netif_txq)
 {
@@ -1456,13 +1456,17 @@ static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_d
 static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 					   int chn, unsigned int budget, bool *tdown)
 {
+	bool single_port = AM65_CPSW_IS_CPSW2G(common);
 	enum am65_cpsw_tx_buf_type buf_type;
+	struct am65_cpsw_tx_swdata *swdata;
+	struct cppi5_host_desc_t *desc_tx;
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
 	unsigned int total_bytes = 0;
 	struct net_device *ndev;
 	struct xdp_frame *xdpf;
+	unsigned int pkt_len;
 	struct sk_buff *skb;
 	dma_addr_t desc_dma;
 	int res, num_tx = 0;
@@ -1470,9 +1474,12 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 	tx_chn = &common->tx_chns[chn];
 
 	while (true) {
-		spin_lock(&tx_chn->lock);
+		if (!single_port)
+			spin_lock(&tx_chn->lock);
 		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
-		spin_unlock(&tx_chn->lock);
+		if (!single_port)
+			spin_unlock(&tx_chn->lock);
+
 		if (res == -ENODATA)
 			break;
 
@@ -1483,27 +1490,43 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 			break;
 		}
 
+		desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+						     desc_dma);
+		swdata = cppi5_hdesc_get_swdata(desc_tx);
+		ndev = swdata->ndev;
 		buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
 		if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
-			skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma);
-			ndev = skb->dev;
-			total_bytes = skb->len;
+			skb = swdata->skb;
+			am65_cpts_tx_timestamp(tx_chn->common->cpts, skb);
+			pkt_len = skb->len;
 			napi_consume_skb(skb, budget);
 		} else {
-			xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn,
-								  desc_dma, &ndev);
-			total_bytes = xdpf->len;
+			xdpf = swdata->xdpf;
+			pkt_len = xdpf->len;
 			if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX)
 				xdp_return_frame_rx_napi(xdpf);
 			else
 				xdp_return_frame(xdpf);
 		}
+
+		total_bytes += pkt_len;
 		num_tx++;
+		am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
+		dev_sw_netstats_tx_add(ndev, 1, pkt_len);
+		if (!single_port) {
+			/* as packets from multi ports can be interleaved
+			 * on the same channel, we have to figure out the
+			 * port/queue at every packet and report it/wake queue.
+			 */
+			netif_txq = netdev_get_tx_queue(ndev, chn);
+			netdev_tx_completed_queue(netif_txq, 1, pkt_len);
+			am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
+		}
+	}
 
+	if (single_port) {
 		netif_txq = netdev_get_tx_queue(ndev, chn);
-
 		netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
-
 		am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
 	}
 
@@ -1512,66 +1535,6 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 	return num_tx;
 }
 
-static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
-					      int chn, unsigned int budget, bool *tdown)
-{
-	enum am65_cpsw_tx_buf_type buf_type;
-	struct device *dev = common->dev;
-	struct am65_cpsw_tx_chn *tx_chn;
-	struct netdev_queue *netif_txq;
-	unsigned int total_bytes = 0;
-	struct net_device *ndev;
-	struct xdp_frame *xdpf;
-	struct sk_buff *skb;
-	dma_addr_t desc_dma;
-	int res, num_tx = 0;
-
-	tx_chn = &common->tx_chns[chn];
-
-	while (true) {
-		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
-		if (res == -ENODATA)
-			break;
-
-		if (cppi5_desc_is_tdcm(desc_dma)) {
-			if (atomic_dec_and_test(&common->tdown_cnt))
-				complete(&common->tdown_complete);
-			*tdown = true;
-			break;
-		}
-
-		buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
-		if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
-			skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma);
-			ndev = skb->dev;
-			total_bytes += skb->len;
-			napi_consume_skb(skb, budget);
-		} else {
-			xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn,
-								  desc_dma, &ndev);
-			total_bytes += xdpf->len;
-			if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX)
-				xdp_return_frame_rx_napi(xdpf);
-			else
-				xdp_return_frame(xdpf);
-		}
-		num_tx++;
-	}
-
-	if (!num_tx)
-		return 0;
-
-	netif_txq = netdev_get_tx_queue(ndev, chn);
-
-	netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
-
-	am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
-
-	dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx);
-
-	return num_tx;
-}
-
 static enum hrtimer_restart am65_cpsw_nuss_tx_timer_callback(struct hrtimer *timer)
 {
 	struct am65_cpsw_tx_chn *tx_chns =
@@ -1587,13 +1550,8 @@ static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget)
 	bool tdown = false;
 	int num_tx;
 
-	if (AM65_CPSW_IS_CPSW2G(tx_chn->common))
-		num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id,
-							    budget, &tdown);
-	else
-		num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common,
-							 tx_chn->id, budget, &tdown);
-
+	num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common,
+						 tx_chn->id, budget, &tdown);
 	if (num_tx >= budget)
 		return budget;
 
@@ -1637,12 +1595,12 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
 	struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc;
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_tx_swdata *swdata;
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
 	dma_addr_t desc_dma, buf_dma;
 	int ret, q_idx, i;
-	void **swdata;
 	u32 *psdata;
 	u32 pkt_len;
 
@@ -1688,7 +1646,8 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
-	*(swdata) = skb;
+	swdata->ndev = ndev;
+	swdata->skb = skb;
 	psdata = cppi5_hdesc_get_psdata(first_desc);
 
 	/* HW csum offload if enabled */
@@ -2242,13 +2201,11 @@ static void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common)
 	struct device *dev = common->dev;
 	int i;
 
-	devm_remove_action(dev, am65_cpsw_nuss_free_tx_chns, common);
-
 	common->tx_ch_rate_msk = 0;
 	for (i = 0; i < common->tx_ch_num; i++) {
 		struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
 
-		if (tx_chn->irq)
+		if (tx_chn->irq > 0)
 			devm_free_irq(dev, tx_chn->irq, tx_chn);
 
 		netif_napi_del(&tx_chn->napi_tx);
@@ -2260,15 +2217,17 @@ static void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common)
 static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 {
 	struct device *dev = common->dev;
+	struct am65_cpsw_tx_chn *tx_chn;
 	int i, ret = 0;
 
 	for (i = 0; i < common->tx_ch_num; i++) {
-		struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
+		tx_chn = &common->tx_chns[i];
+
+		hrtimer_setup(&tx_chn->tx_hrtimer, &am65_cpsw_nuss_tx_timer_callback,
+			      CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 
 		netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx,
 				  am65_cpsw_nuss_tx_poll);
-		hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-		tx_chn->tx_hrtimer.function = &am65_cpsw_nuss_tx_timer_callback;
 
 		ret = devm_request_irq(dev, tx_chn->irq,
 				       am65_cpsw_nuss_tx_irq,
@@ -2281,7 +2240,16 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 		}
 	}
 
+	return 0;
+
 err:
+	netif_napi_del(&tx_chn->napi_tx);
+	for (--i; i >= 0; i--) {
+		tx_chn = &common->tx_chns[i];
+		devm_free_irq(dev, tx_chn->irq, tx_chn);
+		netif_napi_del(&tx_chn->napi_tx);
+	}
+
 	return ret;
 }
 
@@ -2362,12 +2330,10 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common)
 		goto err;
 	}
 
+	return 0;
+
 err:
-	i = devm_add_action(dev, am65_cpsw_nuss_free_tx_chns, common);
-	if (i) {
-		dev_err(dev, "Failed to add free_tx_chns action %d\n", i);
-		return i;
-	}
+	am65_cpsw_nuss_free_tx_chns(common);
 
 	return ret;
 }
@@ -2395,7 +2361,6 @@ static void am65_cpsw_nuss_remove_rx_chns(struct am65_cpsw_common *common)
 
 	rx_chn = &common->rx_chns;
 	flows = rx_chn->flows;
-	devm_remove_action(dev, am65_cpsw_nuss_free_rx_chns, common);
 
 	for (i = 0; i < common->rx_ch_num_flows; i++) {
 		if (!(flows[i].irq < 0))
@@ -2494,7 +2459,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 						i, &rx_flow_cfg);
 		if (ret) {
 			dev_err(dev, "Failed to init rx flow%d %d\n", i, ret);
-			goto err;
+			goto err_flow;
 		}
 		if (!i)
 			fdqring_id =
@@ -2506,17 +2471,17 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 			dev_err(dev, "Failed to get rx dma irq %d\n",
 				flow->irq);
 			ret = flow->irq;
-			goto err;
+			goto err_flow;
 		}
 
 		snprintf(flow->name,
 			 sizeof(flow->name), "%s-rx%d",
 			 dev_name(dev), i);
+		hrtimer_setup(&flow->rx_hrtimer, &am65_cpsw_nuss_rx_timer_callback, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_PINNED);
+
 		netif_napi_add(common->dma_ndev, &flow->napi_rx,
 			       am65_cpsw_nuss_rx_poll);
-		hrtimer_init(&flow->rx_hrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_PINNED);
-		flow->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback;
 
 		ret = devm_request_irq(dev, flow->irq,
 				       am65_cpsw_nuss_rx_irq,
@@ -2526,20 +2491,28 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 			dev_err(dev, "failure requesting rx %d irq %u, %d\n",
 				i, flow->irq, ret);
 			flow->irq = -EINVAL;
-			goto err;
+			goto err_request_irq;
 		}
 	}
 
 	/* setup classifier to route priorities to flows */
 	cpsw_ale_classifier_setup_default(common->ale, common->rx_ch_num_flows);
 
-err:
-	i = devm_add_action(dev, am65_cpsw_nuss_free_rx_chns, common);
-	if (i) {
-		dev_err(dev, "Failed to add free_rx_chns action %d\n", i);
-		return i;
+	return 0;
+
+err_request_irq:
+	netif_napi_del(&flow->napi_rx);
+
+err_flow:
+	for (--i; i >= 0; i--) {
+		flow = &rx_chn->flows[i];
+		devm_free_irq(dev, flow->irq, flow);
+		netif_napi_del(&flow->napi_rx);
 	}
 
+err:
+	am65_cpsw_nuss_free_rx_chns(common);
+
 	return ret;
 }
 
@@ -2559,20 +2532,15 @@ static int am65_cpsw_am654_get_efuse_macid(struct device_node *of_node,
 {
 	u32 mac_lo, mac_hi, offset;
 	struct regmap *syscon;
-	int ret;
 
-	syscon = syscon_regmap_lookup_by_phandle(of_node, "ti,syscon-efuse");
+	syscon = syscon_regmap_lookup_by_phandle_args(of_node, "ti,syscon-efuse",
+						      1, &offset);
 	if (IS_ERR(syscon)) {
 		if (PTR_ERR(syscon) == -ENODEV)
 			return 0;
 		return PTR_ERR(syscon);
 	}
 
-	ret = of_property_read_u32_index(of_node, "ti,syscon-efuse", 1,
-					 &offset);
-	if (ret)
-		return ret;
-
 	regmap_read(syscon, offset, &mac_lo);
 	regmap_read(syscon, offset + 4, &mac_hi);
 
@@ -2698,7 +2666,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 				of_property_read_bool(port_np, "ti,mac-only");
 
 		/* get phy/link info */
-		port->slave.port_np = port_np;
+		port->slave.port_np = of_node_get(port_np);
 		ret = of_get_phy_mode(port_np, &port->slave.phy_if);
 		if (ret) {
 			dev_err(dev, "%pOF read phy-mode err %d\n",
@@ -2711,13 +2679,15 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 			goto of_node_put;
 
 		ret = of_get_mac_address(port_np, port->slave.mac_addr);
-		if (ret) {
+		if (ret == -EPROBE_DEFER) {
+			goto of_node_put;
+		} else if (ret) {
 			am65_cpsw_am654_get_efuse_macid(port_np,
 							port->port_id,
 							port->slave.mac_addr);
 			if (!is_valid_ether_addr(port->slave.mac_addr)) {
 				eth_random_addr(port->slave.mac_addr);
-				dev_err(dev, "Use random MAC address\n");
+				dev_info(dev, "Use random MAC address\n");
 			}
 		}
 
@@ -2752,6 +2722,17 @@ static void am65_cpsw_nuss_phylink_cleanup(struct am65_cpsw_common *common)
 	}
 }
 
+static void am65_cpsw_remove_dt(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_port *port;
+	int i;
+
+	for (i = 0; i < common->port_num; i++) {
+		port = &common->ports[i];
+		of_node_put(port->slave.port_np);
+	}
+}
+
 static int
 am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 {
@@ -2781,7 +2762,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	mutex_init(&ndev_priv->mm_lock);
 	port->qos.link_speed = SPEED_UNKNOWN;
 	SET_NETDEV_DEV(port->ndev, dev);
-	port->ndev->dev.of_node = port->slave.port_np;
+	device_set_node(&port->ndev->dev, of_fwnode_handle(port->slave.port_np));
 
 	eth_hw_addr_set(port->ndev, port->slave.mac_addr);
 
@@ -3349,7 +3330,7 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 		return ret;
 	ret = am65_cpsw_nuss_init_rx_chns(common);
 	if (ret)
-		return ret;
+		goto err_remove_tx;
 
 	/* The DMA Channels are not guaranteed to be in a clean state.
 	 * Reset and disable them to ensure that they are back to the
@@ -3364,13 +3345,13 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 	for (i = 0; i < common->rx_ch_num_flows; i++)
 		k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i,
 					  rx_chan,
-					  am65_cpsw_nuss_rx_cleanup, !!i);
+					  am65_cpsw_nuss_rx_cleanup);
 
 	k3_udma_glue_disable_rx_chn(rx_chan->rx_chn);
 
 	ret = am65_cpsw_nuss_register_devlink(common);
 	if (ret)
-		return ret;
+		goto err_remove_rx;
 
 	for (i = 0; i < common->port_num; i++) {
 		port = &common->ports[i];
@@ -3401,6 +3382,10 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 err_cleanup_ndev:
 	am65_cpsw_nuss_cleanup_ndev(common);
 	am65_cpsw_unregister_devlink(common);
+err_remove_rx:
+	am65_cpsw_nuss_remove_rx_chns(common);
+err_remove_tx:
+	am65_cpsw_nuss_remove_tx_chns(common);
 
 	return ret;
 }
@@ -3420,6 +3405,8 @@ int am65_cpsw_nuss_update_tx_rx_chns(struct am65_cpsw_common *common,
 		return ret;
 
 	ret = am65_cpsw_nuss_init_rx_chns(common);
+	if (ret)
+		am65_cpsw_nuss_remove_tx_chns(common);
 
 	return ret;
 }
@@ -3518,6 +3505,10 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	__be64 id_temp;
 	int ret, i;
 
+	BUILD_BUG_ON_MSG(sizeof(struct am65_cpsw_tx_swdata) > AM65_CPSW_NAV_SW_DATA_SIZE,
+			 "TX SW_DATA size exceeds AM65_CPSW_NAV_SW_DATA_SIZE");
+	BUILD_BUG_ON_MSG(sizeof(struct am65_cpsw_swdata) > AM65_CPSW_NAV_SW_DATA_SIZE,
+			 "SW_DATA size exceeds AM65_CPSW_NAV_SW_DATA_SIZE");
 	common = devm_kzalloc(dev, sizeof(struct am65_cpsw_common), GFP_KERNEL);
 	if (!common)
 		return -ENOMEM;
@@ -3551,7 +3542,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	init_completion(&common->tdown_complete);
 	common->tx_ch_num = AM65_CPSW_DEFAULT_TX_CHNS;
 	common->rx_ch_num_flows = AM65_CPSW_DEFAULT_RX_CHN_FLOWS;
-	common->pf_p0_rx_ptype_rrobin = false;
+	common->pf_p0_rx_ptype_rrobin = true;
 	common->default_vlan = 1;
 
 	common->ports = devm_kcalloc(dev, common->port_num,
@@ -3572,6 +3563,16 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	am65_cpsw_nuss_get_ver(common);
+
+	ret = am65_cpsw_nuss_init_host_p(common);
+	if (ret)
+		goto err_pm_clear;
+
+	ret = am65_cpsw_nuss_init_slave_ports(common);
+	if (ret)
+		goto err_pm_clear;
+
 	node = of_get_child_by_name(dev->of_node, "mdio");
 	if (!node) {
 		dev_warn(dev, "MDIO node not found\n");
@@ -3588,16 +3589,6 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	}
 	of_node_put(node);
 
-	am65_cpsw_nuss_get_ver(common);
-
-	ret = am65_cpsw_nuss_init_host_p(common);
-	if (ret)
-		goto err_of_clear;
-
-	ret = am65_cpsw_nuss_init_slave_ports(common);
-	if (ret)
-		goto err_of_clear;
-
 	/* init common data */
 	ale_params.dev = dev;
 	ale_params.ale_ageout = AM65_CPSW_ALE_AGEOUT_DEFAULT;
@@ -3644,6 +3635,7 @@ err_ndevs_clear:
 	am65_cpsw_nuss_cleanup_ndev(common);
 	am65_cpsw_nuss_phylink_cleanup(common);
 	am65_cpts_release(common->cpts);
+	am65_cpsw_remove_dt(common);
 err_of_clear:
 	if (common->mdio_dev)
 		of_platform_device_destroy(common->mdio_dev, NULL);
@@ -3678,9 +3670,12 @@ static void am65_cpsw_nuss_remove(struct platform_device *pdev)
 	 */
 	am65_cpsw_nuss_cleanup_ndev(common);
 	am65_cpsw_unregister_devlink(common);
+	am65_cpsw_nuss_remove_rx_chns(common);
+	am65_cpsw_nuss_remove_tx_chns(common);
 	am65_cpsw_nuss_phylink_cleanup(common);
 	am65_cpts_release(common->cpts);
 	am65_cpsw_disable_serdes_phy(common);
+	am65_cpsw_remove_dt(common);
 
 	if (common->mdio_dev)
 		of_platform_device_destroy(common->mdio_dev, NULL);
@@ -3739,8 +3734,10 @@ static int am65_cpsw_nuss_resume(struct device *dev)
 	if (ret)
 		return ret;
 	ret = am65_cpsw_nuss_init_rx_chns(common);
-	if (ret)
+	if (ret) {
+		am65_cpsw_nuss_remove_tx_chns(common);
 		return ret;
+	}
 
 	/* If RX IRQ was disabled before suspend, keep it disabled */
 	for (i = 0; i < common->rx_ch_num_flows; i++) {
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index e7832a5cf3cc..917c37e4e89b 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -104,6 +104,14 @@ struct am65_cpsw_rx_flow {
 	char name[32];
 };
 
+struct am65_cpsw_tx_swdata {
+	struct net_device *ndev;
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdpf;
+	};
+};
+
 struct am65_cpsw_swdata {
 	u32 flow_id;
 	struct page *page;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 4ef8cf6ea135..54c24cd3d3be 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -351,6 +351,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	int			ret = 0, port, ch = xmeta->ch;
 	int			headroom = CPSW_HEADROOM_NA;
 	struct net_device	*ndev = xmeta->ndev;
+	u32			metasize = 0;
 	struct cpsw_priv	*priv;
 	struct page_pool	*pool;
 	struct sk_buff		*skb;
@@ -400,7 +401,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 			size -= CPSW_RX_VLAN_ENCAP_HDR_SIZE;
 		}
 
-		xdp_prepare_buff(&xdp, pa, headroom, size, false);
+		xdp_prepare_buff(&xdp, pa, headroom, size, true);
 
 		port = priv->emac_port + cpsw->data.dual_emac;
 		ret = cpsw_run_xdp(priv, ch, &xdp, page, port, &len);
@@ -408,6 +409,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 			goto requeue;
 
 		headroom = xdp.data - xdp.data_hard_start;
+		metasize = xdp.data - xdp.data_meta;
 
 		/* XDP prog can modify vlan tag, so can't use encap header */
 		status &= ~CPDMA_RX_VLAN_ENCAP;
@@ -423,6 +425,8 @@ static void cpsw_rx_handler(void *token, int len, int status)
 
 	skb_reserve(skb, headroom);
 	skb_put(skb, len);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb->dev = ndev;
 	if (status & CPDMA_RX_VLAN_ENCAP)
 		cpsw_rx_vlan_encap(skb);
@@ -635,6 +639,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 
 	slave->phy = phy;
 
+	phy_disable_eee(slave->phy);
+
 	phy_attached_info(slave->phy);
 
 	phy_start(slave->phy);
@@ -684,7 +690,7 @@ static void cpsw_init_host_port(struct cpsw_priv *priv)
 	soft_reset("cpsw", &cpsw->regs->soft_reset);
 	cpsw_ale_start(cpsw->ale);
 
-	/* switch to vlan unaware mode */
+	/* switch to vlan aware mode */
 	cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_VLAN_AWARE,
 			     CPSW_ALE_VLAN_AWARE);
 	control_reg = readl(&cpsw->regs->control);
@@ -1150,6 +1156,27 @@ static void cpsw_ndo_poll_controller(struct net_device *ndev)
 }
 #endif
 
+/* We need a custom implementation of phy_do_ioctl_running() because in switch
+ * mode, dev->phydev may be different than the phy of the active_slave. We need
+ * to operate on the locally saved phy instead.
+ */
+static int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
+{
+	struct cpsw_priv *priv = netdev_priv(dev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+	struct phy_device *phy;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	phy = cpsw->slaves[slave_no].phy;
+	if (phy)
+		return phy_mii_ioctl(phy, req, cmd);
+
+	return -EOPNOTSUPP;
+}
+
 static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_open		= cpsw_ndo_open,
 	.ndo_stop		= cpsw_ndo_stop,
@@ -1168,6 +1195,8 @@ static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_setup_tc           = cpsw_ndo_setup_tc,
 	.ndo_bpf		= cpsw_ndo_bpf,
 	.ndo_xdp_xmit		= cpsw_ndo_xdp_xmit,
+	.ndo_hwtstamp_get	= cpsw_hwtstamp_get,
+	.ndo_hwtstamp_set	= cpsw_hwtstamp_set,
 };
 
 static void cpsw_get_drvinfo(struct net_device *ndev,
@@ -1225,7 +1254,6 @@ static const struct ethtool_ops cpsw_ethtool_ops = {
 	.get_link_ksettings	= cpsw_get_link_ksettings,
 	.set_link_ksettings	= cpsw_set_link_ksettings,
 	.get_eee	= cpsw_get_eee,
-	.set_eee	= cpsw_set_eee,
 	.nway_reset	= cpsw_nway_reset,
 	.get_ringparam = cpsw_get_ringparam,
 	.set_ringparam = cpsw_set_ringparam,
@@ -1641,6 +1669,9 @@ static int cpsw_probe(struct platform_device *pdev)
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
 	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			     NETDEV_XDP_ACT_NDO_XMIT;
+	/* Hijack PHY timestamping requests in order to block them */
+	if (!cpsw->data.dual_emac)
+		ndev->see_all_hwtstamp_requests = true;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
 	ndev->ethtool_ops = &cpsw_ethtool_ops;
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 52e4e350b734..fbe35af615a6 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -127,15 +127,15 @@ struct cpsw_ale_dev_id {
 
 static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits)
 {
-	int idx, idx2;
+	int idx, idx2, index;
 	u32 hi_val = 0;
 
 	idx    = start / 32;
 	idx2 = (start + bits - 1) / 32;
 	/* Check if bits to be fetched exceed a word */
 	if (idx != idx2) {
-		idx2 = 2 - idx2; /* flip */
-		hi_val = ale_entry[idx2] << ((idx2 * 32) - start);
+		index = 2 - idx2; /* flip */
+		hi_val = ale_entry[index] << ((idx2 * 32) - start);
 	}
 	start -= idx * 32;
 	idx    = 2 - idx; /* flip */
@@ -145,16 +145,16 @@ static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits)
 static inline void cpsw_ale_set_field(u32 *ale_entry, u32 start, u32 bits,
 				      u32 value)
 {
-	int idx, idx2;
+	int idx, idx2, index;
 
 	value &= BITMASK(bits);
 	idx = start / 32;
 	idx2 = (start + bits - 1) / 32;
 	/* Check if bits to be set exceed a word */
 	if (idx != idx2) {
-		idx2 = 2 - idx2; /* flip */
-		ale_entry[idx2] &= ~(BITMASK(bits + start - (idx2 * 32)));
-		ale_entry[idx2] |= (value >> ((idx2 * 32) - start));
+		index = 2 - idx2; /* flip */
+		ale_entry[index] &= ~(BITMASK(bits + start - (idx2 * 32)));
+		ale_entry[index] |= (value >> ((idx2 * 32) - start));
 	}
 	start -= idx * 32;
 	idx = 2 - idx; /* flip */
@@ -1231,7 +1231,7 @@ int cpsw_ale_rx_ratelimit_bc(struct cpsw_ale *ale, int port, unsigned int rateli
 
 static void cpsw_ale_timer(struct timer_list *t)
 {
-	struct cpsw_ale *ale = from_timer(ale, t, timer);
+	struct cpsw_ale *ale = timer_container_of(ale, t, timer);
 
 	cpsw_ale_control_set(ale, 0, ALE_AGEOUT, 1);
 
@@ -1287,7 +1287,7 @@ static void cpsw_ale_aging_stop(struct cpsw_ale *ale)
 		return;
 	}
 
-	del_timer_sync(&ale->timer);
+	timer_delete_sync(&ale->timer);
 }
 
 void cpsw_ale_start(struct cpsw_ale *ale)
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index 21d55a180ef6..bdc4db0d169c 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -434,18 +434,6 @@ int cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata)
 		return -EOPNOTSUPP;
 }
 
-int cpsw_set_eee(struct net_device *ndev, struct ethtool_keee *edata)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
-
-	if (cpsw->slaves[slave_no].phy)
-		return phy_ethtool_set_eee(cpsw->slaves[slave_no].phy, edata);
-	else
-		return -EOPNOTSUPP;
-}
-
 int cpsw_nway_reset(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index a98bcc5eb566..8b9e2078c602 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -293,6 +293,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	struct page_pool *pool;
 	struct sk_buff *skb;
 	struct xdp_buff xdp;
+	u32 metasize = 0;
 	int ret = 0;
 	dma_addr_t dma;
 
@@ -345,13 +346,14 @@ static void cpsw_rx_handler(void *token, int len, int status)
 			size -= CPSW_RX_VLAN_ENCAP_HDR_SIZE;
 		}
 
-		xdp_prepare_buff(&xdp, pa, headroom, size, false);
+		xdp_prepare_buff(&xdp, pa, headroom, size, true);
 
 		ret = cpsw_run_xdp(priv, ch, &xdp, page, priv->emac_port, &len);
 		if (ret != CPSW_XDP_PASS)
 			goto requeue;
 
 		headroom = xdp.data - xdp.data_hard_start;
+		metasize = xdp.data - xdp.data_meta;
 
 		/* XDP prog can modify vlan tag, so can't use encap header */
 		status &= ~CPDMA_RX_VLAN_ENCAP;
@@ -368,6 +370,8 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	skb->offload_fwd_mark = priv->offload_fwd_mark;
 	skb_reserve(skb, headroom);
 	skb_put(skb, len);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb->dev = ndev;
 	if (status & CPDMA_RX_VLAN_ENCAP)
 		cpsw_rx_vlan_encap(skb);
@@ -554,7 +558,7 @@ static void cpsw_init_host_port(struct cpsw_priv *priv)
 	soft_reset("cpsw", &cpsw->regs->soft_reset);
 	cpsw_ale_start(cpsw->ale);
 
-	/* switch to vlan unaware mode */
+	/* switch to vlan aware mode */
 	cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_VLAN_AWARE,
 			     CPSW_ALE_VLAN_AWARE);
 	control_reg = readl(&cpsw->regs->control);
@@ -778,6 +782,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 
 	slave->phy = phy;
 
+	phy_disable_eee(slave->phy);
+
 	phy_attached_info(slave->phy);
 
 	phy_start(slave->phy);
@@ -1126,7 +1132,7 @@ static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_stop		= cpsw_ndo_stop,
 	.ndo_start_xmit		= cpsw_ndo_start_xmit,
 	.ndo_set_mac_address	= cpsw_ndo_set_mac_address,
-	.ndo_eth_ioctl		= cpsw_ndo_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= cpsw_ndo_tx_timeout,
 	.ndo_set_rx_mode	= cpsw_ndo_set_rx_mode,
@@ -1141,6 +1147,8 @@ static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_bpf		= cpsw_ndo_bpf,
 	.ndo_xdp_xmit		= cpsw_ndo_xdp_xmit,
 	.ndo_get_port_parent_id	= cpsw_get_port_parent_id,
+	.ndo_hwtstamp_get	= cpsw_hwtstamp_get,
+	.ndo_hwtstamp_set	= cpsw_hwtstamp_set,
 };
 
 static void cpsw_get_drvinfo(struct net_device *ndev,
@@ -1209,7 +1217,6 @@ static const struct ethtool_ops cpsw_ethtool_ops = {
 	.get_link_ksettings	= cpsw_get_link_ksettings,
 	.set_link_ksettings	= cpsw_set_link_ksettings,
 	.get_eee		= cpsw_get_eee,
-	.set_eee		= cpsw_set_eee,
 	.nway_reset		= cpsw_nway_reset,
 	.get_ringparam		= cpsw_get_ringparam,
 	.set_ringparam		= cpsw_set_ringparam,
@@ -1408,7 +1415,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 
 		ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
 				  NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_TC;
-		ndev->netns_local = true;
+		ndev->netns_immutable = true;
 
 		ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
 				     NETDEV_XDP_ACT_REDIRECT |
@@ -1417,6 +1424,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 		ndev->netdev_ops = &cpsw_netdev_ops;
 		ndev->ethtool_ops = &cpsw_ethtool_ops;
 		SET_NETDEV_DEV(ndev, dev);
+		ndev->dev.of_node = slave_data->slave_node;
 
 		if (!napi_ndev) {
 			/* CPSW Host port CPDMA interface is shared between
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 6fe4edabba44..bc4fdf17a99e 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -614,24 +614,29 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 	writel_relaxed(ETH_P_8021Q, &cpsw->regs->vlan_ltype);
 }
 
-static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+int cpsw_hwtstamp_set(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg,
+		      struct netlink_ext_ack *extack)
 {
 	struct cpsw_priv *priv = netdev_priv(dev);
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct hwtstamp_config cfg;
+
+	/* This will only execute if dev->see_all_hwtstamp_requests is set */
+	if (cfg->source != HWTSTAMP_SOURCE_NETDEV) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Switch mode only supports MAC timestamping");
+		return -EOPNOTSUPP;
+	}
 
 	if (cpsw->version != CPSW_VERSION_1 &&
 	    cpsw->version != CPSW_VERSION_2 &&
 	    cpsw->version != CPSW_VERSION_3)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON)
+	if (cfg->tx_type != HWTSTAMP_TX_OFF && cfg->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		priv->rx_ts_enabled = 0;
 		break;
@@ -651,13 +656,13 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V2_EVENT;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	priv->tx_ts_enabled = cfg.tx_type == HWTSTAMP_TX_ON;
+	priv->tx_ts_enabled = cfg->tx_type == HWTSTAMP_TX_ON;
 
 	switch (cpsw->version) {
 	case CPSW_VERSION_1:
@@ -671,65 +676,40 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 		WARN_ON(1);
 	}
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
-static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+int cpsw_hwtstamp_get(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(dev);
 	struct cpsw_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config cfg;
 
 	if (cpsw->version != CPSW_VERSION_1 &&
 	    cpsw->version != CPSW_VERSION_2 &&
 	    cpsw->version != CPSW_VERSION_3)
 		return -EOPNOTSUPP;
 
-	cfg.flags = 0;
-	cfg.tx_type = priv->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	cfg.rx_filter = priv->rx_ts_enabled;
+	cfg->tx_type = priv->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	cfg->rx_filter = priv->rx_ts_enabled;
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 #else
-static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+int cpsw_hwtstamp_get(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg)
 {
 	return -EOPNOTSUPP;
 }
 
-static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+int cpsw_hwtstamp_set(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg,
+		      struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
 #endif /*CONFIG_TI_CPTS*/
 
-int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
-{
-	struct cpsw_priv *priv = netdev_priv(dev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
-	struct phy_device *phy;
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	phy = cpsw->slaves[slave_no].phy;
-
-	if (!phy_has_hwtstamp(phy)) {
-		switch (cmd) {
-		case SIOCSHWTSTAMP:
-			return cpsw_hwtstamp_set(dev, req);
-		case SIOCGHWTSTAMP:
-			return cpsw_hwtstamp_get(dev, req);
-		}
-	}
-
-	if (phy)
-		return phy_mii_ioctl(phy, req, cmd);
-
-	return -EOPNOTSUPP;
-}
-
 int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 1f448290b9f4..91add8925e23 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -461,7 +461,6 @@ void soft_reset(const char *module, void __iomem *reg);
 void cpsw_set_slave_mac(struct cpsw_slave *slave, struct cpsw_priv *priv);
 void cpsw_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue);
 int cpsw_need_resplit(struct cpsw_common *cpsw);
-int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd);
 int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate);
 int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 		      void *type_data);
@@ -469,6 +468,11 @@ bool cpsw_shp_is_off(struct cpsw_priv *priv);
 void cpsw_cbs_resume(struct cpsw_slave *slave, struct cpsw_priv *priv);
 void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv);
 void cpsw_qos_clsflower_resume(struct cpsw_priv *priv);
+int cpsw_hwtstamp_get(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg);
+int cpsw_hwtstamp_set(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg,
+		      struct netlink_ext_ack *extack);
 
 /* ethtool */
 u32 cpsw_get_msglevel(struct net_device *ndev);
@@ -497,7 +501,6 @@ int cpsw_get_link_ksettings(struct net_device *ndev,
 int cpsw_set_link_ksettings(struct net_device *ndev,
 			    const struct ethtool_link_ksettings *ecmd);
 int cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata);
-int cpsw_set_eee(struct net_device *ndev, struct ethtool_keee *edata);
 int cpsw_nway_reset(struct net_device *ndev);
 void cpsw_get_ringparam(struct net_device *ndev,
 			struct ethtool_ringparam *ering,
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index 5d6d1cf78e93..2a1c43316f46 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -215,6 +215,9 @@ static void icss_iep_enable_shadow_mode(struct icss_iep *iep)
 	for (cmp = IEP_MIN_CMP; cmp < IEP_MAX_CMP; cmp++) {
 		regmap_update_bits(iep->map, ICSS_IEP_CMP_STAT_REG,
 				   IEP_CMP_STATUS(cmp), IEP_CMP_STATUS(cmp));
+
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(cmp), 0);
 	}
 
 	/* enable reset counter on CMP0 event */
@@ -403,66 +406,79 @@ static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns)
 static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 				     struct ptp_perout_request *req, int on)
 {
+	struct timespec64 ts;
+	u64 ns_start;
+	u64 ns_width;
 	int ret;
 	u64 cmp;
 
+	if (!on) {
+		/* Disable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), 0);
+
+		/* clear CMP regs */
+		regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
+		if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
+
+		/* Disable sync */
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
+
+		return 0;
+	}
+
+	/* Calculate width of the signal for PPS/PEROUT handling */
+	ts.tv_sec = req->on.sec;
+	ts.tv_nsec = req->on.nsec;
+	ns_width = timespec64_to_ns(&ts);
+
+	if (req->flags & PTP_PEROUT_PHASE) {
+		ts.tv_sec = req->phase.sec;
+		ts.tv_nsec = req->phase.nsec;
+		ns_start = timespec64_to_ns(&ts);
+	} else {
+		ns_start = 0;
+	}
+
 	if (iep->ops && iep->ops->perout_enable) {
 		ret = iep->ops->perout_enable(iep->clockops_data, req, on, &cmp);
 		if (ret)
 			return ret;
 
-		if (on) {
-			/* Configure CMP */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
-			/* Configure SYNC, 1ms pulse width */
-			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG, 1000000);
-			regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
-			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG, 0);
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
-			/* Enable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
-		} else {
-			/* Disable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), 0);
-
-			/* clear regs */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
-		}
+		/* Configure CMP */
+		regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
+		if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
+		/* Configure SYNC, based on req on width */
+		regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+			     div_u64(ns_width, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
+		regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+			     div_u64(ns_start, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
+		/* Enable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
 	} else {
-		if (on) {
-			u64 start_ns;
-
-			iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
-				      req->period.nsec;
-			start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
-				   + req->period.nsec;
-			icss_iep_update_to_next_boundary(iep, start_ns);
-
-			/* Enable Sync in single shot mode  */
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
-				     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
-			/* Enable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
-		} else {
-			/* Disable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), 0);
-
-			/* clear CMP regs */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
-
-			/* Disable sync */
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
-		}
+		u64 start_ns;
+
+		iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
+				req->period.nsec;
+		start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
+				+ req->period.nsec;
+		icss_iep_update_to_next_boundary(iep, start_ns);
+
+		regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+			     div_u64(ns_width, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+			     div_u64(ns_start, iep->def_inc));
+		/* Enable Sync in single shot mode  */
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
+			     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
+		/* Enable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
 	}
 
 	return 0;
@@ -473,6 +489,21 @@ static int icss_iep_perout_enable(struct icss_iep *iep,
 {
 	int ret = 0;
 
+	if (!on)
+		goto disable;
+
+	/* Reject requests with unsupported flags */
+	if (req->flags & ~(PTP_PEROUT_DUTY_CYCLE |
+			  PTP_PEROUT_PHASE))
+		return -EOPNOTSUPP;
+
+	/* Set default "on" time (1ms) for the signal if not passed by the app */
+	if (!(req->flags & PTP_PEROUT_DUTY_CYCLE)) {
+		req->on.sec = 0;
+		req->on.nsec = NSEC_PER_MSEC;
+	}
+
+disable:
 	mutex_lock(&iep->ptp_clk_mutex);
 
 	if (iep->pps_enabled) {
@@ -565,10 +596,13 @@ static int icss_iep_pps_enable(struct icss_iep *iep, int on)
 	if (on) {
 		ns = icss_iep_gettime(iep, NULL);
 		ts = ns_to_timespec64(ns);
+		rq.perout.flags = 0;
 		rq.perout.period.sec = 1;
 		rq.perout.period.nsec = 0;
 		rq.perout.start.sec = ts.tv_sec + 2;
 		rq.perout.start.nsec = 0;
+		rq.perout.on.sec = 0;
+		rq.perout.on.nsec = NSEC_PER_MSEC;
 		ret = icss_iep_perout_enable_hw(iep, &rq.perout, on);
 	} else {
 		ret = icss_iep_perout_enable_hw(iep, &rq.perout, on);
@@ -780,6 +814,11 @@ int icss_iep_exit(struct icss_iep *iep)
 	}
 	icss_iep_disable(iep);
 
+	if (iep->pps_enabled)
+		icss_iep_pps_enable(iep, false);
+	else if (iep->perout_enabled)
+		icss_iep_perout_enable(iep, NULL, false);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(icss_iep_exit);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index fdebeb2f84e0..12f25cec6255 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -45,6 +45,11 @@ void prueth_cleanup_rx_chns(struct prueth_emac *emac,
 			    struct prueth_rx_chn *rx_chn,
 			    int max_rflows)
 {
+	if (rx_chn->pg_pool) {
+		page_pool_destroy(rx_chn->pg_pool);
+		rx_chn->pg_pool = NULL;
+	}
+
 	if (rx_chn->desc_pool)
 		k3_cppi_desc_pool_destroy(rx_chn->desc_pool);
 
@@ -131,12 +136,13 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_tx;
 	struct netdev_queue *netif_txq;
+	struct prueth_swdata *swdata;
 	struct prueth_tx_chn *tx_chn;
 	unsigned int total_bytes = 0;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
 	dma_addr_t desc_dma;
 	int res, num_tx = 0;
-	void **swdata;
 
 	tx_chn = &emac->tx_chns[chn];
 
@@ -157,20 +163,26 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
 						     desc_dma);
 		swdata = cppi5_hdesc_get_swdata(desc_tx);
 
-		/* was this command's TX complete? */
-		if (emac->is_sr1 && *(swdata) == emac->cmd_data) {
+		switch (swdata->type) {
+		case PRUETH_SWDATA_SKB:
+			skb = swdata->data.skb;
+			dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
+			total_bytes += skb->len;
+			napi_consume_skb(skb, budget);
+			break;
+		case PRUETH_SWDATA_XDPF:
+			xdpf = swdata->data.xdpf;
+			dev_sw_netstats_tx_add(ndev, 1, xdpf->len);
+			total_bytes += xdpf->len;
+			xdp_return_frame(xdpf);
+			break;
+		default:
 			prueth_xmit_free(tx_chn, desc_tx);
+			ndev->stats.tx_dropped++;
 			continue;
 		}
 
-		skb = *(swdata);
 		prueth_xmit_free(tx_chn, desc_tx);
-
-		ndev = skb->dev;
-		ndev->stats.tx_packets++;
-		ndev->stats.tx_bytes += skb->len;
-		total_bytes += skb->len;
-		napi_consume_skb(skb, budget);
 		num_tx++;
 	}
 
@@ -249,9 +261,8 @@ int prueth_ndev_add_tx_napi(struct prueth_emac *emac)
 		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
 
 		netif_napi_add_tx(emac->ndev, &tx_chn->napi_tx, emac_napi_tx_poll);
-		hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC,
-			     HRTIMER_MODE_REL_PINNED);
-		tx_chn->tx_hrtimer.function = &emac_tx_timer_callback;
+		hrtimer_setup(&tx_chn->tx_hrtimer, &emac_tx_timer_callback, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL_PINNED);
 		ret = request_irq(tx_chn->irq, prueth_tx_irq,
 				  IRQF_TRIGGER_HIGH, tx_chn->name,
 				  tx_chn);
@@ -461,17 +472,17 @@ fail:
 }
 EXPORT_SYMBOL_GPL(prueth_init_rx_chns);
 
-int prueth_dma_rx_push(struct prueth_emac *emac,
-		       struct sk_buff *skb,
-		       struct prueth_rx_chn *rx_chn)
+int prueth_dma_rx_push_mapped(struct prueth_emac *emac,
+			      struct prueth_rx_chn *rx_chn,
+			      struct page *page, u32 buf_len)
 {
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
-	u32 pkt_len = skb_tailroom(skb);
+	struct prueth_swdata *swdata;
 	dma_addr_t desc_dma;
 	dma_addr_t buf_dma;
-	void **swdata;
 
+	buf_dma = page_pool_get_dma_addr(page) + PRUETH_HEADROOM;
 	desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool);
 	if (!desc_rx) {
 		netdev_err(ndev, "rx push: failed to allocate descriptor\n");
@@ -479,25 +490,19 @@ int prueth_dma_rx_push(struct prueth_emac *emac,
 	}
 	desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx);
 
-	buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) {
-		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-		netdev_err(ndev, "rx push: failed to map rx pkt buffer\n");
-		return -EINVAL;
-	}
-
 	cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
 			 PRUETH_NAV_PS_DATA_SIZE);
 	k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma);
-	cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
+	cppi5_hdesc_attach_buf(desc_rx, buf_dma, buf_len, buf_dma, buf_len);
 
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	*swdata = skb;
+	swdata->type = PRUETH_SWDATA_PAGE;
+	swdata->data.page = page;
 
-	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0,
+	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, PRUETH_RX_FLOW_DATA,
 					desc_rx, desc_dma);
 }
-EXPORT_SYMBOL_GPL(prueth_dma_rx_push);
+EXPORT_SYMBOL_GPL(prueth_dma_rx_push_mapped);
 
 u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns)
 {
@@ -535,18 +540,178 @@ void emac_rx_timestamp(struct prueth_emac *emac,
 	ssh->hwtstamp = ns_to_ktime(ns);
 }
 
-static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
+/**
+ * emac_xmit_xdp_frame - transmits an XDP frame
+ * @emac: emac device
+ * @xdpf: data to transmit
+ * @page: page from page pool if already DMA mapped
+ * @q_idx: queue id
+ *
+ * Return: XDP state
+ */
+u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
+			struct xdp_frame *xdpf,
+			struct page *page,
+			unsigned int q_idx)
+{
+	struct cppi5_host_desc_t *first_desc;
+	struct net_device *ndev = emac->ndev;
+	struct netdev_queue *netif_txq;
+	struct prueth_tx_chn *tx_chn;
+	dma_addr_t desc_dma, buf_dma;
+	struct prueth_swdata *swdata;
+	u32 *epib;
+	int ret;
+
+	if (q_idx >= PRUETH_MAX_TX_QUEUES) {
+		netdev_err(ndev, "xdp tx: invalid q_id %d\n", q_idx);
+		return ICSSG_XDP_CONSUMED;	/* drop */
+	}
+
+	tx_chn = &emac->tx_chns[q_idx];
+
+	first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+	if (!first_desc) {
+		netdev_dbg(ndev, "xdp tx: failed to allocate descriptor\n");
+		return ICSSG_XDP_CONSUMED;	/* drop */
+	}
+
+	if (page) { /* already DMA mapped by page_pool */
+		buf_dma = page_pool_get_dma_addr(page);
+		buf_dma += xdpf->headroom + sizeof(struct xdp_frame);
+	} else { /* Map the linear buffer */
+		buf_dma = dma_map_single(tx_chn->dma_dev, xdpf->data, xdpf->len, DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
+			netdev_err(ndev, "xdp tx: failed to map data buffer\n");
+			goto drop_free_descs;	/* drop */
+		}
+	}
+
+	cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT,
+			 PRUETH_NAV_PS_DATA_SIZE);
+	cppi5_hdesc_set_pkttype(first_desc, 0);
+	epib = first_desc->epib;
+	epib[0] = 0;
+	epib[1] = 0;
+
+	/* set dst tag to indicate internal qid at the firmware which is at
+	 * bit8..bit15. bit0..bit7 indicates port num for directed
+	 * packets in case of switch mode operation
+	 */
+	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8)));
+	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
+	cppi5_hdesc_attach_buf(first_desc, buf_dma, xdpf->len, buf_dma, xdpf->len);
+	swdata = cppi5_hdesc_get_swdata(first_desc);
+	swdata->type = PRUETH_SWDATA_XDPF;
+	swdata->data.xdpf = xdpf;
+
+	/* Report BQL before sending the packet */
+	netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
+	netdev_tx_sent_queue(netif_txq, xdpf->len);
+
+	cppi5_hdesc_set_pktlen(first_desc, xdpf->len);
+	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
+
+	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+	if (ret) {
+		netdev_err(ndev, "xdp tx: push failed: %d\n", ret);
+		netdev_tx_completed_queue(netif_txq, 1, xdpf->len);
+		goto drop_free_descs;
+	}
+
+	return ICSSG_XDP_TX;
+
+drop_free_descs:
+	prueth_xmit_free(tx_chn, first_desc);
+	return ICSSG_XDP_CONSUMED;
+}
+EXPORT_SYMBOL_GPL(emac_xmit_xdp_frame);
+
+/**
+ * emac_run_xdp - run an XDP program
+ * @emac: emac device
+ * @xdp: XDP buffer containing the frame
+ * @page: page with RX data if already DMA mapped
+ * @len: Rx descriptor packet length
+ *
+ * Return: XDP state
+ */
+static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
+			struct page *page, u32 *len)
+{
+	struct net_device *ndev = emac->ndev;
+	struct netdev_queue *netif_txq;
+	int cpu = smp_processor_id();
+	struct bpf_prog *xdp_prog;
+	struct xdp_frame *xdpf;
+	u32 pkt_len = *len;
+	u32 act, result;
+	int q_idx, err;
+
+	xdp_prog = READ_ONCE(emac->xdp_prog);
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		return ICSSG_XDP_PASS;
+	case XDP_TX:
+		/* Send packet to TX ring for immediate transmission */
+		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf)) {
+			ndev->stats.tx_dropped++;
+			goto drop;
+		}
+
+		q_idx = cpu % emac->tx_ch_num;
+		netif_txq = netdev_get_tx_queue(ndev, q_idx);
+		__netif_tx_lock(netif_txq, cpu);
+		result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx);
+		__netif_tx_unlock(netif_txq);
+		if (result == ICSSG_XDP_CONSUMED) {
+			ndev->stats.tx_dropped++;
+			goto drop;
+		}
+
+		dev_sw_netstats_rx_add(ndev, xdpf->len);
+		return result;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(emac->ndev, xdp, xdp_prog);
+		if (err)
+			goto drop;
+
+		dev_sw_netstats_rx_add(ndev, pkt_len);
+		return ICSSG_XDP_REDIR;
+	default:
+		bpf_warn_invalid_xdp_action(emac->ndev, xdp_prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+drop:
+		trace_xdp_exception(emac->ndev, xdp_prog, act);
+		fallthrough; /* handle aborts by dropping packet */
+	case XDP_DROP:
+		ndev->stats.rx_dropped++;
+		page_pool_recycle_direct(emac->rx_chns.pg_pool, page);
+		return ICSSG_XDP_CONSUMED;
+	}
+}
+
+static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state)
 {
 	struct prueth_rx_chn *rx_chn = &emac->rx_chns;
 	u32 buf_dma_len, pkt_len, port_id = 0;
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb, *new_skb;
+	struct prueth_swdata *swdata;
 	dma_addr_t desc_dma, buf_dma;
-	void **swdata;
+	struct page *page, *new_page;
+	struct page_pool *pool;
+	struct sk_buff *skb;
+	struct xdp_buff xdp;
 	u32 *psdata;
+	void *pa;
 	int ret;
 
+	*xdp_state = 0;
+	pool = rx_chn->pg_pool;
 	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
 	if (ret) {
 		if (ret != -ENODATA)
@@ -558,15 +723,15 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 		return 0;
 
 	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
-
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
-
-	psdata = cppi5_hdesc_get_psdata(desc_rx);
-	/* RX HW timestamp */
-	if (emac->rx_ts_enabled)
-		emac_rx_timestamp(emac, skb, psdata);
+	if (swdata->type != PRUETH_SWDATA_PAGE) {
+		netdev_err(ndev, "rx_pkt: invalid swdata->type %d\n", swdata->type);
+		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+		return 0;
+	}
 
+	page = swdata->data.page;
+	page_pool_dma_sync_for_cpu(pool, page, 0, PAGE_SIZE);
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
 	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
 	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
@@ -574,32 +739,63 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 	pkt_len -= 4;
 	cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL);
 
-	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	skb->dev = ndev;
-	new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE);
 	/* if allocation fails we drop the packet but push the
-	 * descriptor back to the ring with old skb to prevent a stall
+	 * descriptor back to the ring with old page to prevent a stall
 	 */
-	if (!new_skb) {
+	new_page = page_pool_dev_alloc_pages(pool);
+	if (unlikely(!new_page)) {
+		new_page = page;
 		ndev->stats.rx_dropped++;
-		new_skb = skb;
+		goto requeue;
+	}
+
+	pa = page_address(page);
+	if (emac->xdp_prog) {
+		xdp_init_buff(&xdp, PAGE_SIZE, &rx_chn->xdp_rxq);
+		xdp_prepare_buff(&xdp, pa, PRUETH_HEADROOM, pkt_len, false);
+
+		*xdp_state = emac_run_xdp(emac, &xdp, page, &pkt_len);
+		if (*xdp_state == ICSSG_XDP_PASS)
+			skb = xdp_build_skb_from_buff(&xdp);
+		else
+			goto requeue;
 	} else {
-		/* send the filled skb up the n/w stack */
-		skb_put(skb, pkt_len);
-		if (emac->prueth->is_switch_mode)
-			skb->offload_fwd_mark = emac->offload_fwd_mark;
-		skb->protocol = eth_type_trans(skb, ndev);
-		napi_gro_receive(&emac->napi_rx, skb);
-		ndev->stats.rx_bytes += pkt_len;
-		ndev->stats.rx_packets++;
+		/* prepare skb and send to n/w stack */
+		skb = napi_build_skb(pa, PAGE_SIZE);
 	}
 
+	if (!skb) {
+		ndev->stats.rx_dropped++;
+		page_pool_recycle_direct(pool, page);
+		goto requeue;
+	}
+
+	skb_reserve(skb, PRUETH_HEADROOM);
+	skb_put(skb, pkt_len);
+	skb->dev = ndev;
+
+	psdata = cppi5_hdesc_get_psdata(desc_rx);
+	/* RX HW timestamp */
+	if (emac->rx_ts_enabled)
+		emac_rx_timestamp(emac, skb, psdata);
+
+	if (emac->prueth->is_switch_mode)
+		skb->offload_fwd_mark = emac->offload_fwd_mark;
+	skb->protocol = eth_type_trans(skb, ndev);
+
+	skb_mark_for_recycle(skb);
+	napi_gro_receive(&emac->napi_rx, skb);
+	ndev->stats.rx_bytes += pkt_len;
+	ndev->stats.rx_packets++;
+
+requeue:
 	/* queue another RX DMA */
-	ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_chns);
+	ret = prueth_dma_rx_push_mapped(emac, &emac->rx_chns, new_page,
+					PRUETH_MAX_PKT_SIZE);
 	if (WARN_ON(ret < 0)) {
-		dev_kfree_skb_any(new_skb);
+		page_pool_recycle_direct(pool, new_page);
 		ndev->stats.rx_errors++;
 		ndev->stats.rx_dropped++;
 	}
@@ -611,22 +807,19 @@ static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct prueth_rx_chn *rx_chn = data;
 	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb;
-	dma_addr_t buf_dma;
-	u32 buf_dma_len;
-	void **swdata;
+	struct prueth_swdata *swdata;
+	struct page_pool *pool;
+	struct page *page;
 
+	pool = rx_chn->pg_pool;
 	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
-	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
-	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
+	if (swdata->type == PRUETH_SWDATA_PAGE) {
+		page = swdata->data.page;
+		page_pool_recycle_direct(pool, page);
+	}
 
-	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len,
-			 DMA_FROM_DEVICE);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-
-	dev_kfree_skb_any(skb);
 }
 
 static int prueth_tx_ts_cookie_get(struct prueth_emac *emac)
@@ -662,13 +855,13 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
 	struct prueth_emac *emac = netdev_priv(ndev);
 	struct prueth *prueth = emac->prueth;
 	struct netdev_queue *netif_txq;
+	struct prueth_swdata *swdata;
 	struct prueth_tx_chn *tx_chn;
 	dma_addr_t desc_dma, buf_dma;
 	u32 pkt_len, dst_tag_id;
 	int i, ret = 0, q_idx;
 	bool in_tx_ts = 0;
 	int tx_ts_cookie;
-	void **swdata;
 	u32 *epib;
 
 	pkt_len = skb_headlen(skb);
@@ -730,7 +923,8 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
 	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
-	*swdata = skb;
+	swdata->type = PRUETH_SWDATA_SKB;
+	swdata->data.skb = skb;
 
 	/* Handle the case where skb is fragmented in pages */
 	cur_desc = first_desc;
@@ -780,6 +974,7 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
 	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
 	if (ret) {
 		netdev_err(ndev, "tx: push failed: %d\n", ret);
+		netdev_tx_completed_queue(netif_txq, 1, pkt_len);
 		goto drop_free_descs;
 	}
 
@@ -833,15 +1028,27 @@ static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct prueth_tx_chn *tx_chn = data;
 	struct cppi5_host_desc_t *desc_tx;
+	struct prueth_swdata *swdata;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
-	void **swdata;
 
 	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	prueth_xmit_free(tx_chn, desc_tx);
 
-	dev_kfree_skb_any(skb);
+	switch (swdata->type) {
+	case PRUETH_SWDATA_SKB:
+		skb = swdata->data.skb;
+		dev_kfree_skb_any(skb);
+		break;
+	case PRUETH_SWDATA_XDPF:
+		xdpf = swdata->data.xdpf;
+		xdp_return_frame(xdpf);
+		break;
+	default:
+		break;
+	}
+
+	prueth_xmit_free(tx_chn, desc_tx);
 }
 
 irqreturn_t prueth_rx_irq(int irq, void *dev_id)
@@ -855,31 +1062,6 @@ irqreturn_t prueth_rx_irq(int irq, void *dev_id)
 }
 EXPORT_SYMBOL_GPL(prueth_rx_irq);
 
-void prueth_emac_stop(struct prueth_emac *emac)
-{
-	struct prueth *prueth = emac->prueth;
-	int slice;
-
-	switch (emac->port_id) {
-	case PRUETH_PORT_MII0:
-		slice = ICSS_SLICE0;
-		break;
-	case PRUETH_PORT_MII1:
-		slice = ICSS_SLICE1;
-		break;
-	default:
-		netdev_err(emac->ndev, "invalid port\n");
-		return;
-	}
-
-	emac->fw_running = 0;
-	if (!emac->is_sr1)
-		rproc_shutdown(prueth->txpru[slice]);
-	rproc_shutdown(prueth->rtu[slice]);
-	rproc_shutdown(prueth->pru[slice]);
-}
-EXPORT_SYMBOL_GPL(prueth_emac_stop);
-
 void prueth_cleanup_tx_ts(struct prueth_emac *emac)
 {
 	int i;
@@ -900,15 +1082,18 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget)
 		PRUETH_RX_FLOW_DATA_SR1 : PRUETH_RX_FLOW_DATA;
 	int flow = emac->is_sr1 ?
 		PRUETH_MAX_RX_FLOWS_SR1 : PRUETH_MAX_RX_FLOWS;
+	int xdp_state_or = 0;
 	int num_rx = 0;
 	int cur_budget;
+	u32 xdp_state;
 	int ret;
 
 	while (flow--) {
 		cur_budget = budget - num_rx;
 
 		while (cur_budget--) {
-			ret = emac_rx_packet(emac, flow);
+			ret = emac_rx_packet(emac, flow, &xdp_state);
+			xdp_state_or |= xdp_state;
 			if (ret)
 				break;
 			num_rx++;
@@ -918,6 +1103,9 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget)
 			break;
 	}
 
+	if (xdp_state_or & ICSSG_XDP_REDIR)
+		xdp_do_flush();
+
 	if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) {
 		if (unlikely(emac->rx_pace_timeout_ns)) {
 			hrtimer_start(&emac->rx_hrtimer,
@@ -932,29 +1120,71 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget)
 }
 EXPORT_SYMBOL_GPL(icssg_napi_rx_poll);
 
+static struct page_pool *prueth_create_page_pool(struct prueth_emac *emac,
+						 struct device *dma_dev,
+						 int size)
+{
+	struct page_pool_params pp_params = { 0 };
+	struct page_pool *pool;
+
+	pp_params.order = 0;
+	pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+	pp_params.pool_size = size;
+	pp_params.nid = dev_to_node(emac->prueth->dev);
+	pp_params.dma_dir = DMA_BIDIRECTIONAL;
+	pp_params.dev = dma_dev;
+	pp_params.napi = &emac->napi_rx;
+	pp_params.max_len = PAGE_SIZE;
+
+	pool = page_pool_create(&pp_params);
+	if (IS_ERR(pool))
+		netdev_err(emac->ndev, "cannot create rx page pool\n");
+
+	return pool;
+}
+
 int prueth_prepare_rx_chan(struct prueth_emac *emac,
 			   struct prueth_rx_chn *chn,
 			   int buf_size)
 {
-	struct sk_buff *skb;
+	struct page_pool *pool;
+	struct page *page;
 	int i, ret;
 
+	pool = prueth_create_page_pool(emac, chn->dma_dev, chn->descs_num);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+
+	chn->pg_pool = pool;
+
 	for (i = 0; i < chn->descs_num; i++) {
-		skb = __netdev_alloc_skb_ip_align(NULL, buf_size, GFP_KERNEL);
-		if (!skb)
-			return -ENOMEM;
+		/* NOTE: we're not using memory efficiently here.
+		 * 1 full page (4KB?) used here instead of
+		 * PRUETH_MAX_PKT_SIZE (~1.5KB?)
+		 */
+		page = page_pool_dev_alloc_pages(pool);
+		if (!page) {
+			netdev_err(emac->ndev, "couldn't allocate rx page\n");
+			ret = -ENOMEM;
+			goto recycle_alloc_pg;
+		}
 
-		ret = prueth_dma_rx_push(emac, skb, chn);
+		ret = prueth_dma_rx_push_mapped(emac, chn, page, buf_size);
 		if (ret < 0) {
 			netdev_err(emac->ndev,
-				   "cannot submit skb for rx chan %s ret %d\n",
+				   "cannot submit page for rx chan %s ret %d\n",
 				   chn->name, ret);
-			kfree_skb(skb);
-			return ret;
+			page_pool_recycle_direct(pool, page);
+			goto recycle_alloc_pg;
 		}
 	}
 
 	return 0;
+
+recycle_alloc_pg:
+	prueth_reset_rx_chan(&emac->rx_chns, PRUETH_MAX_RX_FLOWS, false);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(prueth_prepare_rx_chan);
 
@@ -980,7 +1210,7 @@ void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
 
 	for (i = 0; i < num_flows; i++)
 		k3_udma_glue_reset_rx_chn(chn->rx_chn, i, chn,
-					  prueth_rx_cleanup, !!i);
+					  prueth_rx_cleanup);
 	if (disable)
 		k3_udma_glue_disable_rx_chn(chn->rx_chn);
 }
@@ -1084,10 +1314,28 @@ void icssg_ndo_get_stats64(struct net_device *ndev,
 	stats->rx_over_errors = emac_get_stat_by_name(emac, "rx_over_errors");
 	stats->multicast      = emac_get_stat_by_name(emac, "rx_multicast_frames");
 
-	stats->rx_errors  = ndev->stats.rx_errors;
-	stats->rx_dropped = ndev->stats.rx_dropped;
+	stats->rx_errors  = ndev->stats.rx_errors +
+			    emac_get_stat_by_name(emac, "FW_RX_ERROR") +
+			    emac_get_stat_by_name(emac, "FW_RX_EOF_SHORT_FRMERR") +
+			    emac_get_stat_by_name(emac, "FW_RX_B0_DROP_EARLY_EOF") +
+			    emac_get_stat_by_name(emac, "FW_RX_EXP_FRAG_Q_DROP") +
+			    emac_get_stat_by_name(emac, "FW_RX_FIFO_OVERRUN");
+	stats->rx_dropped = ndev->stats.rx_dropped +
+			    emac_get_stat_by_name(emac, "FW_DROPPED_PKT") +
+			    emac_get_stat_by_name(emac, "FW_INF_PORT_DISABLED") +
+			    emac_get_stat_by_name(emac, "FW_INF_SAV") +
+			    emac_get_stat_by_name(emac, "FW_INF_SA_DL") +
+			    emac_get_stat_by_name(emac, "FW_INF_PORT_BLOCKED") +
+			    emac_get_stat_by_name(emac, "FW_INF_DROP_TAGGED") +
+			    emac_get_stat_by_name(emac, "FW_INF_DROP_PRIOTAGGED") +
+			    emac_get_stat_by_name(emac, "FW_INF_DROP_NOTAG") +
+			    emac_get_stat_by_name(emac, "FW_INF_DROP_NOTMEMBER");
 	stats->tx_errors  = ndev->stats.tx_errors;
-	stats->tx_dropped = ndev->stats.tx_dropped;
+	stats->tx_dropped = ndev->stats.tx_dropped +
+			    emac_get_stat_by_name(emac, "FW_RTU_PKT_DROP") +
+			    emac_get_stat_by_name(emac, "FW_TX_DROPPED_PACKET") +
+			    emac_get_stat_by_name(emac, "FW_TX_TS_DROPPED_PACKET") +
+			    emac_get_stat_by_name(emac, "FW_TX_JUMBO_FRM_CUTOFF");
 }
 EXPORT_SYMBOL_GPL(icssg_ndo_get_stats64);
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index 5d2491c2943a..ddfd1c02a885 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -397,7 +397,7 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac)
 	return 0;
 }
 
-static void icssg_init_emac_mode(struct prueth *prueth)
+void icssg_init_emac_mode(struct prueth *prueth)
 {
 	/* When the device is configured as a bridge and it is being brought
 	 * back to the emac mode, the host mac address has to be set as 0.
@@ -406,9 +406,6 @@ static void icssg_init_emac_mode(struct prueth *prueth)
 	int i;
 	u8 mac[ETH_ALEN] = { 0 };
 
-	if (prueth->emacs_initialized)
-		return;
-
 	/* Set VLAN TABLE address base */
 	regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK,
 			   addr <<  SMEM_VLAN_OFFSET);
@@ -423,15 +420,13 @@ static void icssg_init_emac_mode(struct prueth *prueth)
 	/* Clear host MAC address */
 	icssg_class_set_host_mac_addr(prueth->miig_rt, mac);
 }
+EXPORT_SYMBOL_GPL(icssg_init_emac_mode);
 
-static void icssg_init_fw_offload_mode(struct prueth *prueth)
+void icssg_init_fw_offload_mode(struct prueth *prueth)
 {
 	u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET;
 	int i;
 
-	if (prueth->emacs_initialized)
-		return;
-
 	/* Set VLAN TABLE address base */
 	regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK,
 			   addr <<  SMEM_VLAN_OFFSET);
@@ -448,6 +443,7 @@ static void icssg_init_fw_offload_mode(struct prueth *prueth)
 		icssg_class_set_host_mac_addr(prueth->miig_rt, prueth->hw_bridge_dev->dev_addr);
 	icssg_set_pvid(prueth, prueth->default_vlan, PRUETH_PORT_HOST);
 }
+EXPORT_SYMBOL_GPL(icssg_init_fw_offload_mode);
 
 int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 {
@@ -455,11 +451,6 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 	struct icssg_flow_cfg __iomem *flow_cfg;
 	int ret;
 
-	if (prueth->is_switch_mode || prueth->is_hsr_offload_mode)
-		icssg_init_fw_offload_mode(prueth);
-	else
-		icssg_init_emac_mode(prueth);
-
 	memset_io(config, 0, TAS_GATE_MASK_LIST0);
 	icssg_miig_queues_init(prueth, slice);
 
@@ -786,3 +777,27 @@ void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port)
 		writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT0_DEFAULT_VLAN_OFFSET);
 }
 EXPORT_SYMBOL_GPL(icssg_set_pvid);
+
+int emac_fdb_flow_id_updated(struct prueth_emac *emac)
+{
+	struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 };
+	int slice = prueth_emac_slice(emac);
+	struct mgmt_cmd fdb_cmd = { 0 };
+	int ret;
+
+	fdb_cmd.header = ICSSG_FW_MGMT_CMD_HEADER;
+	fdb_cmd.type   = ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW;
+	fdb_cmd.seqnum = ++(emac->prueth->icssg_hwcmdseq);
+	fdb_cmd.param  = 0;
+
+	fdb_cmd.param |= (slice << 4);
+	fdb_cmd.cmd_args[0] = 0;
+
+	ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp);
+	if (ret)
+		return ret;
+
+	WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum);
+	return fdb_cmd_rsp.status == 1 ? 0 : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(emac_fdb_flow_id_updated);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h
index 92c2deaa3068..c884e9fa099e 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.h
@@ -55,6 +55,7 @@ struct icssg_rxq_ctx {
 #define ICSSG_FW_MGMT_FDB_CMD_TYPE	0x03
 #define ICSSG_FW_MGMT_CMD_TYPE		0x04
 #define ICSSG_FW_MGMT_PKT		0x80000000
+#define ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW	0x05
 
 struct icssg_r30_cmd {
 	u32 cmd[4];
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index c568c84a032b..86fc1278127c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -164,11 +164,26 @@ static struct icssg_firmwares icssg_emac_firmwares[] = {
 	}
 };
 
-static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
+static int prueth_start(struct rproc *rproc, const char *fw_name)
+{
+	int ret;
+
+	ret = rproc_set_firmware(rproc, fw_name);
+	if (ret)
+		return ret;
+	return rproc_boot(rproc);
+}
+
+static void prueth_shutdown(struct rproc *rproc)
+{
+	rproc_shutdown(rproc);
+}
+
+static int prueth_emac_start(struct prueth *prueth)
 {
 	struct icssg_firmwares *firmwares;
 	struct device *dev = prueth->dev;
-	int slice, ret;
+	int ret, slice;
 
 	if (prueth->is_switch_mode)
 		firmwares = icssg_switch_firmwares;
@@ -177,49 +192,126 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
 	else
 		firmwares = icssg_emac_firmwares;
 
-	slice = prueth_emac_slice(emac);
-	if (slice < 0) {
-		netdev_err(emac->ndev, "invalid port\n");
-		return -EINVAL;
+	for (slice = 0; slice < PRUETH_NUM_MACS; slice++) {
+		ret = prueth_start(prueth->pru[slice], firmwares[slice].pru);
+		if (ret) {
+			dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret);
+			goto unwind_slices;
+		}
+
+		ret = prueth_start(prueth->rtu[slice], firmwares[slice].rtu);
+		if (ret) {
+			dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret);
+			rproc_shutdown(prueth->pru[slice]);
+			goto unwind_slices;
+		}
+
+		ret = prueth_start(prueth->txpru[slice], firmwares[slice].txpru);
+		if (ret) {
+			dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret);
+			rproc_shutdown(prueth->rtu[slice]);
+			rproc_shutdown(prueth->pru[slice]);
+			goto unwind_slices;
+		}
 	}
 
-	ret = icssg_config(prueth, emac, slice);
-	if (ret)
-		return ret;
+	return 0;
 
-	ret = rproc_set_firmware(prueth->pru[slice], firmwares[slice].pru);
-	ret = rproc_boot(prueth->pru[slice]);
-	if (ret) {
-		dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret);
-		return -EINVAL;
+unwind_slices:
+	while (--slice >= 0) {
+		prueth_shutdown(prueth->txpru[slice]);
+		prueth_shutdown(prueth->rtu[slice]);
+		prueth_shutdown(prueth->pru[slice]);
 	}
 
-	ret = rproc_set_firmware(prueth->rtu[slice], firmwares[slice].rtu);
-	ret = rproc_boot(prueth->rtu[slice]);
-	if (ret) {
-		dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret);
-		goto halt_pru;
+	return ret;
+}
+
+static void prueth_emac_stop(struct prueth *prueth)
+{
+	int slice;
+
+	for (slice = 0; slice < PRUETH_NUM_MACS; slice++) {
+		prueth_shutdown(prueth->txpru[slice]);
+		prueth_shutdown(prueth->rtu[slice]);
+		prueth_shutdown(prueth->pru[slice]);
 	}
+}
+
+static int prueth_emac_common_start(struct prueth *prueth)
+{
+	struct prueth_emac *emac;
+	int ret = 0;
+	int slice;
+
+	if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1])
+		return -EINVAL;
 
-	ret = rproc_set_firmware(prueth->txpru[slice], firmwares[slice].txpru);
-	ret = rproc_boot(prueth->txpru[slice]);
+	/* clear SMEM and MSMC settings for all slices */
+	memset_io(prueth->msmcram.va, 0, prueth->msmcram.size);
+	memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS);
+
+	icssg_class_default(prueth->miig_rt, ICSS_SLICE0, 0, false);
+	icssg_class_default(prueth->miig_rt, ICSS_SLICE1, 0, false);
+
+	if (prueth->is_switch_mode || prueth->is_hsr_offload_mode)
+		icssg_init_fw_offload_mode(prueth);
+	else
+		icssg_init_emac_mode(prueth);
+
+	for (slice = 0; slice < PRUETH_NUM_MACS; slice++) {
+		emac = prueth->emac[slice];
+		if (!emac)
+			continue;
+		ret = icssg_config(prueth, emac, slice);
+		if (ret)
+			goto disable_class;
+	}
+
+	ret = prueth_emac_start(prueth);
+	if (ret)
+		goto disable_class;
+
+	emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] :
+	       prueth->emac[ICSS_SLICE1];
+	ret = icss_iep_init(emac->iep, &prueth_iep_clockops,
+			    emac, IEP_DEFAULT_CYCLE_TIME_NS);
 	if (ret) {
-		dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret);
-		goto halt_rtu;
+		dev_err(prueth->dev, "Failed to initialize IEP module\n");
+		goto stop_pruss;
 	}
 
-	emac->fw_running = 1;
 	return 0;
 
-halt_rtu:
-	rproc_shutdown(prueth->rtu[slice]);
+stop_pruss:
+	prueth_emac_stop(prueth);
 
-halt_pru:
-	rproc_shutdown(prueth->pru[slice]);
+disable_class:
+	icssg_class_disable(prueth->miig_rt, ICSS_SLICE0);
+	icssg_class_disable(prueth->miig_rt, ICSS_SLICE1);
 
 	return ret;
 }
 
+static int prueth_emac_common_stop(struct prueth *prueth)
+{
+	struct prueth_emac *emac;
+
+	if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1])
+		return -EINVAL;
+
+	icssg_class_disable(prueth->miig_rt, ICSS_SLICE0);
+	icssg_class_disable(prueth->miig_rt, ICSS_SLICE1);
+
+	prueth_emac_stop(prueth);
+
+	emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] :
+	       prueth->emac[ICSS_SLICE1];
+	icss_iep_exit(emac->iep);
+
+	return 0;
+}
+
 /* called back by PHY layer if there is change in link state of hw port*/
 static void emac_adjust_link(struct net_device *ndev)
 {
@@ -374,9 +466,6 @@ static void prueth_iep_settime(void *clockops_data, u64 ns)
 	u32 cycletime;
 	int timeout;
 
-	if (!emac->fw_running)
-		return;
-
 	sc_descp = emac->prueth->shram.va + TIMESYNC_FW_WC_SETCLOCK_DESC_OFFSET;
 
 	cycletime = IEP_DEFAULT_CYCLE_TIME_NS;
@@ -470,63 +559,163 @@ const struct icss_iep_clockops prueth_iep_clockops = {
 	.perout_enable = prueth_perout_enable,
 };
 
+static int prueth_create_xdp_rxqs(struct prueth_emac *emac)
+{
+	struct xdp_rxq_info *rxq = &emac->rx_chns.xdp_rxq;
+	struct page_pool *pool = emac->rx_chns.pg_pool;
+	int ret;
+
+	ret = xdp_rxq_info_reg(rxq, emac->ndev, 0, emac->napi_rx.napi_id);
+	if (ret)
+		return ret;
+
+	ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool);
+	if (ret)
+		xdp_rxq_info_unreg(rxq);
+
+	return ret;
+}
+
+static void prueth_destroy_xdp_rxqs(struct prueth_emac *emac)
+{
+	struct xdp_rxq_info *rxq = &emac->rx_chns.xdp_rxq;
+
+	if (!xdp_rxq_info_is_reg(rxq))
+		return;
+
+	xdp_rxq_info_unreg(rxq);
+}
+
 static int icssg_prueth_add_mcast(struct net_device *ndev, const u8 *addr)
 {
-	struct prueth_emac *emac = netdev_priv(ndev);
-	int port_mask = BIT(emac->port_id);
+	struct net_device *real_dev;
+	struct prueth_emac *emac;
+	int port_mask;
+	u8 vlan_id;
 
-	port_mask |= icssg_fdb_lookup(emac, addr, 0);
-	icssg_fdb_add_del(emac, addr, 0, port_mask, true);
-	icssg_vtbl_modify(emac, 0, port_mask, port_mask, true);
+	vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_MAC;
+	real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev;
+	emac = netdev_priv(real_dev);
+
+	port_mask = BIT(emac->port_id) | icssg_fdb_lookup(emac, addr, vlan_id);
+	icssg_fdb_add_del(emac, addr, vlan_id, port_mask, true);
+	icssg_vtbl_modify(emac, vlan_id, port_mask, port_mask, true);
 
 	return 0;
 }
 
 static int icssg_prueth_del_mcast(struct net_device *ndev, const u8 *addr)
 {
-	struct prueth_emac *emac = netdev_priv(ndev);
-	int port_mask = BIT(emac->port_id);
+	struct net_device *real_dev;
+	struct prueth_emac *emac;
 	int other_port_mask;
+	int port_mask;
+	u8 vlan_id;
+
+	vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_MAC;
+	real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev;
+	emac = netdev_priv(real_dev);
 
-	other_port_mask = port_mask ^ icssg_fdb_lookup(emac, addr, 0);
+	port_mask = BIT(emac->port_id);
+	other_port_mask = port_mask ^ icssg_fdb_lookup(emac, addr, vlan_id);
 
-	icssg_fdb_add_del(emac, addr, 0, port_mask, false);
-	icssg_vtbl_modify(emac, 0, port_mask, port_mask, false);
+	icssg_fdb_add_del(emac, addr, vlan_id, port_mask, false);
+	icssg_vtbl_modify(emac, vlan_id, port_mask, port_mask, false);
 
 	if (other_port_mask) {
-		icssg_fdb_add_del(emac, addr, 0, other_port_mask, true);
-		icssg_vtbl_modify(emac, 0, other_port_mask, other_port_mask, true);
+		icssg_fdb_add_del(emac, addr, vlan_id, other_port_mask, true);
+		icssg_vtbl_modify(emac, vlan_id, other_port_mask,
+				  other_port_mask, true);
 	}
 
 	return 0;
 }
 
-static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
+static void icssg_prueth_hsr_fdb_add_del(struct prueth_emac *emac,
+					 const u8 *addr, u8 vid, bool add)
 {
-	struct prueth_emac *emac = netdev_priv(ndev);
-	struct prueth *prueth = emac->prueth;
-
-	icssg_fdb_add_del(emac, addr, prueth->default_vlan,
+	icssg_fdb_add_del(emac, addr, vid,
 			  ICSSG_FDB_ENTRY_P0_MEMBERSHIP |
 			  ICSSG_FDB_ENTRY_P1_MEMBERSHIP |
 			  ICSSG_FDB_ENTRY_P2_MEMBERSHIP |
-			  ICSSG_FDB_ENTRY_BLOCK, true);
+			  ICSSG_FDB_ENTRY_BLOCK, add);
+
+	if (add)
+		icssg_vtbl_modify(emac, vid, BIT(emac->port_id),
+				  BIT(emac->port_id), add);
+}
+
+static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
+{
+	struct net_device *real_dev;
+	struct prueth_emac *emac;
+	u8 vlan_id, i;
+
+	vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_HSR;
+	real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev;
+
+	if (is_hsr_master(real_dev)) {
+		for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) {
+			emac = netdev_priv(hsr_get_port_ndev(real_dev, i));
+			if (!emac)
+				return -EINVAL;
+			icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id,
+						     true);
+		}
+	} else {
+		emac = netdev_priv(real_dev);
+		icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, true);
+	}
 
-	icssg_vtbl_modify(emac, emac->port_vlan, BIT(emac->port_id),
-			  BIT(emac->port_id), true);
 	return 0;
 }
 
 static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr)
 {
-	struct prueth_emac *emac = netdev_priv(ndev);
-	struct prueth *prueth = emac->prueth;
+	struct net_device *real_dev;
+	struct prueth_emac *emac;
+	u8 vlan_id, i;
+
+	vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_HSR;
+	real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev;
+
+	if (is_hsr_master(real_dev)) {
+		for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) {
+			emac = netdev_priv(hsr_get_port_ndev(real_dev, i));
+			if (!emac)
+				return -EINVAL;
+			icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id,
+						     false);
+		}
+	} else {
+		emac = netdev_priv(real_dev);
+		icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, false);
+	}
 
-	icssg_fdb_add_del(emac, addr, prueth->default_vlan,
-			  ICSSG_FDB_ENTRY_P0_MEMBERSHIP |
-			  ICSSG_FDB_ENTRY_P1_MEMBERSHIP |
-			  ICSSG_FDB_ENTRY_P2_MEMBERSHIP |
-			  ICSSG_FDB_ENTRY_BLOCK, false);
+	return 0;
+}
+
+static int icssg_update_vlan_mcast(struct net_device *vdev, int vid,
+				   void *args)
+{
+	struct prueth_emac *emac = args;
+
+	if (!vdev || !vid)
+		return 0;
+
+	netif_addr_lock_bh(vdev);
+	__hw_addr_sync_multiple(&emac->vlan_mcast_list[vid], &vdev->mc,
+				vdev->addr_len);
+	netif_addr_unlock_bh(vdev);
+
+	if (emac->prueth->is_hsr_offload_mode)
+		__hw_addr_sync_dev(&emac->vlan_mcast_list[vid], vdev,
+				   icssg_prueth_hsr_add_mcast,
+				   icssg_prueth_hsr_del_mcast);
+	else
+		__hw_addr_sync_dev(&emac->vlan_mcast_list[vid], vdev,
+				   icssg_prueth_add_mcast,
+				   icssg_prueth_del_mcast);
 
 	return 0;
 }
@@ -543,23 +732,17 @@ static int emac_ndo_open(struct net_device *ndev)
 {
 	struct prueth_emac *emac = netdev_priv(ndev);
 	int ret, i, num_data_chn = emac->tx_ch_num;
+	struct icssg_flow_cfg __iomem *flow_cfg;
 	struct prueth *prueth = emac->prueth;
 	int slice = prueth_emac_slice(emac);
 	struct device *dev = prueth->dev;
 	int max_rx_flows;
 	int rx_flow;
 
-	/* clear SMEM and MSMC settings for all slices */
-	if (!prueth->emacs_initialized) {
-		memset_io(prueth->msmcram.va, 0, prueth->msmcram.size);
-		memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS);
-	}
-
 	/* set h/w MAC as user might have re-configured */
 	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
 
 	icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
-	icssg_class_default(prueth->miig_rt, slice, 0, false);
 	icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
 
 	/* Notify the stack of the actual queue counts. */
@@ -597,18 +780,23 @@ static int emac_ndo_open(struct net_device *ndev)
 		goto cleanup_napi;
 	}
 
-	/* reset and start PRU firmware */
-	ret = prueth_emac_start(prueth, emac);
-	if (ret)
-		goto free_rx_irq;
+	if (!prueth->emacs_initialized) {
+		ret = prueth_emac_common_start(prueth);
+		if (ret)
+			goto free_rx_irq;
+	}
 
-	icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu);
+	flow_cfg = emac->dram.va + ICSSG_CONFIG_OFFSET + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET;
+	writew(emac->rx_flow_id_base, &flow_cfg->rx_base_flow);
+	ret = emac_fdb_flow_id_updated(emac);
 
-	if (!prueth->emacs_initialized) {
-		ret = icss_iep_init(emac->iep, &prueth_iep_clockops,
-				    emac, IEP_DEFAULT_CYCLE_TIME_NS);
+	if (ret) {
+		netdev_err(ndev, "Failed to update Rx Flow ID %d", ret);
+		goto stop;
 	}
 
+	icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu);
+
 	ret = request_threaded_irq(emac->tx_ts_irq, NULL, prueth_tx_ts_irq,
 				   IRQF_ONESHOT, dev_name(dev), emac);
 	if (ret)
@@ -619,10 +807,14 @@ static int emac_ndo_open(struct net_device *ndev)
 	if (ret)
 		goto free_tx_ts_irq;
 
-	ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn);
+	ret = prueth_create_xdp_rxqs(emac);
 	if (ret)
 		goto reset_rx_chn;
 
+	ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn);
+	if (ret)
+		goto destroy_xdp_rxqs;
+
 	for (i = 0; i < emac->tx_ch_num; i++) {
 		ret = k3_udma_glue_enable_tx_chn(emac->tx_chns[i].tx_chn);
 		if (ret)
@@ -648,12 +840,15 @@ reset_tx_chan:
 	 * any SKB for completion. So set false to free_skb
 	 */
 	prueth_reset_tx_chan(emac, i, false);
+destroy_xdp_rxqs:
+	prueth_destroy_xdp_rxqs(emac);
 reset_rx_chn:
 	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, false);
 free_tx_ts_irq:
 	free_irq(emac->tx_ts_irq, emac);
 stop:
-	prueth_emac_stop(emac);
+	if (!prueth->emacs_initialized)
+		prueth_emac_common_stop(prueth);
 free_rx_irq:
 	free_irq(emac->rx_chns.irq[rx_flow], emac);
 cleanup_napi:
@@ -689,8 +884,6 @@ static int emac_ndo_stop(struct net_device *ndev)
 	if (ndev->phydev)
 		phy_stop(ndev->phydev);
 
-	icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac));
-
 	if (emac->prueth->is_hsr_offload_mode)
 		__dev_mc_unsync(ndev, icssg_prueth_hsr_del_mcast);
 	else
@@ -719,7 +912,7 @@ static int emac_ndo_stop(struct net_device *ndev)
 	k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true);
 
 	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, true);
-
+	prueth_destroy_xdp_rxqs(emac);
 	napi_disable(&emac->napi_rx);
 	hrtimer_cancel(&emac->rx_hrtimer);
 
@@ -728,11 +921,9 @@ static int emac_ndo_stop(struct net_device *ndev)
 	/* Destroying the queued work in ndo_stop() */
 	cancel_delayed_work_sync(&emac->stats_work);
 
-	if (prueth->emacs_initialized == 1)
-		icss_iep_exit(emac->iep);
-
 	/* stop PRUs */
-	prueth_emac_stop(emac);
+	if (prueth->emacs_initialized == 1)
+		prueth_emac_common_stop(prueth);
 
 	free_irq(emac->tx_ts_irq, emac);
 
@@ -772,12 +963,22 @@ static void emac_ndo_set_rx_mode_work(struct work_struct *work)
 		return;
 	}
 
-	if (emac->prueth->is_hsr_offload_mode)
+	if (emac->prueth->is_hsr_offload_mode) {
 		__dev_mc_sync(ndev, icssg_prueth_hsr_add_mcast,
 			      icssg_prueth_hsr_del_mcast);
-	else
+		if (rtnl_trylock()) {
+			vlan_for_each(emac->prueth->hsr_dev,
+				      icssg_update_vlan_mcast, emac);
+			rtnl_unlock();
+		}
+	} else {
 		__dev_mc_sync(ndev, icssg_prueth_add_mcast,
 			      icssg_prueth_del_mcast);
+		if (rtnl_trylock()) {
+			vlan_for_each(ndev, icssg_update_vlan_mcast, emac);
+			rtnl_unlock();
+		}
+	}
 }
 
 /**
@@ -822,19 +1023,19 @@ static int emac_ndo_vlan_rx_add_vid(struct net_device *ndev,
 {
 	struct prueth_emac *emac = netdev_priv(ndev);
 	struct prueth *prueth = emac->prueth;
+	int port_mask = BIT(emac->port_id);
 	int untag_mask = 0;
-	int port_mask;
 
-	if (prueth->is_hsr_offload_mode) {
-		port_mask = BIT(PRUETH_PORT_HOST) | BIT(emac->port_id);
-		untag_mask = 0;
+	if (prueth->is_hsr_offload_mode)
+		port_mask |= BIT(PRUETH_PORT_HOST);
 
-		netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X\n",
-			   vid, port_mask, untag_mask);
+	__hw_addr_init(&emac->vlan_mcast_list[vid]);
+	netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X\n",
+		   vid, port_mask, untag_mask);
+
+	icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true);
+	icssg_set_pvid(emac->prueth, vid, emac->port_id);
 
-		icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true);
-		icssg_set_pvid(emac->prueth, vid, emac->port_id);
-	}
 	return 0;
 }
 
@@ -843,21 +1044,106 @@ static int emac_ndo_vlan_rx_del_vid(struct net_device *ndev,
 {
 	struct prueth_emac *emac = netdev_priv(ndev);
 	struct prueth *prueth = emac->prueth;
+	int port_mask = BIT(emac->port_id);
 	int untag_mask = 0;
-	int port_mask;
 
-	if (prueth->is_hsr_offload_mode) {
+	if (prueth->is_hsr_offload_mode)
 		port_mask = BIT(PRUETH_PORT_HOST);
-		untag_mask = 0;
 
-		netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X untag_mask  %X\n",
-			   vid, port_mask, untag_mask);
+	netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X untag_mask  %X\n",
+		   vid, port_mask, untag_mask);
+	icssg_vtbl_modify(emac, vid, port_mask, untag_mask, false);
 
-		icssg_vtbl_modify(emac, vid, port_mask, untag_mask, false);
+	return 0;
+}
+
+/**
+ * emac_xdp_xmit - Implements ndo_xdp_xmit
+ * @dev: netdev
+ * @n: number of frames
+ * @frames: array of XDP buffer pointers
+ * @flags: XDP extra info
+ *
+ * Return: number of frames successfully sent. Failed frames
+ * will be free'ed by XDP core.
+ *
+ * For error cases, a negative errno code is returned and no-frames
+ * are transmitted (caller must handle freeing frames).
+ **/
+static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+			 u32 flags)
+{
+	struct prueth_emac *emac = netdev_priv(dev);
+	struct net_device *ndev = emac->ndev;
+	struct netdev_queue *netif_txq;
+	int cpu = smp_processor_id();
+	struct xdp_frame *xdpf;
+	unsigned int q_idx;
+	int nxmit = 0;
+	u32 err;
+	int i;
+
+	q_idx = cpu % emac->tx_ch_num;
+	netif_txq = netdev_get_tx_queue(ndev, q_idx);
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	__netif_tx_lock(netif_txq, cpu);
+	for (i = 0; i < n; i++) {
+		xdpf = frames[i];
+		err = emac_xmit_xdp_frame(emac, xdpf, NULL, q_idx);
+		if (err != ICSSG_XDP_TX) {
+			ndev->stats.tx_dropped++;
+			break;
+		}
+		nxmit++;
 	}
+	__netif_tx_unlock(netif_txq);
+
+	return nxmit;
+}
+
+/**
+ * emac_xdp_setup - add/remove an XDP program
+ * @emac: emac device
+ * @bpf: XDP program
+ *
+ * Return: Always 0 (Success)
+ **/
+static int emac_xdp_setup(struct prueth_emac *emac, struct netdev_bpf *bpf)
+{
+	struct bpf_prog *prog = bpf->prog;
+
+	if (!emac->xdpi.prog && !prog)
+		return 0;
+
+	WRITE_ONCE(emac->xdp_prog, prog);
+
+	xdp_attachment_setup(&emac->xdpi, bpf);
+
 	return 0;
 }
 
+/**
+ * emac_ndo_bpf - implements ndo_bpf for icssg_prueth
+ * @ndev: network adapter device
+ * @bpf: XDP program
+ *
+ * Return: 0 on success, error code on failure.
+ **/
+static int emac_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return emac_xdp_setup(emac, bpf);
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops emac_netdev_ops = {
 	.ndo_open = emac_ndo_open,
 	.ndo_stop = emac_ndo_stop,
@@ -872,6 +1158,8 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_fix_features = emac_ndo_fix_features,
 	.ndo_vlan_rx_add_vid = emac_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = emac_ndo_vlan_rx_del_vid,
+	.ndo_bpf = emac_ndo_bpf,
+	.ndo_xdp_xmit = emac_xdp_xmit,
 };
 
 static int prueth_netdev_init(struct prueth *prueth,
@@ -900,6 +1188,8 @@ static int prueth_netdev_init(struct prueth *prueth,
 	emac->prueth = prueth;
 	emac->ndev = ndev;
 	emac->port_id = port;
+	emac->xdp_prog = NULL;
+	emac->ndev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	emac->cmd_wq = create_singlethread_workqueue("icssg_cmd_wq");
 	if (!emac->cmd_wq) {
 		ret = -ENOMEM;
@@ -1001,11 +1291,14 @@ static int prueth_netdev_init(struct prueth *prueth,
 	ndev->hw_features = NETIF_F_SG;
 	ndev->features = ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
 	ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES;
+	xdp_set_features_flag(ndev,
+			      NETDEV_XDP_ACT_BASIC |
+			      NETDEV_XDP_ACT_REDIRECT |
+			      NETDEV_XDP_ACT_NDO_XMIT);
 
 	netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll);
-	hrtimer_init(&emac->rx_hrtimer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_PINNED);
-	emac->rx_hrtimer.function = &emac_rx_timer_callback;
+	hrtimer_setup(&emac->rx_hrtimer, &emac_rx_timer_callback, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_PINNED);
 	prueth->emac[mac] = emac;
 
 	return 0;
@@ -1053,10 +1346,11 @@ static void prueth_offload_fwd_mark_update(struct prueth *prueth)
 	}
 }
 
-static void prueth_emac_restart(struct prueth *prueth)
+static int prueth_emac_restart(struct prueth *prueth)
 {
 	struct prueth_emac *emac0 = prueth->emac[PRUETH_MAC0];
 	struct prueth_emac *emac1 = prueth->emac[PRUETH_MAC1];
+	int ret;
 
 	/* Detach the net_device for both PRUeth ports*/
 	if (netif_running(emac0->ndev))
@@ -1065,36 +1359,46 @@ static void prueth_emac_restart(struct prueth *prueth)
 		netif_device_detach(emac1->ndev);
 
 	/* Disable both PRUeth ports */
-	icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE);
-	icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE);
+	ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE);
+	ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE);
+	if (ret)
+		return ret;
 
 	/* Stop both pru cores for both PRUeth ports*/
-	prueth_emac_stop(emac0);
-	prueth->emacs_initialized--;
-	prueth_emac_stop(emac1);
-	prueth->emacs_initialized--;
+	ret = prueth_emac_common_stop(prueth);
+	if (ret) {
+		dev_err(prueth->dev, "Failed to stop the firmwares");
+		return ret;
+	}
 
 	/* Start both pru cores for both PRUeth ports */
-	prueth_emac_start(prueth, emac0);
-	prueth->emacs_initialized++;
-	prueth_emac_start(prueth, emac1);
-	prueth->emacs_initialized++;
+	ret = prueth_emac_common_start(prueth);
+	if (ret) {
+		dev_err(prueth->dev, "Failed to start the firmwares");
+		return ret;
+	}
 
 	/* Enable forwarding for both PRUeth ports */
-	icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD);
-	icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD);
+	ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD);
+	ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD);
 
 	/* Attache net_device for both PRUeth ports */
 	netif_device_attach(emac0->ndev);
 	netif_device_attach(emac1->ndev);
+
+	return ret;
 }
 
 static void icssg_change_mode(struct prueth *prueth)
 {
 	struct prueth_emac *emac;
-	int mac;
+	int mac, ret;
 
-	prueth_emac_restart(prueth);
+	ret = prueth_emac_restart(prueth);
+	if (ret) {
+		dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process");
+		return;
+	}
 
 	for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) {
 		emac = prueth->emac[mac];
@@ -1158,7 +1462,7 @@ static int prueth_netdevice_port_link(struct net_device *ndev,
 		if (prueth->br_members & BIT(PRUETH_PORT_MII0) &&
 		    prueth->br_members & BIT(PRUETH_PORT_MII1)) {
 			prueth->is_switch_mode = true;
-			prueth->default_vlan = 1;
+			prueth->default_vlan = PRUETH_DFLT_VLAN_SW;
 			emac->port_vlan = prueth->default_vlan;
 			icssg_change_mode(prueth);
 		}
@@ -1173,13 +1477,18 @@ static void prueth_netdevice_port_unlink(struct net_device *ndev)
 {
 	struct prueth_emac *emac = netdev_priv(ndev);
 	struct prueth *prueth = emac->prueth;
+	int ret;
 
 	prueth->br_members &= ~BIT(emac->port_id);
 
 	if (prueth->is_switch_mode) {
 		prueth->is_switch_mode = false;
 		emac->port_vlan = 0;
-		prueth_emac_restart(prueth);
+		ret = prueth_emac_restart(prueth);
+		if (ret) {
+			dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process");
+			return;
+		}
 	}
 
 	prueth_offload_fwd_mark_update(prueth);
@@ -1211,7 +1520,7 @@ static int prueth_hsr_port_link(struct net_device *ndev)
 			      NETIF_PRUETH_HSR_OFFLOAD_FEATURES))
 				return -EOPNOTSUPP;
 			prueth->is_hsr_offload_mode = true;
-			prueth->default_vlan = 1;
+			prueth->default_vlan = PRUETH_DFLT_VLAN_HSR;
 			emac0->port_vlan = prueth->default_vlan;
 			emac1->port_vlan = prueth->default_vlan;
 			icssg_change_mode(prueth);
@@ -1228,6 +1537,7 @@ static void prueth_hsr_port_unlink(struct net_device *ndev)
 	struct prueth *prueth = emac->prueth;
 	struct prueth_emac *emac0;
 	struct prueth_emac *emac1;
+	int ret;
 
 	emac0 = prueth->emac[PRUETH_MAC0];
 	emac1 = prueth->emac[PRUETH_MAC1];
@@ -1238,7 +1548,11 @@ static void prueth_hsr_port_unlink(struct net_device *ndev)
 		emac0->port_vlan = 0;
 		emac1->port_vlan = 0;
 		prueth->hsr_dev = NULL;
-		prueth_emac_restart(prueth);
+		ret = prueth_emac_restart(prueth);
+		if (ret) {
+			dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process");
+			return;
+		}
 		netdev_dbg(ndev, "Disabling HSR Offload mode\n");
 	}
 }
@@ -1335,6 +1649,9 @@ static int prueth_probe(struct platform_device *pdev)
 
 	np = dev->of_node;
 
+	BUILD_BUG_ON_MSG((sizeof(struct prueth_swdata) > PRUETH_NAV_SW_DATA_SIZE),
+			 "insufficient SW_DATA size");
+
 	prueth = devm_kzalloc(dev, sizeof(*prueth), GFP_KERNEL);
 	if (!prueth)
 		return -ENOMEM;
@@ -1413,13 +1730,10 @@ static int prueth_probe(struct platform_device *pdev)
 		prueth->pa_stats = NULL;
 	}
 
-	if (eth0_node) {
+	if (eth0_node || eth1_node) {
 		ret = prueth_get_cores(prueth, ICSS_SLICE0, false);
 		if (ret)
 			goto put_cores;
-	}
-
-	if (eth1_node) {
 		ret = prueth_get_cores(prueth, ICSS_SLICE1, false);
 		if (ret)
 			goto put_cores;
@@ -1495,6 +1809,7 @@ static int prueth_probe(struct platform_device *pdev)
 	}
 
 	spin_lock_init(&prueth->vtbl_lock);
+	spin_lock_init(&prueth->stats_lock);
 	/* setup netdev interfaces */
 	if (eth0_node) {
 		ret = prueth_netdev_init(prueth, eth0_node);
@@ -1618,14 +1933,12 @@ put_pruss:
 	pruss_put(prueth->pruss);
 
 put_cores:
-	if (eth1_node) {
-		prueth_put_cores(prueth, ICSS_SLICE1);
-		of_node_put(eth1_node);
-	}
-
-	if (eth0_node) {
+	if (eth0_node || eth1_node) {
 		prueth_put_cores(prueth, ICSS_SLICE0);
 		of_node_put(eth0_node);
+
+		prueth_put_cores(prueth, ICSS_SLICE1);
+		of_node_put(eth1_node);
 	}
 
 	return ret;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index f5c1d473e9f9..23c465f1ce7f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -8,6 +8,8 @@
 #ifndef __NET_TI_ICSSG_PRUETH_H
 #define __NET_TI_ICSSG_PRUETH_H
 
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 #include <linux/etherdevice.h>
 #include <linux/genalloc.h>
 #include <linux/if_vlan.h>
@@ -33,6 +35,8 @@
 #include <linux/dma/k3-udma-glue.h>
 
 #include <net/devlink.h>
+#include <net/xdp.h>
+#include <net/page_pool/helpers.h>
 
 #include "icssg_config.h"
 #include "icss_iep.h"
@@ -50,7 +54,7 @@
 
 #define ICSSG_MAX_RFLOWS	8	/* per slice */
 
-#define ICSSG_NUM_PA_STATS	4
+#define ICSSG_NUM_PA_STATS	32
 #define ICSSG_NUM_MIIG_STATS	60
 /* Number of ICSSG related stats */
 #define ICSSG_NUM_STATS (ICSSG_NUM_MIIG_STATS + ICSSG_NUM_PA_STATS)
@@ -83,6 +87,12 @@
 #define ICSS_CMD_ADD_FILTER 0x7
 #define ICSS_CMD_ADD_MAC 0x8
 
+/* VLAN Filtering Related MACROs */
+#define PRUETH_DFLT_VLAN_HSR	1
+#define PRUETH_DFLT_VLAN_SW	1
+#define PRUETH_DFLT_VLAN_MAC	0
+#define MAX_VLAN_ID		256
+
 /* In switch mode there are 3 real ports i.e. 3 mac addrs.
  * however Linux sees only the host side port. The other 2 ports
  * are the switch ports.
@@ -125,6 +135,26 @@ struct prueth_rx_chn {
 	u32 descs_num;
 	unsigned int irq[ICSSG_MAX_RFLOWS];	/* separate irq per flow */
 	char name[32];
+	struct page_pool *pg_pool;
+	struct xdp_rxq_info xdp_rxq;
+};
+
+enum prueth_swdata_type {
+	PRUETH_SWDATA_INVALID = 0,
+	PRUETH_SWDATA_SKB,
+	PRUETH_SWDATA_PAGE,
+	PRUETH_SWDATA_CMD,
+	PRUETH_SWDATA_XDPF,
+};
+
+struct prueth_swdata {
+	enum prueth_swdata_type type;
+	union prueth_data {
+		struct sk_buff *skb;
+		struct page *page;
+		u32 cmd;
+		struct xdp_frame *xdpf;
+	} data;
 };
 
 /* There are 4 Tx DMA channels, but the highest priority is CH3 (thread 3)
@@ -134,13 +164,18 @@ struct prueth_rx_chn {
 
 #define PRUETH_MAX_TX_TS_REQUESTS	50 /* Max simultaneous TX_TS requests */
 
+/* XDP BPF state */
+#define ICSSG_XDP_PASS           0
+#define ICSSG_XDP_CONSUMED       BIT(0)
+#define ICSSG_XDP_TX             BIT(1)
+#define ICSSG_XDP_REDIR          BIT(2)
+
 /* Minimum coalesce time in usecs for both Tx and Rx */
 #define ICSSG_MIN_COALESCE_USECS 20
 
 /* data for each emac port */
 struct prueth_emac {
 	bool is_sr1;
-	bool fw_running;
 	struct prueth *prueth;
 	struct net_device *ndev;
 	u8 mac_addr[6];
@@ -201,8 +236,16 @@ struct prueth_emac {
 	/* RX IRQ Coalescing Related */
 	struct hrtimer rx_hrtimer;
 	unsigned long rx_pace_timeout_ns;
+
+	struct netdev_hw_addr_list vlan_mcast_list[MAX_VLAN_ID];
+	struct bpf_prog *xdp_prog;
+	struct xdp_attachment_info xdpi;
 };
 
+/* The buf includes headroom compatible with both skb and xdpf */
+#define PRUETH_HEADROOM_NA (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN)
+#define PRUETH_HEADROOM  ALIGN(PRUETH_HEADROOM_NA, sizeof(long))
+
 /**
  * struct prueth_pdata - PRUeth platform data
  * @fdqring_mode: Free desc queue mode
@@ -298,6 +341,8 @@ struct prueth {
 	int default_vlan;
 	/** @vtbl_lock: Lock for vtbl in shared memory */
 	spinlock_t vtbl_lock;
+	/** @stats_lock: Lock for reading icssg stats */
+	spinlock_t stats_lock;
 };
 
 struct emac_tx_ts_response {
@@ -361,6 +406,8 @@ int icssg_set_port_state(struct prueth_emac *emac,
 			 enum icssg_port_state_cmd state);
 void icssg_config_set_speed(struct prueth_emac *emac);
 void icssg_config_half_duplex(struct prueth_emac *emac);
+void icssg_init_emac_mode(struct prueth *prueth);
+void icssg_init_fw_offload_mode(struct prueth *prueth);
 
 /* Buffer queue helpers */
 int icssg_queue_pop(struct prueth *prueth, u8 queue);
@@ -377,6 +424,7 @@ void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask,
 		       u8 untag_mask, bool add);
 u16 icssg_get_pvid(struct prueth_emac *emac);
 void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port);
+int emac_fdb_flow_id_updated(struct prueth_emac *emac);
 #define prueth_napi_to_tx_chn(pnapi) \
 	container_of(pnapi, struct prueth_tx_chn, napi_tx)
 
@@ -400,14 +448,14 @@ int prueth_init_rx_chns(struct prueth_emac *emac,
 			struct prueth_rx_chn *rx_chn,
 			char *name, u32 max_rflows,
 			u32 max_desc_num);
-int prueth_dma_rx_push(struct prueth_emac *emac,
-		       struct sk_buff *skb,
-		       struct prueth_rx_chn *rx_chn);
+int prueth_dma_rx_push_mapped(struct prueth_emac *emac,
+			      struct prueth_rx_chn *rx_chn,
+			      struct page *page, u32 buf_len);
+unsigned int prueth_rxbuf_total_len(unsigned int len);
 void emac_rx_timestamp(struct prueth_emac *emac,
 		       struct sk_buff *skb, u32 *psdata);
 enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 irqreturn_t prueth_rx_irq(int irq, void *dev_id);
-void prueth_emac_stop(struct prueth_emac *emac);
 void prueth_cleanup_tx_ts(struct prueth_emac *emac);
 int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget);
 int prueth_prepare_rx_chan(struct prueth_emac *emac,
@@ -432,5 +480,9 @@ void prueth_put_cores(struct prueth *prueth, int slice);
 
 /* Revision specific helper */
 u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns);
+u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
+			struct xdp_frame *xdpf,
+			struct page *page,
+			unsigned int q_idx);
 
 #endif /* __NET_TI_ICSSG_PRUETH_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
index 5024f0647a0d..ff5f41bf499e 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
@@ -84,7 +84,7 @@ static int emac_send_command_sr1(struct prueth_emac *emac, u32 cmd)
 	__le32 *data = emac->cmd_data;
 	dma_addr_t desc_dma, buf_dma;
 	struct prueth_tx_chn *tx_chn;
-	void **swdata;
+	struct prueth_swdata *swdata;
 	int ret = 0;
 	u32 *epib;
 
@@ -122,7 +122,8 @@ static int emac_send_command_sr1(struct prueth_emac *emac, u32 cmd)
 
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
-	*swdata = data;
+	swdata->type = PRUETH_SWDATA_CMD;
+	swdata->data.cmd = le32_to_cpu(data[0]);
 
 	cppi5_hdesc_set_pktlen(first_desc, pkt_len);
 	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
@@ -268,16 +269,16 @@ static int emac_phy_connect(struct prueth_emac *emac)
  * Returns skb pointer if packet found else NULL
  * Caller must free the returned skb.
  */
-static struct sk_buff *prueth_process_rx_mgm(struct prueth_emac *emac,
-					     u32 flow_id)
+static struct page *prueth_process_rx_mgm(struct prueth_emac *emac,
+					  u32 flow_id)
 {
 	struct prueth_rx_chn *rx_chn = &emac->rx_mgm_chn;
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb, *new_skb;
+	struct page *page, *new_page;
+	struct prueth_swdata *swdata;
 	dma_addr_t desc_dma, buf_dma;
-	u32 buf_dma_len, pkt_len;
-	void **swdata;
+	u32 buf_dma_len;
 	int ret;
 
 	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
@@ -299,34 +300,31 @@ static struct sk_buff *prueth_process_rx_mgm(struct prueth_emac *emac,
 	}
 
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
+	page = swdata->data.page;
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
-	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
 
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE);
+	new_page = page_pool_dev_alloc_pages(rx_chn->pg_pool);
 	/* if allocation fails we drop the packet but push the
 	 * descriptor back to the ring with old skb to prevent a stall
 	 */
-	if (!new_skb) {
+	if (!new_page) {
 		netdev_err(ndev,
-			   "skb alloc failed, dropped mgm pkt from flow %d\n",
+			   "page alloc failed, dropped mgm pkt from flow %d\n",
 			   flow_id);
-		new_skb = skb;
-		skb = NULL;	/* return NULL */
-	} else {
-		/* return the filled skb */
-		skb_put(skb, pkt_len);
+		new_page = page;
+		page = NULL;	/* return NULL */
 	}
 
 	/* queue another DMA */
-	ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_mgm_chn);
+	ret = prueth_dma_rx_push_mapped(emac, &emac->rx_chns, new_page,
+					PRUETH_MAX_PKT_SIZE);
 	if (WARN_ON(ret < 0))
-		dev_kfree_skb_any(new_skb);
+		page_pool_recycle_direct(rx_chn->pg_pool, new_page);
 
-	return skb;
+	return page;
 }
 
 static void prueth_tx_ts_sr1(struct prueth_emac *emac,
@@ -362,14 +360,14 @@ static void prueth_tx_ts_sr1(struct prueth_emac *emac,
 static irqreturn_t prueth_rx_mgm_ts_thread_sr1(int irq, void *dev_id)
 {
 	struct prueth_emac *emac = dev_id;
-	struct sk_buff *skb;
+	struct page *page;
 
-	skb = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1);
-	if (!skb)
+	page = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1);
+	if (!page)
 		return IRQ_NONE;
 
-	prueth_tx_ts_sr1(emac, (void *)skb->data);
-	dev_kfree_skb_any(skb);
+	prueth_tx_ts_sr1(emac, (void *)page_address(page));
+	page_pool_recycle_direct(page->pp, page);
 
 	return IRQ_HANDLED;
 }
@@ -377,15 +375,15 @@ static irqreturn_t prueth_rx_mgm_ts_thread_sr1(int irq, void *dev_id)
 static irqreturn_t prueth_rx_mgm_rsp_thread(int irq, void *dev_id)
 {
 	struct prueth_emac *emac = dev_id;
-	struct sk_buff *skb;
+	struct page *page;
 	u32 rsp;
 
-	skb = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_RESPONSE_SR1);
-	if (!skb)
+	page = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_RESPONSE_SR1);
+	if (!page)
 		return IRQ_NONE;
 
 	/* Process command response */
-	rsp = le32_to_cpu(*(__le32 *)skb->data) & 0xffff0000;
+	rsp = le32_to_cpu(*(__le32 *)page_address(page)) & 0xffff0000;
 	if (rsp == ICSSG_SHUTDOWN_CMD_SR1) {
 		netdev_dbg(emac->ndev, "f/w Shutdown cmd resp %x\n", rsp);
 		complete(&emac->cmd_complete);
@@ -394,7 +392,7 @@ static irqreturn_t prueth_rx_mgm_rsp_thread(int irq, void *dev_id)
 		complete(&emac->cmd_complete);
 	}
 
-	dev_kfree_skb_any(skb);
+	page_pool_recycle_direct(page->pp, page);
 
 	return IRQ_HANDLED;
 }
@@ -440,7 +438,6 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
 		goto halt_pru;
 	}
 
-	emac->fw_running = 1;
 	return 0;
 
 halt_pru:
@@ -449,6 +446,29 @@ halt_pru:
 	return ret;
 }
 
+static void prueth_emac_stop(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int slice;
+
+	switch (emac->port_id) {
+	case PRUETH_PORT_MII0:
+		slice = ICSS_SLICE0;
+		break;
+	case PRUETH_PORT_MII1:
+		slice = ICSS_SLICE1;
+		break;
+	default:
+		netdev_err(emac->ndev, "invalid port\n");
+		return;
+	}
+
+	if (!emac->is_sr1)
+		rproc_shutdown(prueth->txpru[slice]);
+	rproc_shutdown(prueth->rtu[slice]);
+	rproc_shutdown(prueth->pru[slice]);
+}
+
 /**
  * emac_ndo_open - EMAC device open
  * @ndev: network adapter device
@@ -1009,8 +1029,6 @@ static int prueth_probe(struct platform_device *pdev)
 						   (unsigned long)prueth->msmcram.va);
 	prueth->msmcram.size = msmc_ram_size;
 	memset_io(prueth->msmcram.va, 0, msmc_ram_size);
-	dev_dbg(dev, "sram: pa %llx va %p size %zx\n", prueth->msmcram.pa,
-		prueth->msmcram.va, prueth->msmcram.size);
 
 	prueth->iep0 = icss_iep_get_idx(np, 0);
 	if (IS_ERR(prueth->iep0)) {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index 8800bd3a8d07..7159baa0155c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -11,7 +11,6 @@
 
 #define ICSSG_TX_PACKET_OFFSET	0xA0
 #define ICSSG_TX_BYTE_OFFSET	0xEC
-#define ICSSG_FW_STATS_BASE	0x0248
 
 static u32 stats_base[] = {	0x54c,	/* Slice 0 stats start */
 				0xb18,	/* Slice 1 stats start */
@@ -26,7 +25,17 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 	u32 val, reg;
 	int i;
 
+	spin_lock(&prueth->stats_lock);
+
 	for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) {
+		/* In MII mode TX lines are swapped inside ICSSG, so read Tx stats
+		 * from slice1 for port0 and slice0 for port1 to get accurate Tx
+		 * stats for a given port
+		 */
+		if (emac->phy_if == PHY_INTERFACE_MODE_MII &&
+		    icssg_all_miig_stats[i].offset >= ICSSG_TX_PACKET_OFFSET &&
+		    icssg_all_miig_stats[i].offset <= ICSSG_TX_BYTE_OFFSET)
+			base = stats_base[slice ^ 1];
 		regmap_read(prueth->miig_rt,
 			    base + icssg_all_miig_stats[i].offset,
 			    &val);
@@ -44,13 +53,14 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 
 	if (prueth->pa_stats) {
 		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
-			reg = ICSSG_FW_STATS_BASE +
-			      icssg_all_pa_stats[i].offset *
-			      PRUETH_NUM_MACS + slice * sizeof(u32);
+			reg = icssg_all_pa_stats[i].offset +
+			      slice * sizeof(u32);
 			regmap_read(prueth->pa_stats, reg, &val);
 			emac->pa_stats[i] += val;
 		}
 	}
+
+	spin_unlock(&prueth->stats_lock);
 }
 
 void icssg_stats_work_handler(struct work_struct *work)
@@ -76,7 +86,7 @@ int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name)
 	if (emac->prueth->pa_stats) {
 		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
 			if (!strcmp(icssg_all_pa_stats[i].name, stat_name))
-				return emac->pa_stats[icssg_all_pa_stats[i].offset / sizeof(u32)];
+				return emac->pa_stats[i];
 		}
 	}
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.h b/drivers/net/ethernet/ti/icssg/icssg_stats.h
index e88b919f532c..5ec0b38e0c67 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.h
@@ -155,24 +155,10 @@ static const struct icssg_miig_stats icssg_all_miig_stats[] = {
 	ICSSG_MIIG_STATS(tx_bytes, true),
 };
 
-/**
- * struct pa_stats_regs - ICSSG Firmware maintained PA Stats register
- * @fw_rx_cnt: Number of valid packets sent by Rx PRU to Host on PSI
- * @fw_tx_cnt: Number of valid packets copied by RTU0 to Tx queues
- * @fw_tx_pre_overflow: Host Egress Q (Pre-emptible) Overflow Counter
- * @fw_tx_exp_overflow: Host Egress Q (Express) Overflow Counter
- */
-struct pa_stats_regs {
-	u32 fw_rx_cnt;
-	u32 fw_tx_cnt;
-	u32 fw_tx_pre_overflow;
-	u32 fw_tx_exp_overflow;
-};
-
-#define ICSSG_PA_STATS(field)			\
-{						\
-	#field,					\
-	offsetof(struct pa_stats_regs, field),	\
+#define ICSSG_PA_STATS(field)	\
+{				\
+	#field,			\
+	field,			\
 }
 
 struct icssg_pa_stats {
@@ -181,10 +167,38 @@ struct icssg_pa_stats {
 };
 
 static const struct icssg_pa_stats icssg_all_pa_stats[] = {
-	ICSSG_PA_STATS(fw_rx_cnt),
-	ICSSG_PA_STATS(fw_tx_cnt),
-	ICSSG_PA_STATS(fw_tx_pre_overflow),
-	ICSSG_PA_STATS(fw_tx_exp_overflow),
+	ICSSG_PA_STATS(FW_RTU_PKT_DROP),
+	ICSSG_PA_STATS(FW_Q0_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q1_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q2_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q3_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q4_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q5_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q6_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q7_OVERFLOW),
+	ICSSG_PA_STATS(FW_DROPPED_PKT),
+	ICSSG_PA_STATS(FW_RX_ERROR),
+	ICSSG_PA_STATS(FW_RX_DS_INVALID),
+	ICSSG_PA_STATS(FW_TX_DROPPED_PACKET),
+	ICSSG_PA_STATS(FW_TX_TS_DROPPED_PACKET),
+	ICSSG_PA_STATS(FW_INF_PORT_DISABLED),
+	ICSSG_PA_STATS(FW_INF_SAV),
+	ICSSG_PA_STATS(FW_INF_SA_DL),
+	ICSSG_PA_STATS(FW_INF_PORT_BLOCKED),
+	ICSSG_PA_STATS(FW_INF_DROP_TAGGED),
+	ICSSG_PA_STATS(FW_INF_DROP_PRIOTAGGED),
+	ICSSG_PA_STATS(FW_INF_DROP_NOTAG),
+	ICSSG_PA_STATS(FW_INF_DROP_NOTMEMBER),
+	ICSSG_PA_STATS(FW_RX_EOF_SHORT_FRMERR),
+	ICSSG_PA_STATS(FW_RX_B0_DROP_EARLY_EOF),
+	ICSSG_PA_STATS(FW_TX_JUMBO_FRM_CUTOFF),
+	ICSSG_PA_STATS(FW_RX_EXP_FRAG_Q_DROP),
+	ICSSG_PA_STATS(FW_RX_FIFO_OVERRUN),
+	ICSSG_PA_STATS(FW_CUT_THR_PKT),
+	ICSSG_PA_STATS(FW_HOST_RX_PKT_CNT),
+	ICSSG_PA_STATS(FW_HOST_TX_PKT_CNT),
+	ICSSG_PA_STATS(FW_HOST_EGRESS_Q_PRE_OVERFLOW),
+	ICSSG_PA_STATS(FW_HOST_EGRESS_Q_EXP_OVERFLOW),
 };
 
 #endif /* __NET_TI_ICSSG_STATS_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
index 424a7e945ea8..490a9cc06fb0 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
@@ -231,4 +231,37 @@
 /* Start of 32 bits PA_STAT counters */
 #define PA_STAT_32b_START_OFFSET                           0x0080
 
+#define FW_RTU_PKT_DROP			0x0088
+#define FW_Q0_OVERFLOW			0x0090
+#define FW_Q1_OVERFLOW			0x0098
+#define FW_Q2_OVERFLOW			0x00A0
+#define FW_Q3_OVERFLOW			0x00A8
+#define FW_Q4_OVERFLOW			0x00B0
+#define FW_Q5_OVERFLOW			0x00B8
+#define FW_Q6_OVERFLOW			0x00C0
+#define FW_Q7_OVERFLOW			0x00C8
+#define FW_DROPPED_PKT			0x00F8
+#define FW_RX_ERROR			0x0100
+#define FW_RX_DS_INVALID		0x0108
+#define FW_TX_DROPPED_PACKET		0x0110
+#define FW_TX_TS_DROPPED_PACKET		0x0118
+#define FW_INF_PORT_DISABLED		0x0120
+#define FW_INF_SAV			0x0128
+#define FW_INF_SA_DL			0x0130
+#define FW_INF_PORT_BLOCKED		0x0138
+#define FW_INF_DROP_TAGGED		0x0140
+#define FW_INF_DROP_PRIOTAGGED		0x0148
+#define FW_INF_DROP_NOTAG		0x0150
+#define FW_INF_DROP_NOTMEMBER		0x0158
+#define FW_RX_EOF_SHORT_FRMERR		0x0188
+#define FW_RX_B0_DROP_EARLY_EOF		0x0190
+#define FW_TX_JUMBO_FRM_CUTOFF		0x0198
+#define FW_RX_EXP_FRAG_Q_DROP		0x01A0
+#define FW_RX_FIFO_OVERRUN		0x01A8
+#define FW_CUT_THR_PKT			0x01B0
+#define FW_HOST_RX_PKT_CNT		0x0248
+#define FW_HOST_TX_PKT_CNT		0x0250
+#define FW_HOST_EGRESS_Q_PRE_OVERFLOW	0x0258
+#define FW_HOST_EGRESS_Q_EXP_OVERFLOW	0x0260
+
 #endif /* __NET_TI_ICSSG_SWITCH_MAP_H  */
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 63e686f0b119..55a1a96cd834 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -2833,7 +2833,7 @@ static int gbe_ioctl(void *intf_priv, struct ifreq *req, int cmd)
 
 static void netcp_ethss_timer(struct timer_list *t)
 {
-	struct gbe_priv *gbe_dev = from_timer(gbe_dev, t, timer);
+	struct gbe_priv *gbe_dev = timer_container_of(gbe_dev, t, timer);
 	struct gbe_intf *gbe_intf;
 	struct gbe_slave *slave;
 
@@ -3796,7 +3796,7 @@ static int gbe_remove(struct netcp_device *netcp_device, void *inst_priv)
 {
 	struct gbe_priv *gbe_dev = inst_priv;
 
-	del_timer_sync(&gbe_dev->timer);
+	timer_delete_sync(&gbe_dev->timer);
 	cpts_release(gbe_dev->cpts);
 	cpsw_ale_stop(gbe_dev->ale);
 	netcp_txpipe_close(&gbe_dev->tx_pipe);
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index b3da76efa8f5..a55b0f951181 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -332,13 +332,13 @@ static void tlan_stop(struct net_device *dev)
 {
 	struct tlan_priv *priv = netdev_priv(dev);
 
-	del_timer_sync(&priv->media_timer);
+	timer_delete_sync(&priv->media_timer);
 	tlan_read_and_clear_stats(dev, TLAN_RECORD);
 	outl(TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD);
 	/* Reset and power down phy */
 	tlan_reset_adapter(dev);
 	if (priv->timer.function != NULL) {
-		del_timer_sync(&priv->timer);
+		timer_delete_sync(&priv->timer);
 		priv->timer.function = NULL;
 	}
 }
@@ -1815,7 +1815,7 @@ ThunderLAN driver timer function
 
 static void tlan_timer(struct timer_list *t)
 {
-	struct tlan_priv	*priv = from_timer(priv, t, timer);
+	struct tlan_priv	*priv = timer_container_of(priv, t, timer);
 	struct net_device	*dev = priv->dev;
 	u32		elapsed;
 	unsigned long	flags = 0;
@@ -2746,7 +2746,7 @@ static void tlan_phy_finish_auto_neg(struct net_device *dev)
 
 static void tlan_phy_monitor(struct timer_list *t)
 {
-	struct tlan_priv *priv = from_timer(priv, t, media_timer);
+	struct tlan_priv *priv = timer_container_of(priv, t, media_timer);
 	struct net_device *dev = priv->dev;
 	u16     phy;
 	u16     phy_status;
diff --git a/drivers/net/ethernet/toshiba/Kconfig b/drivers/net/ethernet/toshiba/Kconfig
index 701e9b7c1c3b..b1e27e3b99eb 100644
--- a/drivers/net/ethernet/toshiba/Kconfig
+++ b/drivers/net/ethernet/toshiba/Kconfig
@@ -6,7 +6,7 @@
 config NET_VENDOR_TOSHIBA
 	bool "Toshiba devices"
 	default y
-	depends on PCI && (PPC_IBM_CELL_BLADE || MIPS) || PPC_PS3
+	depends on PCI && MIPS || PPC_PS3
 	help
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
@@ -39,15 +39,6 @@ config GELIC_WIRELESS
 	  the driver automatically distinguishes the models, you can
 	  safely enable this option even if you have a wireless-less model.
 
-config SPIDER_NET
-	tristate "Spider Gigabit Ethernet driver"
-	depends on PCI && PPC_IBM_CELL_BLADE
-	select FW_LOADER
-	select SUNGEM_PHY
-	help
-	  This driver supports the Gigabit Ethernet chips present on the
-	  Cell Processor-Based Blades from IBM.
-
 config TC35815
 	tristate "TOSHIBA TC35815 Ethernet support"
 	depends on PCI && MIPS
diff --git a/drivers/net/ethernet/toshiba/Makefile b/drivers/net/ethernet/toshiba/Makefile
index f434fd0f429e..27e2164cf7e9 100644
--- a/drivers/net/ethernet/toshiba/Makefile
+++ b/drivers/net/ethernet/toshiba/Makefile
@@ -6,6 +6,4 @@
 obj-$(CONFIG_GELIC_NET) += ps3_gelic.o
 gelic_wireless-$(CONFIG_GELIC_WIRELESS) += ps3_gelic_wireless.o
 ps3_gelic-objs += ps3_gelic_net.o $(gelic_wireless-y)
-spidernet-y += spider_net.o spider_net_ethtool.o
-obj-$(CONFIG_SPIDER_NET) += spidernet.o
 obj-$(CONFIG_TC35815) += tc35815.o
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
deleted file mode 100644
index a4937c18d7cb..000000000000
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ /dev/null
@@ -1,2556 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Network device driver for Cell Processor-Based Blade and Celleb platform
- *
- * (C) Copyright IBM Corp. 2005
- * (C) Copyright 2006 TOSHIBA CORPORATION
- *
- * Authors : Utz Bacher <utz.bacher@de.ibm.com>
- *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
- */
-
-#include <linux/compiler.h>
-#include <linux/crc32.h>
-#include <linux/delay.h>
-#include <linux/etherdevice.h>
-#include <linux/ethtool.h>
-#include <linux/firmware.h>
-#include <linux/if_vlan.h>
-#include <linux/in.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/gfp.h>
-#include <linux/ioport.h>
-#include <linux/ip.h>
-#include <linux/kernel.h>
-#include <linux/mii.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/device.h>
-#include <linux/pci.h>
-#include <linux/skbuff.h>
-#include <linux/tcp.h>
-#include <linux/types.h>
-#include <linux/vmalloc.h>
-#include <linux/wait.h>
-#include <linux/workqueue.h>
-#include <linux/bitops.h>
-#include <linux/of.h>
-#include <net/checksum.h>
-
-#include "spider_net.h"
-
-MODULE_AUTHOR("Utz Bacher <utz.bacher@de.ibm.com> and Jens Osterkamp " \
-	      "<Jens.Osterkamp@de.ibm.com>");
-MODULE_DESCRIPTION("Spider Southbridge Gigabit Ethernet driver");
-MODULE_LICENSE("GPL");
-MODULE_VERSION(VERSION);
-MODULE_FIRMWARE(SPIDER_NET_FIRMWARE_NAME);
-
-static int rx_descriptors = SPIDER_NET_RX_DESCRIPTORS_DEFAULT;
-static int tx_descriptors = SPIDER_NET_TX_DESCRIPTORS_DEFAULT;
-
-module_param(rx_descriptors, int, 0444);
-module_param(tx_descriptors, int, 0444);
-
-MODULE_PARM_DESC(rx_descriptors, "number of descriptors used " \
-		 "in rx chains");
-MODULE_PARM_DESC(tx_descriptors, "number of descriptors used " \
-		 "in tx chain");
-
-char spider_net_driver_name[] = "spidernet";
-
-static const struct pci_device_id spider_net_pci_tbl[] = {
-	{ PCI_VENDOR_ID_TOSHIBA_2, PCI_DEVICE_ID_TOSHIBA_SPIDER_NET,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ 0, }
-};
-
-MODULE_DEVICE_TABLE(pci, spider_net_pci_tbl);
-
-/**
- * spider_net_read_reg - reads an SMMIO register of a card
- * @card: device structure
- * @reg: register to read from
- *
- * returns the content of the specified SMMIO register.
- */
-static inline u32
-spider_net_read_reg(struct spider_net_card *card, u32 reg)
-{
-	/* We use the powerpc specific variants instead of readl_be() because
-	 * we know spidernet is not a real PCI device and we can thus avoid the
-	 * performance hit caused by the PCI workarounds.
-	 */
-	return in_be32(card->regs + reg);
-}
-
-/**
- * spider_net_write_reg - writes to an SMMIO register of a card
- * @card: device structure
- * @reg: register to write to
- * @value: value to write into the specified SMMIO register
- */
-static inline void
-spider_net_write_reg(struct spider_net_card *card, u32 reg, u32 value)
-{
-	/* We use the powerpc specific variants instead of writel_be() because
-	 * we know spidernet is not a real PCI device and we can thus avoid the
-	 * performance hit caused by the PCI workarounds.
-	 */
-	out_be32(card->regs + reg, value);
-}
-
-/**
- * spider_net_write_phy - write to phy register
- * @netdev: adapter to be written to
- * @mii_id: id of MII
- * @reg: PHY register
- * @val: value to be written to phy register
- *
- * spider_net_write_phy_register writes to an arbitrary PHY
- * register via the spider GPCWOPCMD register. We assume the queue does
- * not run full (not more than 15 commands outstanding).
- **/
-static void
-spider_net_write_phy(struct net_device *netdev, int mii_id,
-		     int reg, int val)
-{
-	struct spider_net_card *card = netdev_priv(netdev);
-	u32 writevalue;
-
-	writevalue = ((u32)mii_id << 21) |
-		((u32)reg << 16) | ((u32)val);
-
-	spider_net_write_reg(card, SPIDER_NET_GPCWOPCMD, writevalue);
-}
-
-/**
- * spider_net_read_phy - read from phy register
- * @netdev: network device to be read from
- * @mii_id: id of MII
- * @reg: PHY register
- *
- * Returns value read from PHY register
- *
- * spider_net_write_phy reads from an arbitrary PHY
- * register via the spider GPCROPCMD register
- **/
-static int
-spider_net_read_phy(struct net_device *netdev, int mii_id, int reg)
-{
-	struct spider_net_card *card = netdev_priv(netdev);
-	u32 readvalue;
-
-	readvalue = ((u32)mii_id << 21) | ((u32)reg << 16);
-	spider_net_write_reg(card, SPIDER_NET_GPCROPCMD, readvalue);
-
-	/* we don't use semaphores to wait for an SPIDER_NET_GPROPCMPINT
-	 * interrupt, as we poll for the completion of the read operation
-	 * in spider_net_read_phy. Should take about 50 us
-	 */
-	do {
-		readvalue = spider_net_read_reg(card, SPIDER_NET_GPCROPCMD);
-	} while (readvalue & SPIDER_NET_GPREXEC);
-
-	readvalue &= SPIDER_NET_GPRDAT_MASK;
-
-	return readvalue;
-}
-
-/**
- * spider_net_setup_aneg - initial auto-negotiation setup
- * @card: device structure
- **/
-static void
-spider_net_setup_aneg(struct spider_net_card *card)
-{
-	struct mii_phy *phy = &card->phy;
-	u32 advertise = 0;
-	u16 bmsr, estat;
-
-	bmsr  = spider_net_read_phy(card->netdev, phy->mii_id, MII_BMSR);
-	estat = spider_net_read_phy(card->netdev, phy->mii_id, MII_ESTATUS);
-
-	if (bmsr & BMSR_10HALF)
-		advertise |= ADVERTISED_10baseT_Half;
-	if (bmsr & BMSR_10FULL)
-		advertise |= ADVERTISED_10baseT_Full;
-	if (bmsr & BMSR_100HALF)
-		advertise |= ADVERTISED_100baseT_Half;
-	if (bmsr & BMSR_100FULL)
-		advertise |= ADVERTISED_100baseT_Full;
-
-	if ((bmsr & BMSR_ESTATEN) && (estat & ESTATUS_1000_TFULL))
-		advertise |= SUPPORTED_1000baseT_Full;
-	if ((bmsr & BMSR_ESTATEN) && (estat & ESTATUS_1000_THALF))
-		advertise |= SUPPORTED_1000baseT_Half;
-
-	sungem_phy_probe(phy, phy->mii_id);
-	phy->def->ops->setup_aneg(phy, advertise);
-
-}
-
-/**
- * spider_net_rx_irq_off - switch off rx irq on this spider card
- * @card: device structure
- *
- * switches off rx irq by masking them out in the GHIINTnMSK register
- */
-static void
-spider_net_rx_irq_off(struct spider_net_card *card)
-{
-	u32 regvalue;
-
-	regvalue = SPIDER_NET_INT0_MASK_VALUE & (~SPIDER_NET_RXINT);
-	spider_net_write_reg(card, SPIDER_NET_GHIINT0MSK, regvalue);
-}
-
-/**
- * spider_net_rx_irq_on - switch on rx irq on this spider card
- * @card: device structure
- *
- * switches on rx irq by enabling them in the GHIINTnMSK register
- */
-static void
-spider_net_rx_irq_on(struct spider_net_card *card)
-{
-	u32 regvalue;
-
-	regvalue = SPIDER_NET_INT0_MASK_VALUE | SPIDER_NET_RXINT;
-	spider_net_write_reg(card, SPIDER_NET_GHIINT0MSK, regvalue);
-}
-
-/**
- * spider_net_set_promisc - sets the unicast address or the promiscuous mode
- * @card: card structure
- *
- * spider_net_set_promisc sets the unicast destination address filter and
- * thus either allows for non-promisc mode or promisc mode
- */
-static void
-spider_net_set_promisc(struct spider_net_card *card)
-{
-	u32 macu, macl;
-	struct net_device *netdev = card->netdev;
-
-	if (netdev->flags & IFF_PROMISC) {
-		/* clear destination entry 0 */
-		spider_net_write_reg(card, SPIDER_NET_GMRUAFILnR, 0);
-		spider_net_write_reg(card, SPIDER_NET_GMRUAFILnR + 0x04, 0);
-		spider_net_write_reg(card, SPIDER_NET_GMRUA0FIL15R,
-				     SPIDER_NET_PROMISC_VALUE);
-	} else {
-		macu = netdev->dev_addr[0];
-		macu <<= 8;
-		macu |= netdev->dev_addr[1];
-		memcpy(&macl, &netdev->dev_addr[2], sizeof(macl));
-
-		macu |= SPIDER_NET_UA_DESCR_VALUE;
-		spider_net_write_reg(card, SPIDER_NET_GMRUAFILnR, macu);
-		spider_net_write_reg(card, SPIDER_NET_GMRUAFILnR + 0x04, macl);
-		spider_net_write_reg(card, SPIDER_NET_GMRUA0FIL15R,
-				     SPIDER_NET_NONPROMISC_VALUE);
-	}
-}
-
-/**
- * spider_net_get_descr_status -- returns the status of a descriptor
- * @hwdescr: descriptor to look at
- *
- * returns the status as in the dmac_cmd_status field of the descriptor
- */
-static inline int
-spider_net_get_descr_status(struct spider_net_hw_descr *hwdescr)
-{
-	return hwdescr->dmac_cmd_status & SPIDER_NET_DESCR_IND_PROC_MASK;
-}
-
-/**
- * spider_net_free_chain - free descriptor chain
- * @card: card structure
- * @chain: address of chain
- *
- */
-static void
-spider_net_free_chain(struct spider_net_card *card,
-		      struct spider_net_descr_chain *chain)
-{
-	struct spider_net_descr *descr;
-
-	descr = chain->ring;
-	do {
-		descr->bus_addr = 0;
-		descr->hwdescr->next_descr_addr = 0;
-		descr = descr->next;
-	} while (descr != chain->ring);
-
-	dma_free_coherent(&card->pdev->dev, chain->num_desc * sizeof(struct spider_net_hw_descr),
-			  chain->hwring, chain->dma_addr);
-}
-
-/**
- * spider_net_init_chain - alloc and link descriptor chain
- * @card: card structure
- * @chain: address of chain
- *
- * We manage a circular list that mirrors the hardware structure,
- * except that the hardware uses bus addresses.
- *
- * Returns 0 on success, <0 on failure
- */
-static int
-spider_net_init_chain(struct spider_net_card *card,
-		       struct spider_net_descr_chain *chain)
-{
-	int i;
-	struct spider_net_descr *descr;
-	struct spider_net_hw_descr *hwdescr;
-	dma_addr_t buf;
-	size_t alloc_size;
-
-	alloc_size = chain->num_desc * sizeof(struct spider_net_hw_descr);
-
-	chain->hwring = dma_alloc_coherent(&card->pdev->dev, alloc_size,
-					   &chain->dma_addr, GFP_KERNEL);
-	if (!chain->hwring)
-		return -ENOMEM;
-
-	/* Set up the hardware pointers in each descriptor */
-	descr = chain->ring;
-	hwdescr = chain->hwring;
-	buf = chain->dma_addr;
-	for (i=0; i < chain->num_desc; i++, descr++, hwdescr++) {
-		hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
-		hwdescr->next_descr_addr = 0;
-
-		descr->hwdescr = hwdescr;
-		descr->bus_addr = buf;
-		descr->next = descr + 1;
-		descr->prev = descr - 1;
-
-		buf += sizeof(struct spider_net_hw_descr);
-	}
-	/* do actual circular list */
-	(descr-1)->next = chain->ring;
-	chain->ring->prev = descr-1;
-
-	spin_lock_init(&chain->lock);
-	chain->head = chain->ring;
-	chain->tail = chain->ring;
-	return 0;
-}
-
-/**
- * spider_net_free_rx_chain_contents - frees descr contents in rx chain
- * @card: card structure
- *
- * returns 0 on success, <0 on failure
- */
-static void
-spider_net_free_rx_chain_contents(struct spider_net_card *card)
-{
-	struct spider_net_descr *descr;
-
-	descr = card->rx_chain.head;
-	do {
-		if (descr->skb) {
-			dma_unmap_single(&card->pdev->dev,
-					 descr->hwdescr->buf_addr,
-					 SPIDER_NET_MAX_FRAME,
-					 DMA_BIDIRECTIONAL);
-			dev_kfree_skb(descr->skb);
-			descr->skb = NULL;
-		}
-		descr = descr->next;
-	} while (descr != card->rx_chain.head);
-}
-
-/**
- * spider_net_prepare_rx_descr - Reinitialize RX descriptor
- * @card: card structure
- * @descr: descriptor to re-init
- *
- * Return 0 on success, <0 on failure.
- *
- * Allocates a new rx skb, iommu-maps it and attaches it to the
- * descriptor. Mark the descriptor as activated, ready-to-use.
- */
-static int
-spider_net_prepare_rx_descr(struct spider_net_card *card,
-			    struct spider_net_descr *descr)
-{
-	struct spider_net_hw_descr *hwdescr = descr->hwdescr;
-	dma_addr_t buf;
-	int offset;
-	int bufsize;
-
-	/* we need to round up the buffer size to a multiple of 128 */
-	bufsize = (SPIDER_NET_MAX_FRAME + SPIDER_NET_RXBUF_ALIGN - 1) &
-		(~(SPIDER_NET_RXBUF_ALIGN - 1));
-
-	/* and we need to have it 128 byte aligned, therefore we allocate a
-	 * bit more
-	 */
-	/* allocate an skb */
-	descr->skb = netdev_alloc_skb(card->netdev,
-				      bufsize + SPIDER_NET_RXBUF_ALIGN - 1);
-	if (!descr->skb) {
-		if (netif_msg_rx_err(card) && net_ratelimit())
-			dev_err(&card->netdev->dev,
-			        "Not enough memory to allocate rx buffer\n");
-		card->spider_stats.alloc_rx_skb_error++;
-		return -ENOMEM;
-	}
-	hwdescr->buf_size = bufsize;
-	hwdescr->result_size = 0;
-	hwdescr->valid_size = 0;
-	hwdescr->data_status = 0;
-	hwdescr->data_error = 0;
-
-	offset = ((unsigned long)descr->skb->data) &
-		(SPIDER_NET_RXBUF_ALIGN - 1);
-	if (offset)
-		skb_reserve(descr->skb, SPIDER_NET_RXBUF_ALIGN - offset);
-	/* iommu-map the skb */
-	buf = dma_map_single(&card->pdev->dev, descr->skb->data,
-			     SPIDER_NET_MAX_FRAME, DMA_FROM_DEVICE);
-	if (dma_mapping_error(&card->pdev->dev, buf)) {
-		dev_kfree_skb_any(descr->skb);
-		descr->skb = NULL;
-		if (netif_msg_rx_err(card) && net_ratelimit())
-			dev_err(&card->netdev->dev, "Could not iommu-map rx buffer\n");
-		card->spider_stats.rx_iommu_map_error++;
-		hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
-	} else {
-		hwdescr->buf_addr = buf;
-		wmb();
-		hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_CARDOWNED |
-					 SPIDER_NET_DMAC_NOINTR_COMPLETE;
-	}
-
-	return 0;
-}
-
-/**
- * spider_net_enable_rxchtails - sets RX dmac chain tail addresses
- * @card: card structure
- *
- * spider_net_enable_rxchtails sets the RX DMAC chain tail addresses in the
- * chip by writing to the appropriate register. DMA is enabled in
- * spider_net_enable_rxdmac.
- */
-static inline void
-spider_net_enable_rxchtails(struct spider_net_card *card)
-{
-	/* assume chain is aligned correctly */
-	spider_net_write_reg(card, SPIDER_NET_GDADCHA ,
-			     card->rx_chain.tail->bus_addr);
-}
-
-/**
- * spider_net_enable_rxdmac - enables a receive DMA controller
- * @card: card structure
- *
- * spider_net_enable_rxdmac enables the DMA controller by setting RX_DMA_EN
- * in the GDADMACCNTR register
- */
-static inline void
-spider_net_enable_rxdmac(struct spider_net_card *card)
-{
-	wmb();
-	spider_net_write_reg(card, SPIDER_NET_GDADMACCNTR,
-			     SPIDER_NET_DMA_RX_VALUE);
-}
-
-/**
- * spider_net_disable_rxdmac - disables the receive DMA controller
- * @card: card structure
- *
- * spider_net_disable_rxdmac terminates processing on the DMA controller
- * by turing off the DMA controller, with the force-end flag set.
- */
-static inline void
-spider_net_disable_rxdmac(struct spider_net_card *card)
-{
-	spider_net_write_reg(card, SPIDER_NET_GDADMACCNTR,
-			     SPIDER_NET_DMA_RX_FEND_VALUE);
-}
-
-/**
- * spider_net_refill_rx_chain - refills descriptors/skbs in the rx chains
- * @card: card structure
- *
- * refills descriptors in the rx chain: allocates skbs and iommu-maps them.
- */
-static void
-spider_net_refill_rx_chain(struct spider_net_card *card)
-{
-	struct spider_net_descr_chain *chain = &card->rx_chain;
-	unsigned long flags;
-
-	/* one context doing the refill (and a second context seeing that
-	 * and omitting it) is ok. If called by NAPI, we'll be called again
-	 * as spider_net_decode_one_descr is called several times. If some
-	 * interrupt calls us, the NAPI is about to clean up anyway.
-	 */
-	if (!spin_trylock_irqsave(&chain->lock, flags))
-		return;
-
-	while (spider_net_get_descr_status(chain->head->hwdescr) ==
-			SPIDER_NET_DESCR_NOT_IN_USE) {
-		if (spider_net_prepare_rx_descr(card, chain->head))
-			break;
-		chain->head = chain->head->next;
-	}
-
-	spin_unlock_irqrestore(&chain->lock, flags);
-}
-
-/**
- * spider_net_alloc_rx_skbs - Allocates rx skbs in rx descriptor chains
- * @card: card structure
- *
- * Returns 0 on success, <0 on failure.
- */
-static int
-spider_net_alloc_rx_skbs(struct spider_net_card *card)
-{
-	struct spider_net_descr_chain *chain = &card->rx_chain;
-	struct spider_net_descr *start = chain->tail;
-	struct spider_net_descr *descr = start;
-
-	/* Link up the hardware chain pointers */
-	do {
-		descr->prev->hwdescr->next_descr_addr = descr->bus_addr;
-		descr = descr->next;
-	} while (descr != start);
-
-	/* Put at least one buffer into the chain. if this fails,
-	 * we've got a problem. If not, spider_net_refill_rx_chain
-	 * will do the rest at the end of this function.
-	 */
-	if (spider_net_prepare_rx_descr(card, chain->head))
-		goto error;
-	else
-		chain->head = chain->head->next;
-
-	/* This will allocate the rest of the rx buffers;
-	 * if not, it's business as usual later on.
-	 */
-	spider_net_refill_rx_chain(card);
-	spider_net_enable_rxdmac(card);
-	return 0;
-
-error:
-	spider_net_free_rx_chain_contents(card);
-	return -ENOMEM;
-}
-
-/**
- * spider_net_get_multicast_hash - generates hash for multicast filter table
- * @netdev: interface device structure
- * @addr: multicast address
- *
- * returns the hash value.
- *
- * spider_net_get_multicast_hash calculates a hash value for a given multicast
- * address, that is used to set the multicast filter tables
- */
-static u8
-spider_net_get_multicast_hash(struct net_device *netdev, __u8 *addr)
-{
-	u32 crc;
-	u8 hash;
-	char addr_for_crc[ETH_ALEN] = { 0, };
-	int i, bit;
-
-	for (i = 0; i < ETH_ALEN * 8; i++) {
-		bit = (addr[i / 8] >> (i % 8)) & 1;
-		addr_for_crc[ETH_ALEN - 1 - i / 8] += bit << (7 - (i % 8));
-	}
-
-	crc = crc32_be(~0, addr_for_crc, netdev->addr_len);
-
-	hash = (crc >> 27);
-	hash <<= 3;
-	hash |= crc & 7;
-	hash &= 0xff;
-
-	return hash;
-}
-
-/**
- * spider_net_set_multi - sets multicast addresses and promisc flags
- * @netdev: interface device structure
- *
- * spider_net_set_multi configures multicast addresses as needed for the
- * netdev interface. It also sets up multicast, allmulti and promisc
- * flags appropriately
- */
-static void
-spider_net_set_multi(struct net_device *netdev)
-{
-	struct netdev_hw_addr *ha;
-	u8 hash;
-	int i;
-	u32 reg;
-	struct spider_net_card *card = netdev_priv(netdev);
-	DECLARE_BITMAP(bitmask, SPIDER_NET_MULTICAST_HASHES);
-
-	spider_net_set_promisc(card);
-
-	if (netdev->flags & IFF_ALLMULTI) {
-		bitmap_fill(bitmask, SPIDER_NET_MULTICAST_HASHES);
-		goto write_hash;
-	}
-
-	bitmap_zero(bitmask, SPIDER_NET_MULTICAST_HASHES);
-
-	/* well, we know, what the broadcast hash value is: it's xfd
-	hash = spider_net_get_multicast_hash(netdev, netdev->broadcast); */
-	__set_bit(0xfd, bitmask);
-
-	netdev_for_each_mc_addr(ha, netdev) {
-		hash = spider_net_get_multicast_hash(netdev, ha->addr);
-		__set_bit(hash, bitmask);
-	}
-
-write_hash:
-	for (i = 0; i < SPIDER_NET_MULTICAST_HASHES / 4; i++) {
-		reg = 0;
-		if (test_bit(i * 4, bitmask))
-			reg += 0x08;
-		reg <<= 8;
-		if (test_bit(i * 4 + 1, bitmask))
-			reg += 0x08;
-		reg <<= 8;
-		if (test_bit(i * 4 + 2, bitmask))
-			reg += 0x08;
-		reg <<= 8;
-		if (test_bit(i * 4 + 3, bitmask))
-			reg += 0x08;
-
-		spider_net_write_reg(card, SPIDER_NET_GMRMHFILnR + i * 4, reg);
-	}
-}
-
-/**
- * spider_net_prepare_tx_descr - fill tx descriptor with skb data
- * @card: card structure
- * @skb: packet to use
- *
- * returns 0 on success, <0 on failure.
- *
- * fills out the descriptor structure with skb data and len. Copies data,
- * if needed (32bit DMA!)
- */
-static int
-spider_net_prepare_tx_descr(struct spider_net_card *card,
-			    struct sk_buff *skb)
-{
-	struct spider_net_descr_chain *chain = &card->tx_chain;
-	struct spider_net_descr *descr;
-	struct spider_net_hw_descr *hwdescr;
-	dma_addr_t buf;
-	unsigned long flags;
-
-	buf = dma_map_single(&card->pdev->dev, skb->data, skb->len,
-			     DMA_TO_DEVICE);
-	if (dma_mapping_error(&card->pdev->dev, buf)) {
-		if (netif_msg_tx_err(card) && net_ratelimit())
-			dev_err(&card->netdev->dev, "could not iommu-map packet (%p, %i). "
-				  "Dropping packet\n", skb->data, skb->len);
-		card->spider_stats.tx_iommu_map_error++;
-		return -ENOMEM;
-	}
-
-	spin_lock_irqsave(&chain->lock, flags);
-	descr = card->tx_chain.head;
-	if (descr->next == chain->tail->prev) {
-		spin_unlock_irqrestore(&chain->lock, flags);
-		dma_unmap_single(&card->pdev->dev, buf, skb->len,
-				 DMA_TO_DEVICE);
-		return -ENOMEM;
-	}
-	hwdescr = descr->hwdescr;
-	chain->head = descr->next;
-
-	descr->skb = skb;
-	hwdescr->buf_addr = buf;
-	hwdescr->buf_size = skb->len;
-	hwdescr->next_descr_addr = 0;
-	hwdescr->data_status = 0;
-
-	hwdescr->dmac_cmd_status =
-			SPIDER_NET_DESCR_CARDOWNED | SPIDER_NET_DMAC_TXFRMTL;
-	spin_unlock_irqrestore(&chain->lock, flags);
-
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		switch (ip_hdr(skb)->protocol) {
-		case IPPROTO_TCP:
-			hwdescr->dmac_cmd_status |= SPIDER_NET_DMAC_TCP;
-			break;
-		case IPPROTO_UDP:
-			hwdescr->dmac_cmd_status |= SPIDER_NET_DMAC_UDP;
-			break;
-		}
-
-	/* Chain the bus address, so that the DMA engine finds this descr. */
-	wmb();
-	descr->prev->hwdescr->next_descr_addr = descr->bus_addr;
-
-	netif_trans_update(card->netdev); /* set netdev watchdog timer */
-	return 0;
-}
-
-static int
-spider_net_set_low_watermark(struct spider_net_card *card)
-{
-	struct spider_net_descr *descr = card->tx_chain.tail;
-	struct spider_net_hw_descr *hwdescr;
-	unsigned long flags;
-	int status;
-	int cnt=0;
-	int i;
-
-	/* Measure the length of the queue. Measurement does not
-	 * need to be precise -- does not need a lock.
-	 */
-	while (descr != card->tx_chain.head) {
-		status = descr->hwdescr->dmac_cmd_status & SPIDER_NET_DESCR_NOT_IN_USE;
-		if (status == SPIDER_NET_DESCR_NOT_IN_USE)
-			break;
-		descr = descr->next;
-		cnt++;
-	}
-
-	/* If TX queue is short, don't even bother with interrupts */
-	if (cnt < card->tx_chain.num_desc/4)
-		return cnt;
-
-	/* Set low-watermark 3/4th's of the way into the queue. */
-	descr = card->tx_chain.tail;
-	cnt = (cnt*3)/4;
-	for (i=0;i<cnt; i++)
-		descr = descr->next;
-
-	/* Set the new watermark, clear the old watermark */
-	spin_lock_irqsave(&card->tx_chain.lock, flags);
-	descr->hwdescr->dmac_cmd_status |= SPIDER_NET_DESCR_TXDESFLG;
-	if (card->low_watermark && card->low_watermark != descr) {
-		hwdescr = card->low_watermark->hwdescr;
-		hwdescr->dmac_cmd_status =
-		     hwdescr->dmac_cmd_status & ~SPIDER_NET_DESCR_TXDESFLG;
-	}
-	card->low_watermark = descr;
-	spin_unlock_irqrestore(&card->tx_chain.lock, flags);
-	return cnt;
-}
-
-/**
- * spider_net_release_tx_chain - processes sent tx descriptors
- * @card: adapter structure
- * @brutal: if set, don't care about whether descriptor seems to be in use
- *
- * returns 0 if the tx ring is empty, otherwise 1.
- *
- * spider_net_release_tx_chain releases the tx descriptors that spider has
- * finished with (if non-brutal) or simply release tx descriptors (if brutal).
- * If some other context is calling this function, we return 1 so that we're
- * scheduled again (if we were scheduled) and will not lose initiative.
- */
-static int
-spider_net_release_tx_chain(struct spider_net_card *card, int brutal)
-{
-	struct net_device *dev = card->netdev;
-	struct spider_net_descr_chain *chain = &card->tx_chain;
-	struct spider_net_descr *descr;
-	struct spider_net_hw_descr *hwdescr;
-	struct sk_buff *skb;
-	u32 buf_addr;
-	unsigned long flags;
-	int status;
-
-	while (1) {
-		spin_lock_irqsave(&chain->lock, flags);
-		if (chain->tail == chain->head) {
-			spin_unlock_irqrestore(&chain->lock, flags);
-			return 0;
-		}
-		descr = chain->tail;
-		hwdescr = descr->hwdescr;
-
-		status = spider_net_get_descr_status(hwdescr);
-		switch (status) {
-		case SPIDER_NET_DESCR_COMPLETE:
-			dev->stats.tx_packets++;
-			dev->stats.tx_bytes += descr->skb->len;
-			break;
-
-		case SPIDER_NET_DESCR_CARDOWNED:
-			if (!brutal) {
-				spin_unlock_irqrestore(&chain->lock, flags);
-				return 1;
-			}
-
-			/* fallthrough, if we release the descriptors
-			 * brutally (then we don't care about
-			 * SPIDER_NET_DESCR_CARDOWNED)
-			 */
-			fallthrough;
-
-		case SPIDER_NET_DESCR_RESPONSE_ERROR:
-		case SPIDER_NET_DESCR_PROTECTION_ERROR:
-		case SPIDER_NET_DESCR_FORCE_END:
-			if (netif_msg_tx_err(card))
-				dev_err(&card->netdev->dev, "forcing end of tx descriptor "
-				       "with status x%02x\n", status);
-			dev->stats.tx_errors++;
-			break;
-
-		default:
-			dev->stats.tx_dropped++;
-			if (!brutal) {
-				spin_unlock_irqrestore(&chain->lock, flags);
-				return 1;
-			}
-		}
-
-		chain->tail = descr->next;
-		hwdescr->dmac_cmd_status |= SPIDER_NET_DESCR_NOT_IN_USE;
-		skb = descr->skb;
-		descr->skb = NULL;
-		buf_addr = hwdescr->buf_addr;
-		spin_unlock_irqrestore(&chain->lock, flags);
-
-		/* unmap the skb */
-		if (skb) {
-			dma_unmap_single(&card->pdev->dev, buf_addr, skb->len,
-					 DMA_TO_DEVICE);
-			dev_consume_skb_any(skb);
-		}
-	}
-	return 0;
-}
-
-/**
- * spider_net_kick_tx_dma - enables TX DMA processing
- * @card: card structure
- *
- * This routine will start the transmit DMA running if
- * it is not already running. This routine ned only be
- * called when queueing a new packet to an empty tx queue.
- * Writes the current tx chain head as start address
- * of the tx descriptor chain and enables the transmission
- * DMA engine.
- */
-static inline void
-spider_net_kick_tx_dma(struct spider_net_card *card)
-{
-	struct spider_net_descr *descr;
-
-	if (spider_net_read_reg(card, SPIDER_NET_GDTDMACCNTR) &
-			SPIDER_NET_TX_DMA_EN)
-		goto out;
-
-	descr = card->tx_chain.tail;
-	for (;;) {
-		if (spider_net_get_descr_status(descr->hwdescr) ==
-				SPIDER_NET_DESCR_CARDOWNED) {
-			spider_net_write_reg(card, SPIDER_NET_GDTDCHA,
-					descr->bus_addr);
-			spider_net_write_reg(card, SPIDER_NET_GDTDMACCNTR,
-					SPIDER_NET_DMA_TX_VALUE);
-			break;
-		}
-		if (descr == card->tx_chain.head)
-			break;
-		descr = descr->next;
-	}
-
-out:
-	mod_timer(&card->tx_timer, jiffies + SPIDER_NET_TX_TIMER);
-}
-
-/**
- * spider_net_xmit - transmits a frame over the device
- * @skb: packet to send out
- * @netdev: interface device structure
- *
- * returns NETDEV_TX_OK on success, NETDEV_TX_BUSY on failure
- */
-static netdev_tx_t
-spider_net_xmit(struct sk_buff *skb, struct net_device *netdev)
-{
-	int cnt;
-	struct spider_net_card *card = netdev_priv(netdev);
-
-	spider_net_release_tx_chain(card, 0);
-
-	if (spider_net_prepare_tx_descr(card, skb) != 0) {
-		netdev->stats.tx_dropped++;
-		netif_stop_queue(netdev);
-		return NETDEV_TX_BUSY;
-	}
-
-	cnt = spider_net_set_low_watermark(card);
-	if (cnt < 5)
-		spider_net_kick_tx_dma(card);
-	return NETDEV_TX_OK;
-}
-
-/**
- * spider_net_cleanup_tx_ring - cleans up the TX ring
- * @t: timer context used to obtain the pointer to net card data structure
- *
- * spider_net_cleanup_tx_ring is called by either the tx_timer
- * or from the NAPI polling routine.
- * This routine releases resources associted with transmitted
- * packets, including updating the queue tail pointer.
- */
-static void
-spider_net_cleanup_tx_ring(struct timer_list *t)
-{
-	struct spider_net_card *card = from_timer(card, t, tx_timer);
-	if ((spider_net_release_tx_chain(card, 0) != 0) &&
-	    (card->netdev->flags & IFF_UP)) {
-		spider_net_kick_tx_dma(card);
-		netif_wake_queue(card->netdev);
-	}
-}
-
-/**
- * spider_net_do_ioctl - called for device ioctls
- * @netdev: interface device structure
- * @ifr: request parameter structure for ioctl
- * @cmd: command code for ioctl
- *
- * returns 0 on success, <0 on failure. Currently, we have no special ioctls.
- * -EOPNOTSUPP is returned, if an unknown ioctl was requested
- */
-static int
-spider_net_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-/**
- * spider_net_pass_skb_up - takes an skb from a descriptor and passes it on
- * @descr: descriptor to process
- * @card: card structure
- *
- * Fills out skb structure and passes the data to the stack.
- * The descriptor state is not changed.
- */
-static void
-spider_net_pass_skb_up(struct spider_net_descr *descr,
-		       struct spider_net_card *card)
-{
-	struct spider_net_hw_descr *hwdescr = descr->hwdescr;
-	struct sk_buff *skb = descr->skb;
-	struct net_device *netdev = card->netdev;
-	u32 data_status = hwdescr->data_status;
-	u32 data_error = hwdescr->data_error;
-
-	skb_put(skb, hwdescr->valid_size);
-
-	/* the card seems to add 2 bytes of junk in front
-	 * of the ethernet frame
-	 */
-#define SPIDER_MISALIGN		2
-	skb_pull(skb, SPIDER_MISALIGN);
-	skb->protocol = eth_type_trans(skb, netdev);
-
-	/* checksum offload */
-	skb_checksum_none_assert(skb);
-	if (netdev->features & NETIF_F_RXCSUM) {
-		if ( ( (data_status & SPIDER_NET_DATA_STATUS_CKSUM_MASK) ==
-		       SPIDER_NET_DATA_STATUS_CKSUM_MASK) &&
-		     !(data_error & SPIDER_NET_DATA_ERR_CKSUM_MASK))
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-	}
-
-	if (data_status & SPIDER_NET_VLAN_PACKET) {
-		/* further enhancements: HW-accel VLAN */
-	}
-
-	/* update netdevice statistics */
-	netdev->stats.rx_packets++;
-	netdev->stats.rx_bytes += skb->len;
-
-	/* pass skb up to stack */
-	netif_receive_skb(skb);
-}
-
-static void show_rx_chain(struct spider_net_card *card)
-{
-	struct spider_net_descr_chain *chain = &card->rx_chain;
-	struct spider_net_descr *start= chain->tail;
-	struct spider_net_descr *descr= start;
-	struct spider_net_hw_descr *hwd = start->hwdescr;
-	struct device *dev = &card->netdev->dev;
-	u32 curr_desc, next_desc;
-	int status;
-
-	int tot = 0;
-	int cnt = 0;
-	int off = start - chain->ring;
-	int cstat = hwd->dmac_cmd_status;
-
-	dev_info(dev, "Total number of descrs=%d\n",
-		chain->num_desc);
-	dev_info(dev, "Chain tail located at descr=%d, status=0x%x\n",
-		off, cstat);
-
-	curr_desc = spider_net_read_reg(card, SPIDER_NET_GDACTDPA);
-	next_desc = spider_net_read_reg(card, SPIDER_NET_GDACNEXTDA);
-
-	status = cstat;
-	do
-	{
-		hwd = descr->hwdescr;
-		off = descr - chain->ring;
-		status = hwd->dmac_cmd_status;
-
-		if (descr == chain->head)
-			dev_info(dev, "Chain head is at %d, head status=0x%x\n",
-			         off, status);
-
-		if (curr_desc == descr->bus_addr)
-			dev_info(dev, "HW curr desc (GDACTDPA) is at %d, status=0x%x\n",
-			         off, status);
-
-		if (next_desc == descr->bus_addr)
-			dev_info(dev, "HW next desc (GDACNEXTDA) is at %d, status=0x%x\n",
-			         off, status);
-
-		if (hwd->next_descr_addr == 0)
-			dev_info(dev, "chain is cut at %d\n", off);
-
-		if (cstat != status) {
-			int from = (chain->num_desc + off - cnt) % chain->num_desc;
-			int to = (chain->num_desc + off - 1) % chain->num_desc;
-			dev_info(dev, "Have %d (from %d to %d) descrs "
-			         "with stat=0x%08x\n", cnt, from, to, cstat);
-			cstat = status;
-			cnt = 0;
-		}
-
-		cnt ++;
-		tot ++;
-		descr = descr->next;
-	} while (descr != start);
-
-	dev_info(dev, "Last %d descrs with stat=0x%08x "
-	         "for a total of %d descrs\n", cnt, cstat, tot);
-
-#ifdef DEBUG
-	/* Now dump the whole ring */
-	descr = start;
-	do
-	{
-		struct spider_net_hw_descr *hwd = descr->hwdescr;
-		status = spider_net_get_descr_status(hwd);
-		cnt = descr - chain->ring;
-		dev_info(dev, "Descr %d stat=0x%08x skb=%p\n",
-		         cnt, status, descr->skb);
-		dev_info(dev, "bus addr=%08x buf addr=%08x sz=%d\n",
-		         descr->bus_addr, hwd->buf_addr, hwd->buf_size);
-		dev_info(dev, "next=%08x result sz=%d valid sz=%d\n",
-		         hwd->next_descr_addr, hwd->result_size,
-		         hwd->valid_size);
-		dev_info(dev, "dmac=%08x data stat=%08x data err=%08x\n",
-		         hwd->dmac_cmd_status, hwd->data_status,
-		         hwd->data_error);
-		dev_info(dev, "\n");
-
-		descr = descr->next;
-	} while (descr != start);
-#endif
-
-}
-
-/**
- * spider_net_resync_head_ptr - Advance head ptr past empty descrs
- * @card: card structure
- *
- * If the driver fails to keep up and empty the queue, then the
- * hardware wil run out of room to put incoming packets. This
- * will cause the hardware to skip descrs that are full (instead
- * of halting/retrying). Thus, once the driver runs, it wil need
- * to "catch up" to where the hardware chain pointer is at.
- */
-static void spider_net_resync_head_ptr(struct spider_net_card *card)
-{
-	unsigned long flags;
-	struct spider_net_descr_chain *chain = &card->rx_chain;
-	struct spider_net_descr *descr;
-	int i, status;
-
-	/* Advance head pointer past any empty descrs */
-	descr = chain->head;
-	status = spider_net_get_descr_status(descr->hwdescr);
-
-	if (status == SPIDER_NET_DESCR_NOT_IN_USE)
-		return;
-
-	spin_lock_irqsave(&chain->lock, flags);
-
-	descr = chain->head;
-	status = spider_net_get_descr_status(descr->hwdescr);
-	for (i=0; i<chain->num_desc; i++) {
-		if (status != SPIDER_NET_DESCR_CARDOWNED) break;
-		descr = descr->next;
-		status = spider_net_get_descr_status(descr->hwdescr);
-	}
-	chain->head = descr;
-
-	spin_unlock_irqrestore(&chain->lock, flags);
-}
-
-static int spider_net_resync_tail_ptr(struct spider_net_card *card)
-{
-	struct spider_net_descr_chain *chain = &card->rx_chain;
-	struct spider_net_descr *descr;
-	int i, status;
-
-	/* Advance tail pointer past any empty and reaped descrs */
-	descr = chain->tail;
-	status = spider_net_get_descr_status(descr->hwdescr);
-
-	for (i=0; i<chain->num_desc; i++) {
-		if ((status != SPIDER_NET_DESCR_CARDOWNED) &&
-		    (status != SPIDER_NET_DESCR_NOT_IN_USE)) break;
-		descr = descr->next;
-		status = spider_net_get_descr_status(descr->hwdescr);
-	}
-	chain->tail = descr;
-
-	if ((i == chain->num_desc) || (i == 0))
-		return 1;
-	return 0;
-}
-
-/**
- * spider_net_decode_one_descr - processes an RX descriptor
- * @card: card structure
- *
- * Returns 1 if a packet has been sent to the stack, otherwise 0.
- *
- * Processes an RX descriptor by iommu-unmapping the data buffer
- * and passing the packet up to the stack. This function is called
- * in softirq context, e.g. either bottom half from interrupt or
- * NAPI polling context.
- */
-static int
-spider_net_decode_one_descr(struct spider_net_card *card)
-{
-	struct net_device *dev = card->netdev;
-	struct spider_net_descr_chain *chain = &card->rx_chain;
-	struct spider_net_descr *descr = chain->tail;
-	struct spider_net_hw_descr *hwdescr = descr->hwdescr;
-	u32 hw_buf_addr;
-	int status;
-
-	status = spider_net_get_descr_status(hwdescr);
-
-	/* Nothing in the descriptor, or ring must be empty */
-	if ((status == SPIDER_NET_DESCR_CARDOWNED) ||
-	    (status == SPIDER_NET_DESCR_NOT_IN_USE))
-		return 0;
-
-	/* descriptor definitively used -- move on tail */
-	chain->tail = descr->next;
-
-	/* unmap descriptor */
-	hw_buf_addr = hwdescr->buf_addr;
-	hwdescr->buf_addr = 0xffffffff;
-	dma_unmap_single(&card->pdev->dev, hw_buf_addr, SPIDER_NET_MAX_FRAME,
-			 DMA_FROM_DEVICE);
-
-	if ( (status == SPIDER_NET_DESCR_RESPONSE_ERROR) ||
-	     (status == SPIDER_NET_DESCR_PROTECTION_ERROR) ||
-	     (status == SPIDER_NET_DESCR_FORCE_END) ) {
-		if (netif_msg_rx_err(card))
-			dev_err(&dev->dev,
-			       "dropping RX descriptor with state %d\n", status);
-		dev->stats.rx_dropped++;
-		goto bad_desc;
-	}
-
-	if ( (status != SPIDER_NET_DESCR_COMPLETE) &&
-	     (status != SPIDER_NET_DESCR_FRAME_END) ) {
-		if (netif_msg_rx_err(card))
-			dev_err(&card->netdev->dev,
-			       "RX descriptor with unknown state %d\n", status);
-		card->spider_stats.rx_desc_unk_state++;
-		goto bad_desc;
-	}
-
-	/* The cases we'll throw away the packet immediately */
-	if (hwdescr->data_error & SPIDER_NET_DESTROY_RX_FLAGS) {
-		if (netif_msg_rx_err(card))
-			dev_err(&card->netdev->dev,
-			       "error in received descriptor found, "
-			       "data_status=x%08x, data_error=x%08x\n",
-			       hwdescr->data_status, hwdescr->data_error);
-		goto bad_desc;
-	}
-
-	if (hwdescr->dmac_cmd_status & SPIDER_NET_DESCR_BAD_STATUS) {
-		dev_err(&card->netdev->dev, "bad status, cmd_status=x%08x\n",
-			       hwdescr->dmac_cmd_status);
-		pr_err("buf_addr=x%08x\n", hw_buf_addr);
-		pr_err("buf_size=x%08x\n", hwdescr->buf_size);
-		pr_err("next_descr_addr=x%08x\n", hwdescr->next_descr_addr);
-		pr_err("result_size=x%08x\n", hwdescr->result_size);
-		pr_err("valid_size=x%08x\n", hwdescr->valid_size);
-		pr_err("data_status=x%08x\n", hwdescr->data_status);
-		pr_err("data_error=x%08x\n", hwdescr->data_error);
-		pr_err("which=%ld\n", descr - card->rx_chain.ring);
-
-		card->spider_stats.rx_desc_error++;
-		goto bad_desc;
-	}
-
-	/* Ok, we've got a packet in descr */
-	spider_net_pass_skb_up(descr, card);
-	descr->skb = NULL;
-	hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
-	return 1;
-
-bad_desc:
-	if (netif_msg_rx_err(card))
-		show_rx_chain(card);
-	dev_kfree_skb_irq(descr->skb);
-	descr->skb = NULL;
-	hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
-	return 0;
-}
-
-/**
- * spider_net_poll - NAPI poll function called by the stack to return packets
- * @napi: napi device structure
- * @budget: number of packets we can pass to the stack at most
- *
- * returns 0 if no more packets available to the driver/stack. Returns 1,
- * if the quota is exceeded, but the driver has still packets.
- *
- * spider_net_poll returns all packets from the rx descriptors to the stack
- * (using netif_receive_skb). If all/enough packets are up, the driver
- * reenables interrupts and returns 0. If not, 1 is returned.
- */
-static int spider_net_poll(struct napi_struct *napi, int budget)
-{
-	struct spider_net_card *card = container_of(napi, struct spider_net_card, napi);
-	int packets_done = 0;
-
-	while (packets_done < budget) {
-		if (!spider_net_decode_one_descr(card))
-			break;
-
-		packets_done++;
-	}
-
-	if ((packets_done == 0) && (card->num_rx_ints != 0)) {
-		if (!spider_net_resync_tail_ptr(card))
-			packets_done = budget;
-		spider_net_resync_head_ptr(card);
-	}
-	card->num_rx_ints = 0;
-
-	spider_net_refill_rx_chain(card);
-	spider_net_enable_rxdmac(card);
-
-	spider_net_cleanup_tx_ring(&card->tx_timer);
-
-	/* if all packets are in the stack, enable interrupts and return 0 */
-	/* if not, return 1 */
-	if (packets_done < budget) {
-		napi_complete_done(napi, packets_done);
-		spider_net_rx_irq_on(card);
-		card->ignore_rx_ramfull = 0;
-	}
-
-	return packets_done;
-}
-
-/**
- * spider_net_set_mac - sets the MAC of an interface
- * @netdev: interface device structure
- * @p: pointer to new MAC address
- *
- * Returns 0 on success, <0 on failure. Currently, we don't support this
- * and will always return EOPNOTSUPP.
- */
-static int
-spider_net_set_mac(struct net_device *netdev, void *p)
-{
-	struct spider_net_card *card = netdev_priv(netdev);
-	u32 macl, macu, regvalue;
-	struct sockaddr *addr = p;
-
-	if (!is_valid_ether_addr(addr->sa_data))
-		return -EADDRNOTAVAIL;
-
-	eth_hw_addr_set(netdev, addr->sa_data);
-
-	/* switch off GMACTPE and GMACRPE */
-	regvalue = spider_net_read_reg(card, SPIDER_NET_GMACOPEMD);
-	regvalue &= ~((1 << 5) | (1 << 6));
-	spider_net_write_reg(card, SPIDER_NET_GMACOPEMD, regvalue);
-
-	/* write mac */
-	macu = (netdev->dev_addr[0]<<24) + (netdev->dev_addr[1]<<16) +
-		(netdev->dev_addr[2]<<8) + (netdev->dev_addr[3]);
-	macl = (netdev->dev_addr[4]<<8) + (netdev->dev_addr[5]);
-	spider_net_write_reg(card, SPIDER_NET_GMACUNIMACU, macu);
-	spider_net_write_reg(card, SPIDER_NET_GMACUNIMACL, macl);
-
-	/* switch GMACTPE and GMACRPE back on */
-	regvalue = spider_net_read_reg(card, SPIDER_NET_GMACOPEMD);
-	regvalue |= ((1 << 5) | (1 << 6));
-	spider_net_write_reg(card, SPIDER_NET_GMACOPEMD, regvalue);
-
-	spider_net_set_promisc(card);
-
-	return 0;
-}
-
-/**
- * spider_net_link_reset
- * @netdev: net device structure
- *
- * This is called when the PHY_LINK signal is asserted. For the blade this is
- * not connected so we should never get here.
- *
- */
-static void
-spider_net_link_reset(struct net_device *netdev)
-{
-
-	struct spider_net_card *card = netdev_priv(netdev);
-
-	del_timer_sync(&card->aneg_timer);
-
-	/* clear interrupt, block further interrupts */
-	spider_net_write_reg(card, SPIDER_NET_GMACST,
-			     spider_net_read_reg(card, SPIDER_NET_GMACST));
-	spider_net_write_reg(card, SPIDER_NET_GMACINTEN, 0);
-
-	/* reset phy and setup aneg */
-	card->aneg_count = 0;
-	card->medium = BCM54XX_COPPER;
-	spider_net_setup_aneg(card);
-	mod_timer(&card->aneg_timer, jiffies + SPIDER_NET_ANEG_TIMER);
-
-}
-
-/**
- * spider_net_handle_error_irq - handles errors raised by an interrupt
- * @card: card structure
- * @status_reg: interrupt status register 0 (GHIINT0STS)
- * @error_reg1: interrupt status register 1 (GHIINT1STS)
- * @error_reg2: interrupt status register 2 (GHIINT2STS)
- *
- * spider_net_handle_error_irq treats or ignores all error conditions
- * found when an interrupt is presented
- */
-static void
-spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg,
-			    u32 error_reg1, u32 error_reg2)
-{
-	u32 i;
-	int show_error = 1;
-
-	/* check GHIINT0STS ************************************/
-	if (status_reg)
-		for (i = 0; i < 32; i++)
-			if (status_reg & (1<<i))
-				switch (i)
-	{
-	/* let error_reg1 and error_reg2 evaluation decide, what to do
-	case SPIDER_NET_PHYINT:
-	case SPIDER_NET_GMAC2INT:
-	case SPIDER_NET_GMAC1INT:
-	case SPIDER_NET_GFIFOINT:
-	case SPIDER_NET_DMACINT:
-	case SPIDER_NET_GSYSINT:
-		break; */
-
-	case SPIDER_NET_GIPSINT:
-		show_error = 0;
-		break;
-
-	case SPIDER_NET_GPWOPCMPINT:
-		/* PHY write operation completed */
-		show_error = 0;
-		break;
-	case SPIDER_NET_GPROPCMPINT:
-		/* PHY read operation completed */
-		/* we don't use semaphores, as we poll for the completion
-		 * of the read operation in spider_net_read_phy. Should take
-		 * about 50 us
-		 */
-		show_error = 0;
-		break;
-	case SPIDER_NET_GPWFFINT:
-		/* PHY command queue full */
-		if (netif_msg_intr(card))
-			dev_err(&card->netdev->dev, "PHY write queue full\n");
-		show_error = 0;
-		break;
-
-	/* case SPIDER_NET_GRMDADRINT: not used. print a message */
-	/* case SPIDER_NET_GRMARPINT: not used. print a message */
-	/* case SPIDER_NET_GRMMPINT: not used. print a message */
-
-	case SPIDER_NET_GDTDEN0INT:
-		/* someone has set TX_DMA_EN to 0 */
-		show_error = 0;
-		break;
-
-	case SPIDER_NET_GDDDEN0INT:
-	case SPIDER_NET_GDCDEN0INT:
-	case SPIDER_NET_GDBDEN0INT:
-	case SPIDER_NET_GDADEN0INT:
-		/* someone has set RX_DMA_EN to 0 */
-		show_error = 0;
-		break;
-
-	/* RX interrupts */
-	case SPIDER_NET_GDDFDCINT:
-	case SPIDER_NET_GDCFDCINT:
-	case SPIDER_NET_GDBFDCINT:
-	case SPIDER_NET_GDAFDCINT:
-	/* case SPIDER_NET_GDNMINT: not used. print a message */
-	/* case SPIDER_NET_GCNMINT: not used. print a message */
-	/* case SPIDER_NET_GBNMINT: not used. print a message */
-	/* case SPIDER_NET_GANMINT: not used. print a message */
-	/* case SPIDER_NET_GRFNMINT: not used. print a message */
-		show_error = 0;
-		break;
-
-	/* TX interrupts */
-	case SPIDER_NET_GDTFDCINT:
-		show_error = 0;
-		break;
-	case SPIDER_NET_GTTEDINT:
-		show_error = 0;
-		break;
-	case SPIDER_NET_GDTDCEINT:
-		/* chain end. If a descriptor should be sent, kick off
-		 * tx dma
-		if (card->tx_chain.tail != card->tx_chain.head)
-			spider_net_kick_tx_dma(card);
-		*/
-		show_error = 0;
-		break;
-
-	/* case SPIDER_NET_G1TMCNTINT: not used. print a message */
-	/* case SPIDER_NET_GFREECNTINT: not used. print a message */
-	}
-
-	/* check GHIINT1STS ************************************/
-	if (error_reg1)
-		for (i = 0; i < 32; i++)
-			if (error_reg1 & (1<<i))
-				switch (i)
-	{
-	case SPIDER_NET_GTMFLLINT:
-		/* TX RAM full may happen on a usual case.
-		 * Logging is not needed.
-		 */
-		show_error = 0;
-		break;
-	case SPIDER_NET_GRFDFLLINT:
-	case SPIDER_NET_GRFCFLLINT:
-	case SPIDER_NET_GRFBFLLINT:
-	case SPIDER_NET_GRFAFLLINT:
-	case SPIDER_NET_GRMFLLINT:
-		/* Could happen when rx chain is full */
-		if (card->ignore_rx_ramfull == 0) {
-			card->ignore_rx_ramfull = 1;
-			spider_net_resync_head_ptr(card);
-			spider_net_refill_rx_chain(card);
-			spider_net_enable_rxdmac(card);
-			card->num_rx_ints ++;
-			napi_schedule(&card->napi);
-		}
-		show_error = 0;
-		break;
-
-	/* case SPIDER_NET_GTMSHTINT: problem, print a message */
-	case SPIDER_NET_GDTINVDINT:
-		/* allrighty. tx from previous descr ok */
-		show_error = 0;
-		break;
-
-	/* chain end */
-	case SPIDER_NET_GDDDCEINT:
-	case SPIDER_NET_GDCDCEINT:
-	case SPIDER_NET_GDBDCEINT:
-	case SPIDER_NET_GDADCEINT:
-		spider_net_resync_head_ptr(card);
-		spider_net_refill_rx_chain(card);
-		spider_net_enable_rxdmac(card);
-		card->num_rx_ints ++;
-		napi_schedule(&card->napi);
-		show_error = 0;
-		break;
-
-	/* invalid descriptor */
-	case SPIDER_NET_GDDINVDINT:
-	case SPIDER_NET_GDCINVDINT:
-	case SPIDER_NET_GDBINVDINT:
-	case SPIDER_NET_GDAINVDINT:
-		/* Could happen when rx chain is full */
-		spider_net_resync_head_ptr(card);
-		spider_net_refill_rx_chain(card);
-		spider_net_enable_rxdmac(card);
-		card->num_rx_ints ++;
-		napi_schedule(&card->napi);
-		show_error = 0;
-		break;
-
-	/* case SPIDER_NET_GDTRSERINT: problem, print a message */
-	/* case SPIDER_NET_GDDRSERINT: problem, print a message */
-	/* case SPIDER_NET_GDCRSERINT: problem, print a message */
-	/* case SPIDER_NET_GDBRSERINT: problem, print a message */
-	/* case SPIDER_NET_GDARSERINT: problem, print a message */
-	/* case SPIDER_NET_GDSERINT: problem, print a message */
-	/* case SPIDER_NET_GDTPTERINT: problem, print a message */
-	/* case SPIDER_NET_GDDPTERINT: problem, print a message */
-	/* case SPIDER_NET_GDCPTERINT: problem, print a message */
-	/* case SPIDER_NET_GDBPTERINT: problem, print a message */
-	/* case SPIDER_NET_GDAPTERINT: problem, print a message */
-	default:
-		show_error = 1;
-		break;
-	}
-
-	/* check GHIINT2STS ************************************/
-	if (error_reg2)
-		for (i = 0; i < 32; i++)
-			if (error_reg2 & (1<<i))
-				switch (i)
-	{
-	/* there is nothing we can (want  to) do at this time. Log a
-	 * message, we can switch on and off the specific values later on
-	case SPIDER_NET_GPROPERINT:
-	case SPIDER_NET_GMCTCRSNGINT:
-	case SPIDER_NET_GMCTLCOLINT:
-	case SPIDER_NET_GMCTTMOTINT:
-	case SPIDER_NET_GMCRCAERINT:
-	case SPIDER_NET_GMCRCALERINT:
-	case SPIDER_NET_GMCRALNERINT:
-	case SPIDER_NET_GMCROVRINT:
-	case SPIDER_NET_GMCRRNTINT:
-	case SPIDER_NET_GMCRRXERINT:
-	case SPIDER_NET_GTITCSERINT:
-	case SPIDER_NET_GTIFMTERINT:
-	case SPIDER_NET_GTIPKTRVKINT:
-	case SPIDER_NET_GTISPINGINT:
-	case SPIDER_NET_GTISADNGINT:
-	case SPIDER_NET_GTISPDNGINT:
-	case SPIDER_NET_GRIFMTERINT:
-	case SPIDER_NET_GRIPKTRVKINT:
-	case SPIDER_NET_GRISPINGINT:
-	case SPIDER_NET_GRISADNGINT:
-	case SPIDER_NET_GRISPDNGINT:
-		break;
-	*/
-		default:
-			break;
-	}
-
-	if ((show_error) && (netif_msg_intr(card)) && net_ratelimit())
-		dev_err(&card->netdev->dev, "Error interrupt, GHIINT0STS = 0x%08x, "
-		       "GHIINT1STS = 0x%08x, GHIINT2STS = 0x%08x\n",
-		       status_reg, error_reg1, error_reg2);
-
-	/* clear interrupt sources */
-	spider_net_write_reg(card, SPIDER_NET_GHIINT1STS, error_reg1);
-	spider_net_write_reg(card, SPIDER_NET_GHIINT2STS, error_reg2);
-}
-
-/**
- * spider_net_interrupt - interrupt handler for spider_net
- * @irq: interrupt number
- * @ptr: pointer to net_device
- *
- * returns IRQ_HANDLED, if interrupt was for driver, or IRQ_NONE, if no
- * interrupt found raised by card.
- *
- * This is the interrupt handler, that turns off
- * interrupts for this device and makes the stack poll the driver
- */
-static irqreturn_t
-spider_net_interrupt(int irq, void *ptr)
-{
-	struct net_device *netdev = ptr;
-	struct spider_net_card *card = netdev_priv(netdev);
-	u32 status_reg, error_reg1, error_reg2;
-
-	status_reg = spider_net_read_reg(card, SPIDER_NET_GHIINT0STS);
-	error_reg1 = spider_net_read_reg(card, SPIDER_NET_GHIINT1STS);
-	error_reg2 = spider_net_read_reg(card, SPIDER_NET_GHIINT2STS);
-
-	if (!(status_reg & SPIDER_NET_INT0_MASK_VALUE) &&
-	    !(error_reg1 & SPIDER_NET_INT1_MASK_VALUE) &&
-	    !(error_reg2 & SPIDER_NET_INT2_MASK_VALUE))
-		return IRQ_NONE;
-
-	if (status_reg & SPIDER_NET_RXINT ) {
-		spider_net_rx_irq_off(card);
-		napi_schedule(&card->napi);
-		card->num_rx_ints ++;
-	}
-	if (status_reg & SPIDER_NET_TXINT)
-		napi_schedule(&card->napi);
-
-	if (status_reg & SPIDER_NET_LINKINT)
-		spider_net_link_reset(netdev);
-
-	if (status_reg & SPIDER_NET_ERRINT )
-		spider_net_handle_error_irq(card, status_reg,
-					    error_reg1, error_reg2);
-
-	/* clear interrupt sources */
-	spider_net_write_reg(card, SPIDER_NET_GHIINT0STS, status_reg);
-
-	return IRQ_HANDLED;
-}
-
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/**
- * spider_net_poll_controller - artificial interrupt for netconsole etc.
- * @netdev: interface device structure
- *
- * see Documentation/networking/netconsole.rst
- */
-static void
-spider_net_poll_controller(struct net_device *netdev)
-{
-	disable_irq(netdev->irq);
-	spider_net_interrupt(netdev->irq, netdev);
-	enable_irq(netdev->irq);
-}
-#endif /* CONFIG_NET_POLL_CONTROLLER */
-
-/**
- * spider_net_enable_interrupts - enable interrupts
- * @card: card structure
- *
- * spider_net_enable_interrupt enables several interrupts
- */
-static void
-spider_net_enable_interrupts(struct spider_net_card *card)
-{
-	spider_net_write_reg(card, SPIDER_NET_GHIINT0MSK,
-			     SPIDER_NET_INT0_MASK_VALUE);
-	spider_net_write_reg(card, SPIDER_NET_GHIINT1MSK,
-			     SPIDER_NET_INT1_MASK_VALUE);
-	spider_net_write_reg(card, SPIDER_NET_GHIINT2MSK,
-			     SPIDER_NET_INT2_MASK_VALUE);
-}
-
-/**
- * spider_net_disable_interrupts - disable interrupts
- * @card: card structure
- *
- * spider_net_disable_interrupts disables all the interrupts
- */
-static void
-spider_net_disable_interrupts(struct spider_net_card *card)
-{
-	spider_net_write_reg(card, SPIDER_NET_GHIINT0MSK, 0);
-	spider_net_write_reg(card, SPIDER_NET_GHIINT1MSK, 0);
-	spider_net_write_reg(card, SPIDER_NET_GHIINT2MSK, 0);
-	spider_net_write_reg(card, SPIDER_NET_GMACINTEN, 0);
-}
-
-/**
- * spider_net_init_card - initializes the card
- * @card: card structure
- *
- * spider_net_init_card initializes the card so that other registers can
- * be used
- */
-static void
-spider_net_init_card(struct spider_net_card *card)
-{
-	spider_net_write_reg(card, SPIDER_NET_CKRCTRL,
-			     SPIDER_NET_CKRCTRL_STOP_VALUE);
-
-	spider_net_write_reg(card, SPIDER_NET_CKRCTRL,
-			     SPIDER_NET_CKRCTRL_RUN_VALUE);
-
-	/* trigger ETOMOD signal */
-	spider_net_write_reg(card, SPIDER_NET_GMACOPEMD,
-		spider_net_read_reg(card, SPIDER_NET_GMACOPEMD) | 0x4);
-
-	spider_net_disable_interrupts(card);
-}
-
-/**
- * spider_net_enable_card - enables the card by setting all kinds of regs
- * @card: card structure
- *
- * spider_net_enable_card sets a lot of SMMIO registers to enable the device
- */
-static void
-spider_net_enable_card(struct spider_net_card *card)
-{
-	int i;
-	/* the following array consists of (register),(value) pairs
-	 * that are set in this function. A register of 0 ends the list
-	 */
-	u32 regs[][2] = {
-		{ SPIDER_NET_GRESUMINTNUM, 0 },
-		{ SPIDER_NET_GREINTNUM, 0 },
-
-		/* set interrupt frame number registers */
-		/* clear the single DMA engine registers first */
-		{ SPIDER_NET_GFAFRMNUM, SPIDER_NET_GFXFRAMES_VALUE },
-		{ SPIDER_NET_GFBFRMNUM, SPIDER_NET_GFXFRAMES_VALUE },
-		{ SPIDER_NET_GFCFRMNUM, SPIDER_NET_GFXFRAMES_VALUE },
-		{ SPIDER_NET_GFDFRMNUM, SPIDER_NET_GFXFRAMES_VALUE },
-		/* then set, what we really need */
-		{ SPIDER_NET_GFFRMNUM, SPIDER_NET_FRAMENUM_VALUE },
-
-		/* timer counter registers and stuff */
-		{ SPIDER_NET_GFREECNNUM, 0 },
-		{ SPIDER_NET_GONETIMENUM, 0 },
-		{ SPIDER_NET_GTOUTFRMNUM, 0 },
-
-		/* RX mode setting */
-		{ SPIDER_NET_GRXMDSET, SPIDER_NET_RXMODE_VALUE },
-		/* TX mode setting */
-		{ SPIDER_NET_GTXMDSET, SPIDER_NET_TXMODE_VALUE },
-		/* IPSEC mode setting */
-		{ SPIDER_NET_GIPSECINIT, SPIDER_NET_IPSECINIT_VALUE },
-
-		{ SPIDER_NET_GFTRESTRT, SPIDER_NET_RESTART_VALUE },
-
-		{ SPIDER_NET_GMRWOLCTRL, 0 },
-		{ SPIDER_NET_GTESTMD, 0x10000000 },
-		{ SPIDER_NET_GTTQMSK, 0x00400040 },
-
-		{ SPIDER_NET_GMACINTEN, 0 },
-
-		/* flow control stuff */
-		{ SPIDER_NET_GMACAPAUSE, SPIDER_NET_MACAPAUSE_VALUE },
-		{ SPIDER_NET_GMACTXPAUSE, SPIDER_NET_TXPAUSE_VALUE },
-
-		{ SPIDER_NET_GMACBSTLMT, SPIDER_NET_BURSTLMT_VALUE },
-		{ 0, 0}
-	};
-
-	i = 0;
-	while (regs[i][0]) {
-		spider_net_write_reg(card, regs[i][0], regs[i][1]);
-		i++;
-	}
-
-	/* clear unicast filter table entries 1 to 14 */
-	for (i = 1; i <= 14; i++) {
-		spider_net_write_reg(card,
-				     SPIDER_NET_GMRUAFILnR + i * 8,
-				     0x00080000);
-		spider_net_write_reg(card,
-				     SPIDER_NET_GMRUAFILnR + i * 8 + 4,
-				     0x00000000);
-	}
-
-	spider_net_write_reg(card, SPIDER_NET_GMRUA0FIL15R, 0x08080000);
-
-	spider_net_write_reg(card, SPIDER_NET_ECMODE, SPIDER_NET_ECMODE_VALUE);
-
-	/* set chain tail address for RX chains and
-	 * enable DMA
-	 */
-	spider_net_enable_rxchtails(card);
-	spider_net_enable_rxdmac(card);
-
-	spider_net_write_reg(card, SPIDER_NET_GRXDMAEN, SPIDER_NET_WOL_VALUE);
-
-	spider_net_write_reg(card, SPIDER_NET_GMACLENLMT,
-			     SPIDER_NET_LENLMT_VALUE);
-	spider_net_write_reg(card, SPIDER_NET_GMACOPEMD,
-			     SPIDER_NET_OPMODE_VALUE);
-
-	spider_net_write_reg(card, SPIDER_NET_GDTDMACCNTR,
-			     SPIDER_NET_GDTBSTA);
-}
-
-/**
- * spider_net_download_firmware - loads firmware into the adapter
- * @card: card structure
- * @firmware_ptr: pointer to firmware data
- *
- * spider_net_download_firmware loads the firmware data into the
- * adapter. It assumes the length etc. to be allright.
- */
-static int
-spider_net_download_firmware(struct spider_net_card *card,
-			     const void *firmware_ptr)
-{
-	int sequencer, i;
-	const u32 *fw_ptr = firmware_ptr;
-
-	/* stop sequencers */
-	spider_net_write_reg(card, SPIDER_NET_GSINIT,
-			     SPIDER_NET_STOP_SEQ_VALUE);
-
-	for (sequencer = 0; sequencer < SPIDER_NET_FIRMWARE_SEQS;
-	     sequencer++) {
-		spider_net_write_reg(card,
-				     SPIDER_NET_GSnPRGADR + sequencer * 8, 0);
-		for (i = 0; i < SPIDER_NET_FIRMWARE_SEQWORDS; i++) {
-			spider_net_write_reg(card, SPIDER_NET_GSnPRGDAT +
-					     sequencer * 8, *fw_ptr);
-			fw_ptr++;
-		}
-	}
-
-	if (spider_net_read_reg(card, SPIDER_NET_GSINIT))
-		return -EIO;
-
-	spider_net_write_reg(card, SPIDER_NET_GSINIT,
-			     SPIDER_NET_RUN_SEQ_VALUE);
-
-	return 0;
-}
-
-/**
- * spider_net_init_firmware - reads in firmware parts
- * @card: card structure
- *
- * Returns 0 on success, <0 on failure
- *
- * spider_net_init_firmware opens the sequencer firmware and does some basic
- * checks. This function opens and releases the firmware structure. A call
- * to download the firmware is performed before the release.
- *
- * Firmware format
- * ===============
- * spider_fw.bin is expected to be a file containing 6*1024*4 bytes, 4k being
- * the program for each sequencer. Use the command
- *    tail -q -n +2 Seq_code1_0x088.txt Seq_code2_0x090.txt              \
- *         Seq_code3_0x098.txt Seq_code4_0x0A0.txt Seq_code5_0x0A8.txt   \
- *         Seq_code6_0x0B0.txt | xxd -r -p -c4 > spider_fw.bin
- *
- * to generate spider_fw.bin, if you have sequencer programs with something
- * like the following contents for each sequencer:
- *    <ONE LINE COMMENT>
- *    <FIRST 4-BYTES-WORD FOR SEQUENCER>
- *    <SECOND 4-BYTES-WORD FOR SEQUENCER>
- *     ...
- *    <1024th 4-BYTES-WORD FOR SEQUENCER>
- */
-static int
-spider_net_init_firmware(struct spider_net_card *card)
-{
-	struct firmware *firmware = NULL;
-	struct device_node *dn;
-	const u8 *fw_prop = NULL;
-	int err = -ENOENT;
-	int fw_size;
-
-	if (request_firmware((const struct firmware **)&firmware,
-			     SPIDER_NET_FIRMWARE_NAME, &card->pdev->dev) == 0) {
-		if ( (firmware->size != SPIDER_NET_FIRMWARE_LEN) &&
-		     netif_msg_probe(card) ) {
-			dev_err(&card->netdev->dev,
-			       "Incorrect size of spidernet firmware in " \
-			       "filesystem. Looking in host firmware...\n");
-			goto try_host_fw;
-		}
-		err = spider_net_download_firmware(card, firmware->data);
-
-		release_firmware(firmware);
-		if (err)
-			goto try_host_fw;
-
-		goto done;
-	}
-
-try_host_fw:
-	dn = pci_device_to_OF_node(card->pdev);
-	if (!dn)
-		goto out_err;
-
-	fw_prop = of_get_property(dn, "firmware", &fw_size);
-	if (!fw_prop)
-		goto out_err;
-
-	if ( (fw_size != SPIDER_NET_FIRMWARE_LEN) &&
-	     netif_msg_probe(card) ) {
-		dev_err(&card->netdev->dev,
-		       "Incorrect size of spidernet firmware in host firmware\n");
-		goto done;
-	}
-
-	err = spider_net_download_firmware(card, fw_prop);
-
-done:
-	return err;
-out_err:
-	if (netif_msg_probe(card))
-		dev_err(&card->netdev->dev,
-		       "Couldn't find spidernet firmware in filesystem " \
-		       "or host firmware\n");
-	return err;
-}
-
-/**
- * spider_net_open - called upon ifonfig up
- * @netdev: interface device structure
- *
- * returns 0 on success, <0 on failure
- *
- * spider_net_open allocates all the descriptors and memory needed for
- * operation, sets up multicast list and enables interrupts
- */
-int
-spider_net_open(struct net_device *netdev)
-{
-	struct spider_net_card *card = netdev_priv(netdev);
-	int result;
-
-	result = spider_net_init_firmware(card);
-	if (result)
-		goto init_firmware_failed;
-
-	/* start probing with copper */
-	card->aneg_count = 0;
-	card->medium = BCM54XX_COPPER;
-	spider_net_setup_aneg(card);
-	if (card->phy.def->phy_id)
-		mod_timer(&card->aneg_timer, jiffies + SPIDER_NET_ANEG_TIMER);
-
-	result = spider_net_init_chain(card, &card->tx_chain);
-	if (result)
-		goto alloc_tx_failed;
-	card->low_watermark = NULL;
-
-	result = spider_net_init_chain(card, &card->rx_chain);
-	if (result)
-		goto alloc_rx_failed;
-
-	/* Allocate rx skbs */
-	result = spider_net_alloc_rx_skbs(card);
-	if (result)
-		goto alloc_skbs_failed;
-
-	spider_net_set_multi(netdev);
-
-	/* further enhancement: setup hw vlan, if needed */
-
-	result = -EBUSY;
-	if (request_irq(netdev->irq, spider_net_interrupt,
-			     IRQF_SHARED, netdev->name, netdev))
-		goto register_int_failed;
-
-	spider_net_enable_card(card);
-
-	netif_start_queue(netdev);
-	netif_carrier_on(netdev);
-	napi_enable(&card->napi);
-
-	spider_net_enable_interrupts(card);
-
-	return 0;
-
-register_int_failed:
-	spider_net_free_rx_chain_contents(card);
-alloc_skbs_failed:
-	spider_net_free_chain(card, &card->rx_chain);
-alloc_rx_failed:
-	spider_net_free_chain(card, &card->tx_chain);
-alloc_tx_failed:
-	del_timer_sync(&card->aneg_timer);
-init_firmware_failed:
-	return result;
-}
-
-/**
- * spider_net_link_phy
- * @t: timer context used to obtain the pointer to net card data structure
- */
-static void spider_net_link_phy(struct timer_list *t)
-{
-	struct spider_net_card *card = from_timer(card, t, aneg_timer);
-	struct mii_phy *phy = &card->phy;
-
-	/* if link didn't come up after SPIDER_NET_ANEG_TIMEOUT tries, setup phy again */
-	if (card->aneg_count > SPIDER_NET_ANEG_TIMEOUT) {
-
-		pr_debug("%s: link is down trying to bring it up\n",
-			 card->netdev->name);
-
-		switch (card->medium) {
-		case BCM54XX_COPPER:
-			/* enable fiber with autonegotiation first */
-			if (phy->def->ops->enable_fiber)
-				phy->def->ops->enable_fiber(phy, 1);
-			card->medium = BCM54XX_FIBER;
-			break;
-
-		case BCM54XX_FIBER:
-			/* fiber didn't come up, try to disable fiber autoneg */
-			if (phy->def->ops->enable_fiber)
-				phy->def->ops->enable_fiber(phy, 0);
-			card->medium = BCM54XX_UNKNOWN;
-			break;
-
-		case BCM54XX_UNKNOWN:
-			/* copper, fiber with and without failed,
-			 * retry from beginning
-			 */
-			spider_net_setup_aneg(card);
-			card->medium = BCM54XX_COPPER;
-			break;
-		}
-
-		card->aneg_count = 0;
-		mod_timer(&card->aneg_timer, jiffies + SPIDER_NET_ANEG_TIMER);
-		return;
-	}
-
-	/* link still not up, try again later */
-	if (!(phy->def->ops->poll_link(phy))) {
-		card->aneg_count++;
-		mod_timer(&card->aneg_timer, jiffies + SPIDER_NET_ANEG_TIMER);
-		return;
-	}
-
-	/* link came up, get abilities */
-	phy->def->ops->read_link(phy);
-
-	spider_net_write_reg(card, SPIDER_NET_GMACST,
-			     spider_net_read_reg(card, SPIDER_NET_GMACST));
-	spider_net_write_reg(card, SPIDER_NET_GMACINTEN, 0x4);
-
-	if (phy->speed == 1000)
-		spider_net_write_reg(card, SPIDER_NET_GMACMODE, 0x00000001);
-	else
-		spider_net_write_reg(card, SPIDER_NET_GMACMODE, 0);
-
-	card->aneg_count = 0;
-
-	pr_info("%s: link up, %i Mbps, %s-duplex %sautoneg.\n",
-		card->netdev->name, phy->speed,
-		phy->duplex == 1 ? "Full" : "Half",
-		phy->autoneg == 1 ? "" : "no ");
-}
-
-/**
- * spider_net_setup_phy - setup PHY
- * @card: card structure
- *
- * returns 0 on success, <0 on failure
- *
- * spider_net_setup_phy is used as part of spider_net_probe.
- **/
-static int
-spider_net_setup_phy(struct spider_net_card *card)
-{
-	struct mii_phy *phy = &card->phy;
-
-	spider_net_write_reg(card, SPIDER_NET_GDTDMASEL,
-			     SPIDER_NET_DMASEL_VALUE);
-	spider_net_write_reg(card, SPIDER_NET_GPCCTRL,
-			     SPIDER_NET_PHY_CTRL_VALUE);
-
-	phy->dev = card->netdev;
-	phy->mdio_read = spider_net_read_phy;
-	phy->mdio_write = spider_net_write_phy;
-
-	for (phy->mii_id = 1; phy->mii_id <= 31; phy->mii_id++) {
-		unsigned short id;
-		id = spider_net_read_phy(card->netdev, phy->mii_id, MII_BMSR);
-		if (id != 0x0000 && id != 0xffff) {
-			if (!sungem_phy_probe(phy, phy->mii_id)) {
-				pr_info("Found %s.\n", phy->def->name);
-				break;
-			}
-		}
-	}
-
-	return 0;
-}
-
-/**
- * spider_net_workaround_rxramfull - work around firmware bug
- * @card: card structure
- *
- * no return value
- **/
-static void
-spider_net_workaround_rxramfull(struct spider_net_card *card)
-{
-	int i, sequencer = 0;
-
-	/* cancel reset */
-	spider_net_write_reg(card, SPIDER_NET_CKRCTRL,
-			     SPIDER_NET_CKRCTRL_RUN_VALUE);
-
-	/* empty sequencer data */
-	for (sequencer = 0; sequencer < SPIDER_NET_FIRMWARE_SEQS;
-	     sequencer++) {
-		spider_net_write_reg(card, SPIDER_NET_GSnPRGADR +
-				     sequencer * 8, 0x0);
-		for (i = 0; i < SPIDER_NET_FIRMWARE_SEQWORDS; i++) {
-			spider_net_write_reg(card, SPIDER_NET_GSnPRGDAT +
-					     sequencer * 8, 0x0);
-		}
-	}
-
-	/* set sequencer operation */
-	spider_net_write_reg(card, SPIDER_NET_GSINIT, 0x000000fe);
-
-	/* reset */
-	spider_net_write_reg(card, SPIDER_NET_CKRCTRL,
-			     SPIDER_NET_CKRCTRL_STOP_VALUE);
-}
-
-/**
- * spider_net_stop - called upon ifconfig down
- * @netdev: interface device structure
- *
- * always returns 0
- */
-int
-spider_net_stop(struct net_device *netdev)
-{
-	struct spider_net_card *card = netdev_priv(netdev);
-
-	napi_disable(&card->napi);
-	netif_carrier_off(netdev);
-	netif_stop_queue(netdev);
-	del_timer_sync(&card->tx_timer);
-	del_timer_sync(&card->aneg_timer);
-
-	spider_net_disable_interrupts(card);
-
-	free_irq(netdev->irq, netdev);
-
-	spider_net_write_reg(card, SPIDER_NET_GDTDMACCNTR,
-			     SPIDER_NET_DMA_TX_FEND_VALUE);
-
-	/* turn off DMA, force end */
-	spider_net_disable_rxdmac(card);
-
-	/* release chains */
-	spider_net_release_tx_chain(card, 1);
-	spider_net_free_rx_chain_contents(card);
-
-	spider_net_free_chain(card, &card->tx_chain);
-	spider_net_free_chain(card, &card->rx_chain);
-
-	return 0;
-}
-
-/**
- * spider_net_tx_timeout_task - task scheduled by the watchdog timeout
- * function (to be called not under interrupt status)
- * @work: work context used to obtain the pointer to net card data structure
- *
- * called as task when tx hangs, resets interface (if interface is up)
- */
-static void
-spider_net_tx_timeout_task(struct work_struct *work)
-{
-	struct spider_net_card *card =
-		container_of(work, struct spider_net_card, tx_timeout_task);
-	struct net_device *netdev = card->netdev;
-
-	if (!(netdev->flags & IFF_UP))
-		goto out;
-
-	netif_device_detach(netdev);
-	spider_net_stop(netdev);
-
-	spider_net_workaround_rxramfull(card);
-	spider_net_init_card(card);
-
-	if (spider_net_setup_phy(card))
-		goto out;
-
-	spider_net_open(netdev);
-	spider_net_kick_tx_dma(card);
-	netif_device_attach(netdev);
-
-out:
-	atomic_dec(&card->tx_timeout_task_counter);
-}
-
-/**
- * spider_net_tx_timeout - called when the tx timeout watchdog kicks in.
- * @netdev: interface device structure
- * @txqueue: unused
- *
- * called, if tx hangs. Schedules a task that resets the interface
- */
-static void
-spider_net_tx_timeout(struct net_device *netdev, unsigned int txqueue)
-{
-	struct spider_net_card *card;
-
-	card = netdev_priv(netdev);
-	atomic_inc(&card->tx_timeout_task_counter);
-	if (netdev->flags & IFF_UP)
-		schedule_work(&card->tx_timeout_task);
-	else
-		atomic_dec(&card->tx_timeout_task_counter);
-	card->spider_stats.tx_timeouts++;
-}
-
-static const struct net_device_ops spider_net_ops = {
-	.ndo_open		= spider_net_open,
-	.ndo_stop		= spider_net_stop,
-	.ndo_start_xmit		= spider_net_xmit,
-	.ndo_set_rx_mode	= spider_net_set_multi,
-	.ndo_set_mac_address	= spider_net_set_mac,
-	.ndo_eth_ioctl		= spider_net_do_ioctl,
-	.ndo_tx_timeout		= spider_net_tx_timeout,
-	.ndo_validate_addr	= eth_validate_addr,
-	/* HW VLAN */
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	/* poll controller */
-	.ndo_poll_controller	= spider_net_poll_controller,
-#endif /* CONFIG_NET_POLL_CONTROLLER */
-};
-
-/**
- * spider_net_setup_netdev_ops - initialization of net_device operations
- * @netdev: net_device structure
- *
- * fills out function pointers in the net_device structure
- */
-static void
-spider_net_setup_netdev_ops(struct net_device *netdev)
-{
-	netdev->netdev_ops = &spider_net_ops;
-	netdev->watchdog_timeo = SPIDER_NET_WATCHDOG_TIMEOUT;
-	/* ethtool ops */
-	netdev->ethtool_ops = &spider_net_ethtool_ops;
-}
-
-/**
- * spider_net_setup_netdev - initialization of net_device
- * @card: card structure
- *
- * Returns 0 on success or <0 on failure
- *
- * spider_net_setup_netdev initializes the net_device structure
- **/
-static int
-spider_net_setup_netdev(struct spider_net_card *card)
-{
-	int result;
-	struct net_device *netdev = card->netdev;
-	struct device_node *dn;
-	struct sockaddr addr;
-	const u8 *mac;
-
-	SET_NETDEV_DEV(netdev, &card->pdev->dev);
-
-	pci_set_drvdata(card->pdev, netdev);
-
-	timer_setup(&card->tx_timer, spider_net_cleanup_tx_ring, 0);
-	netdev->irq = card->pdev->irq;
-
-	card->aneg_count = 0;
-	timer_setup(&card->aneg_timer, spider_net_link_phy, 0);
-
-	netif_napi_add(netdev, &card->napi, spider_net_poll);
-
-	spider_net_setup_netdev_ops(netdev);
-
-	netdev->hw_features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM;
-	if (SPIDER_NET_RX_CSUM_DEFAULT)
-		netdev->features |= NETIF_F_RXCSUM;
-	netdev->features |= NETIF_F_IP_CSUM;
-	/* some time: NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
-	 *		NETIF_F_HW_VLAN_CTAG_FILTER
-	 */
-	netdev->lltx = true;
-
-	/* MTU range: 64 - 2294 */
-	netdev->min_mtu = SPIDER_NET_MIN_MTU;
-	netdev->max_mtu = SPIDER_NET_MAX_MTU;
-
-	netdev->irq = card->pdev->irq;
-	card->num_rx_ints = 0;
-	card->ignore_rx_ramfull = 0;
-
-	dn = pci_device_to_OF_node(card->pdev);
-	if (!dn)
-		return -EIO;
-
-	mac = of_get_property(dn, "local-mac-address", NULL);
-	if (!mac)
-		return -EIO;
-	memcpy(addr.sa_data, mac, ETH_ALEN);
-
-	result = spider_net_set_mac(netdev, &addr);
-	if ((result) && (netif_msg_probe(card)))
-		dev_err(&card->netdev->dev,
-		        "Failed to set MAC address: %i\n", result);
-
-	result = register_netdev(netdev);
-	if (result) {
-		if (netif_msg_probe(card))
-			dev_err(&card->netdev->dev,
-			        "Couldn't register net_device: %i\n", result);
-		return result;
-	}
-
-	if (netif_msg_probe(card))
-		pr_info("Initialized device %s.\n", netdev->name);
-
-	return 0;
-}
-
-/**
- * spider_net_alloc_card - allocates net_device and card structure
- *
- * returns the card structure or NULL in case of errors
- *
- * the card and net_device structures are linked to each other
- */
-static struct spider_net_card *
-spider_net_alloc_card(void)
-{
-	struct net_device *netdev;
-	struct spider_net_card *card;
-
-	netdev = alloc_etherdev(struct_size(card, darray,
-					    size_add(tx_descriptors, rx_descriptors)));
-	if (!netdev)
-		return NULL;
-
-	card = netdev_priv(netdev);
-	card->netdev = netdev;
-	card->msg_enable = SPIDER_NET_DEFAULT_MSG;
-	INIT_WORK(&card->tx_timeout_task, spider_net_tx_timeout_task);
-	init_waitqueue_head(&card->waitq);
-	atomic_set(&card->tx_timeout_task_counter, 0);
-
-	card->rx_chain.num_desc = rx_descriptors;
-	card->rx_chain.ring = card->darray;
-	card->tx_chain.num_desc = tx_descriptors;
-	card->tx_chain.ring = card->darray + rx_descriptors;
-
-	return card;
-}
-
-/**
- * spider_net_undo_pci_setup - releases PCI ressources
- * @card: card structure
- *
- * spider_net_undo_pci_setup releases the mapped regions
- */
-static void
-spider_net_undo_pci_setup(struct spider_net_card *card)
-{
-	iounmap(card->regs);
-	pci_release_regions(card->pdev);
-}
-
-/**
- * spider_net_setup_pci_dev - sets up the device in terms of PCI operations
- * @pdev: PCI device
- *
- * Returns the card structure or NULL if any errors occur
- *
- * spider_net_setup_pci_dev initializes pdev and together with the
- * functions called in spider_net_open configures the device so that
- * data can be transferred over it
- * The net_device structure is attached to the card structure, if the
- * function returns without error.
- **/
-static struct spider_net_card *
-spider_net_setup_pci_dev(struct pci_dev *pdev)
-{
-	struct spider_net_card *card;
-	unsigned long mmio_start, mmio_len;
-
-	if (pci_enable_device(pdev)) {
-		dev_err(&pdev->dev, "Couldn't enable PCI device\n");
-		return NULL;
-	}
-
-	if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
-		dev_err(&pdev->dev,
-		        "Couldn't find proper PCI device base address.\n");
-		goto out_disable_dev;
-	}
-
-	if (pci_request_regions(pdev, spider_net_driver_name)) {
-		dev_err(&pdev->dev,
-		        "Couldn't obtain PCI resources, aborting.\n");
-		goto out_disable_dev;
-	}
-
-	pci_set_master(pdev);
-
-	card = spider_net_alloc_card();
-	if (!card) {
-		dev_err(&pdev->dev,
-		        "Couldn't allocate net_device structure, aborting.\n");
-		goto out_release_regions;
-	}
-	card->pdev = pdev;
-
-	/* fetch base address and length of first resource */
-	mmio_start = pci_resource_start(pdev, 0);
-	mmio_len = pci_resource_len(pdev, 0);
-
-	card->netdev->mem_start = mmio_start;
-	card->netdev->mem_end = mmio_start + mmio_len;
-	card->regs = ioremap(mmio_start, mmio_len);
-
-	if (!card->regs) {
-		dev_err(&pdev->dev,
-		        "Couldn't obtain PCI resources, aborting.\n");
-		goto out_release_regions;
-	}
-
-	return card;
-
-out_release_regions:
-	pci_release_regions(pdev);
-out_disable_dev:
-	pci_disable_device(pdev);
-	return NULL;
-}
-
-/**
- * spider_net_probe - initialization of a device
- * @pdev: PCI device
- * @ent: entry in the device id list
- *
- * Returns 0 on success, <0 on failure
- *
- * spider_net_probe initializes pdev and registers a net_device
- * structure for it. After that, the device can be ifconfig'ed up
- **/
-static int
-spider_net_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
-{
-	int err = -EIO;
-	struct spider_net_card *card;
-
-	card = spider_net_setup_pci_dev(pdev);
-	if (!card)
-		goto out;
-
-	spider_net_workaround_rxramfull(card);
-	spider_net_init_card(card);
-
-	err = spider_net_setup_phy(card);
-	if (err)
-		goto out_undo_pci;
-
-	err = spider_net_setup_netdev(card);
-	if (err)
-		goto out_undo_pci;
-
-	return 0;
-
-out_undo_pci:
-	spider_net_undo_pci_setup(card);
-	free_netdev(card->netdev);
-out:
-	return err;
-}
-
-/**
- * spider_net_remove - removal of a device
- * @pdev: PCI device
- *
- * Returns 0 on success, <0 on failure
- *
- * spider_net_remove is called to remove the device and unregisters the
- * net_device
- **/
-static void
-spider_net_remove(struct pci_dev *pdev)
-{
-	struct net_device *netdev;
-	struct spider_net_card *card;
-
-	netdev = pci_get_drvdata(pdev);
-	card = netdev_priv(netdev);
-
-	wait_event(card->waitq,
-		   atomic_read(&card->tx_timeout_task_counter) == 0);
-
-	unregister_netdev(netdev);
-
-	/* switch off card */
-	spider_net_write_reg(card, SPIDER_NET_CKRCTRL,
-			     SPIDER_NET_CKRCTRL_STOP_VALUE);
-	spider_net_write_reg(card, SPIDER_NET_CKRCTRL,
-			     SPIDER_NET_CKRCTRL_RUN_VALUE);
-
-	spider_net_undo_pci_setup(card);
-	free_netdev(netdev);
-}
-
-static struct pci_driver spider_net_driver = {
-	.name		= spider_net_driver_name,
-	.id_table	= spider_net_pci_tbl,
-	.probe		= spider_net_probe,
-	.remove		= spider_net_remove
-};
-
-/**
- * spider_net_init - init function when the driver is loaded
- *
- * spider_net_init registers the device driver
- */
-static int __init spider_net_init(void)
-{
-	printk(KERN_INFO "Spidernet version %s.\n", VERSION);
-
-	if (rx_descriptors < SPIDER_NET_RX_DESCRIPTORS_MIN) {
-		rx_descriptors = SPIDER_NET_RX_DESCRIPTORS_MIN;
-		pr_info("adjusting rx descriptors to %i.\n", rx_descriptors);
-	}
-	if (rx_descriptors > SPIDER_NET_RX_DESCRIPTORS_MAX) {
-		rx_descriptors = SPIDER_NET_RX_DESCRIPTORS_MAX;
-		pr_info("adjusting rx descriptors to %i.\n", rx_descriptors);
-	}
-	if (tx_descriptors < SPIDER_NET_TX_DESCRIPTORS_MIN) {
-		tx_descriptors = SPIDER_NET_TX_DESCRIPTORS_MIN;
-		pr_info("adjusting tx descriptors to %i.\n", tx_descriptors);
-	}
-	if (tx_descriptors > SPIDER_NET_TX_DESCRIPTORS_MAX) {
-		tx_descriptors = SPIDER_NET_TX_DESCRIPTORS_MAX;
-		pr_info("adjusting tx descriptors to %i.\n", tx_descriptors);
-	}
-
-	return pci_register_driver(&spider_net_driver);
-}
-
-/**
- * spider_net_cleanup - exit function when driver is unloaded
- *
- * spider_net_cleanup unregisters the device driver
- */
-static void __exit spider_net_cleanup(void)
-{
-	pci_unregister_driver(&spider_net_driver);
-}
-
-module_init(spider_net_init);
-module_exit(spider_net_cleanup);
diff --git a/drivers/net/ethernet/toshiba/spider_net.h b/drivers/net/ethernet/toshiba/spider_net.h
deleted file mode 100644
index 51948e2b3a34..000000000000
--- a/drivers/net/ethernet/toshiba/spider_net.h
+++ /dev/null
@@ -1,475 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Network device driver for Cell Processor-Based Blade and Celleb platform
- *
- * (C) Copyright IBM Corp. 2005
- * (C) Copyright 2006 TOSHIBA CORPORATION
- *
- * Authors : Utz Bacher <utz.bacher@de.ibm.com>
- *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
- */
-
-#ifndef _SPIDER_NET_H
-#define _SPIDER_NET_H
-
-#define VERSION "2.0 B"
-
-#include <linux/sungem_phy.h>
-
-int spider_net_stop(struct net_device *netdev);
-int spider_net_open(struct net_device *netdev);
-
-extern const struct ethtool_ops spider_net_ethtool_ops;
-
-extern char spider_net_driver_name[];
-
-#define SPIDER_NET_MAX_FRAME			2312
-#define SPIDER_NET_MAX_MTU			2294
-#define SPIDER_NET_MIN_MTU			64
-
-#define SPIDER_NET_RXBUF_ALIGN			128
-
-#define SPIDER_NET_RX_DESCRIPTORS_DEFAULT	256
-#define SPIDER_NET_RX_DESCRIPTORS_MIN		16
-#define SPIDER_NET_RX_DESCRIPTORS_MAX		512
-
-#define SPIDER_NET_TX_DESCRIPTORS_DEFAULT	256
-#define SPIDER_NET_TX_DESCRIPTORS_MIN		16
-#define SPIDER_NET_TX_DESCRIPTORS_MAX		512
-
-#define SPIDER_NET_TX_TIMER			(HZ/5)
-#define SPIDER_NET_ANEG_TIMER			(HZ)
-#define SPIDER_NET_ANEG_TIMEOUT			5
-
-#define SPIDER_NET_RX_CSUM_DEFAULT		1
-
-#define SPIDER_NET_WATCHDOG_TIMEOUT		50*HZ
-
-#define SPIDER_NET_FIRMWARE_SEQS	6
-#define SPIDER_NET_FIRMWARE_SEQWORDS	1024
-#define SPIDER_NET_FIRMWARE_LEN		(SPIDER_NET_FIRMWARE_SEQS * \
-					 SPIDER_NET_FIRMWARE_SEQWORDS * \
-					 sizeof(u32))
-#define SPIDER_NET_FIRMWARE_NAME	"spider_fw.bin"
-
-/** spider_net SMMIO registers */
-#define SPIDER_NET_GHIINT0STS		0x00000000
-#define SPIDER_NET_GHIINT1STS		0x00000004
-#define SPIDER_NET_GHIINT2STS		0x00000008
-#define SPIDER_NET_GHIINT0MSK		0x00000010
-#define SPIDER_NET_GHIINT1MSK		0x00000014
-#define SPIDER_NET_GHIINT2MSK		0x00000018
-
-#define SPIDER_NET_GRESUMINTNUM		0x00000020
-#define SPIDER_NET_GREINTNUM		0x00000024
-
-#define SPIDER_NET_GFFRMNUM		0x00000028
-#define SPIDER_NET_GFAFRMNUM		0x0000002c
-#define SPIDER_NET_GFBFRMNUM		0x00000030
-#define SPIDER_NET_GFCFRMNUM		0x00000034
-#define SPIDER_NET_GFDFRMNUM		0x00000038
-
-/* clear them (don't use it) */
-#define SPIDER_NET_GFREECNNUM		0x0000003c
-#define SPIDER_NET_GONETIMENUM		0x00000040
-
-#define SPIDER_NET_GTOUTFRMNUM		0x00000044
-
-#define SPIDER_NET_GTXMDSET		0x00000050
-#define SPIDER_NET_GPCCTRL		0x00000054
-#define SPIDER_NET_GRXMDSET		0x00000058
-#define SPIDER_NET_GIPSECINIT		0x0000005c
-#define SPIDER_NET_GFTRESTRT		0x00000060
-#define SPIDER_NET_GRXDMAEN		0x00000064
-#define SPIDER_NET_GMRWOLCTRL		0x00000068
-#define SPIDER_NET_GPCWOPCMD		0x0000006c
-#define SPIDER_NET_GPCROPCMD		0x00000070
-#define SPIDER_NET_GTTFRMCNT		0x00000078
-#define SPIDER_NET_GTESTMD		0x0000007c
-
-#define SPIDER_NET_GSINIT		0x00000080
-#define SPIDER_NET_GSnPRGADR		0x00000084
-#define SPIDER_NET_GSnPRGDAT		0x00000088
-
-#define SPIDER_NET_GMACOPEMD		0x00000100
-#define SPIDER_NET_GMACLENLMT		0x00000108
-#define SPIDER_NET_GMACST		0x00000110
-#define SPIDER_NET_GMACINTEN		0x00000118
-#define SPIDER_NET_GMACPHYCTRL		0x00000120
-
-#define SPIDER_NET_GMACAPAUSE		0x00000154
-#define SPIDER_NET_GMACTXPAUSE		0x00000164
-
-#define SPIDER_NET_GMACMODE		0x000001b0
-#define SPIDER_NET_GMACBSTLMT		0x000001b4
-
-#define SPIDER_NET_GMACUNIMACU		0x000001c0
-#define SPIDER_NET_GMACUNIMACL		0x000001c8
-
-#define SPIDER_NET_GMRMHFILnR		0x00000400
-#define SPIDER_NET_MULTICAST_HASHES	256
-
-#define SPIDER_NET_GMRUAFILnR		0x00000500
-#define SPIDER_NET_GMRUA0FIL15R		0x00000578
-
-#define SPIDER_NET_GTTQMSK		0x00000934
-
-/* RX DMA controller registers, all 0x00000a.. are for DMA controller A,
- * 0x00000b.. for DMA controller B, etc. */
-#define SPIDER_NET_GDADCHA		0x00000a00
-#define SPIDER_NET_GDADMACCNTR		0x00000a04
-#define SPIDER_NET_GDACTDPA		0x00000a08
-#define SPIDER_NET_GDACTDCNT		0x00000a0c
-#define SPIDER_NET_GDACDBADDR		0x00000a20
-#define SPIDER_NET_GDACDBSIZE		0x00000a24
-#define SPIDER_NET_GDACNEXTDA		0x00000a28
-#define SPIDER_NET_GDACCOMST		0x00000a2c
-#define SPIDER_NET_GDAWBCOMST		0x00000a30
-#define SPIDER_NET_GDAWBRSIZE		0x00000a34
-#define SPIDER_NET_GDAWBVSIZE		0x00000a38
-#define SPIDER_NET_GDAWBTRST		0x00000a3c
-#define SPIDER_NET_GDAWBTRERR		0x00000a40
-
-/* TX DMA controller registers */
-#define SPIDER_NET_GDTDCHA		0x00000e00
-#define SPIDER_NET_GDTDMACCNTR		0x00000e04
-#define SPIDER_NET_GDTCDPA		0x00000e08
-#define SPIDER_NET_GDTDMASEL		0x00000e14
-
-#define SPIDER_NET_ECMODE		0x00000f00
-/* clock and reset control register */
-#define SPIDER_NET_CKRCTRL		0x00000ff0
-
-/** SCONFIG registers */
-#define SPIDER_NET_SCONFIG_IOACTE	0x00002810
-
-/** interrupt mask registers */
-#define SPIDER_NET_INT0_MASK_VALUE	0x3f7fe2c7
-#define SPIDER_NET_INT1_MASK_VALUE	0x0000fff2
-#define SPIDER_NET_INT2_MASK_VALUE	0x000003f1
-
-/* we rely on flagged descriptor interrupts */
-#define SPIDER_NET_FRAMENUM_VALUE	0x00000000
-/* set this first, then the FRAMENUM_VALUE */
-#define SPIDER_NET_GFXFRAMES_VALUE	0x00000000
-
-#define SPIDER_NET_STOP_SEQ_VALUE	0x00000000
-#define SPIDER_NET_RUN_SEQ_VALUE	0x0000007e
-
-#define SPIDER_NET_PHY_CTRL_VALUE	0x00040040
-/* #define SPIDER_NET_PHY_CTRL_VALUE	0x01070080*/
-#define SPIDER_NET_RXMODE_VALUE		0x00000011
-/* auto retransmission in case of MAC aborts */
-#define SPIDER_NET_TXMODE_VALUE		0x00010000
-#define SPIDER_NET_RESTART_VALUE	0x00000000
-#define SPIDER_NET_WOL_VALUE		0x00001111
-#if 0
-#define SPIDER_NET_WOL_VALUE		0x00000000
-#endif
-#define SPIDER_NET_IPSECINIT_VALUE	0x6f716f71
-
-/* pause frames: automatic, no upper retransmission count */
-/* outside loopback mode: ETOMOD signal dont matter, not connected */
-/* ETOMOD signal is brought to PHY reset. bit 2 must be 1 in Celleb */
-#define SPIDER_NET_OPMODE_VALUE		0x00000067
-/*#define SPIDER_NET_OPMODE_VALUE		0x001b0062*/
-#define SPIDER_NET_LENLMT_VALUE		0x00000908
-
-#define SPIDER_NET_MACAPAUSE_VALUE	0x00000800 /* about 1 ms */
-#define SPIDER_NET_TXPAUSE_VALUE	0x00000000
-
-#define SPIDER_NET_MACMODE_VALUE	0x00000001
-#define SPIDER_NET_BURSTLMT_VALUE	0x00000200 /* about 16 us */
-
-/* DMAC control register GDMACCNTR
- *
- * 1(0)				enable r/tx dma
- *  0000000				fixed to 0
- *
- *         000000			fixed to 0
- *               0(1)			en/disable descr writeback on force end
- *                0(1)			force end
- *
- *                 000000		fixed to 0
- *                       00		burst alignment: 128 bytes
- *                       11		burst alignment: 1024 bytes
- *
- *                         00000	fixed to 0
- *                              0	descr writeback size 32 bytes
- *                               0(1)	descr chain end interrupt enable
- *                                0(1)	descr status writeback enable */
-
-/* to set RX_DMA_EN */
-#define SPIDER_NET_DMA_RX_VALUE		0x80000000
-#define SPIDER_NET_DMA_RX_FEND_VALUE	0x00030003
-/* to set TX_DMA_EN */
-#define SPIDER_NET_TX_DMA_EN           0x80000000
-#define SPIDER_NET_GDTBSTA             0x00000300
-#define SPIDER_NET_GDTDCEIDIS          0x00000002
-#define SPIDER_NET_DMA_TX_VALUE        SPIDER_NET_TX_DMA_EN | \
-                                       SPIDER_NET_GDTDCEIDIS | \
-                                       SPIDER_NET_GDTBSTA
-
-#define SPIDER_NET_DMA_TX_FEND_VALUE	0x00030003
-
-/* SPIDER_NET_UA_DESCR_VALUE is OR'ed with the unicast address */
-#define SPIDER_NET_UA_DESCR_VALUE	0x00080000
-#define SPIDER_NET_PROMISC_VALUE	0x00080000
-#define SPIDER_NET_NONPROMISC_VALUE	0x00000000
-
-#define SPIDER_NET_DMASEL_VALUE		0x00000001
-
-#define SPIDER_NET_ECMODE_VALUE		0x00000000
-
-#define SPIDER_NET_CKRCTRL_RUN_VALUE	0x1fff010f
-#define SPIDER_NET_CKRCTRL_STOP_VALUE	0x0000010f
-
-#define SPIDER_NET_SBIMSTATE_VALUE	0x00000000
-#define SPIDER_NET_SBTMSTATE_VALUE	0x00000000
-
-/* SPIDER_NET_GHIINT0STS bits, in reverse order so that they can be used
- * with 1 << SPIDER_NET_... */
-enum spider_net_int0_status {
-	SPIDER_NET_GPHYINT = 0,
-	SPIDER_NET_GMAC2INT,
-	SPIDER_NET_GMAC1INT,
-	SPIDER_NET_GIPSINT,
-	SPIDER_NET_GFIFOINT,
-	SPIDER_NET_GDMACINT,
-	SPIDER_NET_GSYSINT,
-	SPIDER_NET_GPWOPCMPINT,
-	SPIDER_NET_GPROPCMPINT,
-	SPIDER_NET_GPWFFINT,
-	SPIDER_NET_GRMDADRINT,
-	SPIDER_NET_GRMARPINT,
-	SPIDER_NET_GRMMPINT,
-	SPIDER_NET_GDTDEN0INT,
-	SPIDER_NET_GDDDEN0INT,
-	SPIDER_NET_GDCDEN0INT,
-	SPIDER_NET_GDBDEN0INT,
-	SPIDER_NET_GDADEN0INT,
-	SPIDER_NET_GDTFDCINT,
-	SPIDER_NET_GDDFDCINT,
-	SPIDER_NET_GDCFDCINT,
-	SPIDER_NET_GDBFDCINT,
-	SPIDER_NET_GDAFDCINT,
-	SPIDER_NET_GTTEDINT,
-	SPIDER_NET_GDTDCEINT,
-	SPIDER_NET_GRFDNMINT,
-	SPIDER_NET_GRFCNMINT,
-	SPIDER_NET_GRFBNMINT,
-	SPIDER_NET_GRFANMINT,
-	SPIDER_NET_GRFNMINT,
-	SPIDER_NET_G1TMCNTINT,
-	SPIDER_NET_GFREECNTINT
-};
-/* GHIINT1STS bits */
-enum spider_net_int1_status {
-	SPIDER_NET_GTMFLLINT = 0,
-	SPIDER_NET_GRMFLLINT,
-	SPIDER_NET_GTMSHTINT,
-	SPIDER_NET_GDTINVDINT,
-	SPIDER_NET_GRFDFLLINT,
-	SPIDER_NET_GDDDCEINT,
-	SPIDER_NET_GDDINVDINT,
-	SPIDER_NET_GRFCFLLINT,
-	SPIDER_NET_GDCDCEINT,
-	SPIDER_NET_GDCINVDINT,
-	SPIDER_NET_GRFBFLLINT,
-	SPIDER_NET_GDBDCEINT,
-	SPIDER_NET_GDBINVDINT,
-	SPIDER_NET_GRFAFLLINT,
-	SPIDER_NET_GDADCEINT,
-	SPIDER_NET_GDAINVDINT,
-	SPIDER_NET_GDTRSERINT,
-	SPIDER_NET_GDDRSERINT,
-	SPIDER_NET_GDCRSERINT,
-	SPIDER_NET_GDBRSERINT,
-	SPIDER_NET_GDARSERINT,
-	SPIDER_NET_GDSERINT,
-	SPIDER_NET_GDTPTERINT,
-	SPIDER_NET_GDDPTERINT,
-	SPIDER_NET_GDCPTERINT,
-	SPIDER_NET_GDBPTERINT,
-	SPIDER_NET_GDAPTERINT
-};
-/* GHIINT2STS bits */
-enum spider_net_int2_status {
-	SPIDER_NET_GPROPERINT = 0,
-	SPIDER_NET_GMCTCRSNGINT,
-	SPIDER_NET_GMCTLCOLINT,
-	SPIDER_NET_GMCTTMOTINT,
-	SPIDER_NET_GMCRCAERINT,
-	SPIDER_NET_GMCRCALERINT,
-	SPIDER_NET_GMCRALNERINT,
-	SPIDER_NET_GMCROVRINT,
-	SPIDER_NET_GMCRRNTINT,
-	SPIDER_NET_GMCRRXERINT,
-	SPIDER_NET_GTITCSERINT,
-	SPIDER_NET_GTIFMTERINT,
-	SPIDER_NET_GTIPKTRVKINT,
-	SPIDER_NET_GTISPINGINT,
-	SPIDER_NET_GTISADNGINT,
-	SPIDER_NET_GTISPDNGINT,
-	SPIDER_NET_GRIFMTERINT,
-	SPIDER_NET_GRIPKTRVKINT,
-	SPIDER_NET_GRISPINGINT,
-	SPIDER_NET_GRISADNGINT,
-	SPIDER_NET_GRISPDNGINT
-};
-
-#define SPIDER_NET_TXINT	(1 << SPIDER_NET_GDTFDCINT)
-
-/* We rely on flagged descriptor interrupts */
-#define SPIDER_NET_RXINT	( (1 << SPIDER_NET_GDAFDCINT) )
-
-#define SPIDER_NET_LINKINT	( 1 << SPIDER_NET_GMAC2INT )
-
-#define SPIDER_NET_ERRINT	( 0xffffffff & \
-				  (~SPIDER_NET_TXINT) & \
-				  (~SPIDER_NET_RXINT) & \
-				  (~SPIDER_NET_LINKINT) )
-
-#define SPIDER_NET_GPREXEC			0x80000000
-#define SPIDER_NET_GPRDAT_MASK			0x0000ffff
-
-#define SPIDER_NET_DMAC_NOINTR_COMPLETE		0x00800000
-#define SPIDER_NET_DMAC_TXFRMTL		0x00040000
-#define SPIDER_NET_DMAC_TCP			0x00020000
-#define SPIDER_NET_DMAC_UDP			0x00030000
-#define SPIDER_NET_TXDCEST			0x08000000
-
-#define SPIDER_NET_DESCR_RXFDIS        0x00000001
-#define SPIDER_NET_DESCR_RXDCEIS       0x00000002
-#define SPIDER_NET_DESCR_RXDEN0IS      0x00000004
-#define SPIDER_NET_DESCR_RXINVDIS      0x00000008
-#define SPIDER_NET_DESCR_RXRERRIS      0x00000010
-#define SPIDER_NET_DESCR_RXFDCIMS      0x00000100
-#define SPIDER_NET_DESCR_RXDCEIMS      0x00000200
-#define SPIDER_NET_DESCR_RXDEN0IMS     0x00000400
-#define SPIDER_NET_DESCR_RXINVDIMS     0x00000800
-#define SPIDER_NET_DESCR_RXRERRMIS     0x00001000
-#define SPIDER_NET_DESCR_UNUSED        0x077fe0e0
-
-#define SPIDER_NET_DESCR_IND_PROC_MASK		0xF0000000
-#define SPIDER_NET_DESCR_COMPLETE		0x00000000 /* used in rx and tx */
-#define SPIDER_NET_DESCR_RESPONSE_ERROR		0x10000000 /* used in rx and tx */
-#define SPIDER_NET_DESCR_PROTECTION_ERROR	0x20000000 /* used in rx and tx */
-#define SPIDER_NET_DESCR_FRAME_END		0x40000000 /* used in rx */
-#define SPIDER_NET_DESCR_FORCE_END		0x50000000 /* used in rx and tx */
-#define SPIDER_NET_DESCR_CARDOWNED		0xA0000000 /* used in rx and tx */
-#define SPIDER_NET_DESCR_NOT_IN_USE		0xF0000000
-#define SPIDER_NET_DESCR_TXDESFLG		0x00800000
-
-#define SPIDER_NET_DESCR_BAD_STATUS   (SPIDER_NET_DESCR_RXDEN0IS | \
-                                       SPIDER_NET_DESCR_RXRERRIS | \
-                                       SPIDER_NET_DESCR_RXDEN0IMS | \
-                                       SPIDER_NET_DESCR_RXINVDIMS | \
-                                       SPIDER_NET_DESCR_RXRERRMIS | \
-                                       SPIDER_NET_DESCR_UNUSED)
-
-/* Descriptor, as defined by the hardware */
-struct spider_net_hw_descr {
-	u32 buf_addr;
-	u32 buf_size;
-	u32 next_descr_addr;
-	u32 dmac_cmd_status;
-	u32 result_size;
-	u32 valid_size;	/* all zeroes for tx */
-	u32 data_status;
-	u32 data_error;	/* all zeroes for tx */
-} __attribute__((aligned(32)));
-
-struct spider_net_descr {
-	struct spider_net_hw_descr *hwdescr;
-	struct sk_buff *skb;
-	u32 bus_addr;
-	struct spider_net_descr *next;
-	struct spider_net_descr *prev;
-};
-
-struct spider_net_descr_chain {
-	spinlock_t lock;
-	struct spider_net_descr *head;
-	struct spider_net_descr *tail;
-	struct spider_net_descr *ring;
-	int num_desc;
-	struct spider_net_hw_descr *hwring;
-	dma_addr_t dma_addr;
-};
-
-/* descriptor data_status bits */
-#define SPIDER_NET_RX_IPCHK		29
-#define SPIDER_NET_RX_TCPCHK		28
-#define SPIDER_NET_VLAN_PACKET		21
-#define SPIDER_NET_DATA_STATUS_CKSUM_MASK ( (1 << SPIDER_NET_RX_IPCHK) | \
-					  (1 << SPIDER_NET_RX_TCPCHK) )
-
-/* descriptor data_error bits */
-#define SPIDER_NET_RX_IPCHKERR		27
-#define SPIDER_NET_RX_RXTCPCHKERR	28
-
-#define SPIDER_NET_DATA_ERR_CKSUM_MASK	(1 << SPIDER_NET_RX_IPCHKERR)
-
-/* the cases we don't pass the packet to the stack.
- * 701b8000 would be correct, but every packets gets that flag */
-#define SPIDER_NET_DESTROY_RX_FLAGS	0x700b8000
-
-#define SPIDER_NET_DEFAULT_MSG		( NETIF_MSG_DRV | \
-					  NETIF_MSG_PROBE | \
-					  NETIF_MSG_LINK | \
-					  NETIF_MSG_TIMER | \
-					  NETIF_MSG_IFDOWN | \
-					  NETIF_MSG_IFUP | \
-					  NETIF_MSG_RX_ERR | \
-					  NETIF_MSG_TX_ERR | \
-					  NETIF_MSG_TX_QUEUED | \
-					  NETIF_MSG_INTR | \
-					  NETIF_MSG_TX_DONE | \
-					  NETIF_MSG_RX_STATUS | \
-					  NETIF_MSG_PKTDATA | \
-					  NETIF_MSG_HW | \
-					  NETIF_MSG_WOL )
-
-struct spider_net_extra_stats {
-	unsigned long rx_desc_error;
-	unsigned long tx_timeouts;
-	unsigned long alloc_rx_skb_error;
-	unsigned long rx_iommu_map_error;
-	unsigned long tx_iommu_map_error;
-	unsigned long rx_desc_unk_state;
-};
-
-struct spider_net_card {
-	struct net_device *netdev;
-	struct pci_dev *pdev;
-	struct mii_phy phy;
-
-	struct napi_struct napi;
-
-	int medium;
-
-	void __iomem *regs;
-
-	struct spider_net_descr_chain tx_chain;
-	struct spider_net_descr_chain rx_chain;
-	struct spider_net_descr *low_watermark;
-
-	int aneg_count;
-	struct timer_list aneg_timer;
-	struct timer_list tx_timer;
-	struct work_struct tx_timeout_task;
-	atomic_t tx_timeout_task_counter;
-	wait_queue_head_t waitq;
-	int num_rx_ints;
-	int ignore_rx_ramfull;
-
-	/* for ethtool */
-	int msg_enable;
-	struct spider_net_extra_stats spider_stats;
-
-	/* Must be last item in struct */
-	struct spider_net_descr darray[];
-};
-
-#endif
diff --git a/drivers/net/ethernet/toshiba/spider_net_ethtool.c b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
deleted file mode 100644
index fef9fd127b5e..000000000000
--- a/drivers/net/ethernet/toshiba/spider_net_ethtool.c
+++ /dev/null
@@ -1,174 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Network device driver for Cell Processor-Based Blade
- *
- * (C) Copyright IBM Corp. 2005
- *
- * Authors : Utz Bacher <utz.bacher@de.ibm.com>
- *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
- */
-
-#include <linux/netdevice.h>
-#include <linux/ethtool.h>
-#include <linux/pci.h>
-
-#include "spider_net.h"
-
-
-static struct {
-	const char str[ETH_GSTRING_LEN];
-} ethtool_stats_keys[] = {
-	{ "tx_packets" },
-	{ "tx_bytes" },
-	{ "rx_packets" },
-	{ "rx_bytes" },
-	{ "tx_errors" },
-	{ "tx_dropped" },
-	{ "rx_dropped" },
-	{ "rx_descriptor_error" },
-	{ "tx_timeouts" },
-	{ "alloc_rx_skb_error" },
-	{ "rx_iommu_map_error" },
-	{ "tx_iommu_map_error" },
-	{ "rx_desc_unk_state" },
-};
-
-static int
-spider_net_ethtool_get_link_ksettings(struct net_device *netdev,
-				      struct ethtool_link_ksettings *cmd)
-{
-	struct spider_net_card *card;
-	card = netdev_priv(netdev);
-
-	ethtool_link_ksettings_zero_link_mode(cmd, supported);
-	ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
-	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
-
-	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
-	ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
-	ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
-
-	cmd->base.port = PORT_FIBRE;
-	cmd->base.speed = card->phy.speed;
-	cmd->base.duplex = DUPLEX_FULL;
-
-	return 0;
-}
-
-static void
-spider_net_ethtool_get_drvinfo(struct net_device *netdev,
-			       struct ethtool_drvinfo *drvinfo)
-{
-	struct spider_net_card *card;
-	card = netdev_priv(netdev);
-
-	/* clear and fill out info */
-	strscpy(drvinfo->driver, spider_net_driver_name,
-		sizeof(drvinfo->driver));
-	strscpy(drvinfo->version, VERSION, sizeof(drvinfo->version));
-	strscpy(drvinfo->fw_version, "no information",
-		sizeof(drvinfo->fw_version));
-	strscpy(drvinfo->bus_info, pci_name(card->pdev),
-		sizeof(drvinfo->bus_info));
-}
-
-static void
-spider_net_ethtool_get_wol(struct net_device *netdev,
-			   struct ethtool_wolinfo *wolinfo)
-{
-	/* no support for wol */
-	wolinfo->supported = 0;
-	wolinfo->wolopts = 0;
-}
-
-static u32
-spider_net_ethtool_get_msglevel(struct net_device *netdev)
-{
-	struct spider_net_card *card;
-	card = netdev_priv(netdev);
-	return card->msg_enable;
-}
-
-static void
-spider_net_ethtool_set_msglevel(struct net_device *netdev,
-				u32 level)
-{
-	struct spider_net_card *card;
-	card = netdev_priv(netdev);
-	card->msg_enable = level;
-}
-
-static int
-spider_net_ethtool_nway_reset(struct net_device *netdev)
-{
-	if (netif_running(netdev)) {
-		spider_net_stop(netdev);
-		spider_net_open(netdev);
-	}
-	return 0;
-}
-
-static void
-spider_net_ethtool_get_ringparam(struct net_device *netdev,
-				 struct ethtool_ringparam *ering,
-				 struct kernel_ethtool_ringparam *kernel_ering,
-				 struct netlink_ext_ack *extack)
-{
-	struct spider_net_card *card = netdev_priv(netdev);
-
-	ering->tx_max_pending = SPIDER_NET_TX_DESCRIPTORS_MAX;
-	ering->tx_pending = card->tx_chain.num_desc;
-	ering->rx_max_pending = SPIDER_NET_RX_DESCRIPTORS_MAX;
-	ering->rx_pending = card->rx_chain.num_desc;
-}
-
-static int spider_net_get_sset_count(struct net_device *netdev, int sset)
-{
-	switch (sset) {
-	case ETH_SS_STATS:
-		return ARRAY_SIZE(ethtool_stats_keys);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static void spider_net_get_ethtool_stats(struct net_device *netdev,
-		struct ethtool_stats *stats, u64 *data)
-{
-	struct spider_net_card *card = netdev_priv(netdev);
-
-	data[0] = netdev->stats.tx_packets;
-	data[1] = netdev->stats.tx_bytes;
-	data[2] = netdev->stats.rx_packets;
-	data[3] = netdev->stats.rx_bytes;
-	data[4] = netdev->stats.tx_errors;
-	data[5] = netdev->stats.tx_dropped;
-	data[6] = netdev->stats.rx_dropped;
-	data[7] = card->spider_stats.rx_desc_error;
-	data[8] = card->spider_stats.tx_timeouts;
-	data[9] = card->spider_stats.alloc_rx_skb_error;
-	data[10] = card->spider_stats.rx_iommu_map_error;
-	data[11] = card->spider_stats.tx_iommu_map_error;
-	data[12] = card->spider_stats.rx_desc_unk_state;
-}
-
-static void spider_net_get_strings(struct net_device *netdev, u32 stringset,
-				   u8 *data)
-{
-	memcpy(data, ethtool_stats_keys, sizeof(ethtool_stats_keys));
-}
-
-const struct ethtool_ops spider_net_ethtool_ops = {
-	.get_drvinfo		= spider_net_ethtool_get_drvinfo,
-	.get_wol		= spider_net_ethtool_get_wol,
-	.get_msglevel		= spider_net_ethtool_get_msglevel,
-	.set_msglevel		= spider_net_ethtool_set_msglevel,
-	.get_link		= ethtool_op_get_link,
-	.nway_reset		= spider_net_ethtool_nway_reset,
-	.get_ringparam          = spider_net_ethtool_get_ringparam,
-	.get_strings		= spider_net_get_strings,
-	.get_sset_count		= spider_net_get_sset_count,
-	.get_ethtool_stats	= spider_net_get_ethtool_stats,
-	.get_link_ksettings	= spider_net_ethtool_get_link_ksettings,
-};
-
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index c6957e3b7f0f..7e0b3d694ac0 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1379,7 +1379,7 @@ static int tsi108_close(struct net_device *dev)
 	netif_stop_queue(dev);
 	napi_disable(&data->napi);
 
-	del_timer_sync(&data->timer);
+	timer_delete_sync(&data->timer);
 
 	tsi108_stop_ethernet(dev);
 	tsi108_kill_phy(dev);
@@ -1652,7 +1652,7 @@ regs_fail:
 
 static void tsi108_timed_checker(struct timer_list *t)
 {
-	struct tsi108_prv_data *data = from_timer(data, t, timer);
+	struct tsi108_prv_data *data = timer_container_of(data, t, timer);
 	struct net_device *dev = data->dev;
 
 	tsi108_check_phy(dev);
diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 89dc4c401a8d..a75bca1243e3 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -6,7 +6,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/if_vlan.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
@@ -15,6 +17,7 @@
 #include <linux/cache.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/string_choices.h>
 
 #include <linux/spi/spi.h>
 #include <linux/of_net.h>
@@ -33,7 +36,7 @@
 #define CMD_CTR		(0x2 << CMD_SHIFT)
 
 #define CMD_MASK	GENMASK(15, CMD_SHIFT)
-#define LEN_MASK	GENMASK(CMD_SHIFT - 1, 0)
+#define LEN_MASK	GENMASK(CMD_SHIFT - 2, 0)
 
 #define DET_CMD_LEN	4
 #define DET_SOF_LEN	2
@@ -44,7 +47,6 @@
 
 struct mse102x_stats {
 	u64 xfer_err;
-	u64 invalid_cmd;
 	u64 invalid_ctr;
 	u64 invalid_dft;
 	u64 invalid_len;
@@ -55,7 +57,6 @@ struct mse102x_stats {
 
 static const char mse102x_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"SPI transfer errors",
-	"Invalid command",
 	"Invalid CTR",
 	"Invalid DFT",
 	"Invalid frame length",
@@ -84,6 +85,8 @@ struct mse102x_net_spi {
 	struct spi_message	spi_msg;
 	struct spi_transfer	spi_xfer;
 
+	bool			valid_cmd_received;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry		*device_root;
 #endif
@@ -97,16 +100,18 @@ static int mse102x_info_show(struct seq_file *s, void *what)
 {
 	struct mse102x_net_spi *mses = s->private;
 
-	seq_printf(s, "TX ring size        : %u\n",
+	seq_printf(s, "TX ring size            : %u\n",
 		   skb_queue_len(&mses->mse102x.txq));
 
-	seq_printf(s, "IRQ                 : %d\n",
+	seq_printf(s, "IRQ                     : %d\n",
 		   mses->spidev->irq);
 
-	seq_printf(s, "SPI effective speed : %lu\n",
+	seq_printf(s, "SPI effective speed     : %lu\n",
 		   (unsigned long)mses->spi_xfer.effective_speed_hz);
-	seq_printf(s, "SPI mode            : %x\n",
+	seq_printf(s, "SPI mode                : %x\n",
 		   mses->spidev->mode);
+	seq_printf(s, "Received valid CMD once : %s\n",
+		   str_yes_no(mses->valid_cmd_received));
 
 	return 0;
 }
@@ -193,10 +198,10 @@ static int mse102x_rx_cmd_spi(struct mse102x_net *mse, u8 *rxb)
 	} else if (*cmd != cpu_to_be16(DET_CMD)) {
 		net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
 				    __func__, *cmd);
-		mse->stats.invalid_cmd++;
 		ret = -EIO;
 	} else {
 		memcpy(rxb, trx + 2, 2);
+		mses->valid_cmd_received = true;
 	}
 
 	return ret;
@@ -262,7 +267,7 @@ static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp,
 }
 
 static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
-				unsigned int frame_len)
+				unsigned int frame_len, bool drop)
 {
 	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
 	struct spi_transfer *xfer = &mses->spi_xfer;
@@ -280,6 +285,9 @@ static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
 		netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n",
 			   __func__, ret);
 		mse->stats.xfer_err++;
+	} else if (drop) {
+		netdev_dbg(mse->ndev, "%s: Drop frame\n", __func__);
+		ret = -EINVAL;
 	} else if (*sof != cpu_to_be16(DET_SOF)) {
 		netdev_dbg(mse->ndev, "%s: SPI start of frame is invalid (0x%04x)\n",
 			   __func__, *sof);
@@ -302,61 +310,60 @@ static void mse102x_dump_packet(const char *msg, int len, const char *data)
 		       data, len, true);
 }
 
-static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
+static irqreturn_t mse102x_rx_pkt_spi(struct mse102x_net *mse)
 {
 	struct sk_buff *skb;
 	unsigned int rxalign;
 	unsigned int rxlen;
+	bool drop = false;
 	__be16 rx = 0;
 	u16 cmd_resp;
 	u8 *rxpkt;
-	int ret;
 
 	mse102x_tx_cmd_spi(mse, CMD_CTR);
-	ret = mse102x_rx_cmd_spi(mse, (u8 *)&rx);
-	cmd_resp = be16_to_cpu(rx);
-
-	if (ret || ((cmd_resp & CMD_MASK) != CMD_RTS)) {
+	if (mse102x_rx_cmd_spi(mse, (u8 *)&rx)) {
 		usleep_range(50, 100);
+		return IRQ_NONE;
+	}
 
-		mse102x_tx_cmd_spi(mse, CMD_CTR);
-		ret = mse102x_rx_cmd_spi(mse, (u8 *)&rx);
-		if (ret)
-			return;
-
-		cmd_resp = be16_to_cpu(rx);
-		if ((cmd_resp & CMD_MASK) != CMD_RTS) {
-			net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
-					    __func__, cmd_resp);
-			mse->stats.invalid_rts++;
-			return;
-		}
-
-		net_dbg_ratelimited("%s: Unexpected response to first CMD\n",
-				    __func__);
+	cmd_resp = be16_to_cpu(rx);
+	if ((cmd_resp & CMD_MASK) != CMD_RTS) {
+		net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
+				    __func__, cmd_resp);
+		mse->stats.invalid_rts++;
+		drop = true;
+		goto drop;
 	}
 
 	rxlen = cmd_resp & LEN_MASK;
-	if (!rxlen) {
-		net_dbg_ratelimited("%s: No frame length defined\n", __func__);
+	if (rxlen < ETH_ZLEN || rxlen > VLAN_ETH_FRAME_LEN) {
+		net_dbg_ratelimited("%s: Invalid frame length: %d\n", __func__,
+				    rxlen);
 		mse->stats.invalid_len++;
-		return;
+		drop = true;
 	}
 
+	/* In case of a invalid CMD_RTS, the frame must be consumed anyway.
+	 * So assume the maximum possible frame length.
+	 */
+drop:
+	if (drop)
+		rxlen = VLAN_ETH_FRAME_LEN;
+
 	rxalign = ALIGN(rxlen + DET_SOF_LEN + DET_DFT_LEN, 4);
 	skb = netdev_alloc_skb_ip_align(mse->ndev, rxalign);
 	if (!skb)
-		return;
+		return IRQ_NONE;
 
 	/* 2 bytes Start of frame (before ethernet header)
 	 * 2 bytes Data frame tail (after ethernet frame)
 	 * They are copied, but ignored.
 	 */
 	rxpkt = skb_put(skb, rxlen) - DET_SOF_LEN;
-	if (mse102x_rx_frame_spi(mse, rxpkt, rxlen)) {
+	if (mse102x_rx_frame_spi(mse, rxpkt, rxlen, drop)) {
 		mse->ndev->stats.rx_errors++;
 		dev_kfree_skb(skb);
-		return;
+		return IRQ_HANDLED;
 	}
 
 	if (netif_msg_pktdata(mse))
@@ -367,6 +374,8 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
 
 	mse->ndev->stats.rx_packets++;
 	mse->ndev->stats.rx_bytes += rxlen;
+
+	return IRQ_HANDLED;
 }
 
 static int mse102x_tx_pkt_spi(struct mse102x_net *mse, struct sk_buff *txb,
@@ -498,19 +507,36 @@ static irqreturn_t mse102x_irq(int irq, void *_mse)
 {
 	struct mse102x_net *mse = _mse;
 	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
+	irqreturn_t ret;
 
 	mutex_lock(&mses->lock);
-	mse102x_rx_pkt_spi(mse);
+	ret = mse102x_rx_pkt_spi(mse);
 	mutex_unlock(&mses->lock);
 
-	return IRQ_HANDLED;
+	return ret;
 }
 
 static int mse102x_net_open(struct net_device *ndev)
 {
+	struct irq_data *irq_data = irq_get_irq_data(ndev->irq);
 	struct mse102x_net *mse = netdev_priv(ndev);
+	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
 	int ret;
 
+	if (!irq_data) {
+		netdev_err(ndev, "Invalid IRQ: %d\n", ndev->irq);
+		return -EINVAL;
+	}
+
+	switch (irqd_get_trigger_type(irq_data)) {
+	case IRQ_TYPE_LEVEL_HIGH:
+	case IRQ_TYPE_LEVEL_LOW:
+		break;
+	default:
+		netdev_warn_once(ndev, "Only IRQ type level recommended, please update your device tree firmware.\n");
+		break;
+	}
+
 	ret = request_threaded_irq(ndev->irq, NULL, mse102x_irq, IRQF_ONESHOT,
 				   ndev->name, mse);
 	if (ret < 0) {
@@ -524,6 +550,14 @@ static int mse102x_net_open(struct net_device *ndev)
 
 	netif_carrier_on(ndev);
 
+	/* The SPI interrupt can stuck in case of pending packet(s).
+	 * So poll for possible packet(s) to re-arm the interrupt.
+	 */
+	mutex_lock(&mses->lock);
+	if (mse102x_rx_pkt_spi(mse) == IRQ_NONE)
+		mse102x_rx_pkt_spi(mse);
+	mutex_unlock(&mses->lock);
+
 	netif_dbg(mse, ifup, ndev, "network device up\n");
 
 	return 0;
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 894911f3d560..e56ebbdd428d 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -1568,7 +1568,7 @@ static void init_registers(struct net_device *dev)
 	if (rp->quirks & rqMgmt)
 		rhine_init_cam_filter(dev);
 
-	napi_enable(&rp->napi);
+	napi_enable_locked(&rp->napi);
 
 	iowrite16(RHINE_EVENT & 0xffff, ioaddr + IntrEnable);
 
@@ -1696,7 +1696,10 @@ static int rhine_open(struct net_device *dev)
 	rhine_power_init(dev);
 	rhine_chip_reset(dev);
 	rhine_task_enable(rp);
+
+	netdev_lock(dev);
 	init_registers(dev);
+	netdev_unlock(dev);
 
 	netif_dbg(rp, ifup, dev, "%s() Done - status %04x MII status: %04x\n",
 		  __func__, ioread16(ioaddr + ChipCmd),
@@ -1727,6 +1730,8 @@ static void rhine_reset_task(struct work_struct *work)
 
 	napi_disable(&rp->napi);
 	netif_tx_disable(dev);
+
+	netdev_lock(dev);
 	spin_lock_bh(&rp->lock);
 
 	/* clear all descriptors */
@@ -1740,6 +1745,7 @@ static void rhine_reset_task(struct work_struct *work)
 	init_registers(dev);
 
 	spin_unlock_bh(&rp->lock);
+	netdev_unlock(dev);
 
 	netif_trans_update(dev); /* prevent tx timeout */
 	dev->stats.tx_errors++;
@@ -2541,9 +2547,12 @@ static int rhine_resume(struct device *device)
 	alloc_tbufs(dev);
 	rhine_reset_rbufs(rp);
 	rhine_task_enable(rp);
+
+	netdev_lock(dev);
 	spin_lock_bh(&rp->lock);
 	init_registers(dev);
 	spin_unlock_bh(&rp->lock);
+	netdev_unlock(dev);
 
 	netif_device_attach(dev);
 
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index dd4a07c97eee..5aa93144a4f5 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -2320,7 +2320,8 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu)
 		if (ret < 0)
 			goto out_free_tmp_vptr_1;
 
-		napi_disable(&vptr->napi);
+		netdev_lock(dev);
+		napi_disable_locked(&vptr->napi);
 
 		spin_lock_irqsave(&vptr->lock, flags);
 
@@ -2342,12 +2343,13 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu)
 
 		velocity_give_many_rx_descs(vptr);
 
-		napi_enable(&vptr->napi);
+		napi_enable_locked(&vptr->napi);
 
 		mac_enable_int(vptr->mac_regs);
 		netif_start_queue(dev);
 
 		spin_unlock_irqrestore(&vptr->lock, flags);
+		netdev_unlock(dev);
 
 		velocity_free_rings(tmp_vptr);
 
diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig
index e46ccebcfd22..e5fc942c28cc 100644
--- a/drivers/net/ethernet/wangxun/Kconfig
+++ b/drivers/net/ethernet/wangxun/Kconfig
@@ -18,6 +18,7 @@ if NET_VENDOR_WANGXUN
 
 config LIBWX
 	tristate
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select PAGE_POOL
 	help
 	Common library for Wangxun(R) Ethernet drivers.
@@ -25,6 +26,7 @@ config LIBWX
 config NGBE
 	tristate "Wangxun(R) GbE PCI Express adapters support"
 	depends on PCI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select LIBWX
 	select PHYLINK
 	help
@@ -38,10 +40,11 @@ config NGBE
 	  will be called ngbe.
 
 config TXGBE
-	tristate "Wangxun(R) 10GbE PCI Express adapters support"
+	tristate "Wangxun(R) 10/25/40GbE PCI Express adapters support"
 	depends on PCI
 	depends on COMMON_CLK
 	depends on I2C_DESIGNWARE_PLATFORM
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MARVELL_10G_PHY
 	select REGMAP
 	select PHYLINK
@@ -52,7 +55,7 @@ config TXGBE
 	select PCS_XPCS
 	select LIBWX
 	help
-	  This driver supports Wangxun(R) 10GbE PCI Express family of
+	  This driver supports Wangxun(R) 10/25/40GbE PCI Express family of
 	  adapters.
 
 	  More specific information on configuring the driver is in
diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile
index 42ccd6e4052e..9b78b604a94e 100644
--- a/drivers/net/ethernet/wangxun/libwx/Makefile
+++ b/drivers/net/ethernet/wangxun/libwx/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_LIBWX) += libwx.o
 
-libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o
+libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o wx_mbx.o wx_sriov.o
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index abe5921dde02..c12a4cb951f6 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -41,6 +41,9 @@ static const struct wx_stats wx_gstrings_stats[] = {
 	WX_STAT("rx_csum_offload_good_count", hw_csum_rx_good),
 	WX_STAT("rx_csum_offload_errors", hw_csum_rx_error),
 	WX_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed),
+	WX_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
+	WX_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped),
+	WX_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
 };
 
 static const struct wx_stats wx_gstrings_fdir_stats[] = {
@@ -69,7 +72,7 @@ int wx_get_sset_count(struct net_device *netdev, int sset)
 
 	switch (sset) {
 	case ETH_SS_STATS:
-		return (wx->mac.type == wx_mac_sp) ?
+		return (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) ?
 			WX_STATS_LEN + WX_FDIR_STATS_LEN : WX_STATS_LEN;
 	default:
 		return -EOPNOTSUPP;
@@ -87,7 +90,7 @@ void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	case ETH_SS_STATS:
 		for (i = 0; i < WX_GLOBAL_STATS_LEN; i++)
 			ethtool_puts(&p, wx_gstrings_stats[i].stat_string);
-		if (wx->mac.type == wx_mac_sp) {
+		if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) {
 			for (i = 0; i < WX_FDIR_STATS_LEN; i++)
 				ethtool_puts(&p, wx_gstrings_fdir_stats[i].stat_string);
 		}
@@ -121,7 +124,7 @@ void wx_get_ethtool_stats(struct net_device *netdev,
 			   sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) {
 		for (k = 0; k < WX_FDIR_STATS_LEN; k++) {
 			p = (char *)wx + wx_gstrings_fdir_stats[k].stat_offset;
 			data[i++] = *(u64 *)p;
@@ -196,7 +199,7 @@ void wx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info)
 	unsigned int stats_len = WX_STATS_LEN;
 	struct wx *wx = netdev_priv(netdev);
 
-	if (wx->mac.type == wx_mac_sp)
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))
 		stats_len += WX_FDIR_STATS_LEN;
 
 	strscpy(info->driver, wx->driver_name, sizeof(info->driver));
@@ -216,6 +219,9 @@ int wx_nway_reset(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml40)
+		return -EOPNOTSUPP;
+
 	return phylink_ethtool_nway_reset(wx->phylink);
 }
 EXPORT_SYMBOL(wx_nway_reset);
@@ -234,6 +240,9 @@ int wx_set_link_ksettings(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml40)
+		return -EOPNOTSUPP;
+
 	return phylink_ethtool_ksettings_set(wx->phylink, cmd);
 }
 EXPORT_SYMBOL(wx_set_link_ksettings);
@@ -243,6 +252,9 @@ void wx_get_pauseparam(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml40)
+		return;
+
 	phylink_ethtool_get_pauseparam(wx->phylink, pause);
 }
 EXPORT_SYMBOL(wx_get_pauseparam);
@@ -252,6 +264,9 @@ int wx_set_pauseparam(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml40)
+		return -EOPNOTSUPP;
+
 	return phylink_ethtool_set_pauseparam(wx->phylink, pause);
 }
 EXPORT_SYMBOL(wx_set_pauseparam);
@@ -322,10 +337,18 @@ int wx_set_coalesce(struct net_device *netdev,
 	if (ec->tx_max_coalesced_frames_irq)
 		wx->tx_work_limit = ec->tx_max_coalesced_frames_irq;
 
-	if (wx->mac.type == wx_mac_sp)
+	switch (wx->mac.type) {
+	case wx_mac_sp:
 		max_eitr = WX_SP_MAX_EITR;
-	else
+		break;
+	case wx_mac_aml:
+	case wx_mac_aml40:
+		max_eitr = WX_AML_MAX_EITR;
+		break;
+	default:
 		max_eitr = WX_EM_MAX_EITR;
+		break;
+	}
 
 	if ((ec->rx_coalesce_usecs > (max_eitr >> 2)) ||
 	    (ec->tx_coalesce_usecs > (max_eitr >> 2)))
@@ -347,10 +370,16 @@ int wx_set_coalesce(struct net_device *netdev,
 		wx->tx_itr_setting = ec->tx_coalesce_usecs;
 
 	if (wx->tx_itr_setting == 1) {
-		if (wx->mac.type == wx_mac_sp)
+		switch (wx->mac.type) {
+		case wx_mac_sp:
+		case wx_mac_aml:
+		case wx_mac_aml40:
 			tx_itr_param = WX_12K_ITR;
-		else
+			break;
+		default:
 			tx_itr_param = WX_20K_ITR;
+			break;
+		}
 	} else {
 		tx_itr_param = wx->tx_itr_setting;
 	}
@@ -383,7 +412,7 @@ static unsigned int wx_max_channels(struct wx *wx)
 		max_combined = 1;
 	} else {
 		/* support up to max allowed queues with RSS */
-		if (wx->mac.type == wx_mac_sp)
+		if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
 			max_combined = 63;
 		else
 			max_combined = 8;
@@ -452,3 +481,53 @@ void wx_set_msglevel(struct net_device *netdev, u32 data)
 	wx->msg_enable = data;
 }
 EXPORT_SYMBOL(wx_set_msglevel);
+
+int wx_get_ts_info(struct net_device *dev,
+		   struct kernel_ethtool_ts_info *info)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			   BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_EVENT);
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	if (wx->ptp_clock)
+		info->phc_index = ptp_clock_index(wx->ptp_clock);
+	else
+		info->phc_index = -1;
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) |
+			 BIT(HWTSTAMP_TX_ON);
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_get_ts_info);
+
+void wx_get_ptp_stats(struct net_device *dev,
+		      struct ethtool_ts_stats *ts_stats)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	if (wx->ptp_clock) {
+		ts_stats->pkts = wx->tx_hwtstamp_pkts;
+		ts_stats->lost = wx->tx_hwtstamp_timeouts +
+				 wx->tx_hwtstamp_skipped +
+				 wx->rx_hwtstamp_cleared;
+		ts_stats->err = wx->tx_hwtstamp_errors;
+	}
+}
+EXPORT_SYMBOL(wx_get_ptp_stats);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
index 600c3b597d1a..9e002e699eca 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
@@ -40,4 +40,8 @@ int wx_set_channels(struct net_device *dev,
 		    struct ethtool_channels *ch);
 u32 wx_get_msglevel(struct net_device *netdev);
 void wx_set_msglevel(struct net_device *netdev, u32 data);
+int wx_get_ts_info(struct net_device *dev,
+		   struct kernel_ethtool_ts_info *info);
+void wx_get_ptp_stats(struct net_device *dev,
+		      struct ethtool_ts_stats *ts_stats);
 #endif /* _WX_ETHTOOL_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index 1bf9c38e4125..0f4be72116b8 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -10,6 +10,7 @@
 
 #include "wx_type.h"
 #include "wx_lib.h"
+#include "wx_sriov.h"
 #include "wx_hw.h"
 
 static int wx_phy_read_reg_mdi(struct mii_bus *bus, int phy_addr, int devnum, int regnum)
@@ -112,7 +113,7 @@ static void wx_intr_disable(struct wx *wx, u64 qmask)
 	if (mask)
 		wr32(wx, WX_PX_IMS(0), mask);
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		mask = (qmask >> 32);
 		if (mask)
 			wr32(wx, WX_PX_IMS(1), mask);
@@ -126,7 +127,8 @@ void wx_intr_enable(struct wx *wx, u64 qmask)
 	mask = (qmask & U32_MAX);
 	if (mask)
 		wr32(wx, WX_PX_IMC(0), mask);
-	if (wx->mac.type == wx_mac_sp) {
+
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		mask = (qmask >> 32);
 		if (mask)
 			wr32(wx, WX_PX_IMC(1), mask);
@@ -278,22 +280,8 @@ static int wx_acquire_sw_sync(struct wx *wx, u32 mask)
 	return ret;
 }
 
-/**
- *  wx_host_interface_command - Issue command to manageability block
- *  @wx: pointer to the HW structure
- *  @buffer: contains the command to write and where the return status will
- *   be placed
- *  @length: length of buffer, must be multiple of 4 bytes
- *  @timeout: time in ms to wait for command completion
- *  @return_data: read and return data from the buffer (true) or not (false)
- *   Needed because FW structures are big endian and decoding of
- *   these fields can be 8 bit or 16 bit based on command. Decoding
- *   is not easily understood without making a table of commands.
- *   So we will leave this up to the caller to read back the data
- *   in these cases.
- **/
-int wx_host_interface_command(struct wx *wx, u32 *buffer,
-			      u32 length, u32 timeout, bool return_data)
+static int wx_host_interface_command_s(struct wx *wx, u32 *buffer,
+				       u32 length, u32 timeout, bool return_data)
 {
 	u32 hdr_size = sizeof(struct wx_hic_hdr);
 	u32 hicr, i, bi, buf[64] = {};
@@ -301,22 +289,10 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer,
 	u32 dword_len;
 	u16 buf_len;
 
-	if (length == 0 || length > WX_HI_MAX_BLOCK_BYTE_LENGTH) {
-		wx_err(wx, "Buffer length failure buffersize=%d.\n", length);
-		return -EINVAL;
-	}
-
 	status = wx_acquire_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_MB);
 	if (status != 0)
 		return status;
 
-	/* Calculate length in DWORDs. We must be DWORD aligned */
-	if ((length % (sizeof(u32))) != 0) {
-		wx_err(wx, "Buffer length failure, not aligned to dword");
-		status = -EINVAL;
-		goto rel_out;
-	}
-
 	dword_len = length >> 2;
 
 	/* The device driver writes the relevant command block
@@ -334,27 +310,25 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer,
 	status = read_poll_timeout(rd32, hicr, hicr & WX_MNG_MBOX_CTL_FWRDY, 1000,
 				   timeout * 1000, false, wx, WX_MNG_MBOX_CTL);
 
+	buf[0] = rd32(wx, WX_MNG_MBOX);
+	if ((buf[0] & 0xff0000) >> 16 == 0x80) {
+		wx_err(wx, "Unknown FW command: 0x%x\n", buffer[0] & 0xff);
+		status = -EINVAL;
+		goto rel_out;
+	}
+
 	/* Check command completion */
 	if (status) {
-		wx_dbg(wx, "Command has failed with no status valid.\n");
-
-		buf[0] = rd32(wx, WX_MNG_MBOX);
-		if ((buffer[0] & 0xff) != (~buf[0] >> 24)) {
-			status = -EINVAL;
-			goto rel_out;
-		}
-		if ((buf[0] & 0xff0000) >> 16 == 0x80) {
-			wx_dbg(wx, "It's unknown cmd.\n");
-			status = -EINVAL;
-			goto rel_out;
-		}
-
+		wx_err(wx, "Command has failed with no status valid.\n");
 		wx_dbg(wx, "write value:\n");
 		for (i = 0; i < dword_len; i++)
 			wx_dbg(wx, "%x ", buffer[i]);
 		wx_dbg(wx, "read value:\n");
 		for (i = 0; i < dword_len; i++)
 			wx_dbg(wx, "%x ", buf[i]);
+		wx_dbg(wx, "\ncheck: %x %x\n", buffer[0] & 0xff, ~buf[0] >> 24);
+
+		goto rel_out;
 	}
 
 	if (!return_data)
@@ -393,8 +367,166 @@ rel_out:
 	wx_release_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_MB);
 	return status;
 }
+
+static bool wx_poll_fw_reply(struct wx *wx, u32 *buffer, u8 send_cmd)
+{
+	u32 dword_len = sizeof(struct wx_hic_hdr) >> 2;
+	struct wx_hic_hdr *recv_hdr;
+	u32 i;
+
+	/* read hdr */
+	for (i = 0; i < dword_len; i++) {
+		buffer[i] = rd32a(wx, WX_FW2SW_MBOX, i);
+		le32_to_cpus(&buffer[i]);
+	}
+
+	/* check hdr */
+	recv_hdr = (struct wx_hic_hdr *)buffer;
+	if (recv_hdr->cmd == send_cmd &&
+	    recv_hdr->index == wx->swfw_index)
+		return true;
+
+	return false;
+}
+
+static int wx_host_interface_command_r(struct wx *wx, u32 *buffer,
+				       u32 length, u32 timeout, bool return_data)
+{
+	struct wx_hic_hdr *hdr = (struct wx_hic_hdr *)buffer;
+	u32 hdr_size = sizeof(struct wx_hic_hdr);
+	bool busy, reply;
+	u32 dword_len;
+	u16 buf_len;
+	int err = 0;
+	u8 send_cmd;
+	u32 i;
+
+	/* wait to get lock */
+	might_sleep();
+	err = read_poll_timeout(test_and_set_bit, busy, !busy, 1000, timeout * 1000,
+				false, WX_STATE_SWFW_BUSY, wx->state);
+	if (err)
+		return err;
+
+	/* index to unique seq id for each mbox message */
+	hdr->index = wx->swfw_index;
+	send_cmd = hdr->cmd;
+
+	dword_len = length >> 2;
+	/* write data to SW-FW mbox array */
+	for (i = 0; i < dword_len; i++) {
+		wr32a(wx, WX_SW2FW_MBOX, i, (__force u32)cpu_to_le32(buffer[i]));
+		/* write flush */
+		rd32a(wx, WX_SW2FW_MBOX, i);
+	}
+
+	/* generate interrupt to notify FW */
+	wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, 0);
+	wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, WX_SW2FW_MBOX_CMD_VLD);
+
+	/* polling reply from FW */
+	err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 2000,
+				timeout * 1000, true, wx, buffer, send_cmd);
+	if (err) {
+		wx_err(wx, "Polling from FW messages timeout, cmd: 0x%x, index: %d\n",
+		       send_cmd, wx->swfw_index);
+		goto rel_out;
+	}
+
+	if (hdr->cmd_or_resp.ret_status == 0x80) {
+		wx_err(wx, "Unknown FW command: 0x%x\n", send_cmd);
+		err = -EINVAL;
+		goto rel_out;
+	}
+
+	/* expect no reply from FW then return */
+	if (!return_data)
+		goto rel_out;
+
+	/* If there is any thing in data position pull it in */
+	buf_len = hdr->buf_len;
+	if (buf_len == 0)
+		goto rel_out;
+
+	if (length < buf_len + hdr_size) {
+		wx_err(wx, "Buffer not large enough for reply message.\n");
+		err = -EFAULT;
+		goto rel_out;
+	}
+
+	/* Calculate length in DWORDs, add 3 for odd lengths */
+	dword_len = (buf_len + 3) >> 2;
+	for (i = hdr_size >> 2; i <= dword_len; i++) {
+		buffer[i] = rd32a(wx, WX_FW2SW_MBOX, i);
+		le32_to_cpus(&buffer[i]);
+	}
+
+rel_out:
+	/* index++, index replace wx_hic_hdr.checksum */
+	if (wx->swfw_index == WX_HIC_HDR_INDEX_MAX)
+		wx->swfw_index = 0;
+	else
+		wx->swfw_index++;
+
+	clear_bit(WX_STATE_SWFW_BUSY, wx->state);
+	return err;
+}
+
+/**
+ *  wx_host_interface_command - Issue command to manageability block
+ *  @wx: pointer to the HW structure
+ *  @buffer: contains the command to write and where the return status will
+ *   be placed
+ *  @length: length of buffer, must be multiple of 4 bytes
+ *  @timeout: time in ms to wait for command completion
+ *  @return_data: read and return data from the buffer (true) or not (false)
+ *   Needed because FW structures are big endian and decoding of
+ *   these fields can be 8 bit or 16 bit based on command. Decoding
+ *   is not easily understood without making a table of commands.
+ *   So we will leave this up to the caller to read back the data
+ *   in these cases.
+ **/
+int wx_host_interface_command(struct wx *wx, u32 *buffer,
+			      u32 length, u32 timeout, bool return_data)
+{
+	if (length == 0 || length > WX_HI_MAX_BLOCK_BYTE_LENGTH) {
+		wx_err(wx, "Buffer length failure buffersize=%d.\n", length);
+		return -EINVAL;
+	}
+
+	/* Calculate length in DWORDs. We must be DWORD aligned */
+	if ((length % (sizeof(u32))) != 0) {
+		wx_err(wx, "Buffer length failure, not aligned to dword");
+		return -EINVAL;
+	}
+
+	if (test_bit(WX_FLAG_SWFW_RING, wx->flags))
+		return wx_host_interface_command_r(wx, buffer, length,
+						   timeout, return_data);
+
+	return wx_host_interface_command_s(wx, buffer, length, timeout, return_data);
+}
 EXPORT_SYMBOL(wx_host_interface_command);
 
+int wx_set_pps(struct wx *wx, bool enable, u64 nsec, u64 cycles)
+{
+	struct wx_hic_set_pps pps_cmd;
+
+	pps_cmd.hdr.cmd = FW_PPS_SET_CMD;
+	pps_cmd.hdr.buf_len = FW_PPS_SET_LEN;
+	pps_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+	pps_cmd.lan_id = wx->bus.func;
+	pps_cmd.enable = (u8)enable;
+	pps_cmd.nsec = nsec;
+	pps_cmd.cycles = cycles;
+	pps_cmd.hdr.checksum = FW_DEFAULT_CHECKSUM;
+
+	return wx_host_interface_command(wx, (u32 *)&pps_cmd,
+					 sizeof(pps_cmd),
+					 WX_HI_COMMAND_TIMEOUT,
+					 false);
+}
+
 /**
  *  wx_read_ee_hostif_data - Read EEPROM word using a host interface cmd
  *  assuming that the semaphore is already obtained.
@@ -425,7 +557,10 @@ static int wx_read_ee_hostif_data(struct wx *wx, u16 offset, u16 *data)
 	if (status != 0)
 		return status;
 
-	*data = (u16)rd32a(wx, WX_MNG_MBOX, FW_NVM_DATA_OFFSET);
+	if (!test_bit(WX_FLAG_SWFW_RING, wx->flags))
+		*data = (u16)rd32a(wx, WX_MNG_MBOX, FW_NVM_DATA_OFFSET);
+	else
+		*data = (u16)rd32a(wx, WX_FW2SW_MBOX, FW_NVM_DATA_OFFSET);
 
 	return status;
 }
@@ -469,6 +604,7 @@ int wx_read_ee_hostif_buffer(struct wx *wx,
 	u16 words_to_read;
 	u32 value = 0;
 	int status;
+	u32 mbox;
 	u32 i;
 
 	/* Take semaphore for the entire operation. */
@@ -501,8 +637,12 @@ int wx_read_ee_hostif_buffer(struct wx *wx,
 			goto out;
 		}
 
+		if (!test_bit(WX_FLAG_SWFW_RING, wx->flags))
+			mbox = WX_MNG_MBOX;
+		else
+			mbox = WX_FW2SW_MBOX;
 		for (i = 0; i < words_to_read; i++) {
-			u32 reg = WX_MNG_MBOX + (FW_NVM_DATA_OFFSET << 2) + 2 * i;
+			u32 reg = mbox + (FW_NVM_DATA_OFFSET << 2) + 2 * i;
 
 			value = rd32(wx, reg);
 			data[current_word] = (u16)(value & 0xffff);
@@ -552,12 +692,18 @@ void wx_init_eeprom_params(struct wx *wx)
 		}
 	}
 
-	if (wx->mac.type == wx_mac_sp) {
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+	case wx_mac_aml:
+	case wx_mac_aml40:
 		if (wx_read_ee_hostif(wx, WX_SW_REGION_PTR, &data)) {
 			wx_err(wx, "NVM Read Error\n");
 			return;
 		}
 		data = data >> 1;
+		break;
+	default:
+		break;
 	}
 
 	eeprom->sw_region_offset = data;
@@ -618,7 +764,8 @@ static int wx_set_rar(struct wx *wx, u32 index, u8 *addr, u64 pools,
 
 	/* setup VMDq pool mapping */
 	wr32(wx, WX_PSR_MAC_SWC_VM_L, pools & 0xFFFFFFFF);
-	if (wx->mac.type == wx_mac_sp)
+
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
 		wr32(wx, WX_PSR_MAC_SWC_VM_H, pools >> 32);
 
 	/* HW expects these in little endian so we reverse the byte
@@ -757,7 +904,7 @@ void wx_init_rx_addrs(struct wx *wx)
 
 		wx_set_rar(wx, 0, wx->mac.addr, 0, WX_PSR_MAC_SWC_AD_H_AV);
 
-		if (wx->mac.type == wx_mac_sp) {
+		if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 			/* clear VMDq pool/queue selection for RAR 0 */
 			wx_clear_vmdq(wx, 0, WX_CLEAR_VMDQ_ALL);
 		}
@@ -804,11 +951,28 @@ static void wx_sync_mac_table(struct wx *wx)
 	}
 }
 
+static void wx_full_sync_mac_table(struct wx *wx)
+{
+	int i;
+
+	for (i = 0; i < wx->mac.num_rar_entries; i++) {
+		if (wx->mac_table[i].state & WX_MAC_STATE_IN_USE) {
+			wx_set_rar(wx, i,
+				   wx->mac_table[i].addr,
+				   wx->mac_table[i].pools,
+				   WX_PSR_MAC_SWC_AD_H_AV);
+		} else {
+			wx_clear_rar(wx, i);
+		}
+		wx->mac_table[i].state &= ~(WX_MAC_STATE_MODIFIED);
+	}
+}
+
 /* this function destroys the first RAR entry */
 void wx_mac_set_default_filter(struct wx *wx, u8 *addr)
 {
 	memcpy(&wx->mac_table[0].addr, addr, ETH_ALEN);
-	wx->mac_table[0].pools = 1ULL;
+	wx->mac_table[0].pools = BIT(VMDQ_P(0));
 	wx->mac_table[0].state = (WX_MAC_STATE_DEFAULT | WX_MAC_STATE_IN_USE);
 	wx_set_rar(wx, 0, wx->mac_table[0].addr,
 		   wx->mac_table[0].pools,
@@ -833,7 +997,7 @@ void wx_flush_sw_mac_table(struct wx *wx)
 }
 EXPORT_SYMBOL(wx_flush_sw_mac_table);
 
-static int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
+int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 {
 	u32 i;
 
@@ -864,7 +1028,7 @@ static int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 	return -ENOMEM;
 }
 
-static int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool)
+int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 {
 	u32 i;
 
@@ -1046,6 +1210,35 @@ static void wx_update_mc_addr_list(struct wx *wx, struct net_device *netdev)
 	wx_dbg(wx, "Update mc addr list Complete\n");
 }
 
+static void wx_restore_vf_multicasts(struct wx *wx)
+{
+	u32 i, j, vector_bit, vector_reg;
+	struct vf_data_storage *vfinfo;
+
+	for (i = 0; i < wx->num_vfs; i++) {
+		u32 vmolr = rd32(wx, WX_PSR_VM_L2CTL(i));
+
+		vfinfo = &wx->vfinfo[i];
+		for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) {
+			wx->addr_ctrl.mta_in_use++;
+			vector_reg = WX_PSR_MC_TBL_REG(vfinfo->vf_mc_hashes[j]);
+			vector_bit = WX_PSR_MC_TBL_BIT(vfinfo->vf_mc_hashes[j]);
+			wr32m(wx, WX_PSR_MC_TBL(vector_reg),
+			      BIT(vector_bit), BIT(vector_bit));
+			/* errata 5: maintain a copy of the reg table conf */
+			wx->mac.mta_shadow[vector_reg] |= BIT(vector_bit);
+		}
+		if (vfinfo->num_vf_mc_hashes)
+			vmolr |= WX_PSR_VM_L2CTL_ROMPE;
+		else
+			vmolr &= ~WX_PSR_VM_L2CTL_ROMPE;
+		wr32(wx, WX_PSR_VM_L2CTL(i), vmolr);
+	}
+
+	/* Restore any VF macvlans */
+	wx_full_sync_mac_table(wx);
+}
+
 /**
  * wx_write_mc_addr_list - write multicast addresses to MTA
  * @netdev: network interface device structure
@@ -1063,6 +1256,9 @@ static int wx_write_mc_addr_list(struct net_device *netdev)
 
 	wx_update_mc_addr_list(wx, netdev);
 
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		wx_restore_vf_multicasts(wx);
+
 	return netdev_mc_count(netdev);
 }
 
@@ -1083,7 +1279,7 @@ int wx_set_mac(struct net_device *netdev, void *p)
 	if (retval)
 		return retval;
 
-	wx_del_mac_filter(wx, wx->mac.addr, 0);
+	wx_del_mac_filter(wx, wx->mac.addr, VMDQ_P(0));
 	eth_hw_addr_set(netdev, addr->sa_data);
 	memcpy(wx->mac.addr, addr->sa_data, netdev->addr_len);
 
@@ -1185,6 +1381,10 @@ static int wx_hpbthresh(struct wx *wx)
 	/* Calculate delay value for device */
 	dv_id = WX_DV(link, tc);
 
+	/* Loopback switch introduces additional latency */
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		dv_id += WX_B2BT(tc);
+
 	/* Delay value is calculated in bit times convert to KB */
 	kb = WX_BT2KB(dv_id);
 	rx_pba = rd32(wx, WX_RDB_PB_SZ(0)) >> WX_RDB_PB_SZ_SHIFT;
@@ -1240,12 +1440,107 @@ static void wx_pbthresh_setup(struct wx *wx)
 		wx->fc.low_water = 0;
 }
 
+static void wx_set_ethertype_anti_spoofing(struct wx *wx, bool enable, int vf)
+{
+	u32 pfvfspoof, reg_offset, vf_shift;
+
+	vf_shift = WX_VF_IND_SHIFT(vf);
+	reg_offset = WX_VF_REG_OFFSET(vf);
+
+	pfvfspoof = rd32(wx, WX_TDM_ETYPE_AS(reg_offset));
+	if (enable)
+		pfvfspoof |= BIT(vf_shift);
+	else
+		pfvfspoof &= ~BIT(vf_shift);
+	wr32(wx, WX_TDM_ETYPE_AS(reg_offset), pfvfspoof);
+}
+
+int wx_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
+{
+	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
+	struct wx *wx = netdev_priv(netdev);
+	u32 regval;
+
+	if (vf >= wx->num_vfs)
+		return -EINVAL;
+
+	wx->vfinfo[vf].spoofchk_enabled = setting;
+
+	regval = (setting << vf_bit);
+	wr32m(wx, WX_TDM_MAC_AS(index), regval | BIT(vf_bit), regval);
+
+	if (wx->vfinfo[vf].vlan_count)
+		wr32m(wx, WX_TDM_VLAN_AS(index), regval | BIT(vf_bit), regval);
+
+	return 0;
+}
+
+static void wx_configure_virtualization(struct wx *wx)
+{
+	u16 pool = wx->num_rx_pools;
+	u32 reg_offset, vf_shift;
+	u32 i;
+
+	if (!test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		return;
+
+	wr32m(wx, WX_PSR_VM_CTL,
+	      WX_PSR_VM_CTL_POOL_MASK | WX_PSR_VM_CTL_REPLEN,
+	      FIELD_PREP(WX_PSR_VM_CTL_POOL_MASK, VMDQ_P(0)) |
+	      WX_PSR_VM_CTL_REPLEN);
+	while (pool--)
+		wr32m(wx, WX_PSR_VM_L2CTL(pool),
+		      WX_PSR_VM_L2CTL_AUPE, WX_PSR_VM_L2CTL_AUPE);
+
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		vf_shift = BIT(VMDQ_P(0));
+		/* Enable only the PF pools for Tx/Rx */
+		wr32(wx, WX_RDM_VF_RE(0), vf_shift);
+		wr32(wx, WX_TDM_VF_TE(0), vf_shift);
+	} else {
+		vf_shift = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_offset = WX_VF_REG_OFFSET(VMDQ_P(0));
+
+		/* Enable only the PF pools for Tx/Rx */
+		wr32(wx, WX_RDM_VF_RE(reg_offset), GENMASK(31, vf_shift));
+		wr32(wx, WX_RDM_VF_RE(reg_offset ^ 1), reg_offset - 1);
+		wr32(wx, WX_TDM_VF_TE(reg_offset), GENMASK(31, vf_shift));
+		wr32(wx, WX_TDM_VF_TE(reg_offset ^ 1), reg_offset - 1);
+	}
+
+	/* clear VLAN promisc flag so VFTA will be updated if necessary */
+	clear_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+
+	for (i = 0; i < wx->num_vfs; i++) {
+		if (!wx->vfinfo[i].spoofchk_enabled)
+			wx_set_vf_spoofchk(wx->netdev, i, false);
+		/* enable ethertype anti spoofing if hw supports it */
+		wx_set_ethertype_anti_spoofing(wx, true, i);
+	}
+}
+
 static void wx_configure_port(struct wx *wx)
 {
 	u32 value, i;
 
-	value = WX_CFG_PORT_CTL_D_VLAN | WX_CFG_PORT_CTL_QINQ;
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		value = (wx->num_vfs == 0) ?
+			WX_CFG_PORT_CTL_NUM_VT_NONE :
+			WX_CFG_PORT_CTL_NUM_VT_8;
+	} else {
+		if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags)) {
+			if (wx->ring_feature[RING_F_RSS].indices == 4)
+				value = WX_CFG_PORT_CTL_NUM_VT_32;
+			else
+				value = WX_CFG_PORT_CTL_NUM_VT_64;
+		} else {
+			value = 0;
+		}
+	}
+
+	value |= WX_CFG_PORT_CTL_D_VLAN | WX_CFG_PORT_CTL_QINQ;
 	wr32m(wx, WX_CFG_PORT_CTL,
+	      WX_CFG_PORT_CTL_NUM_VT_MASK |
 	      WX_CFG_PORT_CTL_D_VLAN |
 	      WX_CFG_PORT_CTL_QINQ,
 	      value);
@@ -1306,6 +1601,83 @@ static void wx_vlan_strip_control(struct wx *wx, bool enable)
 	}
 }
 
+static void wx_vlan_promisc_enable(struct wx *wx)
+{
+	u32 vlnctrl, i, vind, bits, reg_idx;
+
+	vlnctrl = rd32(wx, WX_PSR_VLAN_CTL);
+	if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags)) {
+		/* we need to keep the VLAN filter on in SRIOV */
+		vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+		wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+	} else {
+		vlnctrl &= ~WX_PSR_VLAN_CTL_VFE;
+		wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+		return;
+	}
+	/* We are already in VLAN promisc, nothing to do */
+	if (test_bit(WX_FLAG_VLAN_PROMISC, wx->flags))
+		return;
+	/* Set flag so we don't redo unnecessary work */
+	set_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+	/* Add PF to all active pools */
+	for (i = WX_PSR_VLAN_SWC_ENTRIES; --i;) {
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, i);
+		vind = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_idx = WX_VF_REG_OFFSET(VMDQ_P(0));
+		bits = rd32(wx, WX_PSR_VLAN_SWC_VM(reg_idx));
+		bits |= BIT(vind);
+		wr32(wx, WX_PSR_VLAN_SWC_VM(reg_idx), bits);
+	}
+	/* Set all bits in the VLAN filter table array */
+	for (i = 0; i < wx->mac.vft_size; i++)
+		wr32(wx, WX_PSR_VLAN_TBL(i), U32_MAX);
+}
+
+static void wx_scrub_vfta(struct wx *wx)
+{
+	u32 i, vid, bits, vfta, vind, vlvf, reg_idx;
+
+	for (i = WX_PSR_VLAN_SWC_ENTRIES; --i;) {
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, i);
+		vlvf = rd32(wx, WX_PSR_VLAN_SWC_IDX);
+		/* pull VLAN ID from VLVF */
+		vid = vlvf & ~WX_PSR_VLAN_SWC_VIEN;
+		if (vlvf & WX_PSR_VLAN_SWC_VIEN) {
+			/* if PF is part of this then continue */
+			if (test_bit(vid, wx->active_vlans))
+				continue;
+		}
+		/* remove PF from the pool */
+		vind = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_idx = WX_VF_REG_OFFSET(VMDQ_P(0));
+		bits = rd32(wx, WX_PSR_VLAN_SWC_VM(reg_idx));
+		bits &= ~BIT(vind);
+		wr32(wx, WX_PSR_VLAN_SWC_VM(reg_idx), bits);
+	}
+	/* extract values from vft_shadow and write back to VFTA */
+	for (i = 0; i < wx->mac.vft_size; i++) {
+		vfta = wx->mac.vft_shadow[i];
+		wr32(wx, WX_PSR_VLAN_TBL(i), vfta);
+	}
+}
+
+static void wx_vlan_promisc_disable(struct wx *wx)
+{
+	u32 vlnctrl;
+
+	/* configure vlan filtering */
+	vlnctrl = rd32(wx, WX_PSR_VLAN_CTL);
+	vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+	wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+	/* We are not in VLAN promisc, nothing to do */
+	if (!test_bit(WX_FLAG_VLAN_PROMISC, wx->flags))
+		return;
+	/* Set flag so we don't redo unnecessary work */
+	clear_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+	wx_scrub_vfta(wx);
+}
+
 void wx_set_rx_mode(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
@@ -1318,7 +1690,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 	/* Check for Promiscuous and All Multicast modes */
 	fctrl = rd32(wx, WX_PSR_CTL);
 	fctrl &= ~(WX_PSR_CTL_UPE | WX_PSR_CTL_MPE);
-	vmolr = rd32(wx, WX_PSR_VM_L2CTL(0));
+	vmolr = rd32(wx, WX_PSR_VM_L2CTL(VMDQ_P(0)));
 	vmolr &= ~(WX_PSR_VM_L2CTL_UPE |
 		   WX_PSR_VM_L2CTL_MPE |
 		   WX_PSR_VM_L2CTL_ROPE |
@@ -1339,7 +1711,10 @@ void wx_set_rx_mode(struct net_device *netdev)
 		fctrl |= WX_PSR_CTL_UPE | WX_PSR_CTL_MPE;
 		/* pf don't want packets routing to vf, so clear UPE */
 		vmolr |= WX_PSR_VM_L2CTL_MPE;
-		vlnctrl &= ~WX_PSR_VLAN_CTL_VFE;
+		if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags) &&
+		    test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+			vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+		features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
 	}
 
 	if (netdev->flags & IFF_ALLMULTI) {
@@ -1362,7 +1737,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 	 * sufficient space to store all the addresses then enable
 	 * unicast promiscuous mode
 	 */
-	count = wx_write_uc_addr_list(netdev, 0);
+	count = wx_write_uc_addr_list(netdev, VMDQ_P(0));
 	if (count < 0) {
 		vmolr &= ~WX_PSR_VM_L2CTL_ROPE;
 		vmolr |= WX_PSR_VM_L2CTL_UPE;
@@ -1380,7 +1755,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 
 	wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
 	wr32(wx, WX_PSR_CTL, fctrl);
-	wr32(wx, WX_PSR_VM_L2CTL(0), vmolr);
+	wr32(wx, WX_PSR_VM_L2CTL(VMDQ_P(0)), vmolr);
 
 	if ((features & NETIF_F_HW_VLAN_CTAG_RX) &&
 	    (features & NETIF_F_HW_VLAN_STAG_RX))
@@ -1388,6 +1763,10 @@ void wx_set_rx_mode(struct net_device *netdev)
 	else
 		wx_vlan_strip_control(wx, false);
 
+	if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		wx_vlan_promisc_disable(wx);
+	else
+		wx_vlan_promisc_enable(wx);
 }
 EXPORT_SYMBOL(wx_set_rx_mode);
 
@@ -1637,6 +2016,13 @@ static void wx_setup_reta(struct wx *wx)
 	u32 random_key_size = WX_RSS_KEY_SIZE / 4;
 	u32 i, j;
 
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags)) {
+		if (wx->mac.type == wx_mac_em)
+			rss_i = 1;
+		else
+			rss_i = rss_i < 4 ? 4 : rss_i;
+	}
+
 	/* Fill out hash function seeds */
 	for (i = 0; i < random_key_size; i++)
 		wr32(wx, WX_RDB_RSSRK(i), wx->rss_key[i]);
@@ -1654,10 +2040,42 @@ static void wx_setup_reta(struct wx *wx)
 	wx_store_reta(wx);
 }
 
+#define WX_RDB_RSS_PL_2		FIELD_PREP(GENMASK(31, 29), 1)
+#define WX_RDB_RSS_PL_4		FIELD_PREP(GENMASK(31, 29), 2)
+static void wx_setup_psrtype(struct wx *wx)
+{
+	int rss_i = wx->ring_feature[RING_F_RSS].indices;
+	u32 psrtype;
+	int pool;
+
+	psrtype = WX_RDB_PL_CFG_L4HDR |
+		  WX_RDB_PL_CFG_L3HDR |
+		  WX_RDB_PL_CFG_L2HDR |
+		  WX_RDB_PL_CFG_TUN_OUTL2HDR |
+		  WX_RDB_PL_CFG_TUN_TUNHDR;
+
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		for_each_set_bit(pool, &wx->fwd_bitmask, 8)
+			wr32(wx, WX_RDB_PL_CFG(VMDQ_P(pool)), psrtype);
+	} else {
+		if (rss_i > 3)
+			psrtype |= WX_RDB_RSS_PL_4;
+		else if (rss_i > 1)
+			psrtype |= WX_RDB_RSS_PL_2;
+
+		for_each_set_bit(pool, &wx->fwd_bitmask, 32)
+			wr32(wx, WX_RDB_PL_CFG(VMDQ_P(pool)), psrtype);
+	}
+}
+
 static void wx_setup_mrqc(struct wx *wx)
 {
 	u32 rss_field = 0;
 
+	/* VT, and RSS do not coexist at the same time */
+	if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
+		return;
+
 	/* Disable indicating checksum in descriptor, enables RSS hash */
 	wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_PCSD, WX_PSR_CTL_PCSD);
 
@@ -1687,21 +2105,16 @@ static void wx_setup_mrqc(struct wx *wx)
  **/
 void wx_configure_rx(struct wx *wx)
 {
-	u32 psrtype, i;
 	int ret;
+	u32 i;
 
 	wx_disable_rx(wx);
-
-	psrtype = WX_RDB_PL_CFG_L4HDR |
-		  WX_RDB_PL_CFG_L3HDR |
-		  WX_RDB_PL_CFG_L2HDR |
-		  WX_RDB_PL_CFG_TUN_TUNHDR;
-	wr32(wx, WX_RDB_PL_CFG(0), psrtype);
+	wx_setup_psrtype(wx);
 
 	/* enable hw crc stripping */
 	wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_CRC_STRIP, WX_RSC_CTL_CRC_STRIP);
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) {
 		u32 psrctl;
 
 		/* RSC Setup */
@@ -1744,6 +2157,7 @@ void wx_configure(struct wx *wx)
 {
 	wx_set_rxpba(wx);
 	wx_pbthresh_setup(wx);
+	wx_configure_virtualization(wx);
 	wx_configure_port(wx);
 
 	wx_set_rx_mode(wx->netdev);
@@ -1838,10 +2252,8 @@ int wx_stop_adapter(struct wx *wx)
 }
 EXPORT_SYMBOL(wx_stop_adapter);
 
-void wx_reset_misc(struct wx *wx)
+void wx_reset_mac(struct wx *wx)
 {
-	int i;
-
 	/* receive packets that size > 2048 */
 	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_JE, WX_MAC_RX_CFG_JE);
 
@@ -1853,6 +2265,14 @@ void wx_reset_misc(struct wx *wx)
 	      WX_MAC_RX_FLOW_CTRL_RFE, WX_MAC_RX_FLOW_CTRL_RFE);
 
 	wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
+}
+EXPORT_SYMBOL(wx_reset_mac);
+
+void wx_reset_misc(struct wx *wx)
+{
+	int i;
+
+	wx_reset_mac(wx);
 
 	wr32m(wx, WX_MIS_RST_ST,
 	      WX_MIS_RST_ST_RST_INIT, 0x1E00);
@@ -2102,7 +2522,7 @@ static int wx_set_vlvf(struct wx *wx, u32 vlan, u32 vind, bool vlan_on,
  *
  *  Turn on/off specified VLAN in the VLAN filter table.
  **/
-static int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on)
+int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on)
 {
 	u32 bitindex, vfta, targetbit;
 	bool vfta_changed = false;
@@ -2353,12 +2773,13 @@ void wx_update_stats(struct wx *wx)
 	hwstats->b2ogprc += rd32(wx, WX_RDM_BMC2OS_CNT);
 	hwstats->rdmdrop += rd32(wx, WX_RDM_DRP_PKT);
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) {
 		hwstats->fdirmatch += rd32(wx, WX_RDB_FDIR_MATCH);
 		hwstats->fdirmiss += rd32(wx, WX_RDB_FDIR_MISS);
 	}
 
-	for (i = 0; i < wx->mac.max_rx_queues; i++)
+	for (i = wx->num_vfs * wx->num_rx_queues_per_pool;
+	     i < wx->mac.max_rx_queues; i++)
 		hwstats->qmprc += rd32(wx, WX_PX_MPRC(i));
 }
 EXPORT_SYMBOL(wx_update_stats);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
index 11fb33349482..26a56cba60b9 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
@@ -18,6 +18,7 @@ void wx_control_hw(struct wx *wx, bool drv);
 int wx_mng_present(struct wx *wx);
 int wx_host_interface_command(struct wx *wx, u32 *buffer,
 			      u32 length, u32 timeout, bool return_data);
+int wx_set_pps(struct wx *wx, bool enable, u64 nsec, u64 cycles);
 int wx_read_ee_hostif(struct wx *wx, u16 offset, u16 *data);
 int wx_read_ee_hostif_buffer(struct wx *wx,
 			     u16 offset, u16 words, u16 *data);
@@ -25,9 +26,12 @@ void wx_init_eeprom_params(struct wx *wx);
 void wx_get_mac_addr(struct wx *wx, u8 *mac_addr);
 void wx_init_rx_addrs(struct wx *wx);
 void wx_mac_set_default_filter(struct wx *wx, u8 *addr);
+int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool);
+int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool);
 void wx_flush_sw_mac_table(struct wx *wx);
 int wx_set_mac(struct net_device *netdev, void *p);
 void wx_disable_rx(struct wx *wx);
+int wx_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting);
 int wx_disable_sec_rx_path(struct wx *wx);
 void wx_enable_sec_rx_path(struct wx *wx);
 void wx_set_rx_mode(struct net_device *netdev);
@@ -38,9 +42,11 @@ void wx_configure(struct wx *wx);
 void wx_start_hw(struct wx *wx);
 int wx_disable_pcie_master(struct wx *wx);
 int wx_stop_adapter(struct wx *wx);
+void wx_reset_mac(struct wx *wx);
 void wx_reset_misc(struct wx *wx);
 int wx_get_pcie_msix_counts(struct wx *wx, u16 *msix_count, u16 max_msix_count);
 int wx_sw_init(struct wx *wx);
+int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on);
 int wx_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid);
 int wx_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid);
 int wx_fc_enable(struct wx *wx, bool tx_pause, bool rx_pause);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 2b3d6586f44a..55e252789db3 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -5,6 +5,7 @@
 #include <net/ip6_checksum.h>
 #include <net/page_pool/helpers.h>
 #include <net/inet_ecn.h>
+#include <linux/workqueue.h>
 #include <linux/iopoll.h>
 #include <linux/sctp.h>
 #include <linux/pci.h>
@@ -13,6 +14,7 @@
 
 #include "wx_type.h"
 #include "wx_lib.h"
+#include "wx_ptp.h"
 #include "wx_hw.h"
 
 /* Lookup table mapping the HW PTYPE to the bit field for decoding */
@@ -309,7 +311,8 @@ static bool wx_alloc_mapped_page(struct wx_ring *rx_ring,
 		return true;
 
 	page = page_pool_dev_alloc_pages(rx_ring->page_pool);
-	WARN_ON(!page);
+	if (unlikely(!page))
+		return false;
 	dma = page_pool_get_dma_addr(page);
 
 	bi->page_dma = dma;
@@ -545,7 +548,8 @@ static void wx_rx_checksum(struct wx_ring *ring,
 		return;
 
 	/* Hardware can't guarantee csum if IPv6 Dest Header found */
-	if (dptype.prot != WX_DEC_PTYPE_PROT_SCTP && WX_RXD_IPV6EX(rx_desc))
+	if (dptype.prot != WX_DEC_PTYPE_PROT_SCTP &&
+	    wx_test_staterr(rx_desc, WX_RXD_STAT_IPV6EX))
 		return;
 
 	/* if L4 checksum error */
@@ -597,8 +601,17 @@ static void wx_process_skb_fields(struct wx_ring *rx_ring,
 				  union wx_rx_desc *rx_desc,
 				  struct sk_buff *skb)
 {
+	struct wx *wx = netdev_priv(rx_ring->netdev);
+
 	wx_rx_hash(rx_ring, rx_desc, skb);
 	wx_rx_checksum(rx_ring, rx_desc, skb);
+
+	if (unlikely(test_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, wx->flags)) &&
+	    unlikely(wx_test_staterr(rx_desc, WX_RXD_STAT_TS))) {
+		wx_ptp_rx_hwtstamp(rx_ring->q_vector->wx, skb);
+		rx_ring->last_rx_timestamp = jiffies;
+	}
+
 	wx_rx_vlan(rx_ring, rx_desc, skb);
 	skb_record_rx_queue(skb, rx_ring->queue_index);
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
@@ -705,6 +718,7 @@ static bool wx_clean_tx_irq(struct wx_q_vector *q_vector,
 {
 	unsigned int budget = q_vector->wx->tx_work_limit;
 	unsigned int total_bytes = 0, total_packets = 0;
+	struct wx *wx = netdev_priv(tx_ring->netdev);
 	unsigned int i = tx_ring->next_to_clean;
 	struct wx_tx_buffer *tx_buffer;
 	union wx_tx_desc *tx_desc;
@@ -737,6 +751,11 @@ static bool wx_clean_tx_irq(struct wx_q_vector *q_vector,
 		total_bytes += tx_buffer->bytecount;
 		total_packets += tx_buffer->gso_segs;
 
+		/* schedule check for Tx timestamp */
+		if (unlikely(test_bit(WX_STATE_PTP_TX_IN_PROGRESS, wx->state)) &&
+		    skb_shinfo(tx_buffer->skb)->tx_flags & SKBTX_IN_PROGRESS)
+			ptp_schedule_worker(wx->ptp_clock, 0);
+
 		/* free the skb */
 		napi_consume_skb(tx_buffer->skb, napi_budget);
 
@@ -932,9 +951,9 @@ static void wx_tx_olinfo_status(union wx_tx_desc *tx_desc,
 	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 }
 
-static void wx_tx_map(struct wx_ring *tx_ring,
-		      struct wx_tx_buffer *first,
-		      const u8 hdr_len)
+static int wx_tx_map(struct wx_ring *tx_ring,
+		     struct wx_tx_buffer *first,
+		     const u8 hdr_len)
 {
 	struct sk_buff *skb = first->skb;
 	struct wx_tx_buffer *tx_buffer;
@@ -1013,6 +1032,8 @@ static void wx_tx_map(struct wx_ring *tx_ring,
 
 	netdev_tx_sent_queue(wx_txring_txq(tx_ring), first->bytecount);
 
+	/* set the timestamp */
+	first->time_stamp = jiffies;
 	skb_tx_timestamp(skb);
 
 	/* Force memory writes to complete before letting h/w know there
@@ -1038,7 +1059,7 @@ static void wx_tx_map(struct wx_ring *tx_ring,
 	if (netif_xmit_stopped(wx_txring_txq(tx_ring)) || !netdev_xmit_more())
 		writel(i, tx_ring->tail);
 
-	return;
+	return 0;
 dma_error:
 	dev_err(tx_ring->dev, "TX DMA map failed\n");
 
@@ -1062,6 +1083,8 @@ dma_error:
 	first->skb = NULL;
 
 	tx_ring->next_to_use = i;
+
+	return -ENOMEM;
 }
 
 static void wx_tx_ctxtdesc(struct wx_ring *tx_ring, u32 vlan_macip_lens,
@@ -1082,26 +1105,6 @@ static void wx_tx_ctxtdesc(struct wx_ring *tx_ring, u32 vlan_macip_lens,
 	context_desc->mss_l4len_idx     = cpu_to_le32(mss_l4len_idx);
 }
 
-static void wx_get_ipv6_proto(struct sk_buff *skb, int offset, u8 *nexthdr)
-{
-	struct ipv6hdr *hdr = (struct ipv6hdr *)(skb->data + offset);
-
-	*nexthdr = hdr->nexthdr;
-	offset += sizeof(struct ipv6hdr);
-	while (ipv6_ext_hdr(*nexthdr)) {
-		struct ipv6_opt_hdr _hdr, *hp;
-
-		if (*nexthdr == NEXTHDR_NONE)
-			return;
-		hp = skb_header_pointer(skb, offset, sizeof(_hdr), &_hdr);
-		if (!hp)
-			return;
-		if (*nexthdr == NEXTHDR_FRAGMENT)
-			break;
-		*nexthdr = hp->nexthdr;
-	}
-}
-
 union network_header {
 	struct iphdr *ipv4;
 	struct ipv6hdr *ipv6;
@@ -1112,6 +1115,8 @@ static u8 wx_encode_tx_desc_ptype(const struct wx_tx_buffer *first)
 {
 	u8 tun_prot = 0, l4_prot = 0, ptype = 0;
 	struct sk_buff *skb = first->skb;
+	unsigned char *exthdr, *l4_hdr;
+	__be16 frag_off;
 
 	if (skb->encapsulation) {
 		union network_header hdr;
@@ -1122,14 +1127,18 @@ static u8 wx_encode_tx_desc_ptype(const struct wx_tx_buffer *first)
 			ptype = WX_PTYPE_TUN_IPV4;
 			break;
 		case htons(ETH_P_IPV6):
-			wx_get_ipv6_proto(skb, skb_network_offset(skb), &tun_prot);
+			l4_hdr = skb_transport_header(skb);
+			exthdr = skb_network_header(skb) + sizeof(struct ipv6hdr);
+			tun_prot = ipv6_hdr(skb)->nexthdr;
+			if (l4_hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data, &tun_prot, &frag_off);
 			ptype = WX_PTYPE_TUN_IPV6;
 			break;
 		default:
 			return ptype;
 		}
 
-		if (tun_prot == IPPROTO_IPIP) {
+		if (tun_prot == IPPROTO_IPIP || tun_prot == IPPROTO_IPV6) {
 			hdr.raw = (void *)inner_ip_hdr(skb);
 			ptype |= WX_PTYPE_PKT_IPIP;
 		} else if (tun_prot == IPPROTO_UDP) {
@@ -1166,7 +1175,11 @@ static u8 wx_encode_tx_desc_ptype(const struct wx_tx_buffer *first)
 			l4_prot = hdr.ipv4->protocol;
 			break;
 		case 6:
-			wx_get_ipv6_proto(skb, skb_inner_network_offset(skb), &l4_prot);
+			l4_hdr = skb_inner_transport_header(skb);
+			exthdr = skb_inner_network_header(skb) + sizeof(struct ipv6hdr);
+			l4_prot = inner_ipv6_hdr(skb)->nexthdr;
+			if (l4_hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data, &l4_prot, &frag_off);
 			ptype |= WX_PTYPE_PKT_IPV6;
 			break;
 		default:
@@ -1179,7 +1192,11 @@ static u8 wx_encode_tx_desc_ptype(const struct wx_tx_buffer *first)
 			ptype = WX_PTYPE_PKT_IP;
 			break;
 		case htons(ETH_P_IPV6):
-			wx_get_ipv6_proto(skb, skb_network_offset(skb), &l4_prot);
+			l4_hdr = skb_transport_header(skb);
+			exthdr = skb_network_header(skb) + sizeof(struct ipv6hdr);
+			l4_prot = ipv6_hdr(skb)->nexthdr;
+			if (l4_hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data, &l4_prot, &frag_off);
 			ptype = WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6;
 			break;
 		default:
@@ -1269,13 +1286,20 @@ static int wx_tso(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 
 	/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
 	if (enc) {
+		unsigned char *exthdr, *l4_hdr;
+		__be16 frag_off;
+
 		switch (first->protocol) {
 		case htons(ETH_P_IP):
 			tun_prot = ip_hdr(skb)->protocol;
 			first->tx_flags |= WX_TX_FLAGS_OUTER_IPV4;
 			break;
 		case htons(ETH_P_IPV6):
+			l4_hdr = skb_transport_header(skb);
+			exthdr = skb_network_header(skb) + sizeof(struct ipv6hdr);
 			tun_prot = ipv6_hdr(skb)->nexthdr;
+			if (l4_hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data, &tun_prot, &frag_off);
 			break;
 		default:
 			break;
@@ -1298,6 +1322,7 @@ static int wx_tso(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 						WX_TXD_TUNNEL_LEN_SHIFT);
 			break;
 		case IPPROTO_IPIP:
+		case IPPROTO_IPV6:
 			tunhdr_eiplen_tunlen = (((char *)inner_ip_hdr(skb) -
 						(char *)ip_hdr(skb)) >> 2) <<
 						WX_TXD_OUTER_IPLEN_SHIFT;
@@ -1335,12 +1360,15 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 	u8 tun_prot = 0;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+csum_failed:
 		if (!(first->tx_flags & WX_TX_FLAGS_HW_VLAN) &&
 		    !(first->tx_flags & WX_TX_FLAGS_CC))
 			return;
 		vlan_macip_lens = skb_network_offset(skb) <<
 				  WX_TXD_MACLEN_SHIFT;
 	} else {
+		unsigned char *exthdr, *l4_hdr;
+		__be16 frag_off;
 		u8 l4_prot = 0;
 		union {
 			struct iphdr *ipv4;
@@ -1362,7 +1390,12 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 				tun_prot = ip_hdr(skb)->protocol;
 				break;
 			case htons(ETH_P_IPV6):
+				l4_hdr = skb_transport_header(skb);
+				exthdr = skb_network_header(skb) + sizeof(struct ipv6hdr);
 				tun_prot = ipv6_hdr(skb)->nexthdr;
+				if (l4_hdr != exthdr)
+					ipv6_skip_exthdr(skb, exthdr - skb->data,
+							 &tun_prot, &frag_off);
 				break;
 			default:
 				return;
@@ -1386,6 +1419,7 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 							  WX_TXD_TUNNEL_LEN_SHIFT);
 				break;
 			case IPPROTO_IPIP:
+			case IPPROTO_IPV6:
 				tunhdr_eiplen_tunlen = (((char *)inner_ip_hdr(skb) -
 							(char *)ip_hdr(skb)) >> 2) <<
 							WX_TXD_OUTER_IPLEN_SHIFT;
@@ -1408,7 +1442,10 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 			break;
 		case 6:
 			vlan_macip_lens |= (transport_hdr.raw - network_hdr.raw) >> 1;
+			exthdr = network_hdr.raw + sizeof(struct ipv6hdr);
 			l4_prot = network_hdr.ipv6->nexthdr;
+			if (transport_hdr.raw != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data, &l4_prot, &frag_off);
 			break;
 		default:
 			break;
@@ -1428,7 +1465,8 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 					WX_TXD_L4LEN_SHIFT;
 			break;
 		default:
-			break;
+			skb_checksum_help(skb);
+			goto csum_failed;
 		}
 
 		/* update TX checksum flag */
@@ -1486,6 +1524,20 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb,
 		tx_flags |= WX_TX_FLAGS_HW_VLAN;
 	}
 
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    wx->ptp_clock) {
+		if (wx->tstamp_config.tx_type == HWTSTAMP_TX_ON &&
+		    !test_and_set_bit_lock(WX_STATE_PTP_TX_IN_PROGRESS,
+					   wx->state)) {
+			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+			tx_flags |= WX_TX_FLAGS_TSTAMP;
+			wx->ptp_tx_skb = skb_get(skb);
+			wx->ptp_tx_start = jiffies;
+		} else {
+			wx->tx_hwtstamp_skipped++;
+		}
+	}
+
 	/* record initial flags and protocol */
 	first->tx_flags = tx_flags;
 	first->protocol = vlan_get_protocol(skb);
@@ -1501,12 +1553,20 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb,
 	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) && tx_ring->atr_sample_rate)
 		wx->atr(tx_ring, first, ptype);
 
-	wx_tx_map(tx_ring, first, hdr_len);
+	if (wx_tx_map(tx_ring, first, hdr_len))
+		goto cleanup_tx_tstamp;
 
 	return NETDEV_TX_OK;
 out_drop:
 	dev_kfree_skb_any(first->skb);
 	first->skb = NULL;
+cleanup_tx_tstamp:
+	if (unlikely(tx_flags & WX_TX_FLAGS_TSTAMP)) {
+		dev_kfree_skb_any(wx->ptp_tx_skb);
+		wx->ptp_tx_skb = NULL;
+		wx->tx_hwtstamp_errors++;
+		clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state);
+	}
 
 	return NETDEV_TX_OK;
 }
@@ -1561,6 +1621,65 @@ void wx_napi_disable_all(struct wx *wx)
 }
 EXPORT_SYMBOL(wx_napi_disable_all);
 
+static bool wx_set_vmdq_queues(struct wx *wx)
+{
+	u16 vmdq_i = wx->ring_feature[RING_F_VMDQ].limit;
+	u16 rss_i = wx->ring_feature[RING_F_RSS].limit;
+	u16 rss_m = WX_RSS_DISABLED_MASK;
+	u16 vmdq_m = 0;
+
+	/* only proceed if VMDq is enabled */
+	if (!test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
+		return false;
+	/* Add starting offset to total pool count */
+	vmdq_i += wx->ring_feature[RING_F_VMDQ].offset;
+
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		/* double check we are limited to maximum pools */
+		vmdq_i = min_t(u16, 64, vmdq_i);
+
+		/* 64 pool mode with 2 queues per pool, or
+		 * 16/32/64 pool mode with 1 queue per pool
+		 */
+		if (vmdq_i > 32 || rss_i < 4) {
+			vmdq_m = WX_VMDQ_2Q_MASK;
+			rss_m = WX_RSS_2Q_MASK;
+			rss_i = min_t(u16, rss_i, 2);
+		/* 32 pool mode with 4 queues per pool */
+		} else {
+			vmdq_m = WX_VMDQ_4Q_MASK;
+			rss_m = WX_RSS_4Q_MASK;
+			rss_i = 4;
+		}
+	} else {
+		/* double check we are limited to maximum pools */
+		vmdq_i = min_t(u16, 8, vmdq_i);
+
+		/* when VMDQ on, disable RSS */
+		rss_i = 1;
+	}
+
+	/* remove the starting offset from the pool count */
+	vmdq_i -= wx->ring_feature[RING_F_VMDQ].offset;
+
+	/* save features for later use */
+	wx->ring_feature[RING_F_VMDQ].indices = vmdq_i;
+	wx->ring_feature[RING_F_VMDQ].mask = vmdq_m;
+
+	/* limit RSS based on user input and save for later use */
+	wx->ring_feature[RING_F_RSS].indices = rss_i;
+	wx->ring_feature[RING_F_RSS].mask = rss_m;
+
+	wx->queues_per_pool = rss_i;/*maybe same to num_rx_queues_per_pool*/
+	wx->num_rx_pools = vmdq_i;
+	wx->num_rx_queues_per_pool = rss_i;
+
+	wx->num_rx_queues = vmdq_i * rss_i;
+	wx->num_tx_queues = vmdq_i * rss_i;
+
+	return true;
+}
+
 /**
  * wx_set_rss_queues: Allocate queues for RSS
  * @wx: board private structure to initialize
@@ -1575,6 +1694,10 @@ static void wx_set_rss_queues(struct wx *wx)
 
 	/* set mask for 16 queue limit of RSS */
 	f = &wx->ring_feature[RING_F_RSS];
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
+		f->mask = WX_RSS_64Q_MASK;
+	else
+		f->mask = WX_RSS_8Q_MASK;
 	f->indices = f->limit;
 
 	if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)))
@@ -1582,6 +1705,7 @@ static void wx_set_rss_queues(struct wx *wx)
 
 	clear_bit(WX_FLAG_FDIR_HASH, wx->flags);
 
+	wx->ring_feature[RING_F_FDIR].indices = 1;
 	/* Use Flow Director in addition to RSS to ensure the best
 	 * distribution of flows across cores, even when an FDIR flow
 	 * isn't matched.
@@ -1607,6 +1731,9 @@ static void wx_set_num_queues(struct wx *wx)
 	wx->num_tx_queues = 1;
 	wx->queues_per_pool = 1;
 
+	if (wx_set_vmdq_queues(wx))
+		return;
+
 	wx_set_rss_queues(wx);
 }
 
@@ -1620,7 +1747,7 @@ static void wx_set_num_queues(struct wx *wx)
  */
 static int wx_acquire_msix_vectors(struct wx *wx)
 {
-	struct irq_affinity affd = { .pre_vectors = 1 };
+	struct irq_affinity affd = { .post_vectors = 1 };
 	int nvecs, i;
 
 	/* We start by asking for one vector per queue pair */
@@ -1657,16 +1784,24 @@ static int wx_acquire_msix_vectors(struct wx *wx)
 		return nvecs;
 	}
 
-	wx->msix_entry->entry = 0;
-	wx->msix_entry->vector = pci_irq_vector(wx->pdev, 0);
 	nvecs -= 1;
 	for (i = 0; i < nvecs; i++) {
 		wx->msix_q_entries[i].entry = i;
-		wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i + 1);
+		wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i);
 	}
 
 	wx->num_q_vectors = nvecs;
 
+	wx->msix_entry->entry = nvecs;
+	wx->msix_entry->vector = pci_irq_vector(wx->pdev, nvecs);
+
+	if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags)) {
+		wx->msix_entry->entry = 0;
+		wx->msix_entry->vector = pci_irq_vector(wx->pdev, 0);
+		wx->msix_q_entries[0].entry = 0;
+		wx->msix_q_entries[0].vector = pci_irq_vector(wx->pdev, 1);
+	}
+
 	return 0;
 }
 
@@ -1687,6 +1822,10 @@ static int wx_set_interrupt_capability(struct wx *wx)
 	if (ret == 0 || (ret == -ENOMEM))
 		return ret;
 
+	/* Disable VMDq support */
+	dev_warn(&wx->pdev->dev, "Disabling VMQQ support\n");
+	clear_bit(WX_FLAG_VMDQ_ENABLED, wx->flags);
+
 	/* Disable RSS */
 	dev_warn(&wx->pdev->dev, "Disabling RSS support\n");
 	wx->ring_feature[RING_F_RSS].limit = 1;
@@ -1713,6 +1852,49 @@ static int wx_set_interrupt_capability(struct wx *wx)
 	return 0;
 }
 
+static bool wx_cache_ring_vmdq(struct wx *wx)
+{
+	struct wx_ring_feature *vmdq = &wx->ring_feature[RING_F_VMDQ];
+	struct wx_ring_feature *rss = &wx->ring_feature[RING_F_RSS];
+	u16 reg_idx;
+	int i;
+
+	/* only proceed if VMDq is enabled */
+	if (!test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
+		return false;
+
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		/* start at VMDq register offset for SR-IOV enabled setups */
+		reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
+		for (i = 0; i < wx->num_rx_queues; i++, reg_idx++) {
+			/* If we are greater than indices move to next pool */
+			if ((reg_idx & ~vmdq->mask) >= rss->indices)
+				reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask);
+			wx->rx_ring[i]->reg_idx = reg_idx;
+		}
+		reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
+		for (i = 0; i < wx->num_tx_queues; i++, reg_idx++) {
+			/* If we are greater than indices move to next pool */
+			if ((reg_idx & rss->mask) >= rss->indices)
+				reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask);
+			wx->tx_ring[i]->reg_idx = reg_idx;
+		}
+	} else {
+		/* start at VMDq register offset for SR-IOV enabled setups */
+		reg_idx = vmdq->offset;
+		for (i = 0; i < wx->num_rx_queues; i++)
+			/* If we are greater than indices move to next pool */
+			wx->rx_ring[i]->reg_idx = reg_idx + i;
+
+		reg_idx = vmdq->offset;
+		for (i = 0; i < wx->num_tx_queues; i++)
+			/* If we are greater than indices move to next pool */
+			wx->tx_ring[i]->reg_idx = reg_idx + i;
+	}
+
+	return true;
+}
+
 /**
  * wx_cache_ring_rss - Descriptor ring to register mapping for RSS
  * @wx: board private structure to initialize
@@ -1724,6 +1906,9 @@ static void wx_cache_ring_rss(struct wx *wx)
 {
 	u16 i;
 
+	if (wx_cache_ring_vmdq(wx))
+		return;
+
 	for (i = 0; i < wx->num_rx_queues; i++)
 		wx->rx_ring[i]->reg_idx = i;
 
@@ -1781,10 +1966,17 @@ static int wx_alloc_q_vector(struct wx *wx,
 	/* initialize pointer to rings */
 	ring = q_vector->ring;
 
-	if (wx->mac.type == wx_mac_sp)
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+	case wx_mac_aml:
+	case wx_mac_aml40:
 		default_itr = WX_12K_ITR;
-	else
+		break;
+	default:
 		default_itr = WX_7K_ITR;
+		break;
+	}
+
 	/* initialize ITR */
 	if (txr_count && !rxr_count)
 		/* tx only vector */
@@ -2108,6 +2300,8 @@ static void wx_set_ivar(struct wx *wx, s8 direction,
 
 	if (direction == -1) {
 		/* other causes */
+		if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags))
+			msix_vector = 0;
 		msix_vector |= WX_PX_IVAR_ALLOC_VAL;
 		index = 0;
 		ivar = rd32(wx, WX_PX_MISC_IVAR);
@@ -2116,7 +2310,6 @@ static void wx_set_ivar(struct wx *wx, s8 direction,
 		wr32(wx, WX_PX_MISC_IVAR, ivar);
 	} else {
 		/* tx or rx causes */
-		msix_vector += 1; /* offset for queue vectors */
 		msix_vector |= WX_PX_IVAR_ALLOC_VAL;
 		index = ((16 * (queue & 1)) + (8 * direction));
 		ivar = rd32(wx, WX_PX_IVAR(queue >> 1));
@@ -2140,14 +2333,22 @@ void wx_write_eitr(struct wx_q_vector *q_vector)
 	int v_idx = q_vector->v_idx;
 	u32 itr_reg;
 
-	if (wx->mac.type == wx_mac_sp)
+	switch (wx->mac.type) {
+	case wx_mac_sp:
 		itr_reg = q_vector->itr & WX_SP_MAX_EITR;
-	else
+		break;
+	case wx_mac_aml:
+	case wx_mac_aml40:
+		itr_reg = (q_vector->itr >> 3) & WX_AML_MAX_EITR;
+		break;
+	default:
 		itr_reg = q_vector->itr & WX_EM_MAX_EITR;
+		break;
+	}
 
 	itr_reg |= WX_PX_ITR_CNT_WDIS;
 
-	wr32(wx, WX_PX_ITR(v_idx + 1), itr_reg);
+	wr32(wx, WX_PX_ITR(v_idx), itr_reg);
 }
 
 /**
@@ -2161,10 +2362,17 @@ void wx_configure_vectors(struct wx *wx)
 {
 	struct pci_dev *pdev = wx->pdev;
 	u32 eitrsel = 0;
-	u16 v_idx;
+	u16 v_idx, i;
 
 	if (pdev->msix_enabled) {
 		/* Populate MSIX to EITR Select */
+		if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+			if (wx->num_vfs >= 32)
+				eitrsel = BIT(wx->num_vfs % 32) - 1;
+		} else {
+			for (i = 0; i < wx->num_vfs; i++)
+				eitrsel |= BIT(i);
+		}
 		wr32(wx, WX_PX_ITRSEL, eitrsel);
 		/* use EIAM to auto-mask when MSI-X interrupt is asserted
 		 * this saves a register write for every interrupt
@@ -2193,9 +2401,9 @@ void wx_configure_vectors(struct wx *wx)
 		wx_write_eitr(q_vector);
 	}
 
-	wx_set_ivar(wx, -1, 0, 0);
+	wx_set_ivar(wx, -1, 0, v_idx);
 	if (pdev->msix_enabled)
-		wr32(wx, WX_PX_ITR(0), 1950);
+		wr32(wx, WX_PX_ITR(v_idx), 1950);
 }
 EXPORT_SYMBOL(wx_configure_vectors);
 
@@ -2424,7 +2632,7 @@ static int wx_alloc_page_pool(struct wx_ring *rx_ring)
 	struct page_pool_params pp_params = {
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 		.order = 0,
-		.pool_size = rx_ring->size,
+		.pool_size = rx_ring->count,
 		.nid = dev_to_node(rx_ring->dev),
 		.dev = rx_ring->dev,
 		.dma_dir = DMA_FROM_DEVICE,
@@ -2719,7 +2927,7 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features)
 
 	netdev->features = features;
 
-	if (wx->mac.type == wx_mac_sp && changed & NETIF_F_HW_VLAN_CTAG_RX)
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX && wx->do_reset)
 		wx->do_reset(netdev);
 	else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER))
 		wx_set_rx_mode(netdev);
@@ -2751,7 +2959,7 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features)
 		break;
 	}
 
-	if (need_reset)
+	if (need_reset && wx->do_reset)
 		wx->do_reset(netdev);
 
 	return 0;
@@ -2804,6 +3012,33 @@ netdev_features_t wx_fix_features(struct net_device *netdev,
 }
 EXPORT_SYMBOL(wx_fix_features);
 
+#define WX_MAX_TUNNEL_HDR_LEN	80
+netdev_features_t wx_features_check(struct sk_buff *skb,
+				    struct net_device *netdev,
+				    netdev_features_t features)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	if (!skb->encapsulation)
+		return features;
+
+	if (wx->mac.type == wx_mac_em)
+		return features & ~NETIF_F_CSUM_MASK;
+
+	if (unlikely(skb_inner_mac_header(skb) - skb_transport_header(skb) >
+		     WX_MAX_TUNNEL_HDR_LEN))
+		return features & ~NETIF_F_CSUM_MASK;
+
+	if (skb->inner_protocol_type == ENCAP_TYPE_ETHER &&
+	    skb->inner_protocol != htons(ETH_P_IP) &&
+	    skb->inner_protocol != htons(ETH_P_IPV6) &&
+	    skb->inner_protocol != htons(ETH_P_TEB))
+		return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+
+	return features;
+}
+EXPORT_SYMBOL(wx_features_check);
+
 void wx_set_ring(struct wx *wx, u32 new_tx_count,
 		 u32 new_rx_count, struct wx_ring *temp_ring)
 {
@@ -2870,5 +3105,35 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count,
 }
 EXPORT_SYMBOL(wx_set_ring);
 
+void wx_service_event_schedule(struct wx *wx)
+{
+	if (!test_and_set_bit(WX_STATE_SERVICE_SCHED, wx->state))
+		queue_work(system_power_efficient_wq, &wx->service_task);
+}
+EXPORT_SYMBOL(wx_service_event_schedule);
+
+void wx_service_event_complete(struct wx *wx)
+{
+	if (WARN_ON(!test_bit(WX_STATE_SERVICE_SCHED, wx->state)))
+		return;
+
+	/* flush memory to make sure state is correct before next watchdog */
+	smp_mb__before_atomic();
+	clear_bit(WX_STATE_SERVICE_SCHED, wx->state);
+}
+EXPORT_SYMBOL(wx_service_event_complete);
+
+void wx_service_timer(struct timer_list *t)
+{
+	struct wx *wx = timer_container_of(wx, t, service_timer);
+	unsigned long next_event_offset = HZ * 2;
+
+	/* Reset the timer */
+	mod_timer(&wx->service_timer, next_event_offset + jiffies);
+
+	wx_service_event_schedule(wx);
+}
+EXPORT_SYMBOL(wx_service_timer);
+
 MODULE_DESCRIPTION("Common library for Wangxun(R) Ethernet drivers.");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
index fdeb0c315b75..aed6ea8cf0d6 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
@@ -33,7 +33,13 @@ void wx_get_stats64(struct net_device *netdev,
 int wx_set_features(struct net_device *netdev, netdev_features_t features);
 netdev_features_t wx_fix_features(struct net_device *netdev,
 				  netdev_features_t features);
+netdev_features_t wx_features_check(struct sk_buff *skb,
+				    struct net_device *netdev,
+				    netdev_features_t features);
 void wx_set_ring(struct wx *wx, u32 new_tx_count,
 		 u32 new_rx_count, struct wx_ring *temp_ring);
+void wx_service_event_schedule(struct wx *wx);
+void wx_service_event_complete(struct wx *wx);
+void wx_service_timer(struct timer_list *t);
 
-#endif /* _NGBE_LIB_H_ */
+#endif /* _WX_LIB_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_mbx.c b/drivers/net/ethernet/wangxun/libwx/wx_mbx.c
new file mode 100644
index 000000000000..73af5f11c3bd
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_mbx.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#include <linux/pci.h>
+#include "wx_type.h"
+#include "wx_mbx.h"
+
+/**
+ *  wx_obtain_mbx_lock_pf - obtain mailbox lock
+ *  @wx: pointer to the HW structure
+ *  @vf: the VF index
+ *
+ *  Return: return 0 on success and -EBUSY on failure
+ **/
+static int wx_obtain_mbx_lock_pf(struct wx *wx, u16 vf)
+{
+	int count = 5;
+	u32 mailbox;
+
+	while (count--) {
+		/* Take ownership of the buffer */
+		wr32(wx, WX_PXMAILBOX(vf), WX_PXMAILBOX_PFU);
+
+		/* reserve mailbox for vf use */
+		mailbox = rd32(wx, WX_PXMAILBOX(vf));
+		if (mailbox & WX_PXMAILBOX_PFU)
+			return 0;
+		else if (count)
+			udelay(10);
+	}
+	wx_err(wx, "Failed to obtain mailbox lock for PF%d", vf);
+
+	return -EBUSY;
+}
+
+static int wx_check_for_bit_pf(struct wx *wx, u32 mask, int index)
+{
+	u32 mbvficr = rd32(wx, WX_MBVFICR(index));
+
+	if (!(mbvficr & mask))
+		return -EBUSY;
+	wr32(wx, WX_MBVFICR(index), mask);
+
+	return 0;
+}
+
+/**
+ *  wx_check_for_ack_pf - checks to see if the VF has acked
+ *  @wx: pointer to the HW structure
+ *  @vf: the VF index
+ *
+ *  Return: return 0 if the VF has set the status bit or else -EBUSY
+ **/
+int wx_check_for_ack_pf(struct wx *wx, u16 vf)
+{
+	u32 index = vf / 16, vf_bit = vf % 16;
+
+	return wx_check_for_bit_pf(wx,
+				   FIELD_PREP(WX_MBVFICR_VFACK_MASK,
+					      BIT(vf_bit)),
+				   index);
+}
+
+/**
+ *  wx_check_for_msg_pf - checks to see if the VF has sent mail
+ *  @wx: pointer to the HW structure
+ *  @vf: the VF index
+ *
+ *  Return: return 0 if the VF has got req bit or else -EBUSY
+ **/
+int wx_check_for_msg_pf(struct wx *wx, u16 vf)
+{
+	u32 index = vf / 16, vf_bit = vf % 16;
+
+	return wx_check_for_bit_pf(wx,
+				   FIELD_PREP(WX_MBVFICR_VFREQ_MASK,
+					      BIT(vf_bit)),
+				   index);
+}
+
+/**
+ *  wx_write_mbx_pf - Places a message in the mailbox
+ *  @wx: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @vf: the VF index
+ *
+ *  Return: return 0 on success and -EINVAL/-EBUSY on failure
+ **/
+int wx_write_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf)
+{
+	struct wx_mbx_info *mbx = &wx->mbx;
+	int ret, i;
+
+	/* mbx->size is up to 15 */
+	if (size > mbx->size) {
+		wx_err(wx, "Invalid mailbox message size %d", size);
+		return -EINVAL;
+	}
+
+	/* lock the mailbox to prevent pf/vf race condition */
+	ret = wx_obtain_mbx_lock_pf(wx, vf);
+	if (ret)
+		return ret;
+
+	/* flush msg and acks as we are overwriting the message buffer */
+	wx_check_for_msg_pf(wx, vf);
+	wx_check_for_ack_pf(wx, vf);
+
+	/* copy the caller specified message to the mailbox memory buffer */
+	for (i = 0; i < size; i++)
+		wr32a(wx, WX_PXMBMEM(vf), i, msg[i]);
+
+	/* Interrupt VF to tell it a message has been sent and release buffer */
+	/* set mirrored mailbox flags */
+	wr32a(wx, WX_PXMBMEM(vf), WX_VXMAILBOX_SIZE, WX_PXMAILBOX_STS);
+	wr32(wx, WX_PXMAILBOX(vf), WX_PXMAILBOX_STS);
+
+	return 0;
+}
+
+/**
+ *  wx_read_mbx_pf - Read a message from the mailbox
+ *  @wx: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @vf: the VF index
+ *
+ *  Return: return 0 on success and -EBUSY on failure
+ **/
+int wx_read_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf)
+{
+	struct wx_mbx_info *mbx = &wx->mbx;
+	int ret;
+	u16 i;
+
+	/* limit read to size of mailbox and mbx->size is up to 15 */
+	if (size > mbx->size)
+		size = mbx->size;
+
+	/* lock the mailbox to prevent pf/vf race condition */
+	ret = wx_obtain_mbx_lock_pf(wx, vf);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < size; i++)
+		msg[i] = rd32a(wx, WX_PXMBMEM(vf), i);
+
+	/* Acknowledge the message and release buffer */
+	/* set mirrored mailbox flags */
+	wr32a(wx, WX_PXMBMEM(vf), WX_VXMAILBOX_SIZE, WX_PXMAILBOX_ACK);
+	wr32(wx, WX_PXMAILBOX(vf), WX_PXMAILBOX_ACK);
+
+	return 0;
+}
+
+/**
+ *  wx_check_for_rst_pf - checks to see if the VF has reset
+ *  @wx: pointer to the HW structure
+ *  @vf: the VF index
+ *
+ *  Return: return 0 on success and -EBUSY on failure
+ **/
+int wx_check_for_rst_pf(struct wx *wx, u16 vf)
+{
+	u32 reg_offset = WX_VF_REG_OFFSET(vf);
+	u32 vf_shift = WX_VF_IND_SHIFT(vf);
+	u32 vflre = 0;
+
+	vflre = rd32(wx, WX_VFLRE(reg_offset));
+	if (!(vflre & BIT(vf_shift)))
+		return -EBUSY;
+	wr32(wx, WX_VFLREC(reg_offset), BIT(vf_shift));
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_mbx.h b/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
new file mode 100644
index 000000000000..05aae138dbc3
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+#ifndef _WX_MBX_H_
+#define _WX_MBX_H_
+
+#define WX_VXMAILBOX_SIZE    15
+
+/* PF Registers */
+#define WX_PXMAILBOX(i)      (0x600 + (4 * (i))) /* i=[0,63] */
+#define WX_PXMAILBOX_STS     BIT(0) /* Initiate message send to VF */
+#define WX_PXMAILBOX_ACK     BIT(1) /* Ack message recv'd from VF */
+#define WX_PXMAILBOX_PFU     BIT(3) /* PF owns the mailbox buffer */
+
+#define WX_PXMBMEM(i)        (0x5000 + (64 * (i))) /* i=[0,63] */
+
+#define WX_VFLRE(i)          (0x4A0 + (4 * (i))) /* i=[0,1] */
+#define WX_VFLREC(i)         (0x4A8 + (4 * (i))) /* i=[0,1] */
+
+/* SR-IOV specific macros */
+#define WX_MBVFICR(i)         (0x480 + (4 * (i))) /* i=[0,3] */
+#define WX_MBVFICR_VFREQ_MASK GENMASK(15, 0)
+#define WX_MBVFICR_VFACK_MASK GENMASK(31, 16)
+
+#define WX_VT_MSGTYPE_ACK     BIT(31)
+#define WX_VT_MSGTYPE_NACK    BIT(30)
+#define WX_VT_MSGTYPE_CTS     BIT(29)
+#define WX_VT_MSGINFO_SHIFT   16
+#define WX_VT_MSGINFO_MASK    GENMASK(23, 16)
+
+enum wx_pfvf_api_rev {
+	wx_mbox_api_null,
+	wx_mbox_api_13 = 4,      /* API version 1.3 */
+	wx_mbox_api_unknown, /* indicates that API version is not known */
+};
+
+/* mailbox API */
+#define WX_VF_RESET                  0x01 /* VF requests reset */
+#define WX_VF_SET_MAC_ADDR           0x02 /* VF requests PF to set MAC addr */
+#define WX_VF_SET_MULTICAST          0x03 /* VF requests PF to set MC addr */
+#define WX_VF_SET_VLAN               0x04 /* VF requests PF to set VLAN */
+#define WX_VF_SET_LPE                0x05 /* VF requests PF to set VMOLR.LPE */
+#define WX_VF_SET_MACVLAN            0x06 /* VF requests PF unicast filter */
+#define WX_VF_API_NEGOTIATE          0x08 /* negotiate API version */
+#define WX_VF_GET_QUEUES             0x09 /* get queue configuration */
+#define WX_VF_GET_RETA               0x0a /* VF request for RETA */
+#define WX_VF_GET_RSS_KEY            0x0b /* get RSS key */
+#define WX_VF_UPDATE_XCAST_MODE      0x0c
+#define WX_VF_GET_LINK_STATE         0x10 /* get vf link state */
+#define WX_VF_GET_FW_VERSION         0x11 /* get fw version */
+
+#define WX_VF_BACKUP                 0x8001 /* VF requests backup */
+
+#define WX_PF_CONTROL_MSG            BIT(8) /* PF control message */
+#define WX_PF_NOFITY_VF_LINK_STATUS  0x1
+#define WX_PF_NOFITY_VF_NET_NOT_RUNNING BIT(31)
+
+#define WX_VF_TX_QUEUES              1 /* number of Tx queues supported */
+#define WX_VF_RX_QUEUES              2 /* number of Rx queues supported */
+#define WX_VF_TRANS_VLAN             3 /* Indication of port vlan */
+#define WX_VF_DEF_QUEUE              4 /* Default queue offset */
+
+#define WX_VF_PERMADDR_MSG_LEN       4
+
+enum wxvf_xcast_modes {
+	WXVF_XCAST_MODE_NONE = 0,
+	WXVF_XCAST_MODE_MULTI,
+	WXVF_XCAST_MODE_ALLMULTI,
+	WXVF_XCAST_MODE_PROMISC,
+};
+
+int wx_write_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf);
+int wx_read_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf);
+int wx_check_for_rst_pf(struct wx *wx, u16 mbx_id);
+int wx_check_for_msg_pf(struct wx *wx, u16 mbx_id);
+int wx_check_for_ack_pf(struct wx *wx, u16 mbx_id);
+
+#endif /* _WX_MBX_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
new file mode 100644
index 000000000000..2c39b879f977
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
@@ -0,0 +1,905 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+/* Copyright (c) 1999 - 2025 Intel Corporation. */
+
+#include <linux/ptp_classify.h>
+#include <linux/clocksource.h>
+#include <linux/pci.h>
+
+#include "wx_type.h"
+#include "wx_ptp.h"
+#include "wx_hw.h"
+
+#define WX_INCVAL_10GB        0xCCCCCC
+#define WX_INCVAL_1GB         0x800000
+#define WX_INCVAL_100         0xA00000
+#define WX_INCVAL_10          0xC7F380
+#define WX_INCVAL_EM          0x2000000
+#define WX_INCVAL_AML         0xA00000
+
+#define WX_INCVAL_SHIFT_10GB  20
+#define WX_INCVAL_SHIFT_1GB   18
+#define WX_INCVAL_SHIFT_100   15
+#define WX_INCVAL_SHIFT_10    12
+#define WX_INCVAL_SHIFT_EM    22
+#define WX_INCVAL_SHIFT_AML   21
+
+#define WX_OVERFLOW_PERIOD    (HZ * 30)
+#define WX_PTP_TX_TIMEOUT     (HZ)
+
+#define WX_1588_PPS_WIDTH_EM  120
+
+#define WX_NS_PER_SEC         1000000000ULL
+
+static u64 wx_ptp_timecounter_cyc2time(struct wx *wx, u64 timestamp)
+{
+	unsigned int seq;
+	u64 ns;
+
+	do {
+		seq = read_seqbegin(&wx->hw_tc_lock);
+		ns = timecounter_cyc2time(&wx->hw_tc, timestamp);
+	} while (read_seqretry(&wx->hw_tc_lock, seq));
+
+	return ns;
+}
+
+static u64 wx_ptp_readtime(struct wx *wx, struct ptp_system_timestamp *sts)
+{
+	u32 timeh1, timeh2, timel;
+
+	timeh1 = rd32ptp(wx, WX_TSC_1588_SYSTIMH);
+	ptp_read_system_prets(sts);
+	timel = rd32ptp(wx, WX_TSC_1588_SYSTIML);
+	ptp_read_system_postts(sts);
+	timeh2 = rd32ptp(wx, WX_TSC_1588_SYSTIMH);
+
+	if (timeh1 != timeh2) {
+		ptp_read_system_prets(sts);
+		timel = rd32ptp(wx, WX_TSC_1588_SYSTIML);
+		ptp_read_system_prets(sts);
+	}
+	return (u64)timel | (u64)timeh2 << 32;
+}
+
+static int wx_ptp_adjfine(struct ptp_clock_info *ptp, long ppb)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	u64 incval, mask;
+
+	smp_mb(); /* Force any pending update before accessing. */
+	incval = READ_ONCE(wx->base_incval);
+	incval = adjust_by_scaled_ppm(incval, ppb);
+
+	mask = (wx->mac.type == wx_mac_em) ? 0x7FFFFFF : 0xFFFFFF;
+	incval &= mask;
+	if (wx->mac.type != wx_mac_em)
+		incval |= 2 << 24;
+
+	wr32ptp(wx, WX_TSC_1588_INC, incval);
+
+	return 0;
+}
+
+static int wx_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	unsigned long flags;
+
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	timecounter_adjtime(&wx->hw_tc, delta);
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+
+	if (wx->ptp_setup_sdp)
+		wx->ptp_setup_sdp(wx);
+
+	return 0;
+}
+
+static int wx_ptp_gettimex64(struct ptp_clock_info *ptp,
+			     struct timespec64 *ts,
+			     struct ptp_system_timestamp *sts)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	u64 ns, stamp;
+
+	stamp = wx_ptp_readtime(wx, sts);
+	ns = wx_ptp_timecounter_cyc2time(wx, stamp);
+	*ts = ns_to_timespec64(ns);
+
+	return 0;
+}
+
+static int wx_ptp_settime64(struct ptp_clock_info *ptp,
+			    const struct timespec64 *ts)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	unsigned long flags;
+	u64 ns;
+
+	ns = timespec64_to_ns(ts);
+	/* reset the timecounter */
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	timecounter_init(&wx->hw_tc, &wx->hw_cc, ns);
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+
+	if (wx->ptp_setup_sdp)
+		wx->ptp_setup_sdp(wx);
+
+	return 0;
+}
+
+/**
+ * wx_ptp_clear_tx_timestamp - utility function to clear Tx timestamp state
+ * @wx: the private board structure
+ *
+ * This function should be called whenever the state related to a Tx timestamp
+ * needs to be cleared. This helps ensure that all related bits are reset for
+ * the next Tx timestamp event.
+ */
+static void wx_ptp_clear_tx_timestamp(struct wx *wx)
+{
+	rd32ptp(wx, WX_TSC_1588_STMPH);
+	if (wx->ptp_tx_skb) {
+		dev_kfree_skb_any(wx->ptp_tx_skb);
+		wx->ptp_tx_skb = NULL;
+	}
+	clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state);
+}
+
+/**
+ * wx_ptp_convert_to_hwtstamp - convert register value to hw timestamp
+ * @wx: private board structure
+ * @hwtstamp: stack timestamp structure
+ * @timestamp: unsigned 64bit system time value
+ *
+ * We need to convert the adapter's RX/TXSTMP registers into a hwtstamp value
+ * which can be used by the stack's ptp functions.
+ *
+ * The lock is used to protect consistency of the cyclecounter and the SYSTIME
+ * registers. However, it does not need to protect against the Rx or Tx
+ * timestamp registers, as there can't be a new timestamp until the old one is
+ * unlatched by reading.
+ *
+ * In addition to the timestamp in hardware, some controllers need a software
+ * overflow cyclecounter, and this function takes this into account as well.
+ **/
+static void wx_ptp_convert_to_hwtstamp(struct wx *wx,
+				       struct skb_shared_hwtstamps *hwtstamp,
+				       u64 timestamp)
+{
+	u64 ns;
+
+	ns = wx_ptp_timecounter_cyc2time(wx, timestamp);
+	hwtstamp->hwtstamp = ns_to_ktime(ns);
+}
+
+/**
+ * wx_ptp_tx_hwtstamp - utility function which checks for TX time stamp
+ * @wx: the private board struct
+ *
+ * if the timestamp is valid, we convert it into the timecounter ns
+ * value, then store that result into the shhwtstamps structure which
+ * is passed up the network stack
+ */
+static void wx_ptp_tx_hwtstamp(struct wx *wx)
+{
+	struct skb_shared_hwtstamps shhwtstamps;
+	struct sk_buff *skb = wx->ptp_tx_skb;
+	u64 regval = 0;
+
+	regval |= (u64)rd32ptp(wx, WX_TSC_1588_STMPL);
+	regval |= (u64)rd32ptp(wx, WX_TSC_1588_STMPH) << 32;
+
+	wx_ptp_convert_to_hwtstamp(wx, &shhwtstamps, regval);
+
+	wx->ptp_tx_skb = NULL;
+	clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state);
+	skb_tstamp_tx(skb, &shhwtstamps);
+	dev_kfree_skb_any(skb);
+	wx->tx_hwtstamp_pkts++;
+}
+
+static int wx_ptp_tx_hwtstamp_work(struct wx *wx)
+{
+	u32 tsynctxctl;
+
+	/* we have to have a valid skb to poll for a timestamp */
+	if (!wx->ptp_tx_skb) {
+		wx_ptp_clear_tx_timestamp(wx);
+		return 0;
+	}
+
+	/* stop polling once we have a valid timestamp */
+	tsynctxctl = rd32ptp(wx, WX_TSC_1588_CTL);
+	if (tsynctxctl & WX_TSC_1588_CTL_VALID) {
+		wx_ptp_tx_hwtstamp(wx);
+		return 0;
+	}
+
+	return -1;
+}
+
+/**
+ * wx_ptp_overflow_check - watchdog task to detect SYSTIME overflow
+ * @wx: pointer to wx struct
+ *
+ * this watchdog task periodically reads the timecounter
+ * in order to prevent missing when the system time registers wrap
+ * around. This needs to be run approximately twice a minute for the fastest
+ * overflowing hardware. We run it for all hardware since it shouldn't have a
+ * large impact.
+ */
+static void wx_ptp_overflow_check(struct wx *wx)
+{
+	bool timeout = time_is_before_jiffies(wx->last_overflow_check +
+					      WX_OVERFLOW_PERIOD);
+	unsigned long flags;
+
+	if (timeout) {
+		/* Update the timecounter */
+		write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+		timecounter_read(&wx->hw_tc);
+		write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+
+		wx->last_overflow_check = jiffies;
+	}
+}
+
+/**
+ * wx_ptp_rx_hang - detect error case when Rx timestamp registers latched
+ * @wx: pointer to wx struct
+ *
+ * this watchdog task is scheduled to detect error case where hardware has
+ * dropped an Rx packet that was timestamped when the ring is full. The
+ * particular error is rare but leaves the device in a state unable to
+ * timestamp any future packets.
+ */
+static void wx_ptp_rx_hang(struct wx *wx)
+{
+	struct wx_ring *rx_ring;
+	unsigned long rx_event;
+	u32 tsyncrxctl;
+	int n;
+
+	tsyncrxctl = rd32(wx, WX_PSR_1588_CTL);
+
+	/* if we don't have a valid timestamp in the registers, just update the
+	 * timeout counter and exit
+	 */
+	if (!(tsyncrxctl & WX_PSR_1588_CTL_VALID)) {
+		wx->last_rx_ptp_check = jiffies;
+		return;
+	}
+
+	/* determine the most recent watchdog or rx_timestamp event */
+	rx_event = wx->last_rx_ptp_check;
+	for (n = 0; n < wx->num_rx_queues; n++) {
+		rx_ring = wx->rx_ring[n];
+		if (time_after(rx_ring->last_rx_timestamp, rx_event))
+			rx_event = rx_ring->last_rx_timestamp;
+	}
+
+	/* only need to read the high RXSTMP register to clear the lock */
+	if (time_is_before_jiffies(rx_event + 5 * HZ)) {
+		rd32(wx, WX_PSR_1588_STMPH);
+		wx->last_rx_ptp_check = jiffies;
+
+		wx->rx_hwtstamp_cleared++;
+		dev_warn(&wx->pdev->dev, "clearing RX Timestamp hang");
+	}
+}
+
+/**
+ * wx_ptp_tx_hang - detect error case where Tx timestamp never finishes
+ * @wx: private network wx structure
+ */
+static void wx_ptp_tx_hang(struct wx *wx)
+{
+	bool timeout = time_is_before_jiffies(wx->ptp_tx_start +
+					      WX_PTP_TX_TIMEOUT);
+
+	if (!wx->ptp_tx_skb)
+		return;
+
+	if (!test_bit(WX_STATE_PTP_TX_IN_PROGRESS, wx->state))
+		return;
+
+	/* If we haven't received a timestamp within the timeout, it is
+	 * reasonable to assume that it will never occur, so we can unlock the
+	 * timestamp bit when this occurs.
+	 */
+	if (timeout) {
+		wx_ptp_clear_tx_timestamp(wx);
+		wx->tx_hwtstamp_timeouts++;
+		dev_warn(&wx->pdev->dev, "clearing Tx timestamp hang\n");
+	}
+}
+
+static long wx_ptp_do_aux_work(struct ptp_clock_info *ptp)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	int ts_done;
+
+	ts_done = wx_ptp_tx_hwtstamp_work(wx);
+
+	wx_ptp_overflow_check(wx);
+	if (unlikely(test_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER,
+			      wx->flags)))
+		wx_ptp_rx_hang(wx);
+	wx_ptp_tx_hang(wx);
+
+	return ts_done ? 1 : HZ;
+}
+
+static u64 wx_ptp_trigger_calc(struct wx *wx)
+{
+	struct cyclecounter *cc = &wx->hw_cc;
+	unsigned long flags;
+	u64 ns = 0;
+	u32 rem;
+
+	/* Read the current clock time, and save the cycle counter value */
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	ns = timecounter_read(&wx->hw_tc);
+	wx->pps_edge_start = wx->hw_tc.cycle_last;
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+	wx->pps_edge_end = wx->pps_edge_start;
+
+	/* Figure out how far past the next second we are */
+	div_u64_rem(ns, WX_NS_PER_SEC, &rem);
+
+	/* Figure out how many nanoseconds to add to round the clock edge up
+	 * to the next full second
+	 */
+	rem = (WX_NS_PER_SEC - rem);
+
+	/* Adjust the clock edge to align with the next full second. */
+	wx->pps_edge_start += div_u64(((u64)rem << cc->shift), cc->mult);
+	wx->pps_edge_end += div_u64(((u64)(rem + wx->pps_width) <<
+				     cc->shift), cc->mult);
+
+	return (ns + rem);
+}
+
+static int wx_ptp_setup_sdp(struct wx *wx)
+{
+	struct cyclecounter *cc = &wx->hw_cc;
+	u32 tsauxc;
+	u64 nsec;
+
+	if (wx->pps_width >= WX_NS_PER_SEC) {
+		wx_err(wx, "PTP pps width cannot be longer than 1s!\n");
+		return -EINVAL;
+	}
+
+	/* disable the pin first */
+	wr32ptp(wx, WX_TSC_1588_AUX_CTL, 0);
+	WX_WRITE_FLUSH(wx);
+
+	if (!test_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags)) {
+		if (wx->pps_enabled) {
+			wx->pps_enabled = false;
+			wx_set_pps(wx, false, 0, 0);
+		}
+		return 0;
+	}
+
+	wx->pps_enabled = true;
+	nsec = wx_ptp_trigger_calc(wx);
+	wx_set_pps(wx, wx->pps_enabled, nsec, wx->pps_edge_start);
+
+	tsauxc = WX_TSC_1588_AUX_CTL_PLSG | WX_TSC_1588_AUX_CTL_EN_TT0 |
+		WX_TSC_1588_AUX_CTL_EN_TT1 | WX_TSC_1588_AUX_CTL_EN_TS0;
+	wr32ptp(wx, WX_TSC_1588_TRGT_L(0), (u32)wx->pps_edge_start);
+	wr32ptp(wx, WX_TSC_1588_TRGT_H(0), (u32)(wx->pps_edge_start >> 32));
+	wr32ptp(wx, WX_TSC_1588_TRGT_L(1), (u32)wx->pps_edge_end);
+	wr32ptp(wx, WX_TSC_1588_TRGT_H(1), (u32)(wx->pps_edge_end >> 32));
+	wr32ptp(wx, WX_TSC_1588_SDP(0),
+		WX_TSC_1588_SDP_FUN_SEL_TT0 | WX_TSC_1588_SDP_OUT_LEVEL_H);
+	wr32ptp(wx, WX_TSC_1588_SDP(1), WX_TSC_1588_SDP_FUN_SEL_TS0);
+	wr32ptp(wx, WX_TSC_1588_AUX_CTL, tsauxc);
+	wr32ptp(wx, WX_TSC_1588_INT_EN, WX_TSC_1588_INT_EN_TT1);
+	WX_WRITE_FLUSH(wx);
+
+	/* Adjust the clock edge to align with the next full second. */
+	wx->sec_to_cc = div_u64(((u64)WX_NS_PER_SEC << cc->shift), cc->mult);
+
+	return 0;
+}
+
+static int wx_ptp_feature_enable(struct ptp_clock_info *ptp,
+				 struct ptp_clock_request *rq, int on)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+
+	/**
+	 * When PPS is enabled, unmask the interrupt for the ClockOut
+	 * feature, so that the interrupt handler can send the PPS
+	 * event when the clock SDP triggers. Clear mask when PPS is
+	 * disabled
+	 */
+	if (rq->type != PTP_CLK_REQ_PEROUT || !wx->ptp_setup_sdp)
+		return -EOPNOTSUPP;
+
+	/* Reject requests with unsupported flags */
+	if (rq->perout.flags & ~(PTP_PEROUT_DUTY_CYCLE |
+				 PTP_PEROUT_PHASE))
+		return -EOPNOTSUPP;
+
+	if (rq->perout.phase.sec || rq->perout.phase.nsec) {
+		wx_err(wx, "Absolute start time not supported.\n");
+		return -EINVAL;
+	}
+
+	if (rq->perout.period.sec != 1 || rq->perout.period.nsec) {
+		wx_err(wx, "Only 1pps is supported.\n");
+		return -EINVAL;
+	}
+
+	if (rq->perout.flags & PTP_PEROUT_DUTY_CYCLE) {
+		struct timespec64 ts_on;
+
+		ts_on.tv_sec = rq->perout.on.sec;
+		ts_on.tv_nsec = rq->perout.on.nsec;
+		wx->pps_width = timespec64_to_ns(&ts_on);
+	} else {
+		wx->pps_width = 120000000;
+	}
+
+	if (on)
+		set_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags);
+	else
+		clear_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags);
+
+	return wx->ptp_setup_sdp(wx);
+}
+
+void wx_ptp_check_pps_event(struct wx *wx)
+{
+	u32 tsauxc, int_status;
+
+	/* this check is necessary in case the interrupt was enabled via some
+	 * alternative means (ex. debug_fs). Better to check here than
+	 * everywhere that calls this function.
+	 */
+	if (!wx->ptp_clock)
+		return;
+
+	int_status = rd32ptp(wx, WX_TSC_1588_INT_ST);
+	if (int_status & WX_TSC_1588_INT_ST_TT1) {
+		/* disable the pin first */
+		wr32ptp(wx, WX_TSC_1588_AUX_CTL, 0);
+		WX_WRITE_FLUSH(wx);
+
+		wx_ptp_trigger_calc(wx);
+
+		tsauxc = WX_TSC_1588_AUX_CTL_PLSG | WX_TSC_1588_AUX_CTL_EN_TT0 |
+			 WX_TSC_1588_AUX_CTL_EN_TT1 | WX_TSC_1588_AUX_CTL_EN_TS0;
+		wr32ptp(wx, WX_TSC_1588_TRGT_L(0), (u32)wx->pps_edge_start);
+		wr32ptp(wx, WX_TSC_1588_TRGT_H(0), (u32)(wx->pps_edge_start >> 32));
+		wr32ptp(wx, WX_TSC_1588_TRGT_L(1), (u32)wx->pps_edge_end);
+		wr32ptp(wx, WX_TSC_1588_TRGT_H(1), (u32)(wx->pps_edge_end >> 32));
+		wr32ptp(wx, WX_TSC_1588_AUX_CTL, tsauxc);
+		WX_WRITE_FLUSH(wx);
+	}
+}
+EXPORT_SYMBOL(wx_ptp_check_pps_event);
+
+static long wx_ptp_create_clock(struct wx *wx)
+{
+	struct net_device *netdev = wx->netdev;
+	long err;
+
+	/* do nothing if we already have a clock device */
+	if (!IS_ERR_OR_NULL(wx->ptp_clock))
+		return 0;
+
+	snprintf(wx->ptp_caps.name, sizeof(wx->ptp_caps.name),
+		 "%s", netdev->name);
+	wx->ptp_caps.owner = THIS_MODULE;
+	wx->ptp_caps.n_alarm = 0;
+	wx->ptp_caps.n_ext_ts = 0;
+	wx->ptp_caps.pps = 0;
+	wx->ptp_caps.adjfine = wx_ptp_adjfine;
+	wx->ptp_caps.adjtime = wx_ptp_adjtime;
+	wx->ptp_caps.gettimex64 = wx_ptp_gettimex64;
+	wx->ptp_caps.settime64 = wx_ptp_settime64;
+	wx->ptp_caps.do_aux_work = wx_ptp_do_aux_work;
+	switch (wx->mac.type) {
+	case wx_mac_aml:
+	case wx_mac_aml40:
+		wx->ptp_caps.max_adj = 250000000;
+		wx->ptp_caps.n_per_out = 1;
+		wx->ptp_setup_sdp = wx_ptp_setup_sdp;
+		wx->ptp_caps.enable = wx_ptp_feature_enable;
+		break;
+	case wx_mac_sp:
+		wx->ptp_caps.max_adj = 250000000;
+		wx->ptp_caps.n_per_out = 0;
+		wx->ptp_setup_sdp = NULL;
+		break;
+	case wx_mac_em:
+		wx->ptp_caps.max_adj = 500000000;
+		wx->ptp_caps.n_per_out = 1;
+		wx->ptp_setup_sdp = wx_ptp_setup_sdp;
+		wx->ptp_caps.enable = wx_ptp_feature_enable;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	wx->ptp_clock = ptp_clock_register(&wx->ptp_caps, &wx->pdev->dev);
+	if (IS_ERR(wx->ptp_clock)) {
+		err = PTR_ERR(wx->ptp_clock);
+		wx->ptp_clock = NULL;
+		wx_err(wx, "ptp clock register failed\n");
+		return err;
+	} else if (wx->ptp_clock) {
+		dev_info(&wx->pdev->dev, "registered PHC device on %s\n",
+			 netdev->name);
+	}
+
+	/* Set the default timestamp mode to disabled here. We do this in
+	 * create_clock instead of initialization, because we don't want to
+	 * override the previous settings during a suspend/resume cycle.
+	 */
+	wx->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	wx->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+
+	return 0;
+}
+
+static int wx_ptp_set_timestamp_mode(struct wx *wx,
+				     struct kernel_hwtstamp_config *config)
+{
+	u32 tsync_tx_ctl = WX_TSC_1588_CTL_ENABLED;
+	u32 tsync_rx_ctl = WX_PSR_1588_CTL_ENABLED;
+	DECLARE_BITMAP(flags, WX_PF_FLAGS_NBITS);
+	u32 tsync_rx_mtrl = PTP_EV_PORT << 16;
+	bool is_l2 = false;
+	u32 regval;
+
+	memcpy(flags, wx->flags, sizeof(wx->flags));
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		tsync_tx_ctl = 0;
+		break;
+	case HWTSTAMP_TX_ON:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		tsync_rx_ctl = 0;
+		tsync_rx_mtrl = 0;
+		clear_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags);
+		clear_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags);
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+		tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_L4_V1;
+		tsync_rx_mtrl |= WX_PSR_1588_MSG_V1_SYNC;
+		set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags);
+		set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags);
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_L4_V1;
+		tsync_rx_mtrl |= WX_PSR_1588_MSG_V1_DELAY_REQ;
+		set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags);
+		set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags);
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+		tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_EVENT_V2;
+		is_l2 = true;
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags);
+		set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags);
+		break;
+	default:
+		/* register PSR_1588_MSG must be set in order to do V1 packets,
+		 * therefore it is not possible to time stamp both V1 Sync and
+		 * Delay_Req messages unless hardware supports timestamping all
+		 * packets => return error
+		 */
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
+		return -ERANGE;
+	}
+
+	/* define ethertype filter for timestamping L2 packets */
+	if (is_l2)
+		wr32(wx, WX_PSR_ETYPE_SWC(WX_PSR_ETYPE_SWC_FILTER_1588),
+		     (WX_PSR_ETYPE_SWC_FILTER_EN | /* enable filter */
+		      WX_PSR_ETYPE_SWC_1588 | /* enable timestamping */
+		      ETH_P_1588)); /* 1588 eth protocol type */
+	else
+		wr32(wx, WX_PSR_ETYPE_SWC(WX_PSR_ETYPE_SWC_FILTER_1588), 0);
+
+	/* enable/disable TX */
+	regval = rd32ptp(wx, WX_TSC_1588_CTL);
+	regval &= ~WX_TSC_1588_CTL_ENABLED;
+	regval |= tsync_tx_ctl;
+	wr32ptp(wx, WX_TSC_1588_CTL, regval);
+
+	/* enable/disable RX */
+	regval = rd32(wx, WX_PSR_1588_CTL);
+	regval &= ~(WX_PSR_1588_CTL_ENABLED | WX_PSR_1588_CTL_TYPE_MASK);
+	regval |= tsync_rx_ctl;
+	wr32(wx, WX_PSR_1588_CTL, regval);
+
+	/* define which PTP packets are time stamped */
+	wr32(wx, WX_PSR_1588_MSG, tsync_rx_mtrl);
+
+	WX_WRITE_FLUSH(wx);
+
+	/* configure adapter flags only when HW is actually configured */
+	memcpy(wx->flags, flags, sizeof(wx->flags));
+
+	/* clear TX/RX timestamp state, just to be sure */
+	wx_ptp_clear_tx_timestamp(wx);
+	rd32(wx, WX_PSR_1588_STMPH);
+
+	return 0;
+}
+
+static u64 wx_ptp_read(const struct cyclecounter *hw_cc)
+{
+	struct wx *wx = container_of(hw_cc, struct wx, hw_cc);
+
+	return wx_ptp_readtime(wx, NULL);
+}
+
+static void wx_ptp_link_speed_adjust(struct wx *wx, u32 *shift, u32 *incval)
+{
+	switch (wx->mac.type) {
+	case wx_mac_aml:
+	case wx_mac_aml40:
+		*shift = WX_INCVAL_SHIFT_AML;
+		*incval = WX_INCVAL_AML;
+		return;
+	case wx_mac_em:
+		*shift = WX_INCVAL_SHIFT_EM;
+		*incval = WX_INCVAL_EM;
+		return;
+	default:
+		break;
+	}
+
+	switch (wx->speed) {
+	case SPEED_10:
+		*shift = WX_INCVAL_SHIFT_10;
+		*incval = WX_INCVAL_10;
+		break;
+	case SPEED_100:
+		*shift = WX_INCVAL_SHIFT_100;
+		*incval = WX_INCVAL_100;
+		break;
+	case SPEED_1000:
+		*shift = WX_INCVAL_SHIFT_1GB;
+		*incval = WX_INCVAL_1GB;
+		break;
+	case SPEED_10000:
+	default:
+		*shift = WX_INCVAL_SHIFT_10GB;
+		*incval = WX_INCVAL_10GB;
+		break;
+	}
+}
+
+/**
+ * wx_ptp_reset_cyclecounter - create the cycle counter from hw
+ * @wx: pointer to the wx structure
+ *
+ * This function should be called to set the proper values for the TSC_1588_INC
+ * register and tell the cyclecounter structure what the tick rate of SYSTIME
+ * is. It does not directly modify SYSTIME registers or the timecounter
+ * structure. It should be called whenever a new TSC_1588_INC value is
+ * necessary, such as during initialization or when the link speed changes.
+ */
+void wx_ptp_reset_cyclecounter(struct wx *wx)
+{
+	u32 incval = 0, mask = 0;
+	struct cyclecounter cc;
+	unsigned long flags;
+
+	/* For some of the boards below this mask is technically incorrect.
+	 * The timestamp mask overflows at approximately 61bits. However the
+	 * particular hardware does not overflow on an even bitmask value.
+	 * Instead, it overflows due to conversion of upper 32bits billions of
+	 * cycles. Timecounters are not really intended for this purpose so
+	 * they do not properly function if the overflow point isn't 2^N-1.
+	 * However, the actual SYSTIME values in question take ~138 years to
+	 * overflow. In practice this means they won't actually overflow. A
+	 * proper fix to this problem would require modification of the
+	 * timecounter delta calculations.
+	 */
+	cc.mask = CLOCKSOURCE_MASK(64);
+	cc.mult = 1;
+	cc.shift = 0;
+
+	cc.read = wx_ptp_read;
+	wx_ptp_link_speed_adjust(wx, &cc.shift, &incval);
+
+	/* update the base incval used to calculate frequency adjustment */
+	WRITE_ONCE(wx->base_incval, incval);
+
+	mask = (wx->mac.type == wx_mac_em) ? 0x7FFFFFF : 0xFFFFFF;
+	incval &= mask;
+	if (wx->mac.type != wx_mac_em)
+		incval |= 2 << 24;
+	wr32ptp(wx, WX_TSC_1588_INC, incval);
+
+	smp_mb(); /* Force the above update. */
+
+	/* need lock to prevent incorrect read while modifying cyclecounter */
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	memcpy(&wx->hw_cc, &cc, sizeof(wx->hw_cc));
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+}
+EXPORT_SYMBOL(wx_ptp_reset_cyclecounter);
+
+void wx_ptp_reset(struct wx *wx)
+{
+	unsigned long flags;
+
+	/* reset the hardware timestamping mode */
+	wx_ptp_set_timestamp_mode(wx, &wx->tstamp_config);
+	wx_ptp_reset_cyclecounter(wx);
+
+	wr32ptp(wx, WX_TSC_1588_SYSTIML, 0);
+	wr32ptp(wx, WX_TSC_1588_SYSTIMH, 0);
+	WX_WRITE_FLUSH(wx);
+
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	timecounter_init(&wx->hw_tc, &wx->hw_cc,
+			 ktime_to_ns(ktime_get_real()));
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+
+	wx->last_overflow_check = jiffies;
+	ptp_schedule_worker(wx->ptp_clock, HZ);
+
+	/* Now that the shift has been calculated and the systime
+	 * registers reset, (re-)enable the Clock out feature
+	 */
+	if (wx->ptp_setup_sdp)
+		wx->ptp_setup_sdp(wx);
+}
+EXPORT_SYMBOL(wx_ptp_reset);
+
+void wx_ptp_init(struct wx *wx)
+{
+	/* Initialize the seqlock_t first, since the user might call the clock
+	 * functions any time after we've initialized the ptp clock device.
+	 */
+	seqlock_init(&wx->hw_tc_lock);
+
+	/* obtain a ptp clock device, or re-use an existing device */
+	if (wx_ptp_create_clock(wx))
+		return;
+
+	wx->tx_hwtstamp_pkts = 0;
+	wx->tx_hwtstamp_timeouts = 0;
+	wx->tx_hwtstamp_skipped = 0;
+	wx->tx_hwtstamp_errors = 0;
+	wx->rx_hwtstamp_cleared = 0;
+	/* reset the ptp related hardware bits */
+	wx_ptp_reset(wx);
+
+	/* enter the WX_STATE_PTP_RUNNING state */
+	set_bit(WX_STATE_PTP_RUNNING, wx->state);
+}
+EXPORT_SYMBOL(wx_ptp_init);
+
+/**
+ * wx_ptp_suspend - stop ptp work items
+ * @wx: pointer to wx struct
+ *
+ * This function suspends ptp activity, and prevents more work from being
+ * generated, but does not destroy the clock device.
+ */
+void wx_ptp_suspend(struct wx *wx)
+{
+	/* leave the WX_STATE_PTP_RUNNING STATE */
+	if (!test_and_clear_bit(WX_STATE_PTP_RUNNING, wx->state))
+		return;
+
+	clear_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags);
+	if (wx->ptp_setup_sdp)
+		wx->ptp_setup_sdp(wx);
+
+	wx_ptp_clear_tx_timestamp(wx);
+}
+EXPORT_SYMBOL(wx_ptp_suspend);
+
+/**
+ * wx_ptp_stop - destroy the ptp_clock device
+ * @wx: pointer to wx struct
+ *
+ * Completely destroy the ptp_clock device, and disable all PTP related
+ * features. Intended to be run when the device is being closed.
+ */
+void wx_ptp_stop(struct wx *wx)
+{
+	/* first, suspend ptp activity */
+	wx_ptp_suspend(wx);
+
+	/* now destroy the ptp clock device */
+	if (wx->ptp_clock) {
+		ptp_clock_unregister(wx->ptp_clock);
+		wx->ptp_clock = NULL;
+		dev_info(&wx->pdev->dev, "removed PHC on %s\n", wx->netdev->name);
+	}
+}
+EXPORT_SYMBOL(wx_ptp_stop);
+
+/**
+ * wx_ptp_rx_hwtstamp - utility function which checks for RX time stamp
+ * @wx: pointer to wx struct
+ * @skb: particular skb to send timestamp with
+ *
+ * if the timestamp is valid, we convert it into the timecounter ns
+ * value, then store that result into the shhwtstamps structure which
+ * is passed up the network stack
+ */
+void wx_ptp_rx_hwtstamp(struct wx *wx, struct sk_buff *skb)
+{
+	u64 regval = 0;
+	u32 tsyncrxctl;
+
+	/* Read the tsyncrxctl register afterwards in order to prevent taking an
+	 * I/O hit on every packet.
+	 */
+	tsyncrxctl = rd32(wx, WX_PSR_1588_CTL);
+	if (!(tsyncrxctl & WX_PSR_1588_CTL_VALID))
+		return;
+
+	regval |= (u64)rd32(wx, WX_PSR_1588_STMPL);
+	regval |= (u64)rd32(wx, WX_PSR_1588_STMPH) << 32;
+
+	wx_ptp_convert_to_hwtstamp(wx, skb_hwtstamps(skb), regval);
+}
+
+int wx_hwtstamp_get(struct net_device *dev,
+		    struct kernel_hwtstamp_config *cfg)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	*cfg = wx->tstamp_config;
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_hwtstamp_get);
+
+int wx_hwtstamp_set(struct net_device *dev,
+		    struct kernel_hwtstamp_config *cfg,
+		    struct netlink_ext_ack *extack)
+{
+	struct wx *wx = netdev_priv(dev);
+	int err;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	err = wx_ptp_set_timestamp_mode(wx, cfg);
+	if (err)
+		return err;
+
+	/* save these settings for future reference */
+	memcpy(&wx->tstamp_config, cfg, sizeof(wx->tstamp_config));
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_hwtstamp_set);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.h b/drivers/net/ethernet/wangxun/libwx/wx_ptp.h
new file mode 100644
index 000000000000..50db90a6e3ee
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#ifndef _WX_PTP_H_
+#define _WX_PTP_H_
+
+void wx_ptp_check_pps_event(struct wx *wx);
+void wx_ptp_reset_cyclecounter(struct wx *wx);
+void wx_ptp_reset(struct wx *wx);
+void wx_ptp_init(struct wx *wx);
+void wx_ptp_suspend(struct wx *wx);
+void wx_ptp_stop(struct wx *wx);
+void wx_ptp_rx_hwtstamp(struct wx *wx, struct sk_buff *skb);
+int wx_hwtstamp_get(struct net_device *dev,
+		    struct kernel_hwtstamp_config *cfg);
+int wx_hwtstamp_set(struct net_device *dev,
+		    struct kernel_hwtstamp_config *cfg,
+		    struct netlink_ext_ack *extack);
+
+#endif /* _WX_PTP_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
new file mode 100644
index 000000000000..c82ae137756c
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
@@ -0,0 +1,913 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#include <linux/etherdevice.h>
+#include <linux/pci.h>
+
+#include "wx_type.h"
+#include "wx_hw.h"
+#include "wx_mbx.h"
+#include "wx_sriov.h"
+
+static void wx_vf_configuration(struct pci_dev *pdev, int event_mask)
+{
+	bool enable = !!WX_VF_ENABLE_CHECK(event_mask);
+	struct wx *wx = pci_get_drvdata(pdev);
+	u32 vfn = WX_VF_NUM_GET(event_mask);
+
+	if (enable)
+		eth_zero_addr(wx->vfinfo[vfn].vf_mac_addr);
+}
+
+static int wx_alloc_vf_macvlans(struct wx *wx, u8 num_vfs)
+{
+	struct vf_macvlans *mv_list;
+	int num_vf_macvlans, i;
+
+	/* Initialize list of VF macvlans */
+	INIT_LIST_HEAD(&wx->vf_mvs.mvlist);
+
+	num_vf_macvlans = wx->mac.num_rar_entries -
+			  (WX_MAX_PF_MACVLANS + 1 + num_vfs);
+	if (!num_vf_macvlans)
+		return -EINVAL;
+
+	mv_list = kcalloc(num_vf_macvlans, sizeof(struct vf_macvlans),
+			  GFP_KERNEL);
+	if (!mv_list)
+		return -ENOMEM;
+
+	for (i = 0; i < num_vf_macvlans; i++) {
+		mv_list[i].vf = -1;
+		mv_list[i].free = true;
+		list_add(&mv_list[i].mvlist, &wx->vf_mvs.mvlist);
+	}
+	wx->mv_list = mv_list;
+
+	return 0;
+}
+
+static void wx_sriov_clear_data(struct wx *wx)
+{
+	/* set num VFs to 0 to prevent access to vfinfo */
+	wx->num_vfs = 0;
+
+	/* free VF control structures */
+	kfree(wx->vfinfo);
+	wx->vfinfo = NULL;
+
+	/* free macvlan list */
+	kfree(wx->mv_list);
+	wx->mv_list = NULL;
+
+	/* set default pool back to 0 */
+	wr32m(wx, WX_PSR_VM_CTL, WX_PSR_VM_CTL_POOL_MASK, 0);
+	wx->ring_feature[RING_F_VMDQ].offset = 0;
+
+	clear_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags);
+	clear_bit(WX_FLAG_SRIOV_ENABLED, wx->flags);
+	/* Disable VMDq flag so device will be set in NM mode */
+	if (wx->ring_feature[RING_F_VMDQ].limit == 1)
+		clear_bit(WX_FLAG_VMDQ_ENABLED, wx->flags);
+}
+
+static int __wx_enable_sriov(struct wx *wx, u8 num_vfs)
+{
+	int i, ret = 0;
+	u32 value = 0;
+
+	set_bit(WX_FLAG_SRIOV_ENABLED, wx->flags);
+	dev_info(&wx->pdev->dev, "SR-IOV enabled with %d VFs\n", num_vfs);
+
+	if (num_vfs == 7 && wx->mac.type == wx_mac_em)
+		set_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags);
+
+	/* Enable VMDq flag so device will be set in VM mode */
+	set_bit(WX_FLAG_VMDQ_ENABLED, wx->flags);
+	if (!wx->ring_feature[RING_F_VMDQ].limit)
+		wx->ring_feature[RING_F_VMDQ].limit = 1;
+	wx->ring_feature[RING_F_VMDQ].offset = num_vfs;
+
+	wx->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage),
+			     GFP_KERNEL);
+	if (!wx->vfinfo)
+		return -ENOMEM;
+
+	ret = wx_alloc_vf_macvlans(wx, num_vfs);
+	if (ret)
+		return ret;
+
+	/* Initialize default switching mode VEB */
+	wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_SW_EN, WX_PSR_CTL_SW_EN);
+
+	for (i = 0; i < num_vfs; i++) {
+		/* enable spoof checking for all VFs */
+		wx->vfinfo[i].spoofchk_enabled = true;
+		wx->vfinfo[i].link_enable = true;
+		/* untrust all VFs */
+		wx->vfinfo[i].trusted = false;
+		/* set the default xcast mode */
+		wx->vfinfo[i].xcast_mode = WXVF_XCAST_MODE_NONE;
+	}
+
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		value = WX_CFG_PORT_CTL_NUM_VT_8;
+	} else {
+		if (num_vfs < 32)
+			value = WX_CFG_PORT_CTL_NUM_VT_32;
+		else
+			value = WX_CFG_PORT_CTL_NUM_VT_64;
+	}
+	wr32m(wx, WX_CFG_PORT_CTL,
+	      WX_CFG_PORT_CTL_NUM_VT_MASK,
+	      value);
+
+	return ret;
+}
+
+static void wx_sriov_reinit(struct wx *wx)
+{
+	rtnl_lock();
+	wx->setup_tc(wx->netdev, netdev_get_num_tc(wx->netdev));
+	rtnl_unlock();
+}
+
+void wx_disable_sriov(struct wx *wx)
+{
+	if (!pci_vfs_assigned(wx->pdev))
+		pci_disable_sriov(wx->pdev);
+	else
+		wx_err(wx, "Unloading driver while VFs are assigned.\n");
+
+	/* clear flags and free allloced data */
+	wx_sriov_clear_data(wx);
+}
+EXPORT_SYMBOL(wx_disable_sriov);
+
+static int wx_pci_sriov_enable(struct pci_dev *dev,
+			       int num_vfs)
+{
+	struct wx *wx = pci_get_drvdata(dev);
+	int err = 0, i;
+
+	err = __wx_enable_sriov(wx, num_vfs);
+	if (err)
+		return err;
+
+	wx->num_vfs = num_vfs;
+	for (i = 0; i < wx->num_vfs; i++)
+		wx_vf_configuration(dev, (i | WX_VF_ENABLE));
+
+	/* reset before enabling SRIOV to avoid mailbox issues */
+	wx_sriov_reinit(wx);
+
+	err = pci_enable_sriov(dev, num_vfs);
+	if (err) {
+		wx_err(wx, "Failed to enable PCI sriov: %d\n", err);
+		goto err_out;
+	}
+
+	return num_vfs;
+err_out:
+	wx_sriov_clear_data(wx);
+	return err;
+}
+
+static void wx_pci_sriov_disable(struct pci_dev *dev)
+{
+	struct wx *wx = pci_get_drvdata(dev);
+
+	wx_disable_sriov(wx);
+	wx_sriov_reinit(wx);
+}
+
+int wx_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	struct wx *wx = pci_get_drvdata(pdev);
+	int err;
+
+	if (!num_vfs) {
+		if (!pci_vfs_assigned(pdev)) {
+			wx_pci_sriov_disable(pdev);
+			return 0;
+		}
+
+		wx_err(wx, "can't free VFs because some are assigned to VMs.\n");
+		return -EBUSY;
+	}
+
+	err = wx_pci_sriov_enable(pdev, num_vfs);
+	if (err)
+		return err;
+
+	return num_vfs;
+}
+EXPORT_SYMBOL(wx_pci_sriov_configure);
+
+static int wx_set_vf_mac(struct wx *wx, u16 vf, const u8 *mac_addr)
+{
+	u8 hw_addr[ETH_ALEN];
+	int ret = 0;
+
+	ether_addr_copy(hw_addr, mac_addr);
+	wx_del_mac_filter(wx, wx->vfinfo[vf].vf_mac_addr, vf);
+	ret = wx_add_mac_filter(wx, hw_addr, vf);
+	if (ret >= 0)
+		ether_addr_copy(wx->vfinfo[vf].vf_mac_addr, mac_addr);
+	else
+		eth_zero_addr(wx->vfinfo[vf].vf_mac_addr);
+
+	return ret;
+}
+
+static void wx_set_vmolr(struct wx *wx, u16 vf, bool aupe)
+{
+	u32 vmolr = rd32(wx, WX_PSR_VM_L2CTL(vf));
+
+	vmolr |=  WX_PSR_VM_L2CTL_BAM;
+	if (aupe)
+		vmolr |= WX_PSR_VM_L2CTL_AUPE;
+	else
+		vmolr &= ~WX_PSR_VM_L2CTL_AUPE;
+	wr32(wx, WX_PSR_VM_L2CTL(vf), vmolr);
+}
+
+static void wx_set_vmvir(struct wx *wx, u16 vid, u16 qos, u16 vf)
+{
+	u32 vmvir = vid | (qos << VLAN_PRIO_SHIFT) |
+		    WX_TDM_VLAN_INS_VLANA_DEFAULT;
+
+	wr32(wx, WX_TDM_VLAN_INS(vf), vmvir);
+}
+
+static int wx_set_vf_vlan(struct wx *wx, int add, int vid, u16 vf)
+{
+	if (!vid && !add)
+		return 0;
+
+	return wx_set_vfta(wx, vid, vf, (bool)add);
+}
+
+static void wx_set_vlan_anti_spoofing(struct wx *wx, bool enable, int vf)
+{
+	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
+	u32 pfvfspoof;
+
+	pfvfspoof = rd32(wx, WX_TDM_VLAN_AS(index));
+	if (enable)
+		pfvfspoof |= BIT(vf_bit);
+	else
+		pfvfspoof &= ~BIT(vf_bit);
+	wr32(wx, WX_TDM_VLAN_AS(index), pfvfspoof);
+}
+
+static void wx_write_qde(struct wx *wx, u32 vf, u32 qde)
+{
+	struct wx_ring_feature *vmdq = &wx->ring_feature[RING_F_VMDQ];
+	u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask);
+	u32 reg = 0, n = vf * q_per_pool / 32;
+	u32 i = vf * q_per_pool;
+
+	reg = rd32(wx, WX_RDM_PF_QDE(n));
+	for (i = (vf * q_per_pool - n * 32);
+	     i < ((vf + 1) * q_per_pool - n * 32);
+	     i++) {
+		if (qde == 1)
+			reg |= qde << i;
+		else
+			reg &= qde << i;
+	}
+
+	wr32(wx, WX_RDM_PF_QDE(n), reg);
+}
+
+static void wx_clear_vmvir(struct wx *wx, u32 vf)
+{
+	wr32(wx, WX_TDM_VLAN_INS(vf), 0);
+}
+
+static void wx_ping_vf(struct wx *wx, int vf)
+{
+	u32 ping = WX_PF_CONTROL_MSG;
+
+	if (wx->vfinfo[vf].clear_to_send)
+		ping |= WX_VT_MSGTYPE_CTS;
+	wx_write_mbx_pf(wx, &ping, 1, vf);
+}
+
+static void wx_set_vf_rx_tx(struct wx *wx, int vf)
+{
+	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
+	u32 reg_cur_tx, reg_cur_rx, reg_req_tx, reg_req_rx;
+
+	reg_cur_tx = rd32(wx, WX_TDM_VF_TE(index));
+	reg_cur_rx = rd32(wx, WX_RDM_VF_RE(index));
+
+	if (wx->vfinfo[vf].link_enable) {
+		reg_req_tx = reg_cur_tx | BIT(vf_bit);
+		reg_req_rx = reg_cur_rx | BIT(vf_bit);
+		/* Enable particular VF */
+		if (reg_cur_tx != reg_req_tx)
+			wr32(wx, WX_TDM_VF_TE(index), reg_req_tx);
+		if (reg_cur_rx != reg_req_rx)
+			wr32(wx, WX_RDM_VF_RE(index), reg_req_rx);
+	} else {
+		reg_req_tx = BIT(vf_bit);
+		reg_req_rx = BIT(vf_bit);
+		/* Disable particular VF */
+		if (reg_cur_tx & reg_req_tx)
+			wr32(wx, WX_TDM_VFTE_CLR(index), reg_req_tx);
+		if (reg_cur_rx & reg_req_rx)
+			wr32(wx, WX_RDM_VFRE_CLR(index), reg_req_rx);
+	}
+}
+
+static int wx_get_vf_queues(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	struct wx_ring_feature *vmdq = &wx->ring_feature[RING_F_VMDQ];
+	unsigned int default_tc = 0;
+
+	msgbuf[WX_VF_TX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask);
+	msgbuf[WX_VF_RX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask);
+
+	if (wx->vfinfo[vf].pf_vlan || wx->vfinfo[vf].pf_qos)
+		msgbuf[WX_VF_TRANS_VLAN] = 1;
+	else
+		msgbuf[WX_VF_TRANS_VLAN] = 0;
+
+	/* notify VF of default queue */
+	msgbuf[WX_VF_DEF_QUEUE] = default_tc;
+
+	return 0;
+}
+
+static void wx_vf_reset_event(struct wx *wx, u16 vf)
+{
+	struct vf_data_storage *vfinfo = &wx->vfinfo[vf];
+	u8 num_tcs = netdev_get_num_tc(wx->netdev);
+
+	/* add PF assigned VLAN */
+	wx_set_vf_vlan(wx, true, vfinfo->pf_vlan, vf);
+
+	/* reset offloads to defaults */
+	wx_set_vmolr(wx, vf, !vfinfo->pf_vlan);
+
+	/* set outgoing tags for VFs */
+	if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) {
+		wx_clear_vmvir(wx, vf);
+	} else {
+		if (vfinfo->pf_qos || !num_tcs)
+			wx_set_vmvir(wx, vfinfo->pf_vlan,
+				     vfinfo->pf_qos, vf);
+		else
+			wx_set_vmvir(wx, vfinfo->pf_vlan,
+				     wx->default_up, vf);
+	}
+
+	/* reset multicast table array for vf */
+	wx->vfinfo[vf].num_vf_mc_hashes = 0;
+
+	/* Flush and reset the mta with the new values */
+	wx_set_rx_mode(wx->netdev);
+
+	wx_del_mac_filter(wx, wx->vfinfo[vf].vf_mac_addr, vf);
+	/* reset VF api back to unknown */
+	wx->vfinfo[vf].vf_api = wx_mbox_api_null;
+}
+
+static void wx_vf_reset_msg(struct wx *wx, u16 vf)
+{
+	const u8 *vf_mac = wx->vfinfo[vf].vf_mac_addr;
+	struct net_device *dev = wx->netdev;
+	u32 msgbuf[5] = {0, 0, 0, 0, 0};
+	u8 *addr = (u8 *)(&msgbuf[1]);
+	u32 reg = 0, index, vf_bit;
+	int pf_max_frame;
+
+	/* reset the filters for the device */
+	wx_vf_reset_event(wx, vf);
+
+	/* set vf mac address */
+	if (!is_zero_ether_addr(vf_mac))
+		wx_set_vf_mac(wx, vf, vf_mac);
+
+	index = WX_VF_REG_OFFSET(vf);
+	vf_bit = WX_VF_IND_SHIFT(vf);
+
+	/* force drop enable for all VF Rx queues */
+	wx_write_qde(wx, vf, 1);
+
+	/* set transmit and receive for vf */
+	wx_set_vf_rx_tx(wx, vf);
+
+	pf_max_frame = dev->mtu + ETH_HLEN;
+
+	if (pf_max_frame > ETH_FRAME_LEN)
+		reg = BIT(vf_bit);
+	wr32(wx, WX_RDM_VFRE_CLR(index), reg);
+
+	/* enable VF mailbox for further messages */
+	wx->vfinfo[vf].clear_to_send = true;
+
+	/* reply to reset with ack and vf mac address */
+	msgbuf[0] = WX_VF_RESET;
+	if (!is_zero_ether_addr(vf_mac)) {
+		msgbuf[0] |= WX_VT_MSGTYPE_ACK;
+		memcpy(addr, vf_mac, ETH_ALEN);
+	} else {
+		msgbuf[0] |= WX_VT_MSGTYPE_NACK;
+		wx_err(wx, "VF %d has no MAC address assigned", vf);
+	}
+
+	msgbuf[3] = wx->mac.mc_filter_type;
+	wx_write_mbx_pf(wx, msgbuf, WX_VF_PERMADDR_MSG_LEN, vf);
+}
+
+static int wx_set_vf_mac_addr(struct wx *wx, u32 *msgbuf, u16 vf)
+{
+	const u8 *new_mac = ((u8 *)(&msgbuf[1]));
+	int ret;
+
+	if (!is_valid_ether_addr(new_mac)) {
+		wx_err(wx, "VF %d attempted to set invalid mac\n", vf);
+		return -EINVAL;
+	}
+
+	if (wx->vfinfo[vf].pf_set_mac &&
+	    memcmp(wx->vfinfo[vf].vf_mac_addr, new_mac, ETH_ALEN)) {
+		wx_err(wx,
+		       "VF %d attempt to set a MAC but it already had a MAC.",
+		       vf);
+		return -EBUSY;
+	}
+
+	ret = wx_set_vf_mac(wx, vf, new_mac);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static void wx_set_vf_multicasts(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	struct vf_data_storage *vfinfo = &wx->vfinfo[vf];
+	u16 entries = (msgbuf[0] & WX_VT_MSGINFO_MASK)
+		      >> WX_VT_MSGINFO_SHIFT;
+	u32 vmolr = rd32(wx, WX_PSR_VM_L2CTL(vf));
+	u32 vector_bit, vector_reg, mta_reg, i;
+	u16 *hash_list = (u16 *)&msgbuf[1];
+
+	/* only so many hash values supported */
+	entries = min_t(u16, entries, WX_MAX_VF_MC_ENTRIES);
+	vfinfo->num_vf_mc_hashes = entries;
+
+	for (i = 0; i < entries; i++)
+		vfinfo->vf_mc_hashes[i] = hash_list[i];
+
+	for (i = 0; i < vfinfo->num_vf_mc_hashes; i++) {
+		vector_reg = WX_PSR_MC_TBL_REG(vfinfo->vf_mc_hashes[i]);
+		vector_bit = WX_PSR_MC_TBL_BIT(vfinfo->vf_mc_hashes[i]);
+		mta_reg = wx->mac.mta_shadow[vector_reg];
+		mta_reg |= BIT(vector_bit);
+		wx->mac.mta_shadow[vector_reg] = mta_reg;
+		wr32(wx, WX_PSR_MC_TBL(vector_reg), mta_reg);
+	}
+	vmolr |= WX_PSR_VM_L2CTL_ROMPE;
+	wr32(wx, WX_PSR_VM_L2CTL(vf), vmolr);
+}
+
+static void wx_set_vf_lpe(struct wx *wx, u32 max_frame, u32 vf)
+{
+	u32 index, vf_bit, vfre;
+	u32 max_frs, reg_val;
+
+	/* determine VF receive enable location */
+	index = WX_VF_REG_OFFSET(vf);
+	vf_bit = WX_VF_IND_SHIFT(vf);
+
+	vfre = rd32(wx, WX_RDM_VF_RE(index));
+	vfre |= BIT(vf_bit);
+	wr32(wx, WX_RDM_VF_RE(index), vfre);
+
+	/* pull current max frame size from hardware */
+	max_frs = DIV_ROUND_UP(max_frame, 1024);
+	reg_val = rd32(wx, WX_MAC_WDG_TIMEOUT) & WX_MAC_WDG_TIMEOUT_WTO_MASK;
+	if (max_frs > (reg_val + WX_MAC_WDG_TIMEOUT_WTO_DELTA))
+		wr32(wx, WX_MAC_WDG_TIMEOUT,
+		     max_frs - WX_MAC_WDG_TIMEOUT_WTO_DELTA);
+}
+
+static int wx_find_vlvf_entry(struct wx *wx, u32 vlan)
+{
+	int regindex;
+	u32 vlvf;
+
+	/* short cut the special case */
+	if (vlan == 0)
+		return 0;
+
+	/* Search for the vlan id in the VLVF entries */
+	for (regindex = 1; regindex < WX_PSR_VLAN_SWC_ENTRIES; regindex++) {
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, regindex);
+		vlvf = rd32(wx, WX_PSR_VLAN_SWC);
+		if ((vlvf & VLAN_VID_MASK) == vlan)
+			break;
+	}
+
+	/* Return a negative value if not found */
+	if (regindex >= WX_PSR_VLAN_SWC_ENTRIES)
+		regindex = -EINVAL;
+
+	return regindex;
+}
+
+static int wx_set_vf_macvlan(struct wx *wx,
+			     u16 vf, int index, unsigned char *mac_addr)
+{
+	struct vf_macvlans *entry;
+	struct list_head *pos;
+	int retval = 0;
+
+	if (index <= 1) {
+		list_for_each(pos, &wx->vf_mvs.mvlist) {
+			entry = list_entry(pos, struct vf_macvlans, mvlist);
+			if (entry->vf == vf) {
+				entry->vf = -1;
+				entry->free = true;
+				entry->is_macvlan = false;
+				wx_del_mac_filter(wx, entry->vf_macvlan, vf);
+			}
+		}
+	}
+
+	if (!index)
+		return 0;
+
+	entry = NULL;
+	list_for_each(pos, &wx->vf_mvs.mvlist) {
+		entry = list_entry(pos, struct vf_macvlans, mvlist);
+		if (entry->free)
+			break;
+	}
+
+	if (!entry || !entry->free)
+		return -ENOSPC;
+
+	retval = wx_add_mac_filter(wx, mac_addr, vf);
+	if (retval >= 0) {
+		entry->free = false;
+		entry->is_macvlan = true;
+		entry->vf = vf;
+		memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN);
+	}
+
+	return retval;
+}
+
+static int wx_set_vf_vlan_msg(struct wx *wx, u32 *msgbuf, u16 vf)
+{
+	int add = (msgbuf[0] & WX_VT_MSGINFO_MASK) >> WX_VT_MSGINFO_SHIFT;
+	int vid = (msgbuf[1] & WX_PSR_VLAN_SWC_VLANID_MASK);
+	int ret;
+
+	if (add)
+		wx->vfinfo[vf].vlan_count++;
+	else if (wx->vfinfo[vf].vlan_count)
+		wx->vfinfo[vf].vlan_count--;
+
+	/* in case of promiscuous mode any VLAN filter set for a VF must
+	 * also have the PF pool added to it.
+	 */
+	if (add && wx->netdev->flags & IFF_PROMISC)
+		wx_set_vf_vlan(wx, add, vid, VMDQ_P(0));
+
+	ret = wx_set_vf_vlan(wx, add, vid, vf);
+	if (!ret && wx->vfinfo[vf].spoofchk_enabled)
+		wx_set_vlan_anti_spoofing(wx, true, vf);
+
+	/* Go through all the checks to see if the VLAN filter should
+	 * be wiped completely.
+	 */
+	if (!add && wx->netdev->flags & IFF_PROMISC) {
+		u32 bits = 0, vlvf;
+		int reg_ndx;
+
+		reg_ndx = wx_find_vlvf_entry(wx, vid);
+		if (reg_ndx < 0)
+			return -ENOSPC;
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, reg_ndx);
+		vlvf = rd32(wx, WX_PSR_VLAN_SWC);
+		/* See if any other pools are set for this VLAN filter
+		 * entry other than the PF.
+		 */
+		if (VMDQ_P(0) < 32) {
+			bits = rd32(wx, WX_PSR_VLAN_SWC_VM_L);
+			bits &= ~BIT(VMDQ_P(0));
+			if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
+				bits |= rd32(wx, WX_PSR_VLAN_SWC_VM_H);
+		} else {
+			if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
+				bits = rd32(wx, WX_PSR_VLAN_SWC_VM_H);
+			bits &= ~BIT(VMDQ_P(0) % 32);
+			bits |= rd32(wx, WX_PSR_VLAN_SWC_VM_L);
+		}
+		/* If the filter was removed then ensure PF pool bit
+		 * is cleared if the PF only added itself to the pool
+		 * because the PF is in promiscuous mode.
+		 */
+		if ((vlvf & VLAN_VID_MASK) == vid && !bits)
+			wx_set_vf_vlan(wx, add, vid, VMDQ_P(0));
+	}
+
+	return 0;
+}
+
+static int wx_set_vf_macvlan_msg(struct wx *wx, u32 *msgbuf, u16 vf)
+{
+	int index = (msgbuf[0] & WX_VT_MSGINFO_MASK) >>
+		    WX_VT_MSGINFO_SHIFT;
+	u8 *new_mac = ((u8 *)(&msgbuf[1]));
+	int err;
+
+	if (wx->vfinfo[vf].pf_set_mac && index > 0) {
+		wx_err(wx, "VF %d request MACVLAN filter but is denied\n", vf);
+		return -EINVAL;
+	}
+
+	/* An non-zero index indicates the VF is setting a filter */
+	if (index) {
+		if (!is_valid_ether_addr(new_mac)) {
+			wx_err(wx, "VF %d attempted to set invalid mac\n", vf);
+			return -EINVAL;
+		}
+		/* If the VF is allowed to set MAC filters then turn off
+		 * anti-spoofing to avoid false positives.
+		 */
+		if (wx->vfinfo[vf].spoofchk_enabled)
+			wx_set_vf_spoofchk(wx->netdev, vf, false);
+	}
+
+	err = wx_set_vf_macvlan(wx, vf, index, new_mac);
+	if (err == -ENOSPC)
+		wx_err(wx,
+		       "VF %d request MACVLAN filter but there is no space\n",
+		       vf);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int wx_negotiate_vf_api(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	int api = msgbuf[1];
+
+	switch (api) {
+	case wx_mbox_api_13:
+		wx->vfinfo[vf].vf_api = api;
+		return 0;
+	default:
+		wx_err(wx, "VF %d requested invalid api version %u\n", vf, api);
+		return -EINVAL;
+	}
+}
+
+static int wx_get_vf_link_state(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	msgbuf[1] = wx->vfinfo[vf].link_enable;
+
+	return 0;
+}
+
+static int wx_get_fw_version(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	unsigned long fw_version = 0ULL;
+	int ret = 0;
+
+	ret = kstrtoul(wx->eeprom_id, 16, &fw_version);
+	if (ret)
+		return -EOPNOTSUPP;
+	msgbuf[1] = fw_version;
+
+	return 0;
+}
+
+static int wx_update_vf_xcast_mode(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	int xcast_mode = msgbuf[1];
+	u32 vmolr, disable, enable;
+
+	if (wx->vfinfo[vf].xcast_mode == xcast_mode)
+		return 0;
+
+	switch (xcast_mode) {
+	case WXVF_XCAST_MODE_NONE:
+		disable = WX_PSR_VM_L2CTL_BAM | WX_PSR_VM_L2CTL_ROMPE |
+			  WX_PSR_VM_L2CTL_MPE | WX_PSR_VM_L2CTL_UPE |
+			  WX_PSR_VM_L2CTL_VPE;
+		enable = 0;
+		break;
+	case WXVF_XCAST_MODE_MULTI:
+		disable = WX_PSR_VM_L2CTL_MPE | WX_PSR_VM_L2CTL_UPE |
+			  WX_PSR_VM_L2CTL_VPE;
+		enable = WX_PSR_VM_L2CTL_BAM | WX_PSR_VM_L2CTL_ROMPE;
+		break;
+	case WXVF_XCAST_MODE_ALLMULTI:
+		disable = WX_PSR_VM_L2CTL_UPE | WX_PSR_VM_L2CTL_VPE;
+		enable = WX_PSR_VM_L2CTL_BAM | WX_PSR_VM_L2CTL_ROMPE |
+			 WX_PSR_VM_L2CTL_MPE;
+		break;
+	case WXVF_XCAST_MODE_PROMISC:
+		disable = 0;
+		enable = WX_PSR_VM_L2CTL_BAM | WX_PSR_VM_L2CTL_ROMPE |
+			 WX_PSR_VM_L2CTL_MPE | WX_PSR_VM_L2CTL_UPE |
+			 WX_PSR_VM_L2CTL_VPE;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	vmolr = rd32(wx, WX_PSR_VM_L2CTL(vf));
+	vmolr &= ~disable;
+	vmolr |= enable;
+	wr32(wx, WX_PSR_VM_L2CTL(vf), vmolr);
+
+	wx->vfinfo[vf].xcast_mode = xcast_mode;
+	msgbuf[1] = xcast_mode;
+
+	return 0;
+}
+
+static void wx_rcv_msg_from_vf(struct wx *wx, u16 vf)
+{
+	u16 mbx_size = WX_VXMAILBOX_SIZE;
+	u32 msgbuf[WX_VXMAILBOX_SIZE];
+	int retval;
+
+	retval = wx_read_mbx_pf(wx, msgbuf, mbx_size, vf);
+	if (retval) {
+		wx_err(wx, "Error receiving message from VF\n");
+		return;
+	}
+
+	/* this is a message we already processed, do nothing */
+	if (msgbuf[0] & (WX_VT_MSGTYPE_ACK | WX_VT_MSGTYPE_NACK))
+		return;
+
+	if (msgbuf[0] == WX_VF_RESET) {
+		wx_vf_reset_msg(wx, vf);
+		return;
+	}
+
+	/* until the vf completes a virtual function reset it should not be
+	 * allowed to start any configuration.
+	 */
+	if (!wx->vfinfo[vf].clear_to_send) {
+		msgbuf[0] |= WX_VT_MSGTYPE_NACK;
+		wx_write_mbx_pf(wx, msgbuf, 1, vf);
+		return;
+	}
+
+	switch ((msgbuf[0] & U16_MAX)) {
+	case WX_VF_SET_MAC_ADDR:
+		retval = wx_set_vf_mac_addr(wx, msgbuf, vf);
+		break;
+	case WX_VF_SET_MULTICAST:
+		wx_set_vf_multicasts(wx, msgbuf, vf);
+		retval = 0;
+		break;
+	case WX_VF_SET_VLAN:
+		retval = wx_set_vf_vlan_msg(wx, msgbuf, vf);
+		break;
+	case WX_VF_SET_LPE:
+		wx_set_vf_lpe(wx, msgbuf[1], vf);
+		retval = 0;
+		break;
+	case WX_VF_SET_MACVLAN:
+		retval = wx_set_vf_macvlan_msg(wx, msgbuf, vf);
+		break;
+	case WX_VF_API_NEGOTIATE:
+		retval = wx_negotiate_vf_api(wx, msgbuf, vf);
+		break;
+	case WX_VF_GET_QUEUES:
+		retval = wx_get_vf_queues(wx, msgbuf, vf);
+		break;
+	case WX_VF_GET_LINK_STATE:
+		retval = wx_get_vf_link_state(wx, msgbuf, vf);
+		break;
+	case WX_VF_GET_FW_VERSION:
+		retval = wx_get_fw_version(wx, msgbuf, vf);
+		break;
+	case WX_VF_UPDATE_XCAST_MODE:
+		retval = wx_update_vf_xcast_mode(wx, msgbuf, vf);
+		break;
+	case WX_VF_BACKUP:
+		break;
+	default:
+		wx_err(wx, "Unhandled Msg %8.8x\n", msgbuf[0]);
+		break;
+	}
+
+	/* notify the VF of the results of what it sent us */
+	if (retval)
+		msgbuf[0] |= WX_VT_MSGTYPE_NACK;
+	else
+		msgbuf[0] |= WX_VT_MSGTYPE_ACK;
+
+	msgbuf[0] |= WX_VT_MSGTYPE_CTS;
+
+	wx_write_mbx_pf(wx, msgbuf, mbx_size, vf);
+}
+
+static void wx_rcv_ack_from_vf(struct wx *wx, u16 vf)
+{
+	u32 msg = WX_VT_MSGTYPE_NACK;
+
+	/* if device isn't clear to send it shouldn't be reading either */
+	if (!wx->vfinfo[vf].clear_to_send)
+		wx_write_mbx_pf(wx, &msg, 1, vf);
+}
+
+void wx_msg_task(struct wx *wx)
+{
+	u16 vf;
+
+	for (vf = 0; vf < wx->num_vfs; vf++) {
+		/* process any reset requests */
+		if (!wx_check_for_rst_pf(wx, vf))
+			wx_vf_reset_event(wx, vf);
+
+		/* process any messages pending */
+		if (!wx_check_for_msg_pf(wx, vf))
+			wx_rcv_msg_from_vf(wx, vf);
+
+		/* process any acks */
+		if (!wx_check_for_ack_pf(wx, vf))
+			wx_rcv_ack_from_vf(wx, vf);
+	}
+}
+EXPORT_SYMBOL(wx_msg_task);
+
+void wx_disable_vf_rx_tx(struct wx *wx)
+{
+	wr32(wx, WX_TDM_VFTE_CLR(0), U32_MAX);
+	wr32(wx, WX_RDM_VFRE_CLR(0), U32_MAX);
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		wr32(wx, WX_TDM_VFTE_CLR(1), U32_MAX);
+		wr32(wx, WX_RDM_VFRE_CLR(1), U32_MAX);
+	}
+}
+EXPORT_SYMBOL(wx_disable_vf_rx_tx);
+
+void wx_ping_all_vfs_with_link_status(struct wx *wx, bool link_up)
+{
+	u32 msgbuf[2] = {0, 0};
+	u16 i;
+
+	if (!wx->num_vfs)
+		return;
+	msgbuf[0] = WX_PF_NOFITY_VF_LINK_STATUS | WX_PF_CONTROL_MSG;
+	if (link_up)
+		msgbuf[1] = FIELD_PREP(GENMASK(31, 1), wx->speed) | link_up;
+	if (wx->notify_down)
+		msgbuf[1] |= WX_PF_NOFITY_VF_NET_NOT_RUNNING;
+	for (i = 0; i < wx->num_vfs; i++) {
+		if (wx->vfinfo[i].clear_to_send)
+			msgbuf[0] |= WX_VT_MSGTYPE_CTS;
+		wx_write_mbx_pf(wx, msgbuf, 2, i);
+	}
+}
+EXPORT_SYMBOL(wx_ping_all_vfs_with_link_status);
+
+static void wx_set_vf_link_state(struct wx *wx, int vf, int state)
+{
+	wx->vfinfo[vf].link_state = state;
+	switch (state) {
+	case IFLA_VF_LINK_STATE_AUTO:
+		if (netif_running(wx->netdev))
+			wx->vfinfo[vf].link_enable = true;
+		else
+			wx->vfinfo[vf].link_enable = false;
+		break;
+	case IFLA_VF_LINK_STATE_ENABLE:
+		wx->vfinfo[vf].link_enable = true;
+		break;
+	case IFLA_VF_LINK_STATE_DISABLE:
+		wx->vfinfo[vf].link_enable = false;
+		break;
+	}
+	/* restart the VF */
+	wx->vfinfo[vf].clear_to_send = false;
+	wx_ping_vf(wx, vf);
+
+	wx_set_vf_rx_tx(wx, vf);
+}
+
+void wx_set_all_vfs(struct wx *wx)
+{
+	int i;
+
+	for (i = 0; i < wx->num_vfs; i++)
+		wx_set_vf_link_state(wx, i, wx->vfinfo[i].link_state);
+}
+EXPORT_SYMBOL(wx_set_all_vfs);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.h b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
new file mode 100644
index 000000000000..8a3a47bb5815
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#ifndef _WX_SRIOV_H_
+#define _WX_SRIOV_H_
+
+#define WX_VF_ENABLE_CHECK(_m)          FIELD_GET(BIT(31), (_m))
+#define WX_VF_NUM_GET(_m)               FIELD_GET(GENMASK(5, 0), (_m))
+#define WX_VF_ENABLE                    BIT(31)
+
+void wx_disable_sriov(struct wx *wx);
+int wx_pci_sriov_configure(struct pci_dev *pdev, int num_vfs);
+void wx_msg_task(struct wx *wx);
+void wx_disable_vf_rx_tx(struct wx *wx);
+void wx_ping_all_vfs_with_link_status(struct wx *wx, bool link_up);
+void wx_set_all_vfs(struct wx *wx);
+
+#endif /* _WX_SRIOV_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index b54bffda027b..c363379126c0 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -4,6 +4,8 @@
 #ifndef _WX_TYPE_H_
 #define _WX_TYPE_H_
 
+#include <linux/ptp_clock_kernel.h>
+#include <linux/timecounter.h>
 #include <linux/bitfield.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
@@ -18,8 +20,13 @@
 /* MSI-X capability fields masks */
 #define WX_PCIE_MSIX_TBL_SZ_MASK                0x7FF
 #define WX_PCI_LINK_STATUS                      0xB2
+#define WX_MAX_PF_MACVLANS                      15
+#define WX_MAX_VF_MC_ENTRIES                    30
 
 /**************** Global Registers ****************************/
+#define WX_VF_REG_OFFSET(_v)         FIELD_GET(GENMASK(15, 5), (_v))
+#define WX_VF_IND_SHIFT(_v)          FIELD_GET(GENMASK(4, 0), (_v))
+
 /* chip control Registers */
 #define WX_MIS_PWR                   0x10000
 #define WX_MIS_RST                   0x1000C
@@ -74,6 +81,9 @@
 #define WX_MAC_LXONOFFRXC            0x11E0C
 
 /*********************** Receive DMA registers **************************/
+#define WX_RDM_VF_RE(_i)             (0x12004 + ((_i) * 4))
+#define WX_RDM_PF_QDE(_i)            (0x12080 + ((_i) * 4))
+#define WX_RDM_VFRE_CLR(_i)          (0x120A0 + ((_i) * 4))
 #define WX_RDM_DRP_PKT               0x12500
 #define WX_RDM_PKT_CNT               0x12504
 #define WX_RDM_BYTE_CNT_LSB          0x12508
@@ -82,12 +92,17 @@
 /************************* Port Registers ************************************/
 /* port cfg Registers */
 #define WX_CFG_PORT_CTL              0x14400
+#define WX_CFG_PORT_CTL_PFRSTD       BIT(14)
 #define WX_CFG_PORT_CTL_DRV_LOAD     BIT(3)
 #define WX_CFG_PORT_CTL_QINQ         BIT(2)
 #define WX_CFG_PORT_CTL_D_VLAN       BIT(0) /* double vlan*/
 #define WX_CFG_TAG_TPID(_i)          (0x14430 + ((_i) * 4))
 #define WX_CFG_PORT_CTL_NUM_VT_MASK  GENMASK(13, 12) /* number of TVs */
 
+#define WX_CFG_PORT_CTL_NUM_VT_NONE  0
+#define WX_CFG_PORT_CTL_NUM_VT_8     FIELD_PREP(GENMASK(13, 12), 1)
+#define WX_CFG_PORT_CTL_NUM_VT_32    FIELD_PREP(GENMASK(13, 12), 2)
+#define WX_CFG_PORT_CTL_NUM_VT_64    FIELD_PREP(GENMASK(13, 12), 3)
 
 /* GPIO Registers */
 #define WX_GPIO_DR                   0x14800
@@ -110,6 +125,11 @@
 /*********************** Transmit DMA registers **************************/
 /* transmit global control */
 #define WX_TDM_CTL                   0x18000
+#define WX_TDM_VF_TE(_i)             (0x18004 + ((_i) * 4))
+#define WX_TDM_MAC_AS(_i)            (0x18060 + ((_i) * 4))
+#define WX_TDM_VLAN_AS(_i)           (0x18070 + ((_i) * 4))
+#define WX_TDM_VFTE_CLR(_i)          (0x180A0 + ((_i) * 4))
+
 /* TDM CTL BIT */
 #define WX_TDM_CTL_TE                BIT(0) /* Transmit Enable */
 #define WX_TDM_PB_THRE(_i)           (0x18020 + ((_i) * 4))
@@ -163,6 +183,7 @@
 /******************************* PSR Registers *******************************/
 /* psr control */
 #define WX_PSR_CTL                   0x15000
+#define WX_PSR_VM_CTL                0x151B0
 /* Header split receive */
 #define WX_PSR_CTL_SW_EN             BIT(18)
 #define WX_PSR_CTL_RSC_ACK           BIT(17)
@@ -180,14 +201,36 @@
 #define WX_PSR_VLAN_CTL              0x15088
 #define WX_PSR_VLAN_CTL_CFIEN        BIT(29)  /* bit 29 */
 #define WX_PSR_VLAN_CTL_VFE          BIT(30)  /* bit 30 */
+/* EType Queue Filter */
+#define WX_PSR_ETYPE_SWC(_i)         (0x15128 + ((_i) * 4))
+#define WX_PSR_ETYPE_SWC_FILTER_1588 3
+#define WX_PSR_ETYPE_SWC_FILTER_EN   BIT(31)
+#define WX_PSR_ETYPE_SWC_1588        BIT(30)
+/* 1588 */
+#define WX_PSR_1588_MSG                 0x15120
+#define WX_PSR_1588_MSG_V1_SYNC         FIELD_PREP(GENMASK(7, 0), 0)
+#define WX_PSR_1588_MSG_V1_DELAY_REQ    FIELD_PREP(GENMASK(7, 0), 1)
+#define WX_PSR_1588_STMPL               0x151E8
+#define WX_PSR_1588_STMPH               0x151A4
+#define WX_PSR_1588_CTL                 0x15188
+#define WX_PSR_1588_CTL_ENABLED         BIT(4)
+#define WX_PSR_1588_CTL_TYPE_MASK       GENMASK(3, 1)
+#define WX_PSR_1588_CTL_TYPE_L4_V1      FIELD_PREP(GENMASK(3, 1), 1)
+#define WX_PSR_1588_CTL_TYPE_EVENT_V2   FIELD_PREP(GENMASK(3, 1), 5)
+#define WX_PSR_1588_CTL_VALID           BIT(0)
 /* mcasst/ucast overflow tbl */
 #define WX_PSR_MC_TBL(_i)            (0x15200  + ((_i) * 4))
+#define WX_PSR_MC_TBL_REG(_i)        FIELD_GET(GENMASK(11, 5), (_i))
+#define WX_PSR_MC_TBL_BIT(_i)        FIELD_GET(GENMASK(4, 0), (_i))
 #define WX_PSR_UC_TBL(_i)            (0x15400 + ((_i) * 4))
+#define WX_PSR_VM_CTL_REPLEN         BIT(30) /* replication enabled */
+#define WX_PSR_VM_CTL_POOL_MASK      GENMASK(12, 7)
 
 /* VM L2 contorl */
 #define WX_PSR_VM_L2CTL(_i)          (0x15600 + ((_i) * 4))
 #define WX_PSR_VM_L2CTL_UPE          BIT(4) /* unicast promiscuous */
 #define WX_PSR_VM_L2CTL_VACC         BIT(6) /* accept nomatched vlan */
+#define WX_PSR_VM_L2CTL_VPE          BIT(7) /* vlan promiscuous mode */
 #define WX_PSR_VM_L2CTL_AUPE         BIT(8) /* accept untagged packets */
 #define WX_PSR_VM_L2CTL_ROMPE        BIT(9) /* accept packets in MTA tbl */
 #define WX_PSR_VM_L2CTL_ROPE         BIT(10) /* accept packets in UC tbl */
@@ -226,10 +269,12 @@
 #define WX_PSR_VLAN_SWC              0x16220
 #define WX_PSR_VLAN_SWC_VM_L         0x16224
 #define WX_PSR_VLAN_SWC_VM_H         0x16228
+#define WX_PSR_VLAN_SWC_VM(_i)       (0x16224 + ((_i) * 4))
 #define WX_PSR_VLAN_SWC_IDX          0x16230         /* 64 vlan entries */
 /* VLAN pool filtering masks */
 #define WX_PSR_VLAN_SWC_VIEN         BIT(31)  /* filter is valid */
 #define WX_PSR_VLAN_SWC_ENTRIES      64
+#define WX_PSR_VLAN_SWC_VLANID_MASK  GENMASK(11, 0)
 
 /********************************* RSEC **************************************/
 /* general rsec */
@@ -240,6 +285,13 @@
 #define WX_RSC_ST                    0x17004
 #define WX_RSC_ST_RSEC_RDY           BIT(0)
 
+/*********************** Transmit DMA registers **************************/
+/* transmit global control */
+#define WX_TDM_ETYPE_AS(_i)          (0x18058 + ((_i) * 4))
+#define WX_TDM_VLAN_INS(_i)          (0x18100 + ((_i) * 4))
+/* Per VF Port VLAN insertion rules */
+#define WX_TDM_VLAN_INS_VLANA_DEFAULT BIT(30) /* Always use default VLAN*/
+
 /****************************** TDB ******************************************/
 #define WX_TDB_PB_SZ(_i)             (0x1CC00 + ((_i) * 4))
 #define WX_TXPKT_SIZE_MAX            0xA /* Max Tx Packet size */
@@ -253,6 +305,32 @@
 #define WX_TSC_ST_SECTX_RDY          BIT(0)
 #define WX_TSC_BUF_AE                0x1D00C
 #define WX_TSC_BUF_AE_THR            GENMASK(9, 0)
+/* 1588 */
+#define WX_TSC_1588_CTL              0x11F00
+#define WX_TSC_1588_CTL_ENABLED      BIT(4)
+#define WX_TSC_1588_CTL_VALID        BIT(0)
+#define WX_TSC_1588_STMPL            0x11F04
+#define WX_TSC_1588_STMPH            0x11F08
+#define WX_TSC_1588_SYSTIML          0x11F0C
+#define WX_TSC_1588_SYSTIMH          0x11F10
+#define WX_TSC_1588_INC              0x11F14
+#define WX_TSC_1588_INT_ST           0x11F20
+#define WX_TSC_1588_INT_ST_TT1       BIT(5)
+#define WX_TSC_1588_INT_EN           0x11F24
+#define WX_TSC_1588_INT_EN_TT1       BIT(5)
+#define WX_TSC_1588_AUX_CTL          0x11F28
+#define WX_TSC_1588_AUX_CTL_EN_TS0   BIT(8)
+#define WX_TSC_1588_AUX_CTL_EN_TT1   BIT(2)
+#define WX_TSC_1588_AUX_CTL_PLSG     BIT(1)
+#define WX_TSC_1588_AUX_CTL_EN_TT0   BIT(0)
+#define WX_TSC_1588_TRGT_L(i)        (0x11F2C + ((i) * 8)) /* [0,1] */
+#define WX_TSC_1588_TRGT_H(i)        (0x11F30 + ((i) * 8)) /* [0,1] */
+#define WX_TSC_1588_SDP(i)           (0x11F5C + ((i) * 4)) /* [0,3] */
+#define WX_TSC_1588_SDP_OUT_LEVEL_H  FIELD_PREP(BIT(4), 0)
+#define WX_TSC_1588_SDP_OUT_LEVEL_L  FIELD_PREP(BIT(4), 1)
+#define WX_TSC_1588_SDP_FUN_SEL_MASK GENMASK(2, 0)
+#define WX_TSC_1588_SDP_FUN_SEL_TT0  FIELD_PREP(WX_TSC_1588_SDP_FUN_SEL_MASK, 1)
+#define WX_TSC_1588_SDP_FUN_SEL_TS0  FIELD_PREP(WX_TSC_1588_SDP_FUN_SEL_MASK, 5)
 
 /************************************** MNG ********************************/
 #define WX_MNG_SWFW_SYNC             0x1E008
@@ -264,6 +342,10 @@
 #define WX_MNG_MBOX_CTL_FWRDY        BIT(2)
 #define WX_MNG_BMC2OS_CNT            0x1E090
 #define WX_MNG_OS2BMC_CNT            0x1E094
+#define WX_SW2FW_MBOX_CMD            0x1E0A0
+#define WX_SW2FW_MBOX_CMD_VLD        BIT(31)
+#define WX_SW2FW_MBOX                0x1E200
+#define WX_FW2SW_MBOX                0x1E300
 
 /************************************* ETH MAC *****************************/
 #define WX_MAC_TX_CFG                0x11000
@@ -279,6 +361,9 @@
 #define WX_MAC_WDG_TIMEOUT           0x1100C
 #define WX_MAC_RX_FLOW_CTRL          0x11090
 #define WX_MAC_RX_FLOW_CTRL_RFE      BIT(0) /* receive fc enable */
+
+#define WX_MAC_WDG_TIMEOUT_WTO_MASK  GENMASK(3, 0)
+#define WX_MAC_WDG_TIMEOUT_WTO_DELTA 2
 /* MDIO Registers */
 #define WX_MSCA                      0x11200
 #define WX_MSCA_RA(v)                FIELD_PREP(U16_MAX, v)
@@ -327,6 +412,7 @@ enum WX_MSCA_CMD_value {
 #define WX_12K_ITR                   336
 #define WX_20K_ITR                   200
 #define WX_SP_MAX_EITR               0x00000FF8U
+#define WX_AML_MAX_EITR              0x00000FFFU
 #define WX_EM_MAX_EITR               0x00007FFCU
 
 /* transmit DMA Registers */
@@ -367,9 +453,19 @@ enum WX_MSCA_CMD_value {
 /* Number of 80 microseconds we wait for PCI Express master disable */
 #define WX_PCI_MASTER_DISABLE_TIMEOUT        80000
 
+#define WX_RSS_64Q_MASK              0x3F
+#define WX_RSS_8Q_MASK               0x7
+#define WX_RSS_4Q_MASK               0x3
+#define WX_RSS_2Q_MASK               0x1
+#define WX_RSS_DISABLED_MASK         0x0
+
+#define WX_VMDQ_4Q_MASK              0x7C
+#define WX_VMDQ_2Q_MASK              0x7E
+
 /****************** Manageablility Host Interface defines ********************/
 #define WX_HI_MAX_BLOCK_BYTE_LENGTH  256 /* Num of bytes in range */
 #define WX_HI_COMMAND_TIMEOUT        1000 /* Process HI command limit */
+#define WX_HIC_HDR_INDEX_MAX         255
 
 #define FW_READ_SHADOW_RAM_CMD       0x31
 #define FW_READ_SHADOW_RAM_LEN       0x6
@@ -382,6 +478,8 @@ enum WX_MSCA_CMD_value {
 #define FW_CEM_CMD_RESERVED          0X0
 #define FW_CEM_MAX_RETRIES           3
 #define FW_CEM_RESP_STATUS_SUCCESS   0x1
+#define FW_PPS_SET_CMD               0xF6
+#define FW_PPS_SET_LEN               0x14
 
 #define WX_SW_REGION_PTR             0x1C
 
@@ -431,7 +529,7 @@ enum WX_MSCA_CMD_value {
 #define WX_REQ_TX_DESCRIPTOR_MULTIPLE   128
 
 #define WX_MAX_JUMBO_FRAME_SIZE      9432 /* max payload 9414 */
-#define VMDQ_P(p)                    p
+#define VMDQ_P(p)       ((p) + wx->ring_feature[RING_F_VMDQ].offset)
 
 /* Supported Rx Buffer Sizes */
 #define WX_RXBUFFER_256      256    /* Used for skb receive header */
@@ -460,6 +558,8 @@ enum WX_MSCA_CMD_value {
 #define WX_RXD_STAT_L4CS             BIT(7) /* L4 xsum calculated */
 #define WX_RXD_STAT_IPCS             BIT(8) /* IP xsum calculated */
 #define WX_RXD_STAT_OUTERIPCS        BIT(10) /* Cloud IP xsum calculated*/
+#define WX_RXD_STAT_IPV6EX           BIT(12) /* IPv6 Dest Header */
+#define WX_RXD_STAT_TS               BIT(14) /* IEEE1588 Time Stamp */
 
 #define WX_RXD_ERR_OUTERIPER         BIT(26) /* CRC IP Header error */
 #define WX_RXD_ERR_RXE               BIT(29) /* Any MAC Error */
@@ -535,8 +635,6 @@ enum wx_l2_ptypes {
 
 #define WX_RXD_PKTTYPE(_rxd) \
 	((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 9) & 0xFF)
-#define WX_RXD_IPV6EX(_rxd) \
-	((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 6) & 0x1)
 /*********************** Transmit Descriptor Config Masks ****************/
 #define WX_TXD_STAT_DD               BIT(0)  /* Descriptor Done */
 #define WX_TXD_DTYP_DATA             0       /* Adv Data Descriptor */
@@ -663,21 +761,30 @@ struct wx_hic_hdr {
 		u8 cmd_resv;
 		u8 ret_status;
 	} cmd_or_resp;
-	u8 checksum;
+	union {
+		u8 checksum;
+		u8 index;
+	};
 };
 
 struct wx_hic_hdr2_req {
 	u8 cmd;
 	u8 buf_lenh;
 	u8 buf_lenl;
-	u8 checksum;
+	union {
+		u8 checksum;
+		u8 index;
+	};
 };
 
 struct wx_hic_hdr2_rsp {
 	u8 cmd;
 	u8 buf_lenl;
 	u8 buf_lenh_status;     /* 7-5: high bits of buf_len, 4-0: status */
-	u8 checksum;
+	union {
+		u8 checksum;
+		u8 index;
+	};
 };
 
 union wx_hic_hdr2 {
@@ -701,12 +808,25 @@ struct wx_hic_reset {
 	u16 reset_type;
 };
 
+struct wx_hic_set_pps {
+	struct wx_hic_hdr hdr;
+	u8 lan_id;
+	u8 enable;
+	u16 pad2;
+	u64 nsec;
+	u64 cycles;
+};
+
 /* Bus parameters */
 struct wx_bus_info {
 	u8 func;
 	u16 device;
 };
 
+struct wx_mbx_info {
+	u16 size;
+};
+
 struct wx_thermal_sensor_data {
 	s16 temp;
 	s16 alarm_thresh;
@@ -716,14 +836,16 @@ struct wx_thermal_sensor_data {
 enum wx_mac_type {
 	wx_mac_unknown = 0,
 	wx_mac_sp,
-	wx_mac_em
+	wx_mac_em,
+	wx_mac_aml,
+	wx_mac_aml40,
 };
 
-enum sp_media_type {
-	sp_media_unknown = 0,
-	sp_media_fiber,
-	sp_media_copper,
-	sp_media_backplane
+enum wx_media_type {
+	wx_media_unknown = 0,
+	wx_media_fiber,
+	wx_media_copper,
+	wx_media_backplane
 };
 
 enum em_mac_type {
@@ -863,6 +985,7 @@ struct wx_tx_context_desc {
  */
 struct wx_tx_buffer {
 	union wx_tx_desc *next_to_watch;
+	unsigned long time_stamp;
 	struct sk_buff *skb;
 	unsigned int bytecount;
 	unsigned short gso_segs;
@@ -924,6 +1047,7 @@ struct wx_ring {
 	unsigned int size;              /* length in bytes */
 
 	u16 count;                      /* amount of descriptors */
+	unsigned long last_rx_timestamp;
 
 	u8 queue_index; /* needed for multiqueue queue management */
 	u8 reg_idx;                     /* holds the special value that gets
@@ -977,6 +1101,7 @@ struct wx_ring_feature {
 
 enum wx_ring_f_enum {
 	RING_F_NONE = 0,
+	RING_F_VMDQ,
 	RING_F_RSS,
 	RING_F_FDIR,
 	RING_F_ARRAY_SIZE  /* must be last in enum set */
@@ -1026,13 +1151,56 @@ struct wx_hw_stats {
 
 enum wx_state {
 	WX_STATE_RESETTING,
-	WX_STATE_NBITS,		/* must be last */
+	WX_STATE_SWFW_BUSY,
+	WX_STATE_PTP_RUNNING,
+	WX_STATE_PTP_TX_IN_PROGRESS,
+	WX_STATE_SERVICE_SCHED,
+	WX_STATE_NBITS		/* must be last */
+};
+
+struct vf_data_storage {
+	struct pci_dev *vfdev;
+	unsigned char vf_mac_addr[ETH_ALEN];
+	bool spoofchk_enabled;
+	bool link_enable;
+	bool trusted;
+	int xcast_mode;
+	unsigned int vf_api;
+	bool clear_to_send;
+	u16 pf_vlan; /* When set, guest VLAN config not allowed. */
+	u16 pf_qos;
+	bool pf_set_mac;
+
+	u16 vf_mc_hashes[WX_MAX_VF_MC_ENTRIES];
+	u16 num_vf_mc_hashes;
+	u16 vlan_count;
+	int link_state;
+};
+
+struct vf_macvlans {
+	struct list_head mvlist;
+	int vf;
+	bool free;
+	bool is_macvlan;
+	u8 vf_macvlan[ETH_ALEN];
 };
 
 enum wx_pf_flags {
+	WX_FLAG_MULTI_64_FUNC,
+	WX_FLAG_SWFW_RING,
+	WX_FLAG_VMDQ_ENABLED,
+	WX_FLAG_VLAN_PROMISC,
+	WX_FLAG_SRIOV_ENABLED,
+	WX_FLAG_IRQ_VECTOR_SHARED,
 	WX_FLAG_FDIR_CAPABLE,
 	WX_FLAG_FDIR_HASH,
 	WX_FLAG_FDIR_PERFECT,
+	WX_FLAG_RSC_CAPABLE,
+	WX_FLAG_RX_HWTSTAMP_ENABLED,
+	WX_FLAG_RX_HWTSTAMP_IN_REGISTER,
+	WX_FLAG_PTP_PPS_ENABLED,
+	WX_FLAG_NEED_LINK_CONFIG,
+	WX_FLAG_NEED_SFP_RESET,
 	WX_PF_FLAGS_NBITS               /* must be last */
 };
 
@@ -1046,9 +1214,10 @@ struct wx {
 	struct pci_dev *pdev;
 	struct net_device *netdev;
 	struct wx_bus_info bus;
+	struct wx_mbx_info mbx;
 	struct wx_mac_info mac;
 	enum em_mac_type mac_type;
-	enum sp_media_type media_type;
+	enum wx_media_type media_type;
 	struct wx_eeprom_info eeprom;
 	struct wx_addr_filter_info addr_ctrl;
 	struct wx_fc_info fc;
@@ -1066,8 +1235,12 @@ struct wx {
 	char eeprom_id[32];
 	char *driver_name;
 	enum wx_reset_type reset_type;
+	u8 swfw_index;
 
 	/* PHY stuff */
+	bool notify_down;
+	int adv_speed;
+	int adv_duplex;
 	unsigned int link;
 	int speed;
 	int duplex;
@@ -1099,6 +1272,8 @@ struct wx {
 	struct wx_ring *tx_ring[64] ____cacheline_aligned_in_smp;
 	struct wx_ring *rx_ring[64];
 	struct wx_q_vector *q_vector[64];
+	int num_rx_pools;
+	int num_rx_queues_per_pool;
 
 	unsigned int queues_per_pool;
 	struct msix_entry *msix_q_entries;
@@ -1120,6 +1295,7 @@ struct wx {
 	u32 wol;
 
 	u16 bd_number;
+	bool default_up;
 
 	struct wx_hw_stats stats;
 	u64 tx_busy;
@@ -1128,15 +1304,47 @@ struct wx {
 	u64 hw_csum_rx_good;
 	u64 hw_csum_rx_error;
 	u64 alloc_rx_buff_failed;
+	unsigned int num_vfs;
+	struct vf_data_storage *vfinfo;
+	struct vf_macvlans vf_mvs;
+	struct vf_macvlans *mv_list;
+	unsigned long fwd_bitmask;
 
 	u32 atr_sample_rate;
 	void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype);
 	void (*configure_fdir)(struct wx *wx);
+	int (*setup_tc)(struct net_device *netdev, u8 tc);
 	void (*do_reset)(struct net_device *netdev);
+	int (*ptp_setup_sdp)(struct wx *wx);
+
+	bool pps_enabled;
+	u64 pps_width;
+	u64 pps_edge_start;
+	u64 pps_edge_end;
+	u64 sec_to_cc;
+	u32 base_incval;
+	u32 tx_hwtstamp_pkts;
+	u32 tx_hwtstamp_timeouts;
+	u32 tx_hwtstamp_skipped;
+	u32 tx_hwtstamp_errors;
+	u32 rx_hwtstamp_cleared;
+	unsigned long last_overflow_check;
+	unsigned long last_rx_ptp_check;
+	unsigned long ptp_tx_start;
+	seqlock_t hw_tc_lock; /* seqlock for ptp */
+	struct cyclecounter hw_cc;
+	struct timecounter hw_tc;
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info ptp_caps;
+	struct kernel_hwtstamp_config tstamp_config;
+	struct sk_buff *ptp_tx_skb;
+
+	struct timer_list service_timer;
+	struct work_struct service_task;
 };
 
 #define WX_INTR_ALL (~0ULL)
-#define WX_INTR_Q(i) BIT((i) + 1)
+#define WX_INTR_Q(i) BIT((i))
 
 /* register operations */
 #define wr32(a, reg, value)	writel((value), ((a)->hw_addr + (reg)))
@@ -1177,6 +1385,24 @@ rd64(struct wx *wx, u32 reg)
 	return (lsb | msb << 32);
 }
 
+static inline u32
+rd32ptp(struct wx *wx, u32 reg)
+{
+	if (wx->mac.type == wx_mac_em)
+		return rd32(wx, reg);
+
+	return rd32(wx, reg + 0xB500);
+}
+
+static inline void
+wr32ptp(struct wx *wx, u32 reg, u32 value)
+{
+	if (wx->mac.type == wx_mac_em)
+		return wr32(wx, reg, value);
+
+	return wr32(wx, reg + 0xB500, value);
+}
+
 /* On some domestic CPU platforms, sometimes IO is not synchronized with
  * flushing memory, here use readl() to flush PCI read and write.
  */
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
index e868f7ef4920..7e2d9ec38a30 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
@@ -138,6 +138,8 @@ static const struct ethtool_ops ngbe_ethtool_ops = {
 	.set_channels		= ngbe_set_channels,
 	.get_msglevel		= wx_get_msglevel,
 	.set_msglevel		= wx_set_msglevel,
+	.get_ts_info		= wx_get_ts_info,
+	.get_ts_stats		= wx_get_ptp_stats,
 };
 
 void ngbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index 53aeae2f884b..e0fc897b0a58 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -14,6 +14,9 @@
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_hw.h"
 #include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
+#include "../libwx/wx_mbx.h"
+#include "../libwx/wx_sriov.h"
 #include "ngbe_type.h"
 #include "ngbe_mdio.h"
 #include "ngbe_hw.h"
@@ -128,6 +131,10 @@ static int ngbe_sw_init(struct wx *wx)
 	wx->tx_work_limit = NGBE_DEFAULT_TX_WORK;
 	wx->rx_work_limit = NGBE_DEFAULT_RX_WORK;
 
+	wx->mbx.size = WX_VXMAILBOX_SIZE;
+	wx->setup_tc = ngbe_setup_tc;
+	set_bit(0, &wx->fwd_bitmask);
+
 	return 0;
 }
 
@@ -154,7 +161,7 @@ static void ngbe_irq_enable(struct wx *wx, bool queues)
 	if (queues)
 		wx_intr_enable(wx, NGBE_INTR_ALL);
 	else
-		wx_intr_enable(wx, NGBE_INTR_MISC);
+		wx_intr_enable(wx, NGBE_INTR_MISC(wx));
 }
 
 /**
@@ -167,7 +174,7 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data)
 	struct wx_q_vector *q_vector;
 	struct wx *wx  = data;
 	struct pci_dev *pdev;
-	u32 eicr;
+	u32 eicr, eicr_misc;
 
 	q_vector = wx->q_vector[0];
 	pdev = wx->pdev;
@@ -185,6 +192,10 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data)
 	if (!(pdev->msi_enabled))
 		wr32(wx, WX_PX_INTA, 1);
 
+	eicr_misc = wx_misc_isb(wx, WX_ISB_MISC);
+	if (unlikely(eicr_misc & NGBE_PX_MISC_IC_TIMESYNC))
+		wx_ptp_check_pps_event(wx);
+
 	wx->isb_mem[WX_ISB_MISC] = 0;
 	/* would disable interrupts here but it is auto disabled */
 	napi_schedule_irqoff(&q_vector->napi);
@@ -195,9 +206,13 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data)
+static irqreturn_t __ngbe_msix_misc(struct wx *wx, u32 eicr)
 {
-	struct wx *wx = data;
+	if (eicr & NGBE_PX_MISC_IC_VF_MBOX)
+		wx_msg_task(wx);
+
+	if (unlikely(eicr & NGBE_PX_MISC_IC_TIMESYNC))
+		wx_ptp_check_pps_event(wx);
 
 	/* re-enable the original interrupt state, no lsc, no queues */
 	if (netif_running(wx->netdev))
@@ -206,6 +221,35 @@ static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t ngbe_msix_misc(int __always_unused irq, void *data)
+{
+	struct wx *wx = data;
+	u32 eicr;
+
+	eicr = wx_misc_isb(wx, WX_ISB_MISC);
+
+	return __ngbe_msix_misc(wx, eicr);
+}
+
+static irqreturn_t ngbe_misc_and_queue(int __always_unused irq, void *data)
+{
+	struct wx_q_vector *q_vector;
+	struct wx *wx = data;
+	u32 eicr;
+
+	eicr = wx_misc_isb(wx, WX_ISB_MISC);
+	if (!eicr) {
+		/* queue */
+		q_vector = wx->q_vector[0];
+		napi_schedule_irqoff(&q_vector->napi);
+		if (netif_running(wx->netdev))
+			ngbe_irq_enable(wx, true);
+		return IRQ_HANDLED;
+	}
+
+	return __ngbe_msix_misc(wx, eicr);
+}
+
 /**
  * ngbe_request_msix_irqs - Initialize MSI-X interrupts
  * @wx: board private structure
@@ -238,8 +282,16 @@ static int ngbe_request_msix_irqs(struct wx *wx)
 		}
 	}
 
-	err = request_irq(wx->msix_entry->vector,
-			  ngbe_msix_other, 0, netdev->name, wx);
+	/* Due to hardware design, when num_vfs < 7, pf can use 0 for misc and 1
+	 * for queue. But when num_vfs == 7, vector[1] is assigned to vf6.
+	 * Misc and queue should reuse interrupt vector[0].
+	 */
+	if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags))
+		err = request_irq(wx->msix_entry->vector,
+				  ngbe_misc_and_queue, 0, netdev->name, wx);
+	else
+		err = request_irq(wx->msix_entry->vector,
+				  ngbe_msix_misc, 0, netdev->name, wx);
 
 	if (err) {
 		wx_err(wx, "request_irq for msix_other failed: %d\n", err);
@@ -291,6 +343,22 @@ static void ngbe_disable_device(struct wx *wx)
 	struct net_device *netdev = wx->netdev;
 	u32 i;
 
+	if (wx->num_vfs) {
+		/* Clear EITR Select mapping */
+		wr32(wx, WX_PX_ITRSEL, 0);
+
+		/* Mark all the VFs as inactive */
+		for (i = 0; i < wx->num_vfs; i++)
+			wx->vfinfo[i].clear_to_send = 0;
+		wx->notify_down = true;
+		/* ping all the active vfs to let them know we are going down */
+		wx_ping_all_vfs_with_link_status(wx, false);
+		wx->notify_down = false;
+
+		/* Disable all VFTE/VFRE TX/RX */
+		wx_disable_vf_rx_tx(wx);
+	}
+
 	/* disable all enabled rx queues */
 	for (i = 0; i < wx->num_rx_queues; i++)
 		/* this call also flushes the previous write */
@@ -313,10 +381,19 @@ static void ngbe_disable_device(struct wx *wx)
 	wx_update_stats(wx);
 }
 
+static void ngbe_reset(struct wx *wx)
+{
+	wx_flush_sw_mac_table(wx);
+	wx_mac_set_default_filter(wx, wx->mac.addr);
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset(wx);
+}
+
 void ngbe_down(struct wx *wx)
 {
 	phylink_stop(wx->phylink);
 	ngbe_disable_device(wx);
+	ngbe_reset(wx);
 	wx_clean_all_tx_rings(wx);
 	wx_clean_all_rx_rings(wx);
 }
@@ -339,6 +416,11 @@ void ngbe_up(struct wx *wx)
 		ngbe_sfp_modules_txrx_powerctl(wx, true);
 
 	phylink_start(wx->phylink);
+	/* Set PF Reset Done bit so PF/VF Mail Ops can work */
+	wr32m(wx, WX_CFG_PORT_CTL,
+	      WX_CFG_PORT_CTL_PFRSTD, WX_CFG_PORT_CTL_PFRSTD);
+	if (wx->num_vfs)
+		wx_ping_all_vfs_with_link_status(wx, false);
 }
 
 /**
@@ -379,6 +461,8 @@ static int ngbe_open(struct net_device *netdev)
 	if (err)
 		goto err_dis_phy;
 
+	wx_ptp_init(wx);
+
 	ngbe_up(wx);
 
 	return 0;
@@ -407,6 +491,7 @@ static int ngbe_close(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	wx_ptp_stop(wx);
 	ngbe_down(wx);
 	wx_free_irq(wx);
 	wx_free_isb_resources(wx);
@@ -502,11 +587,14 @@ static const struct net_device_ops ngbe_netdev_ops = {
 	.ndo_set_rx_mode        = wx_set_rx_mode,
 	.ndo_set_features       = wx_set_features,
 	.ndo_fix_features       = wx_fix_features,
+	.ndo_features_check     = wx_features_check,
 	.ndo_validate_addr      = eth_validate_addr,
 	.ndo_set_mac_address    = wx_set_mac,
 	.ndo_get_stats64        = wx_get_stats64,
 	.ndo_vlan_rx_add_vid    = wx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = wx_vlan_rx_kill_vid,
+	.ndo_hwtstamp_set       = wx_hwtstamp_set,
+	.ndo_hwtstamp_get       = wx_hwtstamp_get,
 };
 
 /**
@@ -578,6 +666,10 @@ static int ngbe_probe(struct pci_dev *pdev,
 		goto err_pci_release_regions;
 	}
 
+	/* The emerald supports up to 8 VFs per pf, but physical
+	 * function also need one pool for basic networking.
+	 */
+	pci_sriov_set_totalvfs(pdev, NGBE_MAX_VFS_DRV_LIMIT);
 	wx->driver_name = ngbe_driver_name;
 	ngbe_set_ethtool_ops(netdev);
 	netdev->netdev_ops = &ngbe_netdev_ops;
@@ -607,7 +699,7 @@ static int ngbe_probe(struct pci_dev *pdev,
 	/* setup the private structure */
 	err = ngbe_sw_init(wx);
 	if (err)
-		goto err_free_mac_table;
+		goto err_pci_release_regions;
 
 	/* check if flash load is done after hw power up */
 	err = wx_check_flash_load(wx, NGBE_SPI_ILDR_STATUS_PERST);
@@ -701,6 +793,7 @@ err_register:
 err_clear_interrupt_scheme:
 	wx_clear_interrupt_scheme(wx);
 err_free_mac_table:
+	kfree(wx->rss_key);
 	kfree(wx->mac_table);
 err_pci_release_regions:
 	pci_release_selected_regions(pdev,
@@ -725,6 +818,7 @@ static void ngbe_remove(struct pci_dev *pdev)
 	struct net_device *netdev;
 
 	netdev = wx->netdev;
+	wx_disable_sriov(wx);
 	unregister_netdev(netdev);
 	phylink_destroy(wx->phylink);
 	pci_release_selected_regions(pdev,
@@ -784,6 +878,7 @@ static struct pci_driver ngbe_driver = {
 	.suspend  = ngbe_suspend,
 	.resume   = ngbe_resume,
 	.shutdown = ngbe_shutdown,
+	.sriov_configure = wx_pci_sriov_configure,
 };
 
 module_pci_driver(ngbe_driver);
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index a5e9b779c44d..c63bb6e6f405 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -7,7 +7,9 @@
 #include <linux/phy.h>
 
 #include "../libwx/wx_type.h"
+#include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
+#include "../libwx/wx_sriov.h"
 #include "ngbe_type.h"
 #include "ngbe_mdio.h"
 
@@ -64,6 +66,13 @@ static void ngbe_mac_config(struct phylink_config *config, unsigned int mode,
 static void ngbe_mac_link_down(struct phylink_config *config,
 			       unsigned int mode, phy_interface_t interface)
 {
+	struct wx *wx = phylink_to_wx(config);
+
+	wx->speed = SPEED_UNKNOWN;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going down */
+	wx_ping_all_vfs_with_link_status(wx, false);
 }
 
 static void ngbe_mac_link_up(struct phylink_config *config,
@@ -103,6 +112,13 @@ static void ngbe_mac_link_up(struct phylink_config *config,
 	wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
 	reg = rd32(wx, WX_MAC_WDG_TIMEOUT);
 	wr32(wx, WX_MAC_WDG_TIMEOUT, reg);
+
+	wx->speed = speed;
+	wx->last_rx_ptp_check = jiffies;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going up */
+	wx_ping_all_vfs_with_link_status(wx, true);
 }
 
 static const struct phylink_mac_ops ngbe_mac_ops = {
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
index f48ed7fc1805..3b2ca7f47e33 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
@@ -70,17 +70,24 @@
 
 /* Extended Interrupt Enable Set */
 #define NGBE_PX_MISC_IEN_DEV_RST		BIT(10)
+#define NGBE_PX_MISC_IEN_TIMESYNC		BIT(11)
 #define NGBE_PX_MISC_IEN_ETH_LK			BIT(18)
 #define NGBE_PX_MISC_IEN_INT_ERR		BIT(20)
+#define NGBE_PX_MISC_IC_VF_MBOX			BIT(23)
 #define NGBE_PX_MISC_IEN_GPIO			BIT(26)
 #define NGBE_PX_MISC_IEN_MASK ( \
 				NGBE_PX_MISC_IEN_DEV_RST | \
+				NGBE_PX_MISC_IEN_TIMESYNC | \
 				NGBE_PX_MISC_IEN_ETH_LK | \
 				NGBE_PX_MISC_IEN_INT_ERR | \
+				NGBE_PX_MISC_IC_VF_MBOX | \
 				NGBE_PX_MISC_IEN_GPIO)
 
+/* Extended Interrupt Cause Read */
+#define NGBE_PX_MISC_IC_TIMESYNC		BIT(11) /* time sync */
+
 #define NGBE_INTR_ALL				0x1FF
-#define NGBE_INTR_MISC				BIT(0)
+#define NGBE_INTR_MISC(A)			BIT((A)->msix_entry->entry)
 
 #define NGBE_PHY_CONFIG(reg_offset)		(0x14000 + ((reg_offset) * 4))
 #define NGBE_CFG_LAN_SPEED			0x14440
@@ -129,6 +136,7 @@
 #define NGBE_MAX_RXD				8192
 #define NGBE_MIN_RXD				128
 
+#define NGBE_MAX_VFS_DRV_LIMIT			7
 extern char ngbe_driver_name[];
 
 void ngbe_down(struct wx *wx);
diff --git a/drivers/net/ethernet/wangxun/txgbe/Makefile b/drivers/net/ethernet/wangxun/txgbe/Makefile
index f74576fe7062..c757fa95e58e 100644
--- a/drivers/net/ethernet/wangxun/txgbe/Makefile
+++ b/drivers/net/ethernet/wangxun/txgbe/Makefile
@@ -11,4 +11,5 @@ txgbe-objs := txgbe_main.o \
               txgbe_phy.o \
               txgbe_irq.o \
               txgbe_fdir.o \
-              txgbe_ethtool.o
+              txgbe_ethtool.o \
+              txgbe_aml.o
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c
new file mode 100644
index 000000000000..dc87ccad9652
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c
@@ -0,0 +1,386 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#include <linux/phylink.h>
+#include <linux/iopoll.h>
+#include <linux/pci.h>
+#include <linux/phy.h>
+
+#include "../libwx/wx_type.h"
+#include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
+#include "../libwx/wx_hw.h"
+#include "../libwx/wx_sriov.h"
+#include "txgbe_type.h"
+#include "txgbe_aml.h"
+#include "txgbe_hw.h"
+
+void txgbe_gpio_init_aml(struct wx *wx)
+{
+	u32 status;
+
+	wr32(wx, WX_GPIO_INTTYPE_LEVEL, TXGBE_GPIOBIT_2 | TXGBE_GPIOBIT_3);
+	wr32(wx, WX_GPIO_INTEN, TXGBE_GPIOBIT_2 | TXGBE_GPIOBIT_3);
+
+	status = rd32(wx, WX_GPIO_INTSTATUS);
+	for (int i = 0; i < 6; i++) {
+		if (status & BIT(i))
+			wr32(wx, WX_GPIO_EOI, BIT(i));
+	}
+}
+
+irqreturn_t txgbe_gpio_irq_handler_aml(int irq, void *data)
+{
+	struct txgbe *txgbe = data;
+	struct wx *wx = txgbe->wx;
+	u32 status;
+
+	wr32(wx, WX_GPIO_INTMASK, 0xFF);
+	status = rd32(wx, WX_GPIO_INTSTATUS);
+	if (status & TXGBE_GPIOBIT_2) {
+		set_bit(WX_FLAG_NEED_SFP_RESET, wx->flags);
+		wr32(wx, WX_GPIO_EOI, TXGBE_GPIOBIT_2);
+		wx_service_event_schedule(wx);
+	}
+	if (status & TXGBE_GPIOBIT_3) {
+		set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags);
+		wx_service_event_schedule(wx);
+		wr32(wx, WX_GPIO_EOI, TXGBE_GPIOBIT_3);
+	}
+
+	wr32(wx, WX_GPIO_INTMASK, 0);
+	return IRQ_HANDLED;
+}
+
+int txgbe_test_hostif(struct wx *wx)
+{
+	struct txgbe_hic_ephy_getlink buffer;
+
+	if (wx->mac.type != wx_mac_aml)
+		return 0;
+
+	buffer.hdr.cmd = FW_PHY_GET_LINK_CMD;
+	buffer.hdr.buf_len = sizeof(struct txgbe_hic_ephy_getlink) -
+			     sizeof(struct wx_hic_hdr);
+	buffer.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+
+	return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer),
+					WX_HI_COMMAND_TIMEOUT, true);
+}
+
+static int txgbe_identify_sfp_hostif(struct wx *wx, struct txgbe_hic_i2c_read *buffer)
+{
+	buffer->hdr.cmd = FW_READ_SFP_INFO_CMD;
+	buffer->hdr.buf_len = sizeof(struct txgbe_hic_i2c_read) -
+			      sizeof(struct wx_hic_hdr);
+	buffer->hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+
+	return wx_host_interface_command(wx, (u32 *)buffer,
+					 sizeof(struct txgbe_hic_i2c_read),
+					 WX_HI_COMMAND_TIMEOUT, true);
+}
+
+static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int duplex)
+{
+	struct txgbe_hic_ephy_setlink buffer;
+
+	buffer.hdr.cmd = FW_PHY_SET_LINK_CMD;
+	buffer.hdr.buf_len = sizeof(struct txgbe_hic_ephy_setlink) -
+			     sizeof(struct wx_hic_hdr);
+	buffer.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+
+	switch (speed) {
+	case SPEED_25000:
+		buffer.speed = TXGBE_LINK_SPEED_25GB_FULL;
+		break;
+	case SPEED_10000:
+		buffer.speed = TXGBE_LINK_SPEED_10GB_FULL;
+		break;
+	}
+
+	buffer.fec_mode = TXGBE_PHY_FEC_AUTO;
+	buffer.autoneg = autoneg;
+	buffer.duplex = duplex;
+
+	return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer),
+					 WX_HI_COMMAND_TIMEOUT, true);
+}
+
+static void txgbe_get_link_capabilities(struct wx *wx)
+{
+	struct txgbe *txgbe = wx->priv;
+
+	if (test_bit(PHY_INTERFACE_MODE_25GBASER, txgbe->sfp_interfaces))
+		wx->adv_speed = SPEED_25000;
+	else if (test_bit(PHY_INTERFACE_MODE_10GBASER, txgbe->sfp_interfaces))
+		wx->adv_speed = SPEED_10000;
+	else
+		wx->adv_speed = SPEED_UNKNOWN;
+
+	wx->adv_duplex = wx->adv_speed == SPEED_UNKNOWN ?
+			 DUPLEX_HALF : DUPLEX_FULL;
+}
+
+static void txgbe_get_phy_link(struct wx *wx, int *speed)
+{
+	u32 status;
+
+	status = rd32(wx, TXGBE_CFG_PORT_ST);
+	if (!(status & TXGBE_CFG_PORT_ST_LINK_UP))
+		*speed = SPEED_UNKNOWN;
+	else if (status & TXGBE_CFG_PORT_ST_LINK_AML_25G)
+		*speed = SPEED_25000;
+	else if (status & TXGBE_CFG_PORT_ST_LINK_AML_10G)
+		*speed = SPEED_10000;
+	else
+		*speed = SPEED_UNKNOWN;
+}
+
+int txgbe_set_phy_link(struct wx *wx)
+{
+	int speed, err;
+	u32 gpio;
+
+	/* Check RX signal */
+	gpio = rd32(wx, WX_GPIO_EXT);
+	if (gpio & TXGBE_GPIOBIT_3)
+		return -ENODEV;
+
+	txgbe_get_link_capabilities(wx);
+	if (wx->adv_speed == SPEED_UNKNOWN)
+		return -ENODEV;
+
+	txgbe_get_phy_link(wx, &speed);
+	if (speed == wx->adv_speed)
+		return 0;
+
+	err = txgbe_set_phy_link_hostif(wx, wx->adv_speed, 0, wx->adv_duplex);
+	if (err) {
+		wx_err(wx, "Failed to setup link\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int txgbe_sfp_to_linkmodes(struct wx *wx, struct txgbe_sfp_id *id)
+{
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, };
+	DECLARE_PHY_INTERFACE_MASK(interfaces);
+	struct txgbe *txgbe = wx->priv;
+
+	if (id->com_25g_code & (TXGBE_SFF_25GBASESR_CAPABLE |
+				TXGBE_SFF_25GBASEER_CAPABLE |
+				TXGBE_SFF_25GBASELR_CAPABLE)) {
+		phylink_set(modes, 25000baseSR_Full);
+		__set_bit(PHY_INTERFACE_MODE_25GBASER, interfaces);
+	}
+	if (id->com_10g_code & TXGBE_SFF_10GBASESR_CAPABLE) {
+		phylink_set(modes, 10000baseSR_Full);
+		__set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces);
+	}
+	if (id->com_10g_code & TXGBE_SFF_10GBASELR_CAPABLE) {
+		phylink_set(modes, 10000baseLR_Full);
+		__set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces);
+	}
+
+	if (phy_interface_empty(interfaces)) {
+		wx_err(wx, "unsupported SFP module\n");
+		return -EINVAL;
+	}
+
+	phylink_set(modes, Pause);
+	phylink_set(modes, Asym_Pause);
+	phylink_set(modes, FIBRE);
+	txgbe->link_port = PORT_FIBRE;
+
+	if (!linkmode_equal(txgbe->sfp_support, modes)) {
+		linkmode_copy(txgbe->sfp_support, modes);
+		phy_interface_and(txgbe->sfp_interfaces,
+				  wx->phylink_config.supported_interfaces,
+				  interfaces);
+		linkmode_copy(txgbe->advertising, modes);
+
+		set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags);
+	}
+
+	return 0;
+}
+
+int txgbe_identify_sfp(struct wx *wx)
+{
+	struct txgbe_hic_i2c_read buffer;
+	struct txgbe_sfp_id *id;
+	int err = 0;
+	u32 gpio;
+
+	gpio = rd32(wx, WX_GPIO_EXT);
+	if (gpio & TXGBE_GPIOBIT_2)
+		return -ENODEV;
+
+	err = txgbe_identify_sfp_hostif(wx, &buffer);
+	if (err) {
+		wx_err(wx, "Failed to identify SFP module\n");
+		return err;
+	}
+
+	id = &buffer.id;
+	if (id->identifier != TXGBE_SFF_IDENTIFIER_SFP) {
+		wx_err(wx, "Invalid SFP module\n");
+		return -ENODEV;
+	}
+
+	err = txgbe_sfp_to_linkmodes(wx, id);
+	if (err)
+		return err;
+
+	if (gpio & TXGBE_GPIOBIT_3)
+		set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags);
+
+	return 0;
+}
+
+void txgbe_setup_link(struct wx *wx)
+{
+	struct txgbe *txgbe = wx->priv;
+
+	phy_interface_zero(txgbe->sfp_interfaces);
+	linkmode_zero(txgbe->sfp_support);
+
+	txgbe_identify_sfp(wx);
+}
+
+static void txgbe_get_link_state(struct phylink_config *config,
+				 struct phylink_link_state *state)
+{
+	struct wx *wx = phylink_to_wx(config);
+	int speed;
+
+	txgbe_get_phy_link(wx, &speed);
+	state->link = speed != SPEED_UNKNOWN;
+	state->speed = speed;
+	state->duplex = state->link ? DUPLEX_FULL : DUPLEX_UNKNOWN;
+}
+
+static void txgbe_reconfig_mac(struct wx *wx)
+{
+	u32 wdg, fc;
+
+	wdg = rd32(wx, WX_MAC_WDG_TIMEOUT);
+	fc = rd32(wx, WX_MAC_RX_FLOW_CTRL);
+
+	wr32(wx, WX_MIS_RST, TXGBE_MIS_RST_MAC_RST(wx->bus.func));
+	/* wait for MAC reset complete */
+	usleep_range(1000, 1500);
+
+	wr32m(wx, TXGBE_MAC_MISC_CTL, TXGBE_MAC_MISC_CTL_LINK_STS_MOD,
+	      TXGBE_MAC_MISC_CTL_LINK_BOTH);
+	wx_reset_mac(wx);
+
+	wr32(wx, WX_MAC_WDG_TIMEOUT, wdg);
+	wr32(wx, WX_MAC_RX_FLOW_CTRL, fc);
+}
+
+static void txgbe_mac_link_up_aml(struct phylink_config *config,
+				  struct phy_device *phy,
+				  unsigned int mode,
+				  phy_interface_t interface,
+				  int speed, int duplex,
+				  bool tx_pause, bool rx_pause)
+{
+	struct wx *wx = phylink_to_wx(config);
+	u32 txcfg;
+
+	wx_fc_enable(wx, tx_pause, rx_pause);
+
+	txgbe_reconfig_mac(wx);
+	txgbe_enable_sec_tx_path(wx);
+
+	txcfg = rd32(wx, TXGBE_AML_MAC_TX_CFG);
+	txcfg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK;
+
+	switch (speed) {
+	case SPEED_25000:
+		txcfg |= TXGBE_AML_MAC_TX_CFG_SPEED_25G;
+		break;
+	case SPEED_10000:
+		txcfg |= TXGBE_AML_MAC_TX_CFG_SPEED_10G;
+		break;
+	default:
+		break;
+	}
+
+	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, WX_MAC_RX_CFG_RE);
+	wr32(wx, TXGBE_AML_MAC_TX_CFG, txcfg | TXGBE_AML_MAC_TX_CFG_TE);
+
+	wx->speed = speed;
+	wx->last_rx_ptp_check = jiffies;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going up */
+	wx_ping_all_vfs_with_link_status(wx, true);
+}
+
+static void txgbe_mac_link_down_aml(struct phylink_config *config,
+				    unsigned int mode,
+				    phy_interface_t interface)
+{
+	struct wx *wx = phylink_to_wx(config);
+
+	wr32m(wx, TXGBE_AML_MAC_TX_CFG, TXGBE_AML_MAC_TX_CFG_TE, 0);
+	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, 0);
+
+	wx->speed = SPEED_UNKNOWN;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going down */
+	wx_ping_all_vfs_with_link_status(wx, false);
+}
+
+static void txgbe_mac_config_aml(struct phylink_config *config, unsigned int mode,
+				 const struct phylink_link_state *state)
+{
+}
+
+static const struct phylink_mac_ops txgbe_mac_ops_aml = {
+	.mac_config = txgbe_mac_config_aml,
+	.mac_link_down = txgbe_mac_link_down_aml,
+	.mac_link_up = txgbe_mac_link_up_aml,
+};
+
+int txgbe_phylink_init_aml(struct txgbe *txgbe)
+{
+	struct phylink_link_state state;
+	struct phylink_config *config;
+	struct wx *wx = txgbe->wx;
+	phy_interface_t phy_mode;
+	struct phylink *phylink;
+	int err;
+
+	config = &wx->phylink_config;
+	config->dev = &wx->netdev->dev;
+	config->type = PHYLINK_NETDEV;
+	config->mac_capabilities = MAC_25000FD | MAC_10000FD |
+				   MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
+	config->get_fixed_state = txgbe_get_link_state;
+
+	phy_mode = PHY_INTERFACE_MODE_25GBASER;
+	__set_bit(PHY_INTERFACE_MODE_25GBASER, config->supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_10GBASER, config->supported_interfaces);
+
+	phylink = phylink_create(config, NULL, phy_mode, &txgbe_mac_ops_aml);
+	if (IS_ERR(phylink))
+		return PTR_ERR(phylink);
+
+	state.speed = SPEED_25000;
+	state.duplex = DUPLEX_FULL;
+	err = phylink_set_fixed_link(phylink, &state);
+	if (err) {
+		wx_err(wx, "Failed to set fixed link\n");
+		return err;
+	}
+
+	wx->phylink = phylink;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h
new file mode 100644
index 000000000000..25d4971ca0d9
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#ifndef _TXGBE_AML_H_
+#define _TXGBE_AML_H_
+
+void txgbe_gpio_init_aml(struct wx *wx);
+irqreturn_t txgbe_gpio_irq_handler_aml(int irq, void *data);
+int txgbe_test_hostif(struct wx *wx);
+int txgbe_set_phy_link(struct wx *wx);
+int txgbe_identify_sfp(struct wx *wx);
+void txgbe_setup_link(struct wx *wx);
+int txgbe_phylink_init_aml(struct txgbe *txgbe);
+
+#endif /* _TXGBE_AML_H_ */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
index d98314b26c19..a4753402660e 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
@@ -12,6 +12,31 @@
 #include "txgbe_fdir.h"
 #include "txgbe_ethtool.h"
 
+int txgbe_get_link_ksettings(struct net_device *netdev,
+			     struct ethtool_link_ksettings *cmd)
+{
+	struct wx *wx = netdev_priv(netdev);
+	struct txgbe *txgbe = wx->priv;
+	int err;
+
+	if (wx->mac.type == wx_mac_aml40)
+		return -EOPNOTSUPP;
+
+	err = wx_get_link_ksettings(netdev, cmd);
+	if (err)
+		return err;
+
+	if (wx->mac.type == wx_mac_sp)
+		return 0;
+
+	cmd->base.port = txgbe->link_port;
+	cmd->base.autoneg = AUTONEG_DISABLE;
+	linkmode_copy(cmd->link_modes.supported, txgbe->sfp_support);
+	linkmode_copy(cmd->link_modes.advertising, txgbe->advertising);
+
+	return 0;
+}
+
 static int txgbe_set_ringparam(struct net_device *netdev,
 			       struct ethtool_ringparam *ring,
 			       struct kernel_ethtool_ringparam *kernel_ring,
@@ -342,12 +367,19 @@ static int txgbe_add_ethtool_fdir_entry(struct txgbe *txgbe,
 		queue = TXGBE_RDB_FDIR_DROP_QUEUE;
 	} else {
 		u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+		u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
 
-		if (ring >= wx->num_rx_queues)
+		if (!vf && ring >= wx->num_rx_queues)
+			return -EINVAL;
+		else if (vf && (vf > wx->num_vfs ||
+				ring >= wx->num_rx_queues_per_pool))
 			return -EINVAL;
 
 		/* Map the ring onto the absolute queue index */
-		queue = wx->rx_ring[ring]->reg_idx;
+		if (!vf)
+			queue = wx->rx_ring[ring]->reg_idx;
+		else
+			queue = ((vf - 1) * wx->num_rx_queues_per_pool) + ring;
 	}
 
 	/* Don't allow indexes to exist outside of available space */
@@ -510,7 +542,7 @@ static const struct ethtool_ops txgbe_ethtool_ops = {
 	.get_drvinfo		= wx_get_drvinfo,
 	.nway_reset		= wx_nway_reset,
 	.get_link		= ethtool_op_get_link,
-	.get_link_ksettings	= wx_get_link_ksettings,
+	.get_link_ksettings	= txgbe_get_link_ksettings,
 	.set_link_ksettings	= wx_set_link_ksettings,
 	.get_sset_count		= wx_get_sset_count,
 	.get_strings		= wx_get_strings,
@@ -529,6 +561,8 @@ static const struct ethtool_ops txgbe_ethtool_ops = {
 	.set_rxnfc		= txgbe_set_rxnfc,
 	.get_msglevel		= wx_get_msglevel,
 	.set_msglevel		= wx_set_msglevel,
+	.get_ts_info		= wx_get_ts_info,
+	.get_ts_stats		= wx_get_ptp_stats,
 };
 
 void txgbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.h
index ace1b3571012..66dbc8ec1bb6 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.h
@@ -4,6 +4,8 @@
 #ifndef _TXGBE_ETHTOOL_H_
 #define _TXGBE_ETHTOOL_H_
 
+int txgbe_get_link_ksettings(struct net_device *netdev,
+			     struct ethtool_link_ksettings *cmd);
 void txgbe_set_ethtool_ops(struct net_device *netdev);
 
 #endif /* _TXGBE_ETHTOOL_H_ */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c
index ef50efbaec0f..a84010828551 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c
@@ -307,6 +307,7 @@ void txgbe_atr(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype)
 int txgbe_fdir_set_input_mask(struct wx *wx, union txgbe_atr_input *input_mask)
 {
 	u32 fdirm = 0, fdirtcpm = 0, flex = 0;
+	int index, offset;
 
 	/* Program the relevant mask registers. If src/dst_port or src/dst_addr
 	 * are zero, then assume a full mask for that field.  Also assume that
@@ -352,15 +353,17 @@ int txgbe_fdir_set_input_mask(struct wx *wx, union txgbe_atr_input *input_mask)
 	/* Now mask VM pool and destination IPv6 - bits 5 and 2 */
 	wr32(wx, TXGBE_RDB_FDIR_OTHER_MSK, fdirm);
 
-	flex = rd32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0));
-	flex &= ~TXGBE_RDB_FDIR_FLEX_CFG_FIELD0;
+	index = VMDQ_P(0) / 4;
+	offset = VMDQ_P(0) % 4;
+	flex = rd32(wx, TXGBE_RDB_FDIR_FLEX_CFG(index));
+	flex &= ~(TXGBE_RDB_FDIR_FLEX_CFG_FIELD0 << (offset * 8));
 	flex |= (TXGBE_RDB_FDIR_FLEX_CFG_BASE_MAC |
-		 TXGBE_RDB_FDIR_FLEX_CFG_OFST(0x6));
+		 TXGBE_RDB_FDIR_FLEX_CFG_OFST(0x6)) << (offset * 8);
 
 	switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) {
 	case 0x0000:
 		/* Mask Flex Bytes */
-		flex |= TXGBE_RDB_FDIR_FLEX_CFG_MSK;
+		flex |= TXGBE_RDB_FDIR_FLEX_CFG_MSK << (offset * 8);
 		break;
 	case 0xFFFF:
 		break;
@@ -368,7 +371,7 @@ int txgbe_fdir_set_input_mask(struct wx *wx, union txgbe_atr_input *input_mask)
 		wx_err(wx, "Error on flexible byte mask\n");
 		return -EINVAL;
 	}
-	wr32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0), flex);
+	wr32(wx, TXGBE_RDB_FDIR_FLEX_CFG(index), flex);
 
 	/* store the TCP/UDP port masks, bit reversed from port layout */
 	fdirtcpm = ntohs(input_mask->formatted.dst_port);
@@ -516,14 +519,16 @@ static void txgbe_fdir_enable(struct wx *wx, u32 fdirctrl)
 static void txgbe_init_fdir_signature(struct wx *wx)
 {
 	u32 fdirctrl = TXGBE_FDIR_PBALLOC_64K;
+	int index = VMDQ_P(0) / 4;
+	int offset = VMDQ_P(0) % 4;
 	u32 flex = 0;
 
-	flex = rd32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0));
-	flex &= ~TXGBE_RDB_FDIR_FLEX_CFG_FIELD0;
+	flex = rd32(wx, TXGBE_RDB_FDIR_FLEX_CFG(index));
+	flex &= ~(TXGBE_RDB_FDIR_FLEX_CFG_FIELD0 << (offset * 8));
 
 	flex |= (TXGBE_RDB_FDIR_FLEX_CFG_BASE_MAC |
-		 TXGBE_RDB_FDIR_FLEX_CFG_OFST(0x6));
-	wr32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0), flex);
+		 TXGBE_RDB_FDIR_FLEX_CFG_OFST(0x6)) << (offset * 8);
+	wr32(wx, TXGBE_RDB_FDIR_FLEX_CFG(index), flex);
 
 	/* Continue setup of fdirctrl register bits:
 	 *  Move the flexible bytes to use the ethertype - shift 6 words
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index cd1372da92a9..e551ae0e2069 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -99,9 +99,15 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum)
 	}
 	local_buffer = eeprom_ptrs;
 
-	for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++)
+	for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++) {
+		if (wx->mac.type == wx_mac_aml) {
+			if (i >= TXGBE_EEPROM_I2C_SRART_PTR &&
+			    i < TXGBE_EEPROM_I2C_END_PTR)
+				local_buffer[i] = 0xffff;
+		}
 		if (i != wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM)
 			*checksum += local_buffer[i];
+	}
 
 	kvfree(eeprom_ptrs);
 
@@ -182,7 +188,7 @@ int txgbe_reset_hw(struct wx *wx)
 	if (status != 0)
 		return status;
 
-	if (wx->media_type != sp_media_copper) {
+	if (wx->media_type != wx_media_copper) {
 		u32 val;
 
 		val = WX_MIS_RST_LAN_RST(wx->bus.func);
@@ -197,6 +203,12 @@ int txgbe_reset_hw(struct wx *wx)
 
 	txgbe_reset_misc(wx);
 
+	if (wx->mac.type != wx_mac_sp) {
+		wr32(wx, TXGBE_PX_PF_BME, 0x1);
+		wr32m(wx, TXGBE_RDM_RSC_CTL, TXGBE_RDM_RSC_CTL_FREE_CTL,
+		      TXGBE_RDM_RSC_CTL_FREE_CTL);
+	}
+
 	wx_clear_hw_cntrs(wx);
 
 	/* Store the permanent mac address */
@@ -206,7 +218,7 @@ int txgbe_reset_hw(struct wx *wx)
 	 * clear the multicast table.  Also reset num_rar_entries to 128,
 	 * since we modify this value when programming the SAN MAC address.
 	 */
-	wx->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES;
+	wx->mac.num_rar_entries = TXGBE_RAR_ENTRIES;
 	wx_init_rx_addrs(wx);
 
 	pci_set_master(wx->pdev);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
index 0ee73a265545..3885283681ec 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
@@ -6,10 +6,13 @@
 
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
+#include "../libwx/wx_sriov.h"
 #include "txgbe_type.h"
 #include "txgbe_phy.h"
 #include "txgbe_irq.h"
+#include "txgbe_aml.h"
 
 /**
  * txgbe_irq_enable - Enable default interrupt generation settings
@@ -18,10 +21,17 @@
  **/
 void txgbe_irq_enable(struct wx *wx, bool queues)
 {
-	wr32(wx, WX_PX_MISC_IEN, TXGBE_PX_MISC_IEN_MASK);
+	u32 misc_ien = TXGBE_PX_MISC_IEN_MASK;
+
+	if (wx->mac.type == wx_mac_aml) {
+		misc_ien |= TXGBE_PX_MISC_GPIO;
+		txgbe_gpio_init_aml(wx);
+	}
+
+	wr32(wx, WX_PX_MISC_IEN, misc_ien);
 
 	/* unmask interrupt */
-	wx_intr_enable(wx, TXGBE_INTR_MISC);
+	wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
 	if (queues)
 		wx_intr_enable(wx, TXGBE_INTR_QALL(wx));
 }
@@ -68,7 +78,6 @@ free_queue_irqs:
 		free_irq(wx->msix_q_entries[vector].vector,
 			 wx->q_vector[vector]);
 	}
-	wx_reset_interrupt_capability(wx);
 	return err;
 }
 
@@ -80,6 +89,14 @@ static int txgbe_request_link_irq(struct txgbe *txgbe)
 				    IRQF_ONESHOT, "txgbe-link-irq", txgbe);
 }
 
+static int txgbe_request_gpio_irq(struct txgbe *txgbe)
+{
+	txgbe->gpio_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_GPIO);
+	return request_threaded_irq(txgbe->gpio_irq, NULL,
+				    txgbe_gpio_irq_handler_aml,
+				    IRQF_ONESHOT, "txgbe-gpio-irq", txgbe);
+}
+
 static const struct irq_chip txgbe_irq_chip = {
 	.name = "txgbe-misc-irq",
 };
@@ -109,8 +126,15 @@ static irqreturn_t txgbe_misc_irq_handle(int irq, void *data)
 	struct wx *wx = txgbe->wx;
 	u32 eicr;
 
-	if (wx->pdev->msix_enabled)
+	if (wx->pdev->msix_enabled) {
+		eicr = wx_misc_isb(wx, WX_ISB_MISC);
+		txgbe->eicr = eicr;
+		if (eicr & TXGBE_PX_MISC_IC_VF_MBOX) {
+			wx_msg_task(txgbe->wx);
+			wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
+		}
 		return IRQ_WAKE_THREAD;
+	}
 
 	eicr = wx_misc_isb(wx, WX_ISB_VEC0);
 	if (!eicr) {
@@ -129,6 +153,8 @@ static irqreturn_t txgbe_misc_irq_handle(int irq, void *data)
 	q_vector = wx->q_vector[0];
 	napi_schedule_irqoff(&q_vector->napi);
 
+	txgbe->eicr = wx_misc_isb(wx, WX_ISB_MISC);
+
 	return IRQ_WAKE_THREAD;
 }
 
@@ -140,15 +166,24 @@ static irqreturn_t txgbe_misc_irq_thread_fn(int irq, void *data)
 	unsigned int sub_irq;
 	u32 eicr;
 
-	eicr = wx_misc_isb(wx, WX_ISB_MISC);
+	eicr = txgbe->eicr;
 	if (eicr & (TXGBE_PX_MISC_ETH_LK | TXGBE_PX_MISC_ETH_LKDN |
 		    TXGBE_PX_MISC_ETH_AN)) {
 		sub_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_LINK);
 		handle_nested_irq(sub_irq);
 		nhandled++;
 	}
+	if (eicr & TXGBE_PX_MISC_GPIO) {
+		sub_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_GPIO);
+		handle_nested_irq(sub_irq);
+		nhandled++;
+	}
+	if (unlikely(eicr & TXGBE_PX_MISC_IC_TIMESYNC)) {
+		wx_ptp_check_pps_event(wx);
+		nhandled++;
+	}
 
-	wx_intr_enable(wx, TXGBE_INTR_MISC);
+	wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
 	return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
 }
 
@@ -166,9 +201,16 @@ static void txgbe_del_irq_domain(struct txgbe *txgbe)
 
 void txgbe_free_misc_irq(struct txgbe *txgbe)
 {
+	if (txgbe->wx->mac.type == wx_mac_aml40)
+		return;
+
+	if (txgbe->wx->mac.type == wx_mac_aml)
+		free_irq(txgbe->gpio_irq, txgbe);
+
 	free_irq(txgbe->link_irq, txgbe);
 	free_irq(txgbe->misc.irq, txgbe);
 	txgbe_del_irq_domain(txgbe);
+	txgbe->wx->misc_irq_domain = false;
 }
 
 int txgbe_setup_misc_irq(struct txgbe *txgbe)
@@ -177,9 +219,12 @@ int txgbe_setup_misc_irq(struct txgbe *txgbe)
 	struct wx *wx = txgbe->wx;
 	int hwirq, err;
 
-	txgbe->misc.nirqs = 1;
-	txgbe->misc.domain = irq_domain_add_simple(NULL, txgbe->misc.nirqs, 0,
-						   &txgbe_misc_irq_domain_ops, txgbe);
+	if (wx->mac.type == wx_mac_aml40)
+		goto skip_sp_irq;
+
+	txgbe->misc.nirqs = TXGBE_IRQ_MAX;
+	txgbe->misc.domain = irq_domain_create_simple(NULL, txgbe->misc.nirqs, 0,
+						      &txgbe_misc_irq_domain_ops, txgbe);
 	if (!txgbe->misc.domain)
 		return -ENOMEM;
 
@@ -206,10 +251,20 @@ int txgbe_setup_misc_irq(struct txgbe *txgbe)
 	if (err)
 		goto free_msic_irq;
 
+	if (wx->mac.type == wx_mac_sp)
+		goto skip_sp_irq;
+
+	err = txgbe_request_gpio_irq(txgbe);
+	if (err)
+		goto free_link_irq;
+
+skip_sp_irq:
 	wx->misc_irq_domain = true;
 
 	return 0;
 
+free_link_irq:
+	free_irq(txgbe->link_irq, txgbe);
 free_msic_irq:
 	free_irq(txgbe->misc.irq, txgbe);
 del_misc_irq:
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index f77450268036..a5867f3c93fc 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -8,15 +8,20 @@
 #include <linux/string.h>
 #include <linux/etherdevice.h>
 #include <linux/phylink.h>
+#include <net/udp_tunnel.h>
 #include <net/ip.h>
 #include <linux/if_vlan.h>
 
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
+#include "../libwx/wx_mbx.h"
+#include "../libwx/wx_sriov.h"
 #include "txgbe_type.h"
 #include "txgbe_hw.h"
 #include "txgbe_phy.h"
+#include "txgbe_aml.h"
 #include "txgbe_irq.h"
 #include "txgbe_fdir.h"
 #include "txgbe_ethtool.h"
@@ -34,6 +39,12 @@ char txgbe_driver_name[] = "txgbe";
 static const struct pci_device_id txgbe_pci_tbl[] = {
 	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_SP1000), 0},
 	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_WX1820), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5010), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5110), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5025), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5125), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5040), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5140), 0},
 	/* required last entry */
 	{ .device = 0 }
 };
@@ -78,9 +89,62 @@ static int txgbe_enumerate_functions(struct wx *wx)
 	return physfns;
 }
 
+static void txgbe_sfp_detection_subtask(struct wx *wx)
+{
+	int err;
+
+	if (!test_bit(WX_FLAG_NEED_SFP_RESET, wx->flags))
+		return;
+
+	/* wait for SFP module ready */
+	msleep(200);
+
+	err = txgbe_identify_sfp(wx);
+	if (err)
+		return;
+
+	clear_bit(WX_FLAG_NEED_SFP_RESET, wx->flags);
+}
+
+static void txgbe_link_config_subtask(struct wx *wx)
+{
+	int err;
+
+	if (!test_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags))
+		return;
+
+	err = txgbe_set_phy_link(wx);
+	if (err)
+		return;
+
+	clear_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags);
+}
+
+/**
+ * txgbe_service_task - manages and runs subtasks
+ * @work: pointer to work_struct containing our data
+ **/
+static void txgbe_service_task(struct work_struct *work)
+{
+	struct wx *wx = container_of(work, struct wx, service_task);
+
+	txgbe_sfp_detection_subtask(wx);
+	txgbe_link_config_subtask(wx);
+
+	wx_service_event_complete(wx);
+}
+
+static void txgbe_init_service(struct wx *wx)
+{
+	timer_setup(&wx->service_timer, wx_service_timer, 0);
+	INIT_WORK(&wx->service_task, txgbe_service_task);
+	clear_bit(WX_STATE_SERVICE_SCHED, wx->state);
+}
+
 static void txgbe_up_complete(struct wx *wx)
 {
 	struct net_device *netdev = wx->netdev;
+	u32 reg;
 
 	wx_control_hw(wx, true);
 	wx_configure_vectors(wx);
@@ -89,7 +153,27 @@ static void txgbe_up_complete(struct wx *wx)
 	smp_mb__before_atomic();
 	wx_napi_enable_all(wx);
 
-	phylink_start(wx->phylink);
+	switch (wx->mac.type) {
+	case wx_mac_aml40:
+		reg = rd32(wx, TXGBE_AML_MAC_TX_CFG);
+		reg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK;
+		reg |= TXGBE_AML_MAC_TX_CFG_SPEED_40G;
+		wr32(wx, WX_MAC_TX_CFG, reg);
+		txgbe_enable_sec_tx_path(wx);
+		netif_carrier_on(wx->netdev);
+		break;
+	case wx_mac_aml:
+		/* Enable TX laser */
+		wr32m(wx, WX_GPIO_DR, TXGBE_GPIOBIT_1, 0);
+		txgbe_setup_link(wx);
+		phylink_start(wx->phylink);
+		break;
+	case wx_mac_sp:
+		phylink_start(wx->phylink);
+		break;
+	default:
+		break;
+	}
 
 	/* clear any pending interrupts, may auto mask */
 	rd32(wx, WX_PX_IC(0));
@@ -99,6 +183,13 @@ static void txgbe_up_complete(struct wx *wx)
 
 	/* enable transmits */
 	netif_tx_start_all_queues(netdev);
+	mod_timer(&wx->service_timer, jiffies);
+
+	/* Set PF Reset Done bit so PF/VF Mail Ops can work */
+	wr32m(wx, WX_CFG_PORT_CTL, WX_CFG_PORT_CTL_PFRSTD,
+	      WX_CFG_PORT_CTL_PFRSTD);
+	/* update setting rx tx for all active vfs */
+	wx_set_all_vfs(wx);
 }
 
 static void txgbe_reset(struct wx *wx)
@@ -116,6 +207,9 @@ static void txgbe_reset(struct wx *wx)
 	memcpy(old_addr, &wx->mac_table[0].addr, netdev->addr_len);
 	wx_flush_sw_mac_table(wx);
 	wx_mac_set_default_filter(wx, old_addr);
+
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset(wx);
 }
 
 static void txgbe_disable_device(struct wx *wx)
@@ -138,12 +232,24 @@ static void txgbe_disable_device(struct wx *wx)
 	wx_irq_disable(wx);
 	wx_napi_disable_all(wx);
 
+	timer_delete_sync(&wx->service_timer);
+
 	if (wx->bus.func < 2)
 		wr32m(wx, TXGBE_MIS_PRB_CTL, TXGBE_MIS_PRB_CTL_LAN_UP(wx->bus.func), 0);
 	else
 		wx_err(wx, "%s: invalid bus lan id %d\n",
 		       __func__, wx->bus.func);
 
+	if (wx->num_vfs) {
+		/* Clear EITR Select mapping */
+		wr32(wx, WX_PX_ITRSEL, 0);
+		/* Mark all the VFs as inactive */
+		for (i = 0; i < wx->num_vfs; i++)
+			wx->vfinfo[i].clear_to_send = 0;
+		/* update setting rx tx for all active vfs */
+		wx_set_all_vfs(wx);
+	}
+
 	if (!(((wx->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) ||
 	      ((wx->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) {
 		/* disable mac transmiter */
@@ -167,7 +273,22 @@ void txgbe_down(struct wx *wx)
 {
 	txgbe_disable_device(wx);
 	txgbe_reset(wx);
-	phylink_stop(wx->phylink);
+
+	switch (wx->mac.type) {
+	case wx_mac_aml40:
+		netif_carrier_off(wx->netdev);
+		break;
+	case wx_mac_aml:
+		phylink_stop(wx->phylink);
+		/* Disable TX laser */
+		wr32m(wx, WX_GPIO_DR, TXGBE_GPIOBIT_1, TXGBE_GPIOBIT_1);
+		break;
+	case wx_mac_sp:
+		phylink_stop(wx->phylink);
+		break;
+	default:
+		break;
+	}
 
 	wx_clean_all_tx_rings(wx);
 	wx_clean_all_rx_rings(wx);
@@ -176,6 +297,7 @@ void txgbe_down(struct wx *wx)
 void txgbe_up(struct wx *wx)
 {
 	wx_configure(wx);
+	wx_ptp_init(wx);
 	txgbe_up_complete(wx);
 }
 
@@ -192,6 +314,16 @@ static void txgbe_init_type_code(struct wx *wx)
 	case TXGBE_DEV_ID_WX1820:
 		wx->mac.type = wx_mac_sp;
 		break;
+	case TXGBE_DEV_ID_AML5010:
+	case TXGBE_DEV_ID_AML5110:
+	case TXGBE_DEV_ID_AML5025:
+	case TXGBE_DEV_ID_AML5125:
+		wx->mac.type = wx_mac_aml;
+		break;
+	case TXGBE_DEV_ID_AML5040:
+	case TXGBE_DEV_ID_AML5140:
+		wx->mac.type = wx_mac_aml40;
+		break;
 	default:
 		wx->mac.type = wx_mac_unknown;
 		break;
@@ -199,25 +331,25 @@ static void txgbe_init_type_code(struct wx *wx)
 
 	switch (device_type) {
 	case TXGBE_ID_SFP:
-		wx->media_type = sp_media_fiber;
+		wx->media_type = wx_media_fiber;
 		break;
 	case TXGBE_ID_XAUI:
 	case TXGBE_ID_SGMII:
-		wx->media_type = sp_media_copper;
+		wx->media_type = wx_media_copper;
 		break;
 	case TXGBE_ID_KR_KX_KX4:
 	case TXGBE_ID_MAC_XAUI:
 	case TXGBE_ID_MAC_SGMII:
-		wx->media_type = sp_media_backplane;
+		wx->media_type = wx_media_backplane;
 		break;
 	case TXGBE_ID_SFI_XAUI:
 		if (wx->bus.func == 0)
-			wx->media_type = sp_media_fiber;
+			wx->media_type = wx_media_fiber;
 		else
-			wx->media_type = sp_media_copper;
+			wx->media_type = wx_media_copper;
 		break;
 	default:
-		wx->media_type = sp_media_unknown;
+		wx->media_type = wx_media_unknown;
 		break;
 	}
 }
@@ -231,13 +363,13 @@ static int txgbe_sw_init(struct wx *wx)
 	u16 msix_count = 0;
 	int err;
 
-	wx->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES;
-	wx->mac.max_tx_queues = TXGBE_SP_MAX_TX_QUEUES;
-	wx->mac.max_rx_queues = TXGBE_SP_MAX_RX_QUEUES;
-	wx->mac.mcft_size = TXGBE_SP_MC_TBL_SIZE;
-	wx->mac.vft_size = TXGBE_SP_VFT_TBL_SIZE;
-	wx->mac.rx_pb_size = TXGBE_SP_RX_PB_SIZE;
-	wx->mac.tx_pb_size = TXGBE_SP_TDB_PB_SZ;
+	wx->mac.num_rar_entries = TXGBE_RAR_ENTRIES;
+	wx->mac.max_tx_queues = TXGBE_MAX_TXQ;
+	wx->mac.max_rx_queues = TXGBE_MAX_RXQ;
+	wx->mac.mcft_size = TXGBE_MC_TBL_SIZE;
+	wx->mac.vft_size = TXGBE_VFT_TBL_SIZE;
+	wx->mac.rx_pb_size = TXGBE_RX_PB_SIZE;
+	wx->mac.tx_pb_size = TXGBE_TDB_PB_SZ;
 
 	/* PCI config space info */
 	err = wx_sw_init(wx);
@@ -265,6 +397,9 @@ static int txgbe_sw_init(struct wx *wx)
 	wx->atr = txgbe_atr;
 	wx->configure_fdir = txgbe_configure_fdir;
 
+	set_bit(WX_FLAG_RSC_CAPABLE, wx->flags);
+	set_bit(WX_FLAG_MULTI_64_FUNC, wx->flags);
+
 	/* enable itr by default in dynamic mode */
 	wx->rx_itr_setting = 1;
 	wx->tx_itr_setting = 1;
@@ -272,12 +407,27 @@ static int txgbe_sw_init(struct wx *wx)
 	/* set default ring sizes */
 	wx->tx_ring_count = TXGBE_DEFAULT_TXD;
 	wx->rx_ring_count = TXGBE_DEFAULT_RXD;
+	wx->mbx.size = WX_VXMAILBOX_SIZE;
 
 	/* set default work limits */
 	wx->tx_work_limit = TXGBE_DEFAULT_TX_WORK;
 	wx->rx_work_limit = TXGBE_DEFAULT_RX_WORK;
 
+	wx->setup_tc = txgbe_setup_tc;
 	wx->do_reset = txgbe_do_reset;
+	set_bit(0, &wx->fwd_bitmask);
+
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+		break;
+	case wx_mac_aml:
+	case wx_mac_aml40:
+		set_bit(WX_FLAG_SWFW_RING, wx->flags);
+		wx->swfw_index = 0;
+		break;
+	default:
+		break;
+	}
 
 	return 0;
 }
@@ -308,10 +458,14 @@ static int txgbe_open(struct net_device *netdev)
 
 	wx_configure(wx);
 
-	err = txgbe_request_queue_irqs(wx);
+	err = txgbe_setup_misc_irq(wx->priv);
 	if (err)
 		goto err_free_resources;
 
+	err = txgbe_request_queue_irqs(wx);
+	if (err)
+		goto err_free_misc_irq;
+
 	/* Notify the stack of the actual queue counts. */
 	err = netif_set_real_num_tx_queues(netdev, wx->num_tx_queues);
 	if (err)
@@ -321,12 +475,17 @@ static int txgbe_open(struct net_device *netdev)
 	if (err)
 		goto err_free_irq;
 
+	wx_ptp_init(wx);
+
 	txgbe_up_complete(wx);
 
 	return 0;
 
 err_free_irq:
 	wx_free_irq(wx);
+err_free_misc_irq:
+	txgbe_free_misc_irq(wx->priv);
+	wx_reset_interrupt_capability(wx);
 err_free_resources:
 	wx_free_resources(wx);
 err_reset:
@@ -344,6 +503,7 @@ err_reset:
  */
 static void txgbe_close_suspend(struct wx *wx)
 {
+	wx_ptp_suspend(wx);
 	txgbe_disable_device(wx);
 	wx_free_resources(wx);
 }
@@ -363,8 +523,10 @@ static int txgbe_close(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	wx_ptp_stop(wx);
 	txgbe_down(wx);
 	wx_free_irq(wx);
+	txgbe_free_misc_irq(wx->priv);
 	wx_free_resources(wx);
 	txgbe_fdir_filter_exit(wx);
 	wx_control_hw(wx, false);
@@ -410,7 +572,6 @@ static void txgbe_shutdown(struct pci_dev *pdev)
 int txgbe_setup_tc(struct net_device *dev, u8 tc)
 {
 	struct wx *wx = netdev_priv(dev);
-	struct txgbe *txgbe = wx->priv;
 
 	/* Hardware has to reinitialize queues and interrupts to
 	 * match packet buffer alignment. Unfortunately, the
@@ -421,7 +582,6 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc)
 	else
 		txgbe_reset(wx);
 
-	txgbe_free_misc_irq(txgbe);
 	wx_clear_interrupt_scheme(wx);
 
 	if (tc)
@@ -430,7 +590,6 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc)
 		netdev_reset_tc(dev);
 
 	wx_init_interrupt_scheme(wx);
-	txgbe_setup_misc_irq(txgbe);
 
 	if (netif_running(dev))
 		txgbe_open(dev);
@@ -466,6 +625,39 @@ void txgbe_do_reset(struct net_device *netdev)
 		txgbe_reset(wx);
 }
 
+static int txgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table)
+{
+	struct wx *wx = netdev_priv(dev);
+	struct udp_tunnel_info ti;
+
+	udp_tunnel_nic_get_port(dev, table, 0, &ti);
+	switch (ti.type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		wr32(wx, TXGBE_CFG_VXLAN, ntohs(ti.port));
+		break;
+	case UDP_TUNNEL_TYPE_VXLAN_GPE:
+		wr32(wx, TXGBE_CFG_VXLAN_GPE, ntohs(ti.port));
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		wr32(wx, TXGBE_CFG_GENEVE, ntohs(ti.port));
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const struct udp_tunnel_nic_info txgbe_udp_tunnels = {
+	.sync_table	= txgbe_udp_tunnel_sync,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.tables		= {
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN_GPE, },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
+	},
+};
+
 static const struct net_device_ops txgbe_netdev_ops = {
 	.ndo_open               = txgbe_open,
 	.ndo_stop               = txgbe_close,
@@ -474,11 +666,14 @@ static const struct net_device_ops txgbe_netdev_ops = {
 	.ndo_set_rx_mode        = wx_set_rx_mode,
 	.ndo_set_features       = wx_set_features,
 	.ndo_fix_features       = wx_fix_features,
+	.ndo_features_check     = wx_features_check,
 	.ndo_validate_addr      = eth_validate_addr,
 	.ndo_set_mac_address    = wx_set_mac,
 	.ndo_get_stats64        = wx_get_stats64,
 	.ndo_vlan_rx_add_vid    = wx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = wx_vlan_rx_kill_vid,
+	.ndo_hwtstamp_set       = wx_hwtstamp_set,
+	.ndo_hwtstamp_get       = wx_hwtstamp_get,
 };
 
 /**
@@ -552,14 +747,19 @@ static int txgbe_probe(struct pci_dev *pdev,
 		goto err_pci_release_regions;
 	}
 
+	/* The sapphire supports up to 63 VFs per pf, but physical
+	 * function also need one pool for basic networking.
+	 */
+	pci_sriov_set_totalvfs(pdev, TXGBE_MAX_VFS_DRV_LIMIT);
 	wx->driver_name = txgbe_driver_name;
 	txgbe_set_ethtool_ops(netdev);
 	netdev->netdev_ops = &txgbe_netdev_ops;
+	netdev->udp_tunnel_nic_info = &txgbe_udp_tunnels;
 
 	/* setup the private structure */
 	err = txgbe_sw_init(wx);
 	if (err)
-		goto err_free_mac_table;
+		goto err_pci_release_regions;
 
 	/* check if flash load is done after hw power up */
 	err = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_PERST);
@@ -600,6 +800,7 @@ static int txgbe_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_HIGHDMA;
 	netdev->hw_features |= NETIF_F_GRO;
 	netdev->features |= NETIF_F_GRO;
+	netdev->features |= NETIF_F_RX_UDP_TUNNEL_PORT;
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
@@ -621,9 +822,11 @@ static int txgbe_probe(struct pci_dev *pdev,
 	eth_hw_addr_set(netdev, wx->mac.perm_addr);
 	wx_mac_set_default_filter(wx, wx->mac.perm_addr);
 
+	txgbe_init_service(wx);
+
 	err = wx_init_interrupt_scheme(wx);
 	if (err)
-		goto err_free_mac_table;
+		goto err_cancel_service;
 
 	/* Save off EEPROM version number and Option Rom version which
 	 * together make a unique identify for the eeprom
@@ -666,6 +869,13 @@ static int txgbe_probe(struct pci_dev *pdev,
 	if (etrack_id < 0x20010)
 		dev_warn(&pdev->dev, "Please upgrade the firmware to 0x20010 or above.\n");
 
+	err = txgbe_test_hostif(wx);
+	if (err != 0) {
+		dev_err(&pdev->dev, "Mismatched Firmware version\n");
+		err = -EIO;
+		goto err_release_hw;
+	}
+
 	txgbe = devm_kzalloc(&pdev->dev, sizeof(*txgbe), GFP_KERNEL);
 	if (!txgbe) {
 		err = -ENOMEM;
@@ -677,13 +887,9 @@ static int txgbe_probe(struct pci_dev *pdev,
 
 	txgbe_init_fdir(txgbe);
 
-	err = txgbe_setup_misc_irq(txgbe);
-	if (err)
-		goto err_release_hw;
-
 	err = txgbe_init_phy(txgbe);
 	if (err)
-		goto err_free_misc_irq;
+		goto err_release_hw;
 
 	err = register_netdev(netdev);
 	if (err)
@@ -711,12 +917,14 @@ static int txgbe_probe(struct pci_dev *pdev,
 
 err_remove_phy:
 	txgbe_remove_phy(txgbe);
-err_free_misc_irq:
-	txgbe_free_misc_irq(txgbe);
 err_release_hw:
 	wx_clear_interrupt_scheme(wx);
 	wx_control_hw(wx, false);
+err_cancel_service:
+	timer_delete_sync(&wx->service_timer);
+	cancel_work_sync(&wx->service_task);
 err_free_mac_table:
+	kfree(wx->rss_key);
 	kfree(wx->mac_table);
 err_pci_release_regions:
 	pci_release_selected_regions(pdev,
@@ -741,11 +949,13 @@ static void txgbe_remove(struct pci_dev *pdev)
 	struct txgbe *txgbe = wx->priv;
 	struct net_device *netdev;
 
+	cancel_work_sync(&wx->service_task);
+
 	netdev = wx->netdev;
+	wx_disable_sriov(wx);
 	unregister_netdev(netdev);
 
 	txgbe_remove_phy(txgbe);
-	txgbe_free_misc_irq(txgbe);
 	wx_free_isb_resources(wx);
 
 	pci_release_selected_regions(pdev,
@@ -764,11 +974,12 @@ static struct pci_driver txgbe_driver = {
 	.probe    = txgbe_probe,
 	.remove   = txgbe_remove,
 	.shutdown = txgbe_shutdown,
+	.sriov_configure = wx_pci_sriov_configure,
 };
 
 module_pci_driver(txgbe_driver);
 
 MODULE_DEVICE_TABLE(pci, txgbe_pci_tbl);
 MODULE_AUTHOR("Beijing WangXun Technology Co., Ltd, <software@trustnetic.com>");
-MODULE_DESCRIPTION("WangXun(R) 10 Gigabit PCI Express Network Driver");
+MODULE_DESCRIPTION("WangXun(R) 10/25/40 Gigabit PCI Express Network Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 1ae68f94dd49..03f1b9bc604d 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -15,8 +15,12 @@
 
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
+#include "../libwx/wx_sriov.h"
+#include "../libwx/wx_mbx.h"
 #include "../libwx/wx_hw.h"
 #include "txgbe_type.h"
+#include "txgbe_aml.h"
 #include "txgbe_phy.h"
 #include "txgbe_hw.h"
 
@@ -162,7 +166,7 @@ static struct phylink_pcs *txgbe_phylink_mac_select(struct phylink_config *confi
 	struct wx *wx = phylink_to_wx(config);
 	struct txgbe *txgbe = wx->priv;
 
-	if (wx->media_type != sp_media_copper)
+	if (wx->media_type != wx_media_copper)
 		return txgbe->pcs;
 
 	return NULL;
@@ -179,6 +183,12 @@ static void txgbe_mac_link_down(struct phylink_config *config,
 	struct wx *wx = phylink_to_wx(config);
 
 	wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0);
+
+	wx->speed = SPEED_UNKNOWN;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going down */
+	wx_ping_all_vfs_with_link_status(wx, false);
 }
 
 static void txgbe_mac_link_up(struct phylink_config *config,
@@ -215,6 +225,13 @@ static void txgbe_mac_link_up(struct phylink_config *config,
 	wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
 	wdg = rd32(wx, WX_MAC_WDG_TIMEOUT);
 	wr32(wx, WX_MAC_WDG_TIMEOUT, wdg);
+
+	wx->speed = speed;
+	wx->last_rx_ptp_check = jiffies;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going up */
+	wx_ping_all_vfs_with_link_status(wx, true);
 }
 
 static int txgbe_mac_prepare(struct phylink_config *config, unsigned int mode,
@@ -262,7 +279,7 @@ static int txgbe_phylink_init(struct txgbe *txgbe)
 	config->mac_capabilities = MAC_10000FD | MAC_1000FD | MAC_100FD |
 				   MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
 
-	if (wx->media_type == sp_media_copper) {
+	if (wx->media_type == wx_media_copper) {
 		phy_mode = PHY_INTERFACE_MODE_XAUI;
 		__set_bit(PHY_INTERFACE_MODE_XAUI, config->supported_interfaces);
 	} else {
@@ -302,7 +319,10 @@ irqreturn_t txgbe_link_irq_handler(int irq, void *data)
 	status = rd32(wx, TXGBE_CFG_PORT_ST);
 	up = !!(status & TXGBE_CFG_PORT_ST_LINK_UP);
 
-	phylink_pcs_change(txgbe->pcs, up);
+	if (txgbe->pcs)
+		phylink_pcs_change(txgbe->pcs, up);
+	else
+		phylink_mac_change(wx->phylink, up);
 
 	return IRQ_HANDLED;
 }
@@ -557,8 +577,18 @@ int txgbe_init_phy(struct txgbe *txgbe)
 	struct wx *wx = txgbe->wx;
 	int ret;
 
-	if (txgbe->wx->media_type == sp_media_copper)
-		return txgbe_ext_phy_init(txgbe);
+	switch (wx->mac.type) {
+	case wx_mac_aml40:
+		return 0;
+	case wx_mac_aml:
+		return txgbe_phylink_init_aml(txgbe);
+	case wx_mac_sp:
+		if (wx->media_type == wx_media_copper)
+			return txgbe_ext_phy_init(txgbe);
+		break;
+	default:
+		break;
+	}
 
 	ret = txgbe_swnodes_register(txgbe);
 	if (ret) {
@@ -621,10 +651,21 @@ err_unregister_swnode:
 
 void txgbe_remove_phy(struct txgbe *txgbe)
 {
-	if (txgbe->wx->media_type == sp_media_copper) {
-		phylink_disconnect_phy(txgbe->wx->phylink);
+	switch (txgbe->wx->mac.type) {
+	case wx_mac_aml40:
+		return;
+	case wx_mac_aml:
 		phylink_destroy(txgbe->wx->phylink);
 		return;
+	case wx_mac_sp:
+		if (txgbe->wx->media_type == wx_media_copper) {
+			phylink_disconnect_phy(txgbe->wx->phylink);
+			phylink_destroy(txgbe->wx->phylink);
+			return;
+		}
+		break;
+	default:
+		break;
 	}
 
 	platform_device_unregister(txgbe->sfp_dev);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h
index 3938985355ed..a32b19d71ea2 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h
@@ -8,4 +8,4 @@ irqreturn_t txgbe_link_irq_handler(int irq, void *data);
 int txgbe_init_phy(struct txgbe *txgbe);
 void txgbe_remove_phy(struct txgbe *txgbe);
 
-#endif /* _TXGBE_NODE_H_ */
+#endif /* _TXGBE_PHY_H_ */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 629a13e96b85..41915d7dd372 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -6,10 +6,18 @@
 
 #include <linux/property.h>
 #include <linux/irq.h>
+#include <linux/phy.h>
+#include "../libwx/wx_type.h"
 
 /* Device IDs */
 #define TXGBE_DEV_ID_SP1000                     0x1001
 #define TXGBE_DEV_ID_WX1820                     0x2001
+#define TXGBE_DEV_ID_AML5010                    0x5010
+#define TXGBE_DEV_ID_AML5110                    0x5110
+#define TXGBE_DEV_ID_AML5025                    0x5025
+#define TXGBE_DEV_ID_AML5125                    0x5125
+#define TXGBE_DEV_ID_AML5040                    0x5040
+#define TXGBE_DEV_ID_AML5140                    0x5140
 
 /* Subsystem IDs */
 /* SFP */
@@ -44,6 +52,8 @@
 
 /**************** SP Registers ****************************/
 /* chip control Registers */
+#define TXGBE_MIS_RST                           0x1000C
+#define TXGBE_MIS_RST_MAC_RST(_i)               BIT(20 - (_i) * 3)
 #define TXGBE_MIS_PRB_CTL                       0x10010
 #define TXGBE_MIS_PRB_CTL_LAN_UP(_i)            BIT(1 - (_i))
 /* FMGR Registers */
@@ -56,6 +66,11 @@
 #define TXGBE_TS_CTL                            0x10300
 #define TXGBE_TS_CTL_EVAL_MD                    BIT(31)
 
+/* MAC Misc Registers */
+#define TXGBE_MAC_MISC_CTL                      0x11F00
+#define TXGBE_MAC_MISC_CTL_LINK_STS_MOD         BIT(0)
+#define TXGBE_MAC_MISC_CTL_LINK_PCS             FIELD_PREP(BIT(0), 0)
+#define TXGBE_MAC_MISC_CTL_LINK_BOTH            FIELD_PREP(BIT(0), 1)
 /* GPIO register bit */
 #define TXGBE_GPIOBIT_0                         BIT(0) /* I:tx fault */
 #define TXGBE_GPIOBIT_1                         BIT(1) /* O:tx disabled */
@@ -67,19 +82,27 @@
 /* Extended Interrupt Enable Set */
 #define TXGBE_PX_MISC_ETH_LKDN                  BIT(8)
 #define TXGBE_PX_MISC_DEV_RST                   BIT(10)
+#define TXGBE_PX_MISC_IC_TIMESYNC               BIT(11)
 #define TXGBE_PX_MISC_ETH_EVENT                 BIT(17)
 #define TXGBE_PX_MISC_ETH_LK                    BIT(18)
 #define TXGBE_PX_MISC_ETH_AN                    BIT(19)
 #define TXGBE_PX_MISC_INT_ERR                   BIT(20)
+#define TXGBE_PX_MISC_IC_VF_MBOX                BIT(23)
 #define TXGBE_PX_MISC_GPIO                      BIT(26)
 #define TXGBE_PX_MISC_IEN_MASK                            \
 	(TXGBE_PX_MISC_ETH_LKDN | TXGBE_PX_MISC_DEV_RST | \
 	 TXGBE_PX_MISC_ETH_EVENT | TXGBE_PX_MISC_ETH_LK | \
-	 TXGBE_PX_MISC_ETH_AN | TXGBE_PX_MISC_INT_ERR)
+	 TXGBE_PX_MISC_ETH_AN | TXGBE_PX_MISC_INT_ERR | \
+	 TXGBE_PX_MISC_IC_VF_MBOX | TXGBE_PX_MISC_IC_TIMESYNC)
 
 /* Port cfg registers */
 #define TXGBE_CFG_PORT_ST                       0x14404
 #define TXGBE_CFG_PORT_ST_LINK_UP               BIT(0)
+#define TXGBE_CFG_PORT_ST_LINK_AML_25G          BIT(3)
+#define TXGBE_CFG_PORT_ST_LINK_AML_10G          BIT(4)
+#define TXGBE_CFG_VXLAN                         0x14410
+#define TXGBE_CFG_VXLAN_GPE                     0x14414
+#define TXGBE_CFG_GENEVE                        0x14418
 
 /* I2C registers */
 #define TXGBE_I2C_BASE                          0x14900
@@ -137,6 +160,17 @@
 #define TXGBE_RDB_FDIR_FLEX_CFG_MSK             BIT(2)
 #define TXGBE_RDB_FDIR_FLEX_CFG_OFST(v)         FIELD_PREP(GENMASK(7, 3), v)
 
+/*************************** Amber Lite Registers ****************************/
+#define TXGBE_PX_PF_BME                         0x4B8
+#define TXGBE_AML_MAC_TX_CFG                    0x11000
+#define TXGBE_AML_MAC_TX_CFG_TE                 BIT(0)
+#define TXGBE_AML_MAC_TX_CFG_SPEED_MASK         GENMASK(30, 27)
+#define TXGBE_AML_MAC_TX_CFG_SPEED_40G          FIELD_PREP(GENMASK(30, 27), 0)
+#define TXGBE_AML_MAC_TX_CFG_SPEED_25G          FIELD_PREP(GENMASK(30, 27), 2)
+#define TXGBE_AML_MAC_TX_CFG_SPEED_10G          FIELD_PREP(GENMASK(30, 27), 8)
+#define TXGBE_RDM_RSC_CTL                       0x1200C
+#define TXGBE_RDM_RSC_CTL_FREE_CTL              BIT(7)
+
 /* Checksum and EEPROM pointers */
 #define TXGBE_EEPROM_LAST_WORD                  0x800
 #define TXGBE_EEPROM_CHECKSUM                   0x2F
@@ -144,6 +178,8 @@
 #define TXGBE_EEPROM_VERSION_L                  0x1D
 #define TXGBE_EEPROM_VERSION_H                  0x1E
 #define TXGBE_ISCSI_BOOT_CONFIG                 0x07
+#define TXGBE_EEPROM_I2C_SRART_PTR              0x580
+#define TXGBE_EEPROM_I2C_END_PTR                0x800
 
 #define TXGBE_MAX_MSIX_VECTORS          64
 #define TXGBE_MAX_FDIR_INDICES          63
@@ -152,13 +188,15 @@
 #define TXGBE_MAX_RX_QUEUES   (TXGBE_MAX_FDIR_INDICES + 1)
 #define TXGBE_MAX_TX_QUEUES   (TXGBE_MAX_FDIR_INDICES + 1)
 
-#define TXGBE_SP_MAX_TX_QUEUES  128
-#define TXGBE_SP_MAX_RX_QUEUES  128
-#define TXGBE_SP_RAR_ENTRIES    128
-#define TXGBE_SP_MC_TBL_SIZE    128
-#define TXGBE_SP_VFT_TBL_SIZE   128
-#define TXGBE_SP_RX_PB_SIZE     512
-#define TXGBE_SP_TDB_PB_SZ      (160 * 1024) /* 160KB Packet Buffer */
+#define TXGBE_MAX_TXQ        128
+#define TXGBE_MAX_RXQ        128
+#define TXGBE_RAR_ENTRIES    128
+#define TXGBE_MC_TBL_SIZE    128
+#define TXGBE_VFT_TBL_SIZE   128
+#define TXGBE_RX_PB_SIZE     512
+#define TXGBE_TDB_PB_SZ      (160 * 1024) /* 160KB Packet Buffer */
+
+#define TXGBE_MAX_VFS_DRV_LIMIT                 63
 
 #define TXGBE_DEFAULT_ATR_SAMPLE_RATE           20
 
@@ -249,7 +287,7 @@ struct txgbe_fdir_filter {
 	struct hlist_node fdir_node;
 	union txgbe_atr_input filter;
 	u16 sw_idx;
-	u16 action;
+	u64 action;
 };
 
 /* TX/RX descriptor defines */
@@ -264,8 +302,8 @@ struct txgbe_fdir_filter {
 #define TXGBE_DEFAULT_RX_WORK           128
 #endif
 
-#define TXGBE_INTR_MISC       BIT(0)
-#define TXGBE_INTR_QALL(A)    GENMASK((A)->num_q_vectors, 1)
+#define TXGBE_INTR_MISC(A)    BIT((A)->num_q_vectors)
+#define TXGBE_INTR_QALL(A)    (TXGBE_INTR_MISC(A) - 1)
 
 #define TXGBE_MAX_EITR        GENMASK(11, 3)
 
@@ -276,6 +314,72 @@ void txgbe_up(struct wx *wx);
 int txgbe_setup_tc(struct net_device *dev, u8 tc);
 void txgbe_do_reset(struct net_device *netdev);
 
+#define TXGBE_LINK_SPEED_10GB_FULL      4
+#define TXGBE_LINK_SPEED_25GB_FULL      0x10
+
+#define TXGBE_SFF_IDENTIFIER_SFP        0x3
+#define TXGBE_SFF_DA_PASSIVE_CABLE      0x4
+#define TXGBE_SFF_DA_ACTIVE_CABLE       0x8
+#define TXGBE_SFF_DA_SPEC_ACTIVE_LIMIT  0x4
+#define TXGBE_SFF_FCPI4_LIMITING        0x3
+#define TXGBE_SFF_10GBASESR_CAPABLE     0x10
+#define TXGBE_SFF_10GBASELR_CAPABLE     0x20
+#define TXGBE_SFF_25GBASESR_CAPABLE     0x2
+#define TXGBE_SFF_25GBASELR_CAPABLE     0x3
+#define TXGBE_SFF_25GBASEER_CAPABLE     0x4
+#define TXGBE_SFF_25GBASECR_91FEC       0xB
+#define TXGBE_SFF_25GBASECR_74FEC       0xC
+#define TXGBE_SFF_25GBASECR_NOFEC       0xD
+
+#define TXGBE_PHY_FEC_RS                BIT(0)
+#define TXGBE_PHY_FEC_BASER             BIT(1)
+#define TXGBE_PHY_FEC_OFF               BIT(2)
+#define TXGBE_PHY_FEC_AUTO              (TXGBE_PHY_FEC_OFF | \
+					 TXGBE_PHY_FEC_BASER |\
+					 TXGBE_PHY_FEC_RS)
+
+#define FW_PHY_GET_LINK_CMD             0xC0
+#define FW_PHY_SET_LINK_CMD             0xC1
+#define FW_READ_SFP_INFO_CMD            0xC5
+
+struct txgbe_sfp_id {
+	u8 identifier;		/* A0H 0x00 */
+	u8 com_1g_code;		/* A0H 0x06 */
+	u8 com_10g_code;	/* A0H 0x03 */
+	u8 com_25g_code;	/* A0H 0x24 */
+	u8 cable_spec;		/* A0H 0x3C */
+	u8 cable_tech;		/* A0H 0x08 */
+	u8 vendor_oui0;		/* A0H 0x25 */
+	u8 vendor_oui1;		/* A0H 0x26 */
+	u8 vendor_oui2;		/* A0H 0x27 */
+	u8 reserved[3];
+};
+
+struct txgbe_hic_i2c_read {
+	struct wx_hic_hdr hdr;
+	struct txgbe_sfp_id id;
+};
+
+struct txgbe_hic_ephy_setlink {
+	struct wx_hic_hdr hdr;
+	u8 speed;
+	u8 duplex;
+	u8 autoneg;
+	u8 fec_mode;
+	u8 resv[4];
+};
+
+struct txgbe_hic_ephy_getlink {
+	struct wx_hic_hdr hdr;
+	u8 speed;
+	u8 duplex;
+	u8 autoneg;
+	u8 flow_ctl;
+	u8 power;
+	u8 fec_mode;
+	u8 resv[6];
+};
+
 #define NODE_PROP(_NAME, _PROP)			\
 	(const struct software_node) {		\
 		.name = _NAME,			\
@@ -313,6 +417,7 @@ struct txgbe_nodes {
 
 enum txgbe_misc_irqs {
 	TXGBE_IRQ_LINK = 0,
+	TXGBE_IRQ_GPIO,
 	TXGBE_IRQ_MAX
 };
 
@@ -334,12 +439,19 @@ struct txgbe {
 	struct clk *clk;
 	struct gpio_chip *gpio;
 	unsigned int link_irq;
+	unsigned int gpio_irq;
+	u32 eicr;
 
 	/* flow director */
 	struct hlist_head fdir_filter_list;
 	union txgbe_atr_input fdir_mask;
 	int fdir_filter_count;
 	spinlock_t fdir_perfect_lock; /* spinlock for FDIR */
+
+	DECLARE_PHY_INTERFACE_MASK(sfp_interfaces);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
+	u8 link_port;
 };
 
 #endif /* _TXGBE_TYPE_H_ */
diff --git a/drivers/net/ethernet/xilinx/Kconfig b/drivers/net/ethernet/xilinx/Kconfig
index 35d96c633a33..7502214cc7d5 100644
--- a/drivers/net/ethernet/xilinx/Kconfig
+++ b/drivers/net/ethernet/xilinx/Kconfig
@@ -28,6 +28,7 @@ config XILINX_AXI_EMAC
 	depends on HAS_IOMEM
 	depends on XILINX_DMA
 	select PHYLINK
+	select DIMLIB
 	help
 	  This driver supports the 10/100/1000 Ethernet from Xilinx for the
 	  AXI bus interface used in Xilinx Virtex FPGAs and Soc's.
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index d64b8abcf018..5ff742103beb 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -9,6 +9,7 @@
 #ifndef XILINX_AXIENET_H
 #define XILINX_AXIENET_H
 
+#include <linux/dim.h>
 #include <linux/netdevice.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
@@ -112,19 +113,18 @@
 #define XAXIDMA_DELAY_MASK		0xFF000000 /* Delay timeout counter */
 #define XAXIDMA_COALESCE_MASK		0x00FF0000 /* Coalesce counter */
 
-#define XAXIDMA_DELAY_SHIFT		24
-#define XAXIDMA_COALESCE_SHIFT		16
-
 #define XAXIDMA_IRQ_IOC_MASK		0x00001000 /* Completion intr */
 #define XAXIDMA_IRQ_DELAY_MASK		0x00002000 /* Delay interrupt */
 #define XAXIDMA_IRQ_ERROR_MASK		0x00004000 /* Error interrupt */
 #define XAXIDMA_IRQ_ALL_MASK		0x00007000 /* All interrupts */
 
+/* Constant to convert delay counts to microseconds */
+#define XAXIDMA_DELAY_SCALE		(125ULL * USEC_PER_SEC)
+
 /* Default TX/RX Threshold and delay timer values for SGDMA mode */
 #define XAXIDMA_DFT_TX_THRESHOLD	24
 #define XAXIDMA_DFT_TX_USEC		50
-#define XAXIDMA_DFT_RX_THRESHOLD	1
-#define XAXIDMA_DFT_RX_USEC		50
+#define XAXIDMA_DFT_RX_USEC		16
 
 #define XAXIDMA_BD_CTRL_TXSOF_MASK	0x08000000 /* First tx packet */
 #define XAXIDMA_BD_CTRL_TXEOF_MASK	0x04000000 /* Last tx packet */
@@ -484,7 +484,12 @@ struct skbuf_dma_descriptor {
  * @regs:	Base address for the axienet_local device address space
  * @dma_regs:	Base address for the axidma device address space
  * @napi_rx:	NAPI RX control structure
+ * @rx_dim:     DIM state for the receive queue
+ * @rx_dim_enabled: Whether DIM is enabled or not
+ * @rx_irqs:    Number of interrupts
+ * @rx_cr_lock: Lock protecting @rx_dma_cr, its register, and @rx_dma_started
  * @rx_dma_cr:  Nominal content of RX DMA control register
+ * @rx_dma_started: Set when RX DMA is started
  * @rx_bd_v:	Virtual address of the RX buffer descriptor ring
  * @rx_bd_p:	Physical address(start address) of the RX buffer descr. ring
  * @rx_bd_num:	Size of RX buffer descriptor ring
@@ -494,7 +499,9 @@ struct skbuf_dma_descriptor {
  * @rx_bytes:	RX byte count for statistics
  * @rx_stat_sync: Synchronization object for RX stats
  * @napi_tx:	NAPI TX control structure
+ * @tx_cr_lock: Lock protecting @tx_dma_cr, its register, and @tx_dma_started
  * @tx_dma_cr:  Nominal content of TX DMA control register
+ * @tx_dma_started: Set when TX DMA is started
  * @tx_bd_v:	Virtual address of the TX buffer descriptor ring
  * @tx_bd_p:	Physical address(start address) of the TX buffer descr. ring
  * @tx_bd_num:	Size of TX buffer descriptor ring
@@ -529,10 +536,6 @@ struct skbuf_dma_descriptor {
  *		  supported, the maximum frame size would be 9k. Else it is
  *		  1522 bytes (assuming support for basic VLAN)
  * @rxmem:	Stores rx memory size for jumbo frame handling.
- * @coalesce_count_rx:	Store the irq coalesce on RX side.
- * @coalesce_usec_rx:	IRQ coalesce delay for RX
- * @coalesce_count_tx:	Store the irq coalesce on TX side.
- * @coalesce_usec_tx:	IRQ coalesce delay for TX
  * @use_dmaengine: flag to check dmaengine framework usage.
  * @tx_chan:	TX DMA channel.
  * @rx_chan:	RX DMA channel.
@@ -566,7 +569,12 @@ struct axienet_local {
 	void __iomem *dma_regs;
 
 	struct napi_struct napi_rx;
+	struct dim rx_dim;
+	bool rx_dim_enabled;
+	u16 rx_irqs;
+	spinlock_t rx_cr_lock;
 	u32 rx_dma_cr;
+	bool rx_dma_started;
 	struct axidma_bd *rx_bd_v;
 	dma_addr_t rx_bd_p;
 	u32 rx_bd_num;
@@ -576,7 +584,9 @@ struct axienet_local {
 	struct u64_stats_sync rx_stat_sync;
 
 	struct napi_struct napi_tx;
+	spinlock_t tx_cr_lock;
 	u32 tx_dma_cr;
+	bool tx_dma_started;
 	struct axidma_bd *tx_bd_v;
 	dma_addr_t tx_bd_p;
 	u32 tx_bd_num;
@@ -607,10 +617,6 @@ struct axienet_local {
 	u32 max_frm_size;
 	u32 rxmem;
 
-	u32 coalesce_count_rx;
-	u32 coalesce_usec_rx;
-	u32 coalesce_count_tx;
-	u32 coalesce_usec_tx;
 	u8  use_dmaengine;
 	struct dma_chan *tx_chan;
 	struct dma_chan *rx_chan;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 0f4b02fe6f85..6011d7eae0c7 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -223,26 +223,62 @@ static void axienet_dma_bd_release(struct net_device *ndev)
 			  lp->rx_bd_p);
 }
 
+static u64 axienet_dma_rate(struct axienet_local *lp)
+{
+	if (lp->axi_clk)
+		return clk_get_rate(lp->axi_clk);
+	return 125000000; /* arbitrary guess if no clock rate set */
+}
+
 /**
- * axienet_usec_to_timer - Calculate IRQ delay timer value
- * @lp:		Pointer to the axienet_local structure
- * @coalesce_usec: Microseconds to convert into timer value
+ * axienet_calc_cr() - Calculate control register value
+ * @lp: Device private data
+ * @count: Number of completions before an interrupt
+ * @usec: Microseconds after the last completion before an interrupt
+ *
+ * Calculate a control register value based on the coalescing settings. The
+ * run/stop bit is not set.
  */
-static u32 axienet_usec_to_timer(struct axienet_local *lp, u32 coalesce_usec)
+static u32 axienet_calc_cr(struct axienet_local *lp, u32 count, u32 usec)
 {
-	u32 result;
-	u64 clk_rate = 125000000; /* arbitrary guess if no clock rate set */
+	u32 cr;
 
-	if (lp->axi_clk)
-		clk_rate = clk_get_rate(lp->axi_clk);
+	cr = FIELD_PREP(XAXIDMA_COALESCE_MASK, count) | XAXIDMA_IRQ_IOC_MASK |
+	     XAXIDMA_IRQ_ERROR_MASK;
+	/* Only set interrupt delay timer if not generating an interrupt on
+	 * the first packet. Otherwise leave at 0 to disable delay interrupt.
+	 */
+	if (count > 1) {
+		u64 clk_rate = axienet_dma_rate(lp);
+		u32 timer;
+
+		/* 1 Timeout Interval = 125 * (clock period of SG clock) */
+		timer = DIV64_U64_ROUND_CLOSEST((u64)usec * clk_rate,
+						XAXIDMA_DELAY_SCALE);
 
-	/* 1 Timeout Interval = 125 * (clock period of SG clock) */
-	result = DIV64_U64_ROUND_CLOSEST((u64)coalesce_usec * clk_rate,
-					 (u64)125000000);
-	if (result > 255)
-		result = 255;
+		timer = min(timer, FIELD_MAX(XAXIDMA_DELAY_MASK));
+		cr |= FIELD_PREP(XAXIDMA_DELAY_MASK, timer) |
+		      XAXIDMA_IRQ_DELAY_MASK;
+	}
+
+	return cr;
+}
+
+/**
+ * axienet_coalesce_params() - Extract coalesce parameters from the CR
+ * @lp: Device private data
+ * @cr: The control register to parse
+ * @count: Number of packets before an interrupt
+ * @usec: Idle time (in usec) before an interrupt
+ */
+static void axienet_coalesce_params(struct axienet_local *lp, u32 cr,
+				    u32 *count, u32 *usec)
+{
+	u64 clk_rate = axienet_dma_rate(lp);
+	u64 timer = FIELD_GET(XAXIDMA_DELAY_MASK, cr);
 
-	return result;
+	*count = FIELD_GET(XAXIDMA_COALESCE_MASK, cr);
+	*usec = DIV64_U64_ROUND_CLOSEST(timer * XAXIDMA_DELAY_SCALE, clk_rate);
 }
 
 /**
@@ -251,30 +287,12 @@ static u32 axienet_usec_to_timer(struct axienet_local *lp, u32 coalesce_usec)
  */
 static void axienet_dma_start(struct axienet_local *lp)
 {
+	spin_lock_irq(&lp->rx_cr_lock);
+
 	/* Start updating the Rx channel control register */
-	lp->rx_dma_cr = (lp->coalesce_count_rx << XAXIDMA_COALESCE_SHIFT) |
-			XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_ERROR_MASK;
-	/* Only set interrupt delay timer if not generating an interrupt on
-	 * the first RX packet. Otherwise leave at 0 to disable delay interrupt.
-	 */
-	if (lp->coalesce_count_rx > 1)
-		lp->rx_dma_cr |= (axienet_usec_to_timer(lp, lp->coalesce_usec_rx)
-					<< XAXIDMA_DELAY_SHIFT) |
-				 XAXIDMA_IRQ_DELAY_MASK;
+	lp->rx_dma_cr &= ~XAXIDMA_CR_RUNSTOP_MASK;
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, lp->rx_dma_cr);
 
-	/* Start updating the Tx channel control register */
-	lp->tx_dma_cr = (lp->coalesce_count_tx << XAXIDMA_COALESCE_SHIFT) |
-			XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_ERROR_MASK;
-	/* Only set interrupt delay timer if not generating an interrupt on
-	 * the first TX packet. Otherwise leave at 0 to disable delay interrupt.
-	 */
-	if (lp->coalesce_count_tx > 1)
-		lp->tx_dma_cr |= (axienet_usec_to_timer(lp, lp->coalesce_usec_tx)
-					<< XAXIDMA_DELAY_SHIFT) |
-				 XAXIDMA_IRQ_DELAY_MASK;
-	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
-
 	/* Populate the tail pointer and bring the Rx Axi DMA engine out of
 	 * halted state. This will make the Rx side ready for reception.
 	 */
@@ -283,6 +301,14 @@ static void axienet_dma_start(struct axienet_local *lp)
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, lp->rx_dma_cr);
 	axienet_dma_out_addr(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p +
 			     (sizeof(*lp->rx_bd_v) * (lp->rx_bd_num - 1)));
+	lp->rx_dma_started = true;
+
+	spin_unlock_irq(&lp->rx_cr_lock);
+	spin_lock_irq(&lp->tx_cr_lock);
+
+	/* Start updating the Tx channel control register */
+	lp->tx_dma_cr &= ~XAXIDMA_CR_RUNSTOP_MASK;
+	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
 
 	/* Write to the RS (Run-stop) bit in the Tx channel control register.
 	 * Tx channel is now ready to run. But only after we write to the
@@ -291,6 +317,9 @@ static void axienet_dma_start(struct axienet_local *lp)
 	axienet_dma_out_addr(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p);
 	lp->tx_dma_cr |= XAXIDMA_CR_RUNSTOP_MASK;
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
+	lp->tx_dma_started = true;
+
+	spin_unlock_irq(&lp->tx_cr_lock);
 }
 
 /**
@@ -626,14 +655,22 @@ static void axienet_dma_stop(struct axienet_local *lp)
 	int count;
 	u32 cr, sr;
 
-	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
-	cr &= ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
+	spin_lock_irq(&lp->rx_cr_lock);
+
+	cr = lp->rx_dma_cr & ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+	lp->rx_dma_started = false;
+
+	spin_unlock_irq(&lp->rx_cr_lock);
 	synchronize_irq(lp->rx_irq);
 
-	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
-	cr &= ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
+	spin_lock_irq(&lp->tx_cr_lock);
+
+	cr = lp->tx_dma_cr & ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+	lp->tx_dma_started = false;
+
+	spin_unlock_irq(&lp->tx_cr_lock);
 	synchronize_irq(lp->tx_irq);
 
 	/* Give DMAs a chance to halt gracefully */
@@ -843,7 +880,7 @@ static void axienet_dma_tx_cb(void *data, const struct dmaengine_result *result)
 	dev_consume_skb_any(skbuf_dma->skb);
 	netif_txq_completed_wake(txq, 1, len,
 				 CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX),
-				 2 * MAX_SKB_FRAGS);
+				 2);
 }
 
 /**
@@ -877,7 +914,7 @@ axienet_start_xmit_dmaengine(struct sk_buff *skb, struct net_device *ndev)
 
 	dma_dev = lp->tx_chan->device;
 	sg_len = skb_shinfo(skb)->nr_frags + 1;
-	if (CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX) <= sg_len) {
+	if (CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX) <= 1) {
 		netif_stop_queue(ndev);
 		if (net_ratelimit())
 			netdev_warn(ndev, "TX ring unexpectedly full\n");
@@ -927,7 +964,7 @@ axienet_start_xmit_dmaengine(struct sk_buff *skb, struct net_device *ndev)
 	txq = skb_get_tx_queue(lp->ndev, skb);
 	netdev_tx_sent_queue(txq, skb->len);
 	netif_txq_maybe_stop(txq, CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX),
-			     MAX_SKB_FRAGS + 1, 2 * MAX_SKB_FRAGS);
+			     1, 2);
 
 	dmaengine_submit(dma_tx_desc);
 	dma_async_issue_pending(lp->tx_chan);
@@ -965,6 +1002,7 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget)
 					&size, budget);
 
 	if (packets) {
+		netdev_completed_queue(ndev, packets, size);
 		u64_stats_update_begin(&lp->tx_stat_sync);
 		u64_stats_add(&lp->tx_packets, packets);
 		u64_stats_add(&lp->tx_bytes, size);
@@ -982,7 +1020,9 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget)
 		 * cause an immediate interrupt if any TX packets are
 		 * already pending.
 		 */
+		spin_lock_irq(&lp->tx_cr_lock);
 		axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
+		spin_unlock_irq(&lp->tx_cr_lock);
 	}
 	return packets;
 }
@@ -1086,6 +1126,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	if (++new_tail_ptr >= lp->tx_bd_num)
 		new_tail_ptr = 0;
 	WRITE_ONCE(lp->tx_bd_tail, new_tail_ptr);
+	netdev_sent_queue(ndev, skb->len);
 
 	/* Start the transfer */
 	axienet_dma_out_addr(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p);
@@ -1244,11 +1285,25 @@ static int axienet_rx_poll(struct napi_struct *napi, int budget)
 		axienet_dma_out_addr(lp, XAXIDMA_RX_TDESC_OFFSET, tail_p);
 
 	if (packets < budget && napi_complete_done(napi, packets)) {
+		if (READ_ONCE(lp->rx_dim_enabled)) {
+			struct dim_sample sample = {
+				.time = ktime_get(),
+				/* Safe because we are the only writer */
+				.pkt_ctr = u64_stats_read(&lp->rx_packets),
+				.byte_ctr = u64_stats_read(&lp->rx_bytes),
+				.event_ctr = READ_ONCE(lp->rx_irqs),
+			};
+
+			net_dim(&lp->rx_dim, &sample);
+		}
+
 		/* Re-enable RX completion interrupts. This should
 		 * cause an immediate interrupt if any RX packets are
 		 * already pending.
 		 */
+		spin_lock_irq(&lp->rx_cr_lock);
 		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, lp->rx_dma_cr);
+		spin_unlock_irq(&lp->rx_cr_lock);
 	}
 	return packets;
 }
@@ -1286,11 +1341,14 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev)
 		/* Disable further TX completion interrupts and schedule
 		 * NAPI to handle the completions.
 		 */
-		u32 cr = lp->tx_dma_cr;
-
-		cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
 		if (napi_schedule_prep(&lp->napi_tx)) {
+			u32 cr;
+
+			spin_lock(&lp->tx_cr_lock);
+			cr = lp->tx_dma_cr;
+			cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
 			axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+			spin_unlock(&lp->tx_cr_lock);
 			__napi_schedule(&lp->napi_tx);
 		}
 	}
@@ -1331,11 +1389,16 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
 		/* Disable further RX completion interrupts and schedule
 		 * NAPI receive.
 		 */
-		u32 cr = lp->rx_dma_cr;
-
-		cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
+		WRITE_ONCE(lp->rx_irqs, READ_ONCE(lp->rx_irqs) + 1);
 		if (napi_schedule_prep(&lp->napi_rx)) {
+			u32 cr;
+
+			spin_lock(&lp->rx_cr_lock);
+			cr = lp->rx_dma_cr;
+			cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
 			axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+			spin_unlock(&lp->rx_cr_lock);
+
 			__napi_schedule(&lp->napi_rx);
 		}
 	}
@@ -1628,6 +1691,7 @@ err_free_eth_irq:
 	if (lp->eth_irq > 0)
 		free_irq(lp->eth_irq, ndev);
 err_phy:
+	cancel_work_sync(&lp->rx_dim.work);
 	cancel_delayed_work_sync(&lp->stats_work);
 	phylink_stop(lp->phylink);
 	phylink_disconnect_phy(lp->phylink);
@@ -1657,6 +1721,7 @@ static int axienet_stop(struct net_device *ndev)
 		napi_disable(&lp->napi_rx);
 	}
 
+	cancel_work_sync(&lp->rx_dim.work);
 	cancel_delayed_work_sync(&lp->stats_work);
 
 	phylink_stop(lp->phylink);
@@ -1688,6 +1753,7 @@ static int axienet_stop(struct net_device *ndev)
 		dma_release_channel(lp->tx_chan);
 	}
 
+	netdev_reset_queue(ndev);
 	axienet_iow(lp, XAE_IE_OFFSET, 0);
 
 	if (lp->eth_irq > 0)
@@ -2002,6 +2068,87 @@ axienet_ethtools_set_pauseparam(struct net_device *ndev,
 }
 
 /**
+ * axienet_update_coalesce_rx() - Set RX CR
+ * @lp: Device private data
+ * @cr: Value to write to the RX CR
+ * @mask: Bits to set from @cr
+ */
+static void axienet_update_coalesce_rx(struct axienet_local *lp, u32 cr,
+				       u32 mask)
+{
+	spin_lock_irq(&lp->rx_cr_lock);
+	lp->rx_dma_cr &= ~mask;
+	lp->rx_dma_cr |= cr;
+	/* If DMA isn't started, then the settings will be applied the next
+	 * time dma_start() is called.
+	 */
+	if (lp->rx_dma_started) {
+		u32 reg = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
+
+		/* Don't enable IRQs if they are disabled by NAPI */
+		if (reg & XAXIDMA_IRQ_ALL_MASK)
+			cr = lp->rx_dma_cr;
+		else
+			cr = lp->rx_dma_cr & ~XAXIDMA_IRQ_ALL_MASK;
+		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+	}
+	spin_unlock_irq(&lp->rx_cr_lock);
+}
+
+/**
+ * axienet_dim_coalesce_count_rx() - RX coalesce count for DIM
+ * @lp: Device private data
+ */
+static u32 axienet_dim_coalesce_count_rx(struct axienet_local *lp)
+{
+	return min(1 << (lp->rx_dim.profile_ix << 1), 255);
+}
+
+/**
+ * axienet_rx_dim_work() - Adjust RX DIM settings
+ * @work: The work struct
+ */
+static void axienet_rx_dim_work(struct work_struct *work)
+{
+	struct axienet_local *lp =
+		container_of(work, struct axienet_local, rx_dim.work);
+	u32 cr = axienet_calc_cr(lp, axienet_dim_coalesce_count_rx(lp), 0);
+	u32 mask = XAXIDMA_COALESCE_MASK | XAXIDMA_IRQ_IOC_MASK |
+		   XAXIDMA_IRQ_ERROR_MASK;
+
+	axienet_update_coalesce_rx(lp, cr, mask);
+	lp->rx_dim.state = DIM_START_MEASURE;
+}
+
+/**
+ * axienet_update_coalesce_tx() - Set TX CR
+ * @lp: Device private data
+ * @cr: Value to write to the TX CR
+ * @mask: Bits to set from @cr
+ */
+static void axienet_update_coalesce_tx(struct axienet_local *lp, u32 cr,
+				       u32 mask)
+{
+	spin_lock_irq(&lp->tx_cr_lock);
+	lp->tx_dma_cr &= ~mask;
+	lp->tx_dma_cr |= cr;
+	/* If DMA isn't started, then the settings will be applied the next
+	 * time dma_start() is called.
+	 */
+	if (lp->tx_dma_started) {
+		u32 reg = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
+
+		/* Don't enable IRQs if they are disabled by NAPI */
+		if (reg & XAXIDMA_IRQ_ALL_MASK)
+			cr = lp->tx_dma_cr;
+		else
+			cr = lp->tx_dma_cr & ~XAXIDMA_IRQ_ALL_MASK;
+		axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+	}
+	spin_unlock_irq(&lp->tx_cr_lock);
+}
+
+/**
  * axienet_ethtools_get_coalesce - Get DMA interrupt coalescing count.
  * @ndev:	Pointer to net_device structure
  * @ecoalesce:	Pointer to ethtool_coalesce structure
@@ -2021,11 +2168,23 @@ axienet_ethtools_get_coalesce(struct net_device *ndev,
 			      struct netlink_ext_ack *extack)
 {
 	struct axienet_local *lp = netdev_priv(ndev);
-
-	ecoalesce->rx_max_coalesced_frames = lp->coalesce_count_rx;
-	ecoalesce->rx_coalesce_usecs = lp->coalesce_usec_rx;
-	ecoalesce->tx_max_coalesced_frames = lp->coalesce_count_tx;
-	ecoalesce->tx_coalesce_usecs = lp->coalesce_usec_tx;
+	u32 cr;
+
+	ecoalesce->use_adaptive_rx_coalesce = lp->rx_dim_enabled;
+
+	spin_lock_irq(&lp->rx_cr_lock);
+	cr = lp->rx_dma_cr;
+	spin_unlock_irq(&lp->rx_cr_lock);
+	axienet_coalesce_params(lp, cr,
+				&ecoalesce->rx_max_coalesced_frames,
+				&ecoalesce->rx_coalesce_usecs);
+
+	spin_lock_irq(&lp->tx_cr_lock);
+	cr = lp->tx_dma_cr;
+	spin_unlock_irq(&lp->tx_cr_lock);
+	axienet_coalesce_params(lp, cr,
+				&ecoalesce->tx_max_coalesced_frames,
+				&ecoalesce->tx_coalesce_usecs);
 	return 0;
 }
 
@@ -2049,22 +2208,56 @@ axienet_ethtools_set_coalesce(struct net_device *ndev,
 			      struct netlink_ext_ack *extack)
 {
 	struct axienet_local *lp = netdev_priv(ndev);
+	bool new_dim = ecoalesce->use_adaptive_rx_coalesce;
+	bool old_dim = lp->rx_dim_enabled;
+	u32 cr, mask = ~XAXIDMA_CR_RUNSTOP_MASK;
 
-	if (netif_running(ndev)) {
+	if (ecoalesce->rx_max_coalesced_frames > 255 ||
+	    ecoalesce->tx_max_coalesced_frames > 255) {
+		NL_SET_ERR_MSG(extack, "frames must be less than 256");
+		return -EINVAL;
+	}
+
+	if (!ecoalesce->rx_max_coalesced_frames ||
+	    !ecoalesce->tx_max_coalesced_frames) {
+		NL_SET_ERR_MSG(extack, "frames must be non-zero");
+		return -EINVAL;
+	}
+
+	if (((ecoalesce->rx_max_coalesced_frames > 1 || new_dim) &&
+	     !ecoalesce->rx_coalesce_usecs) ||
+	    (ecoalesce->tx_max_coalesced_frames > 1 &&
+	     !ecoalesce->tx_coalesce_usecs)) {
 		NL_SET_ERR_MSG(extack,
-			       "Please stop netif before applying configuration");
-		return -EBUSY;
+			       "usecs must be non-zero when frames is greater than one");
+		return -EINVAL;
+	}
+
+	if (new_dim && !old_dim) {
+		cr = axienet_calc_cr(lp, axienet_dim_coalesce_count_rx(lp),
+				     ecoalesce->rx_coalesce_usecs);
+	} else if (!new_dim) {
+		if (old_dim) {
+			WRITE_ONCE(lp->rx_dim_enabled, false);
+			napi_synchronize(&lp->napi_rx);
+			flush_work(&lp->rx_dim.work);
+		}
+
+		cr = axienet_calc_cr(lp, ecoalesce->rx_max_coalesced_frames,
+				     ecoalesce->rx_coalesce_usecs);
+	} else {
+		/* Dummy value for count just to calculate timer */
+		cr = axienet_calc_cr(lp, 2, ecoalesce->rx_coalesce_usecs);
+		mask = XAXIDMA_DELAY_MASK | XAXIDMA_IRQ_DELAY_MASK;
 	}
 
-	if (ecoalesce->rx_max_coalesced_frames)
-		lp->coalesce_count_rx = ecoalesce->rx_max_coalesced_frames;
-	if (ecoalesce->rx_coalesce_usecs)
-		lp->coalesce_usec_rx = ecoalesce->rx_coalesce_usecs;
-	if (ecoalesce->tx_max_coalesced_frames)
-		lp->coalesce_count_tx = ecoalesce->tx_max_coalesced_frames;
-	if (ecoalesce->tx_coalesce_usecs)
-		lp->coalesce_usec_tx = ecoalesce->tx_coalesce_usecs;
+	axienet_update_coalesce_rx(lp, cr, mask);
+	if (new_dim && !old_dim)
+		WRITE_ONCE(lp->rx_dim_enabled, true);
 
+	cr = axienet_calc_cr(lp, ecoalesce->tx_max_coalesced_frames,
+			     ecoalesce->tx_coalesce_usecs);
+	axienet_update_coalesce_tx(lp, cr, ~XAXIDMA_CR_RUNSTOP_MASK);
 	return 0;
 }
 
@@ -2302,7 +2495,8 @@ axienet_ethtool_get_rmon_stats(struct net_device *dev,
 
 static const struct ethtool_ops axienet_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
-				     ETHTOOL_COALESCE_USECS,
+				     ETHTOOL_COALESCE_USECS |
+				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
 	.get_drvinfo    = axienet_ethtools_get_drvinfo,
 	.get_regs_len   = axienet_ethtools_get_regs_len,
 	.get_regs       = axienet_ethtools_get_regs,
@@ -2331,11 +2525,12 @@ static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs)
 }
 
 static void axienet_pcs_get_state(struct phylink_pcs *pcs,
+				  unsigned int neg_mode,
 				  struct phylink_link_state *state)
 {
 	struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy;
 
-	phylink_mii_c22_pcs_get_state(pcs_phy, state);
+	phylink_mii_c22_pcs_get_state(pcs_phy, neg_mode, state);
 }
 
 static void axienet_pcs_an_restart(struct phylink_pcs *pcs)
@@ -2484,6 +2679,7 @@ static void axienet_dma_err_handler(struct work_struct *work)
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 
 	axienet_dma_stop(lp);
+	netdev_reset_queue(ndev);
 
 	for (i = 0; i < lp->tx_bd_num; i++) {
 		cur_p = &lp->tx_bd_v[i];
@@ -2784,7 +2980,7 @@ static int axienet_probe(struct platform_device *pdev)
 			}
 		}
 		if (!IS_ENABLED(CONFIG_64BIT) && lp->features & XAE_FEATURE_DMA_64BIT) {
-			dev_err(&pdev->dev, "64-bit addressable DMA is not compatible with 32-bit archecture\n");
+			dev_err(&pdev->dev, "64-bit addressable DMA is not compatible with 32-bit architecture\n");
 			ret = -EINVAL;
 			goto cleanup_clk;
 		}
@@ -2843,10 +3039,15 @@ static int axienet_probe(struct platform_device *pdev)
 		axienet_set_mac_address(ndev, NULL);
 	}
 
-	lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
-	lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
-	lp->coalesce_usec_rx = XAXIDMA_DFT_RX_USEC;
-	lp->coalesce_usec_tx = XAXIDMA_DFT_TX_USEC;
+	spin_lock_init(&lp->rx_cr_lock);
+	spin_lock_init(&lp->tx_cr_lock);
+	INIT_WORK(&lp->rx_dim.work, axienet_rx_dim_work);
+	lp->rx_dim_enabled = true;
+	lp->rx_dim.profile_ix = 1;
+	lp->rx_dma_cr = axienet_calc_cr(lp, axienet_dim_coalesce_count_rx(lp),
+					XAXIDMA_DFT_RX_USEC);
+	lp->tx_dma_cr = axienet_calc_cr(lp, XAXIDMA_DFT_TX_THRESHOLD,
+					XAXIDMA_DFT_TX_USEC);
 
 	ret = axienet_mdio_setup(lp);
 	if (ret)
@@ -2876,12 +3077,12 @@ static int axienet_probe(struct platform_device *pdev)
 		}
 		of_node_put(np);
 		lp->pcs.ops = &axienet_pcs_ops;
-		lp->pcs.neg_mode = true;
 		lp->pcs.poll = true;
 	}
 
 	lp->phylink_config.dev = &ndev->dev;
 	lp->phylink_config.type = PHYLINK_NETDEV;
+	lp->phylink_config.mac_managed_pm = true;
 	lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE |
 		MAC_10FD | MAC_100FD | MAC_1000FD;
 
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index a2ab1c150822..e1e7f65553e7 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -394,16 +394,20 @@ static void ixp_tx_timestamp(struct port *port, struct sk_buff *skb)
 	__raw_writel(TX_SNAPSHOT_LOCKED, &regs->channel[ch].ch_event);
 }
 
-static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
+static int ixp4xx_hwtstamp_set(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *cfg,
+			       struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config cfg;
 	struct ixp46x_ts_regs *regs;
 	struct port *port = netdev_priv(netdev);
 	int ret;
 	int ch;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
+	if (!cpu_is_ixp46x())
+		return -EOPNOTSUPP;
+
+	if (!netif_running(netdev))
+		return -EINVAL;
 
 	ret = ixp46x_ptp_find(&port->timesync_regs, &port->phc_index);
 	if (ret)
@@ -412,10 +416,10 @@ static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 	ch = PORT2CHANNEL(port);
 	regs = port->timesync_regs;
 
-	if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON)
+	if (cfg->tx_type != HWTSTAMP_TX_OFF && cfg->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		port->hwts_rx_en = 0;
 		break;
@@ -431,39 +435,45 @@ static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	port->hwts_tx_en = cfg.tx_type == HWTSTAMP_TX_ON;
+	port->hwts_tx_en = cfg->tx_type == HWTSTAMP_TX_ON;
 
 	/* Clear out any old time stamps. */
 	__raw_writel(TX_SNAPSHOT_LOCKED | RX_SNAPSHOT_LOCKED,
 		     &regs->channel[ch].ch_event);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
-static int hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
+static int ixp4xx_hwtstamp_get(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *cfg)
 {
-	struct hwtstamp_config cfg;
 	struct port *port = netdev_priv(netdev);
 
-	cfg.flags = 0;
-	cfg.tx_type = port->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	if (!cpu_is_ixp46x())
+		return -EOPNOTSUPP;
+
+	if (!netif_running(netdev))
+		return -EINVAL;
+
+	cfg->flags = 0;
+	cfg->tx_type = port->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
 
 	switch (port->hwts_rx_en) {
 	case 0:
-		cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+		cfg->rx_filter = HWTSTAMP_FILTER_NONE;
 		break;
 	case PTP_SLAVE_MODE:
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
 		break;
 	case PTP_MASTER_MODE:
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		return -ERANGE;
 	}
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static int ixp4xx_mdio_cmd(struct mii_bus *bus, int phy_id, int location,
@@ -985,21 +995,6 @@ static void eth_set_mcast_list(struct net_device *dev)
 }
 
 
-static int eth_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
-{
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	if (cpu_is_ixp46x()) {
-		if (cmd == SIOCSHWTSTAMP)
-			return hwtstamp_set(dev, req);
-		if (cmd == SIOCGHWTSTAMP)
-			return hwtstamp_get(dev, req);
-	}
-
-	return phy_mii_ioctl(dev->phydev, req, cmd);
-}
-
 /* ethtool support */
 
 static void ixp4xx_get_drvinfo(struct net_device *dev,
@@ -1433,9 +1428,11 @@ static const struct net_device_ops ixp4xx_netdev_ops = {
 	.ndo_change_mtu = ixp4xx_eth_change_mtu,
 	.ndo_start_xmit = eth_xmit,
 	.ndo_set_rx_mode = eth_set_mcast_list,
-	.ndo_eth_ioctl = eth_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
 	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
+	.ndo_hwtstamp_get = ixp4xx_hwtstamp_get,
+	.ndo_hwtstamp_set = ixp4xx_hwtstamp_set,
 };
 
 static struct eth_plat_info *ixp4xx_of_get_platdata(struct device *dev)